nohup: ignoring input
10/20/2021 21:47:33 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: False
10/20/2021 21:47:33 - INFO - __main__ - Training/evaluation parameters TrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_find_unused_parameters=None,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_steps=None,
evaluation_strategy=IntervalStrategy.NO,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
gradient_accumulation_steps=1,
greater_is_better=None,
group_by_length=False,
ignore_data_skip=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=3e-05,
length_column_name=length,
load_best_model_at_end=False,
local_rank=-1,
log_level=-1,
log_level_replica=-1,
log_on_each_node=True,
logging_dir=bert-based-uncased-squad/runs/Oct20_21-47-33_rtxws2,
logging_first_step=False,
logging_steps=1,
logging_strategy=IntervalStrategy.STEPS,
lr_scheduler_type=SchedulerType.LINEAR,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
no_cuda=False,
num_train_epochs=2.0,
output_dir=bert-based-uncased-squad,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=16,
per_device_train_batch_size=16,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=bert-based-uncased-squad,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=bert-based-uncased-squad,
save_on_each_node=False,
save_steps=10000,
save_strategy=IntervalStrategy.STEPS,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_legacy_prediction_loop=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
10/20/2021 21:47:34 - INFO - datasets.load - Found main folder for dataset https://raw.githubusercontent.com/huggingface/datasets/1.12.1/datasets/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad
10/20/2021 21:47:34 - INFO - datasets.load - Found specific version folder for dataset https://raw.githubusercontent.com/huggingface/datasets/1.12.1/datasets/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453
10/20/2021 21:47:34 - INFO - datasets.load - Found script file from https://raw.githubusercontent.com/huggingface/datasets/1.12.1/datasets/squad/squad.py to /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453/squad.py
10/20/2021 21:47:34 - INFO - datasets.load - Found dataset infos file from https://raw.githubusercontent.com/huggingface/datasets/1.12.1/datasets/squad/dataset_infos.json to /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453/dataset_infos.json
10/20/2021 21:47:34 - INFO - datasets.load - Found metadata file for dataset https://raw.githubusercontent.com/huggingface/datasets/1.12.1/datasets/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453/squad.json
10/20/2021 21:47:34 - INFO - datasets.builder - No config specified, defaulting to first: squad/plain_text
10/20/2021 21:47:34 - INFO - datasets.info - Loading Dataset Infos from /home/vchua/.cache/huggingface/modules/datasets_modules/datasets/squad/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453
10/20/2021 21:47:34 - INFO - datasets.builder - Overwrite dataset info from restored data version.
10/20/2021 21:47:34 - INFO - datasets.info - Loading Dataset info from /home/vchua/.cache/huggingface/datasets/squad/plain_text/1.0.0/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453
10/20/2021 21:47:34 - WARNING - datasets.builder - Reusing dataset squad (/home/vchua/.cache/huggingface/datasets/squad/plain_text/1.0.0/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453)
10/20/2021 21:47:34 - INFO - datasets.info - Loading Dataset info from /home/vchua/.cache/huggingface/datasets/squad/plain_text/1.0.0/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453

  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 159.55it/s]
[INFO|configuration_utils.py:561] 2021-10-20 21:47:35,190 >> loading configuration file https://huggingface.co/bert-base-uncased/resolve/main/config.json from cache at /home/vchua/.cache/huggingface/transformers/3c61d016573b14f7f008c02c4e51a366c67ab274726fe2910691e2a761acf43e.37395cee442ab11005bcd270f3c34464dc1704b715b5d7d52b1a461abe3b9e4e
[INFO|configuration_utils.py:598] 2021-10-20 21:47:35,191 >> Model config BertConfig {
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.10.3",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}

[INFO|configuration_utils.py:561] 2021-10-20 21:47:35,866 >> loading configuration file https://huggingface.co/bert-base-uncased/resolve/main/config.json from cache at /home/vchua/.cache/huggingface/transformers/3c61d016573b14f7f008c02c4e51a366c67ab274726fe2910691e2a761acf43e.37395cee442ab11005bcd270f3c34464dc1704b715b5d7d52b1a461abe3b9e4e
[INFO|configuration_utils.py:598] 2021-10-20 21:47:35,867 >> Model config BertConfig {
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.10.3",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}

[INFO|tokenization_utils_base.py:1739] 2021-10-20 21:47:37,899 >> loading file https://huggingface.co/bert-base-uncased/resolve/main/vocab.txt from cache at /home/vchua/.cache/huggingface/transformers/45c3f7a79a80e1cf0a489e5c62b43f173c15db47864303a55d623bb3c96f72a5.d789d64ebfe299b0e416afc4a169632f903f693095b4629a7ea271d5a0cf2c99
[INFO|tokenization_utils_base.py:1739] 2021-10-20 21:47:37,900 >> loading file https://huggingface.co/bert-base-uncased/resolve/main/tokenizer.json from cache at /home/vchua/.cache/huggingface/transformers/534479488c54aeaf9c3406f647aa2ec13648c06771ffe269edabebd4c412da1d.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4
[INFO|tokenization_utils_base.py:1739] 2021-10-20 21:47:37,900 >> loading file https://huggingface.co/bert-base-uncased/resolve/main/added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:1739] 2021-10-20 21:47:37,900 >> loading file https://huggingface.co/bert-base-uncased/resolve/main/special_tokens_map.json from cache at None
[INFO|tokenization_utils_base.py:1739] 2021-10-20 21:47:37,900 >> loading file https://huggingface.co/bert-base-uncased/resolve/main/tokenizer_config.json from cache at /home/vchua/.cache/huggingface/transformers/c1d7f0a763fb63861cc08553866f1fc3e5a6f4f07621be277452d26d71303b7e.20430bd8e10ef77a7d2977accefe796051e01bc2fc4aa146bc862997a1a15e79
[INFO|configuration_utils.py:561] 2021-10-20 21:47:38,239 >> loading configuration file https://huggingface.co/bert-base-uncased/resolve/main/config.json from cache at /home/vchua/.cache/huggingface/transformers/3c61d016573b14f7f008c02c4e51a366c67ab274726fe2910691e2a761acf43e.37395cee442ab11005bcd270f3c34464dc1704b715b5d7d52b1a461abe3b9e4e
[INFO|configuration_utils.py:598] 2021-10-20 21:47:38,240 >> Model config BertConfig {
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.10.3",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}

[INFO|modeling_utils.py:1279] 2021-10-20 21:47:38,667 >> loading weights file https://huggingface.co/bert-base-uncased/resolve/main/pytorch_model.bin from cache at /home/vchua/.cache/huggingface/transformers/a8041bf617d7f94ea26d15e218abd04afc2004805632abc0ed2066aa16d50d04.faf6ea826ae9c5867d12b22257f9877e6b8367890837bd60f7c54a29633f7f2f
[WARNING|modeling_utils.py:1515] 2021-10-20 21:47:39,732 >> Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForQuestionAnswering: ['cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertForQuestionAnswering from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForQuestionAnswering from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
[WARNING|modeling_utils.py:1526] 2021-10-20 21:47:39,732 >> Some weights of BertForQuestionAnswering were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['qa_outputs.weight', 'qa_outputs.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Running tokenizer on train dataset:   0%|          | 0/88 [00:00<?, ?ba/s]10/20/2021 21:47:39 - INFO - datasets.arrow_dataset - Caching processed dataset at /home/vchua/.cache/huggingface/datasets/squad/plain_text/1.0.0/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453/cache-9f07b7d306af7270.arrow

Running tokenizer on train dataset:   1%|          | 1/88 [00:00<00:26,  3.25ba/s]
Running tokenizer on train dataset:   2%|▏         | 2/88 [00:00<00:20,  4.13ba/s]
Running tokenizer on train dataset:   3%|▎         | 3/88 [00:00<00:21,  3.96ba/s]
Running tokenizer on train dataset:   5%|▍         | 4/88 [00:00<00:19,  4.41ba/s]
Running tokenizer on train dataset:   6%|▌         | 5/88 [00:01<00:17,  4.67ba/s]
Running tokenizer on train dataset:   7%|▋         | 6/88 [00:01<00:18,  4.40ba/s]
Running tokenizer on train dataset:   8%|▊         | 7/88 [00:01<00:17,  4.65ba/s]
Running tokenizer on train dataset:   9%|▉         | 8/88 [00:01<00:16,  4.90ba/s]
Running tokenizer on train dataset:  10%|█         | 9/88 [00:02<00:17,  4.49ba/s]
Running tokenizer on train dataset:  11%|█▏        | 10/88 [00:02<00:16,  4.74ba/s]
Running tokenizer on train dataset:  12%|█▎        | 11/88 [00:02<00:15,  4.94ba/s]
Running tokenizer on train dataset:  14%|█▎        | 12/88 [00:02<00:16,  4.63ba/s]
Running tokenizer on train dataset:  15%|█▍        | 13/88 [00:02<00:15,  4.83ba/s]
Running tokenizer on train dataset:  16%|█▌        | 14/88 [00:03<00:14,  5.01ba/s]
Running tokenizer on train dataset:  17%|█▋        | 15/88 [00:03<00:15,  4.72ba/s]
Running tokenizer on train dataset:  18%|█▊        | 16/88 [00:03<00:14,  4.88ba/s]
Running tokenizer on train dataset:  19%|█▉        | 17/88 [00:03<00:14,  5.04ba/s]
Running tokenizer on train dataset:  20%|██        | 18/88 [00:03<00:14,  4.69ba/s]
Running tokenizer on train dataset:  22%|██▏       | 19/88 [00:04<00:14,  4.90ba/s]
Running tokenizer on train dataset:  23%|██▎       | 20/88 [00:04<00:14,  4.83ba/s]
Running tokenizer on train dataset:  24%|██▍       | 21/88 [00:04<00:14,  4.63ba/s]
Running tokenizer on train dataset:  25%|██▌       | 22/88 [00:04<00:13,  4.84ba/s]
Running tokenizer on train dataset:  26%|██▌       | 23/88 [00:04<00:12,  5.03ba/s]
Running tokenizer on train dataset:  27%|██▋       | 24/88 [00:05<00:13,  4.73ba/s]
Running tokenizer on train dataset:  28%|██▊       | 25/88 [00:05<00:12,  4.93ba/s]
Running tokenizer on train dataset:  30%|██▉       | 26/88 [00:05<00:13,  4.60ba/s]
Running tokenizer on train dataset:  31%|███       | 27/88 [00:05<00:12,  4.71ba/s]
Running tokenizer on train dataset:  32%|███▏      | 28/88 [00:05<00:12,  4.78ba/s]
Running tokenizer on train dataset:  33%|███▎      | 29/88 [00:06<00:13,  4.44ba/s]
Running tokenizer on train dataset:  34%|███▍      | 30/88 [00:06<00:12,  4.57ba/s]
Running tokenizer on train dataset:  35%|███▌      | 31/88 [00:06<00:12,  4.66ba/s]
Running tokenizer on train dataset:  36%|███▋      | 32/88 [00:06<00:12,  4.35ba/s]
Running tokenizer on train dataset:  38%|███▊      | 33/88 [00:07<00:12,  4.55ba/s]
Running tokenizer on train dataset:  39%|███▊      | 34/88 [00:07<00:11,  4.70ba/s]
Running tokenizer on train dataset:  40%|███▉      | 35/88 [00:07<00:12,  4.40ba/s]
Running tokenizer on train dataset:  41%|████      | 36/88 [00:07<00:11,  4.54ba/s]
Running tokenizer on train dataset:  42%|████▏     | 37/88 [00:07<00:11,  4.61ba/s]
Running tokenizer on train dataset:  43%|████▎     | 38/88 [00:08<00:11,  4.37ba/s]
Running tokenizer on train dataset:  44%|████▍     | 39/88 [00:08<00:10,  4.54ba/s]
Running tokenizer on train dataset:  45%|████▌     | 40/88 [00:08<00:10,  4.65ba/s]
Running tokenizer on train dataset:  47%|████▋     | 41/88 [00:08<00:10,  4.42ba/s]
Running tokenizer on train dataset:  48%|████▊     | 42/88 [00:09<00:10,  4.54ba/s]
Running tokenizer on train dataset:  49%|████▉     | 43/88 [00:09<00:09,  4.70ba/s]
Running tokenizer on train dataset:  50%|█████     | 44/88 [00:09<00:09,  4.48ba/s]
Running tokenizer on train dataset:  51%|█████     | 45/88 [00:09<00:09,  4.65ba/s]
Running tokenizer on train dataset:  52%|█████▏    | 46/88 [00:09<00:08,  4.74ba/s]
Running tokenizer on train dataset:  53%|█████▎    | 47/88 [00:10<00:09,  4.51ba/s]
Running tokenizer on train dataset:  55%|█████▍    | 48/88 [00:10<00:08,  4.68ba/s]
Running tokenizer on train dataset:  56%|█████▌    | 49/88 [00:10<00:08,  4.36ba/s]
Running tokenizer on train dataset:  57%|█████▋    | 50/88 [00:10<00:08,  4.54ba/s]
Running tokenizer on train dataset:  58%|█████▊    | 51/88 [00:11<00:07,  4.67ba/s]
Running tokenizer on train dataset:  59%|█████▉    | 52/88 [00:11<00:08,  4.37ba/s]
Running tokenizer on train dataset:  60%|██████    | 53/88 [00:11<00:07,  4.52ba/s]
Running tokenizer on train dataset:  61%|██████▏   | 54/88 [00:11<00:07,  4.67ba/s]
Running tokenizer on train dataset:  62%|██████▎   | 55/88 [00:11<00:07,  4.36ba/s]
Running tokenizer on train dataset:  64%|██████▎   | 56/88 [00:12<00:07,  4.54ba/s]
Running tokenizer on train dataset:  65%|██████▍   | 57/88 [00:12<00:06,  4.65ba/s]
Running tokenizer on train dataset:  66%|██████▌   | 58/88 [00:12<00:06,  4.36ba/s]
Running tokenizer on train dataset:  67%|██████▋   | 59/88 [00:12<00:06,  4.55ba/s]
Running tokenizer on train dataset:  68%|██████▊   | 60/88 [00:13<00:05,  4.73ba/s]
Running tokenizer on train dataset:  69%|██████▉   | 61/88 [00:13<00:06,  4.44ba/s]
Running tokenizer on train dataset:  70%|███████   | 62/88 [00:13<00:05,  4.62ba/s]
Running tokenizer on train dataset:  72%|███████▏  | 63/88 [00:13<00:05,  4.76ba/s]
Running tokenizer on train dataset:  73%|███████▎  | 64/88 [00:13<00:05,  4.49ba/s]
Running tokenizer on train dataset:  74%|███████▍  | 65/88 [00:14<00:05,  4.58ba/s]
Running tokenizer on train dataset:  75%|███████▌  | 66/88 [00:14<00:04,  4.66ba/s]
Running tokenizer on train dataset:  76%|███████▌  | 67/88 [00:14<00:04,  4.43ba/s]
Running tokenizer on train dataset:  77%|███████▋  | 68/88 [00:14<00:04,  4.63ba/s]
Running tokenizer on train dataset:  78%|███████▊  | 69/88 [00:14<00:04,  4.73ba/s]
Running tokenizer on train dataset:  80%|███████▉  | 70/88 [00:15<00:04,  4.41ba/s]
Running tokenizer on train dataset:  81%|████████  | 71/88 [00:15<00:03,  4.54ba/s]
Running tokenizer on train dataset:  82%|████████▏ | 72/88 [00:15<00:03,  4.25ba/s]
Running tokenizer on train dataset:  83%|████████▎ | 73/88 [00:15<00:03,  4.46ba/s]
Running tokenizer on train dataset:  84%|████████▍ | 74/88 [00:16<00:03,  4.63ba/s]
Running tokenizer on train dataset:  85%|████████▌ | 75/88 [00:16<00:02,  4.36ba/s]
Running tokenizer on train dataset:  86%|████████▋ | 76/88 [00:16<00:02,  4.50ba/s]
Running tokenizer on train dataset:  88%|████████▊ | 77/88 [00:16<00:02,  4.68ba/s]
Running tokenizer on train dataset:  89%|████████▊ | 78/88 [00:17<00:02,  4.39ba/s]
Running tokenizer on train dataset:  90%|████████▉ | 79/88 [00:17<00:01,  4.56ba/s]
Running tokenizer on train dataset:  91%|█████████ | 80/88 [00:17<00:01,  4.73ba/s]
Running tokenizer on train dataset:  92%|█████████▏| 81/88 [00:17<00:01,  4.45ba/s]
Running tokenizer on train dataset:  93%|█████████▎| 82/88 [00:17<00:01,  4.54ba/s]
Running tokenizer on train dataset:  94%|█████████▍| 83/88 [00:18<00:01,  4.60ba/s]
Running tokenizer on train dataset:  95%|█████████▌| 84/88 [00:18<00:00,  4.36ba/s]
Running tokenizer on train dataset:  97%|█████████▋| 85/88 [00:18<00:00,  4.56ba/s]
Running tokenizer on train dataset:  98%|█████████▊| 86/88 [00:18<00:00,  4.69ba/s]
Running tokenizer on train dataset:  99%|█████████▉| 87/88 [00:18<00:00,  4.45ba/s]
Running tokenizer on train dataset: 100%|██████████| 88/88 [00:19<00:00,  5.14ba/s]
Running tokenizer on train dataset: 100%|██████████| 88/88 [00:19<00:00,  4.60ba/s]

Running tokenizer on validation dataset:   0%|          | 0/11 [00:00<?, ?ba/s]10/20/2021 21:47:59 - INFO - datasets.arrow_dataset - Caching processed dataset at /home/vchua/.cache/huggingface/datasets/squad/plain_text/1.0.0/d6ec3ceb99ca480ce37cdd35555d6cb2511d223b9150cce08a837ef62ffea453/cache-d7ee7b2f71da2c8a.arrow

Running tokenizer on validation dataset:   9%|▉         | 1/11 [00:00<00:08,  1.16ba/s]
Running tokenizer on validation dataset:  18%|█▊        | 2/11 [00:01<00:07,  1.22ba/s]
Running tokenizer on validation dataset:  27%|██▋       | 3/11 [00:02<00:06,  1.28ba/s]
Running tokenizer on validation dataset:  36%|███▋      | 4/11 [00:03<00:05,  1.22ba/s]
Running tokenizer on validation dataset:  45%|████▌     | 5/11 [00:04<00:05,  1.10ba/s]
Running tokenizer on validation dataset:  55%|█████▍    | 6/11 [00:05<00:04,  1.11ba/s]
Running tokenizer on validation dataset:  64%|██████▎   | 7/11 [00:06<00:03,  1.11ba/s]
Running tokenizer on validation dataset:  73%|███████▎  | 8/11 [00:06<00:02,  1.13ba/s]
Running tokenizer on validation dataset:  82%|████████▏ | 9/11 [00:07<00:01,  1.15ba/s]
Running tokenizer on validation dataset:  91%|█████████ | 10/11 [00:08<00:00,  1.17ba/s]
Running tokenizer on validation dataset: 100%|██████████| 11/11 [00:09<00:00,  1.35ba/s]
Running tokenizer on validation dataset: 100%|██████████| 11/11 [00:09<00:00,  1.21ba/s]10/20/2021 21:48:09 - INFO - datasets.load - Found main folder for metric https://raw.githubusercontent.com/huggingface/datasets/1.12.1/metrics/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/metrics/squad
10/20/2021 21:48:09 - INFO - datasets.load - Found specific version folder for metric https://raw.githubusercontent.com/huggingface/datasets/1.12.1/metrics/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/metrics/squad/513bf9facd7f12b0871a3d74c6999c866ce28196c9cdb151dcf934848655d77e
10/20/2021 21:48:09 - INFO - datasets.load - Found script file from https://raw.githubusercontent.com/huggingface/datasets/1.12.1/metrics/squad/squad.py to /home/vchua/.cache/huggingface/modules/datasets_modules/metrics/squad/513bf9facd7f12b0871a3d74c6999c866ce28196c9cdb151dcf934848655d77e/squad.py
10/20/2021 21:48:09 - INFO - datasets.load - Couldn't find dataset infos file at https://raw.githubusercontent.com/huggingface/datasets/1.12.1/metrics/squad/dataset_infos.json
10/20/2021 21:48:09 - INFO - datasets.load - Found metadata file for metric https://raw.githubusercontent.com/huggingface/datasets/1.12.1/metrics/squad/squad.py at /home/vchua/.cache/huggingface/modules/datasets_modules/metrics/squad/513bf9facd7f12b0871a3d74c6999c866ce28196c9cdb151dcf934848655d77e/squad.json
10/20/2021 21:48:09 - INFO - datasets.load - Found local import file from /home/vchua/.cache/huggingface/datasets/downloads/2bc5dacc6567632926dc9fb08781d6f7eb1bbb54717f602009e92ecb6b53761b.6f69c3ff9e10aa1cbdc6e91d27e158ea86a785f54a36a9e964ef8b3b78cf3cd6.py at /home/vchua/.cache/huggingface/modules/datasets_modules/metrics/squad/513bf9facd7f12b0871a3d74c6999c866ce28196c9cdb151dcf934848655d77e/evaluate.py

[INFO|trainer.py:1168] 2021-10-20 21:48:15,912 >> ***** Running training *****
[INFO|trainer.py:1169] 2021-10-20 21:48:15,912 >>   Num examples = 88524
[INFO|trainer.py:1170] 2021-10-20 21:48:15,912 >>   Num Epochs = 2
[INFO|trainer.py:1171] 2021-10-20 21:48:15,912 >>   Instantaneous batch size per device = 16
[INFO|trainer.py:1172] 2021-10-20 21:48:15,912 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
[INFO|trainer.py:1173] 2021-10-20 21:48:15,912 >>   Gradient Accumulation steps = 1
[INFO|trainer.py:1174] 2021-10-20 21:48:15,912 >>   Total optimization steps = 11066

  0%|          | 0/11066 [00:00<?, ?it/s]
  0%|          | 1/11066 [00:00<56:43,  3.25it/s]
                                                 

  0%|          | 1/11066 [00:00<56:43,  3.25it/s]
  0%|          | 2/11066 [00:00<47:15,  3.90it/s]
                                                 

  0%|          | 2/11066 [00:00<47:15,  3.90it/s]
  0%|          | 3/11066 [00:00<44:19,  4.16it/s]
                                                 

  0%|          | 3/11066 [00:00<44:19,  4.16it/s]
  0%|          | 4/11066 [00:00<42:46,  4.31it/s]
                                                 

  0%|          | 4/11066 [00:00<42:46,  4.31it/s]
  0%|          | 5/11066 [00:01<41:59,  4.39it/s]
                                                 

  0%|          | 5/11066 [00:01<41:59,  4.39it/s]
  0%|          | 6/11066 [00:01<41:03,  4.49it/s]
                                                 

  0%|          | 6/11066 [00:01<41:03,  4.49it/s]
  0%|          | 7/11066 [00:01<40:50,  4.51it/s]
                                                 

  0%|          | 7/11066 [00:01<40:50,  4.51it/s]
  0%|          | 8/11066 [00:01<40:38,  4.53it/s]
                                                 

  0%|          | 8/11066 [00:01<40:38,  4.53it/s]
  0%|          | 9/11066 [00:02<40:46,  4.52it/s]
                                                 

  0%|          | 9/11066 [00:02<40:46,  4.52it/s]
  0%|          | 10/11066 [00:02<40:41,  4.53it/s]
                                                  

  0%|          | 10/11066 [00:02<40:41,  4.53it/s]
  0%|          | 11/11066 [00:02<41:04,  4.48it/s]
                                                  

  0%|          | 11/11066 [00:02<41:04,  4.48it/s]
  0%|          | 12/11066 [00:02<40:52,  4.51it/s]
                                                  

  0%|          | 12/11066 [00:02<40:52,  4.51it/s]
  0%|          | 13/11066 [00:02<40:40,  4.53it/s]
                                                  

  0%|          | 13/11066 [00:02<40:40,  4.53it/s]
  0%|          | 14/11066 [00:03<40:47,  4.52it/s]
                                                  

  0%|          | 14/11066 [00:03<40:47,  4.52it/s]
  0%|          | 15/11066 [00:03<40:43,  4.52it/s]
                                                  

  0%|          | 15/11066 [00:03<40:43,  4.52it/s]
  0%|          | 16/11066 [00:03<40:27,  4.55it/s]
                                                  

  0%|          | 16/11066 [00:03<40:27,  4.55it/s]
  0%|          | 17/11066 [00:03<40:22,  4.56it/s]
                                                  

  0%|          | 17/11066 [00:03<40:22,  4.56it/s]
  0%|          | 18/11066 [00:04<39:44,  4.63it/s]
                                                  

  0%|          | 18/11066 [00:04<39:44,  4.63it/s]
  0%|          | 19/11066 [00:04<39:48,  4.62it/s]
                                                  

  0%|          | 19/11066 [00:04<39:48,  4.62it/s]
  0%|          | 20/11066 [00:04<39:47,  4.63it/s]
                                                  

  0%|          | 20/11066 [00:04<39:47,  4.63it/s]
  0%|          | 21/11066 [00:04<39:31,  4.66it/s]
                                                  

  0%|          | 21/11066 [00:04<39:31,  4.66it/s]
  0%|          | 22/11066 [00:04<39:42,  4.64it/s]
                                                  

  0%|          | 22/11066 [00:04<39:42,  4.64it/s]
  0%|          | 23/11066 [00:05<39:34,  4.65it/s]
                                                  

  0%|          | 23/11066 [00:05<39:34,  4.65it/s]
  0%|          | 24/11066 [00:05<39:50,  4.62it/s]
                                                  

  0%|          | 24/11066 [00:05<39:50,  4.62it/s]
  0%|          | 25/11066 [00:05<39:24,  4.67it/s]
                                                  

  0%|          | 25/11066 [00:05<39:24,  4.67it/s]
  0%|          | 26/11066 [00:05<39:33,  4.65it/s]
                                                  

  0%|          | 26/11066 [00:05<39:33,  4.65it/s]
  0%|          | 27/11066 [00:05<39:09,  4.70it/s]
                                                  

  0%|          | 27/11066 [00:05<39:09,  4.70it/s]
  0%|          | 28/11066 [00:06<39:21,  4.67it/s]
                                                  

  0%|          | 28/11066 [00:06<39:21,  4.67it/s]
  0%|          | 29/11066 [00:06<39:37,  4.64it/s]
                                                  

  0%|          | 29/11066 [00:06<39:37,  4.64it/s]
  0%|          | 30/11066 [00:06<39:41,  4.63it/s]
                                                  

  0%|          | 30/11066 [00:06<39:41,  4.63it/s]
  0%|          | 31/11066 [00:06<39:51,  4.61it/s]
                                                  

  0%|          | 31/11066 [00:06<39:51,  4.61it/s]
  0%|          | 32/11066 [00:07<39:59,  4.60it/s]
                                                  

  0%|          | 32/11066 [00:07<39:59,  4.60it/s]
  0%|          | 33/11066 [00:07<39:58,  4.60it/s]
                                                  

  0%|          | 33/11066 [00:07<39:58,  4.60it/s]
  0%|          | 34/11066 [00:07<39:54,  4.61it/s]
                                                  

  0%|          | 34/11066 [00:07<39:54,  4.61it/s]
  0%|          | 35/11066 [00:07<39:55,  4.60it/s]
                                                  

  0%|          | 35/11066 [00:07<39:55,  4.60it/s]
  0%|          | 36/11066 [00:07<40:05,  4.58it/s]
                                                  

  0%|          | 36/11066 [00:07<40:05,  4.58it/s]
  0%|          | 37/11066 [00:08<39:52,  4.61it/s]
                                                  

  0%|          | 37/11066 [00:08<39:52,  4.61it/s]
  0%|          | 38/11066 [00:08<40:01,  4.59it/s]
                                                  

  0%|          | 38/11066 [00:08<40:01,  4.59it/s]
  0%|          | 39/11066 [00:08<39:39,  4.64it/s]
                                                  

  0%|          | 39/11066 [00:08<39:39,  4.64it/s]
  0%|          | 40/11066 [00:08<39:33,  4.65it/s]
                                                  

  0%|          | 40/11066 [00:08<39:33,  4.65it/s]
  0%|          | 41/11066 [00:09<39:45,  4.62it/s]
                                                  

  0%|          | 41/11066 [00:09<39:45,  4.62it/s]
  0%|          | 42/11066 [00:09<39:57,  4.60it/s]
                                                  

  0%|          | 42/11066 [00:09<39:57,  4.60it/s]
  0%|          | 43/11066 [00:09<40:03,  4.59it/s]
                                                  

  0%|          | 43/11066 [00:09<40:03,  4.59it/s]
  0%|          | 44/11066 [00:09<39:44,  4.62it/s]
                                                  

  0%|          | 44/11066 [00:09<39:44,  4.62it/s]
  0%|          | 45/11066 [00:09<39:47,  4.62it/s]
                                                  

  0%|          | 45/11066 [00:09<39:47,  4.62it/s]
  0%|          | 46/11066 [00:10<39:25,  4.66it/s]
                                                  

  0%|          | 46/11066 [00:10<39:25,  4.66it/s]
  0%|          | 47/11066 [00:10<39:43,  4.62it/s]
                                                  

  0%|          | 47/11066 [00:10<39:43,  4.62it/s]
  0%|          | 48/11066 [00:10<39:58,  4.59it/s]
                                                  

  0%|          | 48/11066 [00:10<39:58,  4.59it/s]
  0%|          | 49/11066 [00:10<40:05,  4.58it/s]
                                                  

  0%|          | 49/11066 [00:10<40:05,  4.58it/s]
  0%|          | 50/11066 [00:10<40:01,  4.59it/s]
                                                  

  0%|          | 50/11066 [00:10<40:01,  4.59it/s]
  0%|          | 51/11066 [00:11<39:58,  4.59it/s]
                                                  

  0%|          | 51/11066 [00:11<39:58,  4.59it/s]
  0%|          | 52/11066 [00:11<39:41,  4.62it/s]
                                                  

  0%|          | 52/11066 [00:11<39:41,  4.62it/s]
  0%|          | 53/11066 [00:11<39:44,  4.62it/s]
                                                  

  0%|          | 53/11066 [00:11<39:44,  4.62it/s]
  0%|          | 54/11066 [00:11<39:53,  4.60it/s]
                                                  

  0%|          | 54/11066 [00:11<39:53,  4.60it/s]
  0%|          | 55/11066 [00:12<40:03,  4.58it/s]
                                                  

  0%|          | 55/11066 [00:12<40:03,  4.58it/s]
  1%|          | 56/11066 [00:12<39:35,  4.63it/s]
                                                  

  1%|          | 56/11066 [00:12<39:35,  4.63it/s]
  1%|          | 57/11066 [00:12<39:42,  4.62it/s]
                                                  

  1%|          | 57/11066 [00:12<39:42,  4.62it/s]
  1%|          | 58/11066 [00:12<39:48,  4.61it/s]
                                                  

  1%|          | 58/11066 [00:12<39:48,  4.61it/s]
  1%|          | 59/11066 [00:12<40:01,  4.58it/s]
                                                  

  1%|          | 59/11066 [00:12<40:01,  4.58it/s]
  1%|          | 60/11066 [00:13<40:08,  4.57it/s]
                                                  

  1%|          | 60/11066 [00:13<40:08,  4.57it/s]
  1%|          | 61/11066 [00:13<39:55,  4.59it/s]
                                                  

  1%|          | 61/11066 [00:13<39:55,  4.59it/s]
  1%|          | 62/11066 [00:13<40:05,  4.58it/s]
                                                  

  1%|          | 62/11066 [00:13<40:05,  4.58it/s]
  1%|          | 63/11066 [00:13<39:58,  4.59it/s]
                                                  

  1%|          | 63/11066 [00:13<39:58,  4.59it/s]
  1%|          | 64/11066 [00:14<40:01,  4.58it/s]
                                                  

  1%|          | 64/11066 [00:14<40:01,  4.58it/s]
  1%|          | 65/11066 [00:14<39:57,  4.59it/s]
                                                  

  1%|          | 65/11066 [00:14<39:57,  4.59it/s]
  1%|          | 66/11066 [00:14<39:58,  4.59it/s]
                                                  

  1%|          | 66/11066 [00:14<39:58,  4.59it/s]
  1%|          | 67/11066 [00:14<40:02,  4.58it/s]
                                                  

  1%|          | 67/11066 [00:14<40:02,  4.58it/s]
  1%|          | 68/11066 [00:14<40:12,  4.56it/s]
                                                  

  1%|          | 68/11066 [00:14<40:12,  4.56it/s]
  1%|          | 69/11066 [00:15<40:18,  4.55it/s]
                                                  

  1%|          | 69/11066 [00:15<40:18,  4.55it/s]
  1%|          | 70/11066 [00:15<40:19,  4.55it/s]
                                                  

  1%|          | 70/11066 [00:15<40:19,  4.55it/s]
  1%|          | 71/11066 [00:15<40:17,  4.55it/s]
                                                  

  1%|          | 71/11066 [00:15<40:17,  4.55it/s]
  1%|          | 72/11066 [00:15<40:09,  4.56it/s]
                                                  

  1%|          | 72/11066 [00:15<40:09,  4.56it/s]
  1%|          | 73/11066 [00:15<39:40,  4.62it/s]
                                                  

  1%|          | 73/11066 [00:15<39:40,  4.62it/s]
  1%|          | 74/11066 [00:16<39:38,  4.62it/s]
                                                  

  1%|          | 74/11066 [00:16<39:38,  4.62it/s]
  1%|          | 75/11066 [00:16<39:43,  4.61it/s]
                                                  

  1%|          | 75/11066 [00:16<39:43,  4.61it/s]
  1%|          | 76/11066 [00:16<39:55,  4.59it/s]
                                                  

  1%|          | 76/11066 [00:16<39:55,  4.59it/s]
  1%|          | 77/11066 [00:16<39:43,  4.61it/s]
                                                  

  1%|          | 77/11066 [00:16<39:43,  4.61it/s]
  1%|          | 78/11066 [00:17<39:55,  4.59it/s]
                                                  

  1%|          | 78/11066 [00:17<39:55,  4.59it/s]
  1%|          | 79/11066 [00:17<39:29,  4.64it/s]
                                                  

  1%|          | 79/11066 [00:17<39:29,  4.64it/s]
  1%|          | 80/11066 [00:17<39:19,  4.66it/s]
                                                  

  1%|          | 80/11066 [00:17<39:19,  4.66it/s]
  1%|          | 81/11066 [00:17<39:13,  4.67it/s]
                                                  

  1%|          | 81/11066 [00:17<39:13,  4.67it/s]
  1%|          | 82/11066 [00:17<39:29,  4.64it/s]
                                                  

  1%|          | 82/11066 [00:17<39:29,  4.64it/s]
  1%|          | 83/11066 [00:18<39:38,  4.62it/s]
                                                  

  1%|          | 83/11066 [00:18<39:38,  4.62it/s]
  1%|          | 84/11066 [00:18<39:50,  4.59it/s]
                                                  

  1%|          | 84/11066 [00:18<39:50,  4.59it/s]
  1%|          | 85/11066 [00:18<39:56,  4.58it/s]
                                                  

  1%|          | 85/11066 [00:18<39:56,  4.58it/s]
  1%|          | 86/11066 [00:18<39:46,  4.60it/s]
                                                  

  1%|          | 86/11066 [00:18<39:46,  4.60it/s]
  1%|          | 87/11066 [00:19<39:57,  4.58it/s]
                                                  

  1%|          | 87/11066 [00:19<39:57,  4.58it/s]
  1%|          | 88/11066 [00:19<40:09,  4.56it/s]
                                                  

  1%|          | 88/11066 [00:19<40:09,  4.56it/s]
  1%|          | 89/11066 [00:19<40:17,  4.54it/s]
                                                  

  1%|          | 89/11066 [00:19<40:17,  4.54it/s]
  1%|          | 90/11066 [00:19<40:04,  4.57it/s]
                                                  

  1%|          | 90/11066 [00:19<40:04,  4.57it/s]
  1%|          | 91/11066 [00:19<40:01,  4.57it/s]
                                                  

  1%|          | 91/11066 [00:19<40:01,  4.57it/s]
  1%|          | 92/11066 [00:20<40:08,  4.56it/s]
                                                  

  1%|          | 92/11066 [00:20<40:08,  4.56it/s]
  1%|          | 93/11066 [00:20<40:08,  4.56it/s]
                                                  

  1%|          | 93/11066 [00:20<40:08,  4.56it/s]
  1%|          | 94/11066 [00:20<40:05,  4.56it/s]
                                                  

  1%|          | 94/11066 [00:20<40:05,  4.56it/s]
  1%|          | 95/11066 [00:20<40:07,  4.56it/s]
                                                  

  1%|          | 95/11066 [00:20<40:07,  4.56it/s]
  1%|          | 96/11066 [00:20<40:10,  4.55it/s]
                                                  

  1%|          | 96/11066 [00:20<40:10,  4.55it/s]
  1%|          | 97/11066 [00:21<40:09,  4.55it/s]
                                                  

  1%|          | 97/11066 [00:21<40:09,  4.55it/s]
  1%|          | 98/11066 [00:21<40:07,  4.56it/s]
                                                  

  1%|          | 98/11066 [00:21<40:07,  4.56it/s]
  1%|          | 99/11066 [00:21<40:12,  4.55it/s]
                                                  

  1%|          | 99/11066 [00:21<40:12,  4.55it/s]
  1%|          | 100/11066 [00:21<39:55,  4.58it/s]
                                                   

  1%|          | 100/11066 [00:21<39:55,  4.58it/s]
  1%|          | 101/11066 [00:22<39:50,  4.59it/s]
                                                   

  1%|          | 101/11066 [00:22<39:50,  4.59it/s]
  1%|          | 102/11066 [00:22<39:55,  4.58it/s]
                                                   

  1%|          | 102/11066 [00:22<39:55,  4.58it/s]
  1%|          | 103/11066 [00:22<40:00,  4.57it/s]
                                                   

  1%|          | 103/11066 [00:22<40:00,  4.57it/s]
  1%|          | 104/11066 [00:22<40:08,  4.55it/s]
                                                   

  1%|          | 104/11066 [00:22<40:08,  4.55it/s]
  1%|          | 105/11066 [00:22<40:13,  4.54it/s]
                                                   

  1%|          | 105/11066 [00:22<40:13,  4.54it/s]
  1%|          | 106/11066 [00:23<40:16,  4.54it/s]
                                                   

  1%|          | 106/11066 [00:23<40:16,  4.54it/s]
  1%|          | 107/11066 [00:23<40:06,  4.55it/s]
                                                   

  1%|          | 107/11066 [00:23<40:06,  4.55it/s]
  1%|          | 108/11066 [00:23<40:03,  4.56it/s]
                                                   

  1%|          | 108/11066 [00:23<40:03,  4.56it/s]
  1%|          | 109/11066 [00:23<40:03,  4.56it/s]
                                                   

  1%|          | 109/11066 [00:23<40:03,  4.56it/s]
  1%|          | 110/11066 [00:24<40:10,  4.54it/s]
                                                   

  1%|          | 110/11066 [00:24<40:10,  4.54it/s]
  1%|          | 111/11066 [00:24<39:58,  4.57it/s]
                                                   

  1%|          | 111/11066 [00:24<39:58,  4.57it/s]
  1%|          | 112/11066 [00:24<39:59,  4.57it/s]
                                                   

  1%|          | 112/11066 [00:24<39:59,  4.57it/s]
  1%|          | 113/11066 [00:24<39:55,  4.57it/s]
                                                   

  1%|          | 113/11066 [00:24<39:55,  4.57it/s]
  1%|          | 114/11066 [00:24<39:52,  4.58it/s]
                                                   
{'loss': 5.8131, 'learning_rate': 2.9997288993312853e-05, 'epoch': 0.0}
{'loss': 5.867, 'learning_rate': 2.99945779866257e-05, 'epoch': 0.0}
{'loss': 5.7093, 'learning_rate': 2.9991866979938553e-05, 'epoch': 0.0}
{'loss': 5.6477, 'learning_rate': 2.99891559732514e-05, 'epoch': 0.0}
{'loss': 5.5229, 'learning_rate': 2.998644496656425e-05, 'epoch': 0.0}
{'loss': 5.4867, 'learning_rate': 2.99837339598771e-05, 'epoch': 0.0}
{'loss': 5.4317, 'learning_rate': 2.998102295318995e-05, 'epoch': 0.0}
{'loss': 5.3849, 'learning_rate': 2.9978311946502802e-05, 'epoch': 0.0}
{'loss': 5.2677, 'learning_rate': 2.9975600939815654e-05, 'epoch': 0.0}
{'loss': 5.1013, 'learning_rate': 2.9972889933128502e-05, 'epoch': 0.0}
{'loss': 4.9517, 'learning_rate': 2.9970178926441354e-05, 'epoch': 0.0}
{'loss': 4.8092, 'learning_rate': 2.9967467919754202e-05, 'epoch': 0.0}
{'loss': 4.9024, 'learning_rate': 2.996475691306705e-05, 'epoch': 0.0}
{'loss': 4.7373, 'learning_rate': 2.9962045906379903e-05, 'epoch': 0.0}
{'loss': 4.8521, 'learning_rate': 2.9959334899692754e-05, 'epoch': 0.0}
{'loss': 4.6115, 'learning_rate': 2.9956623893005603e-05, 'epoch': 0.0}
{'loss': 4.8838, 'learning_rate': 2.9953912886318455e-05, 'epoch': 0.0}
{'loss': 4.4024, 'learning_rate': 2.9951201879631303e-05, 'epoch': 0.0}
{'loss': 4.4759, 'learning_rate': 2.9948490872944155e-05, 'epoch': 0.0}
{'loss': 4.518, 'learning_rate': 2.9945779866257003e-05, 'epoch': 0.0}
{'loss': 4.563, 'learning_rate': 2.9943068859569852e-05, 'epoch': 0.0}
{'loss': 4.5919, 'learning_rate': 2.9940357852882704e-05, 'epoch': 0.0}
{'loss': 4.7354, 'learning_rate': 2.9937646846195556e-05, 'epoch': 0.0}
{'loss': 4.5677, 'learning_rate': 2.9934935839508404e-05, 'epoch': 0.0}
{'loss': 4.2246, 'learning_rate': 2.9932224832821256e-05, 'epoch': 0.0}
{'loss': 4.3559, 'learning_rate': 2.9929513826134108e-05, 'epoch': 0.0}
{'loss': 3.9653, 'learning_rate': 2.9926802819446956e-05, 'epoch': 0.0}
{'loss': 4.5756, 'learning_rate': 2.9924091812759805e-05, 'epoch': 0.01}
{'loss': 4.1574, 'learning_rate': 2.9921380806072653e-05, 'epoch': 0.01}
{'loss': 4.3055, 'learning_rate': 2.9918669799385505e-05, 'epoch': 0.01}
{'loss': 4.4877, 'learning_rate': 2.9915958792698357e-05, 'epoch': 0.01}
{'loss': 4.3467, 'learning_rate': 2.9913247786011205e-05, 'epoch': 0.01}
{'loss': 4.5641, 'learning_rate': 2.9910536779324057e-05, 'epoch': 0.01}
{'loss': 4.4136, 'learning_rate': 2.990782577263691e-05, 'epoch': 0.01}
{'loss': 4.1937, 'learning_rate': 2.9905114765949757e-05, 'epoch': 0.01}
{'loss': 3.8617, 'learning_rate': 2.9902403759262606e-05, 'epoch': 0.01}
{'loss': 4.1304, 'learning_rate': 2.9899692752575457e-05, 'epoch': 0.01}
{'loss': 3.829, 'learning_rate': 2.9896981745888306e-05, 'epoch': 0.01}
{'loss': 4.1963, 'learning_rate': 2.9894270739201158e-05, 'epoch': 0.01}
{'loss': 4.2229, 'learning_rate': 2.9891559732514006e-05, 'epoch': 0.01}
{'loss': 3.7992, 'learning_rate': 2.9888848725826858e-05, 'epoch': 0.01}
{'loss': 4.1811, 'learning_rate': 2.988613771913971e-05, 'epoch': 0.01}
{'loss': 3.9828, 'learning_rate': 2.9883426712452558e-05, 'epoch': 0.01}
{'loss': 4.2949, 'learning_rate': 2.9880715705765407e-05, 'epoch': 0.01}
{'loss': 3.5624, 'learning_rate': 2.987800469907826e-05, 'epoch': 0.01}
{'loss': 3.7444, 'learning_rate': 2.9875293692391107e-05, 'epoch': 0.01}
{'loss': 3.5932, 'learning_rate': 2.987258268570396e-05, 'epoch': 0.01}
{'loss': 3.7105, 'learning_rate': 2.986987167901681e-05, 'epoch': 0.01}
{'loss': 4.0077, 'learning_rate': 2.986716067232966e-05, 'epoch': 0.01}
{'loss': 3.5106, 'learning_rate': 2.986444966564251e-05, 'epoch': 0.01}
{'loss': 4.0515, 'learning_rate': 2.986173865895536e-05, 'epoch': 0.01}
{'loss': 3.5935, 'learning_rate': 2.9859027652268208e-05, 'epoch': 0.01}
{'loss': 3.942, 'learning_rate': 2.985631664558106e-05, 'epoch': 0.01}
{'loss': 3.8536, 'learning_rate': 2.9853605638893908e-05, 'epoch': 0.01}
{'loss': 3.3275, 'learning_rate': 2.985089463220676e-05, 'epoch': 0.01}
{'loss': 4.062, 'learning_rate': 2.984818362551961e-05, 'epoch': 0.01}
{'loss': 3.7084, 'learning_rate': 2.984547261883246e-05, 'epoch': 0.01}
{'loss': 3.5701, 'learning_rate': 2.9842761612145312e-05, 'epoch': 0.01}
{'loss': 3.3679, 'learning_rate': 2.9840050605458164e-05, 'epoch': 0.01}
{'loss': 4.0951, 'learning_rate': 2.983733959877101e-05, 'epoch': 0.01}
{'loss': 3.4606, 'learning_rate': 2.983462859208386e-05, 'epoch': 0.01}
{'loss': 2.9702, 'learning_rate': 2.983191758539671e-05, 'epoch': 0.01}
{'loss': 3.2061, 'learning_rate': 2.982920657870956e-05, 'epoch': 0.01}
{'loss': 3.5631, 'learning_rate': 2.9826495572022413e-05, 'epoch': 0.01}
{'loss': 3.2902, 'learning_rate': 2.982378456533526e-05, 'epoch': 0.01}
{'loss': 3.5982, 'learning_rate': 2.9821073558648113e-05, 'epoch': 0.01}
{'loss': 3.7596, 'learning_rate': 2.9818362551960965e-05, 'epoch': 0.01}
{'loss': 3.1705, 'learning_rate': 2.981565154527381e-05, 'epoch': 0.01}
{'loss': 3.4415, 'learning_rate': 2.9812940538586662e-05, 'epoch': 0.01}
{'loss': 2.5929, 'learning_rate': 2.9810229531899514e-05, 'epoch': 0.01}
{'loss': 3.0434, 'learning_rate': 2.9807518525212362e-05, 'epoch': 0.01}
{'loss': 3.2459, 'learning_rate': 2.9804807518525214e-05, 'epoch': 0.01}
{'loss': 3.2382, 'learning_rate': 2.9802096511838062e-05, 'epoch': 0.01}
{'loss': 3.4536, 'learning_rate': 2.9799385505150914e-05, 'epoch': 0.01}
{'loss': 2.386, 'learning_rate': 2.9796674498463766e-05, 'epoch': 0.01}
{'loss': 3.9266, 'learning_rate': 2.979396349177661e-05, 'epoch': 0.01}
{'loss': 2.8747, 'learning_rate': 2.9791252485089463e-05, 'epoch': 0.01}
{'loss': 3.4947, 'learning_rate': 2.9788541478402315e-05, 'epoch': 0.01}
{'loss': 2.6419, 'learning_rate': 2.9785830471715163e-05, 'epoch': 0.01}
{'loss': 3.3084, 'learning_rate': 2.9783119465028015e-05, 'epoch': 0.01}
{'loss': 3.5509, 'learning_rate': 2.9780408458340867e-05, 'epoch': 0.01}
{'loss': 3.3718, 'learning_rate': 2.9777697451653715e-05, 'epoch': 0.01}
{'loss': 2.629, 'learning_rate': 2.9774986444966567e-05, 'epoch': 0.02}
{'loss': 2.9046, 'learning_rate': 2.9772275438279415e-05, 'epoch': 0.02}
{'loss': 3.0044, 'learning_rate': 2.9769564431592264e-05, 'epoch': 0.02}
{'loss': 2.694, 'learning_rate': 2.9766853424905116e-05, 'epoch': 0.02}
{'loss': 2.9554, 'learning_rate': 2.9764142418217964e-05, 'epoch': 0.02}
{'loss': 3.4671, 'learning_rate': 2.9761431411530816e-05, 'epoch': 0.02}
{'loss': 2.7424, 'learning_rate': 2.9758720404843668e-05, 'epoch': 0.02}
{'loss': 2.9786, 'learning_rate': 2.9756009398156516e-05, 'epoch': 0.02}
{'loss': 3.1256, 'learning_rate': 2.9753298391469368e-05, 'epoch': 0.02}
{'loss': 2.6842, 'learning_rate': 2.9750587384782217e-05, 'epoch': 0.02}
{'loss': 2.5909, 'learning_rate': 2.9747876378095065e-05, 'epoch': 0.02}
{'loss': 2.9799, 'learning_rate': 2.9745165371407917e-05, 'epoch': 0.02}
{'loss': 3.1519, 'learning_rate': 2.974245436472077e-05, 'epoch': 0.02}
{'loss': 3.2945, 'learning_rate': 2.9739743358033617e-05, 'epoch': 0.02}
{'loss': 2.2057, 'learning_rate': 2.973703235134647e-05, 'epoch': 0.02}
{'loss': 2.5681, 'learning_rate': 2.9734321344659317e-05, 'epoch': 0.02}
{'loss': 2.3096, 'learning_rate': 2.973161033797217e-05, 'epoch': 0.02}
{'loss': 2.7998, 'learning_rate': 2.9728899331285018e-05, 'epoch': 0.02}
{'loss': 2.6053, 'learning_rate': 2.9726188324597866e-05, 'epoch': 0.02}
{'loss': 3.1633, 'learning_rate': 2.9723477317910718e-05, 'epoch': 0.02}
{'loss': 2.2774, 'learning_rate': 2.972076631122357e-05, 'epoch': 0.02}
{'loss': 2.1969, 'learning_rate': 2.9718055304536418e-05, 'epoch': 0.02}
{'loss': 1.9002, 'learning_rate': 2.971534429784927e-05, 'epoch': 0.02}
{'loss': 2.1258, 'learning_rate': 2.9712633291162122e-05, 'epoch': 0.02}
{'loss': 2.0907, 'learning_rate': 2.970992228447497e-05, 'epoch': 0.02}
{'loss': 3.2952, 'learning_rate': 2.970721127778782e-05, 'epoch': 0.02}
{'loss': 2.2971, 'learning_rate': 2.9704500271100667e-05, 'epoch': 0.02}
{'loss': 1.8442, 'learning_rate': 2.970178926441352e-05, 'epoch': 0.02}
{'loss': 3.0905, 'learning_rate': 2.969907825772637e-05, 'epoch': 0.02}
{'loss': 2.6187, 'learning_rate': 2.969636725103922e-05, 'epoch': 0.02}
{'loss': 1.9357, 'learning_rate': 2.969365624435207e-05, 'epoch': 0.02}

  1%|          | 114/11066 [00:24<39:52,  4.58it/s]
  1%|          | 115/11066 [00:25<39:58,  4.57it/s]
                                                   

  1%|          | 115/11066 [00:25<39:58,  4.57it/s]
  1%|          | 116/11066 [00:25<40:03,  4.56it/s]
                                                   

  1%|          | 116/11066 [00:25<40:03,  4.56it/s]
  1%|          | 117/11066 [00:25<39:27,  4.62it/s]
                                                   

  1%|          | 117/11066 [00:25<39:27,  4.62it/s]
  1%|          | 118/11066 [00:25<39:39,  4.60it/s]
                                                   

  1%|          | 118/11066 [00:25<39:39,  4.60it/s]
  1%|          | 119/11066 [00:26<39:45,  4.59it/s]
                                                   

  1%|          | 119/11066 [00:26<39:45,  4.59it/s]
  1%|          | 120/11066 [00:26<39:55,  4.57it/s]
                                                   

  1%|          | 120/11066 [00:26<39:55,  4.57it/s]
  1%|          | 121/11066 [00:26<42:33,  4.29it/s]
                                                   

  1%|          | 121/11066 [00:26<42:33,  4.29it/s]
  1%|          | 122/11066 [00:26<41:56,  4.35it/s]
                                                   

  1%|          | 122/11066 [00:26<41:56,  4.35it/s]
  1%|          | 123/11066 [00:26<41:28,  4.40it/s]
                                                   

  1%|          | 123/11066 [00:26<41:28,  4.40it/s]
  1%|          | 124/11066 [00:27<41:10,  4.43it/s]
                                                   

  1%|          | 124/11066 [00:27<41:10,  4.43it/s]
  1%|          | 125/11066 [00:27<40:45,  4.47it/s]
                                                   

  1%|          | 125/11066 [00:27<40:45,  4.47it/s]
  1%|          | 126/11066 [00:27<40:32,  4.50it/s]
                                                   

  1%|          | 126/11066 [00:27<40:32,  4.50it/s]
  1%|          | 127/11066 [00:27<40:28,  4.50it/s]
                                                   

  1%|          | 127/11066 [00:27<40:28,  4.50it/s]
  1%|          | 128/11066 [00:28<40:12,  4.53it/s]
                                                   

  1%|          | 128/11066 [00:28<40:12,  4.53it/s]
  1%|          | 129/11066 [00:28<40:07,  4.54it/s]
                                                   

  1%|          | 129/11066 [00:28<40:07,  4.54it/s]
  1%|          | 130/11066 [00:28<39:58,  4.56it/s]
                                                   

  1%|          | 130/11066 [00:28<39:58,  4.56it/s]
  1%|          | 131/11066 [00:28<39:37,  4.60it/s]
                                                   

  1%|          | 131/11066 [00:28<39:37,  4.60it/s]
  1%|          | 132/11066 [00:28<39:38,  4.60it/s]
                                                   

  1%|          | 132/11066 [00:28<39:38,  4.60it/s]
  1%|          | 133/11066 [00:29<39:47,  4.58it/s]
                                                   

  1%|          | 133/11066 [00:29<39:47,  4.58it/s]
  1%|          | 134/11066 [00:29<39:58,  4.56it/s]
                                                   

  1%|          | 134/11066 [00:29<39:58,  4.56it/s]
  1%|          | 135/11066 [00:29<39:44,  4.58it/s]
                                                   

  1%|          | 135/11066 [00:29<39:44,  4.58it/s]
  1%|          | 136/11066 [00:29<39:47,  4.58it/s]
                                                   

  1%|          | 136/11066 [00:29<39:47,  4.58it/s]
  1%|          | 137/11066 [00:30<39:40,  4.59it/s]
                                                   

  1%|          | 137/11066 [00:30<39:40,  4.59it/s]
  1%|          | 138/11066 [00:30<39:44,  4.58it/s]
                                                   

  1%|          | 138/11066 [00:30<39:44,  4.58it/s]
  1%|▏         | 139/11066 [00:30<39:58,  4.56it/s]
                                                   

  1%|▏         | 139/11066 [00:30<39:58,  4.56it/s]
  1%|▏         | 140/11066 [00:30<39:50,  4.57it/s]
                                                   

  1%|▏         | 140/11066 [00:30<39:50,  4.57it/s]
  1%|▏         | 141/11066 [00:30<39:53,  4.56it/s]
                                                   

  1%|▏         | 141/11066 [00:30<39:53,  4.56it/s]
  1%|▏         | 142/11066 [00:31<40:01,  4.55it/s]
                                                   

  1%|▏         | 142/11066 [00:31<40:01,  4.55it/s]
  1%|▏         | 143/11066 [00:31<40:07,  4.54it/s]
                                                   

  1%|▏         | 143/11066 [00:31<40:07,  4.54it/s]
  1%|▏         | 144/11066 [00:31<40:12,  4.53it/s]
                                                   

  1%|▏         | 144/11066 [00:31<40:12,  4.53it/s]
  1%|▏         | 145/11066 [00:31<40:26,  4.50it/s]
                                                   

  1%|▏         | 145/11066 [00:31<40:26,  4.50it/s]
  1%|▏         | 146/11066 [00:32<40:26,  4.50it/s]
                                                   

  1%|▏         | 146/11066 [00:32<40:26,  4.50it/s]
  1%|▏         | 147/11066 [00:32<40:17,  4.52it/s]
                                                   

  1%|▏         | 147/11066 [00:32<40:17,  4.52it/s]
  1%|▏         | 148/11066 [00:32<40:22,  4.51it/s]
                                                   

  1%|▏         | 148/11066 [00:32<40:22,  4.51it/s]
  1%|▏         | 149/11066 [00:32<40:03,  4.54it/s]
                                                   

  1%|▏         | 149/11066 [00:32<40:03,  4.54it/s]
  1%|▏         | 150/11066 [00:32<40:06,  4.54it/s]
                                                   

  1%|▏         | 150/11066 [00:32<40:06,  4.54it/s]
  1%|▏         | 151/11066 [00:33<40:11,  4.53it/s]
                                                   

  1%|▏         | 151/11066 [00:33<40:11,  4.53it/s]
  1%|▏         | 152/11066 [00:33<39:57,  4.55it/s]
                                                   

  1%|▏         | 152/11066 [00:33<39:57,  4.55it/s]
  1%|▏         | 153/11066 [00:33<39:59,  4.55it/s]
                                                   

  1%|▏         | 153/11066 [00:33<39:59,  4.55it/s]
  1%|▏         | 154/11066 [00:33<40:08,  4.53it/s]
                                                   

  1%|▏         | 154/11066 [00:33<40:08,  4.53it/s]
  1%|▏         | 155/11066 [00:33<40:14,  4.52it/s]
                                                   

  1%|▏         | 155/11066 [00:33<40:14,  4.52it/s]
  1%|▏         | 156/11066 [00:34<40:16,  4.52it/s]
                                                   

  1%|▏         | 156/11066 [00:34<40:16,  4.52it/s]
  1%|▏         | 157/11066 [00:34<40:09,  4.53it/s]
                                                   

  1%|▏         | 157/11066 [00:34<40:09,  4.53it/s]
  1%|▏         | 158/11066 [00:34<39:51,  4.56it/s]
                                                   

  1%|▏         | 158/11066 [00:34<39:51,  4.56it/s]
  1%|▏         | 159/11066 [00:34<40:01,  4.54it/s]
                                                   

  1%|▏         | 159/11066 [00:34<40:01,  4.54it/s]
  1%|▏         | 160/11066 [00:35<40:10,  4.53it/s]
                                                   

  1%|▏         | 160/11066 [00:35<40:10,  4.53it/s]
  1%|▏         | 161/11066 [00:35<40:14,  4.52it/s]
                                                   

  1%|▏         | 161/11066 [00:35<40:14,  4.52it/s]
  1%|▏         | 162/11066 [00:35<40:17,  4.51it/s]
                                                   

  1%|▏         | 162/11066 [00:35<40:17,  4.51it/s]
  1%|▏         | 163/11066 [00:35<40:17,  4.51it/s]
                                                   

  1%|▏         | 163/11066 [00:35<40:17,  4.51it/s]
  1%|▏         | 164/11066 [00:35<40:18,  4.51it/s]
                                                   

  1%|▏         | 164/11066 [00:35<40:18,  4.51it/s]
  1%|▏         | 165/11066 [00:36<39:43,  4.57it/s]
                                                   

  1%|▏         | 165/11066 [00:36<39:43,  4.57it/s]
  2%|▏         | 166/11066 [00:36<39:42,  4.57it/s]
                                                   

  2%|▏         | 166/11066 [00:36<39:42,  4.57it/s]
  2%|▏         | 167/11066 [00:36<39:49,  4.56it/s]
                                                   

  2%|▏         | 167/11066 [00:36<39:49,  4.56it/s]
  2%|▏         | 168/11066 [00:36<39:57,  4.54it/s]
                                                   

  2%|▏         | 168/11066 [00:36<39:57,  4.54it/s]
  2%|▏         | 169/11066 [00:37<40:07,  4.53it/s]
                                                   

  2%|▏         | 169/11066 [00:37<40:07,  4.53it/s]
  2%|▏         | 170/11066 [00:37<40:14,  4.51it/s]
                                                   

  2%|▏         | 170/11066 [00:37<40:14,  4.51it/s]
  2%|▏         | 171/11066 [00:37<40:18,  4.51it/s]
                                                   

  2%|▏         | 171/11066 [00:37<40:18,  4.51it/s]
  2%|▏         | 172/11066 [00:37<40:22,  4.50it/s]
                                                   

  2%|▏         | 172/11066 [00:37<40:22,  4.50it/s]
  2%|▏         | 173/11066 [00:37<40:22,  4.50it/s]
                                                   

  2%|▏         | 173/11066 [00:37<40:22,  4.50it/s]
  2%|▏         | 174/11066 [00:38<40:21,  4.50it/s]
                                                   

  2%|▏         | 174/11066 [00:38<40:21,  4.50it/s]
  2%|▏         | 175/11066 [00:38<40:03,  4.53it/s]
                                                   

  2%|▏         | 175/11066 [00:38<40:03,  4.53it/s]
  2%|▏         | 176/11066 [00:38<40:01,  4.53it/s]
                                                   

  2%|▏         | 176/11066 [00:38<40:01,  4.53it/s]
  2%|▏         | 177/11066 [00:38<40:02,  4.53it/s]
                                                   

  2%|▏         | 177/11066 [00:38<40:02,  4.53it/s]
  2%|▏         | 178/11066 [00:39<40:04,  4.53it/s]
                                                   

  2%|▏         | 178/11066 [00:39<40:04,  4.53it/s]
  2%|▏         | 179/11066 [00:39<40:09,  4.52it/s]
                                                   

  2%|▏         | 179/11066 [00:39<40:09,  4.52it/s]
  2%|▏         | 180/11066 [00:39<40:12,  4.51it/s]
                                                   

  2%|▏         | 180/11066 [00:39<40:12,  4.51it/s]
  2%|▏         | 181/11066 [00:39<40:16,  4.50it/s]
                                                   

  2%|▏         | 181/11066 [00:39<40:16,  4.50it/s]
  2%|▏         | 182/11066 [00:39<40:16,  4.50it/s]
                                                   

  2%|▏         | 182/11066 [00:39<40:16,  4.50it/s]
  2%|▏         | 183/11066 [00:40<40:20,  4.50it/s]
                                                   

  2%|▏         | 183/11066 [00:40<40:20,  4.50it/s]
  2%|▏         | 184/11066 [00:40<40:19,  4.50it/s]
                                                   

  2%|▏         | 184/11066 [00:40<40:19,  4.50it/s]
  2%|▏         | 185/11066 [00:40<40:18,  4.50it/s]
                                                   

  2%|▏         | 185/11066 [00:40<40:18,  4.50it/s]
  2%|▏         | 186/11066 [00:40<40:19,  4.50it/s]
                                                   

  2%|▏         | 186/11066 [00:40<40:19,  4.50it/s]
  2%|▏         | 187/11066 [00:41<40:21,  4.49it/s]
                                                   

  2%|▏         | 187/11066 [00:41<40:21,  4.49it/s]
  2%|▏         | 188/11066 [00:41<40:21,  4.49it/s]
                                                   

  2%|▏         | 188/11066 [00:41<40:21,  4.49it/s]
  2%|▏         | 189/11066 [00:41<40:20,  4.49it/s]
                                                   

  2%|▏         | 189/11066 [00:41<40:20,  4.49it/s]
  2%|▏         | 190/11066 [00:41<40:20,  4.49it/s]
                                                   

  2%|▏         | 190/11066 [00:41<40:20,  4.49it/s]
  2%|▏         | 191/11066 [00:41<40:20,  4.49it/s]
                                                   

  2%|▏         | 191/11066 [00:41<40:20,  4.49it/s]
  2%|▏         | 192/11066 [00:42<40:21,  4.49it/s]
                                                   

  2%|▏         | 192/11066 [00:42<40:21,  4.49it/s]
  2%|▏         | 193/11066 [00:42<40:19,  4.49it/s]
                                                   

  2%|▏         | 193/11066 [00:42<40:19,  4.49it/s]
  2%|▏         | 194/11066 [00:42<40:17,  4.50it/s]
                                                   

  2%|▏         | 194/11066 [00:42<40:17,  4.50it/s]
  2%|▏         | 195/11066 [00:42<40:16,  4.50it/s]
                                                   

  2%|▏         | 195/11066 [00:42<40:16,  4.50it/s]
  2%|▏         | 196/11066 [00:43<40:19,  4.49it/s]
                                                   

  2%|▏         | 196/11066 [00:43<40:19,  4.49it/s]
  2%|▏         | 197/11066 [00:43<40:20,  4.49it/s]
                                                   

  2%|▏         | 197/11066 [00:43<40:20,  4.49it/s]
  2%|▏         | 198/11066 [00:43<40:22,  4.49it/s]
                                                   

  2%|▏         | 198/11066 [00:43<40:22,  4.49it/s]
  2%|▏         | 199/11066 [00:43<40:19,  4.49it/s]
                                                   

  2%|▏         | 199/11066 [00:43<40:19,  4.49it/s]
  2%|▏         | 200/11066 [00:43<40:16,  4.50it/s]
                                                   

  2%|▏         | 200/11066 [00:43<40:16,  4.50it/s]
  2%|▏         | 201/11066 [00:44<40:15,  4.50it/s]
                                                   

  2%|▏         | 201/11066 [00:44<40:15,  4.50it/s]
  2%|▏         | 202/11066 [00:44<40:16,  4.50it/s]
                                                   

  2%|▏         | 202/11066 [00:44<40:16,  4.50it/s]
  2%|▏         | 203/11066 [00:44<40:15,  4.50it/s]
                                                   

  2%|▏         | 203/11066 [00:44<40:15,  4.50it/s]
  2%|▏         | 204/11066 [00:44<40:13,  4.50it/s]
                                                   

  2%|▏         | 204/11066 [00:44<40:13,  4.50it/s]
  2%|▏         | 205/11066 [00:45<40:13,  4.50it/s]
                                                   

  2%|▏         | 205/11066 [00:45<40:13,  4.50it/s]
  2%|▏         | 206/11066 [00:45<40:11,  4.50it/s]
                                                   

  2%|▏         | 206/11066 [00:45<40:11,  4.50it/s]
  2%|▏         | 207/11066 [00:45<39:50,  4.54it/s]
                                                   

  2%|▏         | 207/11066 [00:45<39:50,  4.54it/s]
  2%|▏         | 208/11066 [00:45<39:49,  4.54it/s]
                                                   

  2%|▏         | 208/11066 [00:45<39:49,  4.54it/s]
  2%|▏         | 209/11066 [00:45<39:51,  4.54it/s]
                                                   

  2%|▏         | 209/11066 [00:45<39:51,  4.54it/s]
  2%|▏         | 210/11066 [00:46<39:56,  4.53it/s]
                                                   

  2%|▏         | 210/11066 [00:46<39:56,  4.53it/s]
  2%|▏         | 211/11066 [00:46<39:59,  4.52it/s]
                                                   

  2%|▏         | 211/11066 [00:46<39:59,  4.52it/s]
  2%|▏         | 212/11066 [00:46<40:04,  4.51it/s]
                                                   

  2%|▏         | 212/11066 [00:46<40:04,  4.51it/s]
  2%|▏         | 213/11066 [00:46<40:05,  4.51it/s]
                                                   

  2%|▏         | 213/11066 [00:46<40:05,  4.51it/s]
  2%|▏         | 214/11066 [00:47<40:06,  4.51it/s]
                                                   

  2%|▏         | 214/11066 [00:47<40:06,  4.51it/s]
  2%|▏         | 215/11066 [00:47<40:05,  4.51it/s]
                                                   

  2%|▏         | 215/11066 [00:47<40:05,  4.51it/s]
  2%|▏         | 216/11066 [00:47<40:06,  4.51it/s]
                                                   

  2%|▏         | 216/11066 [00:47<40:06,  4.51it/s]
  2%|▏         | 217/11066 [00:47<40:04,  4.51it/s]
                                                   

  2%|▏         | 217/11066 [00:47<40:04,  4.51it/s]
  2%|▏         | 218/11066 [00:47<39:57,  4.52it/s]
                                                   

  2%|▏         | 218/11066 [00:47<39:57,  4.52it/s]
  2%|▏         | 219/11066 [00:48<39:30,  4.58it/s]
                                                   

  2%|▏         | 219/11066 [00:48<39:30,  4.58it/s]
  2%|▏         | 220/11066 [00:48<39:45,  4.55it/s]
                                                   

  2%|▏         | 220/11066 [00:48<39:45,  4.55it/s]
  2%|▏         | 221/11066 [00:48<39:52,  4.53it/s]
                                                   

  2%|▏         | 221/11066 [00:48<39:52,  4.53it/s]
  2%|▏         | 222/11066 [00:48<39:57,  4.52it/s]
                                                   

  2%|▏         | 222/11066 [00:48<39:57,  4.52it/s]
  2%|▏         | 223/11066 [00:49<39:58,  4.52it/s]
                                                   

  2%|▏         | 223/11066 [00:49<39:58,  4.52it/s]
  2%|▏         | 224/11066 [00:49<40:00,  4.52it/s]
                                                   

  2%|▏         | 224/11066 [00:49<40:00,  4.52it/s]
  2%|▏         | 225/11066 [00:49<39:41,  4.55it/s]
                                                   

  2%|▏         | 225/11066 [00:49<39:41,  4.55it/s]
  2%|▏         | 226/11066 [00:49<38:57,  4.64it/s]
                                                   
{'loss': 2.9793, 'learning_rate': 2.9690945237664923e-05, 'epoch': 0.02}
{'loss': 2.9322, 'learning_rate': 2.968823423097777e-05, 'epoch': 0.02}
{'loss': 2.4332, 'learning_rate': 2.968552322429062e-05, 'epoch': 0.02}
{'loss': 2.7374, 'learning_rate': 2.968281221760347e-05, 'epoch': 0.02}
{'loss': 3.457, 'learning_rate': 2.968010121091632e-05, 'epoch': 0.02}
{'loss': 2.7925, 'learning_rate': 2.9677390204229172e-05, 'epoch': 0.02}
{'loss': 3.1397, 'learning_rate': 2.967467919754202e-05, 'epoch': 0.02}
{'loss': 2.3759, 'learning_rate': 2.9671968190854872e-05, 'epoch': 0.02}
{'loss': 2.5331, 'learning_rate': 2.9669257184167724e-05, 'epoch': 0.02}
{'loss': 2.2555, 'learning_rate': 2.9666546177480572e-05, 'epoch': 0.02}
{'loss': 2.9601, 'learning_rate': 2.966383517079342e-05, 'epoch': 0.02}
{'loss': 2.4208, 'learning_rate': 2.9661124164106273e-05, 'epoch': 0.02}
{'loss': 2.5289, 'learning_rate': 2.965841315741912e-05, 'epoch': 0.02}
{'loss': 2.614, 'learning_rate': 2.9655702150731973e-05, 'epoch': 0.02}
{'loss': 3.0021, 'learning_rate': 2.9652991144044825e-05, 'epoch': 0.02}
{'loss': 2.6222, 'learning_rate': 2.9650280137357673e-05, 'epoch': 0.02}
{'loss': 2.2244, 'learning_rate': 2.9647569130670525e-05, 'epoch': 0.02}
{'loss': 2.1159, 'learning_rate': 2.964485812398337e-05, 'epoch': 0.02}
{'loss': 2.8683, 'learning_rate': 2.9642147117296222e-05, 'epoch': 0.02}
{'loss': 2.086, 'learning_rate': 2.9639436110609074e-05, 'epoch': 0.02}
{'loss': 2.3683, 'learning_rate': 2.9636725103921922e-05, 'epoch': 0.02}
{'loss': 2.9748, 'learning_rate': 2.9634014097234774e-05, 'epoch': 0.02}
{'loss': 3.119, 'learning_rate': 2.9631303090547626e-05, 'epoch': 0.02}
{'loss': 2.9806, 'learning_rate': 2.9628592083860474e-05, 'epoch': 0.02}
{'loss': 2.4764, 'learning_rate': 2.9625881077173326e-05, 'epoch': 0.02}
{'loss': 2.1445, 'learning_rate': 2.9623170070486175e-05, 'epoch': 0.03}
{'loss': 2.7098, 'learning_rate': 2.9620459063799023e-05, 'epoch': 0.03}
{'loss': 2.6619, 'learning_rate': 2.9617748057111875e-05, 'epoch': 0.03}
{'loss': 2.3003, 'learning_rate': 2.9615037050424723e-05, 'epoch': 0.03}
{'loss': 2.8239, 'learning_rate': 2.9612326043737575e-05, 'epoch': 0.03}
{'loss': 2.0689, 'learning_rate': 2.9609615037050427e-05, 'epoch': 0.03}
{'loss': 2.3302, 'learning_rate': 2.9606904030363275e-05, 'epoch': 0.03}
{'loss': 2.141, 'learning_rate': 2.9604193023676127e-05, 'epoch': 0.03}
{'loss': 2.69, 'learning_rate': 2.9601482016988976e-05, 'epoch': 0.03}
{'loss': 2.0252, 'learning_rate': 2.9598771010301824e-05, 'epoch': 0.03}
{'loss': 2.4255, 'learning_rate': 2.9596060003614676e-05, 'epoch': 0.03}
{'loss': 1.9766, 'learning_rate': 2.9593348996927528e-05, 'epoch': 0.03}
{'loss': 3.1633, 'learning_rate': 2.9590637990240376e-05, 'epoch': 0.03}
{'loss': 2.6725, 'learning_rate': 2.9587926983553228e-05, 'epoch': 0.03}
{'loss': 2.3386, 'learning_rate': 2.9585215976866076e-05, 'epoch': 0.03}
{'loss': 2.2246, 'learning_rate': 2.9582504970178928e-05, 'epoch': 0.03}
{'loss': 2.4671, 'learning_rate': 2.9579793963491777e-05, 'epoch': 0.03}
{'loss': 2.2176, 'learning_rate': 2.9577082956804625e-05, 'epoch': 0.03}
{'loss': 2.3291, 'learning_rate': 2.9574371950117477e-05, 'epoch': 0.03}
{'loss': 2.2117, 'learning_rate': 2.957166094343033e-05, 'epoch': 0.03}
{'loss': 2.4156, 'learning_rate': 2.9568949936743177e-05, 'epoch': 0.03}
{'loss': 2.6955, 'learning_rate': 2.956623893005603e-05, 'epoch': 0.03}
{'loss': 2.2952, 'learning_rate': 2.956352792336888e-05, 'epoch': 0.03}
{'loss': 2.639, 'learning_rate': 2.956081691668173e-05, 'epoch': 0.03}
{'loss': 2.5189, 'learning_rate': 2.9558105909994578e-05, 'epoch': 0.03}
{'loss': 3.0183, 'learning_rate': 2.9555394903307426e-05, 'epoch': 0.03}
{'loss': 1.5289, 'learning_rate': 2.9552683896620278e-05, 'epoch': 0.03}
{'loss': 2.2809, 'learning_rate': 2.954997288993313e-05, 'epoch': 0.03}
{'loss': 2.1165, 'learning_rate': 2.9547261883245978e-05, 'epoch': 0.03}
{'loss': 2.4877, 'learning_rate': 2.954455087655883e-05, 'epoch': 0.03}
{'loss': 2.4834, 'learning_rate': 2.9541839869871682e-05, 'epoch': 0.03}
{'loss': 2.4929, 'learning_rate': 2.953912886318453e-05, 'epoch': 0.03}
{'loss': 1.7292, 'learning_rate': 2.953641785649738e-05, 'epoch': 0.03}
{'loss': 2.0687, 'learning_rate': 2.953370684981023e-05, 'epoch': 0.03}
{'loss': 1.7756, 'learning_rate': 2.953099584312308e-05, 'epoch': 0.03}
{'loss': 1.9391, 'learning_rate': 2.952828483643593e-05, 'epoch': 0.03}
{'loss': 2.465, 'learning_rate': 2.952557382974878e-05, 'epoch': 0.03}
{'loss': 2.8734, 'learning_rate': 2.952286282306163e-05, 'epoch': 0.03}
{'loss': 2.5771, 'learning_rate': 2.9520151816374483e-05, 'epoch': 0.03}
{'loss': 1.8889, 'learning_rate': 2.951744080968733e-05, 'epoch': 0.03}
{'loss': 2.1676, 'learning_rate': 2.951472980300018e-05, 'epoch': 0.03}
{'loss': 3.1156, 'learning_rate': 2.9512018796313032e-05, 'epoch': 0.03}
{'loss': 1.7913, 'learning_rate': 2.950930778962588e-05, 'epoch': 0.03}
{'loss': 2.6479, 'learning_rate': 2.9506596782938732e-05, 'epoch': 0.03}
{'loss': 2.4518, 'learning_rate': 2.9503885776251584e-05, 'epoch': 0.03}
{'loss': 2.0942, 'learning_rate': 2.9501174769564432e-05, 'epoch': 0.03}
{'loss': 2.4306, 'learning_rate': 2.9498463762877284e-05, 'epoch': 0.03}
{'loss': 2.5361, 'learning_rate': 2.9495752756190133e-05, 'epoch': 0.03}
{'loss': 2.5573, 'learning_rate': 2.949304174950298e-05, 'epoch': 0.03}
{'loss': 2.4955, 'learning_rate': 2.9490330742815833e-05, 'epoch': 0.03}
{'loss': 2.7852, 'learning_rate': 2.948761973612868e-05, 'epoch': 0.03}
{'loss': 2.1162, 'learning_rate': 2.9484908729441533e-05, 'epoch': 0.03}
{'loss': 2.3774, 'learning_rate': 2.9482197722754385e-05, 'epoch': 0.03}
{'loss': 2.148, 'learning_rate': 2.9479486716067233e-05, 'epoch': 0.03}
{'loss': 2.5626, 'learning_rate': 2.9476775709380085e-05, 'epoch': 0.03}
{'loss': 2.4154, 'learning_rate': 2.9474064702692937e-05, 'epoch': 0.04}
{'loss': 2.1039, 'learning_rate': 2.9471353696005782e-05, 'epoch': 0.04}
{'loss': 2.3193, 'learning_rate': 2.9468642689318634e-05, 'epoch': 0.04}
{'loss': 2.2391, 'learning_rate': 2.9465931682631482e-05, 'epoch': 0.04}
{'loss': 2.0979, 'learning_rate': 2.9463220675944334e-05, 'epoch': 0.04}
{'loss': 2.2808, 'learning_rate': 2.9460509669257186e-05, 'epoch': 0.04}
{'loss': 2.659, 'learning_rate': 2.9457798662570034e-05, 'epoch': 0.04}
{'loss': 2.3003, 'learning_rate': 2.9455087655882886e-05, 'epoch': 0.04}
{'loss': 2.4122, 'learning_rate': 2.9452376649195738e-05, 'epoch': 0.04}
{'loss': 2.6408, 'learning_rate': 2.9449665642508583e-05, 'epoch': 0.04}
{'loss': 2.2382, 'learning_rate': 2.9446954635821435e-05, 'epoch': 0.04}
{'loss': 1.7609, 'learning_rate': 2.9444243629134287e-05, 'epoch': 0.04}
{'loss': 2.5257, 'learning_rate': 2.9441532622447135e-05, 'epoch': 0.04}
{'loss': 2.5992, 'learning_rate': 2.9438821615759987e-05, 'epoch': 0.04}
{'loss': 2.3529, 'learning_rate': 2.9436110609072835e-05, 'epoch': 0.04}
{'loss': 2.1197, 'learning_rate': 2.9433399602385687e-05, 'epoch': 0.04}
{'loss': 2.0271, 'learning_rate': 2.943068859569854e-05, 'epoch': 0.04}
{'loss': 2.099, 'learning_rate': 2.9427977589011384e-05, 'epoch': 0.04}
{'loss': 2.555, 'learning_rate': 2.9425266582324236e-05, 'epoch': 0.04}
{'loss': 2.0059, 'learning_rate': 2.9422555575637088e-05, 'epoch': 0.04}
{'loss': 2.146, 'learning_rate': 2.9419844568949936e-05, 'epoch': 0.04}
{'loss': 1.9306, 'learning_rate': 2.9417133562262788e-05, 'epoch': 0.04}
{'loss': 2.3847, 'learning_rate': 2.941442255557564e-05, 'epoch': 0.04}
{'loss': 2.7286, 'learning_rate': 2.941171154888849e-05, 'epoch': 0.04}
{'loss': 2.1696, 'learning_rate': 2.940900054220134e-05, 'epoch': 0.04}
{'loss': 2.1023, 'learning_rate': 2.940628953551419e-05, 'epoch': 0.04}
{'loss': 1.9038, 'learning_rate': 2.9403578528827037e-05, 'epoch': 0.04}
{'loss': 2.4279, 'learning_rate': 2.940086752213989e-05, 'epoch': 0.04}
{'loss': 1.7805, 'learning_rate': 2.9398156515452737e-05, 'epoch': 0.04}
{'loss': 2.851, 'learning_rate': 2.939544550876559e-05, 'epoch': 0.04}
{'loss': 1.854, 'learning_rate': 2.939273450207844e-05, 'epoch': 0.04}
{'loss': 2.999, 'learning_rate': 2.939002349539129e-05, 'epoch': 0.04}

  2%|▏         | 226/11066 [00:49<38:57,  4.64it/s]
  2%|▏         | 227/11066 [00:49<39:25,  4.58it/s]
                                                   

  2%|▏         | 227/11066 [00:49<39:25,  4.58it/s]
  2%|▏         | 228/11066 [00:50<39:38,  4.56it/s]
                                                   

  2%|▏         | 228/11066 [00:50<39:38,  4.56it/s]
  2%|▏         | 229/11066 [00:50<39:42,  4.55it/s]
                                                   

  2%|▏         | 229/11066 [00:50<39:42,  4.55it/s]
  2%|▏         | 230/11066 [00:50<39:48,  4.54it/s]
                                                   

  2%|▏         | 230/11066 [00:50<39:48,  4.54it/s]
  2%|▏         | 231/11066 [00:50<39:54,  4.53it/s]
                                                   

  2%|▏         | 231/11066 [00:50<39:54,  4.53it/s]
  2%|▏         | 232/11066 [00:51<39:58,  4.52it/s]
                                                   

  2%|▏         | 232/11066 [00:51<39:58,  4.52it/s]
  2%|▏         | 233/11066 [00:51<40:03,  4.51it/s]
                                                   

  2%|▏         | 233/11066 [00:51<40:03,  4.51it/s]
  2%|▏         | 234/11066 [00:51<40:05,  4.50it/s]
                                                   

  2%|▏         | 234/11066 [00:51<40:05,  4.50it/s]
  2%|▏         | 235/11066 [00:51<40:07,  4.50it/s]
                                                   

  2%|▏         | 235/11066 [00:51<40:07,  4.50it/s]
  2%|▏         | 236/11066 [00:51<40:45,  4.43it/s]
                                                   

  2%|▏         | 236/11066 [00:51<40:45,  4.43it/s]
  2%|▏         | 237/11066 [00:52<39:53,  4.52it/s]
                                                   

  2%|▏         | 237/11066 [00:52<39:53,  4.52it/s]
  2%|▏         | 238/11066 [00:52<40:01,  4.51it/s]
                                                   

  2%|▏         | 238/11066 [00:52<40:01,  4.51it/s]
  2%|▏         | 239/11066 [00:52<39:42,  4.54it/s]
                                                   

  2%|▏         | 239/11066 [00:52<39:42,  4.54it/s]
  2%|▏         | 240/11066 [00:52<39:22,  4.58it/s]
                                                   

  2%|▏         | 240/11066 [00:52<39:22,  4.58it/s]
  2%|▏         | 241/11066 [00:53<39:29,  4.57it/s]
                                                   

  2%|▏         | 241/11066 [00:53<39:29,  4.57it/s]
  2%|▏         | 242/11066 [00:53<39:36,  4.55it/s]
                                                   

  2%|▏         | 242/11066 [00:53<39:36,  4.55it/s]
  2%|▏         | 243/11066 [00:53<39:41,  4.54it/s]
                                                   

  2%|▏         | 243/11066 [00:53<39:41,  4.54it/s]
  2%|▏         | 244/11066 [00:53<39:44,  4.54it/s]
                                                   

  2%|▏         | 244/11066 [00:53<39:44,  4.54it/s]
  2%|▏         | 245/11066 [00:53<39:48,  4.53it/s]
                                                   

  2%|▏         | 245/11066 [00:53<39:48,  4.53it/s]
  2%|▏         | 246/11066 [00:54<39:16,  4.59it/s]
                                                   

  2%|▏         | 246/11066 [00:54<39:16,  4.59it/s]
  2%|▏         | 247/11066 [00:54<39:30,  4.56it/s]
                                                   

  2%|▏         | 247/11066 [00:54<39:30,  4.56it/s]
  2%|▏         | 248/11066 [00:54<39:19,  4.58it/s]
                                                   

  2%|▏         | 248/11066 [00:54<39:19,  4.58it/s]
  2%|▏         | 249/11066 [00:54<39:08,  4.61it/s]
                                                   

  2%|▏         | 249/11066 [00:54<39:08,  4.61it/s]
  2%|▏         | 250/11066 [00:54<40:13,  4.48it/s]
                                                   

  2%|▏         | 250/11066 [00:54<40:13,  4.48it/s]
  2%|▏         | 251/11066 [00:55<40:41,  4.43it/s]
                                                   

  2%|▏         | 251/11066 [00:55<40:41,  4.43it/s]
  2%|▏         | 252/11066 [00:55<40:30,  4.45it/s]
                                                   

  2%|▏         | 252/11066 [00:55<40:30,  4.45it/s]
  2%|▏         | 253/11066 [00:55<40:19,  4.47it/s]
                                                   

  2%|▏         | 253/11066 [00:55<40:19,  4.47it/s]
  2%|▏         | 254/11066 [00:55<39:49,  4.53it/s]
                                                   

  2%|▏         | 254/11066 [00:55<39:49,  4.53it/s]
  2%|▏         | 255/11066 [00:56<39:50,  4.52it/s]
                                                   

  2%|▏         | 255/11066 [00:56<39:50,  4.52it/s]
  2%|▏         | 256/11066 [00:56<39:51,  4.52it/s]
                                                   

  2%|▏         | 256/11066 [00:56<39:51,  4.52it/s]
  2%|▏         | 257/11066 [00:56<39:55,  4.51it/s]
                                                   

  2%|▏         | 257/11066 [00:56<39:55,  4.51it/s]
  2%|▏         | 258/11066 [00:56<39:53,  4.52it/s]
                                                   

  2%|▏         | 258/11066 [00:56<39:53,  4.52it/s]
  2%|▏         | 259/11066 [00:56<39:37,  4.55it/s]
                                                   

  2%|▏         | 259/11066 [00:56<39:37,  4.55it/s]
  2%|▏         | 260/11066 [00:57<39:37,  4.54it/s]
                                                   

  2%|▏         | 260/11066 [00:57<39:37,  4.54it/s]
  2%|▏         | 261/11066 [00:57<39:05,  4.61it/s]
                                                   

  2%|▏         | 261/11066 [00:57<39:05,  4.61it/s]
  2%|▏         | 262/11066 [00:57<38:54,  4.63it/s]
                                                   

  2%|▏         | 262/11066 [00:57<38:54,  4.63it/s]
  2%|▏         | 263/11066 [00:57<38:38,  4.66it/s]
                                                   

  2%|▏         | 263/11066 [00:57<38:38,  4.66it/s]
  2%|▏         | 264/11066 [00:58<38:51,  4.63it/s]
                                                   

  2%|▏         | 264/11066 [00:58<38:51,  4.63it/s]
  2%|▏         | 265/11066 [00:58<39:05,  4.60it/s]
                                                   

  2%|▏         | 265/11066 [00:58<39:05,  4.60it/s]
  2%|▏         | 266/11066 [00:58<39:00,  4.61it/s]
                                                   

  2%|▏         | 266/11066 [00:58<39:00,  4.61it/s]
  2%|▏         | 267/11066 [00:58<38:55,  4.62it/s]
                                                   

  2%|▏         | 267/11066 [00:58<38:55,  4.62it/s]
  2%|▏         | 268/11066 [00:58<38:30,  4.67it/s]
                                                   

  2%|▏         | 268/11066 [00:58<38:30,  4.67it/s]
  2%|▏         | 269/11066 [00:59<38:50,  4.63it/s]
                                                   

  2%|▏         | 269/11066 [00:59<38:50,  4.63it/s]
  2%|▏         | 270/11066 [00:59<38:19,  4.70it/s]
                                                   

  2%|▏         | 270/11066 [00:59<38:19,  4.70it/s]
  2%|▏         | 271/11066 [00:59<38:36,  4.66it/s]
                                                   

  2%|▏         | 271/11066 [00:59<38:36,  4.66it/s]
  2%|▏         | 272/11066 [00:59<38:22,  4.69it/s]
                                                   

  2%|▏         | 272/11066 [00:59<38:22,  4.69it/s]
  2%|▏         | 273/11066 [00:59<38:27,  4.68it/s]
                                                   

  2%|▏         | 273/11066 [00:59<38:27,  4.68it/s]
  2%|▏         | 274/11066 [01:00<38:16,  4.70it/s]
                                                   

  2%|▏         | 274/11066 [01:00<38:16,  4.70it/s]
  2%|▏         | 275/11066 [01:00<38:27,  4.68it/s]
                                                   

  2%|▏         | 275/11066 [01:00<38:27,  4.68it/s]
  2%|▏         | 276/11066 [01:00<38:48,  4.63it/s]
                                                   

  2%|▏         | 276/11066 [01:00<38:48,  4.63it/s]
  3%|▎         | 277/11066 [01:00<39:22,  4.57it/s]
                                                   

  3%|▎         | 277/11066 [01:00<39:22,  4.57it/s]
  3%|▎         | 278/11066 [01:01<39:11,  4.59it/s]
                                                   

  3%|▎         | 278/11066 [01:01<39:11,  4.59it/s]
  3%|▎         | 279/11066 [01:01<39:02,  4.61it/s]
                                                   

  3%|▎         | 279/11066 [01:01<39:02,  4.61it/s]
  3%|▎         | 280/11066 [01:01<39:41,  4.53it/s]
                                                   

  3%|▎         | 280/11066 [01:01<39:41,  4.53it/s]
  3%|▎         | 281/11066 [01:01<39:45,  4.52it/s]
                                                   

  3%|▎         | 281/11066 [01:01<39:45,  4.52it/s]
  3%|▎         | 282/11066 [01:01<40:21,  4.45it/s]
                                                   

  3%|▎         | 282/11066 [01:01<40:21,  4.45it/s]
  3%|▎         | 283/11066 [01:02<40:27,  4.44it/s]
                                                   

  3%|▎         | 283/11066 [01:02<40:27,  4.44it/s]
  3%|▎         | 284/11066 [01:02<39:56,  4.50it/s]
                                                   

  3%|▎         | 284/11066 [01:02<39:56,  4.50it/s]
  3%|▎         | 285/11066 [01:02<39:06,  4.59it/s]
                                                   

  3%|▎         | 285/11066 [01:02<39:06,  4.59it/s]
  3%|▎         | 286/11066 [01:02<39:24,  4.56it/s]
                                                   

  3%|▎         | 286/11066 [01:02<39:24,  4.56it/s]
  3%|▎         | 287/11066 [01:03<39:36,  4.54it/s]
                                                   

  3%|▎         | 287/11066 [01:03<39:36,  4.54it/s]
  3%|▎         | 288/11066 [01:03<39:43,  4.52it/s]
                                                   

  3%|▎         | 288/11066 [01:03<39:43,  4.52it/s]
  3%|▎         | 289/11066 [01:03<39:47,  4.51it/s]
                                                   

  3%|▎         | 289/11066 [01:03<39:47,  4.51it/s]
  3%|▎         | 290/11066 [01:03<39:48,  4.51it/s]
                                                   

  3%|▎         | 290/11066 [01:03<39:48,  4.51it/s]
  3%|▎         | 291/11066 [01:03<39:49,  4.51it/s]
                                                   

  3%|▎         | 291/11066 [01:03<39:49,  4.51it/s]
  3%|▎         | 292/11066 [01:04<39:50,  4.51it/s]
                                                   

  3%|▎         | 292/11066 [01:04<39:50,  4.51it/s]
  3%|▎         | 293/11066 [01:04<39:48,  4.51it/s]
                                                   

  3%|▎         | 293/11066 [01:04<39:48,  4.51it/s]
  3%|▎         | 294/11066 [01:04<39:51,  4.50it/s]
                                                   

  3%|▎         | 294/11066 [01:04<39:51,  4.50it/s]
  3%|▎         | 295/11066 [01:04<39:32,  4.54it/s]
                                                   

  3%|▎         | 295/11066 [01:04<39:32,  4.54it/s]
  3%|▎         | 296/11066 [01:05<39:12,  4.58it/s]
                                                   

  3%|▎         | 296/11066 [01:05<39:12,  4.58it/s]
  3%|▎         | 297/11066 [01:05<38:50,  4.62it/s]
                                                   

  3%|▎         | 297/11066 [01:05<38:50,  4.62it/s]
  3%|▎         | 298/11066 [01:05<39:08,  4.58it/s]
                                                   

  3%|▎         | 298/11066 [01:05<39:08,  4.58it/s]
  3%|▎         | 299/11066 [01:05<38:31,  4.66it/s]
                                                   

  3%|▎         | 299/11066 [01:05<38:31,  4.66it/s]
  3%|▎         | 300/11066 [01:05<39:56,  4.49it/s]
                                                   

  3%|▎         | 300/11066 [01:05<39:56,  4.49it/s]
  3%|▎         | 301/11066 [01:06<39:56,  4.49it/s]
                                                   

  3%|▎         | 301/11066 [01:06<39:56,  4.49it/s]
  3%|▎         | 302/11066 [01:06<39:35,  4.53it/s]
                                                   

  3%|▎         | 302/11066 [01:06<39:35,  4.53it/s]
  3%|▎         | 303/11066 [01:06<39:39,  4.52it/s]
                                                   

  3%|▎         | 303/11066 [01:06<39:39,  4.52it/s]
  3%|▎         | 304/11066 [01:06<39:11,  4.58it/s]
                                                   

  3%|▎         | 304/11066 [01:06<39:11,  4.58it/s]
  3%|▎         | 305/11066 [01:07<39:14,  4.57it/s]
                                                   

  3%|▎         | 305/11066 [01:07<39:14,  4.57it/s]
  3%|▎         | 306/11066 [01:07<39:21,  4.56it/s]
                                                   

  3%|▎         | 306/11066 [01:07<39:21,  4.56it/s]
  3%|▎         | 307/11066 [01:07<40:08,  4.47it/s]
                                                   

  3%|▎         | 307/11066 [01:07<40:08,  4.47it/s]
  3%|▎         | 308/11066 [01:07<39:54,  4.49it/s]
                                                   

  3%|▎         | 308/11066 [01:07<39:54,  4.49it/s]
  3%|▎         | 309/11066 [01:07<39:53,  4.49it/s]
                                                   

  3%|▎         | 309/11066 [01:07<39:53,  4.49it/s]
  3%|▎         | 310/11066 [01:08<39:28,  4.54it/s]
                                                   

  3%|▎         | 310/11066 [01:08<39:28,  4.54it/s]
  3%|▎         | 311/11066 [01:08<39:25,  4.55it/s]
                                                   

  3%|▎         | 311/11066 [01:08<39:25,  4.55it/s]
  3%|▎         | 312/11066 [01:08<39:31,  4.53it/s]
                                                   

  3%|▎         | 312/11066 [01:08<39:31,  4.53it/s]
  3%|▎         | 313/11066 [01:08<39:37,  4.52it/s]
                                                   

  3%|▎         | 313/11066 [01:08<39:37,  4.52it/s]
  3%|▎         | 314/11066 [01:09<39:45,  4.51it/s]
                                                   

  3%|▎         | 314/11066 [01:09<39:45,  4.51it/s]
  3%|▎         | 315/11066 [01:09<39:32,  4.53it/s]
                                                   

  3%|▎         | 315/11066 [01:09<39:32,  4.53it/s]
  3%|▎         | 316/11066 [01:09<39:08,  4.58it/s]
                                                   

  3%|▎         | 316/11066 [01:09<39:08,  4.58it/s]
  3%|▎         | 317/11066 [01:09<39:05,  4.58it/s]
                                                   

  3%|▎         | 317/11066 [01:09<39:05,  4.58it/s]
  3%|▎         | 318/11066 [01:09<39:14,  4.56it/s]
                                                   

  3%|▎         | 318/11066 [01:09<39:14,  4.56it/s]
  3%|▎         | 319/11066 [01:10<39:23,  4.55it/s]
                                                   

  3%|▎         | 319/11066 [01:10<39:23,  4.55it/s]
  3%|▎         | 320/11066 [01:10<39:14,  4.56it/s]
                                                   

  3%|▎         | 320/11066 [01:10<39:14,  4.56it/s]
  3%|▎         | 321/11066 [01:10<39:19,  4.55it/s]
                                                   

  3%|▎         | 321/11066 [01:10<39:19,  4.55it/s]
  3%|▎         | 322/11066 [01:10<39:07,  4.58it/s]
                                                   

  3%|▎         | 322/11066 [01:10<39:07,  4.58it/s]
  3%|▎         | 323/11066 [01:10<38:44,  4.62it/s]
                                                   

  3%|▎         | 323/11066 [01:10<38:44,  4.62it/s]
  3%|▎         | 324/11066 [01:11<39:00,  4.59it/s]
                                                   

  3%|▎         | 324/11066 [01:11<39:00,  4.59it/s]
  3%|▎         | 325/11066 [01:11<38:49,  4.61it/s]
                                                   

  3%|▎         | 325/11066 [01:11<38:49,  4.61it/s]
  3%|▎         | 326/11066 [01:11<39:11,  4.57it/s]
                                                   

  3%|▎         | 326/11066 [01:11<39:11,  4.57it/s]
  3%|▎         | 327/11066 [01:11<39:20,  4.55it/s]
                                                   

  3%|▎         | 327/11066 [01:11<39:20,  4.55it/s]
  3%|▎         | 328/11066 [01:12<38:41,  4.62it/s]
                                                   

  3%|▎         | 328/11066 [01:12<38:41,  4.62it/s]
  3%|▎         | 329/11066 [01:12<39:00,  4.59it/s]
                                                   

  3%|▎         | 329/11066 [01:12<39:00,  4.59it/s]
  3%|▎         | 330/11066 [01:12<39:12,  4.56it/s]
                                                   

  3%|▎         | 330/11066 [01:12<39:12,  4.56it/s]
  3%|▎         | 331/11066 [01:12<39:22,  4.54it/s]
                                                   

  3%|▎         | 331/11066 [01:12<39:22,  4.54it/s]
  3%|▎         | 332/11066 [01:12<39:27,  4.53it/s]
                                                   

  3%|▎         | 332/11066 [01:12<39:27,  4.53it/s]
  3%|▎         | 333/11066 [01:13<39:35,  4.52it/s]
                                                   

  3%|▎         | 333/11066 [01:13<39:35,  4.52it/s]
  3%|▎         | 334/11066 [01:13<39:39,  4.51it/s]
                                                   

  3%|▎         | 334/11066 [01:13<39:39,  4.51it/s]
  3%|▎         | 335/11066 [01:13<39:42,  4.50it/s]
                                                   

  3%|▎         | 335/11066 [01:13<39:42,  4.50it/s]
  3%|▎         | 336/11066 [01:13<39:43,  4.50it/s]
                                                   

  3%|▎         | 336/11066 [01:13<39:43,  4.50it/s]
  3%|▎         | 337/11066 [01:14<39:43,  4.50it/s]
                                                   

  3%|▎         | 337/11066 [01:14<39:43,  4.50it/s]
  3%|▎         | 338/11066 [01:14<39:44,  4.50it/s]
                                                   
{'loss': 2.2498, 'learning_rate': 2.938731248870414e-05, 'epoch': 0.04}
{'loss': 1.4847, 'learning_rate': 2.938460148201699e-05, 'epoch': 0.04}
{'loss': 1.7983, 'learning_rate': 2.9381890475329838e-05, 'epoch': 0.04}
{'loss': 1.2853, 'learning_rate': 2.937917946864269e-05, 'epoch': 0.04}
{'loss': 1.609, 'learning_rate': 2.9376468461955542e-05, 'epoch': 0.04}
{'loss': 1.8714, 'learning_rate': 2.937375745526839e-05, 'epoch': 0.04}
{'loss': 1.6379, 'learning_rate': 2.9371046448581242e-05, 'epoch': 0.04}
{'loss': 2.4026, 'learning_rate': 2.936833544189409e-05, 'epoch': 0.04}
{'loss': 2.8235, 'learning_rate': 2.9365624435206942e-05, 'epoch': 0.04}
{'loss': 2.344, 'learning_rate': 2.936291342851979e-05, 'epoch': 0.04}
{'loss': 2.1571, 'learning_rate': 2.936020242183264e-05, 'epoch': 0.04}
{'loss': 2.164, 'learning_rate': 2.935749141514549e-05, 'epoch': 0.04}
{'loss': 2.3228, 'learning_rate': 2.9354780408458343e-05, 'epoch': 0.04}
{'loss': 1.7097, 'learning_rate': 2.935206940177119e-05, 'epoch': 0.04}
{'loss': 2.2812, 'learning_rate': 2.9349358395084043e-05, 'epoch': 0.04}
{'loss': 2.5421, 'learning_rate': 2.9346647388396895e-05, 'epoch': 0.04}
{'loss': 2.3694, 'learning_rate': 2.9343936381709743e-05, 'epoch': 0.04}
{'loss': 2.2034, 'learning_rate': 2.9341225375022592e-05, 'epoch': 0.04}
{'loss': 2.028, 'learning_rate': 2.933851436833544e-05, 'epoch': 0.04}
{'loss': 1.5084, 'learning_rate': 2.9335803361648292e-05, 'epoch': 0.04}
{'loss': 1.9911, 'learning_rate': 2.9333092354961144e-05, 'epoch': 0.04}
{'loss': 2.4768, 'learning_rate': 2.9330381348273992e-05, 'epoch': 0.04}
{'loss': 1.7299, 'learning_rate': 2.9327670341586844e-05, 'epoch': 0.04}
{'loss': 2.146, 'learning_rate': 2.9324959334899696e-05, 'epoch': 0.05}
{'loss': 2.3871, 'learning_rate': 2.9322248328212544e-05, 'epoch': 0.05}
{'loss': 2.2222, 'learning_rate': 2.9319537321525393e-05, 'epoch': 0.05}
{'loss': 2.1465, 'learning_rate': 2.9316826314838245e-05, 'epoch': 0.05}
{'loss': 1.4889, 'learning_rate': 2.9314115308151093e-05, 'epoch': 0.05}
{'loss': 2.7812, 'learning_rate': 2.9311404301463945e-05, 'epoch': 0.05}
{'loss': 2.8301, 'learning_rate': 2.9308693294776793e-05, 'epoch': 0.05}
{'loss': 2.0572, 'learning_rate': 2.9305982288089645e-05, 'epoch': 0.05}
{'loss': 1.7446, 'learning_rate': 2.9303271281402497e-05, 'epoch': 0.05}
{'loss': 2.1099, 'learning_rate': 2.9300560274715342e-05, 'epoch': 0.05}
{'loss': 2.8554, 'learning_rate': 2.9297849268028194e-05, 'epoch': 0.05}
{'loss': 2.2578, 'learning_rate': 2.9295138261341046e-05, 'epoch': 0.05}
{'loss': 2.6806, 'learning_rate': 2.9292427254653894e-05, 'epoch': 0.05}
{'loss': 1.7889, 'learning_rate': 2.9289716247966746e-05, 'epoch': 0.05}
{'loss': 1.7681, 'learning_rate': 2.9287005241279598e-05, 'epoch': 0.05}
{'loss': 1.5942, 'learning_rate': 2.9284294234592446e-05, 'epoch': 0.05}
{'loss': 2.119, 'learning_rate': 2.9281583227905298e-05, 'epoch': 0.05}
{'loss': 2.3912, 'learning_rate': 2.9278872221218143e-05, 'epoch': 0.05}
{'loss': 2.0893, 'learning_rate': 2.9276161214530995e-05, 'epoch': 0.05}
{'loss': 2.9637, 'learning_rate': 2.9273450207843847e-05, 'epoch': 0.05}
{'loss': 2.2754, 'learning_rate': 2.9270739201156695e-05, 'epoch': 0.05}
{'loss': 1.6581, 'learning_rate': 2.9268028194469547e-05, 'epoch': 0.05}
{'loss': 2.1254, 'learning_rate': 2.92653171877824e-05, 'epoch': 0.05}
{'loss': 2.1677, 'learning_rate': 2.9262606181095247e-05, 'epoch': 0.05}
{'loss': 2.2016, 'learning_rate': 2.92598951744081e-05, 'epoch': 0.05}
{'loss': 1.4915, 'learning_rate': 2.9257184167720948e-05, 'epoch': 0.05}
{'loss': 1.3906, 'learning_rate': 2.9254473161033796e-05, 'epoch': 0.05}
{'loss': 1.9389, 'learning_rate': 2.9251762154346648e-05, 'epoch': 0.05}
{'loss': 1.6062, 'learning_rate': 2.9249051147659496e-05, 'epoch': 0.05}
{'loss': 1.5853, 'learning_rate': 2.9246340140972348e-05, 'epoch': 0.05}
{'loss': 2.0449, 'learning_rate': 2.92436291342852e-05, 'epoch': 0.05}
{'loss': 1.8977, 'learning_rate': 2.924091812759805e-05, 'epoch': 0.05}
{'loss': 1.6778, 'learning_rate': 2.92382071209109e-05, 'epoch': 0.05}
{'loss': 1.701, 'learning_rate': 2.923549611422375e-05, 'epoch': 0.05}
{'loss': 1.5615, 'learning_rate': 2.9232785107536597e-05, 'epoch': 0.05}
{'loss': 1.7431, 'learning_rate': 2.923007410084945e-05, 'epoch': 0.05}
{'loss': 2.1237, 'learning_rate': 2.92273630941623e-05, 'epoch': 0.05}
{'loss': 2.4777, 'learning_rate': 2.922465208747515e-05, 'epoch': 0.05}
{'loss': 1.7966, 'learning_rate': 2.9221941080788e-05, 'epoch': 0.05}
{'loss': 2.1663, 'learning_rate': 2.921923007410085e-05, 'epoch': 0.05}
{'loss': 2.2379, 'learning_rate': 2.92165190674137e-05, 'epoch': 0.05}
{'loss': 2.0654, 'learning_rate': 2.921380806072655e-05, 'epoch': 0.05}
{'loss': 2.3468, 'learning_rate': 2.9211097054039398e-05, 'epoch': 0.05}
{'loss': 2.0488, 'learning_rate': 2.920838604735225e-05, 'epoch': 0.05}
{'loss': 1.6951, 'learning_rate': 2.9205675040665102e-05, 'epoch': 0.05}
{'loss': 2.3308, 'learning_rate': 2.920296403397795e-05, 'epoch': 0.05}
{'loss': 1.1227, 'learning_rate': 2.9200253027290802e-05, 'epoch': 0.05}
{'loss': 2.2433, 'learning_rate': 2.9197542020603654e-05, 'epoch': 0.05}
{'loss': 1.2546, 'learning_rate': 2.9194831013916502e-05, 'epoch': 0.05}
{'loss': 1.9151, 'learning_rate': 2.919212000722935e-05, 'epoch': 0.05}
{'loss': 1.8822, 'learning_rate': 2.91894090005422e-05, 'epoch': 0.05}
{'loss': 1.9898, 'learning_rate': 2.918669799385505e-05, 'epoch': 0.05}
{'loss': 1.8095, 'learning_rate': 2.9183986987167903e-05, 'epoch': 0.05}
{'loss': 2.2742, 'learning_rate': 2.918127598048075e-05, 'epoch': 0.05}
{'loss': 2.5536, 'learning_rate': 2.9178564973793603e-05, 'epoch': 0.05}
{'loss': 1.6182, 'learning_rate': 2.9175853967106455e-05, 'epoch': 0.05}
{'loss': 2.1913, 'learning_rate': 2.9173142960419304e-05, 'epoch': 0.06}
{'loss': 1.7617, 'learning_rate': 2.9170431953732152e-05, 'epoch': 0.06}
{'loss': 2.4153, 'learning_rate': 2.9167720947045004e-05, 'epoch': 0.06}
{'loss': 1.8653, 'learning_rate': 2.9165009940357852e-05, 'epoch': 0.06}
{'loss': 1.9201, 'learning_rate': 2.9162298933670704e-05, 'epoch': 0.06}
{'loss': 2.4575, 'learning_rate': 2.9159587926983553e-05, 'epoch': 0.06}
{'loss': 1.5466, 'learning_rate': 2.9156876920296404e-05, 'epoch': 0.06}
{'loss': 2.294, 'learning_rate': 2.9154165913609256e-05, 'epoch': 0.06}
{'loss': 1.7047, 'learning_rate': 2.9151454906922105e-05, 'epoch': 0.06}
{'loss': 1.9904, 'learning_rate': 2.9148743900234953e-05, 'epoch': 0.06}
{'loss': 1.8362, 'learning_rate': 2.9146032893547805e-05, 'epoch': 0.06}
{'loss': 2.3346, 'learning_rate': 2.9143321886860653e-05, 'epoch': 0.06}
{'loss': 1.1031, 'learning_rate': 2.9140610880173505e-05, 'epoch': 0.06}
{'loss': 1.9463, 'learning_rate': 2.9137899873486357e-05, 'epoch': 0.06}
{'loss': 1.5553, 'learning_rate': 2.9135188866799205e-05, 'epoch': 0.06}
{'loss': 1.2304, 'learning_rate': 2.9132477860112057e-05, 'epoch': 0.06}
{'loss': 1.8553, 'learning_rate': 2.9129766853424906e-05, 'epoch': 0.06}
{'loss': 1.5508, 'learning_rate': 2.9127055846737754e-05, 'epoch': 0.06}
{'loss': 1.7433, 'learning_rate': 2.9124344840050606e-05, 'epoch': 0.06}
{'loss': 2.0361, 'learning_rate': 2.9121633833363454e-05, 'epoch': 0.06}
{'loss': 1.5907, 'learning_rate': 2.9118922826676306e-05, 'epoch': 0.06}
{'loss': 1.7085, 'learning_rate': 2.9116211819989158e-05, 'epoch': 0.06}
{'loss': 1.4822, 'learning_rate': 2.9113500813302007e-05, 'epoch': 0.06}
{'loss': 1.7785, 'learning_rate': 2.911078980661486e-05, 'epoch': 0.06}
{'loss': 1.397, 'learning_rate': 2.910807879992771e-05, 'epoch': 0.06}
{'loss': 1.6978, 'learning_rate': 2.9105367793240555e-05, 'epoch': 0.06}
{'loss': 2.1525, 'learning_rate': 2.9102656786553407e-05, 'epoch': 0.06}
{'loss': 1.7079, 'learning_rate': 2.9099945779866256e-05, 'epoch': 0.06}
{'loss': 1.6592, 'learning_rate': 2.9097234773179107e-05, 'epoch': 0.06}
{'loss': 1.8333, 'learning_rate': 2.909452376649196e-05, 'epoch': 0.06}
{'loss': 2.0608, 'learning_rate': 2.9091812759804808e-05, 'epoch': 0.06}
{'loss': 1.3938, 'learning_rate': 2.908910175311766e-05, 'epoch': 0.06}
{'loss': 1.8675, 'learning_rate': 2.908639074643051e-05, 'epoch': 0.06}

  3%|▎         | 338/11066 [01:14<39:44,  4.50it/s]
  3%|▎         | 339/11066 [01:14<39:44,  4.50it/s]
                                                   

  3%|▎         | 339/11066 [01:14<39:44,  4.50it/s]
  3%|▎         | 340/11066 [01:14<39:43,  4.50it/s]
                                                   

  3%|▎         | 340/11066 [01:14<39:43,  4.50it/s]
  3%|▎         | 341/11066 [01:14<39:43,  4.50it/s]
                                                   

  3%|▎         | 341/11066 [01:14<39:43,  4.50it/s]
  3%|▎         | 342/11066 [01:15<39:45,  4.50it/s]
                                                   

  3%|▎         | 342/11066 [01:15<39:45,  4.50it/s]
  3%|▎         | 343/11066 [01:15<39:46,  4.49it/s]
                                                   

  3%|▎         | 343/11066 [01:15<39:46,  4.49it/s]
  3%|▎         | 344/11066 [01:15<39:43,  4.50it/s]
                                                   

  3%|▎         | 344/11066 [01:15<39:43,  4.50it/s]
  3%|▎         | 345/11066 [01:15<39:41,  4.50it/s]
                                                   

  3%|▎         | 345/11066 [01:15<39:41,  4.50it/s]
  3%|▎         | 346/11066 [01:16<39:40,  4.50it/s]
                                                   

  3%|▎         | 346/11066 [01:16<39:40,  4.50it/s]
  3%|▎         | 347/11066 [01:16<39:41,  4.50it/s]
                                                   

  3%|▎         | 347/11066 [01:16<39:41,  4.50it/s]
  3%|▎         | 348/11066 [01:16<39:42,  4.50it/s]
                                                   

  3%|▎         | 348/11066 [01:16<39:42,  4.50it/s]
  3%|▎         | 349/11066 [01:16<39:41,  4.50it/s]
                                                   

  3%|▎         | 349/11066 [01:16<39:41,  4.50it/s]
  3%|▎         | 350/11066 [01:16<39:21,  4.54it/s]
                                                   

  3%|▎         | 350/11066 [01:16<39:21,  4.54it/s]
  3%|▎         | 351/11066 [01:17<39:01,  4.58it/s]
                                                   

  3%|▎         | 351/11066 [01:17<39:01,  4.58it/s]
  3%|▎         | 352/11066 [01:17<38:45,  4.61it/s]
                                                   

  3%|▎         | 352/11066 [01:17<38:45,  4.61it/s]
  3%|▎         | 353/11066 [01:17<39:01,  4.58it/s]
                                                   

  3%|▎         | 353/11066 [01:17<39:01,  4.58it/s]
  3%|▎         | 354/11066 [01:17<39:15,  4.55it/s]
                                                   

  3%|▎         | 354/11066 [01:17<39:15,  4.55it/s]
  3%|▎         | 355/11066 [01:18<39:05,  4.57it/s]
                                                   

  3%|▎         | 355/11066 [01:18<39:05,  4.57it/s]
  3%|▎         | 356/11066 [01:18<39:14,  4.55it/s]
                                                   

  3%|▎         | 356/11066 [01:18<39:14,  4.55it/s]
  3%|▎         | 357/11066 [01:18<39:18,  4.54it/s]
                                                   

  3%|▎         | 357/11066 [01:18<39:18,  4.54it/s]
  3%|▎         | 358/11066 [01:18<39:22,  4.53it/s]
                                                   

  3%|▎         | 358/11066 [01:18<39:22,  4.53it/s]
  3%|▎         | 359/11066 [01:18<39:10,  4.56it/s]
                                                   

  3%|▎         | 359/11066 [01:18<39:10,  4.56it/s]
  3%|▎         | 360/11066 [01:19<39:24,  4.53it/s]
                                                   

  3%|▎         | 360/11066 [01:19<39:24,  4.53it/s]
  3%|▎         | 361/11066 [01:19<39:29,  4.52it/s]
                                                   

  3%|▎         | 361/11066 [01:19<39:29,  4.52it/s]
  3%|▎         | 362/11066 [01:19<39:13,  4.55it/s]
                                                   

  3%|▎         | 362/11066 [01:19<39:13,  4.55it/s]
  3%|▎         | 363/11066 [01:19<39:15,  4.54it/s]
                                                   

  3%|▎         | 363/11066 [01:19<39:15,  4.54it/s]
  3%|▎         | 364/11066 [01:20<39:18,  4.54it/s]
                                                   

  3%|▎         | 364/11066 [01:20<39:18,  4.54it/s]
  3%|▎         | 365/11066 [01:20<39:23,  4.53it/s]
                                                   

  3%|▎         | 365/11066 [01:20<39:23,  4.53it/s]
  3%|▎         | 366/11066 [01:20<39:10,  4.55it/s]
                                                   

  3%|▎         | 366/11066 [01:20<39:10,  4.55it/s]
  3%|▎         | 367/11066 [01:20<38:45,  4.60it/s]
                                                   

  3%|▎         | 367/11066 [01:20<38:45,  4.60it/s]
  3%|▎         | 368/11066 [01:20<38:56,  4.58it/s]
                                                   

  3%|▎         | 368/11066 [01:20<38:56,  4.58it/s]
  3%|▎         | 369/11066 [01:21<38:45,  4.60it/s]
                                                   

  3%|▎         | 369/11066 [01:21<38:45,  4.60it/s]
  3%|▎         | 370/11066 [01:21<38:45,  4.60it/s]
                                                   

  3%|▎         | 370/11066 [01:21<38:45,  4.60it/s]
  3%|▎         | 371/11066 [01:21<39:00,  4.57it/s]
                                                   

  3%|▎         | 371/11066 [01:21<39:00,  4.57it/s]
  3%|▎         | 372/11066 [01:21<39:08,  4.55it/s]
                                                   

  3%|▎         | 372/11066 [01:21<39:08,  4.55it/s]
  3%|▎         | 373/11066 [01:22<39:15,  4.54it/s]
                                                   

  3%|▎         | 373/11066 [01:22<39:15,  4.54it/s]
  3%|▎         | 374/11066 [01:22<39:19,  4.53it/s]
                                                   

  3%|▎         | 374/11066 [01:22<39:19,  4.53it/s]
  3%|▎         | 375/11066 [01:22<39:23,  4.52it/s]
                                                   

  3%|▎         | 375/11066 [01:22<39:23,  4.52it/s]
  3%|▎         | 376/11066 [01:22<39:25,  4.52it/s]
                                                   

  3%|▎         | 376/11066 [01:22<39:25,  4.52it/s]
  3%|▎         | 377/11066 [01:22<39:28,  4.51it/s]
                                                   

  3%|▎         | 377/11066 [01:22<39:28,  4.51it/s]
  3%|▎         | 378/11066 [01:23<39:30,  4.51it/s]
                                                   

  3%|▎         | 378/11066 [01:23<39:30,  4.51it/s]
  3%|▎         | 379/11066 [01:23<39:30,  4.51it/s]
                                                   

  3%|▎         | 379/11066 [01:23<39:30,  4.51it/s]
  3%|▎         | 380/11066 [01:23<39:32,  4.50it/s]
                                                   

  3%|▎         | 380/11066 [01:23<39:32,  4.50it/s]
  3%|▎         | 381/11066 [01:23<39:32,  4.50it/s]
                                                   

  3%|▎         | 381/11066 [01:23<39:32,  4.50it/s]
  3%|▎         | 382/11066 [01:24<39:31,  4.51it/s]
                                                   

  3%|▎         | 382/11066 [01:24<39:31,  4.51it/s]
  3%|▎         | 383/11066 [01:24<39:32,  4.50it/s]
                                                   

  3%|▎         | 383/11066 [01:24<39:32,  4.50it/s]
  3%|▎         | 384/11066 [01:24<39:33,  4.50it/s]
                                                   

  3%|▎         | 384/11066 [01:24<39:33,  4.50it/s]
  3%|▎         | 385/11066 [01:24<39:12,  4.54it/s]
                                                   

  3%|▎         | 385/11066 [01:24<39:12,  4.54it/s]
  3%|▎         | 386/11066 [01:24<39:13,  4.54it/s]
                                                   

  3%|▎         | 386/11066 [01:24<39:13,  4.54it/s]
  3%|▎         | 387/11066 [01:25<39:17,  4.53it/s]
                                                   

  3%|▎         | 387/11066 [01:25<39:17,  4.53it/s]
  4%|▎         | 388/11066 [01:25<39:00,  4.56it/s]
                                                   

  4%|▎         | 388/11066 [01:25<39:00,  4.56it/s]
  4%|▎         | 389/11066 [01:25<38:48,  4.59it/s]
                                                   

  4%|▎         | 389/11066 [01:25<38:48,  4.59it/s]
  4%|▎         | 390/11066 [01:25<38:54,  4.57it/s]
                                                   

  4%|▎         | 390/11066 [01:25<38:54,  4.57it/s]
  4%|▎         | 391/11066 [01:25<39:14,  4.53it/s]
                                                   

  4%|▎         | 391/11066 [01:25<39:14,  4.53it/s]
  4%|▎         | 392/11066 [01:26<39:20,  4.52it/s]
                                                   

  4%|▎         | 392/11066 [01:26<39:20,  4.52it/s]
  4%|▎         | 393/11066 [01:26<39:27,  4.51it/s]
                                                   

  4%|▎         | 393/11066 [01:26<39:27,  4.51it/s]
  4%|▎         | 394/11066 [01:26<39:08,  4.55it/s]
                                                   

  4%|▎         | 394/11066 [01:26<39:08,  4.55it/s]
  4%|▎         | 395/11066 [01:26<38:36,  4.61it/s]
                                                   

  4%|▎         | 395/11066 [01:26<38:36,  4.61it/s]
  4%|▎         | 396/11066 [01:27<38:49,  4.58it/s]
                                                   

  4%|▎         | 396/11066 [01:27<38:49,  4.58it/s]
  4%|▎         | 397/11066 [01:27<39:01,  4.56it/s]
                                                   

  4%|▎         | 397/11066 [01:27<39:01,  4.56it/s]
  4%|▎         | 398/11066 [01:27<39:07,  4.54it/s]
                                                   

  4%|▎         | 398/11066 [01:27<39:07,  4.54it/s]
  4%|▎         | 399/11066 [01:27<38:54,  4.57it/s]
                                                   

  4%|▎         | 399/11066 [01:27<38:54,  4.57it/s]
  4%|▎         | 400/11066 [01:27<39:18,  4.52it/s]
                                                   

  4%|▎         | 400/11066 [01:27<39:18,  4.52it/s]
  4%|▎         | 401/11066 [01:28<39:40,  4.48it/s]
                                                   

  4%|▎         | 401/11066 [01:28<39:40,  4.48it/s]
  4%|▎         | 402/11066 [01:28<39:38,  4.48it/s]
                                                   

  4%|▎         | 402/11066 [01:28<39:38,  4.48it/s]
  4%|▎         | 403/11066 [01:28<39:36,  4.49it/s]
                                                   

  4%|▎         | 403/11066 [01:28<39:36,  4.49it/s]
  4%|▎         | 404/11066 [01:28<39:36,  4.49it/s]
                                                   

  4%|▎         | 404/11066 [01:28<39:36,  4.49it/s]
  4%|▎         | 405/11066 [01:29<39:41,  4.48it/s]
                                                   

  4%|▎         | 405/11066 [01:29<39:41,  4.48it/s]
  4%|▎         | 406/11066 [01:29<39:38,  4.48it/s]
                                                   

  4%|▎         | 406/11066 [01:29<39:38,  4.48it/s]
  4%|▎         | 407/11066 [01:29<39:35,  4.49it/s]
                                                   

  4%|▎         | 407/11066 [01:29<39:35,  4.49it/s]
  4%|▎         | 408/11066 [01:29<39:33,  4.49it/s]
                                                   

  4%|▎         | 408/11066 [01:29<39:33,  4.49it/s]
  4%|▎         | 409/11066 [01:29<39:31,  4.49it/s]
                                                   

  4%|▎         | 409/11066 [01:29<39:31,  4.49it/s]
  4%|▎         | 410/11066 [01:30<39:28,  4.50it/s]
                                                   

  4%|▎         | 410/11066 [01:30<39:28,  4.50it/s]
  4%|▎         | 411/11066 [01:30<39:32,  4.49it/s]
                                                   

  4%|▎         | 411/11066 [01:30<39:32,  4.49it/s]
  4%|▎         | 412/11066 [01:30<39:31,  4.49it/s]
                                                   

  4%|▎         | 412/11066 [01:30<39:31,  4.49it/s]
  4%|▎         | 413/11066 [01:30<39:28,  4.50it/s]
                                                   

  4%|▎         | 413/11066 [01:30<39:28,  4.50it/s]
  4%|▎         | 414/11066 [01:31<39:28,  4.50it/s]
                                                   

  4%|▎         | 414/11066 [01:31<39:28,  4.50it/s]
  4%|▍         | 415/11066 [01:31<39:27,  4.50it/s]
                                                   

  4%|▍         | 415/11066 [01:31<39:27,  4.50it/s]
  4%|▍         | 416/11066 [01:31<39:30,  4.49it/s]
                                                   

  4%|▍         | 416/11066 [01:31<39:30,  4.49it/s]
  4%|▍         | 417/11066 [01:31<39:26,  4.50it/s]
                                                   

  4%|▍         | 417/11066 [01:31<39:26,  4.50it/s]
  4%|▍         | 418/11066 [01:31<39:27,  4.50it/s]
                                                   

  4%|▍         | 418/11066 [01:31<39:27,  4.50it/s]
  4%|▍         | 419/11066 [01:32<39:30,  4.49it/s]
                                                   

  4%|▍         | 419/11066 [01:32<39:30,  4.49it/s]
  4%|▍         | 420/11066 [01:32<39:25,  4.50it/s]
                                                   

  4%|▍         | 420/11066 [01:32<39:25,  4.50it/s]
  4%|▍         | 421/11066 [01:32<39:24,  4.50it/s]
                                                   

  4%|▍         | 421/11066 [01:32<39:24,  4.50it/s]
  4%|▍         | 422/11066 [01:32<39:23,  4.50it/s]
                                                   

  4%|▍         | 422/11066 [01:32<39:23,  4.50it/s]
  4%|▍         | 423/11066 [01:33<39:26,  4.50it/s]
                                                   

  4%|▍         | 423/11066 [01:33<39:26,  4.50it/s]
  4%|▍         | 424/11066 [01:33<39:23,  4.50it/s]
                                                   

  4%|▍         | 424/11066 [01:33<39:23,  4.50it/s]
  4%|▍         | 425/11066 [01:33<39:06,  4.54it/s]
                                                   

  4%|▍         | 425/11066 [01:33<39:06,  4.54it/s]
  4%|▍         | 426/11066 [01:33<39:04,  4.54it/s]
                                                   

  4%|▍         | 426/11066 [01:33<39:04,  4.54it/s]
  4%|▍         | 427/11066 [01:33<39:05,  4.54it/s]
                                                   

  4%|▍         | 427/11066 [01:33<39:05,  4.54it/s]
  4%|▍         | 428/11066 [01:34<38:40,  4.58it/s]
                                                   

  4%|▍         | 428/11066 [01:34<38:40,  4.58it/s]
  4%|▍         | 429/11066 [01:34<38:36,  4.59it/s]
                                                   

  4%|▍         | 429/11066 [01:34<38:36,  4.59it/s]
  4%|▍         | 430/11066 [01:34<38:33,  4.60it/s]
                                                   

  4%|▍         | 430/11066 [01:34<38:33,  4.60it/s]
  4%|▍         | 431/11066 [01:34<38:46,  4.57it/s]
                                                   

  4%|▍         | 431/11066 [01:34<38:46,  4.57it/s]
  4%|▍         | 432/11066 [01:35<38:40,  4.58it/s]
                                                   

  4%|▍         | 432/11066 [01:35<38:40,  4.58it/s]
  4%|▍         | 433/11066 [01:35<38:49,  4.56it/s]
                                                   

  4%|▍         | 433/11066 [01:35<38:49,  4.56it/s]
  4%|▍         | 434/11066 [01:35<38:37,  4.59it/s]
                                                   

  4%|▍         | 434/11066 [01:35<38:37,  4.59it/s]
  4%|▍         | 435/11066 [01:35<38:43,  4.58it/s]
                                                   

  4%|▍         | 435/11066 [01:35<38:43,  4.58it/s]
  4%|▍         | 436/11066 [01:35<38:49,  4.56it/s]
                                                   

  4%|▍         | 436/11066 [01:35<38:49,  4.56it/s]
  4%|▍         | 437/11066 [01:36<38:59,  4.54it/s]
                                                   

  4%|▍         | 437/11066 [01:36<38:59,  4.54it/s]
  4%|▍         | 438/11066 [01:36<39:05,  4.53it/s]
                                                   

  4%|▍         | 438/11066 [01:36<39:05,  4.53it/s]
  4%|▍         | 439/11066 [01:36<39:10,  4.52it/s]
                                                   

  4%|▍         | 439/11066 [01:36<39:10,  4.52it/s]
  4%|▍         | 440/11066 [01:36<39:11,  4.52it/s]
                                                   

  4%|▍         | 440/11066 [01:36<39:11,  4.52it/s]
  4%|▍         | 441/11066 [01:37<39:12,  4.52it/s]
                                                   

  4%|▍         | 441/11066 [01:37<39:12,  4.52it/s]
  4%|▍         | 442/11066 [01:37<39:14,  4.51it/s]
                                                   

  4%|▍         | 442/11066 [01:37<39:14,  4.51it/s]
  4%|▍         | 443/11066 [01:37<38:57,  4.54it/s]
                                                   

  4%|▍         | 443/11066 [01:37<38:57,  4.54it/s]
  4%|▍         | 444/11066 [01:37<38:59,  4.54it/s]
                                                   

  4%|▍         | 444/11066 [01:37<38:59,  4.54it/s]
  4%|▍         | 445/11066 [01:37<39:03,  4.53it/s]
                                                   

  4%|▍         | 445/11066 [01:37<39:03,  4.53it/s]
  4%|▍         | 446/11066 [01:38<39:05,  4.53it/s]
                                                   

  4%|▍         | 446/11066 [01:38<39:05,  4.53it/s]
  4%|▍         | 447/11066 [01:38<39:11,  4.52it/s]
                                                   

  4%|▍         | 447/11066 [01:38<39:11,  4.52it/s]
  4%|▍         | 448/11066 [01:38<39:09,  4.52it/s]
                                                   

  4%|▍         | 448/11066 [01:38<39:09,  4.52it/s]
  4%|▍         | 449/11066 [01:38<39:13,  4.51it/s]
                                                   

  4%|▍         | 449/11066 [01:38<39:13,  4.51it/s]
  4%|▍         | 450/11066 [01:39<39:17,  4.50it/s]
                                                   
{'loss': 1.9688, 'learning_rate': 2.9083679739743356e-05, 'epoch': 0.06}
{'loss': 2.0622, 'learning_rate': 2.9080968733056208e-05, 'epoch': 0.06}
{'loss': 2.5251, 'learning_rate': 2.907825772636906e-05, 'epoch': 0.06}
{'loss': 1.8319, 'learning_rate': 2.907554671968191e-05, 'epoch': 0.06}
{'loss': 2.5061, 'learning_rate': 2.907283571299476e-05, 'epoch': 0.06}
{'loss': 2.1739, 'learning_rate': 2.907012470630761e-05, 'epoch': 0.06}
{'loss': 2.056, 'learning_rate': 2.906741369962046e-05, 'epoch': 0.06}
{'loss': 1.8152, 'learning_rate': 2.9064702692933312e-05, 'epoch': 0.06}
{'loss': 1.326, 'learning_rate': 2.9061991686246157e-05, 'epoch': 0.06}
{'loss': 1.2062, 'learning_rate': 2.905928067955901e-05, 'epoch': 0.06}
{'loss': 2.1967, 'learning_rate': 2.905656967287186e-05, 'epoch': 0.06}
{'loss': 1.3308, 'learning_rate': 2.905385866618471e-05, 'epoch': 0.06}
{'loss': 1.5806, 'learning_rate': 2.905114765949756e-05, 'epoch': 0.06}
{'loss': 2.0727, 'learning_rate': 2.9048436652810413e-05, 'epoch': 0.06}
{'loss': 1.5464, 'learning_rate': 2.904572564612326e-05, 'epoch': 0.06}
{'loss': 1.4285, 'learning_rate': 2.9043014639436113e-05, 'epoch': 0.06}
{'loss': 1.7527, 'learning_rate': 2.9040303632748962e-05, 'epoch': 0.06}
{'loss': 1.3718, 'learning_rate': 2.903759262606181e-05, 'epoch': 0.06}
{'loss': 1.4609, 'learning_rate': 2.9034881619374662e-05, 'epoch': 0.06}
{'loss': 1.8429, 'learning_rate': 2.903217061268751e-05, 'epoch': 0.06}
{'loss': 1.5308, 'learning_rate': 2.9029459606000362e-05, 'epoch': 0.06}
{'loss': 1.9681, 'learning_rate': 2.9026748599313214e-05, 'epoch': 0.06}
{'loss': 2.3457, 'learning_rate': 2.9024037592626063e-05, 'epoch': 0.07}
{'loss': 2.3322, 'learning_rate': 2.9021326585938914e-05, 'epoch': 0.07}
{'loss': 2.255, 'learning_rate': 2.9018615579251763e-05, 'epoch': 0.07}
{'loss': 2.3572, 'learning_rate': 2.901590457256461e-05, 'epoch': 0.07}
{'loss': 2.0241, 'learning_rate': 2.9013193565877463e-05, 'epoch': 0.07}
{'loss': 1.5013, 'learning_rate': 2.9010482559190315e-05, 'epoch': 0.07}
{'loss': 1.7231, 'learning_rate': 2.9007771552503163e-05, 'epoch': 0.07}
{'loss': 1.5714, 'learning_rate': 2.9005060545816015e-05, 'epoch': 0.07}
{'loss': 2.3282, 'learning_rate': 2.9002349539128864e-05, 'epoch': 0.07}
{'loss': 1.3672, 'learning_rate': 2.8999638532441716e-05, 'epoch': 0.07}
{'loss': 2.4871, 'learning_rate': 2.8996927525754564e-05, 'epoch': 0.07}
{'loss': 1.6951, 'learning_rate': 2.8994216519067412e-05, 'epoch': 0.07}
{'loss': 1.8999, 'learning_rate': 2.8991505512380264e-05, 'epoch': 0.07}
{'loss': 1.9182, 'learning_rate': 2.8988794505693116e-05, 'epoch': 0.07}
{'loss': 1.81, 'learning_rate': 2.8986083499005965e-05, 'epoch': 0.07}
{'loss': 1.4093, 'learning_rate': 2.8983372492318816e-05, 'epoch': 0.07}
{'loss': 1.9885, 'learning_rate': 2.8980661485631668e-05, 'epoch': 0.07}
{'loss': 1.758, 'learning_rate': 2.8977950478944517e-05, 'epoch': 0.07}
{'loss': 1.2293, 'learning_rate': 2.8975239472257365e-05, 'epoch': 0.07}
{'loss': 1.6351, 'learning_rate': 2.8972528465570214e-05, 'epoch': 0.07}
{'loss': 1.2605, 'learning_rate': 2.8969817458883065e-05, 'epoch': 0.07}
{'loss': 1.4166, 'learning_rate': 2.8967106452195917e-05, 'epoch': 0.07}
{'loss': 1.7398, 'learning_rate': 2.8964395445508766e-05, 'epoch': 0.07}
{'loss': 1.7061, 'learning_rate': 2.8961684438821617e-05, 'epoch': 0.07}
{'loss': 2.4242, 'learning_rate': 2.895897343213447e-05, 'epoch': 0.07}
{'loss': 1.5752, 'learning_rate': 2.8956262425447318e-05, 'epoch': 0.07}
{'loss': 1.8631, 'learning_rate': 2.8953551418760166e-05, 'epoch': 0.07}
{'loss': 2.061, 'learning_rate': 2.8950840412073018e-05, 'epoch': 0.07}
{'loss': 1.7565, 'learning_rate': 2.8948129405385866e-05, 'epoch': 0.07}
{'loss': 1.0947, 'learning_rate': 2.8945418398698718e-05, 'epoch': 0.07}
{'loss': 1.8912, 'learning_rate': 2.8942707392011567e-05, 'epoch': 0.07}
{'loss': 1.8797, 'learning_rate': 2.893999638532442e-05, 'epoch': 0.07}
{'loss': 1.5819, 'learning_rate': 2.893728537863727e-05, 'epoch': 0.07}
{'loss': 2.0879, 'learning_rate': 2.8934574371950115e-05, 'epoch': 0.07}
{'loss': 1.4488, 'learning_rate': 2.8931863365262967e-05, 'epoch': 0.07}
{'loss': 1.4853, 'learning_rate': 2.892915235857582e-05, 'epoch': 0.07}
{'loss': 1.2138, 'learning_rate': 2.8926441351888667e-05, 'epoch': 0.07}
{'loss': 1.1239, 'learning_rate': 2.892373034520152e-05, 'epoch': 0.07}
{'loss': 1.6596, 'learning_rate': 2.892101933851437e-05, 'epoch': 0.07}
{'loss': 1.1356, 'learning_rate': 2.891830833182722e-05, 'epoch': 0.07}
{'loss': 1.6265, 'learning_rate': 2.891559732514007e-05, 'epoch': 0.07}
{'loss': 1.2724, 'learning_rate': 2.8912886318452916e-05, 'epoch': 0.07}
{'loss': 1.2583, 'learning_rate': 2.8910175311765768e-05, 'epoch': 0.07}
{'loss': 0.9703, 'learning_rate': 2.890746430507862e-05, 'epoch': 0.07}
{'loss': 1.8156, 'learning_rate': 2.890475329839147e-05, 'epoch': 0.07}
{'loss': 1.693, 'learning_rate': 2.890204229170432e-05, 'epoch': 0.07}
{'loss': 1.7402, 'learning_rate': 2.8899331285017172e-05, 'epoch': 0.07}
{'loss': 1.2778, 'learning_rate': 2.889662027833002e-05, 'epoch': 0.07}
{'loss': 1.2939, 'learning_rate': 2.8893909271642872e-05, 'epoch': 0.07}
{'loss': 2.0742, 'learning_rate': 2.889119826495572e-05, 'epoch': 0.07}
{'loss': 1.941, 'learning_rate': 2.888848725826857e-05, 'epoch': 0.07}
{'loss': 1.2712, 'learning_rate': 2.888577625158142e-05, 'epoch': 0.07}
{'loss': 2.4306, 'learning_rate': 2.888306524489427e-05, 'epoch': 0.07}
{'loss': 1.7812, 'learning_rate': 2.888035423820712e-05, 'epoch': 0.07}
{'loss': 1.4988, 'learning_rate': 2.8877643231519973e-05, 'epoch': 0.07}
{'loss': 1.4322, 'learning_rate': 2.8874932224832822e-05, 'epoch': 0.08}
{'loss': 1.5044, 'learning_rate': 2.8872221218145674e-05, 'epoch': 0.08}
{'loss': 2.2452, 'learning_rate': 2.8869510211458522e-05, 'epoch': 0.08}
{'loss': 1.9538, 'learning_rate': 2.886679920477137e-05, 'epoch': 0.08}
{'loss': 1.0781, 'learning_rate': 2.8864088198084222e-05, 'epoch': 0.08}
{'loss': 1.5358, 'learning_rate': 2.8861377191397074e-05, 'epoch': 0.08}
{'loss': 1.9906, 'learning_rate': 2.8858666184709923e-05, 'epoch': 0.08}
{'loss': 1.7883, 'learning_rate': 2.8855955178022774e-05, 'epoch': 0.08}
{'loss': 1.5432, 'learning_rate': 2.8853244171335623e-05, 'epoch': 0.08}
{'loss': 1.7593, 'learning_rate': 2.8850533164648475e-05, 'epoch': 0.08}
{'loss': 1.4443, 'learning_rate': 2.8847822157961323e-05, 'epoch': 0.08}
{'loss': 1.2129, 'learning_rate': 2.884511115127417e-05, 'epoch': 0.08}
{'loss': 1.4344, 'learning_rate': 2.8842400144587023e-05, 'epoch': 0.08}
{'loss': 2.0925, 'learning_rate': 2.8839689137899875e-05, 'epoch': 0.08}
{'loss': 1.3983, 'learning_rate': 2.8836978131212724e-05, 'epoch': 0.08}
{'loss': 2.1201, 'learning_rate': 2.8834267124525575e-05, 'epoch': 0.08}
{'loss': 1.7714, 'learning_rate': 2.8831556117838427e-05, 'epoch': 0.08}
{'loss': 2.0383, 'learning_rate': 2.8828845111151276e-05, 'epoch': 0.08}
{'loss': 1.355, 'learning_rate': 2.8826134104464124e-05, 'epoch': 0.08}
{'loss': 1.3772, 'learning_rate': 2.8823423097776973e-05, 'epoch': 0.08}
{'loss': 1.3664, 'learning_rate': 2.8820712091089824e-05, 'epoch': 0.08}
{'loss': 1.3119, 'learning_rate': 2.8818001084402676e-05, 'epoch': 0.08}
{'loss': 2.7856, 'learning_rate': 2.8815290077715525e-05, 'epoch': 0.08}
{'loss': 2.0245, 'learning_rate': 2.8812579071028377e-05, 'epoch': 0.08}
{'loss': 2.2244, 'learning_rate': 2.880986806434123e-05, 'epoch': 0.08}
{'loss': 1.4509, 'learning_rate': 2.8807157057654077e-05, 'epoch': 0.08}
{'loss': 1.6023, 'learning_rate': 2.8804446050966925e-05, 'epoch': 0.08}
{'loss': 1.123, 'learning_rate': 2.8801735044279777e-05, 'epoch': 0.08}
{'loss': 1.7081, 'learning_rate': 2.8799024037592625e-05, 'epoch': 0.08}
{'loss': 1.4622, 'learning_rate': 2.8796313030905477e-05, 'epoch': 0.08}
{'loss': 1.9179, 'learning_rate': 2.8793602024218326e-05, 'epoch': 0.08}
{'loss': 1.2908, 'learning_rate': 2.8790891017531178e-05, 'epoch': 0.08}
{'loss': 1.2704, 'learning_rate': 2.878818001084403e-05, 'epoch': 0.08}
{'loss': 1.8802, 'learning_rate': 2.8785469004156878e-05, 'epoch': 0.08}
{'loss': 2.3381, 'learning_rate': 2.8782757997469726e-05, 'epoch': 0.08}

  4%|▍         | 450/11066 [01:39<39:17,  4.50it/s]
  4%|▍         | 451/11066 [01:39<39:18,  4.50it/s]
                                                   

  4%|▍         | 451/11066 [01:39<39:18,  4.50it/s]
  4%|▍         | 452/11066 [01:39<39:17,  4.50it/s]
                                                   

  4%|▍         | 452/11066 [01:39<39:17,  4.50it/s]
  4%|▍         | 453/11066 [01:39<39:18,  4.50it/s]
                                                   

  4%|▍         | 453/11066 [01:39<39:18,  4.50it/s]
  4%|▍         | 454/11066 [01:39<39:18,  4.50it/s]
                                                   

  4%|▍         | 454/11066 [01:39<39:18,  4.50it/s]
  4%|▍         | 455/11066 [01:40<39:18,  4.50it/s]
                                                   

  4%|▍         | 455/11066 [01:40<39:18,  4.50it/s]
  4%|▍         | 456/11066 [01:40<39:19,  4.50it/s]
                                                   

  4%|▍         | 456/11066 [01:40<39:19,  4.50it/s]
  4%|▍         | 457/11066 [01:40<38:53,  4.55it/s]
                                                   

  4%|▍         | 457/11066 [01:40<38:53,  4.55it/s]
  4%|▍         | 458/11066 [01:40<38:27,  4.60it/s]
                                                   

  4%|▍         | 458/11066 [01:40<38:27,  4.60it/s]
  4%|▍         | 459/11066 [01:41<38:48,  4.56it/s]
                                                   

  4%|▍         | 459/11066 [01:41<38:48,  4.56it/s]
  4%|▍         | 460/11066 [01:41<38:33,  4.58it/s]
                                                   

  4%|▍         | 460/11066 [01:41<38:33,  4.58it/s]
  4%|▍         | 461/11066 [01:41<37:59,  4.65it/s]
                                                   

  4%|▍         | 461/11066 [01:41<37:59,  4.65it/s]
  4%|▍         | 462/11066 [01:41<37:52,  4.67it/s]
                                                   

  4%|▍         | 462/11066 [01:41<37:52,  4.67it/s]
  4%|▍         | 463/11066 [01:41<37:44,  4.68it/s]
                                                   

  4%|▍         | 463/11066 [01:41<37:44,  4.68it/s]
  4%|▍         | 464/11066 [01:42<37:50,  4.67it/s]
                                                   

  4%|▍         | 464/11066 [01:42<37:50,  4.67it/s]
  4%|▍         | 465/11066 [01:42<37:38,  4.69it/s]
                                                   

  4%|▍         | 465/11066 [01:42<37:38,  4.69it/s]
  4%|▍         | 466/11066 [01:42<37:44,  4.68it/s]
                                                   

  4%|▍         | 466/11066 [01:42<37:44,  4.68it/s]
  4%|▍         | 467/11066 [01:42<37:26,  4.72it/s]
                                                   

  4%|▍         | 467/11066 [01:42<37:26,  4.72it/s]
  4%|▍         | 468/11066 [01:42<37:26,  4.72it/s]
                                                   

  4%|▍         | 468/11066 [01:42<37:26,  4.72it/s]
  4%|▍         | 469/11066 [01:43<37:59,  4.65it/s]
                                                   

  4%|▍         | 469/11066 [01:43<37:59,  4.65it/s]
  4%|▍         | 470/11066 [01:43<38:24,  4.60it/s]
                                                   

  4%|▍         | 470/11066 [01:43<38:24,  4.60it/s]
  4%|▍         | 471/11066 [01:43<38:38,  4.57it/s]
                                                   

  4%|▍         | 471/11066 [01:43<38:38,  4.57it/s]
  4%|▍         | 472/11066 [01:43<38:52,  4.54it/s]
                                                   

  4%|▍         | 472/11066 [01:43<38:52,  4.54it/s]
  4%|▍         | 473/11066 [01:44<38:59,  4.53it/s]
                                                   

  4%|▍         | 473/11066 [01:44<38:59,  4.53it/s]
  4%|▍         | 474/11066 [01:44<39:04,  4.52it/s]
                                                   

  4%|▍         | 474/11066 [01:44<39:04,  4.52it/s]
  4%|▍         | 475/11066 [01:44<39:10,  4.51it/s]
                                                   

  4%|▍         | 475/11066 [01:44<39:10,  4.51it/s]
  4%|▍         | 476/11066 [01:44<38:30,  4.58it/s]
                                                   

  4%|▍         | 476/11066 [01:44<38:30,  4.58it/s]
  4%|▍         | 477/11066 [01:44<38:56,  4.53it/s]
                                                   

  4%|▍         | 477/11066 [01:44<38:56,  4.53it/s]
  4%|▍         | 478/11066 [01:45<39:05,  4.51it/s]
                                                   

  4%|▍         | 478/11066 [01:45<39:05,  4.51it/s]
  4%|▍         | 479/11066 [01:45<39:19,  4.49it/s]
                                                   

  4%|▍         | 479/11066 [01:45<39:19,  4.49it/s]
  4%|▍         | 480/11066 [01:45<39:11,  4.50it/s]
                                                   

  4%|▍         | 480/11066 [01:45<39:11,  4.50it/s]
  4%|▍         | 481/11066 [01:45<38:57,  4.53it/s]
                                                   

  4%|▍         | 481/11066 [01:45<38:57,  4.53it/s]
  4%|▍         | 482/11066 [01:46<38:59,  4.52it/s]
                                                   

  4%|▍         | 482/11066 [01:46<38:59,  4.52it/s]
  4%|▍         | 483/11066 [01:46<39:02,  4.52it/s]
                                                   

  4%|▍         | 483/11066 [01:46<39:02,  4.52it/s]
  4%|▍         | 484/11066 [01:46<39:06,  4.51it/s]
                                                   

  4%|▍         | 484/11066 [01:46<39:06,  4.51it/s]
  4%|▍         | 485/11066 [01:46<39:10,  4.50it/s]
                                                   

  4%|▍         | 485/11066 [01:46<39:10,  4.50it/s]
  4%|▍         | 486/11066 [01:46<39:16,  4.49it/s]
                                                   

  4%|▍         | 486/11066 [01:46<39:16,  4.49it/s]
  4%|▍         | 487/11066 [01:47<39:17,  4.49it/s]
                                                   

  4%|▍         | 487/11066 [01:47<39:17,  4.49it/s]
  4%|▍         | 488/11066 [01:47<39:16,  4.49it/s]
                                                   

  4%|▍         | 488/11066 [01:47<39:16,  4.49it/s]
  4%|▍         | 489/11066 [01:47<39:10,  4.50it/s]
                                                   

  4%|▍         | 489/11066 [01:47<39:10,  4.50it/s]
  4%|▍         | 490/11066 [01:47<39:09,  4.50it/s]
                                                   

  4%|▍         | 490/11066 [01:47<39:09,  4.50it/s]
  4%|▍         | 491/11066 [01:48<39:07,  4.50it/s]
                                                   

  4%|▍         | 491/11066 [01:48<39:07,  4.50it/s]
  4%|▍         | 492/11066 [01:48<39:07,  4.50it/s]
                                                   

  4%|▍         | 492/11066 [01:48<39:07,  4.50it/s]
  4%|▍         | 493/11066 [01:48<39:06,  4.51it/s]
                                                   

  4%|▍         | 493/11066 [01:48<39:06,  4.51it/s]
  4%|▍         | 494/11066 [01:48<39:06,  4.51it/s]
                                                   

  4%|▍         | 494/11066 [01:48<39:06,  4.51it/s]
  4%|▍         | 495/11066 [01:48<39:04,  4.51it/s]
                                                   

  4%|▍         | 495/11066 [01:48<39:04,  4.51it/s]
  4%|▍         | 496/11066 [01:49<39:05,  4.51it/s]
                                                   

  4%|▍         | 496/11066 [01:49<39:05,  4.51it/s]
  4%|▍         | 497/11066 [01:49<38:47,  4.54it/s]
                                                   

  4%|▍         | 497/11066 [01:49<38:47,  4.54it/s]
  5%|▍         | 498/11066 [01:49<38:49,  4.54it/s]
                                                   

  5%|▍         | 498/11066 [01:49<38:49,  4.54it/s]
  5%|▍         | 499/11066 [01:49<38:50,  4.53it/s]
                                                   

  5%|▍         | 499/11066 [01:49<38:50,  4.53it/s]
  5%|▍         | 500/11066 [01:50<38:54,  4.53it/s]
                                                   

  5%|▍         | 500/11066 [01:50<38:54,  4.53it/s]
  5%|▍         | 501/11066 [01:50<39:00,  4.51it/s]
                                                   

  5%|▍         | 501/11066 [01:50<39:00,  4.51it/s]
  5%|▍         | 502/11066 [01:50<38:42,  4.55it/s]
                                                   

  5%|▍         | 502/11066 [01:50<38:42,  4.55it/s]
  5%|▍         | 503/11066 [01:50<38:50,  4.53it/s]
                                                   

  5%|▍         | 503/11066 [01:50<38:50,  4.53it/s]
  5%|▍         | 504/11066 [01:50<39:01,  4.51it/s]
                                                   

  5%|▍         | 504/11066 [01:50<39:01,  4.51it/s]
  5%|▍         | 505/11066 [01:51<39:10,  4.49it/s]
                                                   

  5%|▍         | 505/11066 [01:51<39:10,  4.49it/s]
  5%|▍         | 506/11066 [01:51<38:51,  4.53it/s]
                                                   

  5%|▍         | 506/11066 [01:51<38:51,  4.53it/s]
  5%|▍         | 507/11066 [01:51<38:50,  4.53it/s]
                                                   

  5%|▍         | 507/11066 [01:51<38:50,  4.53it/s]
  5%|▍         | 508/11066 [01:51<38:50,  4.53it/s]
                                                   

  5%|▍         | 508/11066 [01:51<38:50,  4.53it/s]
  5%|▍         | 509/11066 [01:52<38:56,  4.52it/s]
                                                   

  5%|▍         | 509/11066 [01:52<38:56,  4.52it/s]
  5%|▍         | 510/11066 [01:52<39:00,  4.51it/s]
                                                   

  5%|▍         | 510/11066 [01:52<39:00,  4.51it/s]
  5%|▍         | 511/11066 [01:52<39:02,  4.51it/s]
                                                   

  5%|▍         | 511/11066 [01:52<39:02,  4.51it/s]
  5%|▍         | 512/11066 [01:52<39:03,  4.50it/s]
                                                   

  5%|▍         | 512/11066 [01:52<39:03,  4.50it/s]
  5%|▍         | 513/11066 [01:52<39:04,  4.50it/s]
                                                   

  5%|▍         | 513/11066 [01:52<39:04,  4.50it/s]
  5%|▍         | 514/11066 [01:53<39:06,  4.50it/s]
                                                   

  5%|▍         | 514/11066 [01:53<39:06,  4.50it/s]
  5%|▍         | 515/11066 [01:53<39:02,  4.50it/s]
                                                   

  5%|▍         | 515/11066 [01:53<39:02,  4.50it/s]
  5%|▍         | 516/11066 [01:53<39:02,  4.50it/s]
                                                   

  5%|▍         | 516/11066 [01:53<39:02,  4.50it/s]
  5%|▍         | 517/11066 [01:53<38:57,  4.51it/s]
                                                   

  5%|▍         | 517/11066 [01:53<38:57,  4.51it/s]
  5%|▍         | 518/11066 [01:54<39:02,  4.50it/s]
                                                   

  5%|▍         | 518/11066 [01:54<39:02,  4.50it/s]
  5%|▍         | 519/11066 [01:54<38:44,  4.54it/s]
                                                   

  5%|▍         | 519/11066 [01:54<38:44,  4.54it/s]
  5%|▍         | 520/11066 [01:54<38:43,  4.54it/s]
                                                   

  5%|▍         | 520/11066 [01:54<38:43,  4.54it/s]
  5%|▍         | 521/11066 [01:54<38:46,  4.53it/s]
                                                   

  5%|▍         | 521/11066 [01:54<38:46,  4.53it/s]
  5%|▍         | 522/11066 [01:54<38:52,  4.52it/s]
                                                   

  5%|▍         | 522/11066 [01:54<38:52,  4.52it/s]
  5%|▍         | 523/11066 [01:55<38:52,  4.52it/s]
                                                   

  5%|▍         | 523/11066 [01:55<38:52,  4.52it/s]
  5%|▍         | 524/11066 [01:55<38:53,  4.52it/s]
                                                   

  5%|▍         | 524/11066 [01:55<38:53,  4.52it/s]
  5%|▍         | 525/11066 [01:55<38:39,  4.55it/s]
                                                   

  5%|▍         | 525/11066 [01:55<38:39,  4.55it/s]
  5%|▍         | 526/11066 [01:55<38:26,  4.57it/s]
                                                   

  5%|▍         | 526/11066 [01:55<38:26,  4.57it/s]
  5%|▍         | 527/11066 [01:55<38:39,  4.54it/s]
                                                   

  5%|▍         | 527/11066 [01:55<38:39,  4.54it/s]
  5%|▍         | 528/11066 [01:56<38:45,  4.53it/s]
                                                   

  5%|▍         | 528/11066 [01:56<38:45,  4.53it/s]
  5%|▍         | 529/11066 [01:56<38:54,  4.51it/s]
                                                   

  5%|▍         | 529/11066 [01:56<38:54,  4.51it/s]
  5%|▍         | 530/11066 [01:56<38:56,  4.51it/s]
                                                   

  5%|▍         | 530/11066 [01:56<38:56,  4.51it/s]
  5%|▍         | 531/11066 [01:56<38:59,  4.50it/s]
                                                   

  5%|▍         | 531/11066 [01:56<38:59,  4.50it/s]
  5%|▍         | 532/11066 [01:57<38:40,  4.54it/s]
                                                   

  5%|▍         | 532/11066 [01:57<38:40,  4.54it/s]
  5%|▍         | 533/11066 [01:57<38:26,  4.57it/s]
                                                   

  5%|▍         | 533/11066 [01:57<38:26,  4.57it/s]
  5%|▍         | 534/11066 [01:57<38:34,  4.55it/s]
                                                   

  5%|▍         | 534/11066 [01:57<38:34,  4.55it/s]
  5%|▍         | 535/11066 [01:57<38:48,  4.52it/s]
                                                   

  5%|▍         | 535/11066 [01:57<38:48,  4.52it/s]
  5%|▍         | 536/11066 [01:57<38:54,  4.51it/s]
                                                   

  5%|▍         | 536/11066 [01:57<38:54,  4.51it/s]
  5%|▍         | 537/11066 [01:58<38:57,  4.50it/s]
                                                   

  5%|▍         | 537/11066 [01:58<38:57,  4.50it/s]
  5%|▍         | 538/11066 [01:58<38:58,  4.50it/s]
                                                   

  5%|▍         | 538/11066 [01:58<38:58,  4.50it/s]
  5%|▍         | 539/11066 [01:58<38:59,  4.50it/s]
                                                   

  5%|▍         | 539/11066 [01:58<38:59,  4.50it/s]
  5%|▍         | 540/11066 [01:58<38:57,  4.50it/s]
                                                   

  5%|▍         | 540/11066 [01:58<38:57,  4.50it/s]
  5%|▍         | 541/11066 [01:59<38:39,  4.54it/s]
                                                   

  5%|▍         | 541/11066 [01:59<38:39,  4.54it/s]
  5%|▍         | 542/11066 [01:59<38:38,  4.54it/s]
                                                   

  5%|▍         | 542/11066 [01:59<38:38,  4.54it/s]
  5%|▍         | 543/11066 [01:59<38:26,  4.56it/s]
                                                   

  5%|▍         | 543/11066 [01:59<38:26,  4.56it/s]
  5%|▍         | 544/11066 [01:59<38:45,  4.52it/s]
                                                   

  5%|▍         | 544/11066 [01:59<38:45,  4.52it/s]
  5%|▍         | 545/11066 [01:59<38:51,  4.51it/s]
                                                   

  5%|▍         | 545/11066 [01:59<38:51,  4.51it/s]
  5%|▍         | 546/11066 [02:00<38:54,  4.51it/s]
                                                   

  5%|▍         | 546/11066 [02:00<38:54,  4.51it/s]
  5%|▍         | 547/11066 [02:00<38:37,  4.54it/s]
                                                   

  5%|▍         | 547/11066 [02:00<38:37,  4.54it/s]
  5%|▍         | 548/11066 [02:00<38:41,  4.53it/s]
                                                   

  5%|▍         | 548/11066 [02:00<38:41,  4.53it/s]
  5%|▍         | 549/11066 [02:00<38:46,  4.52it/s]
                                                   

  5%|▍         | 549/11066 [02:00<38:46,  4.52it/s]
  5%|▍         | 550/11066 [02:01<38:50,  4.51it/s]
                                                   

  5%|▍         | 550/11066 [02:01<38:50,  4.51it/s]
  5%|▍         | 551/11066 [02:01<39:00,  4.49it/s]
                                                   

  5%|▍         | 551/11066 [02:01<39:00,  4.49it/s]
  5%|▍         | 552/11066 [02:01<39:04,  4.49it/s]
                                                   

  5%|▍         | 552/11066 [02:01<39:04,  4.49it/s]
  5%|▍         | 553/11066 [02:01<39:00,  4.49it/s]
                                                   

  5%|▍         | 553/11066 [02:01<39:00,  4.49it/s]
  5%|▌         | 554/11066 [02:01<39:00,  4.49it/s]
                                                   

  5%|▌         | 554/11066 [02:01<39:00,  4.49it/s]
  5%|▌         | 555/11066 [02:02<38:59,  4.49it/s]
                                                   

  5%|▌         | 555/11066 [02:02<38:59,  4.49it/s]
  5%|▌         | 556/11066 [02:02<38:56,  4.50it/s]
                                                   

  5%|▌         | 556/11066 [02:02<38:56,  4.50it/s]
  5%|▌         | 557/11066 [02:02<38:53,  4.50it/s]
                                                   

  5%|▌         | 557/11066 [02:02<38:53,  4.50it/s]
  5%|▌         | 558/11066 [02:02<38:58,  4.49it/s]
                                                   

  5%|▌         | 558/11066 [02:02<38:58,  4.49it/s]
  5%|▌         | 559/11066 [02:03<38:55,  4.50it/s]
                                                   

  5%|▌         | 559/11066 [02:03<38:55,  4.50it/s]
  5%|▌         | 560/11066 [02:03<38:55,  4.50it/s]
                                                   

  5%|▌         | 560/11066 [02:03<38:55,  4.50it/s]
  5%|▌         | 561/11066 [02:03<38:36,  4.54it/s]
                                                   

  5%|▌         | 561/11066 [02:03<38:36,  4.54it/s]
  5%|▌         | 562/11066 [02:03<38:10,  4.59it/s]
                                                   

  5%|▌         | 562/11066 [02:03<38:10,  4.59it/s]
  5%|▌         | 563/11066 [02:03<38:20,  4.57it/s]
                                                   
{'loss': 1.3237, 'learning_rate': 2.8780046990782578e-05, 'epoch': 0.08}
{'loss': 1.5885, 'learning_rate': 2.8777335984095427e-05, 'epoch': 0.08}
{'loss': 1.82, 'learning_rate': 2.877462497740828e-05, 'epoch': 0.08}
{'loss': 1.8053, 'learning_rate': 2.877191397072113e-05, 'epoch': 0.08}
{'loss': 1.1485, 'learning_rate': 2.876920296403398e-05, 'epoch': 0.08}
{'loss': 1.7767, 'learning_rate': 2.876649195734683e-05, 'epoch': 0.08}
{'loss': 1.5774, 'learning_rate': 2.876378095065968e-05, 'epoch': 0.08}
{'loss': 2.1925, 'learning_rate': 2.8761069943972527e-05, 'epoch': 0.08}
{'loss': 2.3281, 'learning_rate': 2.875835893728538e-05, 'epoch': 0.08}
{'loss': 1.8536, 'learning_rate': 2.8755647930598228e-05, 'epoch': 0.08}
{'loss': 1.7365, 'learning_rate': 2.875293692391108e-05, 'epoch': 0.08}
{'loss': 1.8846, 'learning_rate': 2.875022591722393e-05, 'epoch': 0.08}
{'loss': 1.3164, 'learning_rate': 2.874751491053678e-05, 'epoch': 0.08}
{'loss': 1.8203, 'learning_rate': 2.874480390384963e-05, 'epoch': 0.08}
{'loss': 1.635, 'learning_rate': 2.8742092897162483e-05, 'epoch': 0.08}
{'loss': 2.1423, 'learning_rate': 2.873938189047533e-05, 'epoch': 0.08}
{'loss': 1.8326, 'learning_rate': 2.873667088378818e-05, 'epoch': 0.08}
{'loss': 1.98, 'learning_rate': 2.873395987710103e-05, 'epoch': 0.08}
{'loss': 1.2633, 'learning_rate': 2.873124887041388e-05, 'epoch': 0.08}
{'loss': 1.5057, 'learning_rate': 2.8728537863726732e-05, 'epoch': 0.08}
{'loss': 1.2216, 'learning_rate': 2.872582685703958e-05, 'epoch': 0.08}
{'loss': 1.9135, 'learning_rate': 2.8723115850352433e-05, 'epoch': 0.09}
{'loss': 1.1969, 'learning_rate': 2.8720404843665284e-05, 'epoch': 0.09}
{'loss': 1.1371, 'learning_rate': 2.871769383697813e-05, 'epoch': 0.09}
{'loss': 2.0456, 'learning_rate': 2.871498283029098e-05, 'epoch': 0.09}
{'loss': 1.6056, 'learning_rate': 2.8712271823603833e-05, 'epoch': 0.09}
{'loss': 1.1252, 'learning_rate': 2.870956081691668e-05, 'epoch': 0.09}
{'loss': 1.7922, 'learning_rate': 2.8706849810229533e-05, 'epoch': 0.09}
{'loss': 1.5013, 'learning_rate': 2.8704138803542382e-05, 'epoch': 0.09}
{'loss': 1.5741, 'learning_rate': 2.8701427796855234e-05, 'epoch': 0.09}
{'loss': 0.9703, 'learning_rate': 2.8698716790168086e-05, 'epoch': 0.09}
{'loss': 1.7088, 'learning_rate': 2.869600578348093e-05, 'epoch': 0.09}
{'loss': 1.6732, 'learning_rate': 2.8693294776793782e-05, 'epoch': 0.09}
{'loss': 1.526, 'learning_rate': 2.8690583770106634e-05, 'epoch': 0.09}
{'loss': 2.6089, 'learning_rate': 2.8687872763419483e-05, 'epoch': 0.09}
{'loss': 1.694, 'learning_rate': 2.8685161756732335e-05, 'epoch': 0.09}
{'loss': 1.6834, 'learning_rate': 2.8682450750045186e-05, 'epoch': 0.09}
{'loss': 1.3771, 'learning_rate': 2.8679739743358035e-05, 'epoch': 0.09}
{'loss': 0.9727, 'learning_rate': 2.8677028736670887e-05, 'epoch': 0.09}
{'loss': 1.3986, 'learning_rate': 2.867431772998373e-05, 'epoch': 0.09}
{'loss': 1.7924, 'learning_rate': 2.8671606723296583e-05, 'epoch': 0.09}
{'loss': 0.802, 'learning_rate': 2.8668895716609435e-05, 'epoch': 0.09}
{'loss': 1.4909, 'learning_rate': 2.8666184709922284e-05, 'epoch': 0.09}
{'loss': 1.3867, 'learning_rate': 2.8663473703235136e-05, 'epoch': 0.09}
{'loss': 1.6186, 'learning_rate': 2.8660762696547987e-05, 'epoch': 0.09}
{'loss': 0.9674, 'learning_rate': 2.8658051689860836e-05, 'epoch': 0.09}
{'loss': 1.3863, 'learning_rate': 2.8655340683173688e-05, 'epoch': 0.09}
{'loss': 1.5791, 'learning_rate': 2.8652629676486536e-05, 'epoch': 0.09}
{'loss': 2.6728, 'learning_rate': 2.8649918669799385e-05, 'epoch': 0.09}
{'loss': 1.6087, 'learning_rate': 2.8647207663112236e-05, 'epoch': 0.09}
{'loss': 1.6939, 'learning_rate': 2.8644496656425085e-05, 'epoch': 0.09}
{'loss': 1.6359, 'learning_rate': 2.8641785649737937e-05, 'epoch': 0.09}
{'loss': 1.2352, 'learning_rate': 2.863907464305079e-05, 'epoch': 0.09}
{'loss': 1.6874, 'learning_rate': 2.8636363636363637e-05, 'epoch': 0.09}
{'loss': 1.5015, 'learning_rate': 2.863365262967649e-05, 'epoch': 0.09}
{'loss': 1.6769, 'learning_rate': 2.8630941622989337e-05, 'epoch': 0.09}
{'loss': 2.0185, 'learning_rate': 2.8628230616302186e-05, 'epoch': 0.09}
{'loss': 1.559, 'learning_rate': 2.8625519609615037e-05, 'epoch': 0.09}
{'loss': 1.2689, 'learning_rate': 2.862280860292789e-05, 'epoch': 0.09}
{'loss': 1.7635, 'learning_rate': 2.8620097596240738e-05, 'epoch': 0.09}
{'loss': 1.4442, 'learning_rate': 2.861738658955359e-05, 'epoch': 0.09}
{'loss': 1.7883, 'learning_rate': 2.8614675582866438e-05, 'epoch': 0.09}
{'loss': 1.459, 'learning_rate': 2.861196457617929e-05, 'epoch': 0.09}
{'loss': 1.7306, 'learning_rate': 2.8609253569492138e-05, 'epoch': 0.09}
{'loss': 1.5112, 'learning_rate': 2.8606542562804987e-05, 'epoch': 0.09}
{'loss': 1.8925, 'learning_rate': 2.860383155611784e-05, 'epoch': 0.09}
{'loss': 1.5551, 'learning_rate': 2.860112054943069e-05, 'epoch': 0.09}
{'loss': 1.475, 'learning_rate': 2.859840954274354e-05, 'epoch': 0.09}
{'loss': 1.1458, 'learning_rate': 2.859569853605639e-05, 'epoch': 0.09}
{'loss': 2.1878, 'learning_rate': 2.8592987529369242e-05, 'epoch': 0.09}
{'loss': 1.6488, 'learning_rate': 2.8590276522682088e-05, 'epoch': 0.09}
{'loss': 2.6784, 'learning_rate': 2.858756551599494e-05, 'epoch': 0.09}
{'loss': 0.9568, 'learning_rate': 2.858485450930779e-05, 'epoch': 0.09}
{'loss': 1.0686, 'learning_rate': 2.858214350262064e-05, 'epoch': 0.09}
{'loss': 1.8142, 'learning_rate': 2.857943249593349e-05, 'epoch': 0.09}
{'loss': 2.5144, 'learning_rate': 2.857672148924634e-05, 'epoch': 0.09}
{'loss': 1.3901, 'learning_rate': 2.8574010482559192e-05, 'epoch': 0.1}
{'loss': 1.2016, 'learning_rate': 2.8571299475872044e-05, 'epoch': 0.1}
{'loss': 2.4518, 'learning_rate': 2.856858846918489e-05, 'epoch': 0.1}
{'loss': 1.9905, 'learning_rate': 2.856587746249774e-05, 'epoch': 0.1}
{'loss': 1.5354, 'learning_rate': 2.8563166455810592e-05, 'epoch': 0.1}
{'loss': 1.3906, 'learning_rate': 2.856045544912344e-05, 'epoch': 0.1}
{'loss': 1.5522, 'learning_rate': 2.8557744442436293e-05, 'epoch': 0.1}
{'loss': 1.7235, 'learning_rate': 2.8555033435749144e-05, 'epoch': 0.1}
{'loss': 1.9096, 'learning_rate': 2.8552322429061993e-05, 'epoch': 0.1}
{'loss': 1.5327, 'learning_rate': 2.8549611422374845e-05, 'epoch': 0.1}
{'loss': 1.7822, 'learning_rate': 2.854690041568769e-05, 'epoch': 0.1}
{'loss': 1.7668, 'learning_rate': 2.854418940900054e-05, 'epoch': 0.1}
{'loss': 1.503, 'learning_rate': 2.8541478402313393e-05, 'epoch': 0.1}
{'loss': 1.9722, 'learning_rate': 2.8538767395626242e-05, 'epoch': 0.1}
{'loss': 1.9234, 'learning_rate': 2.8536056388939094e-05, 'epoch': 0.1}
{'loss': 1.2621, 'learning_rate': 2.8533345382251945e-05, 'epoch': 0.1}
{'loss': 2.249, 'learning_rate': 2.8530634375564794e-05, 'epoch': 0.1}
{'loss': 2.1252, 'learning_rate': 2.8527923368877646e-05, 'epoch': 0.1}
{'loss': 2.4448, 'learning_rate': 2.8525212362190494e-05, 'epoch': 0.1}
{'loss': 1.5071, 'learning_rate': 2.8522501355503343e-05, 'epoch': 0.1}
{'loss': 2.082, 'learning_rate': 2.8519790348816194e-05, 'epoch': 0.1}
{'loss': 2.3638, 'learning_rate': 2.8517079342129043e-05, 'epoch': 0.1}
{'loss': 1.0422, 'learning_rate': 2.8514368335441895e-05, 'epoch': 0.1}
{'loss': 0.9536, 'learning_rate': 2.8511657328754746e-05, 'epoch': 0.1}
{'loss': 1.7131, 'learning_rate': 2.8508946322067595e-05, 'epoch': 0.1}
{'loss': 1.532, 'learning_rate': 2.8506235315380447e-05, 'epoch': 0.1}
{'loss': 1.5345, 'learning_rate': 2.8503524308693295e-05, 'epoch': 0.1}
{'loss': 1.3215, 'learning_rate': 2.8500813302006144e-05, 'epoch': 0.1}
{'loss': 0.9806, 'learning_rate': 2.8498102295318995e-05, 'epoch': 0.1}
{'loss': 1.7096, 'learning_rate': 2.8495391288631847e-05, 'epoch': 0.1}
{'loss': 1.3683, 'learning_rate': 2.8492680281944696e-05, 'epoch': 0.1}
{'loss': 1.3177, 'learning_rate': 2.8489969275257548e-05, 'epoch': 0.1}
{'loss': 1.2712, 'learning_rate': 2.8487258268570396e-05, 'epoch': 0.1}
{'loss': 1.4483, 'learning_rate': 2.8484547261883248e-05, 'epoch': 0.1}
{'loss': 1.0642, 'learning_rate': 2.8481836255196096e-05, 'epoch': 0.1}
{'loss': 1.4139, 'learning_rate': 2.8479125248508945e-05, 'epoch': 0.1}
{'loss': 1.2133, 'learning_rate': 2.8476414241821797e-05, 'epoch': 0.1}

  5%|▌         | 563/11066 [02:03<38:20,  4.57it/s]
  5%|▌         | 564/11066 [02:04<37:59,  4.61it/s]
                                                   

  5%|▌         | 564/11066 [02:04<37:59,  4.61it/s]
  5%|▌         | 565/11066 [02:04<37:51,  4.62it/s]
                                                   

  5%|▌         | 565/11066 [02:04<37:51,  4.62it/s]
  5%|▌         | 566/11066 [02:04<37:44,  4.64it/s]
                                                   

  5%|▌         | 566/11066 [02:04<37:44,  4.64it/s]
  5%|▌         | 567/11066 [02:04<38:06,  4.59it/s]
                                                   

  5%|▌         | 567/11066 [02:04<38:06,  4.59it/s]
  5%|▌         | 568/11066 [02:05<38:02,  4.60it/s]
                                                   

  5%|▌         | 568/11066 [02:05<38:02,  4.60it/s]
  5%|▌         | 569/11066 [02:05<38:00,  4.60it/s]
                                                   

  5%|▌         | 569/11066 [02:05<38:00,  4.60it/s]
  5%|▌         | 570/11066 [02:05<38:14,  4.57it/s]
                                                   

  5%|▌         | 570/11066 [02:05<38:14,  4.57it/s]
  5%|▌         | 571/11066 [02:05<38:26,  4.55it/s]
                                                   

  5%|▌         | 571/11066 [02:05<38:26,  4.55it/s]
  5%|▌         | 572/11066 [02:05<37:52,  4.62it/s]
                                                   

  5%|▌         | 572/11066 [02:05<37:52,  4.62it/s]
  5%|▌         | 573/11066 [02:06<38:18,  4.57it/s]
                                                   

  5%|▌         | 573/11066 [02:06<38:18,  4.57it/s]
  5%|▌         | 574/11066 [02:06<38:27,  4.55it/s]
                                                   

  5%|▌         | 574/11066 [02:06<38:27,  4.55it/s]
  5%|▌         | 575/11066 [02:06<38:18,  4.56it/s]
                                                   

  5%|▌         | 575/11066 [02:06<38:18,  4.56it/s]
  5%|▌         | 576/11066 [02:06<37:54,  4.61it/s]
                                                   

  5%|▌         | 576/11066 [02:06<37:54,  4.61it/s]
  5%|▌         | 577/11066 [02:07<38:11,  4.58it/s]
                                                   

  5%|▌         | 577/11066 [02:07<38:11,  4.58it/s]
  5%|▌         | 578/11066 [02:07<38:27,  4.55it/s]
                                                   

  5%|▌         | 578/11066 [02:07<38:27,  4.55it/s]
  5%|▌         | 579/11066 [02:07<38:28,  4.54it/s]
                                                   

  5%|▌         | 579/11066 [02:07<38:28,  4.54it/s]
  5%|▌         | 580/11066 [02:07<38:35,  4.53it/s]
                                                   

  5%|▌         | 580/11066 [02:07<38:35,  4.53it/s]
  5%|▌         | 581/11066 [02:07<38:43,  4.51it/s]
                                                   

  5%|▌         | 581/11066 [02:07<38:43,  4.51it/s]
  5%|▌         | 582/11066 [02:08<38:41,  4.52it/s]
                                                   

  5%|▌         | 582/11066 [02:08<38:41,  4.52it/s]
  5%|▌         | 583/11066 [02:08<38:15,  4.57it/s]
                                                   

  5%|▌         | 583/11066 [02:08<38:15,  4.57it/s]
  5%|▌         | 584/11066 [02:08<37:57,  4.60it/s]
                                                   

  5%|▌         | 584/11066 [02:08<37:57,  4.60it/s]
  5%|▌         | 585/11066 [02:08<37:52,  4.61it/s]
                                                   

  5%|▌         | 585/11066 [02:08<37:52,  4.61it/s]
  5%|▌         | 586/11066 [02:08<38:09,  4.58it/s]
                                                   

  5%|▌         | 586/11066 [02:08<38:09,  4.58it/s]
  5%|▌         | 587/11066 [02:09<38:04,  4.59it/s]
                                                   

  5%|▌         | 587/11066 [02:09<38:04,  4.59it/s]
  5%|▌         | 588/11066 [02:09<38:03,  4.59it/s]
                                                   

  5%|▌         | 588/11066 [02:09<38:03,  4.59it/s]
  5%|▌         | 589/11066 [02:09<38:14,  4.57it/s]
                                                   

  5%|▌         | 589/11066 [02:09<38:14,  4.57it/s]
  5%|▌         | 590/11066 [02:09<38:08,  4.58it/s]
                                                   

  5%|▌         | 590/11066 [02:09<38:08,  4.58it/s]
  5%|▌         | 591/11066 [02:10<38:04,  4.59it/s]
                                                   

  5%|▌         | 591/11066 [02:10<38:04,  4.59it/s]
  5%|▌         | 592/11066 [02:10<37:59,  4.59it/s]
                                                   

  5%|▌         | 592/11066 [02:10<37:59,  4.59it/s]
  5%|▌         | 593/11066 [02:10<37:39,  4.64it/s]
                                                   

  5%|▌         | 593/11066 [02:10<37:39,  4.64it/s]
  5%|▌         | 594/11066 [02:10<37:22,  4.67it/s]
                                                   

  5%|▌         | 594/11066 [02:10<37:22,  4.67it/s]
  5%|▌         | 595/11066 [02:10<37:42,  4.63it/s]
                                                   

  5%|▌         | 595/11066 [02:10<37:42,  4.63it/s]
  5%|▌         | 596/11066 [02:11<37:43,  4.62it/s]
                                                   

  5%|▌         | 596/11066 [02:11<37:43,  4.62it/s]
  5%|▌         | 597/11066 [02:11<37:21,  4.67it/s]
                                                   

  5%|▌         | 597/11066 [02:11<37:21,  4.67it/s]
  5%|▌         | 598/11066 [02:11<37:41,  4.63it/s]
                                                   

  5%|▌         | 598/11066 [02:11<37:41,  4.63it/s]
  5%|▌         | 599/11066 [02:11<38:00,  4.59it/s]
                                                   

  5%|▌         | 599/11066 [02:11<38:00,  4.59it/s]
  5%|▌         | 600/11066 [02:12<38:15,  4.56it/s]
                                                   

  5%|▌         | 600/11066 [02:12<38:15,  4.56it/s]
  5%|▌         | 601/11066 [02:12<38:27,  4.54it/s]
                                                   

  5%|▌         | 601/11066 [02:12<38:27,  4.54it/s]
  5%|▌         | 602/11066 [02:12<38:32,  4.53it/s]
                                                   

  5%|▌         | 602/11066 [02:12<38:32,  4.53it/s]
  5%|▌         | 603/11066 [02:12<38:34,  4.52it/s]
                                                   

  5%|▌         | 603/11066 [02:12<38:34,  4.52it/s]
  5%|▌         | 604/11066 [02:12<38:38,  4.51it/s]
                                                   

  5%|▌         | 604/11066 [02:12<38:38,  4.51it/s]
  5%|▌         | 605/11066 [02:13<38:40,  4.51it/s]
                                                   

  5%|▌         | 605/11066 [02:13<38:40,  4.51it/s]
  5%|▌         | 606/11066 [02:13<38:43,  4.50it/s]
                                                   

  5%|▌         | 606/11066 [02:13<38:43,  4.50it/s]
  5%|▌         | 607/11066 [02:13<38:45,  4.50it/s]
                                                   

  5%|▌         | 607/11066 [02:13<38:45,  4.50it/s]
  5%|▌         | 608/11066 [02:13<38:42,  4.50it/s]
                                                   

  5%|▌         | 608/11066 [02:13<38:42,  4.50it/s]
  6%|▌         | 609/11066 [02:14<38:42,  4.50it/s]
                                                   

  6%|▌         | 609/11066 [02:14<38:42,  4.50it/s]
  6%|▌         | 610/11066 [02:14<38:41,  4.50it/s]
                                                   

  6%|▌         | 610/11066 [02:14<38:41,  4.50it/s]
  6%|▌         | 611/11066 [02:14<38:41,  4.50it/s]
                                                   

  6%|▌         | 611/11066 [02:14<38:41,  4.50it/s]
  6%|▌         | 612/11066 [02:14<38:42,  4.50it/s]
                                                   

  6%|▌         | 612/11066 [02:14<38:42,  4.50it/s]
  6%|▌         | 613/11066 [02:14<38:45,  4.50it/s]
                                                   

  6%|▌         | 613/11066 [02:14<38:45,  4.50it/s]
  6%|▌         | 614/11066 [02:15<38:45,  4.49it/s]
                                                   

  6%|▌         | 614/11066 [02:15<38:45,  4.49it/s]
  6%|▌         | 615/11066 [02:15<38:38,  4.51it/s]
                                                   

  6%|▌         | 615/11066 [02:15<38:38,  4.51it/s]
  6%|▌         | 616/11066 [02:15<38:48,  4.49it/s]
                                                   

  6%|▌         | 616/11066 [02:15<38:48,  4.49it/s]
  6%|▌         | 617/11066 [02:15<38:46,  4.49it/s]
                                                   

  6%|▌         | 617/11066 [02:15<38:46,  4.49it/s]
  6%|▌         | 618/11066 [02:16<38:47,  4.49it/s]
                                                   

  6%|▌         | 618/11066 [02:16<38:47,  4.49it/s]
  6%|▌         | 619/11066 [02:16<38:43,  4.50it/s]
                                                   

  6%|▌         | 619/11066 [02:16<38:43,  4.50it/s]
  6%|▌         | 620/11066 [02:16<38:40,  4.50it/s]
                                                   

  6%|▌         | 620/11066 [02:16<38:40,  4.50it/s]
  6%|▌         | 621/11066 [02:16<38:21,  4.54it/s]
                                                   

  6%|▌         | 621/11066 [02:16<38:21,  4.54it/s]
  6%|▌         | 622/11066 [02:16<37:56,  4.59it/s]
                                                   

  6%|▌         | 622/11066 [02:16<37:56,  4.59it/s]
  6%|▌         | 623/11066 [02:17<37:24,  4.65it/s]
                                                   

  6%|▌         | 623/11066 [02:17<37:24,  4.65it/s]
  6%|▌         | 624/11066 [02:17<37:46,  4.61it/s]
                                                   

  6%|▌         | 624/11066 [02:17<37:46,  4.61it/s]
  6%|▌         | 625/11066 [02:17<38:02,  4.57it/s]
                                                   

  6%|▌         | 625/11066 [02:17<38:02,  4.57it/s]
  6%|▌         | 626/11066 [02:17<37:55,  4.59it/s]
                                                   

  6%|▌         | 626/11066 [02:17<37:55,  4.59it/s]
  6%|▌         | 627/11066 [02:17<37:39,  4.62it/s]
                                                   

  6%|▌         | 627/11066 [02:17<37:39,  4.62it/s]
  6%|▌         | 628/11066 [02:18<37:17,  4.66it/s]
                                                   

  6%|▌         | 628/11066 [02:18<37:17,  4.66it/s]
  6%|▌         | 629/11066 [02:18<37:34,  4.63it/s]
                                                   

  6%|▌         | 629/11066 [02:18<37:34,  4.63it/s]
  6%|▌         | 630/11066 [02:18<37:56,  4.59it/s]
                                                   

  6%|▌         | 630/11066 [02:18<37:56,  4.59it/s]
  6%|▌         | 631/11066 [02:18<38:08,  4.56it/s]
                                                   

  6%|▌         | 631/11066 [02:18<38:08,  4.56it/s]
  6%|▌         | 632/11066 [02:19<38:17,  4.54it/s]
                                                   

  6%|▌         | 632/11066 [02:19<38:17,  4.54it/s]
  6%|▌         | 633/11066 [02:19<38:23,  4.53it/s]
                                                   

  6%|▌         | 633/11066 [02:19<38:23,  4.53it/s]
  6%|▌         | 634/11066 [02:19<38:27,  4.52it/s]
                                                   

  6%|▌         | 634/11066 [02:19<38:27,  4.52it/s]
  6%|▌         | 635/11066 [02:19<38:31,  4.51it/s]
                                                   

  6%|▌         | 635/11066 [02:19<38:31,  4.51it/s]
  6%|▌         | 636/11066 [02:19<38:34,  4.51it/s]
                                                   

  6%|▌         | 636/11066 [02:19<38:34,  4.51it/s]
  6%|▌         | 637/11066 [02:20<38:37,  4.50it/s]
                                                   

  6%|▌         | 637/11066 [02:20<38:37,  4.50it/s]
  6%|▌         | 638/11066 [02:20<38:37,  4.50it/s]
                                                   

  6%|▌         | 638/11066 [02:20<38:37,  4.50it/s]
  6%|▌         | 639/11066 [02:20<38:19,  4.54it/s]
                                                   

  6%|▌         | 639/11066 [02:20<38:19,  4.54it/s]
  6%|▌         | 640/11066 [02:20<37:39,  4.61it/s]
                                                   

  6%|▌         | 640/11066 [02:20<37:39,  4.61it/s]
  6%|▌         | 641/11066 [02:21<37:42,  4.61it/s]
                                                   

  6%|▌         | 641/11066 [02:21<37:42,  4.61it/s]
  6%|▌         | 642/11066 [02:21<37:45,  4.60it/s]
                                                   

  6%|▌         | 642/11066 [02:21<37:45,  4.60it/s]
  6%|▌         | 643/11066 [02:21<38:00,  4.57it/s]
                                                   

  6%|▌         | 643/11066 [02:21<38:00,  4.57it/s]
  6%|▌         | 644/11066 [02:21<37:55,  4.58it/s]
                                                   

  6%|▌         | 644/11066 [02:21<37:55,  4.58it/s]
  6%|▌         | 645/11066 [02:21<38:26,  4.52it/s]
                                                   

  6%|▌         | 645/11066 [02:21<38:26,  4.52it/s]
  6%|▌         | 646/11066 [02:22<38:14,  4.54it/s]
                                                   

  6%|▌         | 646/11066 [02:22<38:14,  4.54it/s]
  6%|▌         | 647/11066 [02:22<38:29,  4.51it/s]
                                                   

  6%|▌         | 647/11066 [02:22<38:29,  4.51it/s]
  6%|▌         | 648/11066 [02:22<38:51,  4.47it/s]
                                                   

  6%|▌         | 648/11066 [02:22<38:51,  4.47it/s]
  6%|▌         | 649/11066 [02:22<38:55,  4.46it/s]
                                                   

  6%|▌         | 649/11066 [02:22<38:55,  4.46it/s]
  6%|▌         | 650/11066 [02:23<39:21,  4.41it/s]
                                                   

  6%|▌         | 650/11066 [02:23<39:21,  4.41it/s]
  6%|▌         | 651/11066 [02:23<39:13,  4.43it/s]
                                                   

  6%|▌         | 651/11066 [02:23<39:13,  4.43it/s]
  6%|▌         | 652/11066 [02:23<39:08,  4.43it/s]
                                                   

  6%|▌         | 652/11066 [02:23<39:08,  4.43it/s]
  6%|▌         | 653/11066 [02:23<38:57,  4.45it/s]
                                                   

  6%|▌         | 653/11066 [02:23<38:57,  4.45it/s]
  6%|▌         | 654/11066 [02:23<38:47,  4.47it/s]
                                                   

  6%|▌         | 654/11066 [02:23<38:47,  4.47it/s]
  6%|▌         | 655/11066 [02:24<38:08,  4.55it/s]
                                                   

  6%|▌         | 655/11066 [02:24<38:08,  4.55it/s]
  6%|▌         | 656/11066 [02:24<38:18,  4.53it/s]
                                                   

  6%|▌         | 656/11066 [02:24<38:18,  4.53it/s]
  6%|▌         | 657/11066 [02:24<38:07,  4.55it/s]
                                                   

  6%|▌         | 657/11066 [02:24<38:07,  4.55it/s]
  6%|▌         | 658/11066 [02:24<38:18,  4.53it/s]
                                                   

  6%|▌         | 658/11066 [02:24<38:18,  4.53it/s]
  6%|▌         | 659/11066 [02:25<38:33,  4.50it/s]
                                                   

  6%|▌         | 659/11066 [02:25<38:33,  4.50it/s]
  6%|▌         | 660/11066 [02:25<38:36,  4.49it/s]
                                                   

  6%|▌         | 660/11066 [02:25<38:36,  4.49it/s]
  6%|▌         | 661/11066 [02:25<38:04,  4.56it/s]
                                                   

  6%|▌         | 661/11066 [02:25<38:04,  4.56it/s]
  6%|▌         | 662/11066 [02:25<38:14,  4.53it/s]
                                                   

  6%|▌         | 662/11066 [02:25<38:14,  4.53it/s]
  6%|▌         | 663/11066 [02:25<38:21,  4.52it/s]
                                                   

  6%|▌         | 663/11066 [02:25<38:21,  4.52it/s]
  6%|▌         | 664/11066 [02:26<38:06,  4.55it/s]
                                                   

  6%|▌         | 664/11066 [02:26<38:06,  4.55it/s]
  6%|▌         | 665/11066 [02:26<38:02,  4.56it/s]
                                                   

  6%|▌         | 665/11066 [02:26<38:02,  4.56it/s]
  6%|▌         | 666/11066 [02:26<37:51,  4.58it/s]
                                                   

  6%|▌         | 666/11066 [02:26<37:51,  4.58it/s]
  6%|▌         | 667/11066 [02:26<37:35,  4.61it/s]
                                                   

  6%|▌         | 667/11066 [02:26<37:35,  4.61it/s]
  6%|▌         | 668/11066 [02:27<37:19,  4.64it/s]
                                                   

  6%|▌         | 668/11066 [02:27<37:19,  4.64it/s]
  6%|▌         | 669/11066 [02:27<37:48,  4.58it/s]
                                                   

  6%|▌         | 669/11066 [02:27<37:48,  4.58it/s]
  6%|▌         | 670/11066 [02:27<38:15,  4.53it/s]
                                                   

  6%|▌         | 670/11066 [02:27<38:15,  4.53it/s]
  6%|▌         | 671/11066 [02:27<38:25,  4.51it/s]
                                                   

  6%|▌         | 671/11066 [02:27<38:25,  4.51it/s]
  6%|▌         | 672/11066 [02:27<38:40,  4.48it/s]
                                                   

  6%|▌         | 672/11066 [02:27<38:40,  4.48it/s]
  6%|▌         | 673/11066 [02:28<39:00,  4.44it/s]
                                                   

  6%|▌         | 673/11066 [02:28<39:00,  4.44it/s]
  6%|▌         | 674/11066 [02:28<39:03,  4.43it/s]
                                                   

  6%|▌         | 674/11066 [02:28<39:03,  4.43it/s]
  6%|▌         | 675/11066 [02:28<38:53,  4.45it/s]
                                                   

  6%|▌         | 675/11066 [02:28<38:53,  4.45it/s]
  6%|▌         | 676/11066 [02:28<38:14,  4.53it/s]
                                                   
{'loss': 0.8381, 'learning_rate': 2.847370323513465e-05, 'epoch': 0.1}
{'loss': 0.8278, 'learning_rate': 2.8470992228447497e-05, 'epoch': 0.1}
{'loss': 1.4284, 'learning_rate': 2.846828122176035e-05, 'epoch': 0.1}
{'loss': 1.8055, 'learning_rate': 2.84655702150732e-05, 'epoch': 0.1}
{'loss': 0.9977, 'learning_rate': 2.846285920838605e-05, 'epoch': 0.1}
{'loss': 1.7536, 'learning_rate': 2.8460148201698897e-05, 'epoch': 0.1}
{'loss': 1.2484, 'learning_rate': 2.8457437195011746e-05, 'epoch': 0.1}
{'loss': 1.3921, 'learning_rate': 2.8454726188324598e-05, 'epoch': 0.1}
{'loss': 1.4167, 'learning_rate': 2.845201518163745e-05, 'epoch': 0.1}
{'loss': 0.7402, 'learning_rate': 2.8449304174950298e-05, 'epoch': 0.1}
{'loss': 1.3316, 'learning_rate': 2.844659316826315e-05, 'epoch': 0.1}
{'loss': 1.648, 'learning_rate': 2.8443882161576e-05, 'epoch': 0.1}
{'loss': 1.9794, 'learning_rate': 2.844117115488885e-05, 'epoch': 0.1}
{'loss': 0.8002, 'learning_rate': 2.84384601482017e-05, 'epoch': 0.1}
{'loss': 0.8159, 'learning_rate': 2.843574914151455e-05, 'epoch': 0.1}
{'loss': 1.617, 'learning_rate': 2.84330381348274e-05, 'epoch': 0.1}
{'loss': 2.2053, 'learning_rate': 2.843032712814025e-05, 'epoch': 0.1}
{'loss': 1.7646, 'learning_rate': 2.84276161214531e-05, 'epoch': 0.1}
{'loss': 1.1045, 'learning_rate': 2.842490511476595e-05, 'epoch': 0.11}
{'loss': 1.8775, 'learning_rate': 2.8422194108078803e-05, 'epoch': 0.11}
{'loss': 1.2446, 'learning_rate': 2.841948310139165e-05, 'epoch': 0.11}
{'loss': 1.7057, 'learning_rate': 2.84167720947045e-05, 'epoch': 0.11}
{'loss': 1.3601, 'learning_rate': 2.841406108801735e-05, 'epoch': 0.11}
{'loss': 1.2179, 'learning_rate': 2.84113500813302e-05, 'epoch': 0.11}
{'loss': 1.318, 'learning_rate': 2.840863907464305e-05, 'epoch': 0.11}
{'loss': 1.2701, 'learning_rate': 2.8405928067955903e-05, 'epoch': 0.11}
{'loss': 2.278, 'learning_rate': 2.8403217061268752e-05, 'epoch': 0.11}
{'loss': 1.8509, 'learning_rate': 2.8400506054581604e-05, 'epoch': 0.11}
{'loss': 1.8724, 'learning_rate': 2.8397795047894452e-05, 'epoch': 0.11}
{'loss': 1.2666, 'learning_rate': 2.83950840412073e-05, 'epoch': 0.11}
{'loss': 1.7754, 'learning_rate': 2.8392373034520152e-05, 'epoch': 0.11}
{'loss': 2.1415, 'learning_rate': 2.8389662027833e-05, 'epoch': 0.11}
{'loss': 1.8377, 'learning_rate': 2.8386951021145853e-05, 'epoch': 0.11}
{'loss': 1.3448, 'learning_rate': 2.8384240014458705e-05, 'epoch': 0.11}
{'loss': 1.4621, 'learning_rate': 2.8381529007771553e-05, 'epoch': 0.11}
{'loss': 1.2806, 'learning_rate': 2.8378818001084405e-05, 'epoch': 0.11}
{'loss': 1.6919, 'learning_rate': 2.8376106994397257e-05, 'epoch': 0.11}
{'loss': 1.883, 'learning_rate': 2.83733959877101e-05, 'epoch': 0.11}
{'loss': 1.1773, 'learning_rate': 2.8370684981022953e-05, 'epoch': 0.11}
{'loss': 0.9346, 'learning_rate': 2.8367973974335802e-05, 'epoch': 0.11}
{'loss': 1.3429, 'learning_rate': 2.8365262967648654e-05, 'epoch': 0.11}
{'loss': 1.6346, 'learning_rate': 2.8362551960961506e-05, 'epoch': 0.11}
{'loss': 2.0229, 'learning_rate': 2.8359840954274354e-05, 'epoch': 0.11}
{'loss': 1.2839, 'learning_rate': 2.8357129947587206e-05, 'epoch': 0.11}
{'loss': 1.7024, 'learning_rate': 2.8354418940900058e-05, 'epoch': 0.11}
{'loss': 1.4734, 'learning_rate': 2.8351707934212903e-05, 'epoch': 0.11}
{'loss': 1.76, 'learning_rate': 2.8348996927525755e-05, 'epoch': 0.11}
{'loss': 1.5971, 'learning_rate': 2.8346285920838606e-05, 'epoch': 0.11}
{'loss': 1.1585, 'learning_rate': 2.8343574914151455e-05, 'epoch': 0.11}
{'loss': 0.9819, 'learning_rate': 2.8340863907464307e-05, 'epoch': 0.11}
{'loss': 1.7558, 'learning_rate': 2.8338152900777155e-05, 'epoch': 0.11}
{'loss': 1.6226, 'learning_rate': 2.8335441894090007e-05, 'epoch': 0.11}
{'loss': 1.2949, 'learning_rate': 2.833273088740286e-05, 'epoch': 0.11}
{'loss': 1.6631, 'learning_rate': 2.8330019880715704e-05, 'epoch': 0.11}
{'loss': 1.4852, 'learning_rate': 2.8327308874028556e-05, 'epoch': 0.11}
{'loss': 1.3654, 'learning_rate': 2.8324597867341407e-05, 'epoch': 0.11}
{'loss': 1.9607, 'learning_rate': 2.8321886860654256e-05, 'epoch': 0.11}
{'loss': 2.0572, 'learning_rate': 2.8319175853967108e-05, 'epoch': 0.11}
{'loss': 1.0707, 'learning_rate': 2.831646484727996e-05, 'epoch': 0.11}
{'loss': 1.229, 'learning_rate': 2.8313753840592808e-05, 'epoch': 0.11}
{'loss': 2.1652, 'learning_rate': 2.831104283390566e-05, 'epoch': 0.11}
{'loss': 1.3688, 'learning_rate': 2.8308331827218505e-05, 'epoch': 0.11}
{'loss': 1.3316, 'learning_rate': 2.8305620820531357e-05, 'epoch': 0.11}
{'loss': 1.3555, 'learning_rate': 2.830290981384421e-05, 'epoch': 0.11}
{'loss': 1.165, 'learning_rate': 2.8300198807157057e-05, 'epoch': 0.11}
{'loss': 2.5704, 'learning_rate': 2.829748780046991e-05, 'epoch': 0.11}
{'loss': 1.2057, 'learning_rate': 2.829477679378276e-05, 'epoch': 0.11}
{'loss': 1.7036, 'learning_rate': 2.829206578709561e-05, 'epoch': 0.11}
{'loss': 1.4412, 'learning_rate': 2.828935478040846e-05, 'epoch': 0.11}
{'loss': 1.8601, 'learning_rate': 2.828664377372131e-05, 'epoch': 0.11}
{'loss': 1.4765, 'learning_rate': 2.8283932767034158e-05, 'epoch': 0.11}
{'loss': 1.5202, 'learning_rate': 2.828122176034701e-05, 'epoch': 0.11}
{'loss': 1.4951, 'learning_rate': 2.8278510753659858e-05, 'epoch': 0.11}
{'loss': 0.9366, 'learning_rate': 2.827579974697271e-05, 'epoch': 0.11}
{'loss': 1.5464, 'learning_rate': 2.8273088740285562e-05, 'epoch': 0.12}
{'loss': 1.4515, 'learning_rate': 2.827037773359841e-05, 'epoch': 0.12}
{'loss': 1.5152, 'learning_rate': 2.8267666726911262e-05, 'epoch': 0.12}
{'loss': 1.093, 'learning_rate': 2.826495572022411e-05, 'epoch': 0.12}
{'loss': 1.2114, 'learning_rate': 2.826224471353696e-05, 'epoch': 0.12}
{'loss': 1.9168, 'learning_rate': 2.825953370684981e-05, 'epoch': 0.12}
{'loss': 1.1559, 'learning_rate': 2.8256822700162663e-05, 'epoch': 0.12}
{'loss': 1.6528, 'learning_rate': 2.825411169347551e-05, 'epoch': 0.12}
{'loss': 1.1606, 'learning_rate': 2.8251400686788363e-05, 'epoch': 0.12}
{'loss': 1.0794, 'learning_rate': 2.824868968010121e-05, 'epoch': 0.12}
{'loss': 1.0433, 'learning_rate': 2.824597867341406e-05, 'epoch': 0.12}
{'loss': 1.023, 'learning_rate': 2.824326766672691e-05, 'epoch': 0.12}
{'loss': 1.1549, 'learning_rate': 2.824055666003976e-05, 'epoch': 0.12}
{'loss': 0.9864, 'learning_rate': 2.8237845653352612e-05, 'epoch': 0.12}
{'loss': 1.6893, 'learning_rate': 2.8235134646665464e-05, 'epoch': 0.12}
{'loss': 0.8083, 'learning_rate': 2.8232423639978312e-05, 'epoch': 0.12}
{'loss': 0.9089, 'learning_rate': 2.8229712633291164e-05, 'epoch': 0.12}
{'loss': 1.8591, 'learning_rate': 2.8227001626604016e-05, 'epoch': 0.12}
{'loss': 1.3048, 'learning_rate': 2.822429061991686e-05, 'epoch': 0.12}
{'loss': 2.1456, 'learning_rate': 2.8221579613229713e-05, 'epoch': 0.12}
{'loss': 1.6491, 'learning_rate': 2.8218868606542564e-05, 'epoch': 0.12}
{'loss': 0.9065, 'learning_rate': 2.8216157599855413e-05, 'epoch': 0.12}
{'loss': 1.9128, 'learning_rate': 2.8213446593168265e-05, 'epoch': 0.12}
{'loss': 1.6907, 'learning_rate': 2.8210735586481113e-05, 'epoch': 0.12}
{'loss': 1.0875, 'learning_rate': 2.8208024579793965e-05, 'epoch': 0.12}
{'loss': 1.0132, 'learning_rate': 2.8205313573106817e-05, 'epoch': 0.12}
{'loss': 1.4922, 'learning_rate': 2.8202602566419662e-05, 'epoch': 0.12}
{'loss': 1.1859, 'learning_rate': 2.8199891559732514e-05, 'epoch': 0.12}
{'loss': 1.6883, 'learning_rate': 2.8197180553045365e-05, 'epoch': 0.12}
{'loss': 1.7627, 'learning_rate': 2.8194469546358214e-05, 'epoch': 0.12}
{'loss': 1.625, 'learning_rate': 2.8191758539671066e-05, 'epoch': 0.12}
{'loss': 0.9397, 'learning_rate': 2.8189047532983918e-05, 'epoch': 0.12}
{'loss': 1.6626, 'learning_rate': 2.8186336526296766e-05, 'epoch': 0.12}
{'loss': 1.2204, 'learning_rate': 2.8183625519609618e-05, 'epoch': 0.12}
{'loss': 1.2684, 'learning_rate': 2.8180914512922463e-05, 'epoch': 0.12}
{'loss': 1.4496, 'learning_rate': 2.8178203506235315e-05, 'epoch': 0.12}
{'loss': 1.2482, 'learning_rate': 2.8175492499548167e-05, 'epoch': 0.12}
{'loss': 1.2186, 'learning_rate': 2.8172781492861015e-05, 'epoch': 0.12}
{'loss': 1.0006, 'learning_rate': 2.8170070486173867e-05, 'epoch': 0.12}

  6%|▌         | 676/11066 [02:28<38:14,  4.53it/s]
  6%|▌         | 677/11066 [02:29<38:16,  4.52it/s]
                                                   

  6%|▌         | 677/11066 [02:29<38:16,  4.52it/s]
  6%|▌         | 678/11066 [02:29<38:19,  4.52it/s]
                                                   

  6%|▌         | 678/11066 [02:29<38:19,  4.52it/s]
  6%|▌         | 679/11066 [02:29<38:04,  4.55it/s]
                                                   

  6%|▌         | 679/11066 [02:29<38:04,  4.55it/s]
  6%|▌         | 680/11066 [02:29<37:56,  4.56it/s]
                                                   

  6%|▌         | 680/11066 [02:29<37:56,  4.56it/s]
  6%|▌         | 681/11066 [02:29<38:06,  4.54it/s]
                                                   

  6%|▌         | 681/11066 [02:29<38:06,  4.54it/s]
  6%|▌         | 682/11066 [02:30<37:56,  4.56it/s]
                                                   

  6%|▌         | 682/11066 [02:30<37:56,  4.56it/s]
  6%|▌         | 683/11066 [02:30<37:40,  4.59it/s]
                                                   

  6%|▌         | 683/11066 [02:30<37:40,  4.59it/s]
  6%|▌         | 684/11066 [02:30<37:53,  4.57it/s]
                                                   

  6%|▌         | 684/11066 [02:30<37:53,  4.57it/s]
  6%|▌         | 685/11066 [02:30<38:07,  4.54it/s]
                                                   

  6%|▌         | 685/11066 [02:30<38:07,  4.54it/s]
  6%|▌         | 686/11066 [02:31<38:15,  4.52it/s]
                                                   

  6%|▌         | 686/11066 [02:31<38:15,  4.52it/s]
  6%|▌         | 687/11066 [02:31<37:34,  4.60it/s]
                                                   

  6%|▌         | 687/11066 [02:31<37:34,  4.60it/s]
  6%|▌         | 688/11066 [02:31<38:00,  4.55it/s]
                                                   

  6%|▌         | 688/11066 [02:31<38:00,  4.55it/s]
  6%|▌         | 689/11066 [02:31<38:13,  4.52it/s]
                                                   

  6%|▌         | 689/11066 [02:31<38:13,  4.52it/s]
  6%|▌         | 690/11066 [02:31<38:17,  4.52it/s]
                                                   

  6%|▌         | 690/11066 [02:31<38:17,  4.52it/s]
  6%|▌         | 691/11066 [02:32<38:19,  4.51it/s]
                                                   

  6%|▌         | 691/11066 [02:32<38:19,  4.51it/s]
  6%|▋         | 692/11066 [02:32<38:20,  4.51it/s]
                                                   

  6%|▋         | 692/11066 [02:32<38:20,  4.51it/s]
  6%|▋         | 693/11066 [02:32<38:22,  4.51it/s]
                                                   

  6%|▋         | 693/11066 [02:32<38:22,  4.51it/s]
  6%|▋         | 694/11066 [02:32<38:19,  4.51it/s]
                                                   

  6%|▋         | 694/11066 [02:32<38:19,  4.51it/s]
  6%|▋         | 695/11066 [02:32<38:21,  4.51it/s]
                                                   

  6%|▋         | 695/11066 [02:33<38:21,  4.51it/s]
  6%|▋         | 696/11066 [02:33<38:02,  4.54it/s]
                                                   

  6%|▋         | 696/11066 [02:33<38:02,  4.54it/s]
  6%|▋         | 697/11066 [02:33<37:58,  4.55it/s]
                                                   

  6%|▋         | 697/11066 [02:33<37:58,  4.55it/s]
  6%|▋         | 698/11066 [02:33<38:03,  4.54it/s]
                                                   

  6%|▋         | 698/11066 [02:33<38:03,  4.54it/s]
  6%|▋         | 699/11066 [02:33<37:37,  4.59it/s]
                                                   

  6%|▋         | 699/11066 [02:33<37:37,  4.59it/s]
  6%|▋         | 700/11066 [02:34<37:30,  4.61it/s]
                                                   

  6%|▋         | 700/11066 [02:34<37:30,  4.61it/s]
  6%|▋         | 701/11066 [02:34<37:07,  4.65it/s]
                                                   

  6%|▋         | 701/11066 [02:34<37:07,  4.65it/s]
  6%|▋         | 702/11066 [02:34<37:27,  4.61it/s]
                                                   

  6%|▋         | 702/11066 [02:34<37:27,  4.61it/s]
  6%|▋         | 703/11066 [02:34<37:42,  4.58it/s]
                                                   

  6%|▋         | 703/11066 [02:34<37:42,  4.58it/s]
  6%|▋         | 704/11066 [02:34<37:55,  4.55it/s]
                                                   

  6%|▋         | 704/11066 [02:34<37:55,  4.55it/s]
  6%|▋         | 705/11066 [02:35<38:04,  4.54it/s]
                                                   

  6%|▋         | 705/11066 [02:35<38:04,  4.54it/s]
  6%|▋         | 706/11066 [02:35<38:09,  4.52it/s]
                                                   

  6%|▋         | 706/11066 [02:35<38:09,  4.52it/s]
  6%|▋         | 707/11066 [02:35<38:14,  4.51it/s]
                                                   

  6%|▋         | 707/11066 [02:35<38:14,  4.51it/s]
  6%|▋         | 708/11066 [02:35<38:15,  4.51it/s]
                                                   

  6%|▋         | 708/11066 [02:35<38:15,  4.51it/s]
  6%|▋         | 709/11066 [02:36<38:18,  4.51it/s]
                                                   

  6%|▋         | 709/11066 [02:36<38:18,  4.51it/s]
  6%|▋         | 710/11066 [02:36<38:20,  4.50it/s]
                                                   

  6%|▋         | 710/11066 [02:36<38:20,  4.50it/s]
  6%|▋         | 711/11066 [02:36<38:19,  4.50it/s]
                                                   

  6%|▋         | 711/11066 [02:36<38:19,  4.50it/s]
  6%|▋         | 712/11066 [02:36<38:18,  4.50it/s]
                                                   

  6%|▋         | 712/11066 [02:36<38:18,  4.50it/s]
  6%|▋         | 713/11066 [02:36<38:00,  4.54it/s]
                                                   

  6%|▋         | 713/11066 [02:36<38:00,  4.54it/s]
  6%|▋         | 714/11066 [02:37<38:10,  4.52it/s]
                                                   

  6%|▋         | 714/11066 [02:37<38:10,  4.52it/s]
  6%|▋         | 715/11066 [02:37<37:37,  4.59it/s]
                                                   

  6%|▋         | 715/11066 [02:37<37:37,  4.59it/s]
  6%|▋         | 716/11066 [02:37<37:48,  4.56it/s]
                                                   

  6%|▋         | 716/11066 [02:37<37:48,  4.56it/s]
  6%|▋         | 717/11066 [02:37<37:54,  4.55it/s]
                                                   

  6%|▋         | 717/11066 [02:37<37:54,  4.55it/s]
  6%|▋         | 718/11066 [02:38<37:42,  4.57it/s]
                                                   

  6%|▋         | 718/11066 [02:38<37:42,  4.57it/s]
  6%|▋         | 719/11066 [02:38<37:14,  4.63it/s]
                                                   

  6%|▋         | 719/11066 [02:38<37:14,  4.63it/s]
  7%|▋         | 720/11066 [02:38<37:31,  4.60it/s]
                                                   

  7%|▋         | 720/11066 [02:38<37:31,  4.60it/s]
  7%|▋         | 721/11066 [02:38<37:41,  4.58it/s]
                                                   

  7%|▋         | 721/11066 [02:38<37:41,  4.58it/s]
  7%|▋         | 722/11066 [02:38<37:34,  4.59it/s]
                                                   

  7%|▋         | 722/11066 [02:38<37:34,  4.59it/s]
  7%|▋         | 723/11066 [02:39<37:21,  4.61it/s]
                                                   

  7%|▋         | 723/11066 [02:39<37:21,  4.61it/s]
  7%|▋         | 724/11066 [02:39<37:17,  4.62it/s]
                                                   

  7%|▋         | 724/11066 [02:39<37:17,  4.62it/s]
  7%|▋         | 725/11066 [02:39<37:04,  4.65it/s]
                                                   

  7%|▋         | 725/11066 [02:39<37:04,  4.65it/s]
  7%|▋         | 726/11066 [02:39<37:27,  4.60it/s]
                                                   

  7%|▋         | 726/11066 [02:39<37:27,  4.60it/s]
  7%|▋         | 727/11066 [02:40<37:44,  4.57it/s]
                                                   

  7%|▋         | 727/11066 [02:40<37:44,  4.57it/s]
  7%|▋         | 728/11066 [02:40<37:57,  4.54it/s]
                                                   

  7%|▋         | 728/11066 [02:40<37:57,  4.54it/s]
  7%|▋         | 729/11066 [02:40<37:47,  4.56it/s]
                                                   

  7%|▋         | 729/11066 [02:40<37:47,  4.56it/s]
  7%|▋         | 730/11066 [02:40<37:28,  4.60it/s]
                                                   

  7%|▋         | 730/11066 [02:40<37:28,  4.60it/s]
  7%|▋         | 731/11066 [02:40<37:51,  4.55it/s]
                                                   

  7%|▋         | 731/11066 [02:40<37:51,  4.55it/s]
  7%|▋         | 732/11066 [02:41<38:03,  4.53it/s]
                                                   

  7%|▋         | 732/11066 [02:41<38:03,  4.53it/s]
  7%|▋         | 733/11066 [02:41<37:50,  4.55it/s]
                                                   

  7%|▋         | 733/11066 [02:41<37:50,  4.55it/s]
  7%|▋         | 734/11066 [02:41<37:16,  4.62it/s]
                                                   

  7%|▋         | 734/11066 [02:41<37:16,  4.62it/s]
  7%|▋         | 735/11066 [02:41<37:34,  4.58it/s]
                                                   

  7%|▋         | 735/11066 [02:41<37:34,  4.58it/s]
  7%|▋         | 736/11066 [02:41<37:46,  4.56it/s]
                                                   

  7%|▋         | 736/11066 [02:41<37:46,  4.56it/s]
  7%|▋         | 737/11066 [02:42<37:57,  4.54it/s]
                                                   

  7%|▋         | 737/11066 [02:42<37:57,  4.54it/s]
  7%|▋         | 738/11066 [02:42<37:46,  4.56it/s]
                                                   

  7%|▋         | 738/11066 [02:42<37:46,  4.56it/s]
  7%|▋         | 739/11066 [02:42<37:44,  4.56it/s]
                                                   

  7%|▋         | 739/11066 [02:42<37:44,  4.56it/s]
  7%|▋         | 740/11066 [02:42<37:37,  4.57it/s]
                                                   

  7%|▋         | 740/11066 [02:42<37:37,  4.57it/s]
  7%|▋         | 741/11066 [02:43<37:16,  4.62it/s]
                                                   

  7%|▋         | 741/11066 [02:43<37:16,  4.62it/s]
  7%|▋         | 742/11066 [02:43<37:40,  4.57it/s]
                                                   

  7%|▋         | 742/11066 [02:43<37:40,  4.57it/s]
  7%|▋         | 743/11066 [02:43<37:34,  4.58it/s]
                                                   

  7%|▋         | 743/11066 [02:43<37:34,  4.58it/s]
  7%|▋         | 744/11066 [02:43<37:07,  4.63it/s]
                                                   

  7%|▋         | 744/11066 [02:43<37:07,  4.63it/s]
  7%|▋         | 745/11066 [02:43<37:33,  4.58it/s]
                                                   

  7%|▋         | 745/11066 [02:43<37:33,  4.58it/s]
  7%|▋         | 746/11066 [02:44<37:42,  4.56it/s]
                                                   

  7%|▋         | 746/11066 [02:44<37:42,  4.56it/s]
  7%|▋         | 747/11066 [02:44<37:15,  4.62it/s]
                                                   

  7%|▋         | 747/11066 [02:44<37:15,  4.62it/s]
  7%|▋         | 748/11066 [02:44<36:48,  4.67it/s]
                                                   

  7%|▋         | 748/11066 [02:44<36:48,  4.67it/s]
  7%|▋         | 749/11066 [02:44<37:01,  4.64it/s]
                                                   

  7%|▋         | 749/11066 [02:44<37:01,  4.64it/s]
  7%|▋         | 750/11066 [02:45<36:41,  4.69it/s]
                                                   

  7%|▋         | 750/11066 [02:45<36:41,  4.69it/s]
  7%|▋         | 751/11066 [02:45<36:39,  4.69it/s]
                                                   

  7%|▋         | 751/11066 [02:45<36:39,  4.69it/s]
  7%|▋         | 752/11066 [02:45<36:46,  4.67it/s]
                                                   

  7%|▋         | 752/11066 [02:45<36:46,  4.67it/s]
  7%|▋         | 753/11066 [02:45<36:49,  4.67it/s]
                                                   

  7%|▋         | 753/11066 [02:45<36:49,  4.67it/s]
  7%|▋         | 754/11066 [02:45<37:15,  4.61it/s]
                                                   

  7%|▋         | 754/11066 [02:45<37:15,  4.61it/s]
  7%|▋         | 755/11066 [02:46<37:20,  4.60it/s]
                                                   

  7%|▋         | 755/11066 [02:46<37:20,  4.60it/s]
  7%|▋         | 756/11066 [02:46<37:28,  4.59it/s]
                                                   

  7%|▋         | 756/11066 [02:46<37:28,  4.59it/s]
  7%|▋         | 757/11066 [02:46<37:21,  4.60it/s]
                                                   

  7%|▋         | 757/11066 [02:46<37:21,  4.60it/s]
  7%|▋         | 758/11066 [02:46<36:59,  4.64it/s]
                                                   

  7%|▋         | 758/11066 [02:46<36:59,  4.64it/s]
  7%|▋         | 759/11066 [02:46<36:53,  4.66it/s]
                                                   

  7%|▋         | 759/11066 [02:46<36:53,  4.66it/s]
  7%|▋         | 760/11066 [02:47<37:09,  4.62it/s]
                                                   

  7%|▋         | 760/11066 [02:47<37:09,  4.62it/s]
  7%|▋         | 761/11066 [02:47<36:54,  4.65it/s]
                                                   

  7%|▋         | 761/11066 [02:47<36:54,  4.65it/s]
  7%|▋         | 762/11066 [02:47<36:46,  4.67it/s]
                                                   

  7%|▋         | 762/11066 [02:47<36:46,  4.67it/s]
  7%|▋         | 763/11066 [02:47<36:28,  4.71it/s]
                                                   

  7%|▋         | 763/11066 [02:47<36:28,  4.71it/s]
  7%|▋         | 764/11066 [02:48<36:44,  4.67it/s]
                                                   

  7%|▋         | 764/11066 [02:48<36:44,  4.67it/s]
  7%|▋         | 765/11066 [02:48<36:30,  4.70it/s]
                                                   

  7%|▋         | 765/11066 [02:48<36:30,  4.70it/s]
  7%|▋         | 766/11066 [02:48<36:56,  4.65it/s]
                                                   

  7%|▋         | 766/11066 [02:48<36:56,  4.65it/s]
  7%|▋         | 767/11066 [02:48<36:59,  4.64it/s]
                                                   

  7%|▋         | 767/11066 [02:48<36:59,  4.64it/s]
  7%|▋         | 768/11066 [02:48<37:06,  4.63it/s]
                                                   

  7%|▋         | 768/11066 [02:48<37:06,  4.63it/s]
  7%|▋         | 769/11066 [02:49<37:06,  4.62it/s]
                                                   

  7%|▋         | 769/11066 [02:49<37:06,  4.62it/s]
  7%|▋         | 770/11066 [02:49<37:00,  4.64it/s]
                                                   

  7%|▋         | 770/11066 [02:49<37:00,  4.64it/s]
  7%|▋         | 771/11066 [02:49<37:00,  4.64it/s]
                                                   

  7%|▋         | 771/11066 [02:49<37:00,  4.64it/s]
  7%|▋         | 772/11066 [02:49<37:03,  4.63it/s]
                                                   

  7%|▋         | 772/11066 [02:49<37:03,  4.63it/s]
  7%|▋         | 773/11066 [02:49<37:13,  4.61it/s]
                                                   

  7%|▋         | 773/11066 [02:49<37:13,  4.61it/s]
  7%|▋         | 774/11066 [02:50<37:01,  4.63it/s]
                                                   

  7%|▋         | 774/11066 [02:50<37:01,  4.63it/s]
  7%|▋         | 775/11066 [02:50<37:22,  4.59it/s]
                                                   

  7%|▋         | 775/11066 [02:50<37:22,  4.59it/s]
  7%|▋         | 776/11066 [02:50<37:39,  4.55it/s]
                                                   

  7%|▋         | 776/11066 [02:50<37:39,  4.55it/s]
  7%|▋         | 777/11066 [02:50<37:55,  4.52it/s]
                                                   

  7%|▋         | 777/11066 [02:50<37:55,  4.52it/s]
  7%|▋         | 778/11066 [02:51<38:12,  4.49it/s]
                                                   

  7%|▋         | 778/11066 [02:51<38:12,  4.49it/s]
  7%|▋         | 779/11066 [02:51<38:10,  4.49it/s]
                                                   

  7%|▋         | 779/11066 [02:51<38:10,  4.49it/s]
  7%|▋         | 780/11066 [02:51<38:09,  4.49it/s]
                                                   

  7%|▋         | 780/11066 [02:51<38:09,  4.49it/s]
  7%|▋         | 781/11066 [02:51<38:09,  4.49it/s]
                                                   

  7%|▋         | 781/11066 [02:51<38:09,  4.49it/s]
  7%|▋         | 782/11066 [02:51<38:15,  4.48it/s]
                                                   

  7%|▋         | 782/11066 [02:51<38:15,  4.48it/s]
  7%|▋         | 783/11066 [02:52<38:18,  4.47it/s]
                                                   

  7%|▋         | 783/11066 [02:52<38:18,  4.47it/s]
  7%|▋         | 784/11066 [02:52<37:37,  4.55it/s]
                                                   

  7%|▋         | 784/11066 [02:52<37:37,  4.55it/s]
  7%|▋         | 785/11066 [02:52<37:13,  4.60it/s]
                                                   

  7%|▋         | 785/11066 [02:52<37:13,  4.60it/s]
  7%|▋         | 786/11066 [02:52<36:47,  4.66it/s]
                                                   

  7%|▋         | 786/11066 [02:52<36:47,  4.66it/s]
  7%|▋         | 787/11066 [02:53<37:15,  4.60it/s]
                                                   

  7%|▋         | 787/11066 [02:53<37:15,  4.60it/s]
  7%|▋         | 788/11066 [02:53<37:32,  4.56it/s]
                                                   
{'loss': 1.336, 'learning_rate': 2.816735947948672e-05, 'epoch': 0.12}
{'loss': 1.8145, 'learning_rate': 2.8164648472799567e-05, 'epoch': 0.12}
{'loss': 1.8692, 'learning_rate': 2.816193746611242e-05, 'epoch': 0.12}
{'loss': 2.5005, 'learning_rate': 2.8159226459425267e-05, 'epoch': 0.12}
{'loss': 1.6582, 'learning_rate': 2.8156515452738116e-05, 'epoch': 0.12}
{'loss': 2.3782, 'learning_rate': 2.8153804446050968e-05, 'epoch': 0.12}
{'loss': 2.8293, 'learning_rate': 2.8151093439363816e-05, 'epoch': 0.12}
{'loss': 1.4738, 'learning_rate': 2.8148382432676668e-05, 'epoch': 0.12}
{'loss': 1.7961, 'learning_rate': 2.814567142598952e-05, 'epoch': 0.12}
{'loss': 1.7145, 'learning_rate': 2.8142960419302368e-05, 'epoch': 0.12}
{'loss': 0.9449, 'learning_rate': 2.814024941261522e-05, 'epoch': 0.12}
{'loss': 1.1767, 'learning_rate': 2.813753840592807e-05, 'epoch': 0.12}
{'loss': 1.4792, 'learning_rate': 2.8134827399240917e-05, 'epoch': 0.12}
{'loss': 1.2841, 'learning_rate': 2.813211639255377e-05, 'epoch': 0.12}
{'loss': 1.864, 'learning_rate': 2.812940538586662e-05, 'epoch': 0.12}
{'loss': 1.2993, 'learning_rate': 2.812669437917947e-05, 'epoch': 0.12}
{'loss': 2.2131, 'learning_rate': 2.812398337249232e-05, 'epoch': 0.13}
{'loss': 1.2374, 'learning_rate': 2.812127236580517e-05, 'epoch': 0.13}
{'loss': 0.9613, 'learning_rate': 2.811856135911802e-05, 'epoch': 0.13}
{'loss': 0.9574, 'learning_rate': 2.811585035243087e-05, 'epoch': 0.13}
{'loss': 1.208, 'learning_rate': 2.8113139345743718e-05, 'epoch': 0.13}
{'loss': 1.4253, 'learning_rate': 2.811042833905657e-05, 'epoch': 0.13}
{'loss': 1.2199, 'learning_rate': 2.810771733236942e-05, 'epoch': 0.13}
{'loss': 1.0694, 'learning_rate': 2.810500632568227e-05, 'epoch': 0.13}
{'loss': 2.1214, 'learning_rate': 2.8102295318995122e-05, 'epoch': 0.13}
{'loss': 1.0465, 'learning_rate': 2.8099584312307974e-05, 'epoch': 0.13}
{'loss': 1.4756, 'learning_rate': 2.8096873305620822e-05, 'epoch': 0.13}
{'loss': 1.7896, 'learning_rate': 2.809416229893367e-05, 'epoch': 0.13}
{'loss': 1.118, 'learning_rate': 2.809145129224652e-05, 'epoch': 0.13}
{'loss': 1.5795, 'learning_rate': 2.808874028555937e-05, 'epoch': 0.13}
{'loss': 1.8597, 'learning_rate': 2.8086029278872223e-05, 'epoch': 0.13}
{'loss': 1.3051, 'learning_rate': 2.808331827218507e-05, 'epoch': 0.13}
{'loss': 2.2246, 'learning_rate': 2.8080607265497923e-05, 'epoch': 0.13}
{'loss': 1.3521, 'learning_rate': 2.8077896258810775e-05, 'epoch': 0.13}
{'loss': 1.7955, 'learning_rate': 2.8075185252123623e-05, 'epoch': 0.13}
{'loss': 1.9576, 'learning_rate': 2.807247424543647e-05, 'epoch': 0.13}
{'loss': 0.7538, 'learning_rate': 2.8069763238749323e-05, 'epoch': 0.13}
{'loss': 2.2223, 'learning_rate': 2.8067052232062172e-05, 'epoch': 0.13}
{'loss': 2.1558, 'learning_rate': 2.8064341225375024e-05, 'epoch': 0.13}
{'loss': 2.0614, 'learning_rate': 2.8061630218687872e-05, 'epoch': 0.13}
{'loss': 1.6626, 'learning_rate': 2.8058919212000724e-05, 'epoch': 0.13}
{'loss': 1.229, 'learning_rate': 2.8056208205313576e-05, 'epoch': 0.13}
{'loss': 1.4634, 'learning_rate': 2.8053497198626424e-05, 'epoch': 0.13}
{'loss': 1.4366, 'learning_rate': 2.8050786191939273e-05, 'epoch': 0.13}
{'loss': 0.9298, 'learning_rate': 2.8048075185252125e-05, 'epoch': 0.13}
{'loss': 1.1517, 'learning_rate': 2.8045364178564973e-05, 'epoch': 0.13}
{'loss': 2.3786, 'learning_rate': 2.8042653171877825e-05, 'epoch': 0.13}
{'loss': 1.9484, 'learning_rate': 2.8039942165190677e-05, 'epoch': 0.13}
{'loss': 1.4541, 'learning_rate': 2.8037231158503525e-05, 'epoch': 0.13}
{'loss': 1.6789, 'learning_rate': 2.8034520151816377e-05, 'epoch': 0.13}
{'loss': 0.9742, 'learning_rate': 2.8031809145129225e-05, 'epoch': 0.13}
{'loss': 1.3029, 'learning_rate': 2.8029098138442074e-05, 'epoch': 0.13}
{'loss': 1.2607, 'learning_rate': 2.8026387131754926e-05, 'epoch': 0.13}
{'loss': 1.0348, 'learning_rate': 2.8023676125067774e-05, 'epoch': 0.13}
{'loss': 1.278, 'learning_rate': 2.8020965118380626e-05, 'epoch': 0.13}
{'loss': 1.1018, 'learning_rate': 2.8018254111693478e-05, 'epoch': 0.13}
{'loss': 1.7663, 'learning_rate': 2.8015543105006326e-05, 'epoch': 0.13}
{'loss': 1.0289, 'learning_rate': 2.8012832098319178e-05, 'epoch': 0.13}
{'loss': 1.8278, 'learning_rate': 2.801012109163203e-05, 'epoch': 0.13}
{'loss': 1.8795, 'learning_rate': 2.8007410084944875e-05, 'epoch': 0.13}
{'loss': 1.4956, 'learning_rate': 2.8004699078257727e-05, 'epoch': 0.13}
{'loss': 1.201, 'learning_rate': 2.8001988071570575e-05, 'epoch': 0.13}
{'loss': 1.3892, 'learning_rate': 2.7999277064883427e-05, 'epoch': 0.13}
{'loss': 0.8644, 'learning_rate': 2.799656605819628e-05, 'epoch': 0.13}
{'loss': 1.2239, 'learning_rate': 2.7993855051509127e-05, 'epoch': 0.13}
{'loss': 1.8824, 'learning_rate': 2.799114404482198e-05, 'epoch': 0.13}
{'loss': 1.7849, 'learning_rate': 2.798843303813483e-05, 'epoch': 0.13}
{'loss': 1.6522, 'learning_rate': 2.7985722031447676e-05, 'epoch': 0.13}
{'loss': 1.9213, 'learning_rate': 2.7983011024760528e-05, 'epoch': 0.13}
{'loss': 1.7799, 'learning_rate': 2.798030001807338e-05, 'epoch': 0.13}
{'loss': 1.5043, 'learning_rate': 2.7977589011386228e-05, 'epoch': 0.13}
{'loss': 0.9324, 'learning_rate': 2.797487800469908e-05, 'epoch': 0.14}
{'loss': 1.5638, 'learning_rate': 2.7972166998011928e-05, 'epoch': 0.14}
{'loss': 1.6166, 'learning_rate': 2.796945599132478e-05, 'epoch': 0.14}
{'loss': 1.0174, 'learning_rate': 2.7966744984637632e-05, 'epoch': 0.14}
{'loss': 1.2929, 'learning_rate': 2.7964033977950477e-05, 'epoch': 0.14}
{'loss': 1.2656, 'learning_rate': 2.796132297126333e-05, 'epoch': 0.14}
{'loss': 1.3442, 'learning_rate': 2.795861196457618e-05, 'epoch': 0.14}
{'loss': 2.075, 'learning_rate': 2.795590095788903e-05, 'epoch': 0.14}
{'loss': 1.6361, 'learning_rate': 2.795318995120188e-05, 'epoch': 0.14}
{'loss': 1.3289, 'learning_rate': 2.7950478944514733e-05, 'epoch': 0.14}
{'loss': 1.9188, 'learning_rate': 2.794776793782758e-05, 'epoch': 0.14}
{'loss': 1.4185, 'learning_rate': 2.7945056931140433e-05, 'epoch': 0.14}
{'loss': 1.4485, 'learning_rate': 2.7942345924453278e-05, 'epoch': 0.14}
{'loss': 1.5796, 'learning_rate': 2.793963491776613e-05, 'epoch': 0.14}
{'loss': 1.5179, 'learning_rate': 2.7936923911078982e-05, 'epoch': 0.14}
{'loss': 1.1652, 'learning_rate': 2.793421290439183e-05, 'epoch': 0.14}
{'loss': 1.4621, 'learning_rate': 2.7931501897704682e-05, 'epoch': 0.14}
{'loss': 2.2181, 'learning_rate': 2.7928790891017534e-05, 'epoch': 0.14}
{'loss': 0.7592, 'learning_rate': 2.7926079884330382e-05, 'epoch': 0.14}
{'loss': 0.9101, 'learning_rate': 2.7923368877643234e-05, 'epoch': 0.14}
{'loss': 1.4595, 'learning_rate': 2.7920657870956083e-05, 'epoch': 0.14}
{'loss': 1.9067, 'learning_rate': 2.791794686426893e-05, 'epoch': 0.14}
{'loss': 1.1606, 'learning_rate': 2.7915235857581783e-05, 'epoch': 0.14}
{'loss': 0.9222, 'learning_rate': 2.791252485089463e-05, 'epoch': 0.14}
{'loss': 1.8671, 'learning_rate': 2.7909813844207483e-05, 'epoch': 0.14}
{'loss': 0.886, 'learning_rate': 2.7907102837520335e-05, 'epoch': 0.14}
{'loss': 1.6442, 'learning_rate': 2.7904391830833183e-05, 'epoch': 0.14}
{'loss': 1.9321, 'learning_rate': 2.7901680824146032e-05, 'epoch': 0.14}
{'loss': 1.2881, 'learning_rate': 2.7898969817458884e-05, 'epoch': 0.14}
{'loss': 1.8495, 'learning_rate': 2.7896258810771732e-05, 'epoch': 0.14}
{'loss': 2.0968, 'learning_rate': 2.7893547804084584e-05, 'epoch': 0.14}
{'loss': 1.6106, 'learning_rate': 2.7890836797397436e-05, 'epoch': 0.14}
{'loss': 1.8478, 'learning_rate': 2.7888125790710284e-05, 'epoch': 0.14}
{'loss': 1.4958, 'learning_rate': 2.7885414784023136e-05, 'epoch': 0.14}
{'loss': 1.6092, 'learning_rate': 2.7882703777335984e-05, 'epoch': 0.14}
{'loss': 1.5398, 'learning_rate': 2.7879992770648833e-05, 'epoch': 0.14}
{'loss': 1.2929, 'learning_rate': 2.7877281763961685e-05, 'epoch': 0.14}
{'loss': 1.8968, 'learning_rate': 2.7874570757274533e-05, 'epoch': 0.14}
{'loss': 1.5639, 'learning_rate': 2.7871859750587385e-05, 'epoch': 0.14}
{'loss': 0.9741, 'learning_rate': 2.7869148743900237e-05, 'epoch': 0.14}
{'loss': 1.7381, 'learning_rate': 2.7866437737213085e-05, 'epoch': 0.14}

  7%|▋         | 788/11066 [02:53<37:32,  4.56it/s]
  7%|▋         | 789/11066 [02:53<37:46,  4.53it/s]
                                                   

  7%|▋         | 789/11066 [02:53<37:46,  4.53it/s]
  7%|▋         | 790/11066 [02:53<37:34,  4.56it/s]
                                                   

  7%|▋         | 790/11066 [02:53<37:34,  4.56it/s]
  7%|▋         | 791/11066 [02:53<37:17,  4.59it/s]
                                                   

  7%|▋         | 791/11066 [02:53<37:17,  4.59it/s]
  7%|▋         | 792/11066 [02:54<36:56,  4.63it/s]
                                                   

  7%|▋         | 792/11066 [02:54<36:56,  4.63it/s]
  7%|▋         | 793/11066 [02:54<37:21,  4.58it/s]
                                                   

  7%|▋         | 793/11066 [02:54<37:21,  4.58it/s]
  7%|▋         | 794/11066 [02:54<37:23,  4.58it/s]
                                                   

  7%|▋         | 794/11066 [02:54<37:23,  4.58it/s]
  7%|▋         | 795/11066 [02:54<37:33,  4.56it/s]
                                                   

  7%|▋         | 795/11066 [02:54<37:33,  4.56it/s]
  7%|▋         | 796/11066 [02:55<37:09,  4.61it/s]
                                                   

  7%|▋         | 796/11066 [02:55<37:09,  4.61it/s]
  7%|▋         | 797/11066 [02:55<37:26,  4.57it/s]
                                                   

  7%|▋         | 797/11066 [02:55<37:26,  4.57it/s]
  7%|▋         | 798/11066 [02:55<37:08,  4.61it/s]
                                                   

  7%|▋         | 798/11066 [02:55<37:08,  4.61it/s]
  7%|▋         | 799/11066 [02:55<36:51,  4.64it/s]
                                                   

  7%|▋         | 799/11066 [02:55<36:51,  4.64it/s]
  7%|▋         | 800/11066 [02:55<36:55,  4.63it/s]
                                                   

  7%|▋         | 800/11066 [02:55<36:55,  4.63it/s]
  7%|▋         | 801/11066 [02:56<36:34,  4.68it/s]
                                                   

  7%|▋         | 801/11066 [02:56<36:34,  4.68it/s]
  7%|▋         | 802/11066 [02:56<37:05,  4.61it/s]
                                                   

  7%|▋         | 802/11066 [02:56<37:05,  4.61it/s]
  7%|▋         | 803/11066 [02:56<37:26,  4.57it/s]
                                                   

  7%|▋         | 803/11066 [02:56<37:26,  4.57it/s]
  7%|▋         | 804/11066 [02:56<37:12,  4.60it/s]
                                                   

  7%|▋         | 804/11066 [02:56<37:12,  4.60it/s]
  7%|▋         | 805/11066 [02:56<36:53,  4.64it/s]
                                                   

  7%|▋         | 805/11066 [02:56<36:53,  4.64it/s]
  7%|▋         | 806/11066 [02:57<37:06,  4.61it/s]
                                                   

  7%|▋         | 806/11066 [02:57<37:06,  4.61it/s]
  7%|▋         | 807/11066 [02:57<36:58,  4.62it/s]
                                                   

  7%|▋         | 807/11066 [02:57<36:58,  4.62it/s]
  7%|▋         | 808/11066 [02:57<36:40,  4.66it/s]
                                                   

  7%|▋         | 808/11066 [02:57<36:40,  4.66it/s]
  7%|▋         | 809/11066 [02:57<36:37,  4.67it/s]
                                                   

  7%|▋         | 809/11066 [02:57<36:37,  4.67it/s]
  7%|▋         | 810/11066 [02:58<36:26,  4.69it/s]
                                                   

  7%|▋         | 810/11066 [02:58<36:26,  4.69it/s]
  7%|▋         | 811/11066 [02:58<36:09,  4.73it/s]
                                                   

  7%|▋         | 811/11066 [02:58<36:09,  4.73it/s]
  7%|▋         | 812/11066 [02:58<36:35,  4.67it/s]
                                                   

  7%|▋         | 812/11066 [02:58<36:35,  4.67it/s]
  7%|▋         | 813/11066 [02:58<36:44,  4.65it/s]
                                                   

  7%|▋         | 813/11066 [02:58<36:44,  4.65it/s]
  7%|▋         | 814/11066 [02:58<37:05,  4.61it/s]
                                                   

  7%|▋         | 814/11066 [02:58<37:05,  4.61it/s]
  7%|▋         | 815/11066 [02:59<36:50,  4.64it/s]
                                                   

  7%|▋         | 815/11066 [02:59<36:50,  4.64it/s]
  7%|▋         | 816/11066 [02:59<37:09,  4.60it/s]
                                                   

  7%|▋         | 816/11066 [02:59<37:09,  4.60it/s]
  7%|▋         | 817/11066 [02:59<36:55,  4.63it/s]
                                                   

  7%|▋         | 817/11066 [02:59<36:55,  4.63it/s]
  7%|▋         | 818/11066 [02:59<37:22,  4.57it/s]
                                                   

  7%|▋         | 818/11066 [02:59<37:22,  4.57it/s]
  7%|▋         | 819/11066 [02:59<37:38,  4.54it/s]
                                                   

  7%|▋         | 819/11066 [02:59<37:38,  4.54it/s]
  7%|▋         | 820/11066 [03:00<37:54,  4.51it/s]
                                                   

  7%|▋         | 820/11066 [03:00<37:54,  4.51it/s]
  7%|▋         | 821/11066 [03:00<37:59,  4.49it/s]
                                                   

  7%|▋         | 821/11066 [03:00<37:59,  4.49it/s]
  7%|▋         | 822/11066 [03:00<38:00,  4.49it/s]
                                                   

  7%|▋         | 822/11066 [03:00<38:00,  4.49it/s]
  7%|▋         | 823/11066 [03:00<37:56,  4.50it/s]
                                                   

  7%|▋         | 823/11066 [03:00<37:56,  4.50it/s]
  7%|▋         | 824/11066 [03:01<37:38,  4.53it/s]
                                                   

  7%|▋         | 824/11066 [03:01<37:38,  4.53it/s]
  7%|▋         | 825/11066 [03:01<37:02,  4.61it/s]
                                                   

  7%|▋         | 825/11066 [03:01<37:02,  4.61it/s]
  7%|▋         | 826/11066 [03:01<36:36,  4.66it/s]
                                                   

  7%|▋         | 826/11066 [03:01<36:36,  4.66it/s]
  7%|▋         | 827/11066 [03:01<37:04,  4.60it/s]
                                                   

  7%|▋         | 827/11066 [03:01<37:04,  4.60it/s]
  7%|▋         | 828/11066 [03:01<37:19,  4.57it/s]
                                                   

  7%|▋         | 828/11066 [03:01<37:19,  4.57it/s]
  7%|▋         | 829/11066 [03:02<37:34,  4.54it/s]
                                                   

  7%|▋         | 829/11066 [03:02<37:34,  4.54it/s]
  8%|▊         | 830/11066 [03:02<37:24,  4.56it/s]
                                                   

  8%|▊         | 830/11066 [03:02<37:24,  4.56it/s]
  8%|▊         | 831/11066 [03:02<36:57,  4.61it/s]
                                                   

  8%|▊         | 831/11066 [03:02<36:57,  4.61it/s]
  8%|▊         | 832/11066 [03:02<37:07,  4.59it/s]
                                                   

  8%|▊         | 832/11066 [03:02<37:07,  4.59it/s]
  8%|▊         | 833/11066 [03:03<37:25,  4.56it/s]
                                                   

  8%|▊         | 833/11066 [03:03<37:25,  4.56it/s]
  8%|▊         | 834/11066 [03:03<37:40,  4.53it/s]
                                                   

  8%|▊         | 834/11066 [03:03<37:40,  4.53it/s]
  8%|▊         | 835/11066 [03:03<37:54,  4.50it/s]
                                                   

  8%|▊         | 835/11066 [03:03<37:54,  4.50it/s]
  8%|▊         | 836/11066 [03:03<37:56,  4.49it/s]
                                                   

  8%|▊         | 836/11066 [03:03<37:56,  4.49it/s]
  8%|▊         | 837/11066 [03:03<37:54,  4.50it/s]
                                                   

  8%|▊         | 837/11066 [03:03<37:54,  4.50it/s]
  8%|▊         | 838/11066 [03:04<37:52,  4.50it/s]
                                                   

  8%|▊         | 838/11066 [03:04<37:52,  4.50it/s]
  8%|▊         | 839/11066 [03:04<37:53,  4.50it/s]
                                                   

  8%|▊         | 839/11066 [03:04<37:53,  4.50it/s]
  8%|▊         | 840/11066 [03:04<37:51,  4.50it/s]
                                                   

  8%|▊         | 840/11066 [03:04<37:51,  4.50it/s]
  8%|▊         | 841/11066 [03:04<37:53,  4.50it/s]
                                                   

  8%|▊         | 841/11066 [03:04<37:53,  4.50it/s]
  8%|▊         | 842/11066 [03:05<37:53,  4.50it/s]
                                                   

  8%|▊         | 842/11066 [03:05<37:53,  4.50it/s]
  8%|▊         | 843/11066 [03:05<37:51,  4.50it/s]
                                                   

  8%|▊         | 843/11066 [03:05<37:51,  4.50it/s]
  8%|▊         | 844/11066 [03:05<37:50,  4.50it/s]
                                                   

  8%|▊         | 844/11066 [03:05<37:50,  4.50it/s]
  8%|▊         | 845/11066 [03:05<37:49,  4.50it/s]
                                                   

  8%|▊         | 845/11066 [03:05<37:49,  4.50it/s]
  8%|▊         | 846/11066 [03:05<37:52,  4.50it/s]
                                                   

  8%|▊         | 846/11066 [03:05<37:52,  4.50it/s]
  8%|▊         | 847/11066 [03:06<37:51,  4.50it/s]
                                                   

  8%|▊         | 847/11066 [03:06<37:51,  4.50it/s]
  8%|▊         | 848/11066 [03:06<37:49,  4.50it/s]
                                                   

  8%|▊         | 848/11066 [03:06<37:49,  4.50it/s]
  8%|▊         | 849/11066 [03:06<37:50,  4.50it/s]
                                                   

  8%|▊         | 849/11066 [03:06<37:50,  4.50it/s]
  8%|▊         | 850/11066 [03:06<37:50,  4.50it/s]
                                                   

  8%|▊         | 850/11066 [03:06<37:50,  4.50it/s]
  8%|▊         | 851/11066 [03:07<37:49,  4.50it/s]
                                                   

  8%|▊         | 851/11066 [03:07<37:49,  4.50it/s]
  8%|▊         | 852/11066 [03:07<37:48,  4.50it/s]
                                                   

  8%|▊         | 852/11066 [03:07<37:48,  4.50it/s]
  8%|▊         | 853/11066 [03:07<37:47,  4.50it/s]
                                                   

  8%|▊         | 853/11066 [03:07<37:47,  4.50it/s]
  8%|▊         | 854/11066 [03:07<37:48,  4.50it/s]
                                                   

  8%|▊         | 854/11066 [03:07<37:48,  4.50it/s]
  8%|▊         | 855/11066 [03:07<37:49,  4.50it/s]
                                                   

  8%|▊         | 855/11066 [03:07<37:49,  4.50it/s]
  8%|▊         | 856/11066 [03:08<37:49,  4.50it/s]
                                                   

  8%|▊         | 856/11066 [03:08<37:49,  4.50it/s]
  8%|▊         | 857/11066 [03:08<37:49,  4.50it/s]
                                                   

  8%|▊         | 857/11066 [03:08<37:49,  4.50it/s]
  8%|▊         | 858/11066 [03:08<37:48,  4.50it/s]
                                                   

  8%|▊         | 858/11066 [03:08<37:48,  4.50it/s]
  8%|▊         | 859/11066 [03:08<37:46,  4.50it/s]
                                                   

  8%|▊         | 859/11066 [03:08<37:46,  4.50it/s]
  8%|▊         | 860/11066 [03:09<37:45,  4.50it/s]
                                                   

  8%|▊         | 860/11066 [03:09<37:45,  4.50it/s]
  8%|▊         | 861/11066 [03:09<37:46,  4.50it/s]
                                                   

  8%|▊         | 861/11066 [03:09<37:46,  4.50it/s]
  8%|▊         | 862/11066 [03:09<37:44,  4.51it/s]
                                                   

  8%|▊         | 862/11066 [03:09<37:44,  4.51it/s]
  8%|▊         | 863/11066 [03:09<37:44,  4.51it/s]
                                                   

  8%|▊         | 863/11066 [03:09<37:44,  4.51it/s]
  8%|▊         | 864/11066 [03:09<37:44,  4.50it/s]
                                                   

  8%|▊         | 864/11066 [03:09<37:44,  4.50it/s]
  8%|▊         | 865/11066 [03:10<37:46,  4.50it/s]
                                                   

  8%|▊         | 865/11066 [03:10<37:46,  4.50it/s]
  8%|▊         | 866/11066 [03:10<37:48,  4.50it/s]
                                                   

  8%|▊         | 866/11066 [03:10<37:48,  4.50it/s]
  8%|▊         | 867/11066 [03:10<37:48,  4.50it/s]
                                                   

  8%|▊         | 867/11066 [03:10<37:48,  4.50it/s]
  8%|▊         | 868/11066 [03:10<37:47,  4.50it/s]
                                                   

  8%|▊         | 868/11066 [03:10<37:47,  4.50it/s]
  8%|▊         | 869/11066 [03:11<37:46,  4.50it/s]
                                                   

  8%|▊         | 869/11066 [03:11<37:46,  4.50it/s]
  8%|▊         | 870/11066 [03:11<37:47,  4.50it/s]
                                                   

  8%|▊         | 870/11066 [03:11<37:47,  4.50it/s]
  8%|▊         | 871/11066 [03:11<37:48,  4.49it/s]
                                                   

  8%|▊         | 871/11066 [03:11<37:48,  4.49it/s]
  8%|▊         | 872/11066 [03:11<37:47,  4.50it/s]
                                                   

  8%|▊         | 872/11066 [03:11<37:47,  4.50it/s]
  8%|▊         | 873/11066 [03:11<37:46,  4.50it/s]
                                                   

  8%|▊         | 873/11066 [03:11<37:46,  4.50it/s]
  8%|▊         | 874/11066 [03:12<37:49,  4.49it/s]
                                                   

  8%|▊         | 874/11066 [03:12<37:49,  4.49it/s]
  8%|▊         | 875/11066 [03:12<37:48,  4.49it/s]
                                                   

  8%|▊         | 875/11066 [03:12<37:48,  4.49it/s]
  8%|▊         | 876/11066 [03:12<37:47,  4.49it/s]
                                                   

  8%|▊         | 876/11066 [03:12<37:47,  4.49it/s]
  8%|▊         | 877/11066 [03:12<37:43,  4.50it/s]
                                                   

  8%|▊         | 877/11066 [03:12<37:43,  4.50it/s]
  8%|▊         | 878/11066 [03:13<37:42,  4.50it/s]
                                                   

  8%|▊         | 878/11066 [03:13<37:42,  4.50it/s]
  8%|▊         | 879/11066 [03:13<37:44,  4.50it/s]
                                                   

  8%|▊         | 879/11066 [03:13<37:44,  4.50it/s]
  8%|▊         | 880/11066 [03:13<37:45,  4.50it/s]
                                                   

  8%|▊         | 880/11066 [03:13<37:45,  4.50it/s]
  8%|▊         | 881/11066 [03:13<37:47,  4.49it/s]
                                                   

  8%|▊         | 881/11066 [03:13<37:47,  4.49it/s]
  8%|▊         | 882/11066 [03:13<37:49,  4.49it/s]
                                                   

  8%|▊         | 882/11066 [03:13<37:49,  4.49it/s]
  8%|▊         | 883/11066 [03:14<37:46,  4.49it/s]
                                                   

  8%|▊         | 883/11066 [03:14<37:46,  4.49it/s]
  8%|▊         | 884/11066 [03:14<37:44,  4.50it/s]
                                                   

  8%|▊         | 884/11066 [03:14<37:44,  4.50it/s]
  8%|▊         | 885/11066 [03:14<37:44,  4.50it/s]
                                                   

  8%|▊         | 885/11066 [03:14<37:44,  4.50it/s]
  8%|▊         | 886/11066 [03:14<37:43,  4.50it/s]
                                                   

  8%|▊         | 886/11066 [03:14<37:43,  4.50it/s]
  8%|▊         | 887/11066 [03:15<37:42,  4.50it/s]
                                                   

  8%|▊         | 887/11066 [03:15<37:42,  4.50it/s]
  8%|▊         | 888/11066 [03:15<37:44,  4.50it/s]
                                                   

  8%|▊         | 888/11066 [03:15<37:44,  4.50it/s]
  8%|▊         | 889/11066 [03:15<37:44,  4.49it/s]
                                                   

  8%|▊         | 889/11066 [03:15<37:44,  4.49it/s]
  8%|▊         | 890/11066 [03:15<37:44,  4.49it/s]
                                                   

  8%|▊         | 890/11066 [03:15<37:44,  4.49it/s]
  8%|▊         | 891/11066 [03:15<37:45,  4.49it/s]
                                                   

  8%|▊         | 891/11066 [03:15<37:45,  4.49it/s]
  8%|▊         | 892/11066 [03:16<37:44,  4.49it/s]
                                                   

  8%|▊         | 892/11066 [03:16<37:44,  4.49it/s]
  8%|▊         | 893/11066 [03:16<37:42,  4.50it/s]
                                                   

  8%|▊         | 893/11066 [03:16<37:42,  4.50it/s]
  8%|▊         | 894/11066 [03:16<37:41,  4.50it/s]
                                                   

  8%|▊         | 894/11066 [03:16<37:41,  4.50it/s]
  8%|▊         | 895/11066 [03:16<37:40,  4.50it/s]
                                                   

  8%|▊         | 895/11066 [03:16<37:40,  4.50it/s]
  8%|▊         | 896/11066 [03:17<37:42,  4.49it/s]
                                                   

  8%|▊         | 896/11066 [03:17<37:42,  4.49it/s]
  8%|▊         | 897/11066 [03:17<37:43,  4.49it/s]
                                                   

  8%|▊         | 897/11066 [03:17<37:43,  4.49it/s]
  8%|▊         | 898/11066 [03:17<37:40,  4.50it/s]
                                                   

  8%|▊         | 898/11066 [03:17<37:40,  4.50it/s]
  8%|▊         | 899/11066 [03:17<37:42,  4.49it/s]
                                                   

  8%|▊         | 899/11066 [03:17<37:42,  4.49it/s]
  8%|▊         | 900/11066 [03:17<37:41,  4.49it/s]
                                                   

  8%|▊         | 900/11066 [03:17<37:41,  4.49it/s]
  8%|▊         | 901/11066 [03:18<37:43,  4.49it/s]
                                                   
{'loss': 1.915, 'learning_rate': 2.7863726730525937e-05, 'epoch': 0.14}
{'loss': 1.27, 'learning_rate': 2.786101572383879e-05, 'epoch': 0.14}
{'loss': 1.1909, 'learning_rate': 2.7858304717151634e-05, 'epoch': 0.14}
{'loss': 1.4762, 'learning_rate': 2.7855593710464486e-05, 'epoch': 0.14}
{'loss': 1.362, 'learning_rate': 2.7852882703777338e-05, 'epoch': 0.14}
{'loss': 1.1847, 'learning_rate': 2.7850171697090186e-05, 'epoch': 0.14}
{'loss': 1.4034, 'learning_rate': 2.7847460690403038e-05, 'epoch': 0.14}
{'loss': 1.607, 'learning_rate': 2.7844749683715886e-05, 'epoch': 0.14}
{'loss': 2.0379, 'learning_rate': 2.7842038677028738e-05, 'epoch': 0.14}
{'loss': 1.362, 'learning_rate': 2.783932767034159e-05, 'epoch': 0.14}
{'loss': 1.0423, 'learning_rate': 2.7836616663654435e-05, 'epoch': 0.14}
{'loss': 1.3649, 'learning_rate': 2.7833905656967287e-05, 'epoch': 0.14}
{'loss': 2.1617, 'learning_rate': 2.783119465028014e-05, 'epoch': 0.14}
{'loss': 1.2382, 'learning_rate': 2.7828483643592987e-05, 'epoch': 0.14}
{'loss': 1.6331, 'learning_rate': 2.782577263690584e-05, 'epoch': 0.14}
{'loss': 1.3135, 'learning_rate': 2.782306163021869e-05, 'epoch': 0.15}
{'loss': 1.9213, 'learning_rate': 2.782035062353154e-05, 'epoch': 0.15}
{'loss': 1.0475, 'learning_rate': 2.781763961684439e-05, 'epoch': 0.15}
{'loss': 1.7022, 'learning_rate': 2.7814928610157236e-05, 'epoch': 0.15}
{'loss': 1.0803, 'learning_rate': 2.7812217603470088e-05, 'epoch': 0.15}
{'loss': 1.3057, 'learning_rate': 2.780950659678294e-05, 'epoch': 0.15}
{'loss': 1.388, 'learning_rate': 2.7806795590095788e-05, 'epoch': 0.15}
{'loss': 1.3236, 'learning_rate': 2.780408458340864e-05, 'epoch': 0.15}
{'loss': 1.5372, 'learning_rate': 2.7801373576721492e-05, 'epoch': 0.15}
{'loss': 1.4807, 'learning_rate': 2.779866257003434e-05, 'epoch': 0.15}
{'loss': 1.4414, 'learning_rate': 2.7795951563347192e-05, 'epoch': 0.15}
{'loss': 1.1731, 'learning_rate': 2.779324055666004e-05, 'epoch': 0.15}
{'loss': 1.4755, 'learning_rate': 2.779052954997289e-05, 'epoch': 0.15}
{'loss': 1.3674, 'learning_rate': 2.778781854328574e-05, 'epoch': 0.15}
{'loss': 1.2507, 'learning_rate': 2.778510753659859e-05, 'epoch': 0.15}
{'loss': 0.4954, 'learning_rate': 2.778239652991144e-05, 'epoch': 0.15}
{'loss': 1.4325, 'learning_rate': 2.7779685523224293e-05, 'epoch': 0.15}
{'loss': 1.5546, 'learning_rate': 2.777697451653714e-05, 'epoch': 0.15}
{'loss': 1.7425, 'learning_rate': 2.7774263509849993e-05, 'epoch': 0.15}
{'loss': 1.7167, 'learning_rate': 2.777155250316284e-05, 'epoch': 0.15}
{'loss': 1.5157, 'learning_rate': 2.776884149647569e-05, 'epoch': 0.15}
{'loss': 1.6686, 'learning_rate': 2.7766130489788542e-05, 'epoch': 0.15}
{'loss': 1.0087, 'learning_rate': 2.7763419483101394e-05, 'epoch': 0.15}
{'loss': 0.8828, 'learning_rate': 2.7760708476414242e-05, 'epoch': 0.15}
{'loss': 1.3901, 'learning_rate': 2.7757997469727094e-05, 'epoch': 0.15}
{'loss': 1.3027, 'learning_rate': 2.7755286463039942e-05, 'epoch': 0.15}
{'loss': 1.6511, 'learning_rate': 2.7752575456352794e-05, 'epoch': 0.15}
{'loss': 1.7985, 'learning_rate': 2.7749864449665643e-05, 'epoch': 0.15}
{'loss': 0.9074, 'learning_rate': 2.774715344297849e-05, 'epoch': 0.15}
{'loss': 1.0855, 'learning_rate': 2.7744442436291343e-05, 'epoch': 0.15}
{'loss': 1.6934, 'learning_rate': 2.7741731429604195e-05, 'epoch': 0.15}
{'loss': 1.1602, 'learning_rate': 2.7739020422917043e-05, 'epoch': 0.15}
{'loss': 0.8767, 'learning_rate': 2.7736309416229895e-05, 'epoch': 0.15}
{'loss': 0.8478, 'learning_rate': 2.7733598409542747e-05, 'epoch': 0.15}
{'loss': 1.5823, 'learning_rate': 2.7730887402855595e-05, 'epoch': 0.15}
{'loss': 0.9519, 'learning_rate': 2.7728176396168444e-05, 'epoch': 0.15}
{'loss': 1.3653, 'learning_rate': 2.7725465389481292e-05, 'epoch': 0.15}
{'loss': 1.621, 'learning_rate': 2.7722754382794144e-05, 'epoch': 0.15}
{'loss': 1.3014, 'learning_rate': 2.7720043376106996e-05, 'epoch': 0.15}
{'loss': 1.6295, 'learning_rate': 2.7717332369419844e-05, 'epoch': 0.15}
{'loss': 1.3253, 'learning_rate': 2.7714621362732696e-05, 'epoch': 0.15}
{'loss': 1.2103, 'learning_rate': 2.7711910356045548e-05, 'epoch': 0.15}
{'loss': 0.6711, 'learning_rate': 2.7709199349358396e-05, 'epoch': 0.15}
{'loss': 1.1278, 'learning_rate': 2.7706488342671245e-05, 'epoch': 0.15}
{'loss': 0.9123, 'learning_rate': 2.7703777335984097e-05, 'epoch': 0.15}
{'loss': 1.2692, 'learning_rate': 2.7701066329296945e-05, 'epoch': 0.15}
{'loss': 1.6772, 'learning_rate': 2.7698355322609797e-05, 'epoch': 0.15}
{'loss': 1.6089, 'learning_rate': 2.7695644315922645e-05, 'epoch': 0.15}
{'loss': 1.5244, 'learning_rate': 2.7692933309235497e-05, 'epoch': 0.15}
{'loss': 1.1262, 'learning_rate': 2.769022230254835e-05, 'epoch': 0.15}
{'loss': 1.8361, 'learning_rate': 2.7687511295861197e-05, 'epoch': 0.15}
{'loss': 1.6302, 'learning_rate': 2.7684800289174046e-05, 'epoch': 0.15}
{'loss': 1.759, 'learning_rate': 2.7682089282486898e-05, 'epoch': 0.15}
{'loss': 1.5601, 'learning_rate': 2.7679378275799746e-05, 'epoch': 0.15}
{'loss': 1.811, 'learning_rate': 2.7676667269112598e-05, 'epoch': 0.15}
{'loss': 1.3286, 'learning_rate': 2.767395626242545e-05, 'epoch': 0.16}
{'loss': 1.4216, 'learning_rate': 2.7671245255738298e-05, 'epoch': 0.16}
{'loss': 1.4646, 'learning_rate': 2.766853424905115e-05, 'epoch': 0.16}
{'loss': 0.564, 'learning_rate': 2.7665823242364e-05, 'epoch': 0.16}
{'loss': 2.3867, 'learning_rate': 2.7663112235676847e-05, 'epoch': 0.16}
{'loss': 2.031, 'learning_rate': 2.76604012289897e-05, 'epoch': 0.16}
{'loss': 1.5519, 'learning_rate': 2.7657690222302547e-05, 'epoch': 0.16}
{'loss': 1.0555, 'learning_rate': 2.76549792156154e-05, 'epoch': 0.16}
{'loss': 2.2191, 'learning_rate': 2.765226820892825e-05, 'epoch': 0.16}
{'loss': 1.0895, 'learning_rate': 2.76495572022411e-05, 'epoch': 0.16}
{'loss': 1.3412, 'learning_rate': 2.764684619555395e-05, 'epoch': 0.16}
{'loss': 0.9356, 'learning_rate': 2.7644135188866803e-05, 'epoch': 0.16}
{'loss': 1.011, 'learning_rate': 2.7641424182179648e-05, 'epoch': 0.16}
{'loss': 0.7509, 'learning_rate': 2.76387131754925e-05, 'epoch': 0.16}
{'loss': 1.1129, 'learning_rate': 2.763600216880535e-05, 'epoch': 0.16}
{'loss': 1.3762, 'learning_rate': 2.76332911621182e-05, 'epoch': 0.16}
{'loss': 1.3219, 'learning_rate': 2.7630580155431052e-05, 'epoch': 0.16}
{'loss': 1.0541, 'learning_rate': 2.76278691487439e-05, 'epoch': 0.16}
{'loss': 1.2152, 'learning_rate': 2.7625158142056752e-05, 'epoch': 0.16}
{'loss': 2.121, 'learning_rate': 2.7622447135369604e-05, 'epoch': 0.16}
{'loss': 1.8951, 'learning_rate': 2.761973612868245e-05, 'epoch': 0.16}
{'loss': 2.478, 'learning_rate': 2.76170251219953e-05, 'epoch': 0.16}
{'loss': 1.8836, 'learning_rate': 2.7614314115308153e-05, 'epoch': 0.16}
{'loss': 2.1591, 'learning_rate': 2.7611603108621e-05, 'epoch': 0.16}
{'loss': 2.227, 'learning_rate': 2.7608892101933853e-05, 'epoch': 0.16}
{'loss': 1.1518, 'learning_rate': 2.76061810952467e-05, 'epoch': 0.16}
{'loss': 1.3148, 'learning_rate': 2.7603470088559553e-05, 'epoch': 0.16}
{'loss': 1.403, 'learning_rate': 2.7600759081872405e-05, 'epoch': 0.16}
{'loss': 0.9945, 'learning_rate': 2.759804807518525e-05, 'epoch': 0.16}
{'loss': 1.0527, 'learning_rate': 2.7595337068498102e-05, 'epoch': 0.16}
{'loss': 0.9933, 'learning_rate': 2.7592626061810954e-05, 'epoch': 0.16}
{'loss': 1.7834, 'learning_rate': 2.7589915055123802e-05, 'epoch': 0.16}
{'loss': 1.2275, 'learning_rate': 2.7587204048436654e-05, 'epoch': 0.16}
{'loss': 1.0062, 'learning_rate': 2.7584493041749506e-05, 'epoch': 0.16}
{'loss': 0.9146, 'learning_rate': 2.7581782035062354e-05, 'epoch': 0.16}
{'loss': 1.1434, 'learning_rate': 2.7579071028375206e-05, 'epoch': 0.16}
{'loss': 1.7508, 'learning_rate': 2.757636002168805e-05, 'epoch': 0.16}
{'loss': 1.5335, 'learning_rate': 2.7573649015000903e-05, 'epoch': 0.16}
{'loss': 1.7775, 'learning_rate': 2.7570938008313755e-05, 'epoch': 0.16}
{'loss': 1.1619, 'learning_rate': 2.7568227001626603e-05, 'epoch': 0.16}
{'loss': 1.5116, 'learning_rate': 2.7565515994939455e-05, 'epoch': 0.16}
{'loss': 0.8639, 'learning_rate': 2.7562804988252307e-05, 'epoch': 0.16}
{'loss': 1.0809, 'learning_rate': 2.7560093981565155e-05, 'epoch': 0.16}

  8%|▊         | 901/11066 [03:18<37:43,  4.49it/s]
  8%|▊         | 902/11066 [03:18<37:48,  4.48it/s]
                                                   

  8%|▊         | 902/11066 [03:18<37:48,  4.48it/s]
  8%|▊         | 903/11066 [03:18<37:44,  4.49it/s]
                                                   

  8%|▊         | 903/11066 [03:18<37:44,  4.49it/s]
  8%|▊         | 904/11066 [03:18<37:40,  4.50it/s]
                                                   

  8%|▊         | 904/11066 [03:18<37:40,  4.50it/s]
  8%|▊         | 905/11066 [03:19<37:39,  4.50it/s]
                                                   

  8%|▊         | 905/11066 [03:19<37:39,  4.50it/s]
  8%|▊         | 906/11066 [03:19<37:39,  4.50it/s]
                                                   

  8%|▊         | 906/11066 [03:19<37:39,  4.50it/s]
  8%|▊         | 907/11066 [03:19<37:07,  4.56it/s]
                                                   

  8%|▊         | 907/11066 [03:19<37:07,  4.56it/s]
  8%|▊         | 908/11066 [03:19<37:03,  4.57it/s]
                                                   

  8%|▊         | 908/11066 [03:19<37:03,  4.57it/s]
  8%|▊         | 909/11066 [03:19<36:50,  4.59it/s]
                                                   

  8%|▊         | 909/11066 [03:19<36:50,  4.59it/s]
  8%|▊         | 910/11066 [03:20<36:52,  4.59it/s]
                                                   

  8%|▊         | 910/11066 [03:20<36:52,  4.59it/s]
  8%|▊         | 911/11066 [03:20<36:48,  4.60it/s]
                                                   

  8%|▊         | 911/11066 [03:20<36:48,  4.60it/s]
  8%|▊         | 912/11066 [03:20<37:11,  4.55it/s]
                                                   

  8%|▊         | 912/11066 [03:20<37:11,  4.55it/s]
  8%|▊         | 913/11066 [03:20<37:05,  4.56it/s]
                                                   

  8%|▊         | 913/11066 [03:20<37:05,  4.56it/s]
  8%|▊         | 914/11066 [03:21<36:49,  4.59it/s]
                                                   

  8%|▊         | 914/11066 [03:21<36:49,  4.59it/s]
  8%|▊         | 915/11066 [03:21<36:30,  4.63it/s]
                                                   

  8%|▊         | 915/11066 [03:21<36:30,  4.63it/s]
  8%|▊         | 916/11066 [03:21<36:12,  4.67it/s]
                                                   

  8%|▊         | 916/11066 [03:21<36:12,  4.67it/s]
  8%|▊         | 917/11066 [03:21<37:04,  4.56it/s]
                                                   

  8%|▊         | 917/11066 [03:21<37:04,  4.56it/s]
  8%|▊         | 918/11066 [03:21<37:41,  4.49it/s]
                                                   

  8%|▊         | 918/11066 [03:21<37:41,  4.49it/s]
  8%|▊         | 919/11066 [03:22<37:02,  4.57it/s]
                                                   

  8%|▊         | 919/11066 [03:22<37:02,  4.57it/s]
  8%|▊         | 920/11066 [03:22<37:27,  4.51it/s]
                                                   

  8%|▊         | 920/11066 [03:22<37:27,  4.51it/s]
  8%|▊         | 921/11066 [03:22<37:51,  4.47it/s]
                                                   

  8%|▊         | 921/11066 [03:22<37:51,  4.47it/s]
  8%|▊         | 922/11066 [03:22<37:34,  4.50it/s]
                                                   

  8%|▊         | 922/11066 [03:22<37:34,  4.50it/s]
  8%|▊         | 923/11066 [03:23<37:21,  4.53it/s]
                                                   

  8%|▊         | 923/11066 [03:23<37:21,  4.53it/s]
  8%|▊         | 924/11066 [03:23<37:28,  4.51it/s]
                                                   

  8%|▊         | 924/11066 [03:23<37:28,  4.51it/s]
  8%|▊         | 925/11066 [03:23<37:30,  4.51it/s]
                                                   

  8%|▊         | 925/11066 [03:23<37:30,  4.51it/s]
  8%|▊         | 926/11066 [03:23<37:31,  4.50it/s]
                                                   

  8%|▊         | 926/11066 [03:23<37:31,  4.50it/s]
  8%|▊         | 927/11066 [03:23<37:33,  4.50it/s]
                                                   

  8%|▊         | 927/11066 [03:23<37:33,  4.50it/s]
  8%|▊         | 928/11066 [03:24<37:31,  4.50it/s]
                                                   

  8%|▊         | 928/11066 [03:24<37:31,  4.50it/s]
  8%|▊         | 929/11066 [03:24<37:14,  4.54it/s]
                                                   

  8%|▊         | 929/11066 [03:24<37:14,  4.54it/s]
  8%|▊         | 930/11066 [03:24<36:55,  4.57it/s]
                                                   

  8%|▊         | 930/11066 [03:24<36:55,  4.57it/s]
  8%|▊         | 931/11066 [03:24<37:17,  4.53it/s]
                                                   

  8%|▊         | 931/11066 [03:24<37:17,  4.53it/s]
  8%|▊         | 932/11066 [03:25<37:25,  4.51it/s]
                                                   

  8%|▊         | 932/11066 [03:25<37:25,  4.51it/s]
  8%|▊         | 933/11066 [03:25<37:09,  4.54it/s]
                                                   

  8%|▊         | 933/11066 [03:25<37:09,  4.54it/s]
  8%|▊         | 934/11066 [03:25<37:20,  4.52it/s]
                                                   

  8%|▊         | 934/11066 [03:25<37:20,  4.52it/s]
  8%|▊         | 935/11066 [03:25<37:21,  4.52it/s]
                                                   

  8%|▊         | 935/11066 [03:25<37:21,  4.52it/s]
  8%|▊         | 936/11066 [03:25<37:02,  4.56it/s]
                                                   

  8%|▊         | 936/11066 [03:25<37:02,  4.56it/s]
  8%|▊         | 937/11066 [03:26<37:09,  4.54it/s]
                                                   

  8%|▊         | 937/11066 [03:26<37:09,  4.54it/s]
  8%|▊         | 938/11066 [03:26<36:54,  4.57it/s]
                                                   

  8%|▊         | 938/11066 [03:26<36:54,  4.57it/s]
  8%|▊         | 939/11066 [03:26<37:08,  4.54it/s]
                                                   

  8%|▊         | 939/11066 [03:26<37:08,  4.54it/s]
  8%|▊         | 940/11066 [03:26<37:03,  4.55it/s]
                                                   

  8%|▊         | 940/11066 [03:26<37:03,  4.55it/s]
  9%|▊         | 941/11066 [03:26<37:03,  4.55it/s]
                                                   

  9%|▊         | 941/11066 [03:26<37:03,  4.55it/s]
  9%|▊         | 942/11066 [03:27<37:09,  4.54it/s]
                                                   

  9%|▊         | 942/11066 [03:27<37:09,  4.54it/s]
  9%|▊         | 943/11066 [03:27<37:14,  4.53it/s]
                                                   

  9%|▊         | 943/11066 [03:27<37:14,  4.53it/s]
  9%|▊         | 944/11066 [03:27<37:02,  4.55it/s]
                                                   

  9%|▊         | 944/11066 [03:27<37:02,  4.55it/s]
  9%|▊         | 945/11066 [03:27<37:21,  4.52it/s]
                                                   

  9%|▊         | 945/11066 [03:27<37:21,  4.52it/s]
  9%|▊         | 946/11066 [03:28<37:28,  4.50it/s]
                                                   

  9%|▊         | 946/11066 [03:28<37:28,  4.50it/s]
  9%|▊         | 947/11066 [03:28<37:15,  4.53it/s]
                                                   

  9%|▊         | 947/11066 [03:28<37:15,  4.53it/s]
  9%|▊         | 948/11066 [03:28<37:23,  4.51it/s]
                                                   

  9%|▊         | 948/11066 [03:28<37:23,  4.51it/s]
  9%|▊         | 949/11066 [03:28<37:07,  4.54it/s]
                                                   

  9%|▊         | 949/11066 [03:28<37:07,  4.54it/s]
  9%|▊         | 950/11066 [03:28<37:14,  4.53it/s]
                                                   

  9%|▊         | 950/11066 [03:28<37:14,  4.53it/s]
  9%|▊         | 951/11066 [03:29<37:22,  4.51it/s]
                                                   

  9%|▊         | 951/11066 [03:29<37:22,  4.51it/s]
  9%|▊         | 952/11066 [03:29<38:01,  4.43it/s]
                                                   

  9%|▊         | 952/11066 [03:29<38:01,  4.43it/s]
  9%|▊         | 953/11066 [03:29<38:36,  4.37it/s]
                                                   

  9%|▊         | 953/11066 [03:29<38:36,  4.37it/s]
  9%|▊         | 954/11066 [03:29<38:29,  4.38it/s]
                                                   

  9%|▊         | 954/11066 [03:29<38:29,  4.38it/s]
  9%|▊         | 955/11066 [03:30<38:11,  4.41it/s]
                                                   

  9%|▊         | 955/11066 [03:30<38:11,  4.41it/s]
  9%|▊         | 956/11066 [03:30<38:25,  4.39it/s]
                                                   

  9%|▊         | 956/11066 [03:30<38:25,  4.39it/s]
  9%|▊         | 957/11066 [03:30<38:11,  4.41it/s]
                                                   

  9%|▊         | 957/11066 [03:30<38:11,  4.41it/s]
  9%|▊         | 958/11066 [03:30<38:07,  4.42it/s]
                                                   

  9%|▊         | 958/11066 [03:30<38:07,  4.42it/s]
  9%|▊         | 959/11066 [03:31<38:17,  4.40it/s]
                                                   

  9%|▊         | 959/11066 [03:31<38:17,  4.40it/s]
  9%|▊         | 960/11066 [03:31<38:10,  4.41it/s]
                                                   

  9%|▊         | 960/11066 [03:31<38:10,  4.41it/s]
  9%|▊         | 961/11066 [03:31<37:57,  4.44it/s]
                                                   

  9%|▊         | 961/11066 [03:31<37:57,  4.44it/s]
  9%|▊         | 962/11066 [03:31<37:10,  4.53it/s]
                                                   

  9%|▊         | 962/11066 [03:31<37:10,  4.53it/s]
  9%|▊         | 963/11066 [03:31<37:28,  4.49it/s]
                                                   

  9%|▊         | 963/11066 [03:31<37:28,  4.49it/s]
  9%|▊         | 964/11066 [03:32<37:01,  4.55it/s]
                                                   

  9%|▊         | 964/11066 [03:32<37:01,  4.55it/s]
  9%|▊         | 965/11066 [03:32<36:42,  4.59it/s]
                                                   

  9%|▊         | 965/11066 [03:32<36:42,  4.59it/s]
  9%|▊         | 966/11066 [03:32<37:01,  4.55it/s]
                                                   

  9%|▊         | 966/11066 [03:32<37:01,  4.55it/s]
  9%|▊         | 967/11066 [03:32<37:22,  4.50it/s]
                                                   

  9%|▊         | 967/11066 [03:32<37:22,  4.50it/s]
  9%|▊         | 968/11066 [03:33<37:53,  4.44it/s]
                                                   

  9%|▊         | 968/11066 [03:33<37:53,  4.44it/s]
  9%|▉         | 969/11066 [03:33<37:25,  4.50it/s]
                                                   

  9%|▉         | 969/11066 [03:33<37:25,  4.50it/s]
  9%|▉         | 970/11066 [03:33<37:19,  4.51it/s]
                                                   

  9%|▉         | 970/11066 [03:33<37:19,  4.51it/s]
  9%|▉         | 971/11066 [03:33<37:27,  4.49it/s]
                                                   

  9%|▉         | 971/11066 [03:33<37:27,  4.49it/s]
  9%|▉         | 972/11066 [03:33<37:37,  4.47it/s]
                                                   

  9%|▉         | 972/11066 [03:33<37:37,  4.47it/s]
  9%|▉         | 973/11066 [03:34<37:41,  4.46it/s]
                                                   

  9%|▉         | 973/11066 [03:34<37:41,  4.46it/s]
  9%|▉         | 974/11066 [03:34<38:01,  4.42it/s]
                                                   

  9%|▉         | 974/11066 [03:34<38:01,  4.42it/s]
  9%|▉         | 975/11066 [03:34<38:20,  4.39it/s]
                                                   

  9%|▉         | 975/11066 [03:34<38:20,  4.39it/s]
  9%|▉         | 976/11066 [03:34<37:48,  4.45it/s]
                                                   

  9%|▉         | 976/11066 [03:34<37:48,  4.45it/s]
  9%|▉         | 977/11066 [03:35<37:28,  4.49it/s]
                                                   

  9%|▉         | 977/11066 [03:35<37:28,  4.49it/s]
  9%|▉         | 978/11066 [03:35<37:39,  4.47it/s]
                                                   

  9%|▉         | 978/11066 [03:35<37:39,  4.47it/s]
  9%|▉         | 979/11066 [03:35<37:41,  4.46it/s]
                                                   

  9%|▉         | 979/11066 [03:35<37:41,  4.46it/s]
  9%|▉         | 980/11066 [03:35<37:44,  4.45it/s]
                                                   

  9%|▉         | 980/11066 [03:35<37:44,  4.45it/s]
  9%|▉         | 981/11066 [03:35<37:42,  4.46it/s]
                                                   

  9%|▉         | 981/11066 [03:35<37:42,  4.46it/s]
  9%|▉         | 982/11066 [03:36<37:49,  4.44it/s]
                                                   

  9%|▉         | 982/11066 [03:36<37:49,  4.44it/s]
  9%|▉         | 983/11066 [03:36<37:47,  4.45it/s]
                                                   

  9%|▉         | 983/11066 [03:36<37:47,  4.45it/s]
  9%|▉         | 984/11066 [03:36<37:39,  4.46it/s]
                                                   

  9%|▉         | 984/11066 [03:36<37:39,  4.46it/s]
  9%|▉         | 985/11066 [03:36<37:39,  4.46it/s]
                                                   

  9%|▉         | 985/11066 [03:36<37:39,  4.46it/s]
  9%|▉         | 986/11066 [03:37<37:39,  4.46it/s]
                                                   

  9%|▉         | 986/11066 [03:37<37:39,  4.46it/s]
  9%|▉         | 987/11066 [03:37<37:47,  4.44it/s]
                                                   

  9%|▉         | 987/11066 [03:37<37:47,  4.44it/s]
  9%|▉         | 988/11066 [03:37<37:51,  4.44it/s]
                                                   

  9%|▉         | 988/11066 [03:37<37:51,  4.44it/s]
  9%|▉         | 989/11066 [03:37<38:07,  4.41it/s]
                                                   

  9%|▉         | 989/11066 [03:37<38:07,  4.41it/s]
  9%|▉         | 990/11066 [03:37<37:53,  4.43it/s]
                                                   

  9%|▉         | 990/11066 [03:37<37:53,  4.43it/s]
  9%|▉         | 991/11066 [03:38<37:42,  4.45it/s]
                                                   

  9%|▉         | 991/11066 [03:38<37:42,  4.45it/s]
  9%|▉         | 992/11066 [03:38<37:34,  4.47it/s]
                                                   

  9%|▉         | 992/11066 [03:38<37:34,  4.47it/s]
  9%|▉         | 993/11066 [03:38<38:00,  4.42it/s]
                                                   

  9%|▉         | 993/11066 [03:38<38:00,  4.42it/s]
  9%|▉         | 994/11066 [03:38<37:51,  4.43it/s]
                                                   

  9%|▉         | 994/11066 [03:38<37:51,  4.43it/s]
  9%|▉         | 995/11066 [03:39<37:43,  4.45it/s]
                                                   

  9%|▉         | 995/11066 [03:39<37:43,  4.45it/s]
  9%|▉         | 996/11066 [03:39<37:35,  4.46it/s]
                                                   

  9%|▉         | 996/11066 [03:39<37:35,  4.46it/s]
  9%|▉         | 997/11066 [03:39<37:31,  4.47it/s]
                                                   

  9%|▉         | 997/11066 [03:39<37:31,  4.47it/s]
  9%|▉         | 998/11066 [03:39<37:27,  4.48it/s]
                                                   

  9%|▉         | 998/11066 [03:39<37:27,  4.48it/s]
  9%|▉         | 999/11066 [03:39<37:24,  4.49it/s]
                                                   

  9%|▉         | 999/11066 [03:39<37:24,  4.49it/s]
  9%|▉         | 1000/11066 [03:40<37:22,  4.49it/s]
                                                    

  9%|▉         | 1000/11066 [03:40<37:22,  4.49it/s]
  9%|▉         | 1001/11066 [03:40<37:04,  4.52it/s]
                                                    

  9%|▉         | 1001/11066 [03:40<37:04,  4.52it/s]
  9%|▉         | 1002/11066 [03:40<37:24,  4.48it/s]
                                                    

  9%|▉         | 1002/11066 [03:40<37:24,  4.48it/s]
  9%|▉         | 1003/11066 [03:40<37:20,  4.49it/s]
                                                    

  9%|▉         | 1003/11066 [03:40<37:20,  4.49it/s]
  9%|▉         | 1004/11066 [03:41<37:21,  4.49it/s]
                                                    

  9%|▉         | 1004/11066 [03:41<37:21,  4.49it/s]
  9%|▉         | 1005/11066 [03:41<37:20,  4.49it/s]
                                                    

  9%|▉         | 1005/11066 [03:41<37:20,  4.49it/s]
  9%|▉         | 1006/11066 [03:41<37:19,  4.49it/s]
                                                    

  9%|▉         | 1006/11066 [03:41<37:19,  4.49it/s]
  9%|▉         | 1007/11066 [03:41<37:16,  4.50it/s]
                                                    

  9%|▉         | 1007/11066 [03:41<37:16,  4.50it/s]
  9%|▉         | 1008/11066 [03:41<37:03,  4.52it/s]
                                                    

  9%|▉         | 1008/11066 [03:41<37:03,  4.52it/s]
  9%|▉         | 1009/11066 [03:42<36:47,  4.56it/s]
                                                    

  9%|▉         | 1009/11066 [03:42<36:47,  4.56it/s]
  9%|▉         | 1010/11066 [03:42<36:55,  4.54it/s]
                                                    

  9%|▉         | 1010/11066 [03:42<36:55,  4.54it/s]
  9%|▉         | 1011/11066 [03:42<36:44,  4.56it/s]
                                                    

  9%|▉         | 1011/11066 [03:42<36:44,  4.56it/s]
  9%|▉         | 1012/11066 [03:42<36:40,  4.57it/s]
                                                    

  9%|▉         | 1012/11066 [03:42<36:40,  4.57it/s]
  9%|▉         | 1013/11066 [03:43<36:34,  4.58it/s]
                                                    

  9%|▉         | 1013/11066 [03:43<36:34,  4.58it/s]
  9%|▉         | 1014/11066 [03:43<36:35,  4.58it/s]
                                                    
{'loss': 1.5509, 'learning_rate': 2.7557382974878004e-05, 'epoch': 0.16}
{'loss': 1.4252, 'learning_rate': 2.7554671968190856e-05, 'epoch': 0.16}
{'loss': 1.8589, 'learning_rate': 2.7551960961503704e-05, 'epoch': 0.16}
{'loss': 0.8532, 'learning_rate': 2.7549249954816556e-05, 'epoch': 0.16}
{'loss': 1.4916, 'learning_rate': 2.7546538948129404e-05, 'epoch': 0.16}
{'loss': 2.1607, 'learning_rate': 2.7543827941442256e-05, 'epoch': 0.16}
{'loss': 1.5667, 'learning_rate': 2.7541116934755108e-05, 'epoch': 0.16}
{'loss': 0.962, 'learning_rate': 2.7538405928067957e-05, 'epoch': 0.16}
{'loss': 1.3283, 'learning_rate': 2.7535694921380805e-05, 'epoch': 0.16}
{'loss': 1.3265, 'learning_rate': 2.7532983914693657e-05, 'epoch': 0.16}
{'loss': 1.7632, 'learning_rate': 2.7530272908006505e-05, 'epoch': 0.16}
{'loss': 1.6695, 'learning_rate': 2.7527561901319357e-05, 'epoch': 0.16}
{'loss': 1.242, 'learning_rate': 2.752485089463221e-05, 'epoch': 0.17}
{'loss': 1.2528, 'learning_rate': 2.7522139887945057e-05, 'epoch': 0.17}
{'loss': 1.5344, 'learning_rate': 2.751942888125791e-05, 'epoch': 0.17}
{'loss': 1.4, 'learning_rate': 2.7516717874570758e-05, 'epoch': 0.17}
{'loss': 1.0778, 'learning_rate': 2.7514006867883606e-05, 'epoch': 0.17}
{'loss': 1.1307, 'learning_rate': 2.7511295861196458e-05, 'epoch': 0.17}
{'loss': 1.1655, 'learning_rate': 2.7508584854509306e-05, 'epoch': 0.17}
{'loss': 1.6872, 'learning_rate': 2.7505873847822158e-05, 'epoch': 0.17}
{'loss': 2.2609, 'learning_rate': 2.750316284113501e-05, 'epoch': 0.17}
{'loss': 1.7723, 'learning_rate': 2.750045183444786e-05, 'epoch': 0.17}
{'loss': 1.8643, 'learning_rate': 2.749774082776071e-05, 'epoch': 0.17}
{'loss': 1.8209, 'learning_rate': 2.7495029821073562e-05, 'epoch': 0.17}
{'loss': 1.4284, 'learning_rate': 2.7492318814386407e-05, 'epoch': 0.17}
{'loss': 0.9093, 'learning_rate': 2.748960780769926e-05, 'epoch': 0.17}
{'loss': 1.5051, 'learning_rate': 2.7486896801012107e-05, 'epoch': 0.17}
{'loss': 1.358, 'learning_rate': 2.748418579432496e-05, 'epoch': 0.17}
{'loss': 2.0595, 'learning_rate': 2.748147478763781e-05, 'epoch': 0.17}
{'loss': 1.9383, 'learning_rate': 2.747876378095066e-05, 'epoch': 0.17}
{'loss': 1.0778, 'learning_rate': 2.747605277426351e-05, 'epoch': 0.17}
{'loss': 1.6838, 'learning_rate': 2.7473341767576363e-05, 'epoch': 0.17}
{'loss': 2.0678, 'learning_rate': 2.7470630760889208e-05, 'epoch': 0.17}
{'loss': 1.017, 'learning_rate': 2.746791975420206e-05, 'epoch': 0.17}
{'loss': 1.3344, 'learning_rate': 2.7465208747514912e-05, 'epoch': 0.17}
{'loss': 1.4836, 'learning_rate': 2.746249774082776e-05, 'epoch': 0.17}
{'loss': 1.5601, 'learning_rate': 2.7459786734140612e-05, 'epoch': 0.17}
{'loss': 1.626, 'learning_rate': 2.745707572745346e-05, 'epoch': 0.17}
{'loss': 1.4621, 'learning_rate': 2.7454364720766312e-05, 'epoch': 0.17}
{'loss': 1.5824, 'learning_rate': 2.7451653714079164e-05, 'epoch': 0.17}
{'loss': 1.3691, 'learning_rate': 2.744894270739201e-05, 'epoch': 0.17}
{'loss': 1.1128, 'learning_rate': 2.744623170070486e-05, 'epoch': 0.17}
{'loss': 1.1357, 'learning_rate': 2.7443520694017713e-05, 'epoch': 0.17}
{'loss': 1.4141, 'learning_rate': 2.744080968733056e-05, 'epoch': 0.17}
{'loss': 1.6681, 'learning_rate': 2.7438098680643413e-05, 'epoch': 0.17}
{'loss': 1.008, 'learning_rate': 2.7435387673956265e-05, 'epoch': 0.17}
{'loss': 0.7155, 'learning_rate': 2.7432676667269113e-05, 'epoch': 0.17}
{'loss': 0.9281, 'learning_rate': 2.7429965660581965e-05, 'epoch': 0.17}
{'loss': 1.4412, 'learning_rate': 2.7427254653894814e-05, 'epoch': 0.17}
{'loss': 2.068, 'learning_rate': 2.7424543647207662e-05, 'epoch': 0.17}
{'loss': 1.26, 'learning_rate': 2.7421832640520514e-05, 'epoch': 0.17}
{'loss': 1.5473, 'learning_rate': 2.7419121633833362e-05, 'epoch': 0.17}
{'loss': 1.1881, 'learning_rate': 2.7416410627146214e-05, 'epoch': 0.17}
{'loss': 0.9008, 'learning_rate': 2.7413699620459066e-05, 'epoch': 0.17}
{'loss': 1.4195, 'learning_rate': 2.7410988613771915e-05, 'epoch': 0.17}
{'loss': 1.7989, 'learning_rate': 2.7408277607084766e-05, 'epoch': 0.17}
{'loss': 1.0972, 'learning_rate': 2.7405566600397615e-05, 'epoch': 0.17}
{'loss': 1.6404, 'learning_rate': 2.7402855593710463e-05, 'epoch': 0.17}
{'loss': 1.4384, 'learning_rate': 2.7400144587023315e-05, 'epoch': 0.17}
{'loss': 0.884, 'learning_rate': 2.7397433580336167e-05, 'epoch': 0.17}
{'loss': 1.9524, 'learning_rate': 2.7394722573649015e-05, 'epoch': 0.17}
{'loss': 0.9372, 'learning_rate': 2.7392011566961867e-05, 'epoch': 0.17}
{'loss': 1.6075, 'learning_rate': 2.7389300560274716e-05, 'epoch': 0.17}
{'loss': 1.7458, 'learning_rate': 2.7386589553587567e-05, 'epoch': 0.17}
{'loss': 1.55, 'learning_rate': 2.7383878546900416e-05, 'epoch': 0.17}
{'loss': 1.1779, 'learning_rate': 2.7381167540213264e-05, 'epoch': 0.17}
{'loss': 1.395, 'learning_rate': 2.7378456533526116e-05, 'epoch': 0.17}
{'loss': 1.7095, 'learning_rate': 2.7375745526838968e-05, 'epoch': 0.17}
{'loss': 1.291, 'learning_rate': 2.7373034520151816e-05, 'epoch': 0.18}
{'loss': 1.8019, 'learning_rate': 2.7370323513464668e-05, 'epoch': 0.18}
{'loss': 1.2895, 'learning_rate': 2.736761250677752e-05, 'epoch': 0.18}
{'loss': 1.5737, 'learning_rate': 2.736490150009037e-05, 'epoch': 0.18}
{'loss': 1.4497, 'learning_rate': 2.7362190493403217e-05, 'epoch': 0.18}
{'loss': 1.139, 'learning_rate': 2.7359479486716065e-05, 'epoch': 0.18}
{'loss': 1.3104, 'learning_rate': 2.7356768480028917e-05, 'epoch': 0.18}
{'loss': 1.507, 'learning_rate': 2.735405747334177e-05, 'epoch': 0.18}
{'loss': 1.7832, 'learning_rate': 2.7351346466654618e-05, 'epoch': 0.18}
{'loss': 1.4104, 'learning_rate': 2.734863545996747e-05, 'epoch': 0.18}
{'loss': 0.7787, 'learning_rate': 2.734592445328032e-05, 'epoch': 0.18}
{'loss': 1.614, 'learning_rate': 2.734321344659317e-05, 'epoch': 0.18}
{'loss': 0.8666, 'learning_rate': 2.7340502439906018e-05, 'epoch': 0.18}
{'loss': 2.1354, 'learning_rate': 2.733779143321887e-05, 'epoch': 0.18}
{'loss': 0.776, 'learning_rate': 2.733508042653172e-05, 'epoch': 0.18}
{'loss': 1.5464, 'learning_rate': 2.733236941984457e-05, 'epoch': 0.18}
{'loss': 0.9871, 'learning_rate': 2.732965841315742e-05, 'epoch': 0.18}
{'loss': 1.4985, 'learning_rate': 2.732694740647027e-05, 'epoch': 0.18}
{'loss': 0.8762, 'learning_rate': 2.7324236399783122e-05, 'epoch': 0.18}
{'loss': 1.4693, 'learning_rate': 2.732152539309597e-05, 'epoch': 0.18}
{'loss': 1.27, 'learning_rate': 2.731881438640882e-05, 'epoch': 0.18}
{'loss': 1.352, 'learning_rate': 2.731610337972167e-05, 'epoch': 0.18}
{'loss': 1.769, 'learning_rate': 2.731339237303452e-05, 'epoch': 0.18}
{'loss': 1.3887, 'learning_rate': 2.731068136634737e-05, 'epoch': 0.18}
{'loss': 1.2489, 'learning_rate': 2.7307970359660223e-05, 'epoch': 0.18}
{'loss': 1.4682, 'learning_rate': 2.730525935297307e-05, 'epoch': 0.18}
{'loss': 1.4084, 'learning_rate': 2.7302548346285923e-05, 'epoch': 0.18}
{'loss': 1.3116, 'learning_rate': 2.7299837339598772e-05, 'epoch': 0.18}
{'loss': 0.8455, 'learning_rate': 2.729712633291162e-05, 'epoch': 0.18}
{'loss': 1.6154, 'learning_rate': 2.7294415326224472e-05, 'epoch': 0.18}
{'loss': 1.2562, 'learning_rate': 2.729170431953732e-05, 'epoch': 0.18}
{'loss': 0.7434, 'learning_rate': 2.7288993312850172e-05, 'epoch': 0.18}
{'loss': 1.3334, 'learning_rate': 2.7286282306163024e-05, 'epoch': 0.18}
{'loss': 0.8564, 'learning_rate': 2.7283571299475873e-05, 'epoch': 0.18}
{'loss': 1.2792, 'learning_rate': 2.7280860292788724e-05, 'epoch': 0.18}
{'loss': 1.4907, 'learning_rate': 2.7278149286101576e-05, 'epoch': 0.18}
{'loss': 1.7123, 'learning_rate': 2.727543827941442e-05, 'epoch': 0.18}
{'loss': 1.6822, 'learning_rate': 2.7272727272727273e-05, 'epoch': 0.18}
{'loss': 1.5703, 'learning_rate': 2.727001626604012e-05, 'epoch': 0.18}
{'loss': 0.9858, 'learning_rate': 2.7267305259352973e-05, 'epoch': 0.18}
{'loss': 1.3807, 'learning_rate': 2.7264594252665825e-05, 'epoch': 0.18}
{'loss': 2.101, 'learning_rate': 2.7261883245978674e-05, 'epoch': 0.18}
{'loss': 1.1209, 'learning_rate': 2.7259172239291525e-05, 'epoch': 0.18}
{'loss': 1.6005, 'learning_rate': 2.7256461232604377e-05, 'epoch': 0.18}
{'loss': 1.7607, 'learning_rate': 2.7253750225917222e-05, 'epoch': 0.18}

  9%|▉         | 1014/11066 [03:43<36:35,  4.58it/s]
  9%|▉         | 1015/11066 [03:43<36:49,  4.55it/s]
                                                    

  9%|▉         | 1015/11066 [03:43<36:49,  4.55it/s]
  9%|▉         | 1016/11066 [03:43<36:40,  4.57it/s]
                                                    

  9%|▉         | 1016/11066 [03:43<36:40,  4.57it/s]
  9%|▉         | 1017/11066 [03:43<36:47,  4.55it/s]
                                                    

  9%|▉         | 1017/11066 [03:43<36:47,  4.55it/s]
  9%|▉         | 1018/11066 [03:44<36:49,  4.55it/s]
                                                    

  9%|▉         | 1018/11066 [03:44<36:49,  4.55it/s]
  9%|▉         | 1019/11066 [03:44<36:41,  4.56it/s]
                                                    

  9%|▉         | 1019/11066 [03:44<36:41,  4.56it/s]
  9%|▉         | 1020/11066 [03:44<36:35,  4.58it/s]
                                                    

  9%|▉         | 1020/11066 [03:44<36:35,  4.58it/s]
  9%|▉         | 1021/11066 [03:44<36:17,  4.61it/s]
                                                    

  9%|▉         | 1021/11066 [03:44<36:17,  4.61it/s]
  9%|▉         | 1022/11066 [03:45<36:23,  4.60it/s]
                                                    

  9%|▉         | 1022/11066 [03:45<36:23,  4.60it/s]
  9%|▉         | 1023/11066 [03:45<36:38,  4.57it/s]
                                                    

  9%|▉         | 1023/11066 [03:45<36:38,  4.57it/s]
  9%|▉         | 1024/11066 [03:45<36:50,  4.54it/s]
                                                    

  9%|▉         | 1024/11066 [03:45<36:50,  4.54it/s]
  9%|▉         | 1025/11066 [03:45<36:42,  4.56it/s]
                                                    

  9%|▉         | 1025/11066 [03:45<36:42,  4.56it/s]
  9%|▉         | 1026/11066 [03:45<36:54,  4.53it/s]
                                                    

  9%|▉         | 1026/11066 [03:45<36:54,  4.53it/s]
  9%|▉         | 1027/11066 [03:46<36:45,  4.55it/s]
                                                    

  9%|▉         | 1027/11066 [03:46<36:45,  4.55it/s]
  9%|▉         | 1028/11066 [03:46<36:25,  4.59it/s]
                                                    

  9%|▉         | 1028/11066 [03:46<36:25,  4.59it/s]
  9%|▉         | 1029/11066 [03:46<36:34,  4.57it/s]
                                                    

  9%|▉         | 1029/11066 [03:46<36:34,  4.57it/s]
  9%|▉         | 1030/11066 [03:46<36:57,  4.52it/s]
                                                    

  9%|▉         | 1030/11066 [03:46<36:57,  4.52it/s]
  9%|▉         | 1031/11066 [03:47<37:07,  4.51it/s]
                                                    

  9%|▉         | 1031/11066 [03:47<37:07,  4.51it/s]
  9%|▉         | 1032/11066 [03:47<37:09,  4.50it/s]
                                                    

  9%|▉         | 1032/11066 [03:47<37:09,  4.50it/s]
  9%|▉         | 1033/11066 [03:47<37:09,  4.50it/s]
                                                    

  9%|▉         | 1033/11066 [03:47<37:09,  4.50it/s]
  9%|▉         | 1034/11066 [03:47<37:08,  4.50it/s]
                                                    

  9%|▉         | 1034/11066 [03:47<37:08,  4.50it/s]
  9%|▉         | 1035/11066 [03:47<36:49,  4.54it/s]
                                                    

  9%|▉         | 1035/11066 [03:47<36:49,  4.54it/s]
  9%|▉         | 1036/11066 [03:48<36:50,  4.54it/s]
                                                    

  9%|▉         | 1036/11066 [03:48<36:50,  4.54it/s]
  9%|▉         | 1037/11066 [03:48<36:32,  4.57it/s]
                                                    

  9%|▉         | 1037/11066 [03:48<36:32,  4.57it/s]
  9%|▉         | 1038/11066 [03:48<36:50,  4.54it/s]
                                                    

  9%|▉         | 1038/11066 [03:48<36:50,  4.54it/s]
  9%|▉         | 1039/11066 [03:48<36:39,  4.56it/s]
                                                    

  9%|▉         | 1039/11066 [03:48<36:39,  4.56it/s]
  9%|▉         | 1040/11066 [03:49<36:56,  4.52it/s]
                                                    

  9%|▉         | 1040/11066 [03:49<36:56,  4.52it/s]
  9%|▉         | 1041/11066 [03:49<36:46,  4.54it/s]
                                                    

  9%|▉         | 1041/11066 [03:49<36:46,  4.54it/s]
  9%|▉         | 1042/11066 [03:49<36:55,  4.52it/s]
                                                    

  9%|▉         | 1042/11066 [03:49<36:55,  4.52it/s]
  9%|▉         | 1043/11066 [03:49<37:09,  4.50it/s]
                                                    

  9%|▉         | 1043/11066 [03:49<37:09,  4.50it/s]
  9%|▉         | 1044/11066 [03:49<37:13,  4.49it/s]
                                                    

  9%|▉         | 1044/11066 [03:49<37:13,  4.49it/s]
  9%|▉         | 1045/11066 [03:50<37:11,  4.49it/s]
                                                    

  9%|▉         | 1045/11066 [03:50<37:11,  4.49it/s]
  9%|▉         | 1046/11066 [03:50<36:49,  4.53it/s]
                                                    

  9%|▉         | 1046/11066 [03:50<36:49,  4.53it/s]
  9%|▉         | 1047/11066 [03:50<37:04,  4.50it/s]
                                                    

  9%|▉         | 1047/11066 [03:50<37:04,  4.50it/s]
  9%|▉         | 1048/11066 [03:50<36:52,  4.53it/s]
                                                    

  9%|▉         | 1048/11066 [03:50<36:52,  4.53it/s]
  9%|▉         | 1049/11066 [03:51<36:48,  4.53it/s]
                                                    

  9%|▉         | 1049/11066 [03:51<36:48,  4.53it/s]
  9%|▉         | 1050/11066 [03:51<36:56,  4.52it/s]
                                                    

  9%|▉         | 1050/11066 [03:51<36:56,  4.52it/s]
  9%|▉         | 1051/11066 [03:51<37:03,  4.50it/s]
                                                    

  9%|▉         | 1051/11066 [03:51<37:03,  4.50it/s]
 10%|▉         | 1052/11066 [03:51<37:15,  4.48it/s]
                                                    

 10%|▉         | 1052/11066 [03:51<37:15,  4.48it/s]
 10%|▉         | 1053/11066 [03:51<37:15,  4.48it/s]
                                                    

 10%|▉         | 1053/11066 [03:51<37:15,  4.48it/s]
 10%|▉         | 1054/11066 [03:52<37:12,  4.48it/s]
                                                    

 10%|▉         | 1054/11066 [03:52<37:12,  4.48it/s]
 10%|▉         | 1055/11066 [03:52<37:09,  4.49it/s]
                                                    

 10%|▉         | 1055/11066 [03:52<37:09,  4.49it/s]
 10%|▉         | 1056/11066 [03:52<37:08,  4.49it/s]
                                                    

 10%|▉         | 1056/11066 [03:52<37:08,  4.49it/s]
 10%|▉         | 1057/11066 [03:52<36:49,  4.53it/s]
                                                    

 10%|▉         | 1057/11066 [03:52<36:49,  4.53it/s]
 10%|▉         | 1058/11066 [03:53<37:03,  4.50it/s]
                                                    

 10%|▉         | 1058/11066 [03:53<37:03,  4.50it/s]
 10%|▉         | 1059/11066 [03:53<37:07,  4.49it/s]
                                                    

 10%|▉         | 1059/11066 [03:53<37:07,  4.49it/s]
 10%|▉         | 1060/11066 [03:53<37:06,  4.50it/s]
                                                    

 10%|▉         | 1060/11066 [03:53<37:06,  4.50it/s]
 10%|▉         | 1061/11066 [03:53<37:06,  4.49it/s]
                                                    

 10%|▉         | 1061/11066 [03:53<37:06,  4.49it/s]
 10%|▉         | 1062/11066 [03:53<36:49,  4.53it/s]
                                                    

 10%|▉         | 1062/11066 [03:53<36:49,  4.53it/s]
 10%|▉         | 1063/11066 [03:54<36:57,  4.51it/s]
                                                    

 10%|▉         | 1063/11066 [03:54<36:57,  4.51it/s]
 10%|▉         | 1064/11066 [03:54<36:46,  4.53it/s]
                                                    

 10%|▉         | 1064/11066 [03:54<36:46,  4.53it/s]
 10%|▉         | 1065/11066 [03:54<36:25,  4.58it/s]
                                                    

 10%|▉         | 1065/11066 [03:54<36:25,  4.58it/s]
 10%|▉         | 1066/11066 [03:54<36:43,  4.54it/s]
                                                    

 10%|▉         | 1066/11066 [03:54<36:43,  4.54it/s]
 10%|▉         | 1067/11066 [03:54<36:33,  4.56it/s]
                                                    

 10%|▉         | 1067/11066 [03:54<36:33,  4.56it/s]
 10%|▉         | 1068/11066 [03:55<36:50,  4.52it/s]
                                                    

 10%|▉         | 1068/11066 [03:55<36:50,  4.52it/s]
 10%|▉         | 1069/11066 [03:55<36:59,  4.50it/s]
                                                    

 10%|▉         | 1069/11066 [03:55<36:59,  4.50it/s]
 10%|▉         | 1070/11066 [03:55<36:58,  4.51it/s]
                                                    

 10%|▉         | 1070/11066 [03:55<36:58,  4.51it/s]
 10%|▉         | 1071/11066 [03:55<36:44,  4.53it/s]
                                                    

 10%|▉         | 1071/11066 [03:55<36:44,  4.53it/s]
 10%|▉         | 1072/11066 [03:56<36:41,  4.54it/s]
                                                    

 10%|▉         | 1072/11066 [03:56<36:41,  4.54it/s]
 10%|▉         | 1073/11066 [03:56<36:20,  4.58it/s]
                                                    

 10%|▉         | 1073/11066 [03:56<36:20,  4.58it/s]
 10%|▉         | 1074/11066 [03:56<36:05,  4.61it/s]
                                                    

 10%|▉         | 1074/11066 [03:56<36:05,  4.61it/s]
 10%|▉         | 1075/11066 [03:56<36:30,  4.56it/s]
                                                    

 10%|▉         | 1075/11066 [03:56<36:30,  4.56it/s]
 10%|▉         | 1076/11066 [03:56<36:27,  4.57it/s]
                                                    

 10%|▉         | 1076/11066 [03:56<36:27,  4.57it/s]
 10%|▉         | 1077/11066 [03:57<36:43,  4.53it/s]
                                                    

 10%|▉         | 1077/11066 [03:57<36:43,  4.53it/s]
 10%|▉         | 1078/11066 [03:57<36:51,  4.52it/s]
                                                    

 10%|▉         | 1078/11066 [03:57<36:51,  4.52it/s]
 10%|▉         | 1079/11066 [03:57<36:40,  4.54it/s]
                                                    

 10%|▉         | 1079/11066 [03:57<36:40,  4.54it/s]
 10%|▉         | 1080/11066 [03:57<36:21,  4.58it/s]
                                                    

 10%|▉         | 1080/11066 [03:57<36:21,  4.58it/s]
 10%|▉         | 1081/11066 [03:58<36:16,  4.59it/s]
                                                    

 10%|▉         | 1081/11066 [03:58<36:16,  4.59it/s]
 10%|▉         | 1082/11066 [03:58<36:26,  4.57it/s]
                                                    

 10%|▉         | 1082/11066 [03:58<36:26,  4.57it/s]
 10%|▉         | 1083/11066 [03:58<36:33,  4.55it/s]
                                                    

 10%|▉         | 1083/11066 [03:58<36:33,  4.55it/s]
 10%|▉         | 1084/11066 [03:58<36:42,  4.53it/s]
                                                    

 10%|▉         | 1084/11066 [03:58<36:42,  4.53it/s]
 10%|▉         | 1085/11066 [03:58<36:29,  4.56it/s]
                                                    

 10%|▉         | 1085/11066 [03:58<36:29,  4.56it/s]
 10%|▉         | 1086/11066 [03:59<36:13,  4.59it/s]
                                                    

 10%|▉         | 1086/11066 [03:59<36:13,  4.59it/s]
 10%|▉         | 1087/11066 [03:59<36:31,  4.55it/s]
                                                    

 10%|▉         | 1087/11066 [03:59<36:31,  4.55it/s]
 10%|▉         | 1088/11066 [03:59<36:25,  4.56it/s]
                                                    

 10%|▉         | 1088/11066 [03:59<36:25,  4.56it/s]
 10%|▉         | 1089/11066 [03:59<36:09,  4.60it/s]
                                                    

 10%|▉         | 1089/11066 [03:59<36:09,  4.60it/s]
 10%|▉         | 1090/11066 [04:00<36:09,  4.60it/s]
                                                    

 10%|▉         | 1090/11066 [04:00<36:09,  4.60it/s]
 10%|▉         | 1091/11066 [04:00<37:00,  4.49it/s]
                                                    

 10%|▉         | 1091/11066 [04:00<37:00,  4.49it/s]
 10%|▉         | 1092/11066 [04:00<37:14,  4.46it/s]
                                                    

 10%|▉         | 1092/11066 [04:00<37:14,  4.46it/s]
 10%|▉         | 1093/11066 [04:00<37:11,  4.47it/s]
                                                    

 10%|▉         | 1093/11066 [04:00<37:11,  4.47it/s]
 10%|▉         | 1094/11066 [04:00<37:10,  4.47it/s]
                                                    

 10%|▉         | 1094/11066 [04:00<37:10,  4.47it/s]
 10%|▉         | 1095/11066 [04:01<37:05,  4.48it/s]
                                                    

 10%|▉         | 1095/11066 [04:01<37:05,  4.48it/s]
 10%|▉         | 1096/11066 [04:01<37:01,  4.49it/s]
                                                    

 10%|▉         | 1096/11066 [04:01<37:01,  4.49it/s]
 10%|▉         | 1097/11066 [04:01<36:58,  4.49it/s]
                                                    

 10%|▉         | 1097/11066 [04:01<36:58,  4.49it/s]
 10%|▉         | 1098/11066 [04:01<37:02,  4.49it/s]
                                                    

 10%|▉         | 1098/11066 [04:01<37:02,  4.49it/s]
 10%|▉         | 1099/11066 [04:02<37:11,  4.47it/s]
                                                    

 10%|▉         | 1099/11066 [04:02<37:11,  4.47it/s]
 10%|▉         | 1100/11066 [04:02<37:39,  4.41it/s]
                                                    

 10%|▉         | 1100/11066 [04:02<37:39,  4.41it/s]
 10%|▉         | 1101/11066 [04:02<37:30,  4.43it/s]
                                                    

 10%|▉         | 1101/11066 [04:02<37:30,  4.43it/s]
 10%|▉         | 1102/11066 [04:02<37:20,  4.45it/s]
                                                    

 10%|▉         | 1102/11066 [04:02<37:20,  4.45it/s]
 10%|▉         | 1103/11066 [04:02<37:12,  4.46it/s]
                                                    

 10%|▉         | 1103/11066 [04:02<37:12,  4.46it/s]
 10%|▉         | 1104/11066 [04:03<37:04,  4.48it/s]
                                                    

 10%|▉         | 1104/11066 [04:03<37:04,  4.48it/s]
 10%|▉         | 1105/11066 [04:03<37:02,  4.48it/s]
                                                    

 10%|▉         | 1105/11066 [04:03<37:02,  4.48it/s]
 10%|▉         | 1106/11066 [04:03<36:59,  4.49it/s]
                                                    

 10%|▉         | 1106/11066 [04:03<36:59,  4.49it/s]
 10%|█         | 1107/11066 [04:03<36:56,  4.49it/s]
                                                    

 10%|█         | 1107/11066 [04:03<36:56,  4.49it/s]
 10%|█         | 1108/11066 [04:04<36:36,  4.53it/s]
                                                    

 10%|█         | 1108/11066 [04:04<36:36,  4.53it/s]
 10%|█         | 1109/11066 [04:04<36:18,  4.57it/s]
                                                    

 10%|█         | 1109/11066 [04:04<36:18,  4.57it/s]
 10%|█         | 1110/11066 [04:04<36:31,  4.54it/s]
                                                    

 10%|█         | 1110/11066 [04:04<36:31,  4.54it/s]
 10%|█         | 1111/11066 [04:04<36:34,  4.54it/s]
                                                    

 10%|█         | 1111/11066 [04:04<36:34,  4.54it/s]
 10%|█         | 1112/11066 [04:04<36:43,  4.52it/s]
                                                    

 10%|█         | 1112/11066 [04:04<36:43,  4.52it/s]
 10%|█         | 1113/11066 [04:05<36:28,  4.55it/s]
                                                    

 10%|█         | 1113/11066 [04:05<36:28,  4.55it/s]
 10%|█         | 1114/11066 [04:05<36:24,  4.55it/s]
                                                    

 10%|█         | 1114/11066 [04:05<36:24,  4.55it/s]
 10%|█         | 1115/11066 [04:05<36:16,  4.57it/s]
                                                    

 10%|█         | 1115/11066 [04:05<36:16,  4.57it/s]
 10%|█         | 1116/11066 [04:05<36:07,  4.59it/s]
                                                    

 10%|█         | 1116/11066 [04:05<36:07,  4.59it/s]
 10%|█         | 1117/11066 [04:06<36:14,  4.57it/s]
                                                    

 10%|█         | 1117/11066 [04:06<36:14,  4.57it/s]
 10%|█         | 1118/11066 [04:06<36:11,  4.58it/s]
                                                    

 10%|█         | 1118/11066 [04:06<36:11,  4.58it/s]
 10%|█         | 1119/11066 [04:06<36:27,  4.55it/s]
                                                    

 10%|█         | 1119/11066 [04:06<36:27,  4.55it/s]
 10%|█         | 1120/11066 [04:06<36:23,  4.56it/s]
                                                    

 10%|█         | 1120/11066 [04:06<36:23,  4.56it/s]
 10%|█         | 1121/11066 [04:06<36:32,  4.54it/s]
                                                    

 10%|█         | 1121/11066 [04:06<36:32,  4.54it/s]
 10%|█         | 1122/11066 [04:07<36:27,  4.55it/s]
                                                    

 10%|█         | 1122/11066 [04:07<36:27,  4.55it/s]
 10%|█         | 1123/11066 [04:07<36:33,  4.53it/s]
                                                    

 10%|█         | 1123/11066 [04:07<36:33,  4.53it/s]
 10%|█         | 1124/11066 [04:07<36:28,  4.54it/s]
                                                    

 10%|█         | 1124/11066 [04:07<36:28,  4.54it/s]
 10%|█         | 1125/11066 [04:07<36:21,  4.56it/s]
                                                    

 10%|█         | 1125/11066 [04:07<36:21,  4.56it/s]
 10%|█         | 1126/11066 [04:08<36:17,  4.57it/s]
                                                    

 10%|█         | 1126/11066 [04:08<36:17,  4.57it/s]
 10%|█         | 1127/11066 [04:08<36:09,  4.58it/s]
                                                    
{'loss': 0.9062, 'learning_rate': 2.7251039219230074e-05, 'epoch': 0.18}
{'loss': 1.4628, 'learning_rate': 2.7248328212542926e-05, 'epoch': 0.18}
{'loss': 1.9137, 'learning_rate': 2.7245617205855774e-05, 'epoch': 0.18}
{'loss': 1.8804, 'learning_rate': 2.7242906199168626e-05, 'epoch': 0.18}
{'loss': 1.8524, 'learning_rate': 2.7240195192481475e-05, 'epoch': 0.18}
{'loss': 0.9643, 'learning_rate': 2.7237484185794327e-05, 'epoch': 0.18}
{'loss': 1.5404, 'learning_rate': 2.723477317910718e-05, 'epoch': 0.18}
{'loss': 1.7029, 'learning_rate': 2.7232062172420023e-05, 'epoch': 0.18}
{'loss': 1.8739, 'learning_rate': 2.7229351165732875e-05, 'epoch': 0.18}
{'loss': 1.2704, 'learning_rate': 2.7226640159045727e-05, 'epoch': 0.18}
{'loss': 1.7513, 'learning_rate': 2.7223929152358576e-05, 'epoch': 0.19}
{'loss': 1.112, 'learning_rate': 2.7221218145671427e-05, 'epoch': 0.19}
{'loss': 1.3223, 'learning_rate': 2.721850713898428e-05, 'epoch': 0.19}
{'loss': 1.0846, 'learning_rate': 2.7215796132297128e-05, 'epoch': 0.19}
{'loss': 1.7419, 'learning_rate': 2.721308512560998e-05, 'epoch': 0.19}
{'loss': 2.0355, 'learning_rate': 2.7210374118922825e-05, 'epoch': 0.19}
{'loss': 0.8841, 'learning_rate': 2.7207663112235676e-05, 'epoch': 0.19}
{'loss': 0.9158, 'learning_rate': 2.7204952105548528e-05, 'epoch': 0.19}
{'loss': 1.0803, 'learning_rate': 2.7202241098861377e-05, 'epoch': 0.19}
{'loss': 1.3277, 'learning_rate': 2.719953009217423e-05, 'epoch': 0.19}
{'loss': 1.2473, 'learning_rate': 2.719681908548708e-05, 'epoch': 0.19}
{'loss': 0.7079, 'learning_rate': 2.719410807879993e-05, 'epoch': 0.19}
{'loss': 2.4951, 'learning_rate': 2.7191397072112777e-05, 'epoch': 0.19}
{'loss': 1.2336, 'learning_rate': 2.718868606542563e-05, 'epoch': 0.19}
{'loss': 1.4885, 'learning_rate': 2.7185975058738477e-05, 'epoch': 0.19}
{'loss': 2.0095, 'learning_rate': 2.718326405205133e-05, 'epoch': 0.19}
{'loss': 1.6769, 'learning_rate': 2.7180553045364178e-05, 'epoch': 0.19}
{'loss': 1.979, 'learning_rate': 2.717784203867703e-05, 'epoch': 0.19}
{'loss': 1.5445, 'learning_rate': 2.717513103198988e-05, 'epoch': 0.19}
{'loss': 1.7232, 'learning_rate': 2.717242002530273e-05, 'epoch': 0.19}
{'loss': 1.6426, 'learning_rate': 2.7169709018615578e-05, 'epoch': 0.19}
{'loss': 1.3445, 'learning_rate': 2.716699801192843e-05, 'epoch': 0.19}
{'loss': 1.1767, 'learning_rate': 2.716428700524128e-05, 'epoch': 0.19}
{'loss': 1.2197, 'learning_rate': 2.716157599855413e-05, 'epoch': 0.19}
{'loss': 1.3449, 'learning_rate': 2.7158864991866982e-05, 'epoch': 0.19}
{'loss': 1.5214, 'learning_rate': 2.715615398517983e-05, 'epoch': 0.19}
{'loss': 1.0026, 'learning_rate': 2.7153442978492682e-05, 'epoch': 0.19}
{'loss': 1.9728, 'learning_rate': 2.715073197180553e-05, 'epoch': 0.19}
{'loss': 0.8824, 'learning_rate': 2.714802096511838e-05, 'epoch': 0.19}
{'loss': 0.957, 'learning_rate': 2.714530995843123e-05, 'epoch': 0.19}
{'loss': 2.0404, 'learning_rate': 2.714259895174408e-05, 'epoch': 0.19}
{'loss': 1.3442, 'learning_rate': 2.713988794505693e-05, 'epoch': 0.19}
{'loss': 1.8999, 'learning_rate': 2.7137176938369783e-05, 'epoch': 0.19}
{'loss': 1.908, 'learning_rate': 2.713446593168263e-05, 'epoch': 0.19}
{'loss': 1.6524, 'learning_rate': 2.7131754924995483e-05, 'epoch': 0.19}
{'loss': 0.7136, 'learning_rate': 2.7129043918308335e-05, 'epoch': 0.19}
{'loss': 1.6288, 'learning_rate': 2.712633291162118e-05, 'epoch': 0.19}
{'loss': 0.9408, 'learning_rate': 2.7123621904934032e-05, 'epoch': 0.19}
{'loss': 1.3893, 'learning_rate': 2.712091089824688e-05, 'epoch': 0.19}
{'loss': 1.1287, 'learning_rate': 2.7118199891559732e-05, 'epoch': 0.19}
{'loss': 0.9585, 'learning_rate': 2.7115488884872584e-05, 'epoch': 0.19}
{'loss': 1.5622, 'learning_rate': 2.7112777878185433e-05, 'epoch': 0.19}
{'loss': 1.2484, 'learning_rate': 2.7110066871498285e-05, 'epoch': 0.19}
{'loss': 1.4023, 'learning_rate': 2.7107355864811136e-05, 'epoch': 0.19}
{'loss': 0.8818, 'learning_rate': 2.710464485812398e-05, 'epoch': 0.19}
{'loss': 1.3145, 'learning_rate': 2.7101933851436833e-05, 'epoch': 0.19}
{'loss': 0.9571, 'learning_rate': 2.7099222844749685e-05, 'epoch': 0.19}
{'loss': 0.8563, 'learning_rate': 2.7096511838062534e-05, 'epoch': 0.19}
{'loss': 1.3125, 'learning_rate': 2.7093800831375385e-05, 'epoch': 0.19}
{'loss': 1.6771, 'learning_rate': 2.7091089824688234e-05, 'epoch': 0.19}
{'loss': 1.535, 'learning_rate': 2.7088378818001086e-05, 'epoch': 0.19}
{'loss': 1.9488, 'learning_rate': 2.7085667811313937e-05, 'epoch': 0.19}
{'loss': 0.7889, 'learning_rate': 2.7082956804626783e-05, 'epoch': 0.19}
{'loss': 1.361, 'learning_rate': 2.7080245797939634e-05, 'epoch': 0.19}
{'loss': 0.8496, 'learning_rate': 2.7077534791252486e-05, 'epoch': 0.19}
{'loss': 1.3736, 'learning_rate': 2.7074823784565335e-05, 'epoch': 0.2}
{'loss': 1.5377, 'learning_rate': 2.7072112777878186e-05, 'epoch': 0.2}
{'loss': 1.335, 'learning_rate': 2.7069401771191038e-05, 'epoch': 0.2}
{'loss': 1.3907, 'learning_rate': 2.7066690764503887e-05, 'epoch': 0.2}
{'loss': 1.8112, 'learning_rate': 2.706397975781674e-05, 'epoch': 0.2}
{'loss': 1.682, 'learning_rate': 2.7061268751129587e-05, 'epoch': 0.2}
{'loss': 0.5081, 'learning_rate': 2.7058557744442435e-05, 'epoch': 0.2}
{'loss': 1.7465, 'learning_rate': 2.7055846737755287e-05, 'epoch': 0.2}
{'loss': 1.4016, 'learning_rate': 2.7053135731068136e-05, 'epoch': 0.2}
{'loss': 0.9802, 'learning_rate': 2.7050424724380988e-05, 'epoch': 0.2}
{'loss': 0.6116, 'learning_rate': 2.704771371769384e-05, 'epoch': 0.2}
{'loss': 1.599, 'learning_rate': 2.7045002711006688e-05, 'epoch': 0.2}
{'loss': 0.9053, 'learning_rate': 2.704229170431954e-05, 'epoch': 0.2}
{'loss': 1.4653, 'learning_rate': 2.7039580697632388e-05, 'epoch': 0.2}
{'loss': 2.3477, 'learning_rate': 2.7036869690945236e-05, 'epoch': 0.2}
{'loss': 1.8853, 'learning_rate': 2.703415868425809e-05, 'epoch': 0.2}
{'loss': 1.2223, 'learning_rate': 2.703144767757094e-05, 'epoch': 0.2}
{'loss': 1.5236, 'learning_rate': 2.702873667088379e-05, 'epoch': 0.2}
{'loss': 0.9324, 'learning_rate': 2.702602566419664e-05, 'epoch': 0.2}
{'loss': 1.582, 'learning_rate': 2.702331465750949e-05, 'epoch': 0.2}
{'loss': 1.0098, 'learning_rate': 2.702060365082234e-05, 'epoch': 0.2}
{'loss': 1.2031, 'learning_rate': 2.701789264413519e-05, 'epoch': 0.2}
{'loss': 1.5803, 'learning_rate': 2.7015181637448038e-05, 'epoch': 0.2}
{'loss': 1.923, 'learning_rate': 2.701247063076089e-05, 'epoch': 0.2}
{'loss': 0.943, 'learning_rate': 2.700975962407374e-05, 'epoch': 0.2}
{'loss': 1.3184, 'learning_rate': 2.700704861738659e-05, 'epoch': 0.2}
{'loss': 1.6709, 'learning_rate': 2.700433761069944e-05, 'epoch': 0.2}
{'loss': 1.492, 'learning_rate': 2.7001626604012293e-05, 'epoch': 0.2}
{'loss': 1.1729, 'learning_rate': 2.6998915597325142e-05, 'epoch': 0.2}
{'loss': 1.1529, 'learning_rate': 2.699620459063799e-05, 'epoch': 0.2}
{'loss': 1.0311, 'learning_rate': 2.699349358395084e-05, 'epoch': 0.2}
{'loss': 1.0418, 'learning_rate': 2.699078257726369e-05, 'epoch': 0.2}
{'loss': 1.4124, 'learning_rate': 2.6988071570576542e-05, 'epoch': 0.2}
{'loss': 1.0457, 'learning_rate': 2.698536056388939e-05, 'epoch': 0.2}
{'loss': 1.3759, 'learning_rate': 2.6982649557202243e-05, 'epoch': 0.2}
{'loss': 2.1346, 'learning_rate': 2.6979938550515094e-05, 'epoch': 0.2}
{'loss': 1.847, 'learning_rate': 2.6977227543827943e-05, 'epoch': 0.2}
{'loss': 1.2934, 'learning_rate': 2.697451653714079e-05, 'epoch': 0.2}
{'loss': 1.9505, 'learning_rate': 2.6971805530453643e-05, 'epoch': 0.2}
{'loss': 0.9823, 'learning_rate': 2.696909452376649e-05, 'epoch': 0.2}
{'loss': 1.3221, 'learning_rate': 2.6966383517079343e-05, 'epoch': 0.2}
{'loss': 1.4005, 'learning_rate': 2.6963672510392192e-05, 'epoch': 0.2}
{'loss': 1.5384, 'learning_rate': 2.6960961503705044e-05, 'epoch': 0.2}
{'loss': 1.5855, 'learning_rate': 2.6958250497017895e-05, 'epoch': 0.2}
{'loss': 0.9163, 'learning_rate': 2.6955539490330744e-05, 'epoch': 0.2}
{'loss': 1.4976, 'learning_rate': 2.6952828483643592e-05, 'epoch': 0.2}
{'loss': 2.178, 'learning_rate': 2.6950117476956444e-05, 'epoch': 0.2}
{'loss': 1.6179, 'learning_rate': 2.6947406470269293e-05, 'epoch': 0.2}

 10%|█         | 1127/11066 [04:08<36:09,  4.58it/s]
 10%|█         | 1128/11066 [04:08<36:29,  4.54it/s]
                                                    

 10%|█         | 1128/11066 [04:08<36:29,  4.54it/s]
 10%|█         | 1129/11066 [04:08<36:45,  4.51it/s]
                                                    

 10%|█         | 1129/11066 [04:08<36:45,  4.51it/s]
 10%|█         | 1130/11066 [04:08<36:46,  4.50it/s]
                                                    

 10%|█         | 1130/11066 [04:08<36:46,  4.50it/s]
 10%|█         | 1131/11066 [04:09<36:47,  4.50it/s]
                                                    

 10%|█         | 1131/11066 [04:09<36:47,  4.50it/s]
 10%|█         | 1132/11066 [04:09<36:46,  4.50it/s]
                                                    

 10%|█         | 1132/11066 [04:09<36:46,  4.50it/s]
 10%|█         | 1133/11066 [04:09<36:47,  4.50it/s]
                                                    

 10%|█         | 1133/11066 [04:09<36:47,  4.50it/s]
 10%|█         | 1134/11066 [04:09<36:29,  4.54it/s]
                                                    

 10%|█         | 1134/11066 [04:09<36:29,  4.54it/s]
 10%|█         | 1135/11066 [04:10<36:42,  4.51it/s]
                                                    

 10%|█         | 1135/11066 [04:10<36:42,  4.51it/s]
 10%|█         | 1136/11066 [04:10<36:45,  4.50it/s]
                                                    

 10%|█         | 1136/11066 [04:10<36:45,  4.50it/s]
 10%|█         | 1137/11066 [04:10<36:46,  4.50it/s]
                                                    

 10%|█         | 1137/11066 [04:10<36:46,  4.50it/s]
 10%|█         | 1138/11066 [04:10<36:47,  4.50it/s]
                                                    

 10%|█         | 1138/11066 [04:10<36:47,  4.50it/s]
 10%|█         | 1139/11066 [04:10<36:46,  4.50it/s]
                                                    

 10%|█         | 1139/11066 [04:10<36:46,  4.50it/s]
 10%|█         | 1140/11066 [04:11<36:46,  4.50it/s]
                                                    

 10%|█         | 1140/11066 [04:11<36:46,  4.50it/s]
 10%|█         | 1141/11066 [04:11<36:45,  4.50it/s]
                                                    

 10%|█         | 1141/11066 [04:11<36:45,  4.50it/s]
 10%|█         | 1142/11066 [04:11<36:43,  4.50it/s]
                                                    

 10%|█         | 1142/11066 [04:11<36:43,  4.50it/s]
 10%|█         | 1143/11066 [04:11<36:46,  4.50it/s]
                                                    

 10%|█         | 1143/11066 [04:11<36:46,  4.50it/s]
 10%|█         | 1144/11066 [04:12<36:46,  4.50it/s]
                                                    

 10%|█         | 1144/11066 [04:12<36:46,  4.50it/s]
 10%|█         | 1145/11066 [04:12<36:44,  4.50it/s]
                                                    

 10%|█         | 1145/11066 [04:12<36:44,  4.50it/s]
 10%|█         | 1146/11066 [04:12<36:43,  4.50it/s]
                                                    

 10%|█         | 1146/11066 [04:12<36:43,  4.50it/s]
 10%|█         | 1147/11066 [04:12<36:42,  4.50it/s]
                                                    

 10%|█         | 1147/11066 [04:12<36:42,  4.50it/s]
 10%|█         | 1148/11066 [04:12<36:40,  4.51it/s]
                                                    

 10%|█         | 1148/11066 [04:12<36:40,  4.51it/s]
 10%|█         | 1149/11066 [04:13<36:42,  4.50it/s]
                                                    

 10%|█         | 1149/11066 [04:13<36:42,  4.50it/s]
 10%|█         | 1150/11066 [04:13<36:25,  4.54it/s]
                                                    

 10%|█         | 1150/11066 [04:13<36:25,  4.54it/s]
 10%|█         | 1151/11066 [04:13<36:39,  4.51it/s]
                                                    

 10%|█         | 1151/11066 [04:13<36:39,  4.51it/s]
 10%|█         | 1152/11066 [04:13<36:28,  4.53it/s]
                                                    

 10%|█         | 1152/11066 [04:13<36:28,  4.53it/s]
 10%|█         | 1153/11066 [04:14<36:34,  4.52it/s]
                                                    

 10%|█         | 1153/11066 [04:14<36:34,  4.52it/s]
 10%|█         | 1154/11066 [04:14<36:43,  4.50it/s]
                                                    

 10%|█         | 1154/11066 [04:14<36:43,  4.50it/s]
 10%|█         | 1155/11066 [04:14<36:31,  4.52it/s]
                                                    

 10%|█         | 1155/11066 [04:14<36:31,  4.52it/s]
 10%|█         | 1156/11066 [04:14<36:37,  4.51it/s]
                                                    

 10%|█         | 1156/11066 [04:14<36:37,  4.51it/s]
 10%|█         | 1157/11066 [04:14<36:43,  4.50it/s]
                                                    

 10%|█         | 1157/11066 [04:14<36:43,  4.50it/s]
 10%|█         | 1158/11066 [04:15<36:53,  4.48it/s]
                                                    

 10%|█         | 1158/11066 [04:15<36:53,  4.48it/s]
 10%|█         | 1159/11066 [04:15<36:53,  4.48it/s]
                                                    

 10%|█         | 1159/11066 [04:15<36:53,  4.48it/s]
 10%|█         | 1160/11066 [04:15<36:50,  4.48it/s]
                                                    

 10%|█         | 1160/11066 [04:15<36:50,  4.48it/s]
 10%|█         | 1161/11066 [04:15<36:30,  4.52it/s]
                                                    

 10%|█         | 1161/11066 [04:15<36:30,  4.52it/s]
 11%|█         | 1162/11066 [04:16<36:40,  4.50it/s]
                                                    

 11%|█         | 1162/11066 [04:16<36:40,  4.50it/s]
 11%|█         | 1163/11066 [04:16<36:49,  4.48it/s]
                                                    

 11%|█         | 1163/11066 [04:16<36:49,  4.48it/s]
 11%|█         | 1164/11066 [04:16<36:32,  4.52it/s]
                                                    

 11%|█         | 1164/11066 [04:16<36:32,  4.52it/s]
 11%|█         | 1165/11066 [04:16<36:43,  4.49it/s]
                                                    

 11%|█         | 1165/11066 [04:16<36:43,  4.49it/s]
 11%|█         | 1166/11066 [04:16<36:47,  4.48it/s]
                                                    

 11%|█         | 1166/11066 [04:16<36:47,  4.48it/s]
 11%|█         | 1167/11066 [04:17<36:46,  4.49it/s]
                                                    

 11%|█         | 1167/11066 [04:17<36:46,  4.49it/s]
 11%|█         | 1168/11066 [04:17<36:28,  4.52it/s]
                                                    

 11%|█         | 1168/11066 [04:17<36:28,  4.52it/s]
 11%|█         | 1169/11066 [04:17<36:20,  4.54it/s]
                                                    

 11%|█         | 1169/11066 [04:17<36:20,  4.54it/s]
 11%|█         | 1170/11066 [04:17<36:24,  4.53it/s]
                                                    

 11%|█         | 1170/11066 [04:17<36:24,  4.53it/s]
 11%|█         | 1171/11066 [04:18<36:31,  4.51it/s]
                                                    

 11%|█         | 1171/11066 [04:18<36:31,  4.51it/s]
 11%|█         | 1172/11066 [04:18<36:34,  4.51it/s]
                                                    

 11%|█         | 1172/11066 [04:18<36:34,  4.51it/s]
 11%|█         | 1173/11066 [04:18<36:18,  4.54it/s]
                                                    

 11%|█         | 1173/11066 [04:18<36:18,  4.54it/s]
 11%|█         | 1174/11066 [04:18<36:16,  4.55it/s]
                                                    

 11%|█         | 1174/11066 [04:18<36:16,  4.55it/s]
 11%|█         | 1175/11066 [04:18<36:04,  4.57it/s]
                                                    

 11%|█         | 1175/11066 [04:18<36:04,  4.57it/s]
 11%|█         | 1176/11066 [04:19<36:23,  4.53it/s]
                                                    

 11%|█         | 1176/11066 [04:19<36:23,  4.53it/s]
 11%|█         | 1177/11066 [04:19<36:33,  4.51it/s]
                                                    

 11%|█         | 1177/11066 [04:19<36:33,  4.51it/s]
 11%|█         | 1178/11066 [04:19<36:33,  4.51it/s]
                                                    

 11%|█         | 1178/11066 [04:19<36:33,  4.51it/s]
 11%|█         | 1179/11066 [04:19<36:34,  4.50it/s]
                                                    

 11%|█         | 1179/11066 [04:19<36:34,  4.50it/s]
 11%|█         | 1180/11066 [04:19<36:36,  4.50it/s]
                                                    

 11%|█         | 1180/11066 [04:19<36:36,  4.50it/s]
 11%|█         | 1181/11066 [04:20<36:20,  4.53it/s]
                                                    

 11%|█         | 1181/11066 [04:20<36:20,  4.53it/s]
 11%|█         | 1182/11066 [04:20<36:00,  4.57it/s]
                                                    

 11%|█         | 1182/11066 [04:20<36:00,  4.57it/s]
 11%|█         | 1183/11066 [04:20<36:15,  4.54it/s]
                                                    

 11%|█         | 1183/11066 [04:20<36:15,  4.54it/s]
 11%|█         | 1184/11066 [04:20<36:24,  4.52it/s]
                                                    

 11%|█         | 1184/11066 [04:20<36:24,  4.52it/s]
 11%|█         | 1185/11066 [04:21<36:33,  4.50it/s]
                                                    

 11%|█         | 1185/11066 [04:21<36:33,  4.50it/s]
 11%|█         | 1186/11066 [04:21<36:38,  4.49it/s]
                                                    

 11%|█         | 1186/11066 [04:21<36:38,  4.49it/s]
 11%|█         | 1187/11066 [04:21<36:35,  4.50it/s]
                                                    

 11%|█         | 1187/11066 [04:21<36:35,  4.50it/s]
 11%|█         | 1188/11066 [04:21<36:35,  4.50it/s]
                                                    

 11%|█         | 1188/11066 [04:21<36:35,  4.50it/s]
 11%|█         | 1189/11066 [04:21<36:17,  4.54it/s]
                                                    

 11%|█         | 1189/11066 [04:21<36:17,  4.54it/s]
 11%|█         | 1190/11066 [04:22<36:00,  4.57it/s]
                                                    

 11%|█         | 1190/11066 [04:22<36:00,  4.57it/s]
 11%|█         | 1191/11066 [04:22<36:13,  4.54it/s]
                                                    

 11%|█         | 1191/11066 [04:22<36:13,  4.54it/s]
 11%|█         | 1192/11066 [04:22<36:05,  4.56it/s]
                                                    

 11%|█         | 1192/11066 [04:22<36:05,  4.56it/s]
 11%|█         | 1193/11066 [04:22<35:59,  4.57it/s]
                                                    

 11%|█         | 1193/11066 [04:22<35:59,  4.57it/s]
 11%|█         | 1194/11066 [04:23<35:54,  4.58it/s]
                                                    

 11%|█         | 1194/11066 [04:23<35:54,  4.58it/s]
 11%|█         | 1195/11066 [04:23<36:08,  4.55it/s]
                                                    

 11%|█         | 1195/11066 [04:23<36:08,  4.55it/s]
 11%|█         | 1196/11066 [04:23<36:10,  4.55it/s]
                                                    

 11%|█         | 1196/11066 [04:23<36:10,  4.55it/s]
 11%|█         | 1197/11066 [04:23<35:58,  4.57it/s]
                                                    

 11%|█         | 1197/11066 [04:23<35:58,  4.57it/s]
 11%|█         | 1198/11066 [04:23<36:04,  4.56it/s]
                                                    

 11%|█         | 1198/11066 [04:23<36:04,  4.56it/s]
 11%|█         | 1199/11066 [04:24<35:44,  4.60it/s]
                                                    

 11%|█         | 1199/11066 [04:24<35:44,  4.60it/s]
 11%|█         | 1200/11066 [04:24<35:52,  4.58it/s]
                                                    

 11%|█         | 1200/11066 [04:24<35:52,  4.58it/s]
 11%|█         | 1201/11066 [04:24<35:45,  4.60it/s]
                                                    

 11%|█         | 1201/11066 [04:24<35:45,  4.60it/s]
 11%|█         | 1202/11066 [04:24<35:38,  4.61it/s]
                                                    

 11%|█         | 1202/11066 [04:24<35:38,  4.61it/s]
 11%|█         | 1203/11066 [04:25<35:57,  4.57it/s]
                                                    

 11%|█         | 1203/11066 [04:25<35:57,  4.57it/s]
 11%|█         | 1204/11066 [04:25<35:52,  4.58it/s]
                                                    

 11%|█         | 1204/11066 [04:25<35:52,  4.58it/s]
 11%|█         | 1205/11066 [04:25<36:08,  4.55it/s]
                                                    

 11%|█         | 1205/11066 [04:25<36:08,  4.55it/s]
 11%|█         | 1206/11066 [04:25<36:01,  4.56it/s]
                                                    

 11%|█         | 1206/11066 [04:25<36:01,  4.56it/s]
 11%|█         | 1207/11066 [04:25<36:06,  4.55it/s]
                                                    

 11%|█         | 1207/11066 [04:25<36:06,  4.55it/s]
 11%|█         | 1208/11066 [04:26<36:01,  4.56it/s]
                                                    

 11%|█         | 1208/11066 [04:26<36:01,  4.56it/s]
 11%|█         | 1209/11066 [04:26<35:46,  4.59it/s]
                                                    

 11%|█         | 1209/11066 [04:26<35:46,  4.59it/s]
 11%|█         | 1210/11066 [04:26<35:56,  4.57it/s]
                                                    

 11%|█         | 1210/11066 [04:26<35:56,  4.57it/s]
 11%|█         | 1211/11066 [04:26<35:45,  4.59it/s]
                                                    

 11%|█         | 1211/11066 [04:26<35:45,  4.59it/s]
 11%|█         | 1212/11066 [04:27<36:03,  4.56it/s]
                                                    

 11%|█         | 1212/11066 [04:27<36:03,  4.56it/s]
 11%|█         | 1213/11066 [04:27<36:16,  4.53it/s]
                                                    

 11%|█         | 1213/11066 [04:27<36:16,  4.53it/s]
 11%|█         | 1214/11066 [04:27<36:27,  4.50it/s]
                                                    

 11%|█         | 1214/11066 [04:27<36:27,  4.50it/s]
 11%|█         | 1215/11066 [04:27<37:02,  4.43it/s]
                                                    

 11%|█         | 1215/11066 [04:27<37:02,  4.43it/s]
 11%|█         | 1216/11066 [04:27<37:07,  4.42it/s]
                                                    

 11%|█         | 1216/11066 [04:27<37:07,  4.42it/s]
 11%|█         | 1217/11066 [04:28<36:58,  4.44it/s]
                                                    

 11%|█         | 1217/11066 [04:28<36:58,  4.44it/s]
 11%|█         | 1218/11066 [04:28<37:08,  4.42it/s]
                                                    

 11%|█         | 1218/11066 [04:28<37:08,  4.42it/s]
 11%|█         | 1219/11066 [04:28<36:47,  4.46it/s]
                                                    

 11%|█         | 1219/11066 [04:28<36:47,  4.46it/s]
 11%|█         | 1220/11066 [04:28<36:13,  4.53it/s]
                                                    

 11%|█         | 1220/11066 [04:28<36:13,  4.53it/s]
 11%|█         | 1221/11066 [04:29<36:16,  4.52it/s]
                                                    

 11%|█         | 1221/11066 [04:29<36:16,  4.52it/s]
 11%|█         | 1222/11066 [04:29<36:00,  4.56it/s]
                                                    

 11%|█         | 1222/11066 [04:29<36:00,  4.56it/s]
 11%|█         | 1223/11066 [04:29<35:59,  4.56it/s]
                                                    

 11%|█         | 1223/11066 [04:29<35:59,  4.56it/s]
 11%|█         | 1224/11066 [04:29<36:04,  4.55it/s]
                                                    

 11%|█         | 1224/11066 [04:29<36:04,  4.55it/s]
 11%|█         | 1225/11066 [04:29<35:52,  4.57it/s]
                                                    

 11%|█         | 1225/11066 [04:29<35:52,  4.57it/s]
 11%|█         | 1226/11066 [04:30<35:39,  4.60it/s]
                                                    

 11%|█         | 1226/11066 [04:30<35:39,  4.60it/s]
 11%|█         | 1227/11066 [04:30<35:43,  4.59it/s]
                                                    

 11%|█         | 1227/11066 [04:30<35:43,  4.59it/s]
 11%|█         | 1228/11066 [04:30<36:04,  4.54it/s]
                                                    

 11%|█         | 1228/11066 [04:30<36:04,  4.54it/s]
 11%|█         | 1229/11066 [04:30<36:16,  4.52it/s]
                                                    

 11%|█         | 1229/11066 [04:30<36:16,  4.52it/s]
 11%|█         | 1230/11066 [04:31<36:27,  4.50it/s]
                                                    

 11%|█         | 1230/11066 [04:31<36:27,  4.50it/s]
 11%|█         | 1231/11066 [04:31<36:26,  4.50it/s]
                                                    

 11%|█         | 1231/11066 [04:31<36:26,  4.50it/s]
 11%|█         | 1232/11066 [04:31<35:54,  4.56it/s]
                                                    

 11%|█         | 1232/11066 [04:31<35:54,  4.56it/s]
 11%|█         | 1233/11066 [04:31<35:45,  4.58it/s]
                                                    

 11%|█         | 1233/11066 [04:31<35:45,  4.58it/s]
 11%|█         | 1234/11066 [04:31<35:31,  4.61it/s]
                                                    

 11%|█         | 1234/11066 [04:31<35:31,  4.61it/s]
 11%|█         | 1235/11066 [04:32<35:29,  4.62it/s]
                                                    

 11%|█         | 1235/11066 [04:32<35:29,  4.62it/s]
 11%|█         | 1236/11066 [04:32<35:29,  4.62it/s]
                                                    

 11%|█         | 1236/11066 [04:32<35:29,  4.62it/s]
 11%|█         | 1237/11066 [04:32<35:24,  4.63it/s]
                                                    

 11%|█         | 1237/11066 [04:32<35:24,  4.63it/s]
 11%|█         | 1238/11066 [04:32<35:16,  4.64it/s]
                                                    

 11%|█         | 1238/11066 [04:32<35:16,  4.64it/s]
 11%|█         | 1239/11066 [04:32<35:39,  4.59it/s]
                                                    

 11%|█         | 1239/11066 [04:32<35:39,  4.59it/s]
 11%|█         | 1240/11066 [04:33<35:39,  4.59it/s]
                                                    
{'loss': 1.2563, 'learning_rate': 2.6944695463582144e-05, 'epoch': 0.2}
{'loss': 1.0921, 'learning_rate': 2.6941984456894996e-05, 'epoch': 0.2}
{'loss': 1.6534, 'learning_rate': 2.6939273450207845e-05, 'epoch': 0.2}
{'loss': 1.0301, 'learning_rate': 2.6936562443520697e-05, 'epoch': 0.2}
{'loss': 1.6061, 'learning_rate': 2.6933851436833545e-05, 'epoch': 0.2}
{'loss': 1.697, 'learning_rate': 2.6931140430146393e-05, 'epoch': 0.2}
{'loss': 1.8328, 'learning_rate': 2.6928429423459245e-05, 'epoch': 0.2}
{'loss': 1.9209, 'learning_rate': 2.6925718416772094e-05, 'epoch': 0.2}
{'loss': 1.5088, 'learning_rate': 2.6923007410084946e-05, 'epoch': 0.21}
{'loss': 1.1921, 'learning_rate': 2.6920296403397797e-05, 'epoch': 0.21}
{'loss': 1.1036, 'learning_rate': 2.6917585396710646e-05, 'epoch': 0.21}
{'loss': 2.1663, 'learning_rate': 2.6914874390023498e-05, 'epoch': 0.21}
{'loss': 1.516, 'learning_rate': 2.691216338333635e-05, 'epoch': 0.21}
{'loss': 1.9421, 'learning_rate': 2.6909452376649194e-05, 'epoch': 0.21}
{'loss': 1.905, 'learning_rate': 2.6906741369962046e-05, 'epoch': 0.21}
{'loss': 1.1975, 'learning_rate': 2.6904030363274895e-05, 'epoch': 0.21}
{'loss': 1.6965, 'learning_rate': 2.6901319356587747e-05, 'epoch': 0.21}
{'loss': 0.8957, 'learning_rate': 2.68986083499006e-05, 'epoch': 0.21}
{'loss': 0.9554, 'learning_rate': 2.6895897343213447e-05, 'epoch': 0.21}
{'loss': 0.8314, 'learning_rate': 2.68931863365263e-05, 'epoch': 0.21}
{'loss': 1.28, 'learning_rate': 2.689047532983915e-05, 'epoch': 0.21}
{'loss': 1.0887, 'learning_rate': 2.6887764323151996e-05, 'epoch': 0.21}
{'loss': 1.9061, 'learning_rate': 2.6885053316464847e-05, 'epoch': 0.21}
{'loss': 1.0683, 'learning_rate': 2.68823423097777e-05, 'epoch': 0.21}
{'loss': 1.9752, 'learning_rate': 2.6879631303090548e-05, 'epoch': 0.21}
{'loss': 1.1224, 'learning_rate': 2.68769202964034e-05, 'epoch': 0.21}
{'loss': 0.9348, 'learning_rate': 2.6874209289716248e-05, 'epoch': 0.21}
{'loss': 0.8522, 'learning_rate': 2.68714982830291e-05, 'epoch': 0.21}
{'loss': 1.6131, 'learning_rate': 2.686878727634195e-05, 'epoch': 0.21}
{'loss': 0.9252, 'learning_rate': 2.6866076269654797e-05, 'epoch': 0.21}
{'loss': 1.4503, 'learning_rate': 2.686336526296765e-05, 'epoch': 0.21}
{'loss': 1.8702, 'learning_rate': 2.68606542562805e-05, 'epoch': 0.21}
{'loss': 0.9522, 'learning_rate': 2.685794324959335e-05, 'epoch': 0.21}
{'loss': 1.861, 'learning_rate': 2.68552322429062e-05, 'epoch': 0.21}
{'loss': 1.9098, 'learning_rate': 2.6852521236219052e-05, 'epoch': 0.21}
{'loss': 2.2332, 'learning_rate': 2.68498102295319e-05, 'epoch': 0.21}
{'loss': 2.073, 'learning_rate': 2.684709922284475e-05, 'epoch': 0.21}
{'loss': 1.5089, 'learning_rate': 2.6844388216157598e-05, 'epoch': 0.21}
{'loss': 1.206, 'learning_rate': 2.684167720947045e-05, 'epoch': 0.21}
{'loss': 1.0134, 'learning_rate': 2.68389662027833e-05, 'epoch': 0.21}
{'loss': 1.2653, 'learning_rate': 2.683625519609615e-05, 'epoch': 0.21}
{'loss': 1.0223, 'learning_rate': 2.6833544189409e-05, 'epoch': 0.21}
{'loss': 1.7447, 'learning_rate': 2.6830833182721853e-05, 'epoch': 0.21}
{'loss': 1.1116, 'learning_rate': 2.6828122176034702e-05, 'epoch': 0.21}
{'loss': 0.7189, 'learning_rate': 2.682541116934755e-05, 'epoch': 0.21}
{'loss': 1.3053, 'learning_rate': 2.6822700162660402e-05, 'epoch': 0.21}
{'loss': 1.6461, 'learning_rate': 2.681998915597325e-05, 'epoch': 0.21}
{'loss': 1.5068, 'learning_rate': 2.6817278149286102e-05, 'epoch': 0.21}
{'loss': 1.1268, 'learning_rate': 2.681456714259895e-05, 'epoch': 0.21}
{'loss': 1.3778, 'learning_rate': 2.6811856135911803e-05, 'epoch': 0.21}
{'loss': 1.1914, 'learning_rate': 2.6809145129224655e-05, 'epoch': 0.21}
{'loss': 1.0249, 'learning_rate': 2.6806434122537503e-05, 'epoch': 0.21}
{'loss': 1.0466, 'learning_rate': 2.680372311585035e-05, 'epoch': 0.21}
{'loss': 1.3174, 'learning_rate': 2.6801012109163203e-05, 'epoch': 0.21}
{'loss': 1.4967, 'learning_rate': 2.679830110247605e-05, 'epoch': 0.21}
{'loss': 0.7624, 'learning_rate': 2.6795590095788904e-05, 'epoch': 0.21}
{'loss': 1.4425, 'learning_rate': 2.6792879089101755e-05, 'epoch': 0.21}
{'loss': 1.2821, 'learning_rate': 2.6790168082414604e-05, 'epoch': 0.21}
{'loss': 1.7487, 'learning_rate': 2.6787457075727456e-05, 'epoch': 0.21}
{'loss': 1.9901, 'learning_rate': 2.6784746069040304e-05, 'epoch': 0.21}
{'loss': 1.4772, 'learning_rate': 2.6782035062353152e-05, 'epoch': 0.21}
{'loss': 1.4579, 'learning_rate': 2.6779324055666004e-05, 'epoch': 0.21}
{'loss': 1.5285, 'learning_rate': 2.6776613048978853e-05, 'epoch': 0.21}
{'loss': 1.1125, 'learning_rate': 2.6773902042291705e-05, 'epoch': 0.22}
{'loss': 1.4084, 'learning_rate': 2.6771191035604556e-05, 'epoch': 0.22}
{'loss': 1.3202, 'learning_rate': 2.6768480028917405e-05, 'epoch': 0.22}
{'loss': 1.1488, 'learning_rate': 2.6765769022230257e-05, 'epoch': 0.22}
{'loss': 1.8258, 'learning_rate': 2.676305801554311e-05, 'epoch': 0.22}
{'loss': 1.9122, 'learning_rate': 2.6760347008855954e-05, 'epoch': 0.22}
{'loss': 2.2394, 'learning_rate': 2.6757636002168805e-05, 'epoch': 0.22}
{'loss': 2.0075, 'learning_rate': 2.6754924995481654e-05, 'epoch': 0.22}
{'loss': 1.1875, 'learning_rate': 2.6752213988794506e-05, 'epoch': 0.22}
{'loss': 1.4799, 'learning_rate': 2.6749502982107357e-05, 'epoch': 0.22}
{'loss': 0.9844, 'learning_rate': 2.6746791975420206e-05, 'epoch': 0.22}
{'loss': 1.3212, 'learning_rate': 2.6744080968733058e-05, 'epoch': 0.22}
{'loss': 1.3499, 'learning_rate': 2.674136996204591e-05, 'epoch': 0.22}
{'loss': 1.0824, 'learning_rate': 2.6738658955358755e-05, 'epoch': 0.22}
{'loss': 1.8892, 'learning_rate': 2.6735947948671606e-05, 'epoch': 0.22}
{'loss': 0.8448, 'learning_rate': 2.6733236941984458e-05, 'epoch': 0.22}
{'loss': 1.2644, 'learning_rate': 2.6730525935297307e-05, 'epoch': 0.22}
{'loss': 1.6783, 'learning_rate': 2.672781492861016e-05, 'epoch': 0.22}
{'loss': 1.2407, 'learning_rate': 2.6725103921923007e-05, 'epoch': 0.22}
{'loss': 1.6852, 'learning_rate': 2.672239291523586e-05, 'epoch': 0.22}
{'loss': 1.4024, 'learning_rate': 2.671968190854871e-05, 'epoch': 0.22}
{'loss': 1.0861, 'learning_rate': 2.6716970901861556e-05, 'epoch': 0.22}
{'loss': 1.2643, 'learning_rate': 2.6714259895174408e-05, 'epoch': 0.22}
{'loss': 1.5964, 'learning_rate': 2.671154888848726e-05, 'epoch': 0.22}
{'loss': 1.2262, 'learning_rate': 2.6708837881800108e-05, 'epoch': 0.22}
{'loss': 1.8245, 'learning_rate': 2.670612687511296e-05, 'epoch': 0.22}
{'loss': 1.4097, 'learning_rate': 2.670341586842581e-05, 'epoch': 0.22}
{'loss': 1.0879, 'learning_rate': 2.670070486173866e-05, 'epoch': 0.22}
{'loss': 1.4111, 'learning_rate': 2.6697993855051512e-05, 'epoch': 0.22}
{'loss': 1.3538, 'learning_rate': 2.669528284836436e-05, 'epoch': 0.22}
{'loss': 1.0038, 'learning_rate': 2.669257184167721e-05, 'epoch': 0.22}
{'loss': 1.5316, 'learning_rate': 2.668986083499006e-05, 'epoch': 0.22}
{'loss': 1.6324, 'learning_rate': 2.668714982830291e-05, 'epoch': 0.22}
{'loss': 1.3163, 'learning_rate': 2.668443882161576e-05, 'epoch': 0.22}
{'loss': 1.0891, 'learning_rate': 2.6681727814928613e-05, 'epoch': 0.22}
{'loss': 1.0024, 'learning_rate': 2.667901680824146e-05, 'epoch': 0.22}
{'loss': 1.4381, 'learning_rate': 2.6676305801554313e-05, 'epoch': 0.22}
{'loss': 1.3101, 'learning_rate': 2.667359479486716e-05, 'epoch': 0.22}
{'loss': 1.7932, 'learning_rate': 2.667088378818001e-05, 'epoch': 0.22}
{'loss': 1.0972, 'learning_rate': 2.666817278149286e-05, 'epoch': 0.22}
{'loss': 1.2447, 'learning_rate': 2.6665461774805713e-05, 'epoch': 0.22}
{'loss': 0.8819, 'learning_rate': 2.6662750768118562e-05, 'epoch': 0.22}
{'loss': 1.0214, 'learning_rate': 2.6660039761431414e-05, 'epoch': 0.22}
{'loss': 0.9914, 'learning_rate': 2.6657328754744262e-05, 'epoch': 0.22}
{'loss': 1.1109, 'learning_rate': 2.6654617748057114e-05, 'epoch': 0.22}
{'loss': 1.5488, 'learning_rate': 2.6651906741369962e-05, 'epoch': 0.22}
{'loss': 1.078, 'learning_rate': 2.664919573468281e-05, 'epoch': 0.22}
{'loss': 0.8268, 'learning_rate': 2.6646484727995663e-05, 'epoch': 0.22}
{'loss': 1.0925, 'learning_rate': 2.6643773721308514e-05, 'epoch': 0.22}
{'loss': 0.9388, 'learning_rate': 2.6641062714621363e-05, 'epoch': 0.22}

 11%|█         | 1240/11066 [04:33<35:39,  4.59it/s]
 11%|█         | 1241/11066 [04:33<35:25,  4.62it/s]
                                                    

 11%|█         | 1241/11066 [04:33<35:25,  4.62it/s]
 11%|█         | 1242/11066 [04:33<35:51,  4.57it/s]
                                                    

 11%|█         | 1242/11066 [04:33<35:51,  4.57it/s]
 11%|█         | 1243/11066 [04:33<36:06,  4.53it/s]
                                                    

 11%|█         | 1243/11066 [04:33<36:06,  4.53it/s]
 11%|█         | 1244/11066 [04:34<36:12,  4.52it/s]
                                                    

 11%|█         | 1244/11066 [04:34<36:12,  4.52it/s]
 11%|█▏        | 1245/11066 [04:34<36:16,  4.51it/s]
                                                    

 11%|█▏        | 1245/11066 [04:34<36:16,  4.51it/s]
 11%|█▏        | 1246/11066 [04:34<35:50,  4.57it/s]
                                                    

 11%|█▏        | 1246/11066 [04:34<35:50,  4.57it/s]
 11%|█▏        | 1247/11066 [04:34<35:35,  4.60it/s]
                                                    

 11%|█▏        | 1247/11066 [04:34<35:35,  4.60it/s]
 11%|█▏        | 1248/11066 [04:34<35:31,  4.61it/s]
                                                    

 11%|█▏        | 1248/11066 [04:34<35:31,  4.61it/s]
 11%|█▏        | 1249/11066 [04:35<35:53,  4.56it/s]
                                                    

 11%|█▏        | 1249/11066 [04:35<35:53,  4.56it/s]
 11%|█▏        | 1250/11066 [04:35<35:47,  4.57it/s]
                                                    

 11%|█▏        | 1250/11066 [04:35<35:47,  4.57it/s]
 11%|█▏        | 1251/11066 [04:35<36:03,  4.54it/s]
                                                    

 11%|█▏        | 1251/11066 [04:35<36:03,  4.54it/s]
 11%|█▏        | 1252/11066 [04:35<35:44,  4.58it/s]
                                                    

 11%|█▏        | 1252/11066 [04:35<35:44,  4.58it/s]
 11%|█▏        | 1253/11066 [04:36<36:24,  4.49it/s]
                                                    

 11%|█▏        | 1253/11066 [04:36<36:24,  4.49it/s]
 11%|█▏        | 1254/11066 [04:36<36:10,  4.52it/s]
                                                    

 11%|█▏        | 1254/11066 [04:36<36:10,  4.52it/s]
 11%|█▏        | 1255/11066 [04:36<35:47,  4.57it/s]
                                                    

 11%|█▏        | 1255/11066 [04:36<35:47,  4.57it/s]
 11%|█▏        | 1256/11066 [04:36<36:02,  4.54it/s]
                                                    

 11%|█▏        | 1256/11066 [04:36<36:02,  4.54it/s]
 11%|█▏        | 1257/11066 [04:36<36:17,  4.50it/s]
                                                    

 11%|█▏        | 1257/11066 [04:36<36:17,  4.50it/s]
 11%|█▏        | 1258/11066 [04:37<36:22,  4.49it/s]
                                                    

 11%|█▏        | 1258/11066 [04:37<36:22,  4.49it/s]
 11%|█▏        | 1259/11066 [04:37<36:22,  4.49it/s]
                                                    

 11%|█▏        | 1259/11066 [04:37<36:22,  4.49it/s]
 11%|█▏        | 1260/11066 [04:37<36:19,  4.50it/s]
                                                    

 11%|█▏        | 1260/11066 [04:37<36:19,  4.50it/s]
 11%|█▏        | 1261/11066 [04:37<36:21,  4.49it/s]
                                                    

 11%|█▏        | 1261/11066 [04:37<36:21,  4.49it/s]
 11%|█▏        | 1262/11066 [04:38<36:20,  4.50it/s]
                                                    

 11%|█▏        | 1262/11066 [04:38<36:20,  4.50it/s]
 11%|█▏        | 1263/11066 [04:38<36:20,  4.50it/s]
                                                    

 11%|█▏        | 1263/11066 [04:38<36:20,  4.50it/s]
 11%|█▏        | 1264/11066 [04:38<36:19,  4.50it/s]
                                                    

 11%|█▏        | 1264/11066 [04:38<36:19,  4.50it/s]
 11%|█▏        | 1265/11066 [04:38<36:18,  4.50it/s]
                                                    

 11%|█▏        | 1265/11066 [04:38<36:18,  4.50it/s]
 11%|█▏        | 1266/11066 [04:38<36:00,  4.54it/s]
                                                    

 11%|█▏        | 1266/11066 [04:38<36:00,  4.54it/s]
 11%|█▏        | 1267/11066 [04:39<35:28,  4.60it/s]
                                                    

 11%|█▏        | 1267/11066 [04:39<35:28,  4.60it/s]
 11%|█▏        | 1268/11066 [04:39<35:15,  4.63it/s]
                                                    

 11%|█▏        | 1268/11066 [04:39<35:15,  4.63it/s]
 11%|█▏        | 1269/11066 [04:39<35:33,  4.59it/s]
                                                    

 11%|█▏        | 1269/11066 [04:39<35:33,  4.59it/s]
 11%|█▏        | 1270/11066 [04:39<35:23,  4.61it/s]
                                                    

 11%|█▏        | 1270/11066 [04:39<35:23,  4.61it/s]
 11%|█▏        | 1271/11066 [04:39<35:43,  4.57it/s]
                                                    

 11%|█▏        | 1271/11066 [04:39<35:43,  4.57it/s]
 11%|█▏        | 1272/11066 [04:40<35:42,  4.57it/s]
                                                    

 11%|█▏        | 1272/11066 [04:40<35:42,  4.57it/s]
 12%|█▏        | 1273/11066 [04:40<35:22,  4.61it/s]
                                                    

 12%|█▏        | 1273/11066 [04:40<35:22,  4.61it/s]
 12%|█▏        | 1274/11066 [04:40<35:12,  4.64it/s]
                                                    

 12%|█▏        | 1274/11066 [04:40<35:12,  4.64it/s]
 12%|█▏        | 1275/11066 [04:40<34:52,  4.68it/s]
                                                    

 12%|█▏        | 1275/11066 [04:40<34:52,  4.68it/s]
 12%|█▏        | 1276/11066 [04:41<35:18,  4.62it/s]
                                                    

 12%|█▏        | 1276/11066 [04:41<35:18,  4.62it/s]
 12%|█▏        | 1277/11066 [04:41<35:18,  4.62it/s]
                                                    

 12%|█▏        | 1277/11066 [04:41<35:18,  4.62it/s]
 12%|█▏        | 1278/11066 [04:41<35:15,  4.63it/s]
                                                    

 12%|█▏        | 1278/11066 [04:41<35:15,  4.63it/s]
 12%|█▏        | 1279/11066 [04:41<35:36,  4.58it/s]
                                                    

 12%|█▏        | 1279/11066 [04:41<35:36,  4.58it/s]
 12%|█▏        | 1280/11066 [04:41<35:32,  4.59it/s]
                                                    

 12%|█▏        | 1280/11066 [04:41<35:32,  4.59it/s]
 12%|█▏        | 1281/11066 [04:42<36:30,  4.47it/s]
                                                    

 12%|█▏        | 1281/11066 [04:42<36:30,  4.47it/s]
 12%|█▏        | 1282/11066 [04:42<36:26,  4.47it/s]
                                                    

 12%|█▏        | 1282/11066 [04:42<36:26,  4.47it/s]
 12%|█▏        | 1283/11066 [04:42<36:15,  4.50it/s]
                                                    

 12%|█▏        | 1283/11066 [04:42<36:15,  4.50it/s]
 12%|█▏        | 1284/11066 [04:42<35:33,  4.58it/s]
                                                    

 12%|█▏        | 1284/11066 [04:42<35:33,  4.58it/s]
 12%|█▏        | 1285/11066 [04:43<35:12,  4.63it/s]
                                                    

 12%|█▏        | 1285/11066 [04:43<35:12,  4.63it/s]
 12%|█▏        | 1286/11066 [04:43<35:46,  4.56it/s]
                                                    

 12%|█▏        | 1286/11066 [04:43<35:46,  4.56it/s]
 12%|█▏        | 1287/11066 [04:43<35:56,  4.53it/s]
                                                    

 12%|█▏        | 1287/11066 [04:43<35:56,  4.53it/s]
 12%|█▏        | 1288/11066 [04:43<36:06,  4.51it/s]
                                                    

 12%|█▏        | 1288/11066 [04:43<36:06,  4.51it/s]
 12%|█▏        | 1289/11066 [04:43<35:50,  4.55it/s]
                                                    

 12%|█▏        | 1289/11066 [04:43<35:50,  4.55it/s]
 12%|█▏        | 1290/11066 [04:44<35:21,  4.61it/s]
                                                    

 12%|█▏        | 1290/11066 [04:44<35:21,  4.61it/s]
 12%|█▏        | 1291/11066 [04:44<35:06,  4.64it/s]
                                                    

 12%|█▏        | 1291/11066 [04:44<35:06,  4.64it/s]
 12%|█▏        | 1292/11066 [04:44<34:55,  4.66it/s]
                                                    

 12%|█▏        | 1292/11066 [04:44<34:55,  4.66it/s]
 12%|█▏        | 1293/11066 [04:44<35:00,  4.65it/s]
                                                    

 12%|█▏        | 1293/11066 [04:44<35:00,  4.65it/s]
 12%|█▏        | 1294/11066 [04:45<35:28,  4.59it/s]
                                                    

 12%|█▏        | 1294/11066 [04:45<35:28,  4.59it/s]
 12%|█▏        | 1295/11066 [04:45<35:43,  4.56it/s]
                                                    

 12%|█▏        | 1295/11066 [04:45<35:43,  4.56it/s]
 12%|█▏        | 1296/11066 [04:45<35:52,  4.54it/s]
                                                    

 12%|█▏        | 1296/11066 [04:45<35:52,  4.54it/s]
 12%|█▏        | 1297/11066 [04:45<35:29,  4.59it/s]
                                                    

 12%|█▏        | 1297/11066 [04:45<35:29,  4.59it/s]
 12%|█▏        | 1298/11066 [04:45<35:13,  4.62it/s]
                                                    

 12%|█▏        | 1298/11066 [04:45<35:13,  4.62it/s]
 12%|█▏        | 1299/11066 [04:46<35:18,  4.61it/s]
                                                    

 12%|█▏        | 1299/11066 [04:46<35:18,  4.61it/s]
 12%|█▏        | 1300/11066 [04:46<35:30,  4.58it/s]
                                                    

 12%|█▏        | 1300/11066 [04:46<35:30,  4.58it/s]
 12%|█▏        | 1301/11066 [04:46<35:53,  4.53it/s]
                                                    

 12%|█▏        | 1301/11066 [04:46<35:53,  4.53it/s]
 12%|█▏        | 1302/11066 [04:46<35:44,  4.55it/s]
                                                    

 12%|█▏        | 1302/11066 [04:46<35:44,  4.55it/s]
 12%|█▏        | 1303/11066 [04:46<35:13,  4.62it/s]
                                                    

 12%|█▏        | 1303/11066 [04:46<35:13,  4.62it/s]
 12%|█▏        | 1304/11066 [04:47<35:13,  4.62it/s]
                                                    

 12%|█▏        | 1304/11066 [04:47<35:13,  4.62it/s]
 12%|█▏        | 1305/11066 [04:47<34:56,  4.66it/s]
                                                    

 12%|█▏        | 1305/11066 [04:47<34:56,  4.66it/s]
 12%|█▏        | 1306/11066 [04:47<34:51,  4.67it/s]
                                                    

 12%|█▏        | 1306/11066 [04:47<34:51,  4.67it/s]
 12%|█▏        | 1307/11066 [04:47<34:44,  4.68it/s]
                                                    

 12%|█▏        | 1307/11066 [04:47<34:44,  4.68it/s]
 12%|█▏        | 1308/11066 [04:48<34:52,  4.66it/s]
                                                    

 12%|█▏        | 1308/11066 [04:48<34:52,  4.66it/s]
 12%|█▏        | 1309/11066 [04:48<34:46,  4.68it/s]
                                                    

 12%|█▏        | 1309/11066 [04:48<34:46,  4.68it/s]
 12%|█▏        | 1310/11066 [04:48<34:40,  4.69it/s]
                                                    

 12%|█▏        | 1310/11066 [04:48<34:40,  4.69it/s]
 12%|█▏        | 1311/11066 [04:48<35:06,  4.63it/s]
                                                    

 12%|█▏        | 1311/11066 [04:48<35:06,  4.63it/s]
 12%|█▏        | 1312/11066 [04:48<34:53,  4.66it/s]
                                                    

 12%|█▏        | 1312/11066 [04:48<34:53,  4.66it/s]
 12%|█▏        | 1313/11066 [04:49<34:49,  4.67it/s]
                                                    

 12%|█▏        | 1313/11066 [04:49<34:49,  4.67it/s]
 12%|█▏        | 1314/11066 [04:49<34:35,  4.70it/s]
                                                    

 12%|█▏        | 1314/11066 [04:49<34:35,  4.70it/s]
 12%|█▏        | 1315/11066 [04:49<34:49,  4.67it/s]
                                                    

 12%|█▏        | 1315/11066 [04:49<34:49,  4.67it/s]
 12%|█▏        | 1316/11066 [04:49<34:48,  4.67it/s]
                                                    

 12%|█▏        | 1316/11066 [04:49<34:48,  4.67it/s]
 12%|█▏        | 1317/11066 [04:49<34:45,  4.67it/s]
                                                    

 12%|█▏        | 1317/11066 [04:49<34:45,  4.67it/s]
 12%|█▏        | 1318/11066 [04:50<34:42,  4.68it/s]
                                                    

 12%|█▏        | 1318/11066 [04:50<34:42,  4.68it/s]
 12%|█▏        | 1319/11066 [04:50<34:52,  4.66it/s]
                                                    

 12%|█▏        | 1319/11066 [04:50<34:52,  4.66it/s]
 12%|█▏        | 1320/11066 [04:50<34:35,  4.69it/s]
                                                    

 12%|█▏        | 1320/11066 [04:50<34:35,  4.69it/s]
 12%|█▏        | 1321/11066 [04:50<34:34,  4.70it/s]
                                                    

 12%|█▏        | 1321/11066 [04:50<34:34,  4.70it/s]
 12%|█▏        | 1322/11066 [04:51<34:32,  4.70it/s]
                                                    

 12%|█▏        | 1322/11066 [04:51<34:32,  4.70it/s]
 12%|█▏        | 1323/11066 [04:51<34:57,  4.64it/s]
                                                    

 12%|█▏        | 1323/11066 [04:51<34:57,  4.64it/s]
 12%|█▏        | 1324/11066 [04:51<34:59,  4.64it/s]
                                                    

 12%|█▏        | 1324/11066 [04:51<34:59,  4.64it/s]
 12%|█▏        | 1325/11066 [04:51<35:00,  4.64it/s]
                                                    

 12%|█▏        | 1325/11066 [04:51<35:00,  4.64it/s]
 12%|█▏        | 1326/11066 [04:51<35:17,  4.60it/s]
                                                    

 12%|█▏        | 1326/11066 [04:51<35:17,  4.60it/s]
 12%|█▏        | 1327/11066 [04:52<35:35,  4.56it/s]
                                                    

 12%|█▏        | 1327/11066 [04:52<35:35,  4.56it/s]
 12%|█▏        | 1328/11066 [04:52<35:46,  4.54it/s]
                                                    

 12%|█▏        | 1328/11066 [04:52<35:46,  4.54it/s]
 12%|█▏        | 1329/11066 [04:52<35:22,  4.59it/s]
                                                    

 12%|█▏        | 1329/11066 [04:52<35:22,  4.59it/s]
 12%|█▏        | 1330/11066 [04:52<34:56,  4.64it/s]
                                                    

 12%|█▏        | 1330/11066 [04:52<34:56,  4.64it/s]
 12%|█▏        | 1331/11066 [04:52<34:52,  4.65it/s]
                                                    

 12%|█▏        | 1331/11066 [04:52<34:52,  4.65it/s]
 12%|█▏        | 1332/11066 [04:53<34:44,  4.67it/s]
                                                    

 12%|█▏        | 1332/11066 [04:53<34:44,  4.67it/s]
 12%|█▏        | 1333/11066 [04:53<34:39,  4.68it/s]
                                                    

 12%|█▏        | 1333/11066 [04:53<34:39,  4.68it/s]
 12%|█▏        | 1334/11066 [04:53<35:01,  4.63it/s]
                                                    

 12%|█▏        | 1334/11066 [04:53<35:01,  4.63it/s]
 12%|█▏        | 1335/11066 [04:53<34:49,  4.66it/s]
                                                    

 12%|█▏        | 1335/11066 [04:53<34:49,  4.66it/s]
 12%|█▏        | 1336/11066 [04:54<34:53,  4.65it/s]
                                                    

 12%|█▏        | 1336/11066 [04:54<34:53,  4.65it/s]
 12%|█▏        | 1337/11066 [04:54<34:37,  4.68it/s]
                                                    

 12%|█▏        | 1337/11066 [04:54<34:37,  4.68it/s]
 12%|█▏        | 1338/11066 [04:54<34:24,  4.71it/s]
                                                    

 12%|█▏        | 1338/11066 [04:54<34:24,  4.71it/s]
 12%|█▏        | 1339/11066 [04:54<34:24,  4.71it/s]
                                                    

 12%|█▏        | 1339/11066 [04:54<34:24,  4.71it/s]
 12%|█▏        | 1340/11066 [04:54<34:23,  4.71it/s]
                                                    

 12%|█▏        | 1340/11066 [04:54<34:23,  4.71it/s]
 12%|█▏        | 1341/11066 [04:55<34:34,  4.69it/s]
                                                    

 12%|█▏        | 1341/11066 [04:55<34:34,  4.69it/s]
 12%|█▏        | 1342/11066 [04:55<34:54,  4.64it/s]
                                                    

 12%|█▏        | 1342/11066 [04:55<34:54,  4.64it/s]
 12%|█▏        | 1343/11066 [04:55<34:47,  4.66it/s]
                                                    

 12%|█▏        | 1343/11066 [04:55<34:47,  4.66it/s]
 12%|█▏        | 1344/11066 [04:55<34:30,  4.70it/s]
                                                    

 12%|█▏        | 1344/11066 [04:55<34:30,  4.70it/s]
 12%|█▏        | 1345/11066 [04:55<34:30,  4.69it/s]
                                                    

 12%|█▏        | 1345/11066 [04:55<34:30,  4.69it/s]
 12%|█▏        | 1346/11066 [04:56<34:38,  4.68it/s]
                                                    

 12%|█▏        | 1346/11066 [04:56<34:38,  4.68it/s]
 12%|█▏        | 1347/11066 [04:56<34:28,  4.70it/s]
                                                    

 12%|█▏        | 1347/11066 [04:56<34:28,  4.70it/s]
 12%|█▏        | 1348/11066 [04:56<34:14,  4.73it/s]
                                                    

 12%|█▏        | 1348/11066 [04:56<34:14,  4.73it/s]
 12%|█▏        | 1349/11066 [04:56<34:19,  4.72it/s]
                                                    

 12%|█▏        | 1349/11066 [04:56<34:19,  4.72it/s]
 12%|█▏        | 1350/11066 [04:57<34:32,  4.69it/s]
                                                    

 12%|█▏        | 1350/11066 [04:57<34:32,  4.69it/s]
 12%|█▏        | 1351/11066 [04:57<34:34,  4.68it/s]
                                                    

 12%|█▏        | 1351/11066 [04:57<34:34,  4.68it/s]
 12%|█▏        | 1352/11066 [04:57<34:29,  4.69it/s]
                                                    
{'loss': 1.371, 'learning_rate': 2.6638351707934215e-05, 'epoch': 0.22}
{'loss': 0.8691, 'learning_rate': 2.6635640701247067e-05, 'epoch': 0.22}
{'loss': 1.2595, 'learning_rate': 2.6632929694559915e-05, 'epoch': 0.22}
{'loss': 1.4102, 'learning_rate': 2.6630218687872763e-05, 'epoch': 0.22}
{'loss': 0.8254, 'learning_rate': 2.6627507681185612e-05, 'epoch': 0.22}
{'loss': 1.061, 'learning_rate': 2.6624796674498464e-05, 'epoch': 0.23}
{'loss': 1.4701, 'learning_rate': 2.6622085667811316e-05, 'epoch': 0.23}
{'loss': 1.245, 'learning_rate': 2.6619374661124164e-05, 'epoch': 0.23}
{'loss': 2.1855, 'learning_rate': 2.6616663654437016e-05, 'epoch': 0.23}
{'loss': 0.9895, 'learning_rate': 2.6613952647749868e-05, 'epoch': 0.23}
{'loss': 1.1953, 'learning_rate': 2.6611241641062716e-05, 'epoch': 0.23}
{'loss': 1.4532, 'learning_rate': 2.6608530634375564e-05, 'epoch': 0.23}
{'loss': 1.4985, 'learning_rate': 2.6605819627688416e-05, 'epoch': 0.23}
{'loss': 2.0284, 'learning_rate': 2.6603108621001265e-05, 'epoch': 0.23}
{'loss': 1.5249, 'learning_rate': 2.6600397614314117e-05, 'epoch': 0.23}
{'loss': 1.1197, 'learning_rate': 2.6597686607626965e-05, 'epoch': 0.23}
{'loss': 0.9072, 'learning_rate': 2.6594975600939817e-05, 'epoch': 0.23}
{'loss': 0.8468, 'learning_rate': 2.659226459425267e-05, 'epoch': 0.23}
{'loss': 1.1874, 'learning_rate': 2.6589553587565517e-05, 'epoch': 0.23}
{'loss': 1.0292, 'learning_rate': 2.6586842580878366e-05, 'epoch': 0.23}
{'loss': 1.2354, 'learning_rate': 2.6584131574191217e-05, 'epoch': 0.23}
{'loss': 1.3056, 'learning_rate': 2.6581420567504066e-05, 'epoch': 0.23}
{'loss': 2.0188, 'learning_rate': 2.6578709560816918e-05, 'epoch': 0.23}
{'loss': 0.7933, 'learning_rate': 2.657599855412977e-05, 'epoch': 0.23}
{'loss': 1.28, 'learning_rate': 2.6573287547442618e-05, 'epoch': 0.23}
{'loss': 1.1875, 'learning_rate': 2.657057654075547e-05, 'epoch': 0.23}
{'loss': 1.0247, 'learning_rate': 2.6567865534068318e-05, 'epoch': 0.23}
{'loss': 1.1614, 'learning_rate': 2.6565154527381167e-05, 'epoch': 0.23}
{'loss': 0.9148, 'learning_rate': 2.656244352069402e-05, 'epoch': 0.23}
{'loss': 1.2753, 'learning_rate': 2.6559732514006867e-05, 'epoch': 0.23}
{'loss': 0.5297, 'learning_rate': 2.655702150731972e-05, 'epoch': 0.23}
{'loss': 1.4993, 'learning_rate': 2.655431050063257e-05, 'epoch': 0.23}
{'loss': 2.1229, 'learning_rate': 2.655159949394542e-05, 'epoch': 0.23}
{'loss': 1.0702, 'learning_rate': 2.654888848725827e-05, 'epoch': 0.23}
{'loss': 1.2908, 'learning_rate': 2.6546177480571123e-05, 'epoch': 0.23}
{'loss': 1.9813, 'learning_rate': 2.6543466473883968e-05, 'epoch': 0.23}
{'loss': 1.4393, 'learning_rate': 2.654075546719682e-05, 'epoch': 0.23}
{'loss': 1.1724, 'learning_rate': 2.6538044460509668e-05, 'epoch': 0.23}
{'loss': 1.5605, 'learning_rate': 2.653533345382252e-05, 'epoch': 0.23}
{'loss': 1.5062, 'learning_rate': 2.653262244713537e-05, 'epoch': 0.23}
{'loss': 1.3566, 'learning_rate': 2.652991144044822e-05, 'epoch': 0.23}
{'loss': 1.2801, 'learning_rate': 2.6527200433761072e-05, 'epoch': 0.23}
{'loss': 0.8925, 'learning_rate': 2.6524489427073924e-05, 'epoch': 0.23}
{'loss': 0.8406, 'learning_rate': 2.652177842038677e-05, 'epoch': 0.23}
{'loss': 1.0333, 'learning_rate': 2.651906741369962e-05, 'epoch': 0.23}
{'loss': 1.152, 'learning_rate': 2.6516356407012472e-05, 'epoch': 0.23}
{'loss': 1.0095, 'learning_rate': 2.651364540032532e-05, 'epoch': 0.23}
{'loss': 1.8366, 'learning_rate': 2.6510934393638173e-05, 'epoch': 0.23}
{'loss': 2.0164, 'learning_rate': 2.650822338695102e-05, 'epoch': 0.23}
{'loss': 1.1124, 'learning_rate': 2.6505512380263873e-05, 'epoch': 0.23}
{'loss': 0.7654, 'learning_rate': 2.650280137357672e-05, 'epoch': 0.23}
{'loss': 0.7203, 'learning_rate': 2.650009036688957e-05, 'epoch': 0.23}
{'loss': 2.5863, 'learning_rate': 2.649737936020242e-05, 'epoch': 0.23}
{'loss': 1.2758, 'learning_rate': 2.6494668353515274e-05, 'epoch': 0.23}
{'loss': 1.7567, 'learning_rate': 2.6491957346828122e-05, 'epoch': 0.23}
{'loss': 1.4353, 'learning_rate': 2.6489246340140974e-05, 'epoch': 0.23}
{'loss': 0.8867, 'learning_rate': 2.6486535333453826e-05, 'epoch': 0.23}
{'loss': 1.6953, 'learning_rate': 2.6483824326766674e-05, 'epoch': 0.23}
{'loss': 0.8214, 'learning_rate': 2.6481113320079522e-05, 'epoch': 0.23}
{'loss': 1.3896, 'learning_rate': 2.647840231339237e-05, 'epoch': 0.23}
{'loss': 1.4595, 'learning_rate': 2.6475691306705223e-05, 'epoch': 0.23}
{'loss': 1.9674, 'learning_rate': 2.6472980300018075e-05, 'epoch': 0.24}
{'loss': 1.0965, 'learning_rate': 2.6470269293330923e-05, 'epoch': 0.24}
{'loss': 1.2373, 'learning_rate': 2.6467558286643775e-05, 'epoch': 0.24}
{'loss': 1.1647, 'learning_rate': 2.6464847279956627e-05, 'epoch': 0.24}
{'loss': 2.2518, 'learning_rate': 2.6462136273269475e-05, 'epoch': 0.24}
{'loss': 0.8376, 'learning_rate': 2.6459425266582324e-05, 'epoch': 0.24}
{'loss': 1.6597, 'learning_rate': 2.6456714259895175e-05, 'epoch': 0.24}
{'loss': 1.349, 'learning_rate': 2.6454003253208024e-05, 'epoch': 0.24}
{'loss': 1.9598, 'learning_rate': 2.6451292246520876e-05, 'epoch': 0.24}
{'loss': 1.052, 'learning_rate': 2.6448581239833724e-05, 'epoch': 0.24}
{'loss': 1.3689, 'learning_rate': 2.6445870233146576e-05, 'epoch': 0.24}
{'loss': 1.8317, 'learning_rate': 2.6443159226459428e-05, 'epoch': 0.24}
{'loss': 1.5849, 'learning_rate': 2.6440448219772276e-05, 'epoch': 0.24}
{'loss': 1.1807, 'learning_rate': 2.6437737213085125e-05, 'epoch': 0.24}
{'loss': 1.09, 'learning_rate': 2.6435026206397976e-05, 'epoch': 0.24}
{'loss': 1.5653, 'learning_rate': 2.6432315199710825e-05, 'epoch': 0.24}
{'loss': 1.5569, 'learning_rate': 2.6429604193023677e-05, 'epoch': 0.24}
{'loss': 0.8231, 'learning_rate': 2.642689318633653e-05, 'epoch': 0.24}
{'loss': 1.1209, 'learning_rate': 2.6424182179649377e-05, 'epoch': 0.24}
{'loss': 1.4046, 'learning_rate': 2.642147117296223e-05, 'epoch': 0.24}
{'loss': 1.4829, 'learning_rate': 2.6418760166275077e-05, 'epoch': 0.24}
{'loss': 1.1787, 'learning_rate': 2.6416049159587926e-05, 'epoch': 0.24}
{'loss': 1.0707, 'learning_rate': 2.6413338152900778e-05, 'epoch': 0.24}
{'loss': 1.1956, 'learning_rate': 2.6410627146213626e-05, 'epoch': 0.24}
{'loss': 0.9727, 'learning_rate': 2.6407916139526478e-05, 'epoch': 0.24}
{'loss': 1.1307, 'learning_rate': 2.640520513283933e-05, 'epoch': 0.24}
{'loss': 1.4066, 'learning_rate': 2.6402494126152178e-05, 'epoch': 0.24}
{'loss': 1.4925, 'learning_rate': 2.639978311946503e-05, 'epoch': 0.24}
{'loss': 1.9837, 'learning_rate': 2.6397072112777882e-05, 'epoch': 0.24}
{'loss': 1.4772, 'learning_rate': 2.6394361106090727e-05, 'epoch': 0.24}
{'loss': 1.2627, 'learning_rate': 2.639165009940358e-05, 'epoch': 0.24}
{'loss': 0.8261, 'learning_rate': 2.6388939092716427e-05, 'epoch': 0.24}
{'loss': 1.6376, 'learning_rate': 2.638622808602928e-05, 'epoch': 0.24}
{'loss': 0.6412, 'learning_rate': 2.638351707934213e-05, 'epoch': 0.24}
{'loss': 1.3523, 'learning_rate': 2.638080607265498e-05, 'epoch': 0.24}
{'loss': 1.0674, 'learning_rate': 2.637809506596783e-05, 'epoch': 0.24}
{'loss': 1.9176, 'learning_rate': 2.6375384059280683e-05, 'epoch': 0.24}
{'loss': 2.0115, 'learning_rate': 2.6372673052593528e-05, 'epoch': 0.24}
{'loss': 1.4501, 'learning_rate': 2.636996204590638e-05, 'epoch': 0.24}
{'loss': 1.5736, 'learning_rate': 2.636725103921923e-05, 'epoch': 0.24}
{'loss': 1.3871, 'learning_rate': 2.636454003253208e-05, 'epoch': 0.24}
{'loss': 1.9154, 'learning_rate': 2.6361829025844932e-05, 'epoch': 0.24}
{'loss': 0.7863, 'learning_rate': 2.635911801915778e-05, 'epoch': 0.24}
{'loss': 1.9283, 'learning_rate': 2.6356407012470632e-05, 'epoch': 0.24}
{'loss': 1.3438, 'learning_rate': 2.6353696005783484e-05, 'epoch': 0.24}
{'loss': 0.5046, 'learning_rate': 2.635098499909633e-05, 'epoch': 0.24}
{'loss': 0.7495, 'learning_rate': 2.634827399240918e-05, 'epoch': 0.24}
{'loss': 1.5145, 'learning_rate': 2.6345562985722033e-05, 'epoch': 0.24}
{'loss': 0.4123, 'learning_rate': 2.634285197903488e-05, 'epoch': 0.24}
{'loss': 0.8501, 'learning_rate': 2.6340140972347733e-05, 'epoch': 0.24}
{'loss': 0.6387, 'learning_rate': 2.6337429965660585e-05, 'epoch': 0.24}

 12%|█▏        | 1352/11066 [04:57<34:29,  4.69it/s]
 12%|█▏        | 1353/11066 [04:57<34:42,  4.66it/s]
                                                    

 12%|█▏        | 1353/11066 [04:57<34:42,  4.66it/s]
 12%|█▏        | 1354/11066 [04:57<34:26,  4.70it/s]
                                                    

 12%|█▏        | 1354/11066 [04:57<34:26,  4.70it/s]
 12%|█▏        | 1355/11066 [04:58<34:54,  4.64it/s]
                                                    

 12%|█▏        | 1355/11066 [04:58<34:54,  4.64it/s]
 12%|█▏        | 1356/11066 [04:58<34:44,  4.66it/s]
                                                    

 12%|█▏        | 1356/11066 [04:58<34:44,  4.66it/s]
 12%|█▏        | 1357/11066 [04:58<35:09,  4.60it/s]
                                                    

 12%|█▏        | 1357/11066 [04:58<35:09,  4.60it/s]
 12%|█▏        | 1358/11066 [04:58<35:07,  4.61it/s]
                                                    

 12%|█▏        | 1358/11066 [04:58<35:07,  4.61it/s]
 12%|█▏        | 1359/11066 [04:58<35:31,  4.55it/s]
                                                    

 12%|█▏        | 1359/11066 [04:58<35:31,  4.55it/s]
 12%|█▏        | 1360/11066 [04:59<35:42,  4.53it/s]
                                                    

 12%|█▏        | 1360/11066 [04:59<35:42,  4.53it/s]
 12%|█▏        | 1361/11066 [04:59<35:15,  4.59it/s]
                                                    

 12%|█▏        | 1361/11066 [04:59<35:15,  4.59it/s]
 12%|█▏        | 1362/11066 [04:59<35:10,  4.60it/s]
                                                    

 12%|█▏        | 1362/11066 [04:59<35:10,  4.60it/s]
 12%|█▏        | 1363/11066 [04:59<35:10,  4.60it/s]
                                                    

 12%|█▏        | 1363/11066 [04:59<35:10,  4.60it/s]
 12%|█▏        | 1364/11066 [05:00<34:54,  4.63it/s]
                                                    

 12%|█▏        | 1364/11066 [05:00<34:54,  4.63it/s]
 12%|█▏        | 1365/11066 [05:00<34:42,  4.66it/s]
                                                    

 12%|█▏        | 1365/11066 [05:00<34:42,  4.66it/s]
 12%|█▏        | 1366/11066 [05:00<34:32,  4.68it/s]
                                                    

 12%|█▏        | 1366/11066 [05:00<34:32,  4.68it/s]
 12%|█▏        | 1367/11066 [05:00<34:28,  4.69it/s]
                                                    

 12%|█▏        | 1367/11066 [05:00<34:28,  4.69it/s]
 12%|█▏        | 1368/11066 [05:00<34:23,  4.70it/s]
                                                    

 12%|█▏        | 1368/11066 [05:00<34:23,  4.70it/s]
 12%|█▏        | 1369/11066 [05:01<34:20,  4.71it/s]
                                                    

 12%|█▏        | 1369/11066 [05:01<34:20,  4.71it/s]
 12%|█▏        | 1370/11066 [05:01<34:19,  4.71it/s]
                                                    

 12%|█▏        | 1370/11066 [05:01<34:19,  4.71it/s]
 12%|█▏        | 1371/11066 [05:01<34:58,  4.62it/s]
                                                    

 12%|█▏        | 1371/11066 [05:01<34:58,  4.62it/s]
 12%|█▏        | 1372/11066 [05:01<35:27,  4.56it/s]
                                                    

 12%|█▏        | 1372/11066 [05:01<35:27,  4.56it/s]
 12%|█▏        | 1373/11066 [05:02<36:08,  4.47it/s]
                                                    

 12%|█▏        | 1373/11066 [05:02<36:08,  4.47it/s]
 12%|█▏        | 1374/11066 [05:02<36:05,  4.48it/s]
                                                    

 12%|█▏        | 1374/11066 [05:02<36:05,  4.48it/s]
 12%|█▏        | 1375/11066 [05:02<36:01,  4.48it/s]
                                                    

 12%|█▏        | 1375/11066 [05:02<36:01,  4.48it/s]
 12%|█▏        | 1376/11066 [05:02<35:57,  4.49it/s]
                                                    

 12%|█▏        | 1376/11066 [05:02<35:57,  4.49it/s]
 12%|█▏        | 1377/11066 [05:02<35:55,  4.49it/s]
                                                    

 12%|█▏        | 1377/11066 [05:02<35:55,  4.49it/s]
 12%|█▏        | 1378/11066 [05:03<35:36,  4.53it/s]
                                                    

 12%|█▏        | 1378/11066 [05:03<35:36,  4.53it/s]
 12%|█▏        | 1379/11066 [05:03<35:17,  4.58it/s]
                                                    

 12%|█▏        | 1379/11066 [05:03<35:17,  4.58it/s]
 12%|█▏        | 1380/11066 [05:03<35:12,  4.58it/s]
                                                    

 12%|█▏        | 1380/11066 [05:03<35:12,  4.58it/s]
 12%|█▏        | 1381/11066 [05:03<35:22,  4.56it/s]
                                                    

 12%|█▏        | 1381/11066 [05:03<35:22,  4.56it/s]
 12%|█▏        | 1382/11066 [05:03<35:01,  4.61it/s]
                                                    

 12%|█▏        | 1382/11066 [05:03<35:01,  4.61it/s]
 12%|█▏        | 1383/11066 [05:04<34:45,  4.64it/s]
                                                    

 12%|█▏        | 1383/11066 [05:04<34:45,  4.64it/s]
 13%|█▎        | 1384/11066 [05:04<35:05,  4.60it/s]
                                                    

 13%|█▎        | 1384/11066 [05:04<35:05,  4.60it/s]
 13%|█▎        | 1385/11066 [05:04<35:04,  4.60it/s]
                                                    

 13%|█▎        | 1385/11066 [05:04<35:04,  4.60it/s]
 13%|█▎        | 1386/11066 [05:04<35:22,  4.56it/s]
                                                    

 13%|█▎        | 1386/11066 [05:04<35:22,  4.56it/s]
 13%|█▎        | 1387/11066 [05:05<35:34,  4.53it/s]
                                                    

 13%|█▎        | 1387/11066 [05:05<35:34,  4.53it/s]
 13%|█▎        | 1388/11066 [05:05<35:23,  4.56it/s]
                                                    

 13%|█▎        | 1388/11066 [05:05<35:23,  4.56it/s]
 13%|█▎        | 1389/11066 [05:05<35:10,  4.59it/s]
                                                    

 13%|█▎        | 1389/11066 [05:05<35:10,  4.59it/s]
 13%|█▎        | 1390/11066 [05:05<35:24,  4.55it/s]
                                                    

 13%|█▎        | 1390/11066 [05:05<35:24,  4.55it/s]
 13%|█▎        | 1391/11066 [05:05<35:18,  4.57it/s]
                                                    

 13%|█▎        | 1391/11066 [05:05<35:18,  4.57it/s]
 13%|█▎        | 1392/11066 [05:06<35:37,  4.53it/s]
                                                    

 13%|█▎        | 1392/11066 [05:06<35:37,  4.53it/s]
 13%|█▎        | 1393/11066 [05:06<35:14,  4.57it/s]
                                                    

 13%|█▎        | 1393/11066 [05:06<35:14,  4.57it/s]
 13%|█▎        | 1394/11066 [05:06<35:26,  4.55it/s]
                                                    

 13%|█▎        | 1394/11066 [05:06<35:26,  4.55it/s]
 13%|█▎        | 1395/11066 [05:06<35:04,  4.60it/s]
                                                    

 13%|█▎        | 1395/11066 [05:06<35:04,  4.60it/s]
 13%|█▎        | 1396/11066 [05:07<35:02,  4.60it/s]
                                                    

 13%|█▎        | 1396/11066 [05:07<35:02,  4.60it/s]
 13%|█▎        | 1397/11066 [05:07<35:09,  4.58it/s]
                                                    

 13%|█▎        | 1397/11066 [05:07<35:09,  4.58it/s]
 13%|█▎        | 1398/11066 [05:07<35:02,  4.60it/s]
                                                    

 13%|█▎        | 1398/11066 [05:07<35:02,  4.60it/s]
 13%|█▎        | 1399/11066 [05:07<34:59,  4.60it/s]
                                                    

 13%|█▎        | 1399/11066 [05:07<34:59,  4.60it/s]
 13%|█▎        | 1400/11066 [05:07<35:00,  4.60it/s]
                                                    

 13%|█▎        | 1400/11066 [05:07<35:00,  4.60it/s]
 13%|█▎        | 1401/11066 [05:08<34:53,  4.62it/s]
                                                    

 13%|█▎        | 1401/11066 [05:08<34:53,  4.62it/s]
 13%|█▎        | 1402/11066 [05:08<34:44,  4.64it/s]
                                                    

 13%|█▎        | 1402/11066 [05:08<34:44,  4.64it/s]
 13%|█▎        | 1403/11066 [05:08<34:49,  4.62it/s]
                                                    

 13%|█▎        | 1403/11066 [05:08<34:49,  4.62it/s]
 13%|█▎        | 1404/11066 [05:08<34:36,  4.65it/s]
                                                    

 13%|█▎        | 1404/11066 [05:08<34:36,  4.65it/s]
 13%|█▎        | 1405/11066 [05:09<34:39,  4.65it/s]
                                                    

 13%|█▎        | 1405/11066 [05:09<34:39,  4.65it/s]
 13%|█▎        | 1406/11066 [05:09<34:36,  4.65it/s]
                                                    

 13%|█▎        | 1406/11066 [05:09<34:36,  4.65it/s]
 13%|█▎        | 1407/11066 [05:09<34:29,  4.67it/s]
                                                    

 13%|█▎        | 1407/11066 [05:09<34:29,  4.67it/s]
 13%|█▎        | 1408/11066 [05:09<34:58,  4.60it/s]
                                                    

 13%|█▎        | 1408/11066 [05:09<34:58,  4.60it/s]
 13%|█▎        | 1409/11066 [05:09<35:13,  4.57it/s]
                                                    

 13%|█▎        | 1409/11066 [05:09<35:13,  4.57it/s]
 13%|█▎        | 1410/11066 [05:10<35:09,  4.58it/s]
                                                    

 13%|█▎        | 1410/11066 [05:10<35:09,  4.58it/s]
 13%|█▎        | 1411/11066 [05:10<35:29,  4.53it/s]
                                                    

 13%|█▎        | 1411/11066 [05:10<35:29,  4.53it/s]
 13%|█▎        | 1412/11066 [05:10<35:38,  4.51it/s]
                                                    

 13%|█▎        | 1412/11066 [05:10<35:38,  4.51it/s]
 13%|█▎        | 1413/11066 [05:10<35:41,  4.51it/s]
                                                    

 13%|█▎        | 1413/11066 [05:10<35:41,  4.51it/s]
 13%|█▎        | 1414/11066 [05:10<35:45,  4.50it/s]
                                                    

 13%|█▎        | 1414/11066 [05:10<35:45,  4.50it/s]
 13%|█▎        | 1415/11066 [05:11<35:47,  4.49it/s]
                                                    

 13%|█▎        | 1415/11066 [05:11<35:47,  4.49it/s]
 13%|█▎        | 1416/11066 [05:11<35:19,  4.55it/s]
                                                    

 13%|█▎        | 1416/11066 [05:11<35:19,  4.55it/s]
 13%|█▎        | 1417/11066 [05:11<35:28,  4.53it/s]
                                                    

 13%|█▎        | 1417/11066 [05:11<35:28,  4.53it/s]
 13%|█▎        | 1418/11066 [05:11<35:05,  4.58it/s]
                                                    

 13%|█▎        | 1418/11066 [05:11<35:05,  4.58it/s]
 13%|█▎        | 1419/11066 [05:12<34:46,  4.62it/s]
                                                    

 13%|█▎        | 1419/11066 [05:12<34:46,  4.62it/s]
 13%|█▎        | 1420/11066 [05:12<35:04,  4.58it/s]
                                                    

 13%|█▎        | 1420/11066 [05:12<35:04,  4.58it/s]
 13%|█▎        | 1421/11066 [05:12<34:47,  4.62it/s]
                                                    

 13%|█▎        | 1421/11066 [05:12<34:47,  4.62it/s]
 13%|█▎        | 1422/11066 [05:12<34:47,  4.62it/s]
                                                    

 13%|█▎        | 1422/11066 [05:12<34:47,  4.62it/s]
 13%|█▎        | 1423/11066 [05:12<34:30,  4.66it/s]
                                                    

 13%|█▎        | 1423/11066 [05:12<34:30,  4.66it/s]
 13%|█▎        | 1424/11066 [05:13<34:14,  4.69it/s]
                                                    

 13%|█▎        | 1424/11066 [05:13<34:14,  4.69it/s]
 13%|█▎        | 1425/11066 [05:13<34:28,  4.66it/s]
                                                    

 13%|█▎        | 1425/11066 [05:13<34:28,  4.66it/s]
 13%|█▎        | 1426/11066 [05:13<34:55,  4.60it/s]
                                                    

 13%|█▎        | 1426/11066 [05:13<34:55,  4.60it/s]
 13%|█▎        | 1427/11066 [05:13<35:13,  4.56it/s]
                                                    

 13%|█▎        | 1427/11066 [05:13<35:13,  4.56it/s]
 13%|█▎        | 1428/11066 [05:14<34:58,  4.59it/s]
                                                    

 13%|█▎        | 1428/11066 [05:14<34:58,  4.59it/s]
 13%|█▎        | 1429/11066 [05:14<35:11,  4.56it/s]
                                                    

 13%|█▎        | 1429/11066 [05:14<35:11,  4.56it/s]
 13%|█▎        | 1430/11066 [05:14<35:19,  4.55it/s]
                                                    

 13%|█▎        | 1430/11066 [05:14<35:19,  4.55it/s]
 13%|█▎        | 1431/11066 [05:14<35:27,  4.53it/s]
                                                    

 13%|█▎        | 1431/11066 [05:14<35:27,  4.53it/s]
 13%|█▎        | 1432/11066 [05:14<35:33,  4.51it/s]
                                                    

 13%|█▎        | 1432/11066 [05:14<35:33,  4.51it/s]
 13%|█▎        | 1433/11066 [05:15<35:38,  4.50it/s]
                                                    

 13%|█▎        | 1433/11066 [05:15<35:38,  4.50it/s]
 13%|█▎        | 1434/11066 [05:15<35:40,  4.50it/s]
                                                    

 13%|█▎        | 1434/11066 [05:15<35:40,  4.50it/s]
 13%|█▎        | 1435/11066 [05:15<35:40,  4.50it/s]
                                                    

 13%|█▎        | 1435/11066 [05:15<35:40,  4.50it/s]
 13%|█▎        | 1436/11066 [05:15<35:41,  4.50it/s]
                                                    

 13%|█▎        | 1436/11066 [05:15<35:41,  4.50it/s]
 13%|█▎        | 1437/11066 [05:16<35:41,  4.50it/s]
                                                    

 13%|█▎        | 1437/11066 [05:16<35:41,  4.50it/s]
 13%|█▎        | 1438/11066 [05:16<35:40,  4.50it/s]
                                                    

 13%|█▎        | 1438/11066 [05:16<35:40,  4.50it/s]
 13%|█▎        | 1439/11066 [05:16<35:40,  4.50it/s]
                                                    

 13%|█▎        | 1439/11066 [05:16<35:40,  4.50it/s]
 13%|█▎        | 1440/11066 [05:16<35:40,  4.50it/s]
                                                    

 13%|█▎        | 1440/11066 [05:16<35:40,  4.50it/s]
 13%|█▎        | 1441/11066 [05:16<35:39,  4.50it/s]
                                                    

 13%|█▎        | 1441/11066 [05:16<35:39,  4.50it/s]
 13%|█▎        | 1442/11066 [05:17<35:04,  4.57it/s]
                                                    

 13%|█▎        | 1442/11066 [05:17<35:04,  4.57it/s]
 13%|█▎        | 1443/11066 [05:17<35:20,  4.54it/s]
                                                    

 13%|█▎        | 1443/11066 [05:17<35:20,  4.54it/s]
 13%|█▎        | 1444/11066 [05:17<35:28,  4.52it/s]
                                                    

 13%|█▎        | 1444/11066 [05:17<35:28,  4.52it/s]
 13%|█▎        | 1445/11066 [05:17<35:31,  4.51it/s]
                                                    

 13%|█▎        | 1445/11066 [05:17<35:31,  4.51it/s]
 13%|█▎        | 1446/11066 [05:18<36:06,  4.44it/s]
                                                    

 13%|█▎        | 1446/11066 [05:18<36:06,  4.44it/s]
 13%|█▎        | 1447/11066 [05:18<36:18,  4.42it/s]
                                                    

 13%|█▎        | 1447/11066 [05:18<36:18,  4.42it/s]
 13%|█▎        | 1448/11066 [05:18<36:13,  4.43it/s]
                                                    

 13%|█▎        | 1448/11066 [05:18<36:13,  4.43it/s]
 13%|█▎        | 1449/11066 [05:18<36:04,  4.44it/s]
                                                    

 13%|█▎        | 1449/11066 [05:18<36:04,  4.44it/s]
 13%|█▎        | 1450/11066 [05:18<36:14,  4.42it/s]
                                                    

 13%|█▎        | 1450/11066 [05:18<36:14,  4.42it/s]
 13%|█▎        | 1451/11066 [05:19<36:41,  4.37it/s]
                                                    

 13%|█▎        | 1451/11066 [05:19<36:41,  4.37it/s]
 13%|█▎        | 1452/11066 [05:19<36:53,  4.34it/s]
                                                    

 13%|█▎        | 1452/11066 [05:19<36:53,  4.34it/s]
 13%|█▎        | 1453/11066 [05:19<36:30,  4.39it/s]
                                                    

 13%|█▎        | 1453/11066 [05:19<36:30,  4.39it/s]
 13%|█▎        | 1454/11066 [05:19<36:14,  4.42it/s]
                                                    

 13%|█▎        | 1454/11066 [05:19<36:14,  4.42it/s]
 13%|█▎        | 1455/11066 [05:20<36:02,  4.45it/s]
                                                    

 13%|█▎        | 1455/11066 [05:20<36:02,  4.45it/s]
 13%|█▎        | 1456/11066 [05:20<35:56,  4.46it/s]
                                                    

 13%|█▎        | 1456/11066 [05:20<35:56,  4.46it/s]
 13%|█▎        | 1457/11066 [05:20<35:49,  4.47it/s]
                                                    

 13%|█▎        | 1457/11066 [05:20<35:49,  4.47it/s]
 13%|█▎        | 1458/11066 [05:20<35:43,  4.48it/s]
                                                    

 13%|█▎        | 1458/11066 [05:20<35:43,  4.48it/s]
 13%|█▎        | 1459/11066 [05:20<35:38,  4.49it/s]
                                                    

 13%|█▎        | 1459/11066 [05:20<35:38,  4.49it/s]
 13%|█▎        | 1460/11066 [05:21<35:35,  4.50it/s]
                                                    

 13%|█▎        | 1460/11066 [05:21<35:35,  4.50it/s]
 13%|█▎        | 1461/11066 [05:21<35:37,  4.49it/s]
                                                    

 13%|█▎        | 1461/11066 [05:21<35:37,  4.49it/s]
 13%|█▎        | 1462/11066 [05:21<35:39,  4.49it/s]
                                                    

 13%|█▎        | 1462/11066 [05:21<35:39,  4.49it/s]
 13%|█▎        | 1463/11066 [05:21<35:21,  4.53it/s]
                                                    

 13%|█▎        | 1463/11066 [05:21<35:21,  4.53it/s]
 13%|█▎        | 1464/11066 [05:22<34:59,  4.57it/s]
                                                    
{'loss': 0.7562, 'learning_rate': 2.6334718958973433e-05, 'epoch': 0.24}
{'loss': 1.0448, 'learning_rate': 2.6332007952286285e-05, 'epoch': 0.24}
{'loss': 1.9441, 'learning_rate': 2.6329296945599133e-05, 'epoch': 0.24}
{'loss': 1.8611, 'learning_rate': 2.6326585938911982e-05, 'epoch': 0.24}
{'loss': 1.6296, 'learning_rate': 2.6323874932224834e-05, 'epoch': 0.25}
{'loss': 1.5682, 'learning_rate': 2.6321163925537682e-05, 'epoch': 0.25}
{'loss': 1.6131, 'learning_rate': 2.6318452918850534e-05, 'epoch': 0.25}
{'loss': 1.8757, 'learning_rate': 2.6315741912163386e-05, 'epoch': 0.25}
{'loss': 1.0363, 'learning_rate': 2.6313030905476234e-05, 'epoch': 0.25}
{'loss': 1.3865, 'learning_rate': 2.6310319898789086e-05, 'epoch': 0.25}
{'loss': 1.8389, 'learning_rate': 2.6307608892101934e-05, 'epoch': 0.25}
{'loss': 1.6124, 'learning_rate': 2.6304897885414783e-05, 'epoch': 0.25}
{'loss': 1.4154, 'learning_rate': 2.6302186878727635e-05, 'epoch': 0.25}
{'loss': 2.0021, 'learning_rate': 2.6299475872040487e-05, 'epoch': 0.25}
{'loss': 1.7975, 'learning_rate': 2.6296764865353335e-05, 'epoch': 0.25}
{'loss': 1.0141, 'learning_rate': 2.6294053858666187e-05, 'epoch': 0.25}
{'loss': 1.1708, 'learning_rate': 2.6291342851979035e-05, 'epoch': 0.25}
{'loss': 1.3817, 'learning_rate': 2.6288631845291887e-05, 'epoch': 0.25}
{'loss': 1.4273, 'learning_rate': 2.6285920838604736e-05, 'epoch': 0.25}
{'loss': 1.7679, 'learning_rate': 2.6283209831917584e-05, 'epoch': 0.25}
{'loss': 0.9169, 'learning_rate': 2.6280498825230436e-05, 'epoch': 0.25}
{'loss': 1.2078, 'learning_rate': 2.6277787818543288e-05, 'epoch': 0.25}
{'loss': 2.0918, 'learning_rate': 2.6275076811856136e-05, 'epoch': 0.25}
{'loss': 1.2816, 'learning_rate': 2.6272365805168988e-05, 'epoch': 0.25}
{'loss': 1.0514, 'learning_rate': 2.626965479848184e-05, 'epoch': 0.25}
{'loss': 1.1679, 'learning_rate': 2.6266943791794688e-05, 'epoch': 0.25}
{'loss': 1.5958, 'learning_rate': 2.6264232785107537e-05, 'epoch': 0.25}
{'loss': 1.0676, 'learning_rate': 2.6261521778420385e-05, 'epoch': 0.25}
{'loss': 0.6821, 'learning_rate': 2.6258810771733237e-05, 'epoch': 0.25}
{'loss': 1.8319, 'learning_rate': 2.625609976504609e-05, 'epoch': 0.25}
{'loss': 0.8483, 'learning_rate': 2.6253388758358937e-05, 'epoch': 0.25}
{'loss': 0.8749, 'learning_rate': 2.625067775167179e-05, 'epoch': 0.25}
{'loss': 2.2219, 'learning_rate': 2.624796674498464e-05, 'epoch': 0.25}
{'loss': 0.8713, 'learning_rate': 2.624525573829749e-05, 'epoch': 0.25}
{'loss': 1.4106, 'learning_rate': 2.6242544731610338e-05, 'epoch': 0.25}
{'loss': 0.9499, 'learning_rate': 2.623983372492319e-05, 'epoch': 0.25}
{'loss': 1.3781, 'learning_rate': 2.6237122718236038e-05, 'epoch': 0.25}
{'loss': 0.8493, 'learning_rate': 2.623441171154889e-05, 'epoch': 0.25}
{'loss': 1.3811, 'learning_rate': 2.6231700704861738e-05, 'epoch': 0.25}
{'loss': 1.2714, 'learning_rate': 2.622898969817459e-05, 'epoch': 0.25}
{'loss': 2.0452, 'learning_rate': 2.6226278691487442e-05, 'epoch': 0.25}
{'loss': 1.2902, 'learning_rate': 2.622356768480029e-05, 'epoch': 0.25}
{'loss': 1.3841, 'learning_rate': 2.622085667811314e-05, 'epoch': 0.25}
{'loss': 1.3565, 'learning_rate': 2.621814567142599e-05, 'epoch': 0.25}
{'loss': 1.8285, 'learning_rate': 2.621543466473884e-05, 'epoch': 0.25}
{'loss': 1.5335, 'learning_rate': 2.621272365805169e-05, 'epoch': 0.25}
{'loss': 0.7227, 'learning_rate': 2.6210012651364543e-05, 'epoch': 0.25}
{'loss': 0.9507, 'learning_rate': 2.620730164467739e-05, 'epoch': 0.25}
{'loss': 0.7399, 'learning_rate': 2.6204590637990243e-05, 'epoch': 0.25}
{'loss': 1.2909, 'learning_rate': 2.620187963130309e-05, 'epoch': 0.25}
{'loss': 1.5417, 'learning_rate': 2.619916862461594e-05, 'epoch': 0.25}
{'loss': 1.1104, 'learning_rate': 2.619645761792879e-05, 'epoch': 0.25}
{'loss': 1.9094, 'learning_rate': 2.619374661124164e-05, 'epoch': 0.25}
{'loss': 1.2441, 'learning_rate': 2.6191035604554492e-05, 'epoch': 0.25}
{'loss': 1.2958, 'learning_rate': 2.6188324597867344e-05, 'epoch': 0.25}
{'loss': 0.9607, 'learning_rate': 2.6185613591180192e-05, 'epoch': 0.25}
{'loss': 1.4696, 'learning_rate': 2.6182902584493044e-05, 'epoch': 0.25}
{'loss': 1.0358, 'learning_rate': 2.6180191577805896e-05, 'epoch': 0.25}
{'loss': 1.3348, 'learning_rate': 2.617748057111874e-05, 'epoch': 0.25}
{'loss': 1.31, 'learning_rate': 2.6174769564431593e-05, 'epoch': 0.26}
{'loss': 1.0976, 'learning_rate': 2.617205855774444e-05, 'epoch': 0.26}
{'loss': 1.4541, 'learning_rate': 2.6169347551057293e-05, 'epoch': 0.26}
{'loss': 1.4559, 'learning_rate': 2.6166636544370145e-05, 'epoch': 0.26}
{'loss': 1.1864, 'learning_rate': 2.6163925537682993e-05, 'epoch': 0.26}
{'loss': 1.9255, 'learning_rate': 2.6161214530995845e-05, 'epoch': 0.26}
{'loss': 0.9856, 'learning_rate': 2.6158503524308694e-05, 'epoch': 0.26}
{'loss': 1.7671, 'learning_rate': 2.6155792517621542e-05, 'epoch': 0.26}
{'loss': 1.5877, 'learning_rate': 2.6153081510934394e-05, 'epoch': 0.26}
{'loss': 0.8024, 'learning_rate': 2.6150370504247246e-05, 'epoch': 0.26}
{'loss': 1.7569, 'learning_rate': 2.6147659497560094e-05, 'epoch': 0.26}
{'loss': 1.365, 'learning_rate': 2.6144948490872946e-05, 'epoch': 0.26}
{'loss': 2.0304, 'learning_rate': 2.6142237484185794e-05, 'epoch': 0.26}
{'loss': 1.2768, 'learning_rate': 2.6139526477498646e-05, 'epoch': 0.26}
{'loss': 0.9408, 'learning_rate': 2.6136815470811495e-05, 'epoch': 0.26}
{'loss': 0.7061, 'learning_rate': 2.6134104464124343e-05, 'epoch': 0.26}
{'loss': 1.2166, 'learning_rate': 2.6131393457437195e-05, 'epoch': 0.26}
{'loss': 1.5715, 'learning_rate': 2.6128682450750047e-05, 'epoch': 0.26}
{'loss': 2.7555, 'learning_rate': 2.6125971444062895e-05, 'epoch': 0.26}
{'loss': 0.9139, 'learning_rate': 2.6123260437375747e-05, 'epoch': 0.26}
{'loss': 1.1008, 'learning_rate': 2.61205494306886e-05, 'epoch': 0.26}
{'loss': 1.5912, 'learning_rate': 2.6117838424001447e-05, 'epoch': 0.26}
{'loss': 1.3287, 'learning_rate': 2.6115127417314296e-05, 'epoch': 0.26}
{'loss': 2.138, 'learning_rate': 2.6112416410627144e-05, 'epoch': 0.26}
{'loss': 0.8436, 'learning_rate': 2.6109705403939996e-05, 'epoch': 0.26}
{'loss': 1.3273, 'learning_rate': 2.6106994397252848e-05, 'epoch': 0.26}
{'loss': 1.1466, 'learning_rate': 2.6104283390565696e-05, 'epoch': 0.26}
{'loss': 1.1747, 'learning_rate': 2.6101572383878548e-05, 'epoch': 0.26}
{'loss': 1.2587, 'learning_rate': 2.60988613771914e-05, 'epoch': 0.26}
{'loss': 1.3306, 'learning_rate': 2.609615037050425e-05, 'epoch': 0.26}
{'loss': 1.1549, 'learning_rate': 2.6093439363817097e-05, 'epoch': 0.26}
{'loss': 1.1906, 'learning_rate': 2.609072835712995e-05, 'epoch': 0.26}
{'loss': 1.6197, 'learning_rate': 2.6088017350442797e-05, 'epoch': 0.26}
{'loss': 0.8611, 'learning_rate': 2.608530634375565e-05, 'epoch': 0.26}
{'loss': 1.6689, 'learning_rate': 2.6082595337068497e-05, 'epoch': 0.26}
{'loss': 1.7255, 'learning_rate': 2.607988433038135e-05, 'epoch': 0.26}
{'loss': 1.3371, 'learning_rate': 2.60771733236942e-05, 'epoch': 0.26}
{'loss': 0.9383, 'learning_rate': 2.607446231700705e-05, 'epoch': 0.26}
{'loss': 1.434, 'learning_rate': 2.6071751310319898e-05, 'epoch': 0.26}
{'loss': 0.9466, 'learning_rate': 2.606904030363275e-05, 'epoch': 0.26}
{'loss': 2.1412, 'learning_rate': 2.6066329296945598e-05, 'epoch': 0.26}
{'loss': 1.3303, 'learning_rate': 2.606361829025845e-05, 'epoch': 0.26}
{'loss': 0.8075, 'learning_rate': 2.6060907283571302e-05, 'epoch': 0.26}
{'loss': 1.1731, 'learning_rate': 2.605819627688415e-05, 'epoch': 0.26}
{'loss': 0.5022, 'learning_rate': 2.6055485270197002e-05, 'epoch': 0.26}
{'loss': 0.9909, 'learning_rate': 2.605277426350985e-05, 'epoch': 0.26}
{'loss': 1.6177, 'learning_rate': 2.60500632568227e-05, 'epoch': 0.26}
{'loss': 1.1802, 'learning_rate': 2.604735225013555e-05, 'epoch': 0.26}
{'loss': 1.3656, 'learning_rate': 2.60446412434484e-05, 'epoch': 0.26}
{'loss': 1.8931, 'learning_rate': 2.604193023676125e-05, 'epoch': 0.26}
{'loss': 0.672, 'learning_rate': 2.6039219230074103e-05, 'epoch': 0.26}
{'loss': 1.729, 'learning_rate': 2.603650822338695e-05, 'epoch': 0.26}
{'loss': 1.6297, 'learning_rate': 2.6033797216699803e-05, 'epoch': 0.26}

 13%|█▎        | 1464/11066 [05:22<34:59,  4.57it/s]
 13%|█▎        | 1465/11066 [05:22<34:44,  4.61it/s]
                                                    

 13%|█▎        | 1465/11066 [05:22<34:44,  4.61it/s]
 13%|█▎        | 1466/11066 [05:22<34:39,  4.62it/s]
                                                    

 13%|█▎        | 1466/11066 [05:22<34:39,  4.62it/s]
 13%|█▎        | 1467/11066 [05:22<34:28,  4.64it/s]
                                                    

 13%|█▎        | 1467/11066 [05:22<34:28,  4.64it/s]
 13%|█▎        | 1468/11066 [05:22<34:32,  4.63it/s]
                                                    

 13%|█▎        | 1468/11066 [05:22<34:32,  4.63it/s]
 13%|█▎        | 1469/11066 [05:23<34:26,  4.64it/s]
                                                    

 13%|█▎        | 1469/11066 [05:23<34:26,  4.64it/s]
 13%|█▎        | 1470/11066 [05:23<34:54,  4.58it/s]
                                                    

 13%|█▎        | 1470/11066 [05:23<34:54,  4.58it/s]
 13%|█▎        | 1471/11066 [05:23<35:12,  4.54it/s]
                                                    

 13%|█▎        | 1471/11066 [05:23<35:12,  4.54it/s]
 13%|█▎        | 1472/11066 [05:23<35:50,  4.46it/s]
                                                    

 13%|█▎        | 1472/11066 [05:23<35:50,  4.46it/s]
 13%|█▎        | 1473/11066 [05:24<35:56,  4.45it/s]
                                                    

 13%|█▎        | 1473/11066 [05:24<35:56,  4.45it/s]
 13%|█▎        | 1474/11066 [05:24<35:59,  4.44it/s]
                                                    

 13%|█▎        | 1474/11066 [05:24<35:59,  4.44it/s]
 13%|█▎        | 1475/11066 [05:24<35:55,  4.45it/s]
                                                    

 13%|█▎        | 1475/11066 [05:24<35:55,  4.45it/s]
 13%|█▎        | 1476/11066 [05:24<35:50,  4.46it/s]
                                                    

 13%|█▎        | 1476/11066 [05:24<35:50,  4.46it/s]
 13%|█▎        | 1477/11066 [05:24<35:47,  4.47it/s]
                                                    

 13%|█▎        | 1477/11066 [05:24<35:47,  4.47it/s]
 13%|█▎        | 1478/11066 [05:25<35:43,  4.47it/s]
                                                    

 13%|█▎        | 1478/11066 [05:25<35:43,  4.47it/s]
 13%|█▎        | 1479/11066 [05:25<35:38,  4.48it/s]
                                                    

 13%|█▎        | 1479/11066 [05:25<35:38,  4.48it/s]
 13%|█▎        | 1480/11066 [05:25<35:36,  4.49it/s]
                                                    

 13%|█▎        | 1480/11066 [05:25<35:36,  4.49it/s]
 13%|█▎        | 1481/11066 [05:25<35:35,  4.49it/s]
                                                    

 13%|█▎        | 1481/11066 [05:25<35:35,  4.49it/s]
 13%|█▎        | 1482/11066 [05:26<35:37,  4.48it/s]
                                                    

 13%|█▎        | 1482/11066 [05:26<35:37,  4.48it/s]
 13%|█▎        | 1483/11066 [05:26<35:36,  4.49it/s]
                                                    

 13%|█▎        | 1483/11066 [05:26<35:36,  4.49it/s]
 13%|█▎        | 1484/11066 [05:26<35:37,  4.48it/s]
                                                    

 13%|█▎        | 1484/11066 [05:26<35:37,  4.48it/s]
 13%|█▎        | 1485/11066 [05:26<35:38,  4.48it/s]
                                                    

 13%|█▎        | 1485/11066 [05:26<35:38,  4.48it/s]
 13%|█▎        | 1486/11066 [05:26<35:34,  4.49it/s]
                                                    

 13%|█▎        | 1486/11066 [05:26<35:34,  4.49it/s]
 13%|█▎        | 1487/11066 [05:27<35:34,  4.49it/s]
                                                    

 13%|█▎        | 1487/11066 [05:27<35:34,  4.49it/s]
 13%|█▎        | 1488/11066 [05:27<35:06,  4.55it/s]
                                                    

 13%|█▎        | 1488/11066 [05:27<35:06,  4.55it/s]
 13%|█▎        | 1489/11066 [05:27<35:11,  4.53it/s]
                                                    

 13%|█▎        | 1489/11066 [05:27<35:11,  4.53it/s]
 13%|█▎        | 1490/11066 [05:27<34:47,  4.59it/s]
                                                    

 13%|█▎        | 1490/11066 [05:27<34:47,  4.59it/s]
 13%|█▎        | 1491/11066 [05:28<34:45,  4.59it/s]
                                                    

 13%|█▎        | 1491/11066 [05:28<34:45,  4.59it/s]
 13%|█▎        | 1492/11066 [05:28<34:40,  4.60it/s]
                                                    

 13%|█▎        | 1492/11066 [05:28<34:40,  4.60it/s]
 13%|█▎        | 1493/11066 [05:28<34:39,  4.60it/s]
                                                    

 13%|█▎        | 1493/11066 [05:28<34:39,  4.60it/s]
 14%|█▎        | 1494/11066 [05:28<34:59,  4.56it/s]
                                                    

 14%|█▎        | 1494/11066 [05:28<34:59,  4.56it/s]
 14%|█▎        | 1495/11066 [05:28<34:57,  4.56it/s]
                                                    

 14%|█▎        | 1495/11066 [05:28<34:57,  4.56it/s]
 14%|█▎        | 1496/11066 [05:29<34:49,  4.58it/s]
                                                    

 14%|█▎        | 1496/11066 [05:29<34:49,  4.58it/s]
 14%|█▎        | 1497/11066 [05:29<34:39,  4.60it/s]
                                                    

 14%|█▎        | 1497/11066 [05:29<34:39,  4.60it/s]
 14%|█▎        | 1498/11066 [05:29<35:00,  4.55it/s]
                                                    

 14%|█▎        | 1498/11066 [05:29<35:00,  4.55it/s]
 14%|█▎        | 1499/11066 [05:29<34:56,  4.56it/s]
                                                    

 14%|█▎        | 1499/11066 [05:29<34:56,  4.56it/s]
 14%|█▎        | 1500/11066 [05:29<34:40,  4.60it/s]
                                                    

 14%|█▎        | 1500/11066 [05:29<34:40,  4.60it/s]
 14%|█▎        | 1501/11066 [05:30<34:31,  4.62it/s]
                                                    

 14%|█▎        | 1501/11066 [05:30<34:31,  4.62it/s]
 14%|█▎        | 1502/11066 [05:30<34:19,  4.64it/s]
                                                    

 14%|█▎        | 1502/11066 [05:30<34:19,  4.64it/s]
 14%|█▎        | 1503/11066 [05:30<34:25,  4.63it/s]
                                                    

 14%|█▎        | 1503/11066 [05:30<34:25,  4.63it/s]
 14%|█▎        | 1504/11066 [05:30<34:04,  4.68it/s]
                                                    

 14%|█▎        | 1504/11066 [05:30<34:04,  4.68it/s]
 14%|█▎        | 1505/11066 [05:31<34:13,  4.66it/s]
                                                    

 14%|█▎        | 1505/11066 [05:31<34:13,  4.66it/s]
 14%|█▎        | 1506/11066 [05:31<34:30,  4.62it/s]
                                                    

 14%|█▎        | 1506/11066 [05:31<34:30,  4.62it/s]
 14%|█▎        | 1507/11066 [05:31<34:45,  4.58it/s]
                                                    

 14%|█▎        | 1507/11066 [05:31<34:45,  4.58it/s]
 14%|█▎        | 1508/11066 [05:31<34:58,  4.55it/s]
                                                    

 14%|█▎        | 1508/11066 [05:31<34:58,  4.55it/s]
 14%|█▎        | 1509/11066 [05:31<34:51,  4.57it/s]
                                                    

 14%|█▎        | 1509/11066 [05:31<34:51,  4.57it/s]
 14%|█▎        | 1510/11066 [05:32<34:55,  4.56it/s]
                                                    

 14%|█▎        | 1510/11066 [05:32<34:55,  4.56it/s]
 14%|█▎        | 1511/11066 [05:32<34:40,  4.59it/s]
                                                    

 14%|█▎        | 1511/11066 [05:32<34:40,  4.59it/s]
 14%|█▎        | 1512/11066 [05:32<35:03,  4.54it/s]
                                                    

 14%|█▎        | 1512/11066 [05:32<35:03,  4.54it/s]
 14%|█▎        | 1513/11066 [05:32<35:13,  4.52it/s]
                                                    

 14%|█▎        | 1513/11066 [05:32<35:13,  4.52it/s]
 14%|█▎        | 1514/11066 [05:33<35:16,  4.51it/s]
                                                    

 14%|█▎        | 1514/11066 [05:33<35:16,  4.51it/s]
 14%|█▎        | 1515/11066 [05:33<35:16,  4.51it/s]
                                                    

 14%|█▎        | 1515/11066 [05:33<35:16,  4.51it/s]
 14%|█▎        | 1516/11066 [05:33<35:19,  4.51it/s]
                                                    

 14%|█▎        | 1516/11066 [05:33<35:19,  4.51it/s]
 14%|█▎        | 1517/11066 [05:33<35:19,  4.51it/s]
                                                    

 14%|█▎        | 1517/11066 [05:33<35:19,  4.51it/s]
 14%|█▎        | 1518/11066 [05:33<35:02,  4.54it/s]
                                                    

 14%|█▎        | 1518/11066 [05:33<35:02,  4.54it/s]
 14%|█▎        | 1519/11066 [05:34<34:31,  4.61it/s]
                                                    

 14%|█▎        | 1519/11066 [05:34<34:31,  4.61it/s]
 14%|█▎        | 1520/11066 [05:34<34:27,  4.62it/s]
                                                    

 14%|█▎        | 1520/11066 [05:34<34:27,  4.62it/s]
 14%|█▎        | 1521/11066 [05:34<34:20,  4.63it/s]
                                                    

 14%|█▎        | 1521/11066 [05:34<34:20,  4.63it/s]
 14%|█▍        | 1522/11066 [05:34<34:44,  4.58it/s]
                                                    

 14%|█▍        | 1522/11066 [05:34<34:44,  4.58it/s]
 14%|█▍        | 1523/11066 [05:35<34:58,  4.55it/s]
                                                    

 14%|█▍        | 1523/11066 [05:35<34:58,  4.55it/s]
 14%|█▍        | 1524/11066 [05:35<35:08,  4.53it/s]
                                                    

 14%|█▍        | 1524/11066 [05:35<35:08,  4.53it/s]
 14%|█▍        | 1525/11066 [05:35<34:45,  4.58it/s]
                                                    

 14%|█▍        | 1525/11066 [05:35<34:45,  4.58it/s]
 14%|█▍        | 1526/11066 [05:35<34:55,  4.55it/s]
                                                    

 14%|█▍        | 1526/11066 [05:35<34:55,  4.55it/s]
 14%|█▍        | 1527/11066 [05:35<34:49,  4.56it/s]
                                                    

 14%|█▍        | 1527/11066 [05:35<34:49,  4.56it/s]
 14%|█▍        | 1528/11066 [05:36<34:26,  4.62it/s]
                                                    

 14%|█▍        | 1528/11066 [05:36<34:26,  4.62it/s]
 14%|█▍        | 1529/11066 [05:36<34:23,  4.62it/s]
                                                    

 14%|█▍        | 1529/11066 [05:36<34:23,  4.62it/s]
 14%|█▍        | 1530/11066 [05:36<34:27,  4.61it/s]
                                                    

 14%|█▍        | 1530/11066 [05:36<34:27,  4.61it/s]
 14%|█▍        | 1531/11066 [05:36<34:04,  4.66it/s]
                                                    

 14%|█▍        | 1531/11066 [05:36<34:04,  4.66it/s]
 14%|█▍        | 1532/11066 [05:36<33:59,  4.67it/s]
                                                    

 14%|█▍        | 1532/11066 [05:36<33:59,  4.67it/s]
 14%|█▍        | 1533/11066 [05:37<33:53,  4.69it/s]
                                                    

 14%|█▍        | 1533/11066 [05:37<33:53,  4.69it/s]
 14%|█▍        | 1534/11066 [05:37<34:05,  4.66it/s]
                                                    

 14%|█▍        | 1534/11066 [05:37<34:05,  4.66it/s]
 14%|█▍        | 1535/11066 [05:37<34:02,  4.67it/s]
                                                    

 14%|█▍        | 1535/11066 [05:37<34:02,  4.67it/s]
 14%|█▍        | 1536/11066 [05:37<34:21,  4.62it/s]
                                                    

 14%|█▍        | 1536/11066 [05:37<34:21,  4.62it/s]
 14%|█▍        | 1537/11066 [05:38<34:07,  4.65it/s]
                                                    

 14%|█▍        | 1537/11066 [05:38<34:07,  4.65it/s]
 14%|█▍        | 1538/11066 [05:38<34:01,  4.67it/s]
                                                    

 14%|█▍        | 1538/11066 [05:38<34:01,  4.67it/s]
 14%|█▍        | 1539/11066 [05:38<33:59,  4.67it/s]
                                                    

 14%|█▍        | 1539/11066 [05:38<33:59,  4.67it/s]
 14%|█▍        | 1540/11066 [05:38<34:10,  4.64it/s]
                                                    

 14%|█▍        | 1540/11066 [05:38<34:10,  4.64it/s]
 14%|█▍        | 1541/11066 [05:38<34:05,  4.66it/s]
                                                    

 14%|█▍        | 1541/11066 [05:38<34:05,  4.66it/s]
 14%|█▍        | 1542/11066 [05:39<35:12,  4.51it/s]
                                                    

 14%|█▍        | 1542/11066 [05:39<35:12,  4.51it/s]
 14%|█▍        | 1543/11066 [05:39<35:46,  4.44it/s]
                                                    

 14%|█▍        | 1543/11066 [05:39<35:46,  4.44it/s]
 14%|█▍        | 1544/11066 [05:39<35:39,  4.45it/s]
                                                    

 14%|█▍        | 1544/11066 [05:39<35:39,  4.45it/s]
 14%|█▍        | 1545/11066 [05:39<35:04,  4.52it/s]
                                                    

 14%|█▍        | 1545/11066 [05:39<35:04,  4.52it/s]
 14%|█▍        | 1546/11066 [05:40<35:07,  4.52it/s]
                                                    

 14%|█▍        | 1546/11066 [05:40<35:07,  4.52it/s]
 14%|█▍        | 1547/11066 [05:40<34:22,  4.61it/s]
                                                    

 14%|█▍        | 1547/11066 [05:40<34:22,  4.61it/s]
 14%|█▍        | 1548/11066 [05:40<34:25,  4.61it/s]
                                                    

 14%|█▍        | 1548/11066 [05:40<34:25,  4.61it/s]
 14%|█▍        | 1549/11066 [05:40<34:44,  4.57it/s]
                                                    

 14%|█▍        | 1549/11066 [05:40<34:44,  4.57it/s]
 14%|█▍        | 1550/11066 [05:40<34:55,  4.54it/s]
                                                    

 14%|█▍        | 1550/11066 [05:40<34:55,  4.54it/s]
 14%|█▍        | 1551/11066 [05:41<35:02,  4.53it/s]
                                                    

 14%|█▍        | 1551/11066 [05:41<35:02,  4.53it/s]
 14%|█▍        | 1552/11066 [05:41<34:51,  4.55it/s]
                                                    

 14%|█▍        | 1552/11066 [05:41<34:51,  4.55it/s]
 14%|█▍        | 1553/11066 [05:41<35:10,  4.51it/s]
                                                    

 14%|█▍        | 1553/11066 [05:41<35:10,  4.51it/s]
 14%|█▍        | 1554/11066 [05:41<35:19,  4.49it/s]
                                                    

 14%|█▍        | 1554/11066 [05:41<35:19,  4.49it/s]
 14%|█▍        | 1555/11066 [05:42<35:50,  4.42it/s]
                                                    

 14%|█▍        | 1555/11066 [05:42<35:50,  4.42it/s]
 14%|█▍        | 1556/11066 [05:42<35:39,  4.45it/s]
                                                    

 14%|█▍        | 1556/11066 [05:42<35:39,  4.45it/s]
 14%|█▍        | 1557/11066 [05:42<35:33,  4.46it/s]
                                                    

 14%|█▍        | 1557/11066 [05:42<35:33,  4.46it/s]
 14%|█▍        | 1558/11066 [05:42<35:25,  4.47it/s]
                                                    

 14%|█▍        | 1558/11066 [05:42<35:25,  4.47it/s]
 14%|█▍        | 1559/11066 [05:42<35:21,  4.48it/s]
                                                    

 14%|█▍        | 1559/11066 [05:42<35:21,  4.48it/s]
 14%|█▍        | 1560/11066 [05:43<35:18,  4.49it/s]
                                                    

 14%|█▍        | 1560/11066 [05:43<35:18,  4.49it/s]
 14%|█▍        | 1561/11066 [05:43<35:15,  4.49it/s]
                                                    

 14%|█▍        | 1561/11066 [05:43<35:15,  4.49it/s]
 14%|█▍        | 1562/11066 [05:43<35:13,  4.50it/s]
                                                    

 14%|█▍        | 1562/11066 [05:43<35:13,  4.50it/s]
 14%|█▍        | 1563/11066 [05:43<35:12,  4.50it/s]
                                                    

 14%|█▍        | 1563/11066 [05:43<35:12,  4.50it/s]
 14%|█▍        | 1564/11066 [05:44<35:07,  4.51it/s]
                                                    

 14%|█▍        | 1564/11066 [05:44<35:07,  4.51it/s]
 14%|█▍        | 1565/11066 [05:44<34:56,  4.53it/s]
                                                    

 14%|█▍        | 1565/11066 [05:44<34:56,  4.53it/s]
 14%|█▍        | 1566/11066 [05:44<34:33,  4.58it/s]
                                                    

 14%|█▍        | 1566/11066 [05:44<34:33,  4.58it/s]
 14%|█▍        | 1567/11066 [05:44<34:35,  4.58it/s]
                                                    

 14%|█▍        | 1567/11066 [05:44<34:35,  4.58it/s]
 14%|█▍        | 1568/11066 [05:44<34:42,  4.56it/s]
                                                    

 14%|█▍        | 1568/11066 [05:44<34:42,  4.56it/s]
 14%|█▍        | 1569/11066 [05:45<34:54,  4.53it/s]
                                                    

 14%|█▍        | 1569/11066 [05:45<34:54,  4.53it/s]
 14%|█▍        | 1570/11066 [05:45<34:45,  4.55it/s]
                                                    

 14%|█▍        | 1570/11066 [05:45<34:45,  4.55it/s]
 14%|█▍        | 1571/11066 [05:45<34:36,  4.57it/s]
                                                    

 14%|█▍        | 1571/11066 [05:45<34:36,  4.57it/s]
 14%|█▍        | 1572/11066 [05:45<34:47,  4.55it/s]
                                                    

 14%|█▍        | 1572/11066 [05:45<34:47,  4.55it/s]
 14%|█▍        | 1573/11066 [05:45<34:55,  4.53it/s]
                                                    

 14%|█▍        | 1573/11066 [05:45<34:55,  4.53it/s]
 14%|█▍        | 1574/11066 [05:46<34:58,  4.52it/s]
                                                    

 14%|█▍        | 1574/11066 [05:46<34:58,  4.52it/s]
 14%|█▍        | 1575/11066 [05:46<34:45,  4.55it/s]
                                                    

 14%|█▍        | 1575/11066 [05:46<34:45,  4.55it/s]
 14%|█▍        | 1576/11066 [05:46<34:28,  4.59it/s]
                                                    
{'loss': 0.8893, 'learning_rate': 2.6031086210012655e-05, 'epoch': 0.26}
{'loss': 0.9511, 'learning_rate': 2.60283752033255e-05, 'epoch': 0.26}
{'loss': 0.4248, 'learning_rate': 2.6025664196638352e-05, 'epoch': 0.26}
{'loss': 1.9539, 'learning_rate': 2.60229531899512e-05, 'epoch': 0.27}
{'loss': 1.0707, 'learning_rate': 2.6020242183264052e-05, 'epoch': 0.27}
{'loss': 1.0558, 'learning_rate': 2.6017531176576904e-05, 'epoch': 0.27}
{'loss': 0.5778, 'learning_rate': 2.6014820169889752e-05, 'epoch': 0.27}
{'loss': 1.0383, 'learning_rate': 2.6012109163202604e-05, 'epoch': 0.27}
{'loss': 1.1809, 'learning_rate': 2.6009398156515456e-05, 'epoch': 0.27}
{'loss': 1.4051, 'learning_rate': 2.60066871498283e-05, 'epoch': 0.27}
{'loss': 1.8138, 'learning_rate': 2.6003976143141153e-05, 'epoch': 0.27}
{'loss': 1.853, 'learning_rate': 2.6001265136454005e-05, 'epoch': 0.27}
{'loss': 1.9002, 'learning_rate': 2.5998554129766853e-05, 'epoch': 0.27}
{'loss': 1.767, 'learning_rate': 2.5995843123079705e-05, 'epoch': 0.27}
{'loss': 1.3136, 'learning_rate': 2.5993132116392553e-05, 'epoch': 0.27}
{'loss': 1.0388, 'learning_rate': 2.5990421109705405e-05, 'epoch': 0.27}
{'loss': 1.7101, 'learning_rate': 2.5987710103018257e-05, 'epoch': 0.27}
{'loss': 1.7014, 'learning_rate': 2.5984999096331102e-05, 'epoch': 0.27}
{'loss': 1.1828, 'learning_rate': 2.5982288089643954e-05, 'epoch': 0.27}
{'loss': 1.4049, 'learning_rate': 2.5979577082956806e-05, 'epoch': 0.27}
{'loss': 1.4467, 'learning_rate': 2.5976866076269654e-05, 'epoch': 0.27}
{'loss': 1.7342, 'learning_rate': 2.5974155069582506e-05, 'epoch': 0.27}
{'loss': 0.7352, 'learning_rate': 2.5971444062895358e-05, 'epoch': 0.27}
{'loss': 1.4479, 'learning_rate': 2.5968733056208206e-05, 'epoch': 0.27}
{'loss': 1.5758, 'learning_rate': 2.5966022049521058e-05, 'epoch': 0.27}
{'loss': 1.0552, 'learning_rate': 2.5963311042833903e-05, 'epoch': 0.27}
{'loss': 0.7282, 'learning_rate': 2.5960600036146755e-05, 'epoch': 0.27}
{'loss': 1.3718, 'learning_rate': 2.5957889029459607e-05, 'epoch': 0.27}
{'loss': 1.5486, 'learning_rate': 2.5955178022772455e-05, 'epoch': 0.27}
{'loss': 0.9, 'learning_rate': 2.5952467016085307e-05, 'epoch': 0.27}
{'loss': 1.4181, 'learning_rate': 2.594975600939816e-05, 'epoch': 0.27}
{'loss': 1.9002, 'learning_rate': 2.5947045002711007e-05, 'epoch': 0.27}
{'loss': 1.3293, 'learning_rate': 2.594433399602386e-05, 'epoch': 0.27}
{'loss': 0.9657, 'learning_rate': 2.5941622989336708e-05, 'epoch': 0.27}
{'loss': 0.8766, 'learning_rate': 2.5938911982649556e-05, 'epoch': 0.27}
{'loss': 1.6083, 'learning_rate': 2.5936200975962408e-05, 'epoch': 0.27}
{'loss': 1.307, 'learning_rate': 2.5933489969275256e-05, 'epoch': 0.27}
{'loss': 2.0437, 'learning_rate': 2.5930778962588108e-05, 'epoch': 0.27}
{'loss': 1.7398, 'learning_rate': 2.592806795590096e-05, 'epoch': 0.27}
{'loss': 1.4841, 'learning_rate': 2.592535694921381e-05, 'epoch': 0.27}
{'loss': 1.5207, 'learning_rate': 2.592264594252666e-05, 'epoch': 0.27}
{'loss': 1.4371, 'learning_rate': 2.591993493583951e-05, 'epoch': 0.27}
{'loss': 2.246, 'learning_rate': 2.5917223929152357e-05, 'epoch': 0.27}
{'loss': 1.0463, 'learning_rate': 2.591451292246521e-05, 'epoch': 0.27}
{'loss': 1.6371, 'learning_rate': 2.591180191577806e-05, 'epoch': 0.27}
{'loss': 0.7876, 'learning_rate': 2.590909090909091e-05, 'epoch': 0.27}
{'loss': 1.4542, 'learning_rate': 2.590637990240376e-05, 'epoch': 0.27}
{'loss': 0.9741, 'learning_rate': 2.590366889571661e-05, 'epoch': 0.27}
{'loss': 1.3681, 'learning_rate': 2.590095788902946e-05, 'epoch': 0.27}
{'loss': 1.1525, 'learning_rate': 2.589824688234231e-05, 'epoch': 0.27}
{'loss': 1.5836, 'learning_rate': 2.5895535875655158e-05, 'epoch': 0.27}
{'loss': 0.9936, 'learning_rate': 2.589282486896801e-05, 'epoch': 0.27}
{'loss': 1.2944, 'learning_rate': 2.5890113862280862e-05, 'epoch': 0.27}
{'loss': 1.1131, 'learning_rate': 2.588740285559371e-05, 'epoch': 0.27}
{'loss': 1.1701, 'learning_rate': 2.5884691848906562e-05, 'epoch': 0.27}
{'loss': 0.5133, 'learning_rate': 2.5881980842219414e-05, 'epoch': 0.27}
{'loss': 1.4879, 'learning_rate': 2.5879269835532262e-05, 'epoch': 0.27}
{'loss': 1.6739, 'learning_rate': 2.587655882884511e-05, 'epoch': 0.27}
{'loss': 1.3926, 'learning_rate': 2.5873847822157963e-05, 'epoch': 0.28}
{'loss': 1.2939, 'learning_rate': 2.587113681547081e-05, 'epoch': 0.28}
{'loss': 1.4108, 'learning_rate': 2.5868425808783663e-05, 'epoch': 0.28}
{'loss': 1.5889, 'learning_rate': 2.586571480209651e-05, 'epoch': 0.28}
{'loss': 1.0803, 'learning_rate': 2.5863003795409363e-05, 'epoch': 0.28}
{'loss': 1.0482, 'learning_rate': 2.5860292788722215e-05, 'epoch': 0.28}
{'loss': 1.6213, 'learning_rate': 2.5857581782035064e-05, 'epoch': 0.28}
{'loss': 1.1227, 'learning_rate': 2.5854870775347912e-05, 'epoch': 0.28}
{'loss': 0.9129, 'learning_rate': 2.5852159768660764e-05, 'epoch': 0.28}
{'loss': 0.8621, 'learning_rate': 2.5849448761973612e-05, 'epoch': 0.28}
{'loss': 1.1604, 'learning_rate': 2.5846737755286464e-05, 'epoch': 0.28}
{'loss': 0.7889, 'learning_rate': 2.5844026748599316e-05, 'epoch': 0.28}
{'loss': 1.8673, 'learning_rate': 2.5841315741912164e-05, 'epoch': 0.28}
{'loss': 2.1102, 'learning_rate': 2.5838604735225016e-05, 'epoch': 0.28}
{'loss': 1.1475, 'learning_rate': 2.5835893728537865e-05, 'epoch': 0.28}
{'loss': 1.0998, 'learning_rate': 2.5833182721850713e-05, 'epoch': 0.28}
{'loss': 1.7855, 'learning_rate': 2.5830471715163565e-05, 'epoch': 0.28}
{'loss': 1.3715, 'learning_rate': 2.5827760708476413e-05, 'epoch': 0.28}
{'loss': 1.0533, 'learning_rate': 2.5825049701789265e-05, 'epoch': 0.28}
{'loss': 1.7408, 'learning_rate': 2.5822338695102117e-05, 'epoch': 0.28}
{'loss': 1.4924, 'learning_rate': 2.5819627688414965e-05, 'epoch': 0.28}
{'loss': 0.7911, 'learning_rate': 2.5816916681727817e-05, 'epoch': 0.28}
{'loss': 1.1504, 'learning_rate': 2.581420567504067e-05, 'epoch': 0.28}
{'loss': 1.1141, 'learning_rate': 2.5811494668353514e-05, 'epoch': 0.28}
{'loss': 2.1897, 'learning_rate': 2.5808783661666366e-05, 'epoch': 0.28}
{'loss': 1.5049, 'learning_rate': 2.5806072654979214e-05, 'epoch': 0.28}
{'loss': 1.0368, 'learning_rate': 2.5803361648292066e-05, 'epoch': 0.28}
{'loss': 0.7496, 'learning_rate': 2.5800650641604918e-05, 'epoch': 0.28}
{'loss': 1.7828, 'learning_rate': 2.5797939634917766e-05, 'epoch': 0.28}
{'loss': 0.9959, 'learning_rate': 2.579522862823062e-05, 'epoch': 0.28}
{'loss': 1.267, 'learning_rate': 2.5792517621543467e-05, 'epoch': 0.28}
{'loss': 1.0095, 'learning_rate': 2.5789806614856315e-05, 'epoch': 0.28}
{'loss': 1.2605, 'learning_rate': 2.5787095608169167e-05, 'epoch': 0.28}
{'loss': 1.3202, 'learning_rate': 2.578438460148202e-05, 'epoch': 0.28}
{'loss': 0.8702, 'learning_rate': 2.5781673594794867e-05, 'epoch': 0.28}
{'loss': 0.6592, 'learning_rate': 2.577896258810772e-05, 'epoch': 0.28}
{'loss': 1.8501, 'learning_rate': 2.5776251581420568e-05, 'epoch': 0.28}
{'loss': 1.4974, 'learning_rate': 2.577354057473342e-05, 'epoch': 0.28}
{'loss': 1.663, 'learning_rate': 2.5770829568046268e-05, 'epoch': 0.28}
{'loss': 2.0877, 'learning_rate': 2.5768118561359116e-05, 'epoch': 0.28}
{'loss': 2.8446, 'learning_rate': 2.5765407554671968e-05, 'epoch': 0.28}
{'loss': 1.1022, 'learning_rate': 2.576269654798482e-05, 'epoch': 0.28}
{'loss': 1.0946, 'learning_rate': 2.575998554129767e-05, 'epoch': 0.28}
{'loss': 1.3637, 'learning_rate': 2.575727453461052e-05, 'epoch': 0.28}
{'loss': 0.9731, 'learning_rate': 2.5754563527923372e-05, 'epoch': 0.28}
{'loss': 1.2922, 'learning_rate': 2.575185252123622e-05, 'epoch': 0.28}
{'loss': 0.9852, 'learning_rate': 2.574914151454907e-05, 'epoch': 0.28}
{'loss': 1.0115, 'learning_rate': 2.5746430507861917e-05, 'epoch': 0.28}
{'loss': 1.4487, 'learning_rate': 2.574371950117477e-05, 'epoch': 0.28}
{'loss': 1.6086, 'learning_rate': 2.574100849448762e-05, 'epoch': 0.28}
{'loss': 1.045, 'learning_rate': 2.573829748780047e-05, 'epoch': 0.28}
{'loss': 1.1803, 'learning_rate': 2.573558648111332e-05, 'epoch': 0.28}
{'loss': 1.5205, 'learning_rate': 2.5732875474426173e-05, 'epoch': 0.28}
{'loss': 2.2361, 'learning_rate': 2.573016446773902e-05, 'epoch': 0.28}

 14%|█▍        | 1576/11066 [05:46<34:28,  4.59it/s]
 14%|█▍        | 1577/11066 [05:46<34:46,  4.55it/s]
                                                    

 14%|█▍        | 1577/11066 [05:46<34:46,  4.55it/s]
 14%|█▍        | 1578/11066 [05:47<34:55,  4.53it/s]
                                                    

 14%|█▍        | 1578/11066 [05:47<34:55,  4.53it/s]
 14%|█▍        | 1579/11066 [05:47<35:04,  4.51it/s]
                                                    

 14%|█▍        | 1579/11066 [05:47<35:04,  4.51it/s]
 14%|█▍        | 1580/11066 [05:47<35:05,  4.51it/s]
                                                    

 14%|█▍        | 1580/11066 [05:47<35:05,  4.51it/s]
 14%|█▍        | 1581/11066 [05:47<35:05,  4.50it/s]
                                                    

 14%|█▍        | 1581/11066 [05:47<35:05,  4.50it/s]
 14%|█▍        | 1582/11066 [05:47<35:08,  4.50it/s]
                                                    

 14%|█▍        | 1582/11066 [05:47<35:08,  4.50it/s]
 14%|█▍        | 1583/11066 [05:48<35:09,  4.50it/s]
                                                    

 14%|█▍        | 1583/11066 [05:48<35:09,  4.50it/s]
 14%|█▍        | 1584/11066 [05:48<34:56,  4.52it/s]
                                                    

 14%|█▍        | 1584/11066 [05:48<34:56,  4.52it/s]
 14%|█▍        | 1585/11066 [05:48<34:43,  4.55it/s]
                                                    

 14%|█▍        | 1585/11066 [05:48<34:43,  4.55it/s]
 14%|█▍        | 1586/11066 [05:48<34:51,  4.53it/s]
                                                    

 14%|█▍        | 1586/11066 [05:48<34:51,  4.53it/s]
 14%|█▍        | 1587/11066 [05:49<34:56,  4.52it/s]
                                                    

 14%|█▍        | 1587/11066 [05:49<34:56,  4.52it/s]
 14%|█▍        | 1588/11066 [05:49<34:58,  4.52it/s]
                                                    

 14%|█▍        | 1588/11066 [05:49<34:58,  4.52it/s]
 14%|█▍        | 1589/11066 [05:49<34:44,  4.55it/s]
                                                    

 14%|█▍        | 1589/11066 [05:49<34:44,  4.55it/s]
 14%|█▍        | 1590/11066 [05:49<34:41,  4.55it/s]
                                                    

 14%|█▍        | 1590/11066 [05:49<34:41,  4.55it/s]
 14%|█▍        | 1591/11066 [05:49<34:31,  4.57it/s]
                                                    

 14%|█▍        | 1591/11066 [05:49<34:31,  4.57it/s]
 14%|█▍        | 1592/11066 [05:50<34:50,  4.53it/s]
                                                    

 14%|█▍        | 1592/11066 [05:50<34:50,  4.53it/s]
 14%|█▍        | 1593/11066 [05:50<35:00,  4.51it/s]
                                                    

 14%|█▍        | 1593/11066 [05:50<35:00,  4.51it/s]
 14%|█▍        | 1594/11066 [05:50<34:46,  4.54it/s]
                                                    

 14%|█▍        | 1594/11066 [05:50<34:46,  4.54it/s]
 14%|█▍        | 1595/11066 [05:50<34:31,  4.57it/s]
                                                    

 14%|█▍        | 1595/11066 [05:50<34:31,  4.57it/s]
 14%|█▍        | 1596/11066 [05:51<34:29,  4.58it/s]
                                                    

 14%|█▍        | 1596/11066 [05:51<34:29,  4.58it/s]
 14%|█▍        | 1597/11066 [05:51<34:44,  4.54it/s]
                                                    

 14%|█▍        | 1597/11066 [05:51<34:44,  4.54it/s]
 14%|█▍        | 1598/11066 [05:51<34:45,  4.54it/s]
                                                    

 14%|█▍        | 1598/11066 [05:51<34:45,  4.54it/s]
 14%|█▍        | 1599/11066 [05:51<34:51,  4.53it/s]
                                                    

 14%|█▍        | 1599/11066 [05:51<34:51,  4.53it/s]
 14%|█▍        | 1600/11066 [05:51<34:40,  4.55it/s]
                                                    

 14%|█▍        | 1600/11066 [05:51<34:40,  4.55it/s]
 14%|█▍        | 1601/11066 [05:52<34:40,  4.55it/s]
                                                    

 14%|█▍        | 1601/11066 [05:52<34:40,  4.55it/s]
 14%|█▍        | 1602/11066 [05:52<34:34,  4.56it/s]
                                                    

 14%|█▍        | 1602/11066 [05:52<34:34,  4.56it/s]
 14%|█▍        | 1603/11066 [05:52<34:45,  4.54it/s]
                                                    

 14%|█▍        | 1603/11066 [05:52<34:45,  4.54it/s]
 14%|█▍        | 1604/11066 [05:52<34:54,  4.52it/s]
                                                    

 14%|█▍        | 1604/11066 [05:52<34:54,  4.52it/s]
 15%|█▍        | 1605/11066 [05:53<34:40,  4.55it/s]
                                                    

 15%|█▍        | 1605/11066 [05:53<34:40,  4.55it/s]
 15%|█▍        | 1606/11066 [05:53<34:21,  4.59it/s]
                                                    

 15%|█▍        | 1606/11066 [05:53<34:21,  4.59it/s]
 15%|█▍        | 1607/11066 [05:53<34:27,  4.57it/s]
                                                    

 15%|█▍        | 1607/11066 [05:53<34:27,  4.57it/s]
 15%|█▍        | 1608/11066 [05:53<34:42,  4.54it/s]
                                                    

 15%|█▍        | 1608/11066 [05:53<34:42,  4.54it/s]
 15%|█▍        | 1609/11066 [05:53<34:57,  4.51it/s]
                                                    

 15%|█▍        | 1609/11066 [05:53<34:57,  4.51it/s]
 15%|█▍        | 1610/11066 [05:54<35:33,  4.43it/s]
                                                    

 15%|█▍        | 1610/11066 [05:54<35:33,  4.43it/s]
 15%|█▍        | 1611/11066 [05:54<35:27,  4.44it/s]
                                                    

 15%|█▍        | 1611/11066 [05:54<35:27,  4.44it/s]
 15%|█▍        | 1612/11066 [05:54<35:21,  4.46it/s]
                                                    

 15%|█▍        | 1612/11066 [05:54<35:21,  4.46it/s]
 15%|█▍        | 1613/11066 [05:54<34:58,  4.50it/s]
                                                    

 15%|█▍        | 1613/11066 [05:54<34:58,  4.50it/s]
 15%|█▍        | 1614/11066 [05:55<34:52,  4.52it/s]
                                                    

 15%|█▍        | 1614/11066 [05:55<34:52,  4.52it/s]
 15%|█▍        | 1615/11066 [05:55<34:50,  4.52it/s]
                                                    

 15%|█▍        | 1615/11066 [05:55<34:50,  4.52it/s]
 15%|█▍        | 1616/11066 [05:55<34:25,  4.58it/s]
                                                    

 15%|█▍        | 1616/11066 [05:55<34:25,  4.58it/s]
 15%|█▍        | 1617/11066 [05:55<34:36,  4.55it/s]
                                                    

 15%|█▍        | 1617/11066 [05:55<34:36,  4.55it/s]
 15%|█▍        | 1618/11066 [05:55<34:43,  4.54it/s]
                                                    

 15%|█▍        | 1618/11066 [05:55<34:43,  4.54it/s]
 15%|█▍        | 1619/11066 [05:56<34:26,  4.57it/s]
                                                    

 15%|█▍        | 1619/11066 [05:56<34:26,  4.57it/s]
 15%|█▍        | 1620/11066 [05:56<34:33,  4.56it/s]
                                                    

 15%|█▍        | 1620/11066 [05:56<34:33,  4.56it/s]
 15%|█▍        | 1621/11066 [05:56<34:24,  4.58it/s]
                                                    

 15%|█▍        | 1621/11066 [05:56<34:24,  4.58it/s]
 15%|█▍        | 1622/11066 [05:56<34:39,  4.54it/s]
                                                    

 15%|█▍        | 1622/11066 [05:56<34:39,  4.54it/s]
 15%|█▍        | 1623/11066 [05:57<34:51,  4.51it/s]
                                                    

 15%|█▍        | 1623/11066 [05:57<34:51,  4.51it/s]
 15%|█▍        | 1624/11066 [05:57<34:54,  4.51it/s]
                                                    

 15%|█▍        | 1624/11066 [05:57<34:54,  4.51it/s]
 15%|█▍        | 1625/11066 [05:57<34:53,  4.51it/s]
                                                    

 15%|█▍        | 1625/11066 [05:57<34:53,  4.51it/s]
 15%|█▍        | 1626/11066 [05:57<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1626/11066 [05:57<34:57,  4.50it/s]
 15%|█▍        | 1627/11066 [05:57<34:55,  4.50it/s]
                                                    

 15%|█▍        | 1627/11066 [05:57<34:55,  4.50it/s]
 15%|█▍        | 1628/11066 [05:58<34:56,  4.50it/s]
                                                    

 15%|█▍        | 1628/11066 [05:58<34:56,  4.50it/s]
 15%|█▍        | 1629/11066 [05:58<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1629/11066 [05:58<34:57,  4.50it/s]
 15%|█▍        | 1630/11066 [05:58<34:55,  4.50it/s]
                                                    

 15%|█▍        | 1630/11066 [05:58<34:55,  4.50it/s]
 15%|█▍        | 1631/11066 [05:58<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1631/11066 [05:58<34:57,  4.50it/s]
 15%|█▍        | 1632/11066 [05:59<34:55,  4.50it/s]
                                                    

 15%|█▍        | 1632/11066 [05:59<34:55,  4.50it/s]
 15%|█▍        | 1633/11066 [05:59<34:55,  4.50it/s]
                                                    

 15%|█▍        | 1633/11066 [05:59<34:55,  4.50it/s]
 15%|█▍        | 1634/11066 [05:59<34:56,  4.50it/s]
                                                    

 15%|█▍        | 1634/11066 [05:59<34:56,  4.50it/s]
 15%|█▍        | 1635/11066 [05:59<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1635/11066 [05:59<34:57,  4.50it/s]
 15%|█▍        | 1636/11066 [05:59<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1636/11066 [05:59<34:57,  4.50it/s]
 15%|█▍        | 1637/11066 [06:00<34:57,  4.50it/s]
                                                    

 15%|█▍        | 1637/11066 [06:00<34:57,  4.50it/s]
 15%|█▍        | 1638/11066 [06:00<34:55,  4.50it/s]
                                                    

 15%|█▍        | 1638/11066 [06:00<34:55,  4.50it/s]
 15%|█▍        | 1639/11066 [06:00<34:54,  4.50it/s]
                                                    

 15%|█▍        | 1639/11066 [06:00<34:54,  4.50it/s]
 15%|█▍        | 1640/11066 [06:00<34:56,  4.50it/s]
                                                    

 15%|█▍        | 1640/11066 [06:00<34:56,  4.50it/s]
 15%|█▍        | 1641/11066 [06:01<35:43,  4.40it/s]
                                                    

 15%|█▍        | 1641/11066 [06:01<35:43,  4.40it/s]
 15%|█▍        | 1642/11066 [06:01<35:36,  4.41it/s]
                                                    

 15%|█▍        | 1642/11066 [06:01<35:36,  4.41it/s]
 15%|█▍        | 1643/11066 [06:01<35:24,  4.44it/s]
                                                    

 15%|█▍        | 1643/11066 [06:01<35:24,  4.44it/s]
 15%|█▍        | 1644/11066 [06:01<35:15,  4.45it/s]
                                                    

 15%|█▍        | 1644/11066 [06:01<35:15,  4.45it/s]
 15%|█▍        | 1645/11066 [06:01<35:11,  4.46it/s]
                                                    

 15%|█▍        | 1645/11066 [06:01<35:11,  4.46it/s]
 15%|█▍        | 1646/11066 [06:02<35:06,  4.47it/s]
                                                    

 15%|█▍        | 1646/11066 [06:02<35:06,  4.47it/s]
 15%|█▍        | 1647/11066 [06:02<35:01,  4.48it/s]
                                                    

 15%|█▍        | 1647/11066 [06:02<35:01,  4.48it/s]
 15%|█▍        | 1648/11066 [06:02<34:57,  4.49it/s]
                                                    

 15%|█▍        | 1648/11066 [06:02<34:57,  4.49it/s]
 15%|█▍        | 1649/11066 [06:02<34:57,  4.49it/s]
                                                    

 15%|█▍        | 1649/11066 [06:02<34:57,  4.49it/s]
 15%|█▍        | 1650/11066 [06:03<34:55,  4.49it/s]
                                                    

 15%|█▍        | 1650/11066 [06:03<34:55,  4.49it/s]
 15%|█▍        | 1651/11066 [06:03<34:55,  4.49it/s]
                                                    

 15%|█▍        | 1651/11066 [06:03<34:55,  4.49it/s]
 15%|█▍        | 1652/11066 [06:03<34:54,  4.49it/s]
                                                    

 15%|█▍        | 1652/11066 [06:03<34:54,  4.49it/s]
 15%|█▍        | 1653/11066 [06:03<34:53,  4.50it/s]
                                                    

 15%|█▍        | 1653/11066 [06:03<34:53,  4.50it/s]
 15%|█▍        | 1654/11066 [06:03<34:54,  4.49it/s]
                                                    

 15%|█▍        | 1654/11066 [06:03<34:54,  4.49it/s]
 15%|█▍        | 1655/11066 [06:04<34:53,  4.49it/s]
                                                    

 15%|█▍        | 1655/11066 [06:04<34:53,  4.49it/s]
 15%|█▍        | 1656/11066 [06:04<34:51,  4.50it/s]
                                                    

 15%|█▍        | 1656/11066 [06:04<34:51,  4.50it/s]
 15%|█▍        | 1657/11066 [06:04<34:50,  4.50it/s]
                                                    

 15%|█▍        | 1657/11066 [06:04<34:50,  4.50it/s]
 15%|█▍        | 1658/11066 [06:04<34:48,  4.50it/s]
                                                    

 15%|█▍        | 1658/11066 [06:04<34:48,  4.50it/s]
 15%|█▍        | 1659/11066 [06:05<34:46,  4.51it/s]
                                                    

 15%|█▍        | 1659/11066 [06:05<34:46,  4.51it/s]
 15%|█▌        | 1660/11066 [06:05<34:47,  4.51it/s]
                                                    

 15%|█▌        | 1660/11066 [06:05<34:47,  4.51it/s]
 15%|█▌        | 1661/11066 [06:05<34:47,  4.51it/s]
                                                    

 15%|█▌        | 1661/11066 [06:05<34:47,  4.51it/s]
 15%|█▌        | 1662/11066 [06:05<34:51,  4.50it/s]
                                                    

 15%|█▌        | 1662/11066 [06:05<34:51,  4.50it/s]
 15%|█▌        | 1663/11066 [06:05<34:39,  4.52it/s]
                                                    

 15%|█▌        | 1663/11066 [06:05<34:39,  4.52it/s]
 15%|█▌        | 1664/11066 [06:06<34:48,  4.50it/s]
                                                    

 15%|█▌        | 1664/11066 [06:06<34:48,  4.50it/s]
 15%|█▌        | 1665/11066 [06:06<34:50,  4.50it/s]
                                                    

 15%|█▌        | 1665/11066 [06:06<34:50,  4.50it/s]
 15%|█▌        | 1666/11066 [06:06<34:49,  4.50it/s]
                                                    

 15%|█▌        | 1666/11066 [06:06<34:49,  4.50it/s]
 15%|█▌        | 1667/11066 [06:06<34:49,  4.50it/s]
                                                    

 15%|█▌        | 1667/11066 [06:06<34:49,  4.50it/s]
 15%|█▌        | 1668/11066 [06:07<34:51,  4.49it/s]
                                                    

 15%|█▌        | 1668/11066 [06:07<34:51,  4.49it/s]
 15%|█▌        | 1669/11066 [06:07<34:54,  4.49it/s]
                                                    

 15%|█▌        | 1669/11066 [06:07<34:54,  4.49it/s]
 15%|█▌        | 1670/11066 [06:07<34:55,  4.48it/s]
                                                    

 15%|█▌        | 1670/11066 [06:07<34:55,  4.48it/s]
 15%|█▌        | 1671/11066 [06:07<35:04,  4.46it/s]
                                                    

 15%|█▌        | 1671/11066 [06:07<35:04,  4.46it/s]
 15%|█▌        | 1672/11066 [06:07<35:04,  4.46it/s]
                                                    

 15%|█▌        | 1672/11066 [06:07<35:04,  4.46it/s]
 15%|█▌        | 1673/11066 [06:08<35:01,  4.47it/s]
                                                    

 15%|█▌        | 1673/11066 [06:08<35:01,  4.47it/s]
 15%|█▌        | 1674/11066 [06:08<34:55,  4.48it/s]
                                                    

 15%|█▌        | 1674/11066 [06:08<34:55,  4.48it/s]
 15%|█▌        | 1675/11066 [06:08<34:52,  4.49it/s]
                                                    

 15%|█▌        | 1675/11066 [06:08<34:52,  4.49it/s]
 15%|█▌        | 1676/11066 [06:08<34:50,  4.49it/s]
                                                    

 15%|█▌        | 1676/11066 [06:08<34:50,  4.49it/s]
 15%|█▌        | 1677/11066 [06:09<34:49,  4.49it/s]
                                                    

 15%|█▌        | 1677/11066 [06:09<34:49,  4.49it/s]
 15%|█▌        | 1678/11066 [06:09<34:46,  4.50it/s]
                                                    

 15%|█▌        | 1678/11066 [06:09<34:46,  4.50it/s]
 15%|█▌        | 1679/11066 [06:09<34:44,  4.50it/s]
                                                    

 15%|█▌        | 1679/11066 [06:09<34:44,  4.50it/s]
 15%|█▌        | 1680/11066 [06:09<34:43,  4.50it/s]
                                                    

 15%|█▌        | 1680/11066 [06:09<34:43,  4.50it/s]
 15%|█▌        | 1681/11066 [06:09<34:43,  4.50it/s]
                                                    

 15%|█▌        | 1681/11066 [06:09<34:43,  4.50it/s]
 15%|█▌        | 1682/11066 [06:10<34:44,  4.50it/s]
                                                    

 15%|█▌        | 1682/11066 [06:10<34:44,  4.50it/s]
 15%|█▌        | 1683/11066 [06:10<34:44,  4.50it/s]
                                                    

 15%|█▌        | 1683/11066 [06:10<34:44,  4.50it/s]
 15%|█▌        | 1684/11066 [06:10<34:44,  4.50it/s]
                                                    

 15%|█▌        | 1684/11066 [06:10<34:44,  4.50it/s]
 15%|█▌        | 1685/11066 [06:10<34:43,  4.50it/s]
                                                    

 15%|█▌        | 1685/11066 [06:10<34:43,  4.50it/s]
 15%|█▌        | 1686/11066 [06:11<34:41,  4.51it/s]
                                                    

 15%|█▌        | 1686/11066 [06:11<34:41,  4.51it/s]
 15%|█▌        | 1687/11066 [06:11<34:41,  4.51it/s]
                                                    

 15%|█▌        | 1687/11066 [06:11<34:41,  4.51it/s]
 15%|█▌        | 1688/11066 [06:11<34:40,  4.51it/s]
                                                    

 15%|█▌        | 1688/11066 [06:11<34:40,  4.51it/s]
 15%|█▌        | 1689/11066 [06:11<34:39,  4.51it/s]
                                                    
{'loss': 1.1503, 'learning_rate': 2.572745346105187e-05, 'epoch': 0.28}
{'loss': 0.7773, 'learning_rate': 2.5724742454364722e-05, 'epoch': 0.29}
{'loss': 1.3313, 'learning_rate': 2.572203144767757e-05, 'epoch': 0.29}
{'loss': 1.8346, 'learning_rate': 2.5719320440990422e-05, 'epoch': 0.29}
{'loss': 1.4168, 'learning_rate': 2.571660943430327e-05, 'epoch': 0.29}
{'loss': 0.9021, 'learning_rate': 2.5713898427616122e-05, 'epoch': 0.29}
{'loss': 1.5324, 'learning_rate': 2.5711187420928974e-05, 'epoch': 0.29}
{'loss': 1.3366, 'learning_rate': 2.5708476414241823e-05, 'epoch': 0.29}
{'loss': 1.1465, 'learning_rate': 2.570576540755467e-05, 'epoch': 0.29}
{'loss': 1.3531, 'learning_rate': 2.5703054400867523e-05, 'epoch': 0.29}
{'loss': 1.4026, 'learning_rate': 2.570034339418037e-05, 'epoch': 0.29}
{'loss': 1.4479, 'learning_rate': 2.5697632387493223e-05, 'epoch': 0.29}
{'loss': 1.3254, 'learning_rate': 2.5694921380806075e-05, 'epoch': 0.29}
{'loss': 2.1051, 'learning_rate': 2.5692210374118923e-05, 'epoch': 0.29}
{'loss': 0.8256, 'learning_rate': 2.5689499367431775e-05, 'epoch': 0.29}
{'loss': 1.4373, 'learning_rate': 2.5686788360744624e-05, 'epoch': 0.29}
{'loss': 1.4133, 'learning_rate': 2.5684077354057472e-05, 'epoch': 0.29}
{'loss': 0.8527, 'learning_rate': 2.5681366347370324e-05, 'epoch': 0.29}
{'loss': 1.702, 'learning_rate': 2.5678655340683172e-05, 'epoch': 0.29}
{'loss': 1.4186, 'learning_rate': 2.5675944333996024e-05, 'epoch': 0.29}
{'loss': 1.2115, 'learning_rate': 2.5673233327308876e-05, 'epoch': 0.29}
{'loss': 0.9229, 'learning_rate': 2.5670522320621724e-05, 'epoch': 0.29}
{'loss': 1.1023, 'learning_rate': 2.5667811313934576e-05, 'epoch': 0.29}
{'loss': 0.7672, 'learning_rate': 2.5665100307247428e-05, 'epoch': 0.29}
{'loss': 1.118, 'learning_rate': 2.5662389300560273e-05, 'epoch': 0.29}
{'loss': 1.4962, 'learning_rate': 2.5659678293873125e-05, 'epoch': 0.29}
{'loss': 1.2252, 'learning_rate': 2.5656967287185973e-05, 'epoch': 0.29}
{'loss': 0.8598, 'learning_rate': 2.5654256280498825e-05, 'epoch': 0.29}
{'loss': 0.945, 'learning_rate': 2.5651545273811677e-05, 'epoch': 0.29}
{'loss': 0.7467, 'learning_rate': 2.5648834267124526e-05, 'epoch': 0.29}
{'loss': 0.7556, 'learning_rate': 2.5646123260437377e-05, 'epoch': 0.29}
{'loss': 1.7143, 'learning_rate': 2.564341225375023e-05, 'epoch': 0.29}
{'loss': 2.3025, 'learning_rate': 2.5640701247063074e-05, 'epoch': 0.29}
{'loss': 1.1177, 'learning_rate': 2.5637990240375926e-05, 'epoch': 0.29}
{'loss': 1.1454, 'learning_rate': 2.5635279233688778e-05, 'epoch': 0.29}
{'loss': 1.7139, 'learning_rate': 2.5632568227001626e-05, 'epoch': 0.29}
{'loss': 0.9625, 'learning_rate': 2.5629857220314478e-05, 'epoch': 0.29}
{'loss': 1.3888, 'learning_rate': 2.5627146213627327e-05, 'epoch': 0.29}
{'loss': 1.1835, 'learning_rate': 2.562443520694018e-05, 'epoch': 0.29}
{'loss': 0.7513, 'learning_rate': 2.562172420025303e-05, 'epoch': 0.29}
{'loss': 1.4343, 'learning_rate': 2.5619013193565875e-05, 'epoch': 0.29}
{'loss': 0.7465, 'learning_rate': 2.5616302186878727e-05, 'epoch': 0.29}
{'loss': 1.5541, 'learning_rate': 2.561359118019158e-05, 'epoch': 0.29}
{'loss': 1.3451, 'learning_rate': 2.5610880173504427e-05, 'epoch': 0.29}
{'loss': 1.7839, 'learning_rate': 2.560816916681728e-05, 'epoch': 0.29}
{'loss': 1.2889, 'learning_rate': 2.560545816013013e-05, 'epoch': 0.29}
{'loss': 1.6942, 'learning_rate': 2.560274715344298e-05, 'epoch': 0.29}
{'loss': 1.0189, 'learning_rate': 2.560003614675583e-05, 'epoch': 0.29}
{'loss': 1.1684, 'learning_rate': 2.5597325140068676e-05, 'epoch': 0.29}
{'loss': 0.9459, 'learning_rate': 2.5594614133381528e-05, 'epoch': 0.29}
{'loss': 0.7816, 'learning_rate': 2.559190312669438e-05, 'epoch': 0.29}
{'loss': 1.4363, 'learning_rate': 2.558919212000723e-05, 'epoch': 0.29}
{'loss': 1.203, 'learning_rate': 2.558648111332008e-05, 'epoch': 0.29}
{'loss': 1.1942, 'learning_rate': 2.5583770106632932e-05, 'epoch': 0.29}
{'loss': 1.3758, 'learning_rate': 2.558105909994578e-05, 'epoch': 0.29}
{'loss': 1.5777, 'learning_rate': 2.5578348093258632e-05, 'epoch': 0.29}
{'loss': 1.136, 'learning_rate': 2.557563708657148e-05, 'epoch': 0.29}
{'loss': 0.7505, 'learning_rate': 2.557292607988433e-05, 'epoch': 0.3}
{'loss': 0.903, 'learning_rate': 2.557021507319718e-05, 'epoch': 0.3}
{'loss': 0.463, 'learning_rate': 2.556750406651003e-05, 'epoch': 0.3}
{'loss': 1.1016, 'learning_rate': 2.556479305982288e-05, 'epoch': 0.3}
{'loss': 1.791, 'learning_rate': 2.5562082053135733e-05, 'epoch': 0.3}
{'loss': 1.457, 'learning_rate': 2.555937104644858e-05, 'epoch': 0.3}
{'loss': 1.2548, 'learning_rate': 2.5556660039761434e-05, 'epoch': 0.3}
{'loss': 1.2888, 'learning_rate': 2.5553949033074282e-05, 'epoch': 0.3}
{'loss': 1.6987, 'learning_rate': 2.555123802638713e-05, 'epoch': 0.3}
{'loss': 1.0535, 'learning_rate': 2.5548527019699982e-05, 'epoch': 0.3}
{'loss': 0.8335, 'learning_rate': 2.5545816013012834e-05, 'epoch': 0.3}
{'loss': 1.862, 'learning_rate': 2.5543105006325682e-05, 'epoch': 0.3}
{'loss': 0.9572, 'learning_rate': 2.5540393999638534e-05, 'epoch': 0.3}
{'loss': 1.3104, 'learning_rate': 2.5537682992951383e-05, 'epoch': 0.3}
{'loss': 1.5589, 'learning_rate': 2.5534971986264235e-05, 'epoch': 0.3}
{'loss': 1.9529, 'learning_rate': 2.5532260979577083e-05, 'epoch': 0.3}
{'loss': 1.2147, 'learning_rate': 2.552954997288993e-05, 'epoch': 0.3}
{'loss': 1.0551, 'learning_rate': 2.5526838966202783e-05, 'epoch': 0.3}
{'loss': 1.9553, 'learning_rate': 2.5524127959515635e-05, 'epoch': 0.3}
{'loss': 1.006, 'learning_rate': 2.5521416952828484e-05, 'epoch': 0.3}
{'loss': 1.4315, 'learning_rate': 2.5518705946141335e-05, 'epoch': 0.3}
{'loss': 1.7222, 'learning_rate': 2.5515994939454187e-05, 'epoch': 0.3}
{'loss': 1.4023, 'learning_rate': 2.5513283932767036e-05, 'epoch': 0.3}
{'loss': 0.8351, 'learning_rate': 2.5510572926079884e-05, 'epoch': 0.3}
{'loss': 1.6844, 'learning_rate': 2.5507861919392736e-05, 'epoch': 0.3}
{'loss': 1.6053, 'learning_rate': 2.5505150912705584e-05, 'epoch': 0.3}
{'loss': 1.1303, 'learning_rate': 2.5502439906018436e-05, 'epoch': 0.3}
{'loss': 1.0493, 'learning_rate': 2.5499728899331285e-05, 'epoch': 0.3}
{'loss': 0.8867, 'learning_rate': 2.5497017892644136e-05, 'epoch': 0.3}
{'loss': 1.4348, 'learning_rate': 2.5494306885956988e-05, 'epoch': 0.3}
{'loss': 1.0324, 'learning_rate': 2.5491595879269837e-05, 'epoch': 0.3}
{'loss': 0.9931, 'learning_rate': 2.5488884872582685e-05, 'epoch': 0.3}
{'loss': 1.0841, 'learning_rate': 2.5486173865895537e-05, 'epoch': 0.3}
{'loss': 0.7782, 'learning_rate': 2.5483462859208385e-05, 'epoch': 0.3}
{'loss': 1.2662, 'learning_rate': 2.5480751852521237e-05, 'epoch': 0.3}
{'loss': 1.0697, 'learning_rate': 2.547804084583409e-05, 'epoch': 0.3}
{'loss': 1.1349, 'learning_rate': 2.5475329839146938e-05, 'epoch': 0.3}
{'loss': 1.0086, 'learning_rate': 2.547261883245979e-05, 'epoch': 0.3}
{'loss': 1.5121, 'learning_rate': 2.5469907825772638e-05, 'epoch': 0.3}
{'loss': 1.0966, 'learning_rate': 2.5467196819085486e-05, 'epoch': 0.3}
{'loss': 2.0329, 'learning_rate': 2.5464485812398338e-05, 'epoch': 0.3}
{'loss': 1.0444, 'learning_rate': 2.5461774805711187e-05, 'epoch': 0.3}
{'loss': 0.9935, 'learning_rate': 2.545906379902404e-05, 'epoch': 0.3}
{'loss': 1.078, 'learning_rate': 2.545635279233689e-05, 'epoch': 0.3}
{'loss': 1.0357, 'learning_rate': 2.545364178564974e-05, 'epoch': 0.3}
{'loss': 1.2109, 'learning_rate': 2.545093077896259e-05, 'epoch': 0.3}
{'loss': 0.7156, 'learning_rate': 2.544821977227544e-05, 'epoch': 0.3}
{'loss': 0.9496, 'learning_rate': 2.5445508765588287e-05, 'epoch': 0.3}
{'loss': 0.8757, 'learning_rate': 2.544279775890114e-05, 'epoch': 0.3}
{'loss': 1.7017, 'learning_rate': 2.5440086752213988e-05, 'epoch': 0.3}
{'loss': 1.4691, 'learning_rate': 2.543737574552684e-05, 'epoch': 0.3}
{'loss': 1.0146, 'learning_rate': 2.543466473883969e-05, 'epoch': 0.3}
{'loss': 1.2964, 'learning_rate': 2.543195373215254e-05, 'epoch': 0.3}
{'loss': 1.0002, 'learning_rate': 2.542924272546539e-05, 'epoch': 0.3}
{'loss': 0.7505, 'learning_rate': 2.542653171877824e-05, 'epoch': 0.3}
{'loss': 1.5425, 'learning_rate': 2.542382071209109e-05, 'epoch': 0.31}

 15%|█▌        | 1689/11066 [06:11<34:39,  4.51it/s]
 15%|█▌        | 1690/11066 [06:11<34:25,  4.54it/s]
                                                    

 15%|█▌        | 1690/11066 [06:11<34:25,  4.54it/s]
 15%|█▌        | 1691/11066 [06:12<34:36,  4.51it/s]
                                                    

 15%|█▌        | 1691/11066 [06:12<34:36,  4.51it/s]
 15%|█▌        | 1692/11066 [06:12<34:40,  4.51it/s]
                                                    

 15%|█▌        | 1692/11066 [06:12<34:40,  4.51it/s]
 15%|█▌        | 1693/11066 [06:12<34:41,  4.50it/s]
                                                    

 15%|█▌        | 1693/11066 [06:12<34:41,  4.50it/s]
 15%|█▌        | 1694/11066 [06:12<34:40,  4.50it/s]
                                                    

 15%|█▌        | 1694/11066 [06:12<34:40,  4.50it/s]
 15%|█▌        | 1695/11066 [06:13<34:41,  4.50it/s]
                                                    

 15%|█▌        | 1695/11066 [06:13<34:41,  4.50it/s]
 15%|█▌        | 1696/11066 [06:13<34:45,  4.49it/s]
                                                    

 15%|█▌        | 1696/11066 [06:13<34:45,  4.49it/s]
 15%|█▌        | 1697/11066 [06:13<34:48,  4.49it/s]
                                                    

 15%|█▌        | 1697/11066 [06:13<34:48,  4.49it/s]
 15%|█▌        | 1698/11066 [06:13<34:54,  4.47it/s]
                                                    

 15%|█▌        | 1698/11066 [06:13<34:54,  4.47it/s]
 15%|█▌        | 1699/11066 [06:13<34:57,  4.47it/s]
                                                    

 15%|█▌        | 1699/11066 [06:13<34:57,  4.47it/s]
 15%|█▌        | 1700/11066 [06:14<34:57,  4.47it/s]
                                                    

 15%|█▌        | 1700/11066 [06:14<34:57,  4.47it/s]
 15%|█▌        | 1701/11066 [06:14<34:52,  4.48it/s]
                                                    

 15%|█▌        | 1701/11066 [06:14<34:52,  4.48it/s]
 15%|█▌        | 1702/11066 [06:14<34:46,  4.49it/s]
                                                    

 15%|█▌        | 1702/11066 [06:14<34:46,  4.49it/s]
 15%|█▌        | 1703/11066 [06:14<34:47,  4.49it/s]
                                                    

 15%|█▌        | 1703/11066 [06:14<34:47,  4.49it/s]
 15%|█▌        | 1704/11066 [06:15<34:43,  4.49it/s]
                                                    

 15%|█▌        | 1704/11066 [06:15<34:43,  4.49it/s]
 15%|█▌        | 1705/11066 [06:15<34:42,  4.50it/s]
                                                    

 15%|█▌        | 1705/11066 [06:15<34:42,  4.50it/s]
 15%|█▌        | 1706/11066 [06:15<34:42,  4.49it/s]
                                                    

 15%|█▌        | 1706/11066 [06:15<34:42,  4.49it/s]
 15%|█▌        | 1707/11066 [06:15<34:42,  4.49it/s]
                                                    

 15%|█▌        | 1707/11066 [06:15<34:42,  4.49it/s]
 15%|█▌        | 1708/11066 [06:15<34:23,  4.54it/s]
                                                    

 15%|█▌        | 1708/11066 [06:15<34:23,  4.54it/s]
 15%|█▌        | 1709/11066 [06:16<34:33,  4.51it/s]
                                                    

 15%|█▌        | 1709/11066 [06:16<34:33,  4.51it/s]
 15%|█▌        | 1710/11066 [06:16<34:49,  4.48it/s]
                                                    

 15%|█▌        | 1710/11066 [06:16<34:49,  4.48it/s]
 15%|█▌        | 1711/11066 [06:16<34:49,  4.48it/s]
                                                    

 15%|█▌        | 1711/11066 [06:16<34:49,  4.48it/s]
 15%|█▌        | 1712/11066 [06:16<34:50,  4.47it/s]
                                                    

 15%|█▌        | 1712/11066 [06:16<34:50,  4.47it/s]
 15%|█▌        | 1713/11066 [06:17<34:56,  4.46it/s]
                                                    

 15%|█▌        | 1713/11066 [06:17<34:56,  4.46it/s]
 15%|█▌        | 1714/11066 [06:17<34:55,  4.46it/s]
                                                    

 15%|█▌        | 1714/11066 [06:17<34:55,  4.46it/s]
 15%|█▌        | 1715/11066 [06:17<34:51,  4.47it/s]
                                                    

 15%|█▌        | 1715/11066 [06:17<34:51,  4.47it/s]
 16%|█▌        | 1716/11066 [06:17<34:51,  4.47it/s]
                                                    

 16%|█▌        | 1716/11066 [06:17<34:51,  4.47it/s]
 16%|█▌        | 1717/11066 [06:17<34:50,  4.47it/s]
                                                    

 16%|█▌        | 1717/11066 [06:17<34:50,  4.47it/s]
 16%|█▌        | 1718/11066 [06:18<34:32,  4.51it/s]
                                                    

 16%|█▌        | 1718/11066 [06:18<34:32,  4.51it/s]
 16%|█▌        | 1719/11066 [06:18<34:09,  4.56it/s]
                                                    

 16%|█▌        | 1719/11066 [06:18<34:09,  4.56it/s]
 16%|█▌        | 1720/11066 [06:18<34:11,  4.56it/s]
                                                    

 16%|█▌        | 1720/11066 [06:18<34:11,  4.56it/s]
 16%|█▌        | 1721/11066 [06:18<34:26,  4.52it/s]
                                                    

 16%|█▌        | 1721/11066 [06:18<34:26,  4.52it/s]
 16%|█▌        | 1722/11066 [06:19<34:38,  4.50it/s]
                                                    

 16%|█▌        | 1722/11066 [06:19<34:38,  4.50it/s]
 16%|█▌        | 1723/11066 [06:19<34:43,  4.48it/s]
                                                    

 16%|█▌        | 1723/11066 [06:19<34:43,  4.48it/s]
 16%|█▌        | 1724/11066 [06:19<34:47,  4.47it/s]
                                                    

 16%|█▌        | 1724/11066 [06:19<34:47,  4.47it/s]
 16%|█▌        | 1725/11066 [06:19<34:45,  4.48it/s]
                                                    

 16%|█▌        | 1725/11066 [06:19<34:45,  4.48it/s]
 16%|█▌        | 1726/11066 [06:19<34:44,  4.48it/s]
                                                    

 16%|█▌        | 1726/11066 [06:19<34:44,  4.48it/s]
 16%|█▌        | 1727/11066 [06:20<34:42,  4.48it/s]
                                                    

 16%|█▌        | 1727/11066 [06:20<34:42,  4.48it/s]
 16%|█▌        | 1728/11066 [06:20<34:24,  4.52it/s]
                                                    

 16%|█▌        | 1728/11066 [06:20<34:24,  4.52it/s]
 16%|█▌        | 1729/11066 [06:20<34:30,  4.51it/s]
                                                    

 16%|█▌        | 1729/11066 [06:20<34:30,  4.51it/s]
 16%|█▌        | 1730/11066 [06:20<34:37,  4.49it/s]
                                                    

 16%|█▌        | 1730/11066 [06:20<34:37,  4.49it/s]
 16%|█▌        | 1731/11066 [06:21<34:39,  4.49it/s]
                                                    

 16%|█▌        | 1731/11066 [06:21<34:39,  4.49it/s]
 16%|█▌        | 1732/11066 [06:21<34:43,  4.48it/s]
                                                    

 16%|█▌        | 1732/11066 [06:21<34:43,  4.48it/s]
 16%|█▌        | 1733/11066 [06:21<34:25,  4.52it/s]
                                                    

 16%|█▌        | 1733/11066 [06:21<34:25,  4.52it/s]
 16%|█▌        | 1734/11066 [06:21<34:30,  4.51it/s]
                                                    

 16%|█▌        | 1734/11066 [06:21<34:30,  4.51it/s]
 16%|█▌        | 1735/11066 [06:21<34:20,  4.53it/s]
                                                    

 16%|█▌        | 1735/11066 [06:21<34:20,  4.53it/s]
 16%|█▌        | 1736/11066 [06:22<34:19,  4.53it/s]
                                                    

 16%|█▌        | 1736/11066 [06:22<34:19,  4.53it/s]
 16%|█▌        | 1737/11066 [06:22<34:13,  4.54it/s]
                                                    

 16%|█▌        | 1737/11066 [06:22<34:13,  4.54it/s]
 16%|█▌        | 1738/11066 [06:22<34:19,  4.53it/s]
                                                    

 16%|█▌        | 1738/11066 [06:22<34:19,  4.53it/s]
 16%|█▌        | 1739/11066 [06:22<34:24,  4.52it/s]
                                                    

 16%|█▌        | 1739/11066 [06:22<34:24,  4.52it/s]
 16%|█▌        | 1740/11066 [06:23<34:14,  4.54it/s]
                                                    

 16%|█▌        | 1740/11066 [06:23<34:14,  4.54it/s]
 16%|█▌        | 1741/11066 [06:23<34:24,  4.52it/s]
                                                    

 16%|█▌        | 1741/11066 [06:23<34:24,  4.52it/s]
 16%|█▌        | 1742/11066 [06:23<34:10,  4.55it/s]
                                                    

 16%|█▌        | 1742/11066 [06:23<34:10,  4.55it/s]
 16%|█▌        | 1743/11066 [06:23<34:14,  4.54it/s]
                                                    

 16%|█▌        | 1743/11066 [06:23<34:14,  4.54it/s]
 16%|█▌        | 1744/11066 [06:23<34:17,  4.53it/s]
                                                    

 16%|█▌        | 1744/11066 [06:23<34:17,  4.53it/s]
 16%|█▌        | 1745/11066 [06:24<34:24,  4.52it/s]
                                                    

 16%|█▌        | 1745/11066 [06:24<34:24,  4.52it/s]
 16%|█▌        | 1746/11066 [06:24<34:27,  4.51it/s]
                                                    

 16%|█▌        | 1746/11066 [06:24<34:27,  4.51it/s]
 16%|█▌        | 1747/11066 [06:24<34:27,  4.51it/s]
                                                    

 16%|█▌        | 1747/11066 [06:24<34:27,  4.51it/s]
 16%|█▌        | 1748/11066 [06:24<34:27,  4.51it/s]
                                                    

 16%|█▌        | 1748/11066 [06:24<34:27,  4.51it/s]
 16%|█▌        | 1749/11066 [06:25<34:29,  4.50it/s]
                                                    

 16%|█▌        | 1749/11066 [06:25<34:29,  4.50it/s]
 16%|█▌        | 1750/11066 [06:25<34:31,  4.50it/s]
                                                    

 16%|█▌        | 1750/11066 [06:25<34:31,  4.50it/s]
 16%|█▌        | 1751/11066 [06:25<34:17,  4.53it/s]
                                                    

 16%|█▌        | 1751/11066 [06:25<34:17,  4.53it/s]
 16%|█▌        | 1752/11066 [06:25<34:19,  4.52it/s]
                                                    

 16%|█▌        | 1752/11066 [06:25<34:19,  4.52it/s]
 16%|█▌        | 1753/11066 [06:25<34:28,  4.50it/s]
                                                    

 16%|█▌        | 1753/11066 [06:25<34:28,  4.50it/s]
 16%|█▌        | 1754/11066 [06:26<34:40,  4.48it/s]
                                                    

 16%|█▌        | 1754/11066 [06:26<34:40,  4.48it/s]
 16%|█▌        | 1755/11066 [06:26<34:40,  4.47it/s]
                                                    

 16%|█▌        | 1755/11066 [06:26<34:40,  4.47it/s]
 16%|█▌        | 1756/11066 [06:26<34:41,  4.47it/s]
                                                    

 16%|█▌        | 1756/11066 [06:26<34:41,  4.47it/s]
 16%|█▌        | 1757/11066 [06:26<34:40,  4.47it/s]
                                                    

 16%|█▌        | 1757/11066 [06:26<34:40,  4.47it/s]
 16%|█▌        | 1758/11066 [06:27<34:36,  4.48it/s]
                                                    

 16%|█▌        | 1758/11066 [06:27<34:36,  4.48it/s]
 16%|█▌        | 1759/11066 [06:27<34:37,  4.48it/s]
                                                    

 16%|█▌        | 1759/11066 [06:27<34:37,  4.48it/s]
 16%|█▌        | 1760/11066 [06:27<34:37,  4.48it/s]
                                                    

 16%|█▌        | 1760/11066 [06:27<34:37,  4.48it/s]
 16%|█▌        | 1761/11066 [06:27<34:36,  4.48it/s]
                                                    

 16%|█▌        | 1761/11066 [06:27<34:36,  4.48it/s]
 16%|█▌        | 1762/11066 [06:27<34:35,  4.48it/s]
                                                    

 16%|█▌        | 1762/11066 [06:27<34:35,  4.48it/s]
 16%|█▌        | 1763/11066 [06:28<34:34,  4.49it/s]
                                                    

 16%|█▌        | 1763/11066 [06:28<34:34,  4.49it/s]
 16%|█▌        | 1764/11066 [06:28<34:32,  4.49it/s]
                                                    

 16%|█▌        | 1764/11066 [06:28<34:32,  4.49it/s]
 16%|█▌        | 1765/11066 [06:28<34:33,  4.49it/s]
                                                    

 16%|█▌        | 1765/11066 [06:28<34:33,  4.49it/s]
 16%|█▌        | 1766/11066 [06:28<34:13,  4.53it/s]
                                                    

 16%|█▌        | 1766/11066 [06:28<34:13,  4.53it/s]
 16%|█▌        | 1767/11066 [06:29<34:21,  4.51it/s]
                                                    

 16%|█▌        | 1767/11066 [06:29<34:21,  4.51it/s]
 16%|█▌        | 1768/11066 [06:29<34:32,  4.49it/s]
                                                    

 16%|█▌        | 1768/11066 [06:29<34:32,  4.49it/s]
 16%|█▌        | 1769/11066 [06:29<34:19,  4.51it/s]
                                                    

 16%|█▌        | 1769/11066 [06:29<34:19,  4.51it/s]
 16%|█▌        | 1770/11066 [06:29<34:10,  4.53it/s]
                                                    

 16%|█▌        | 1770/11066 [06:29<34:10,  4.53it/s]
 16%|█▌        | 1771/11066 [06:29<34:16,  4.52it/s]
                                                    

 16%|█▌        | 1771/11066 [06:29<34:16,  4.52it/s]
 16%|█▌        | 1772/11066 [06:30<34:20,  4.51it/s]
                                                    

 16%|█▌        | 1772/11066 [06:30<34:20,  4.51it/s]
 16%|█▌        | 1773/11066 [06:30<34:23,  4.50it/s]
                                                    

 16%|█▌        | 1773/11066 [06:30<34:23,  4.50it/s]
 16%|█▌        | 1774/11066 [06:30<34:08,  4.54it/s]
                                                    

 16%|█▌        | 1774/11066 [06:30<34:08,  4.54it/s]
 16%|█▌        | 1775/11066 [06:30<34:07,  4.54it/s]
                                                    

 16%|█▌        | 1775/11066 [06:30<34:07,  4.54it/s]
 16%|█▌        | 1776/11066 [06:31<33:58,  4.56it/s]
                                                    

 16%|█▌        | 1776/11066 [06:31<33:58,  4.56it/s]
 16%|█▌        | 1777/11066 [06:31<34:11,  4.53it/s]
                                                    

 16%|█▌        | 1777/11066 [06:31<34:11,  4.53it/s]
 16%|█▌        | 1778/11066 [06:31<34:17,  4.51it/s]
                                                    

 16%|█▌        | 1778/11066 [06:31<34:17,  4.51it/s]
 16%|█▌        | 1779/11066 [06:31<34:06,  4.54it/s]
                                                    

 16%|█▌        | 1779/11066 [06:31<34:06,  4.54it/s]
 16%|█▌        | 1780/11066 [06:31<34:14,  4.52it/s]
                                                    

 16%|█▌        | 1780/11066 [06:31<34:14,  4.52it/s]
 16%|█▌        | 1781/11066 [06:32<34:27,  4.49it/s]
                                                    

 16%|█▌        | 1781/11066 [06:32<34:27,  4.49it/s]
 16%|█▌        | 1782/11066 [06:32<34:31,  4.48it/s]
                                                    

 16%|█▌        | 1782/11066 [06:32<34:31,  4.48it/s]
 16%|█▌        | 1783/11066 [06:32<34:27,  4.49it/s]
                                                    

 16%|█▌        | 1783/11066 [06:32<34:27,  4.49it/s]
 16%|█▌        | 1784/11066 [06:32<34:11,  4.52it/s]
                                                    

 16%|█▌        | 1784/11066 [06:32<34:11,  4.52it/s]
 16%|█▌        | 1785/11066 [06:33<34:15,  4.51it/s]
                                                    

 16%|█▌        | 1785/11066 [06:33<34:15,  4.51it/s]
 16%|█▌        | 1786/11066 [06:33<34:22,  4.50it/s]
                                                    

 16%|█▌        | 1786/11066 [06:33<34:22,  4.50it/s]
 16%|█▌        | 1787/11066 [06:33<34:30,  4.48it/s]
                                                    

 16%|█▌        | 1787/11066 [06:33<34:30,  4.48it/s]
 16%|█▌        | 1788/11066 [06:33<34:15,  4.51it/s]
                                                    

 16%|█▌        | 1788/11066 [06:33<34:15,  4.51it/s]
 16%|█▌        | 1789/11066 [06:33<34:21,  4.50it/s]
                                                    

 16%|█▌        | 1789/11066 [06:33<34:21,  4.50it/s]
 16%|█▌        | 1790/11066 [06:34<34:18,  4.51it/s]
                                                    

 16%|█▌        | 1790/11066 [06:34<34:18,  4.51it/s]
 16%|█▌        | 1791/11066 [06:34<34:24,  4.49it/s]
                                                    

 16%|█▌        | 1791/11066 [06:34<34:24,  4.49it/s]
 16%|█▌        | 1792/11066 [06:34<34:05,  4.53it/s]
                                                    

 16%|█▌        | 1792/11066 [06:34<34:05,  4.53it/s]
 16%|█▌        | 1793/11066 [06:34<33:57,  4.55it/s]
                                                    

 16%|█▌        | 1793/11066 [06:34<33:57,  4.55it/s]
 16%|█▌        | 1794/11066 [06:35<33:56,  4.55it/s]
                                                    

 16%|█▌        | 1794/11066 [06:35<33:56,  4.55it/s]
 16%|█▌        | 1795/11066 [06:35<34:33,  4.47it/s]
                                                    

 16%|█▌        | 1795/11066 [06:35<34:33,  4.47it/s]
 16%|█▌        | 1796/11066 [06:35<34:20,  4.50it/s]
                                                    

 16%|█▌        | 1796/11066 [06:35<34:20,  4.50it/s]
 16%|█▌        | 1797/11066 [06:35<34:30,  4.48it/s]
                                                    

 16%|█▌        | 1797/11066 [06:35<34:30,  4.48it/s]
 16%|█▌        | 1798/11066 [06:35<34:34,  4.47it/s]
                                                    

 16%|█▌        | 1798/11066 [06:35<34:34,  4.47it/s]
 16%|█▋        | 1799/11066 [06:36<35:01,  4.41it/s]
                                                    

 16%|█▋        | 1799/11066 [06:36<35:01,  4.41it/s]
 16%|█▋        | 1800/11066 [06:36<35:03,  4.41it/s]
                                                    

 16%|█▋        | 1800/11066 [06:36<35:03,  4.41it/s]
 16%|█▋        | 1801/11066 [06:36<34:48,  4.44it/s]
                                                    
{'loss': 0.8198, 'learning_rate': 2.542110970540394e-05, 'epoch': 0.31}
{'loss': 1.5075, 'learning_rate': 2.5418398698716792e-05, 'epoch': 0.31}
{'loss': 1.1314, 'learning_rate': 2.541568769202964e-05, 'epoch': 0.31}
{'loss': 1.1758, 'learning_rate': 2.5412976685342492e-05, 'epoch': 0.31}
{'loss': 1.2981, 'learning_rate': 2.541026567865534e-05, 'epoch': 0.31}
{'loss': 1.0044, 'learning_rate': 2.5407554671968193e-05, 'epoch': 0.31}
{'loss': 1.2013, 'learning_rate': 2.540484366528104e-05, 'epoch': 0.31}
{'loss': 1.4362, 'learning_rate': 2.540213265859389e-05, 'epoch': 0.31}
{'loss': 0.8256, 'learning_rate': 2.539942165190674e-05, 'epoch': 0.31}
{'loss': 0.9782, 'learning_rate': 2.5396710645219593e-05, 'epoch': 0.31}
{'loss': 1.2352, 'learning_rate': 2.539399963853244e-05, 'epoch': 0.31}
{'loss': 1.5273, 'learning_rate': 2.5391288631845293e-05, 'epoch': 0.31}
{'loss': 1.8071, 'learning_rate': 2.5388577625158145e-05, 'epoch': 0.31}
{'loss': 1.7243, 'learning_rate': 2.5385866618470994e-05, 'epoch': 0.31}
{'loss': 1.3206, 'learning_rate': 2.5383155611783842e-05, 'epoch': 0.31}
{'loss': 0.9009, 'learning_rate': 2.538044460509669e-05, 'epoch': 0.31}
{'loss': 1.4974, 'learning_rate': 2.5377733598409542e-05, 'epoch': 0.31}
{'loss': 0.9846, 'learning_rate': 2.5375022591722394e-05, 'epoch': 0.31}
{'loss': 0.9099, 'learning_rate': 2.5372311585035243e-05, 'epoch': 0.31}
{'loss': 1.3303, 'learning_rate': 2.5369600578348094e-05, 'epoch': 0.31}
{'loss': 2.2947, 'learning_rate': 2.5366889571660946e-05, 'epoch': 0.31}
{'loss': 0.7815, 'learning_rate': 2.5364178564973795e-05, 'epoch': 0.31}
{'loss': 0.9099, 'learning_rate': 2.5361467558286643e-05, 'epoch': 0.31}
{'loss': 1.1867, 'learning_rate': 2.5358756551599495e-05, 'epoch': 0.31}
{'loss': 1.3073, 'learning_rate': 2.5356045544912343e-05, 'epoch': 0.31}
{'loss': 1.4253, 'learning_rate': 2.5353334538225195e-05, 'epoch': 0.31}
{'loss': 1.2457, 'learning_rate': 2.5350623531538044e-05, 'epoch': 0.31}
{'loss': 1.3308, 'learning_rate': 2.5347912524850896e-05, 'epoch': 0.31}
{'loss': 0.9309, 'learning_rate': 2.5345201518163747e-05, 'epoch': 0.31}
{'loss': 0.9241, 'learning_rate': 2.5342490511476596e-05, 'epoch': 0.31}
{'loss': 0.8722, 'learning_rate': 2.5339779504789444e-05, 'epoch': 0.31}
{'loss': 1.0257, 'learning_rate': 2.5337068498102296e-05, 'epoch': 0.31}
{'loss': 0.8382, 'learning_rate': 2.5334357491415145e-05, 'epoch': 0.31}
{'loss': 1.2003, 'learning_rate': 2.5331646484727996e-05, 'epoch': 0.31}
{'loss': 1.2713, 'learning_rate': 2.5328935478040848e-05, 'epoch': 0.31}
{'loss': 1.3793, 'learning_rate': 2.5326224471353697e-05, 'epoch': 0.31}
{'loss': 1.5769, 'learning_rate': 2.532351346466655e-05, 'epoch': 0.31}
{'loss': 1.2718, 'learning_rate': 2.5320802457979397e-05, 'epoch': 0.31}
{'loss': 1.0315, 'learning_rate': 2.5318091451292245e-05, 'epoch': 0.31}
{'loss': 1.3639, 'learning_rate': 2.5315380444605097e-05, 'epoch': 0.31}
{'loss': 1.5833, 'learning_rate': 2.5312669437917946e-05, 'epoch': 0.31}
{'loss': 1.7803, 'learning_rate': 2.5309958431230797e-05, 'epoch': 0.31}
{'loss': 1.1188, 'learning_rate': 2.530724742454365e-05, 'epoch': 0.31}
{'loss': 1.0086, 'learning_rate': 2.5304536417856498e-05, 'epoch': 0.31}
{'loss': 0.9217, 'learning_rate': 2.530182541116935e-05, 'epoch': 0.31}
{'loss': 1.2276, 'learning_rate': 2.52991144044822e-05, 'epoch': 0.31}
{'loss': 0.9087, 'learning_rate': 2.5296403397795046e-05, 'epoch': 0.31}
{'loss': 0.9575, 'learning_rate': 2.5293692391107898e-05, 'epoch': 0.31}
{'loss': 0.974, 'learning_rate': 2.5290981384420747e-05, 'epoch': 0.31}
{'loss': 1.4562, 'learning_rate': 2.52882703777336e-05, 'epoch': 0.31}
{'loss': 1.1581, 'learning_rate': 2.528555937104645e-05, 'epoch': 0.31}
{'loss': 1.4369, 'learning_rate': 2.52828483643593e-05, 'epoch': 0.31}
{'loss': 0.6451, 'learning_rate': 2.528013735767215e-05, 'epoch': 0.31}
{'loss': 0.9616, 'learning_rate': 2.5277426350985002e-05, 'epoch': 0.31}
{'loss': 0.7368, 'learning_rate': 2.5274715344297847e-05, 'epoch': 0.32}
{'loss': 1.0667, 'learning_rate': 2.52720043376107e-05, 'epoch': 0.32}
{'loss': 1.3296, 'learning_rate': 2.526929333092355e-05, 'epoch': 0.32}
{'loss': 1.0468, 'learning_rate': 2.52665823242364e-05, 'epoch': 0.32}
{'loss': 0.5652, 'learning_rate': 2.526387131754925e-05, 'epoch': 0.32}
{'loss': 0.957, 'learning_rate': 2.52611603108621e-05, 'epoch': 0.32}
{'loss': 0.9995, 'learning_rate': 2.525844930417495e-05, 'epoch': 0.32}
{'loss': 2.2533, 'learning_rate': 2.5255738297487804e-05, 'epoch': 0.32}
{'loss': 0.9014, 'learning_rate': 2.525302729080065e-05, 'epoch': 0.32}
{'loss': 1.4253, 'learning_rate': 2.52503162841135e-05, 'epoch': 0.32}
{'loss': 1.7122, 'learning_rate': 2.5247605277426352e-05, 'epoch': 0.32}
{'loss': 1.2387, 'learning_rate': 2.52448942707392e-05, 'epoch': 0.32}
{'loss': 1.1144, 'learning_rate': 2.5242183264052052e-05, 'epoch': 0.32}
{'loss': 1.3889, 'learning_rate': 2.5239472257364904e-05, 'epoch': 0.32}
{'loss': 1.3719, 'learning_rate': 2.5236761250677753e-05, 'epoch': 0.32}
{'loss': 0.6333, 'learning_rate': 2.5234050243990605e-05, 'epoch': 0.32}
{'loss': 1.4543, 'learning_rate': 2.523133923730345e-05, 'epoch': 0.32}
{'loss': 1.0149, 'learning_rate': 2.52286282306163e-05, 'epoch': 0.32}
{'loss': 0.7018, 'learning_rate': 2.5225917223929153e-05, 'epoch': 0.32}
{'loss': 0.9371, 'learning_rate': 2.5223206217242002e-05, 'epoch': 0.32}
{'loss': 0.7286, 'learning_rate': 2.5220495210554854e-05, 'epoch': 0.32}
{'loss': 0.9994, 'learning_rate': 2.5217784203867705e-05, 'epoch': 0.32}
{'loss': 0.9026, 'learning_rate': 2.5215073197180554e-05, 'epoch': 0.32}
{'loss': 1.7586, 'learning_rate': 2.5212362190493406e-05, 'epoch': 0.32}
{'loss': 0.861, 'learning_rate': 2.5209651183806254e-05, 'epoch': 0.32}
{'loss': 1.1644, 'learning_rate': 2.5206940177119103e-05, 'epoch': 0.32}
{'loss': 1.5825, 'learning_rate': 2.5204229170431954e-05, 'epoch': 0.32}
{'loss': 1.3523, 'learning_rate': 2.5201518163744803e-05, 'epoch': 0.32}
{'loss': 0.9715, 'learning_rate': 2.5198807157057655e-05, 'epoch': 0.32}
{'loss': 1.0266, 'learning_rate': 2.5196096150370506e-05, 'epoch': 0.32}
{'loss': 1.2442, 'learning_rate': 2.5193385143683355e-05, 'epoch': 0.32}
{'loss': 2.3621, 'learning_rate': 2.5190674136996207e-05, 'epoch': 0.32}
{'loss': 0.8689, 'learning_rate': 2.5187963130309055e-05, 'epoch': 0.32}
{'loss': 1.8434, 'learning_rate': 2.5185252123621904e-05, 'epoch': 0.32}
{'loss': 0.9996, 'learning_rate': 2.5182541116934755e-05, 'epoch': 0.32}
{'loss': 1.288, 'learning_rate': 2.5179830110247607e-05, 'epoch': 0.32}
{'loss': 1.5558, 'learning_rate': 2.5177119103560456e-05, 'epoch': 0.32}
{'loss': 1.1983, 'learning_rate': 2.5174408096873308e-05, 'epoch': 0.32}
{'loss': 1.3826, 'learning_rate': 2.5171697090186156e-05, 'epoch': 0.32}
{'loss': 1.9589, 'learning_rate': 2.5168986083499008e-05, 'epoch': 0.32}
{'loss': 1.5072, 'learning_rate': 2.5166275076811856e-05, 'epoch': 0.32}
{'loss': 0.6025, 'learning_rate': 2.5163564070124705e-05, 'epoch': 0.32}
{'loss': 1.1238, 'learning_rate': 2.5160853063437557e-05, 'epoch': 0.32}
{'loss': 1.1352, 'learning_rate': 2.515814205675041e-05, 'epoch': 0.32}
{'loss': 1.4418, 'learning_rate': 2.5155431050063257e-05, 'epoch': 0.32}
{'loss': 1.3233, 'learning_rate': 2.515272004337611e-05, 'epoch': 0.32}
{'loss': 1.716, 'learning_rate': 2.515000903668896e-05, 'epoch': 0.32}
{'loss': 0.7926, 'learning_rate': 2.514729803000181e-05, 'epoch': 0.32}
{'loss': 1.8319, 'learning_rate': 2.5144587023314657e-05, 'epoch': 0.32}
{'loss': 1.8259, 'learning_rate': 2.514187601662751e-05, 'epoch': 0.32}
{'loss': 1.1833, 'learning_rate': 2.5139165009940358e-05, 'epoch': 0.32}
{'loss': 1.5688, 'learning_rate': 2.513645400325321e-05, 'epoch': 0.32}
{'loss': 0.8188, 'learning_rate': 2.5133742996566058e-05, 'epoch': 0.32}
{'loss': 0.8866, 'learning_rate': 2.513103198987891e-05, 'epoch': 0.32}
{'loss': 0.9267, 'learning_rate': 2.512832098319176e-05, 'epoch': 0.32}
{'loss': 1.5288, 'learning_rate': 2.512560997650461e-05, 'epoch': 0.32}
{'loss': 1.4252, 'learning_rate': 2.512289896981746e-05, 'epoch': 0.33}
{'loss': 0.9417, 'learning_rate': 2.512018796313031e-05, 'epoch': 0.33}

 16%|█▋        | 1801/11066 [06:36<34:48,  4.44it/s]
 16%|█▋        | 1802/11066 [06:36<34:43,  4.45it/s]
                                                    

 16%|█▋        | 1802/11066 [06:36<34:43,  4.45it/s]
 16%|█▋        | 1803/11066 [06:37<34:37,  4.46it/s]
                                                    

 16%|█▋        | 1803/11066 [06:37<34:37,  4.46it/s]
 16%|█▋        | 1804/11066 [06:37<34:35,  4.46it/s]
                                                    

 16%|█▋        | 1804/11066 [06:37<34:35,  4.46it/s]
 16%|█▋        | 1805/11066 [06:37<34:24,  4.49it/s]
                                                    

 16%|█▋        | 1805/11066 [06:37<34:24,  4.49it/s]
 16%|█▋        | 1806/11066 [06:37<34:24,  4.49it/s]
                                                    

 16%|█▋        | 1806/11066 [06:37<34:24,  4.49it/s]
 16%|█▋        | 1807/11066 [06:37<34:50,  4.43it/s]
                                                    

 16%|█▋        | 1807/11066 [06:37<34:50,  4.43it/s]
 16%|█▋        | 1808/11066 [06:38<34:46,  4.44it/s]
                                                    

 16%|█▋        | 1808/11066 [06:38<34:46,  4.44it/s]
 16%|█▋        | 1809/11066 [06:38<35:06,  4.39it/s]
                                                    

 16%|█▋        | 1809/11066 [06:38<35:06,  4.39it/s]
 16%|█▋        | 1810/11066 [06:38<34:52,  4.42it/s]
                                                    

 16%|█▋        | 1810/11066 [06:38<34:52,  4.42it/s]
 16%|█▋        | 1811/11066 [06:38<34:44,  4.44it/s]
                                                    

 16%|█▋        | 1811/11066 [06:38<34:44,  4.44it/s]
 16%|█▋        | 1812/11066 [06:39<34:37,  4.45it/s]
                                                    

 16%|█▋        | 1812/11066 [06:39<34:37,  4.45it/s]
 16%|█▋        | 1813/11066 [06:39<34:31,  4.47it/s]
                                                    

 16%|█▋        | 1813/11066 [06:39<34:31,  4.47it/s]
 16%|█▋        | 1814/11066 [06:39<34:27,  4.48it/s]
                                                    

 16%|█▋        | 1814/11066 [06:39<34:27,  4.48it/s]
 16%|█▋        | 1815/11066 [06:39<34:23,  4.48it/s]
                                                    

 16%|█▋        | 1815/11066 [06:39<34:23,  4.48it/s]
 16%|█▋        | 1816/11066 [06:39<34:18,  4.49it/s]
                                                    

 16%|█▋        | 1816/11066 [06:39<34:18,  4.49it/s]
 16%|█▋        | 1817/11066 [06:40<34:18,  4.49it/s]
                                                    

 16%|█▋        | 1817/11066 [06:40<34:18,  4.49it/s]
 16%|█▋        | 1818/11066 [06:40<34:15,  4.50it/s]
                                                    

 16%|█▋        | 1818/11066 [06:40<34:15,  4.50it/s]
 16%|█▋        | 1819/11066 [06:40<34:15,  4.50it/s]
                                                    

 16%|█▋        | 1819/11066 [06:40<34:15,  4.50it/s]
 16%|█▋        | 1820/11066 [06:40<34:14,  4.50it/s]
                                                    

 16%|█▋        | 1820/11066 [06:40<34:14,  4.50it/s]
 16%|█▋        | 1821/11066 [06:41<34:14,  4.50it/s]
                                                    

 16%|█▋        | 1821/11066 [06:41<34:14,  4.50it/s]
 16%|█▋        | 1822/11066 [06:41<34:17,  4.49it/s]
                                                    

 16%|█▋        | 1822/11066 [06:41<34:17,  4.49it/s]
 16%|█▋        | 1823/11066 [06:41<34:16,  4.49it/s]
                                                    

 16%|█▋        | 1823/11066 [06:41<34:16,  4.49it/s]
 16%|█▋        | 1824/11066 [06:41<34:19,  4.49it/s]
                                                    

 16%|█▋        | 1824/11066 [06:41<34:19,  4.49it/s]
 16%|█▋        | 1825/11066 [06:41<34:12,  4.50it/s]
                                                    

 16%|█▋        | 1825/11066 [06:41<34:12,  4.50it/s]
 17%|█▋        | 1826/11066 [06:42<34:14,  4.50it/s]
                                                    

 17%|█▋        | 1826/11066 [06:42<34:14,  4.50it/s]
 17%|█▋        | 1827/11066 [06:42<34:20,  4.48it/s]
                                                    

 17%|█▋        | 1827/11066 [06:42<34:20,  4.48it/s]
 17%|█▋        | 1828/11066 [06:42<34:27,  4.47it/s]
                                                    

 17%|█▋        | 1828/11066 [06:42<34:27,  4.47it/s]
 17%|█▋        | 1829/11066 [06:42<34:25,  4.47it/s]
                                                    

 17%|█▋        | 1829/11066 [06:42<34:25,  4.47it/s]
 17%|█▋        | 1830/11066 [06:43<34:21,  4.48it/s]
                                                    

 17%|█▋        | 1830/11066 [06:43<34:21,  4.48it/s]
 17%|█▋        | 1831/11066 [06:43<34:18,  4.49it/s]
                                                    

 17%|█▋        | 1831/11066 [06:43<34:18,  4.49it/s]
 17%|█▋        | 1832/11066 [06:43<34:16,  4.49it/s]
                                                    

 17%|█▋        | 1832/11066 [06:43<34:16,  4.49it/s]
 17%|█▋        | 1833/11066 [06:43<34:13,  4.50it/s]
                                                    

 17%|█▋        | 1833/11066 [06:43<34:13,  4.50it/s]
 17%|█▋        | 1834/11066 [06:43<34:13,  4.50it/s]
                                                    

 17%|█▋        | 1834/11066 [06:43<34:13,  4.50it/s]
 17%|█▋        | 1835/11066 [06:44<34:11,  4.50it/s]
                                                    

 17%|█▋        | 1835/11066 [06:44<34:11,  4.50it/s]
 17%|█▋        | 1836/11066 [06:44<34:09,  4.50it/s]
                                                    

 17%|█▋        | 1836/11066 [06:44<34:09,  4.50it/s]
 17%|█▋        | 1837/11066 [06:44<34:10,  4.50it/s]
                                                    

 17%|█▋        | 1837/11066 [06:44<34:10,  4.50it/s]
 17%|█▋        | 1838/11066 [06:44<34:09,  4.50it/s]
                                                    

 17%|█▋        | 1838/11066 [06:44<34:09,  4.50it/s]
 17%|█▋        | 1839/11066 [06:45<34:09,  4.50it/s]
                                                    

 17%|█▋        | 1839/11066 [06:45<34:09,  4.50it/s]
 17%|█▋        | 1840/11066 [06:45<34:10,  4.50it/s]
                                                    

 17%|█▋        | 1840/11066 [06:45<34:10,  4.50it/s]
 17%|█▋        | 1841/11066 [06:45<34:07,  4.51it/s]
                                                    

 17%|█▋        | 1841/11066 [06:45<34:07,  4.51it/s]
 17%|█▋        | 1842/11066 [06:45<34:08,  4.50it/s]
                                                    

 17%|█▋        | 1842/11066 [06:45<34:08,  4.50it/s]
 17%|█▋        | 1843/11066 [06:45<34:06,  4.51it/s]
                                                    

 17%|█▋        | 1843/11066 [06:45<34:06,  4.51it/s]
 17%|█▋        | 1844/11066 [06:46<34:07,  4.50it/s]
                                                    

 17%|█▋        | 1844/11066 [06:46<34:07,  4.50it/s]
 17%|█▋        | 1845/11066 [06:46<34:08,  4.50it/s]
                                                    

 17%|█▋        | 1845/11066 [06:46<34:08,  4.50it/s]
 17%|█▋        | 1846/11066 [06:46<34:08,  4.50it/s]
                                                    

 17%|█▋        | 1846/11066 [06:46<34:08,  4.50it/s]
 17%|█▋        | 1847/11066 [06:46<34:07,  4.50it/s]
                                                    

 17%|█▋        | 1847/11066 [06:46<34:07,  4.50it/s]
 17%|█▋        | 1848/11066 [06:47<34:07,  4.50it/s]
                                                    

 17%|█▋        | 1848/11066 [06:47<34:07,  4.50it/s]
 17%|█▋        | 1849/11066 [06:47<34:06,  4.50it/s]
                                                    

 17%|█▋        | 1849/11066 [06:47<34:06,  4.50it/s]
 17%|█▋        | 1850/11066 [06:47<34:07,  4.50it/s]
                                                    

 17%|█▋        | 1850/11066 [06:47<34:07,  4.50it/s]
 17%|█▋        | 1851/11066 [06:47<34:07,  4.50it/s]
                                                    

 17%|█▋        | 1851/11066 [06:47<34:07,  4.50it/s]
 17%|█▋        | 1852/11066 [06:47<34:05,  4.50it/s]
                                                    

 17%|█▋        | 1852/11066 [06:47<34:05,  4.50it/s]
 17%|█▋        | 1853/11066 [06:48<34:03,  4.51it/s]
                                                    

 17%|█▋        | 1853/11066 [06:48<34:03,  4.51it/s]
 17%|█▋        | 1854/11066 [06:48<34:04,  4.51it/s]
                                                    

 17%|█▋        | 1854/11066 [06:48<34:04,  4.51it/s]
 17%|█▋        | 1855/11066 [06:48<34:05,  4.50it/s]
                                                    

 17%|█▋        | 1855/11066 [06:48<34:05,  4.50it/s]
 17%|█▋        | 1856/11066 [06:48<34:39,  4.43it/s]
                                                    

 17%|█▋        | 1856/11066 [06:48<34:39,  4.43it/s]
 17%|█▋        | 1857/11066 [06:49<34:38,  4.43it/s]
                                                    

 17%|█▋        | 1857/11066 [06:49<34:38,  4.43it/s]
 17%|█▋        | 1858/11066 [06:49<34:34,  4.44it/s]
                                                    

 17%|█▋        | 1858/11066 [06:49<34:34,  4.44it/s]
 17%|█▋        | 1859/11066 [06:49<34:29,  4.45it/s]
                                                    

 17%|█▋        | 1859/11066 [06:49<34:29,  4.45it/s]
 17%|█▋        | 1860/11066 [06:49<34:21,  4.47it/s]
                                                    

 17%|█▋        | 1860/11066 [06:49<34:21,  4.47it/s]
 17%|█▋        | 1861/11066 [06:49<34:16,  4.47it/s]
                                                    

 17%|█▋        | 1861/11066 [06:49<34:16,  4.47it/s]
 17%|█▋        | 1862/11066 [06:50<34:11,  4.49it/s]
                                                    

 17%|█▋        | 1862/11066 [06:50<34:11,  4.49it/s]
 17%|█▋        | 1863/11066 [06:50<34:10,  4.49it/s]
                                                    

 17%|█▋        | 1863/11066 [06:50<34:10,  4.49it/s]
 17%|█▋        | 1864/11066 [06:50<34:10,  4.49it/s]
                                                    

 17%|█▋        | 1864/11066 [06:50<34:10,  4.49it/s]
 17%|█▋        | 1865/11066 [06:50<34:07,  4.49it/s]
                                                    

 17%|█▋        | 1865/11066 [06:50<34:07,  4.49it/s]
 17%|█▋        | 1866/11066 [06:51<34:06,  4.50it/s]
                                                    

 17%|█▋        | 1866/11066 [06:51<34:06,  4.50it/s]
 17%|█▋        | 1867/11066 [06:51<34:03,  4.50it/s]
                                                    

 17%|█▋        | 1867/11066 [06:51<34:03,  4.50it/s]
 17%|█▋        | 1868/11066 [06:51<34:02,  4.50it/s]
                                                    

 17%|█▋        | 1868/11066 [06:51<34:02,  4.50it/s]
 17%|█▋        | 1869/11066 [06:51<34:03,  4.50it/s]
                                                    

 17%|█▋        | 1869/11066 [06:51<34:03,  4.50it/s]
 17%|█▋        | 1870/11066 [06:51<33:49,  4.53it/s]
                                                    

 17%|█▋        | 1870/11066 [06:51<33:49,  4.53it/s]
 17%|█▋        | 1871/11066 [06:52<34:00,  4.51it/s]
                                                    

 17%|█▋        | 1871/11066 [06:52<34:00,  4.51it/s]
 17%|█▋        | 1872/11066 [06:52<34:03,  4.50it/s]
                                                    

 17%|█▋        | 1872/11066 [06:52<34:03,  4.50it/s]
 17%|█▋        | 1873/11066 [06:52<34:02,  4.50it/s]
                                                    

 17%|█▋        | 1873/11066 [06:52<34:02,  4.50it/s]
 17%|█▋        | 1874/11066 [06:52<34:00,  4.50it/s]
                                                    

 17%|█▋        | 1874/11066 [06:52<34:00,  4.50it/s]
 17%|█▋        | 1875/11066 [06:53<34:00,  4.50it/s]
                                                    

 17%|█▋        | 1875/11066 [06:53<34:00,  4.50it/s]
 17%|█▋        | 1876/11066 [06:53<34:01,  4.50it/s]
                                                    

 17%|█▋        | 1876/11066 [06:53<34:01,  4.50it/s]
 17%|█▋        | 1877/11066 [06:53<34:00,  4.50it/s]
                                                    

 17%|█▋        | 1877/11066 [06:53<34:00,  4.50it/s]
 17%|█▋        | 1878/11066 [06:53<34:01,  4.50it/s]
                                                    

 17%|█▋        | 1878/11066 [06:53<34:01,  4.50it/s]
 17%|█▋        | 1879/11066 [06:54<34:45,  4.41it/s]
                                                    

 17%|█▋        | 1879/11066 [06:54<34:45,  4.41it/s]
 17%|█▋        | 1880/11066 [06:54<35:02,  4.37it/s]
                                                    

 17%|█▋        | 1880/11066 [06:54<35:02,  4.37it/s]
 17%|█▋        | 1881/11066 [06:54<34:47,  4.40it/s]
                                                    

 17%|█▋        | 1881/11066 [06:54<34:47,  4.40it/s]
 17%|█▋        | 1882/11066 [06:54<34:33,  4.43it/s]
                                                    

 17%|█▋        | 1882/11066 [06:54<34:33,  4.43it/s]
 17%|█▋        | 1883/11066 [06:54<34:22,  4.45it/s]
                                                    

 17%|█▋        | 1883/11066 [06:54<34:22,  4.45it/s]
 17%|█▋        | 1884/11066 [06:55<34:16,  4.47it/s]
                                                    

 17%|█▋        | 1884/11066 [06:55<34:16,  4.47it/s]
 17%|█▋        | 1885/11066 [06:55<34:10,  4.48it/s]
                                                    

 17%|█▋        | 1885/11066 [06:55<34:10,  4.48it/s]
 17%|█▋        | 1886/11066 [06:55<34:06,  4.49it/s]
                                                    

 17%|█▋        | 1886/11066 [06:55<34:06,  4.49it/s]
 17%|█▋        | 1887/11066 [06:55<34:04,  4.49it/s]
                                                    

 17%|█▋        | 1887/11066 [06:55<34:04,  4.49it/s]
 17%|█▋        | 1888/11066 [06:56<34:02,  4.49it/s]
                                                    

 17%|█▋        | 1888/11066 [06:56<34:02,  4.49it/s]
 17%|█▋        | 1889/11066 [06:56<34:03,  4.49it/s]
                                                    

 17%|█▋        | 1889/11066 [06:56<34:03,  4.49it/s]
 17%|█▋        | 1890/11066 [06:56<33:59,  4.50it/s]
                                                    

 17%|█▋        | 1890/11066 [06:56<33:59,  4.50it/s]
 17%|█▋        | 1891/11066 [06:56<34:00,  4.50it/s]
                                                    

 17%|█▋        | 1891/11066 [06:56<34:00,  4.50it/s]
 17%|█▋        | 1892/11066 [06:56<34:01,  4.49it/s]
                                                    

 17%|█▋        | 1892/11066 [06:56<34:01,  4.49it/s]
 17%|█▋        | 1893/11066 [06:57<33:59,  4.50it/s]
                                                    

 17%|█▋        | 1893/11066 [06:57<33:59,  4.50it/s]
 17%|█▋        | 1894/11066 [06:57<33:59,  4.50it/s]
                                                    

 17%|█▋        | 1894/11066 [06:57<33:59,  4.50it/s]
 17%|█▋        | 1895/11066 [06:57<33:59,  4.50it/s]
                                                    

 17%|█▋        | 1895/11066 [06:57<33:59,  4.50it/s]
 17%|█▋        | 1896/11066 [06:57<33:57,  4.50it/s]
                                                    

 17%|█▋        | 1896/11066 [06:57<33:57,  4.50it/s]
 17%|█▋        | 1897/11066 [06:58<33:57,  4.50it/s]
                                                    

 17%|█▋        | 1897/11066 [06:58<33:57,  4.50it/s]
 17%|█▋        | 1898/11066 [06:58<33:57,  4.50it/s]
                                                    

 17%|█▋        | 1898/11066 [06:58<33:57,  4.50it/s]
 17%|█▋        | 1899/11066 [06:58<33:54,  4.50it/s]
                                                    

 17%|█▋        | 1899/11066 [06:58<33:54,  4.50it/s]
 17%|█▋        | 1900/11066 [06:58<33:56,  4.50it/s]
                                                    

 17%|█▋        | 1900/11066 [06:58<33:56,  4.50it/s]
 17%|█▋        | 1901/11066 [06:58<33:54,  4.51it/s]
                                                    

 17%|█▋        | 1901/11066 [06:58<33:54,  4.51it/s]
 17%|█▋        | 1902/11066 [06:59<33:54,  4.50it/s]
                                                    

 17%|█▋        | 1902/11066 [06:59<33:54,  4.50it/s]
 17%|█▋        | 1903/11066 [06:59<33:55,  4.50it/s]
                                                    

 17%|█▋        | 1903/11066 [06:59<33:55,  4.50it/s]
 17%|█▋        | 1904/11066 [06:59<33:53,  4.51it/s]
                                                    

 17%|█▋        | 1904/11066 [06:59<33:53,  4.51it/s]
 17%|█▋        | 1905/11066 [06:59<33:54,  4.50it/s]
                                                    

 17%|█▋        | 1905/11066 [06:59<33:54,  4.50it/s]
 17%|█▋        | 1906/11066 [07:00<33:57,  4.50it/s]
                                                    

 17%|█▋        | 1906/11066 [07:00<33:57,  4.50it/s]
 17%|█▋        | 1907/11066 [07:00<33:56,  4.50it/s]
                                                    

 17%|█▋        | 1907/11066 [07:00<33:56,  4.50it/s]
 17%|█▋        | 1908/11066 [07:00<33:53,  4.50it/s]
                                                    

 17%|█▋        | 1908/11066 [07:00<33:53,  4.50it/s]
 17%|█▋        | 1909/11066 [07:00<33:52,  4.50it/s]
                                                    

 17%|█▋        | 1909/11066 [07:00<33:52,  4.50it/s]
 17%|█▋        | 1910/11066 [07:00<33:52,  4.50it/s]
                                                    

 17%|█▋        | 1910/11066 [07:00<33:52,  4.50it/s]
 17%|█▋        | 1911/11066 [07:01<33:53,  4.50it/s]
                                                    

 17%|█▋        | 1911/11066 [07:01<33:53,  4.50it/s]
 17%|█▋        | 1912/11066 [07:01<33:52,  4.50it/s]
                                                    

 17%|█▋        | 1912/11066 [07:01<33:52,  4.50it/s]
 17%|█▋        | 1913/11066 [07:01<33:51,  4.51it/s]
                                                    
{'loss': 1.5164, 'learning_rate': 2.511747695644316e-05, 'epoch': 0.33}
{'loss': 1.2536, 'learning_rate': 2.511476594975601e-05, 'epoch': 0.33}
{'loss': 1.2395, 'learning_rate': 2.5112054943068862e-05, 'epoch': 0.33}
{'loss': 1.0061, 'learning_rate': 2.510934393638171e-05, 'epoch': 0.33}
{'loss': 0.8089, 'learning_rate': 2.5106632929694563e-05, 'epoch': 0.33}
{'loss': 1.0337, 'learning_rate': 2.5103921923007408e-05, 'epoch': 0.33}
{'loss': 1.1836, 'learning_rate': 2.510121091632026e-05, 'epoch': 0.33}
{'loss': 1.5772, 'learning_rate': 2.509849990963311e-05, 'epoch': 0.33}
{'loss': 1.6714, 'learning_rate': 2.509578890294596e-05, 'epoch': 0.33}
{'loss': 0.7858, 'learning_rate': 2.509307789625881e-05, 'epoch': 0.33}
{'loss': 1.3068, 'learning_rate': 2.5090366889571663e-05, 'epoch': 0.33}
{'loss': 1.9102, 'learning_rate': 2.5087655882884512e-05, 'epoch': 0.33}
{'loss': 1.5618, 'learning_rate': 2.5084944876197364e-05, 'epoch': 0.33}
{'loss': 1.3727, 'learning_rate': 2.5082233869510212e-05, 'epoch': 0.33}
{'loss': 1.3484, 'learning_rate': 2.507952286282306e-05, 'epoch': 0.33}
{'loss': 1.3635, 'learning_rate': 2.5076811856135912e-05, 'epoch': 0.33}
{'loss': 1.1727, 'learning_rate': 2.507410084944876e-05, 'epoch': 0.33}
{'loss': 0.8225, 'learning_rate': 2.5071389842761613e-05, 'epoch': 0.33}
{'loss': 1.4039, 'learning_rate': 2.5068678836074464e-05, 'epoch': 0.33}
{'loss': 0.9442, 'learning_rate': 2.5065967829387313e-05, 'epoch': 0.33}
{'loss': 1.4311, 'learning_rate': 2.5063256822700165e-05, 'epoch': 0.33}
{'loss': 1.4734, 'learning_rate': 2.5060545816013013e-05, 'epoch': 0.33}
{'loss': 2.085, 'learning_rate': 2.505783480932586e-05, 'epoch': 0.33}
{'loss': 1.4116, 'learning_rate': 2.5055123802638713e-05, 'epoch': 0.33}
{'loss': 1.4294, 'learning_rate': 2.5052412795951565e-05, 'epoch': 0.33}
{'loss': 1.35, 'learning_rate': 2.5049701789264414e-05, 'epoch': 0.33}
{'loss': 0.953, 'learning_rate': 2.5046990782577266e-05, 'epoch': 0.33}
{'loss': 0.7535, 'learning_rate': 2.5044279775890114e-05, 'epoch': 0.33}
{'loss': 0.7802, 'learning_rate': 2.5041568769202966e-05, 'epoch': 0.33}
{'loss': 1.0053, 'learning_rate': 2.5038857762515814e-05, 'epoch': 0.33}
{'loss': 1.2801, 'learning_rate': 2.5036146755828663e-05, 'epoch': 0.33}
{'loss': 0.8092, 'learning_rate': 2.5033435749141515e-05, 'epoch': 0.33}
{'loss': 1.3808, 'learning_rate': 2.5030724742454366e-05, 'epoch': 0.33}
{'loss': 1.0823, 'learning_rate': 2.5028013735767215e-05, 'epoch': 0.33}
{'loss': 1.6902, 'learning_rate': 2.5025302729080067e-05, 'epoch': 0.33}
{'loss': 1.8357, 'learning_rate': 2.502259172239292e-05, 'epoch': 0.33}
{'loss': 1.1301, 'learning_rate': 2.5019880715705767e-05, 'epoch': 0.33}
{'loss': 1.5305, 'learning_rate': 2.5017169709018615e-05, 'epoch': 0.33}
{'loss': 0.8192, 'learning_rate': 2.5014458702331464e-05, 'epoch': 0.33}
{'loss': 1.0925, 'learning_rate': 2.5011747695644316e-05, 'epoch': 0.33}
{'loss': 1.7527, 'learning_rate': 2.5009036688957167e-05, 'epoch': 0.33}
{'loss': 0.8384, 'learning_rate': 2.5006325682270016e-05, 'epoch': 0.33}
{'loss': 1.0831, 'learning_rate': 2.5003614675582868e-05, 'epoch': 0.33}
{'loss': 1.1535, 'learning_rate': 2.500090366889572e-05, 'epoch': 0.33}
{'loss': 1.7578, 'learning_rate': 2.4998192662208568e-05, 'epoch': 0.33}
{'loss': 0.8481, 'learning_rate': 2.4995481655521416e-05, 'epoch': 0.33}
{'loss': 0.944, 'learning_rate': 2.4992770648834268e-05, 'epoch': 0.33}
{'loss': 1.9263, 'learning_rate': 2.4990059642147117e-05, 'epoch': 0.33}
{'loss': 1.0041, 'learning_rate': 2.498734863545997e-05, 'epoch': 0.33}
{'loss': 0.831, 'learning_rate': 2.4984637628772817e-05, 'epoch': 0.33}
{'loss': 1.4712, 'learning_rate': 2.498192662208567e-05, 'epoch': 0.33}
{'loss': 1.3355, 'learning_rate': 2.497921561539852e-05, 'epoch': 0.33}
{'loss': 1.2194, 'learning_rate': 2.497650460871137e-05, 'epoch': 0.33}
{'loss': 1.2598, 'learning_rate': 2.4973793602024217e-05, 'epoch': 0.34}
{'loss': 0.8445, 'learning_rate': 2.497108259533707e-05, 'epoch': 0.34}
{'loss': 1.2749, 'learning_rate': 2.4968371588649918e-05, 'epoch': 0.34}
{'loss': 1.2631, 'learning_rate': 2.496566058196277e-05, 'epoch': 0.34}
{'loss': 2.0738, 'learning_rate': 2.496294957527562e-05, 'epoch': 0.34}
{'loss': 0.7497, 'learning_rate': 2.496023856858847e-05, 'epoch': 0.34}
{'loss': 1.3969, 'learning_rate': 2.495752756190132e-05, 'epoch': 0.34}
{'loss': 1.1078, 'learning_rate': 2.495481655521417e-05, 'epoch': 0.34}
{'loss': 1.459, 'learning_rate': 2.495210554852702e-05, 'epoch': 0.34}
{'loss': 0.9606, 'learning_rate': 2.494939454183987e-05, 'epoch': 0.34}
{'loss': 0.9038, 'learning_rate': 2.494668353515272e-05, 'epoch': 0.34}
{'loss': 1.1814, 'learning_rate': 2.494397252846557e-05, 'epoch': 0.34}
{'loss': 1.0077, 'learning_rate': 2.4941261521778422e-05, 'epoch': 0.34}
{'loss': 0.9019, 'learning_rate': 2.493855051509127e-05, 'epoch': 0.34}
{'loss': 1.2856, 'learning_rate': 2.4935839508404123e-05, 'epoch': 0.34}
{'loss': 1.8335, 'learning_rate': 2.4933128501716975e-05, 'epoch': 0.34}
{'loss': 1.2818, 'learning_rate': 2.493041749502982e-05, 'epoch': 0.34}
{'loss': 1.4508, 'learning_rate': 2.492770648834267e-05, 'epoch': 0.34}
{'loss': 0.9881, 'learning_rate': 2.492499548165552e-05, 'epoch': 0.34}
{'loss': 1.6283, 'learning_rate': 2.4922284474968372e-05, 'epoch': 0.34}
{'loss': 1.4064, 'learning_rate': 2.4919573468281224e-05, 'epoch': 0.34}
{'loss': 1.5154, 'learning_rate': 2.4916862461594072e-05, 'epoch': 0.34}
{'loss': 1.9165, 'learning_rate': 2.4914151454906924e-05, 'epoch': 0.34}
{'loss': 0.9501, 'learning_rate': 2.4911440448219776e-05, 'epoch': 0.34}
{'loss': 1.3334, 'learning_rate': 2.490872944153262e-05, 'epoch': 0.34}
{'loss': 1.188, 'learning_rate': 2.4906018434845473e-05, 'epoch': 0.34}
{'loss': 1.4408, 'learning_rate': 2.4903307428158324e-05, 'epoch': 0.34}
{'loss': 1.4223, 'learning_rate': 2.4900596421471173e-05, 'epoch': 0.34}
{'loss': 1.0629, 'learning_rate': 2.4897885414784025e-05, 'epoch': 0.34}
{'loss': 1.4311, 'learning_rate': 2.4895174408096873e-05, 'epoch': 0.34}
{'loss': 0.9365, 'learning_rate': 2.4892463401409725e-05, 'epoch': 0.34}
{'loss': 1.1324, 'learning_rate': 2.4889752394722577e-05, 'epoch': 0.34}
{'loss': 0.9397, 'learning_rate': 2.4887041388035422e-05, 'epoch': 0.34}
{'loss': 1.3931, 'learning_rate': 2.4884330381348274e-05, 'epoch': 0.34}
{'loss': 1.2352, 'learning_rate': 2.4881619374661125e-05, 'epoch': 0.34}
{'loss': 1.5986, 'learning_rate': 2.4878908367973974e-05, 'epoch': 0.34}
{'loss': 0.7665, 'learning_rate': 2.4876197361286826e-05, 'epoch': 0.34}
{'loss': 1.2098, 'learning_rate': 2.4873486354599678e-05, 'epoch': 0.34}
{'loss': 0.7148, 'learning_rate': 2.4870775347912526e-05, 'epoch': 0.34}
{'loss': 1.4751, 'learning_rate': 2.4868064341225378e-05, 'epoch': 0.34}
{'loss': 0.6546, 'learning_rate': 2.4865353334538223e-05, 'epoch': 0.34}
{'loss': 1.4889, 'learning_rate': 2.4862642327851075e-05, 'epoch': 0.34}
{'loss': 1.3491, 'learning_rate': 2.4859931321163926e-05, 'epoch': 0.34}
{'loss': 1.8591, 'learning_rate': 2.4857220314476775e-05, 'epoch': 0.34}
{'loss': 0.7064, 'learning_rate': 2.4854509307789627e-05, 'epoch': 0.34}
{'loss': 1.6264, 'learning_rate': 2.485179830110248e-05, 'epoch': 0.34}
{'loss': 0.8073, 'learning_rate': 2.4849087294415327e-05, 'epoch': 0.34}
{'loss': 1.4424, 'learning_rate': 2.484637628772818e-05, 'epoch': 0.34}
{'loss': 1.2692, 'learning_rate': 2.4843665281041027e-05, 'epoch': 0.34}
{'loss': 0.9922, 'learning_rate': 2.4840954274353876e-05, 'epoch': 0.34}
{'loss': 1.2554, 'learning_rate': 2.4838243267666728e-05, 'epoch': 0.34}
{'loss': 1.3235, 'learning_rate': 2.4835532260979576e-05, 'epoch': 0.34}
{'loss': 1.294, 'learning_rate': 2.4832821254292428e-05, 'epoch': 0.34}
{'loss': 1.0946, 'learning_rate': 2.483011024760528e-05, 'epoch': 0.34}
{'loss': 0.7807, 'learning_rate': 2.4827399240918128e-05, 'epoch': 0.34}
{'loss': 1.0342, 'learning_rate': 2.482468823423098e-05, 'epoch': 0.35}
{'loss': 1.1477, 'learning_rate': 2.482197722754383e-05, 'epoch': 0.35}
{'loss': 1.551, 'learning_rate': 2.4819266220856677e-05, 'epoch': 0.35}
{'loss': 1.0227, 'learning_rate': 2.481655521416953e-05, 'epoch': 0.35}

 17%|█▋        | 1913/11066 [07:01<33:51,  4.51it/s]
 17%|█▋        | 1914/11066 [07:01<33:51,  4.51it/s]
                                                    

 17%|█▋        | 1914/11066 [07:01<33:51,  4.51it/s]
 17%|█▋        | 1915/11066 [07:02<33:51,  4.51it/s]
                                                    

 17%|█▋        | 1915/11066 [07:02<33:51,  4.51it/s]
 17%|█▋        | 1916/11066 [07:02<33:50,  4.51it/s]
                                                    

 17%|█▋        | 1916/11066 [07:02<33:50,  4.51it/s]
 17%|█▋        | 1917/11066 [07:02<33:50,  4.51it/s]
                                                    

 17%|█▋        | 1917/11066 [07:02<33:50,  4.51it/s]
 17%|█▋        | 1918/11066 [07:02<33:50,  4.51it/s]
                                                    

 17%|█▋        | 1918/11066 [07:02<33:50,  4.51it/s]
 17%|█▋        | 1919/11066 [07:02<33:52,  4.50it/s]
                                                    

 17%|█▋        | 1919/11066 [07:02<33:52,  4.50it/s]
 17%|█▋        | 1920/11066 [07:03<33:53,  4.50it/s]
                                                    

 17%|█▋        | 1920/11066 [07:03<33:53,  4.50it/s]
 17%|█▋        | 1921/11066 [07:03<33:57,  4.49it/s]
                                                    

 17%|█▋        | 1921/11066 [07:03<33:57,  4.49it/s]
 17%|█▋        | 1922/11066 [07:03<34:03,  4.47it/s]
                                                    

 17%|█▋        | 1922/11066 [07:03<34:03,  4.47it/s]
 17%|█▋        | 1923/11066 [07:03<34:03,  4.47it/s]
                                                    

 17%|█▋        | 1923/11066 [07:03<34:03,  4.47it/s]
 17%|█▋        | 1924/11066 [07:04<34:05,  4.47it/s]
                                                    

 17%|█▋        | 1924/11066 [07:04<34:05,  4.47it/s]
 17%|█▋        | 1925/11066 [07:04<34:00,  4.48it/s]
                                                    

 17%|█▋        | 1925/11066 [07:04<34:00,  4.48it/s]
 17%|█▋        | 1926/11066 [07:04<33:57,  4.49it/s]
                                                    

 17%|█▋        | 1926/11066 [07:04<33:57,  4.49it/s]
 17%|█▋        | 1927/11066 [07:04<33:55,  4.49it/s]
                                                    

 17%|█▋        | 1927/11066 [07:04<33:55,  4.49it/s]
 17%|█▋        | 1928/11066 [07:04<33:56,  4.49it/s]
                                                    

 17%|█▋        | 1928/11066 [07:04<33:56,  4.49it/s]
 17%|█▋        | 1929/11066 [07:05<33:55,  4.49it/s]
                                                    

 17%|█▋        | 1929/11066 [07:05<33:55,  4.49it/s]
 17%|█▋        | 1930/11066 [07:05<33:54,  4.49it/s]
                                                    

 17%|█▋        | 1930/11066 [07:05<33:54,  4.49it/s]
 17%|█▋        | 1931/11066 [07:05<33:56,  4.49it/s]
                                                    

 17%|█▋        | 1931/11066 [07:05<33:56,  4.49it/s]
 17%|█▋        | 1932/11066 [07:05<33:56,  4.48it/s]
                                                    

 17%|█▋        | 1932/11066 [07:05<33:56,  4.48it/s]
 17%|█▋        | 1933/11066 [07:06<33:57,  4.48it/s]
                                                    

 17%|█▋        | 1933/11066 [07:06<33:57,  4.48it/s]
 17%|█▋        | 1934/11066 [07:06<34:05,  4.46it/s]
                                                    

 17%|█▋        | 1934/11066 [07:06<34:05,  4.46it/s]
 17%|█▋        | 1935/11066 [07:06<34:06,  4.46it/s]
                                                    

 17%|█▋        | 1935/11066 [07:06<34:06,  4.46it/s]
 17%|█▋        | 1936/11066 [07:06<34:02,  4.47it/s]
                                                    

 17%|█▋        | 1936/11066 [07:06<34:02,  4.47it/s]
 18%|█▊        | 1937/11066 [07:06<33:58,  4.48it/s]
                                                    

 18%|█▊        | 1937/11066 [07:06<33:58,  4.48it/s]
 18%|█▊        | 1938/11066 [07:07<33:54,  4.49it/s]
                                                    

 18%|█▊        | 1938/11066 [07:07<33:54,  4.49it/s]
 18%|█▊        | 1939/11066 [07:07<33:52,  4.49it/s]
                                                    

 18%|█▊        | 1939/11066 [07:07<33:52,  4.49it/s]
 18%|█▊        | 1940/11066 [07:07<33:33,  4.53it/s]
                                                    

 18%|█▊        | 1940/11066 [07:07<33:33,  4.53it/s]
 18%|█▊        | 1941/11066 [07:07<33:45,  4.51it/s]
                                                    

 18%|█▊        | 1941/11066 [07:07<33:45,  4.51it/s]
 18%|█▊        | 1942/11066 [07:08<33:52,  4.49it/s]
                                                    

 18%|█▊        | 1942/11066 [07:08<33:52,  4.49it/s]
 18%|█▊        | 1943/11066 [07:08<33:53,  4.49it/s]
                                                    

 18%|█▊        | 1943/11066 [07:08<33:53,  4.49it/s]
 18%|█▊        | 1944/11066 [07:08<33:50,  4.49it/s]
                                                    

 18%|█▊        | 1944/11066 [07:08<33:50,  4.49it/s]
 18%|█▊        | 1945/11066 [07:08<33:49,  4.49it/s]
                                                    

 18%|█▊        | 1945/11066 [07:08<33:49,  4.49it/s]
 18%|█▊        | 1946/11066 [07:08<33:50,  4.49it/s]
                                                    

 18%|█▊        | 1946/11066 [07:08<33:50,  4.49it/s]
 18%|█▊        | 1947/11066 [07:09<33:52,  4.49it/s]
                                                    

 18%|█▊        | 1947/11066 [07:09<33:52,  4.49it/s]
 18%|█▊        | 1948/11066 [07:09<33:52,  4.49it/s]
                                                    

 18%|█▊        | 1948/11066 [07:09<33:52,  4.49it/s]
 18%|█▊        | 1949/11066 [07:09<33:50,  4.49it/s]
                                                    

 18%|█▊        | 1949/11066 [07:09<33:50,  4.49it/s]
 18%|█▊        | 1950/11066 [07:09<33:51,  4.49it/s]
                                                    

 18%|█▊        | 1950/11066 [07:09<33:51,  4.49it/s]
 18%|█▊        | 1951/11066 [07:10<33:48,  4.49it/s]
                                                    

 18%|█▊        | 1951/11066 [07:10<33:48,  4.49it/s]
 18%|█▊        | 1952/11066 [07:10<33:49,  4.49it/s]
                                                    

 18%|█▊        | 1952/11066 [07:10<33:49,  4.49it/s]
 18%|█▊        | 1953/11066 [07:10<33:48,  4.49it/s]
                                                    

 18%|█▊        | 1953/11066 [07:10<33:48,  4.49it/s]
 18%|█▊        | 1954/11066 [07:10<33:47,  4.49it/s]
                                                    

 18%|█▊        | 1954/11066 [07:10<33:47,  4.49it/s]
 18%|█▊        | 1955/11066 [07:10<33:46,  4.50it/s]
                                                    

 18%|█▊        | 1955/11066 [07:10<33:46,  4.50it/s]
 18%|█▊        | 1956/11066 [07:11<33:46,  4.50it/s]
                                                    

 18%|█▊        | 1956/11066 [07:11<33:46,  4.50it/s]
 18%|█▊        | 1957/11066 [07:11<33:44,  4.50it/s]
                                                    

 18%|█▊        | 1957/11066 [07:11<33:44,  4.50it/s]
 18%|█▊        | 1958/11066 [07:11<33:44,  4.50it/s]
                                                    

 18%|█▊        | 1958/11066 [07:11<33:44,  4.50it/s]
 18%|█▊        | 1959/11066 [07:11<33:44,  4.50it/s]
                                                    

 18%|█▊        | 1959/11066 [07:11<33:44,  4.50it/s]
 18%|█▊        | 1960/11066 [07:12<33:43,  4.50it/s]
                                                    

 18%|█▊        | 1960/11066 [07:12<33:43,  4.50it/s]
 18%|█▊        | 1961/11066 [07:12<33:28,  4.53it/s]
                                                    

 18%|█▊        | 1961/11066 [07:12<33:28,  4.53it/s]
 18%|█▊        | 1962/11066 [07:12<33:44,  4.50it/s]
                                                    

 18%|█▊        | 1962/11066 [07:12<33:44,  4.50it/s]
 18%|█▊        | 1963/11066 [07:12<33:47,  4.49it/s]
                                                    

 18%|█▊        | 1963/11066 [07:12<33:47,  4.49it/s]
 18%|█▊        | 1964/11066 [07:12<33:46,  4.49it/s]
                                                    

 18%|█▊        | 1964/11066 [07:12<33:46,  4.49it/s]
 18%|█▊        | 1965/11066 [07:13<33:45,  4.49it/s]
                                                    

 18%|█▊        | 1965/11066 [07:13<33:45,  4.49it/s]
 18%|█▊        | 1966/11066 [07:13<33:44,  4.50it/s]
                                                    

 18%|█▊        | 1966/11066 [07:13<33:44,  4.50it/s]
 18%|█▊        | 1967/11066 [07:13<33:41,  4.50it/s]
                                                    

 18%|█▊        | 1967/11066 [07:13<33:41,  4.50it/s]
 18%|█▊        | 1968/11066 [07:13<33:41,  4.50it/s]
                                                    

 18%|█▊        | 1968/11066 [07:13<33:41,  4.50it/s]
 18%|█▊        | 1969/11066 [07:14<33:39,  4.50it/s]
                                                    

 18%|█▊        | 1969/11066 [07:14<33:39,  4.50it/s]
 18%|█▊        | 1970/11066 [07:14<33:41,  4.50it/s]
                                                    

 18%|█▊        | 1970/11066 [07:14<33:41,  4.50it/s]
 18%|█▊        | 1971/11066 [07:14<33:41,  4.50it/s]
                                                    

 18%|█▊        | 1971/11066 [07:14<33:41,  4.50it/s]
 18%|█▊        | 1972/11066 [07:14<33:40,  4.50it/s]
                                                    

 18%|█▊        | 1972/11066 [07:14<33:40,  4.50it/s]
 18%|█▊        | 1973/11066 [07:14<33:39,  4.50it/s]
                                                    

 18%|█▊        | 1973/11066 [07:14<33:39,  4.50it/s]
 18%|█▊        | 1974/11066 [07:15<33:39,  4.50it/s]
                                                    

 18%|█▊        | 1974/11066 [07:15<33:39,  4.50it/s]
 18%|█▊        | 1975/11066 [07:15<33:47,  4.48it/s]
                                                    

 18%|█▊        | 1975/11066 [07:15<33:47,  4.48it/s]
 18%|█▊        | 1976/11066 [07:15<33:48,  4.48it/s]
                                                    

 18%|█▊        | 1976/11066 [07:15<33:48,  4.48it/s]
 18%|█▊        | 1977/11066 [07:15<33:54,  4.47it/s]
                                                    

 18%|█▊        | 1977/11066 [07:15<33:54,  4.47it/s]
 18%|█▊        | 1978/11066 [07:16<33:55,  4.46it/s]
                                                    

 18%|█▊        | 1978/11066 [07:16<33:55,  4.46it/s]
 18%|█▊        | 1979/11066 [07:16<33:54,  4.47it/s]
                                                    

 18%|█▊        | 1979/11066 [07:16<33:54,  4.47it/s]
 18%|█▊        | 1980/11066 [07:16<33:50,  4.47it/s]
                                                    

 18%|█▊        | 1980/11066 [07:16<33:50,  4.47it/s]
 18%|█▊        | 1981/11066 [07:16<33:48,  4.48it/s]
                                                    

 18%|█▊        | 1981/11066 [07:16<33:48,  4.48it/s]
 18%|█▊        | 1982/11066 [07:16<33:44,  4.49it/s]
                                                    

 18%|█▊        | 1982/11066 [07:16<33:44,  4.49it/s]
 18%|█▊        | 1983/11066 [07:17<33:41,  4.49it/s]
                                                    

 18%|█▊        | 1983/11066 [07:17<33:41,  4.49it/s]
 18%|█▊        | 1984/11066 [07:17<33:40,  4.49it/s]
                                                    

 18%|█▊        | 1984/11066 [07:17<33:40,  4.49it/s]
 18%|█▊        | 1985/11066 [07:17<33:39,  4.50it/s]
                                                    

 18%|█▊        | 1985/11066 [07:17<33:39,  4.50it/s]
 18%|█▊        | 1986/11066 [07:17<33:39,  4.50it/s]
                                                    

 18%|█▊        | 1986/11066 [07:17<33:39,  4.50it/s]
 18%|█▊        | 1987/11066 [07:18<33:38,  4.50it/s]
                                                    

 18%|█▊        | 1987/11066 [07:18<33:38,  4.50it/s]
 18%|█▊        | 1988/11066 [07:18<34:14,  4.42it/s]
                                                    

 18%|█▊        | 1988/11066 [07:18<34:14,  4.42it/s]
 18%|█▊        | 1989/11066 [07:18<34:13,  4.42it/s]
                                                    

 18%|█▊        | 1989/11066 [07:18<34:13,  4.42it/s]
 18%|█▊        | 1990/11066 [07:18<34:07,  4.43it/s]
                                                    

 18%|█▊        | 1990/11066 [07:18<34:07,  4.43it/s]
 18%|█▊        | 1991/11066 [07:18<34:00,  4.45it/s]
                                                    

 18%|█▊        | 1991/11066 [07:18<34:00,  4.45it/s]
 18%|█▊        | 1992/11066 [07:19<33:54,  4.46it/s]
                                                    

 18%|█▊        | 1992/11066 [07:19<33:54,  4.46it/s]
 18%|█▊        | 1993/11066 [07:19<33:47,  4.47it/s]
                                                    

 18%|█▊        | 1993/11066 [07:19<33:47,  4.47it/s]
 18%|█▊        | 1994/11066 [07:19<33:23,  4.53it/s]
                                                    

 18%|█▊        | 1994/11066 [07:19<33:23,  4.53it/s]
 18%|█▊        | 1995/11066 [07:19<33:13,  4.55it/s]
                                                    

 18%|█▊        | 1995/11066 [07:19<33:13,  4.55it/s]
 18%|█▊        | 1996/11066 [07:20<33:25,  4.52it/s]
                                                    

 18%|█▊        | 1996/11066 [07:20<33:25,  4.52it/s]
 18%|█▊        | 1997/11066 [07:20<33:32,  4.51it/s]
                                                    

 18%|█▊        | 1997/11066 [07:20<33:32,  4.51it/s]
 18%|█▊        | 1998/11066 [07:20<33:31,  4.51it/s]
                                                    

 18%|█▊        | 1998/11066 [07:20<33:31,  4.51it/s]
 18%|█▊        | 1999/11066 [07:20<33:32,  4.51it/s]
                                                    

 18%|█▊        | 1999/11066 [07:20<33:32,  4.51it/s]
 18%|█▊        | 2000/11066 [07:20<33:34,  4.50it/s]
                                                    

 18%|█▊        | 2000/11066 [07:20<33:34,  4.50it/s]
 18%|█▊        | 2001/11066 [07:21<33:32,  4.50it/s]
                                                    

 18%|█▊        | 2001/11066 [07:21<33:32,  4.50it/s]
 18%|█▊        | 2002/11066 [07:21<33:33,  4.50it/s]
                                                    

 18%|█▊        | 2002/11066 [07:21<33:33,  4.50it/s]
 18%|█▊        | 2003/11066 [07:21<33:21,  4.53it/s]
                                                    

 18%|█▊        | 2003/11066 [07:21<33:21,  4.53it/s]
 18%|█▊        | 2004/11066 [07:21<33:34,  4.50it/s]
                                                    

 18%|█▊        | 2004/11066 [07:21<33:34,  4.50it/s]
 18%|█▊        | 2005/11066 [07:22<33:36,  4.49it/s]
                                                    

 18%|█▊        | 2005/11066 [07:22<33:36,  4.49it/s]
 18%|█▊        | 2006/11066 [07:22<33:38,  4.49it/s]
                                                    

 18%|█▊        | 2006/11066 [07:22<33:38,  4.49it/s]
 18%|█▊        | 2007/11066 [07:22<33:46,  4.47it/s]
                                                    

 18%|█▊        | 2007/11066 [07:22<33:46,  4.47it/s]
 18%|█▊        | 2008/11066 [07:22<33:52,  4.46it/s]
                                                    

 18%|█▊        | 2008/11066 [07:22<33:52,  4.46it/s]
 18%|█▊        | 2009/11066 [07:22<33:51,  4.46it/s]
                                                    

 18%|█▊        | 2009/11066 [07:22<33:51,  4.46it/s]
 18%|█▊        | 2010/11066 [07:23<33:45,  4.47it/s]
                                                    

 18%|█▊        | 2010/11066 [07:23<33:45,  4.47it/s]
 18%|█▊        | 2011/11066 [07:23<33:41,  4.48it/s]
                                                    

 18%|█▊        | 2011/11066 [07:23<33:41,  4.48it/s]
 18%|█▊        | 2012/11066 [07:23<33:36,  4.49it/s]
                                                    

 18%|█▊        | 2012/11066 [07:23<33:36,  4.49it/s]
 18%|█▊        | 2013/11066 [07:23<33:34,  4.49it/s]
                                                    

 18%|█▊        | 2013/11066 [07:23<33:34,  4.49it/s]
 18%|█▊        | 2014/11066 [07:24<33:32,  4.50it/s]
                                                    

 18%|█▊        | 2014/11066 [07:24<33:32,  4.50it/s]
 18%|█▊        | 2015/11066 [07:24<33:32,  4.50it/s]
                                                    

 18%|█▊        | 2015/11066 [07:24<33:32,  4.50it/s]
 18%|█▊        | 2016/11066 [07:24<33:33,  4.50it/s]
                                                    

 18%|█▊        | 2016/11066 [07:24<33:33,  4.50it/s]
 18%|█▊        | 2017/11066 [07:24<33:46,  4.46it/s]
                                                    

 18%|█▊        | 2017/11066 [07:24<33:46,  4.46it/s]
 18%|█▊        | 2018/11066 [07:24<33:54,  4.45it/s]
                                                    

 18%|█▊        | 2018/11066 [07:24<33:54,  4.45it/s]
 18%|█▊        | 2019/11066 [07:25<33:47,  4.46it/s]
                                                    

 18%|█▊        | 2019/11066 [07:25<33:47,  4.46it/s]
 18%|█▊        | 2020/11066 [07:25<33:42,  4.47it/s]
                                                    

 18%|█▊        | 2020/11066 [07:25<33:42,  4.47it/s]
 18%|█▊        | 2021/11066 [07:25<33:38,  4.48it/s]
                                                    

 18%|█▊        | 2021/11066 [07:25<33:38,  4.48it/s]
 18%|█▊        | 2022/11066 [07:25<33:49,  4.46it/s]
                                                    

 18%|█▊        | 2022/11066 [07:25<33:49,  4.46it/s]
 18%|█▊        | 2023/11066 [07:26<33:50,  4.45it/s]
                                                    

 18%|█▊        | 2023/11066 [07:26<33:50,  4.45it/s]
 18%|█▊        | 2024/11066 [07:26<33:49,  4.46it/s]
                                                    

 18%|█▊        | 2024/11066 [07:26<33:49,  4.46it/s]
 18%|█▊        | 2025/11066 [07:26<33:42,  4.47it/s]
                                                    
{'loss': 1.0447, 'learning_rate': 2.481384420748238e-05, 'epoch': 0.35}
{'loss': 1.6264, 'learning_rate': 2.481113320079523e-05, 'epoch': 0.35}
{'loss': 1.4302, 'learning_rate': 2.480842219410808e-05, 'epoch': 0.35}
{'loss': 0.8095, 'learning_rate': 2.480571118742093e-05, 'epoch': 0.35}
{'loss': 1.5579, 'learning_rate': 2.480300018073378e-05, 'epoch': 0.35}
{'loss': 1.6211, 'learning_rate': 2.480028917404663e-05, 'epoch': 0.35}
{'loss': 1.3138, 'learning_rate': 2.4797578167359478e-05, 'epoch': 0.35}
{'loss': 1.6187, 'learning_rate': 2.479486716067233e-05, 'epoch': 0.35}
{'loss': 1.4486, 'learning_rate': 2.479215615398518e-05, 'epoch': 0.35}
{'loss': 0.8844, 'learning_rate': 2.478944514729803e-05, 'epoch': 0.35}
{'loss': 1.2516, 'learning_rate': 2.4786734140610882e-05, 'epoch': 0.35}
{'loss': 1.3925, 'learning_rate': 2.4784023133923734e-05, 'epoch': 0.35}
{'loss': 1.6536, 'learning_rate': 2.4781312127236582e-05, 'epoch': 0.35}
{'loss': 0.9204, 'learning_rate': 2.477860112054943e-05, 'epoch': 0.35}
{'loss': 1.4509, 'learning_rate': 2.477589011386228e-05, 'epoch': 0.35}
{'loss': 1.6333, 'learning_rate': 2.477317910717513e-05, 'epoch': 0.35}
{'loss': 1.5115, 'learning_rate': 2.4770468100487983e-05, 'epoch': 0.35}
{'loss': 1.1619, 'learning_rate': 2.476775709380083e-05, 'epoch': 0.35}
{'loss': 1.5214, 'learning_rate': 2.4765046087113683e-05, 'epoch': 0.35}
{'loss': 1.0447, 'learning_rate': 2.4762335080426535e-05, 'epoch': 0.35}
{'loss': 1.3267, 'learning_rate': 2.475962407373938e-05, 'epoch': 0.35}
{'loss': 1.6898, 'learning_rate': 2.475691306705223e-05, 'epoch': 0.35}
{'loss': 1.087, 'learning_rate': 2.4754202060365083e-05, 'epoch': 0.35}
{'loss': 0.5982, 'learning_rate': 2.4751491053677932e-05, 'epoch': 0.35}
{'loss': 0.9983, 'learning_rate': 2.4748780046990784e-05, 'epoch': 0.35}
{'loss': 0.9715, 'learning_rate': 2.4746069040303632e-05, 'epoch': 0.35}
{'loss': 2.1069, 'learning_rate': 2.4743358033616484e-05, 'epoch': 0.35}
{'loss': 0.8109, 'learning_rate': 2.4740647026929336e-05, 'epoch': 0.35}
{'loss': 0.8613, 'learning_rate': 2.473793602024218e-05, 'epoch': 0.35}
{'loss': 1.0206, 'learning_rate': 2.4735225013555033e-05, 'epoch': 0.35}
{'loss': 1.0283, 'learning_rate': 2.4732514006867885e-05, 'epoch': 0.35}
{'loss': 1.4938, 'learning_rate': 2.4729803000180733e-05, 'epoch': 0.35}
{'loss': 1.3322, 'learning_rate': 2.4727091993493585e-05, 'epoch': 0.35}
{'loss': 1.1452, 'learning_rate': 2.4724380986806437e-05, 'epoch': 0.35}
{'loss': 0.8256, 'learning_rate': 2.4721669980119285e-05, 'epoch': 0.35}
{'loss': 0.4273, 'learning_rate': 2.4718958973432137e-05, 'epoch': 0.35}
{'loss': 1.3966, 'learning_rate': 2.4716247966744985e-05, 'epoch': 0.35}
{'loss': 0.9004, 'learning_rate': 2.4713536960057834e-05, 'epoch': 0.35}
{'loss': 1.1062, 'learning_rate': 2.4710825953370686e-05, 'epoch': 0.35}
{'loss': 0.8992, 'learning_rate': 2.4708114946683534e-05, 'epoch': 0.35}
{'loss': 2.0131, 'learning_rate': 2.4705403939996386e-05, 'epoch': 0.35}
{'loss': 1.9976, 'learning_rate': 2.4702692933309238e-05, 'epoch': 0.35}
{'loss': 1.1143, 'learning_rate': 2.4699981926622086e-05, 'epoch': 0.35}
{'loss': 1.171, 'learning_rate': 2.4697270919934938e-05, 'epoch': 0.35}
{'loss': 0.5717, 'learning_rate': 2.4694559913247786e-05, 'epoch': 0.35}
{'loss': 1.2602, 'learning_rate': 2.4691848906560635e-05, 'epoch': 0.35}
{'loss': 1.1918, 'learning_rate': 2.4689137899873487e-05, 'epoch': 0.35}
{'loss': 1.4114, 'learning_rate': 2.468642689318634e-05, 'epoch': 0.35}
{'loss': 1.4456, 'learning_rate': 2.4683715886499187e-05, 'epoch': 0.35}
{'loss': 1.2482, 'learning_rate': 2.468100487981204e-05, 'epoch': 0.35}
{'loss': 1.1974, 'learning_rate': 2.4678293873124887e-05, 'epoch': 0.35}
{'loss': 0.7729, 'learning_rate': 2.467558286643774e-05, 'epoch': 0.35}
{'loss': 1.1815, 'learning_rate': 2.4672871859750587e-05, 'epoch': 0.36}
{'loss': 0.621, 'learning_rate': 2.4670160853063436e-05, 'epoch': 0.36}
{'loss': 1.7501, 'learning_rate': 2.4667449846376288e-05, 'epoch': 0.36}
{'loss': 1.8788, 'learning_rate': 2.466473883968914e-05, 'epoch': 0.36}
{'loss': 1.2313, 'learning_rate': 2.4662027833001988e-05, 'epoch': 0.36}
{'loss': 0.7143, 'learning_rate': 2.465931682631484e-05, 'epoch': 0.36}
{'loss': 1.354, 'learning_rate': 2.465660581962769e-05, 'epoch': 0.36}
{'loss': 0.9082, 'learning_rate': 2.465389481294054e-05, 'epoch': 0.36}
{'loss': 0.7762, 'learning_rate': 2.465118380625339e-05, 'epoch': 0.36}
{'loss': 1.7169, 'learning_rate': 2.4648472799566237e-05, 'epoch': 0.36}
{'loss': 1.0956, 'learning_rate': 2.464576179287909e-05, 'epoch': 0.36}
{'loss': 1.2026, 'learning_rate': 2.464305078619194e-05, 'epoch': 0.36}
{'loss': 0.9381, 'learning_rate': 2.464033977950479e-05, 'epoch': 0.36}
{'loss': 0.8769, 'learning_rate': 2.463762877281764e-05, 'epoch': 0.36}
{'loss': 1.2861, 'learning_rate': 2.4634917766130493e-05, 'epoch': 0.36}
{'loss': 0.968, 'learning_rate': 2.463220675944334e-05, 'epoch': 0.36}
{'loss': 1.3165, 'learning_rate': 2.462949575275619e-05, 'epoch': 0.36}
{'loss': 1.0459, 'learning_rate': 2.462678474606904e-05, 'epoch': 0.36}
{'loss': 0.776, 'learning_rate': 2.462407373938189e-05, 'epoch': 0.36}
{'loss': 0.8852, 'learning_rate': 2.4621362732694742e-05, 'epoch': 0.36}
{'loss': 1.4213, 'learning_rate': 2.461865172600759e-05, 'epoch': 0.36}
{'loss': 0.5337, 'learning_rate': 2.4615940719320442e-05, 'epoch': 0.36}
{'loss': 1.825, 'learning_rate': 2.4613229712633294e-05, 'epoch': 0.36}
{'loss': 0.8373, 'learning_rate': 2.4610518705946142e-05, 'epoch': 0.36}
{'loss': 1.1053, 'learning_rate': 2.460780769925899e-05, 'epoch': 0.36}
{'loss': 0.6605, 'learning_rate': 2.4605096692571843e-05, 'epoch': 0.36}
{'loss': 1.8019, 'learning_rate': 2.460238568588469e-05, 'epoch': 0.36}
{'loss': 1.4201, 'learning_rate': 2.4599674679197543e-05, 'epoch': 0.36}
{'loss': 1.0032, 'learning_rate': 2.4596963672510395e-05, 'epoch': 0.36}
{'loss': 1.6718, 'learning_rate': 2.4594252665823243e-05, 'epoch': 0.36}
{'loss': 2.1751, 'learning_rate': 2.4591541659136095e-05, 'epoch': 0.36}
{'loss': 1.2718, 'learning_rate': 2.4588830652448943e-05, 'epoch': 0.36}
{'loss': 0.9445, 'learning_rate': 2.4586119645761792e-05, 'epoch': 0.36}
{'loss': 0.8237, 'learning_rate': 2.4583408639074644e-05, 'epoch': 0.36}
{'loss': 1.0303, 'learning_rate': 2.4580697632387492e-05, 'epoch': 0.36}
{'loss': 1.4472, 'learning_rate': 2.4577986625700344e-05, 'epoch': 0.36}
{'loss': 1.5977, 'learning_rate': 2.4575275619013196e-05, 'epoch': 0.36}
{'loss': 2.1449, 'learning_rate': 2.4572564612326044e-05, 'epoch': 0.36}
{'loss': 1.0558, 'learning_rate': 2.4569853605638896e-05, 'epoch': 0.36}
{'loss': 1.9011, 'learning_rate': 2.4567142598951748e-05, 'epoch': 0.36}
{'loss': 0.8356, 'learning_rate': 2.4564431592264593e-05, 'epoch': 0.36}
{'loss': 1.0818, 'learning_rate': 2.4561720585577445e-05, 'epoch': 0.36}
{'loss': 0.78, 'learning_rate': 2.4559009578890293e-05, 'epoch': 0.36}
{'loss': 1.157, 'learning_rate': 2.4556298572203145e-05, 'epoch': 0.36}
{'loss': 0.8392, 'learning_rate': 2.4553587565515997e-05, 'epoch': 0.36}
{'loss': 1.2216, 'learning_rate': 2.4550876558828845e-05, 'epoch': 0.36}
{'loss': 1.4739, 'learning_rate': 2.4548165552141697e-05, 'epoch': 0.36}
{'loss': 1.0475, 'learning_rate': 2.454545454545455e-05, 'epoch': 0.36}
{'loss': 1.1236, 'learning_rate': 2.4542743538767394e-05, 'epoch': 0.36}
{'loss': 1.2995, 'learning_rate': 2.4540032532080246e-05, 'epoch': 0.36}
{'loss': 1.1659, 'learning_rate': 2.4537321525393098e-05, 'epoch': 0.36}
{'loss': 1.1664, 'learning_rate': 2.4534610518705946e-05, 'epoch': 0.36}
{'loss': 1.1078, 'learning_rate': 2.4531899512018798e-05, 'epoch': 0.36}
{'loss': 0.9977, 'learning_rate': 2.4529188505331646e-05, 'epoch': 0.36}
{'loss': 1.8178, 'learning_rate': 2.4526477498644498e-05, 'epoch': 0.36}
{'loss': 0.8057, 'learning_rate': 2.452376649195735e-05, 'epoch': 0.37}
{'loss': 1.3083, 'learning_rate': 2.4521055485270195e-05, 'epoch': 0.37}
{'loss': 1.5139, 'learning_rate': 2.4518344478583047e-05, 'epoch': 0.37}
{'loss': 1.5432, 'learning_rate': 2.45156334718959e-05, 'epoch': 0.37}
{'loss': 1.1899, 'learning_rate': 2.4512922465208747e-05, 'epoch': 0.37}

 18%|█▊        | 2025/11066 [07:26<33:42,  4.47it/s]
 18%|█▊        | 2026/11066 [07:26<33:41,  4.47it/s]
                                                    

 18%|█▊        | 2026/11066 [07:26<33:41,  4.47it/s]
 18%|█▊        | 2027/11066 [07:26<33:37,  4.48it/s]
                                                    

 18%|█▊        | 2027/11066 [07:26<33:37,  4.48it/s]
 18%|█▊        | 2028/11066 [07:27<33:35,  4.48it/s]
                                                    

 18%|█▊        | 2028/11066 [07:27<33:35,  4.48it/s]
 18%|█▊        | 2029/11066 [07:27<33:32,  4.49it/s]
                                                    

 18%|█▊        | 2029/11066 [07:27<33:32,  4.49it/s]
 18%|█▊        | 2030/11066 [07:27<33:30,  4.49it/s]
                                                    

 18%|█▊        | 2030/11066 [07:27<33:30,  4.49it/s]
 18%|█▊        | 2031/11066 [07:27<34:16,  4.39it/s]
                                                    

 18%|█▊        | 2031/11066 [07:27<34:16,  4.39it/s]
 18%|█▊        | 2032/11066 [07:28<34:08,  4.41it/s]
                                                    

 18%|█▊        | 2032/11066 [07:28<34:08,  4.41it/s]
 18%|█▊        | 2033/11066 [07:28<33:57,  4.43it/s]
                                                    

 18%|█▊        | 2033/11066 [07:28<33:57,  4.43it/s]
 18%|█▊        | 2034/11066 [07:28<33:48,  4.45it/s]
                                                    

 18%|█▊        | 2034/11066 [07:28<33:48,  4.45it/s]
 18%|█▊        | 2035/11066 [07:28<33:44,  4.46it/s]
                                                    

 18%|█▊        | 2035/11066 [07:28<33:44,  4.46it/s]
 18%|█▊        | 2036/11066 [07:29<33:40,  4.47it/s]
                                                    

 18%|█▊        | 2036/11066 [07:29<33:40,  4.47it/s]
 18%|█▊        | 2037/11066 [07:29<33:36,  4.48it/s]
                                                    

 18%|█▊        | 2037/11066 [07:29<33:36,  4.48it/s]
 18%|█▊        | 2038/11066 [07:29<33:33,  4.48it/s]
                                                    

 18%|█▊        | 2038/11066 [07:29<33:33,  4.48it/s]
 18%|█▊        | 2039/11066 [07:29<33:31,  4.49it/s]
                                                    

 18%|█▊        | 2039/11066 [07:29<33:31,  4.49it/s]
 18%|█▊        | 2040/11066 [07:29<33:28,  4.49it/s]
                                                    

 18%|█▊        | 2040/11066 [07:29<33:28,  4.49it/s]
 18%|█▊        | 2041/11066 [07:30<33:27,  4.50it/s]
                                                    

 18%|█▊        | 2041/11066 [07:30<33:27,  4.50it/s]
 18%|█▊        | 2042/11066 [07:30<33:26,  4.50it/s]
                                                    

 18%|█▊        | 2042/11066 [07:30<33:26,  4.50it/s]
 18%|█▊        | 2043/11066 [07:30<33:25,  4.50it/s]
                                                    

 18%|█▊        | 2043/11066 [07:30<33:25,  4.50it/s]
 18%|█▊        | 2044/11066 [07:30<33:25,  4.50it/s]
                                                    

 18%|█▊        | 2044/11066 [07:30<33:25,  4.50it/s]
 18%|█▊        | 2045/11066 [07:31<33:38,  4.47it/s]
                                                    

 18%|█▊        | 2045/11066 [07:31<33:38,  4.47it/s]
 18%|█▊        | 2046/11066 [07:31<34:14,  4.39it/s]
                                                    

 18%|█▊        | 2046/11066 [07:31<34:14,  4.39it/s]
 18%|█▊        | 2047/11066 [07:31<34:24,  4.37it/s]
                                                    

 18%|█▊        | 2047/11066 [07:31<34:24,  4.37it/s]
 19%|█▊        | 2048/11066 [07:31<34:06,  4.41it/s]
                                                    

 19%|█▊        | 2048/11066 [07:31<34:06,  4.41it/s]
 19%|█▊        | 2049/11066 [07:31<33:54,  4.43it/s]
                                                    

 19%|█▊        | 2049/11066 [07:31<33:54,  4.43it/s]
 19%|█▊        | 2050/11066 [07:32<33:43,  4.46it/s]
                                                    

 19%|█▊        | 2050/11066 [07:32<33:43,  4.46it/s]
 19%|█▊        | 2051/11066 [07:32<33:37,  4.47it/s]
                                                    

 19%|█▊        | 2051/11066 [07:32<33:37,  4.47it/s]
 19%|█▊        | 2052/11066 [07:32<33:31,  4.48it/s]
                                                    

 19%|█▊        | 2052/11066 [07:32<33:31,  4.48it/s]
 19%|█▊        | 2053/11066 [07:32<33:28,  4.49it/s]
                                                    

 19%|█▊        | 2053/11066 [07:32<33:28,  4.49it/s]
 19%|█▊        | 2054/11066 [07:33<33:26,  4.49it/s]
                                                    

 19%|█▊        | 2054/11066 [07:33<33:26,  4.49it/s]
 19%|█▊        | 2055/11066 [07:33<33:24,  4.50it/s]
                                                    

 19%|█▊        | 2055/11066 [07:33<33:24,  4.50it/s]
 19%|█▊        | 2056/11066 [07:33<33:26,  4.49it/s]
                                                    

 19%|█▊        | 2056/11066 [07:33<33:26,  4.49it/s]
 19%|█▊        | 2057/11066 [07:33<33:01,  4.55it/s]
                                                    

 19%|█▊        | 2057/11066 [07:33<33:01,  4.55it/s]
 19%|█▊        | 2058/11066 [07:33<32:59,  4.55it/s]
                                                    

 19%|█▊        | 2058/11066 [07:33<32:59,  4.55it/s]
 19%|█▊        | 2059/11066 [07:34<33:20,  4.50it/s]
                                                    

 19%|█▊        | 2059/11066 [07:34<33:20,  4.50it/s]
 19%|█▊        | 2060/11066 [07:34<33:34,  4.47it/s]
                                                    

 19%|█▊        | 2060/11066 [07:34<33:34,  4.47it/s]
 19%|█▊        | 2061/11066 [07:34<33:29,  4.48it/s]
                                                    

 19%|█▊        | 2061/11066 [07:34<33:29,  4.48it/s]
 19%|█▊        | 2062/11066 [07:34<33:25,  4.49it/s]
                                                    

 19%|█▊        | 2062/11066 [07:34<33:25,  4.49it/s]
 19%|█▊        | 2063/11066 [07:35<32:43,  4.59it/s]
                                                    

 19%|█▊        | 2063/11066 [07:35<32:43,  4.59it/s]
 19%|█▊        | 2064/11066 [07:35<33:02,  4.54it/s]
                                                    

 19%|█▊        | 2064/11066 [07:35<33:02,  4.54it/s]
 19%|█▊        | 2065/11066 [07:35<32:42,  4.59it/s]
                                                    

 19%|█▊        | 2065/11066 [07:35<32:42,  4.59it/s]
 19%|█▊        | 2066/11066 [07:35<32:52,  4.56it/s]
                                                    

 19%|█▊        | 2066/11066 [07:35<32:52,  4.56it/s]
 19%|█▊        | 2067/11066 [07:35<32:44,  4.58it/s]
                                                    

 19%|█▊        | 2067/11066 [07:35<32:44,  4.58it/s]
 19%|█▊        | 2068/11066 [07:36<33:03,  4.54it/s]
                                                    

 19%|█▊        | 2068/11066 [07:36<33:03,  4.54it/s]
 19%|█▊        | 2069/11066 [07:36<33:11,  4.52it/s]
                                                    

 19%|█▊        | 2069/11066 [07:36<33:11,  4.52it/s]
 19%|█▊        | 2070/11066 [07:36<33:15,  4.51it/s]
                                                    

 19%|█▊        | 2070/11066 [07:36<33:15,  4.51it/s]
 19%|█▊        | 2071/11066 [07:36<33:15,  4.51it/s]
                                                    

 19%|█▊        | 2071/11066 [07:36<33:15,  4.51it/s]
 19%|█▊        | 2072/11066 [07:37<33:16,  4.51it/s]
                                                    

 19%|█▊        | 2072/11066 [07:37<33:16,  4.51it/s]
 19%|█▊        | 2073/11066 [07:37<33:18,  4.50it/s]
                                                    

 19%|█▊        | 2073/11066 [07:37<33:18,  4.50it/s]
 19%|█▊        | 2074/11066 [07:37<33:18,  4.50it/s]
                                                    

 19%|█▊        | 2074/11066 [07:37<33:18,  4.50it/s]
 19%|█▉        | 2075/11066 [07:37<33:17,  4.50it/s]
                                                    

 19%|█▉        | 2075/11066 [07:37<33:17,  4.50it/s]
 19%|█▉        | 2076/11066 [07:37<33:16,  4.50it/s]
                                                    

 19%|█▉        | 2076/11066 [07:37<33:16,  4.50it/s]
 19%|█▉        | 2077/11066 [07:38<33:17,  4.50it/s]
                                                    

 19%|█▉        | 2077/11066 [07:38<33:17,  4.50it/s]
 19%|█▉        | 2078/11066 [07:38<33:18,  4.50it/s]
                                                    

 19%|█▉        | 2078/11066 [07:38<33:18,  4.50it/s]
 19%|█▉        | 2079/11066 [07:38<33:18,  4.50it/s]
                                                    

 19%|█▉        | 2079/11066 [07:38<33:18,  4.50it/s]
 19%|█▉        | 2080/11066 [07:38<33:17,  4.50it/s]
                                                    

 19%|█▉        | 2080/11066 [07:38<33:17,  4.50it/s]
 19%|█▉        | 2081/11066 [07:39<33:16,  4.50it/s]
                                                    

 19%|█▉        | 2081/11066 [07:39<33:16,  4.50it/s]
 19%|█▉        | 2082/11066 [07:39<33:15,  4.50it/s]
                                                    

 19%|█▉        | 2082/11066 [07:39<33:15,  4.50it/s]
 19%|█▉        | 2083/11066 [07:39<32:48,  4.56it/s]
                                                    

 19%|█▉        | 2083/11066 [07:39<32:48,  4.56it/s]
 19%|█▉        | 2084/11066 [07:39<32:43,  4.57it/s]
                                                    

 19%|█▉        | 2084/11066 [07:39<32:43,  4.57it/s]
 19%|█▉        | 2085/11066 [07:39<33:00,  4.53it/s]
                                                    

 19%|█▉        | 2085/11066 [07:39<33:00,  4.53it/s]
 19%|█▉        | 2086/11066 [07:40<32:38,  4.58it/s]
                                                    

 19%|█▉        | 2086/11066 [07:40<32:38,  4.58it/s]
 19%|█▉        | 2087/11066 [07:40<32:54,  4.55it/s]
                                                    

 19%|█▉        | 2087/11066 [07:40<32:54,  4.55it/s]
 19%|█▉        | 2088/11066 [07:40<33:00,  4.53it/s]
                                                    

 19%|█▉        | 2088/11066 [07:40<33:00,  4.53it/s]
 19%|█▉        | 2089/11066 [07:40<32:49,  4.56it/s]
                                                    

 19%|█▉        | 2089/11066 [07:40<32:49,  4.56it/s]
 19%|█▉        | 2090/11066 [07:40<32:35,  4.59it/s]
                                                    

 19%|█▉        | 2090/11066 [07:40<32:35,  4.59it/s]
 19%|█▉        | 2091/11066 [07:41<33:23,  4.48it/s]
                                                    

 19%|█▉        | 2091/11066 [07:41<33:23,  4.48it/s]
 19%|█▉        | 2092/11066 [07:41<32:53,  4.55it/s]
                                                    

 19%|█▉        | 2092/11066 [07:41<32:53,  4.55it/s]
 19%|█▉        | 2093/11066 [07:41<32:58,  4.54it/s]
                                                    

 19%|█▉        | 2093/11066 [07:41<32:58,  4.54it/s]
 19%|█▉        | 2094/11066 [07:41<33:02,  4.52it/s]
                                                    

 19%|█▉        | 2094/11066 [07:41<33:02,  4.52it/s]
 19%|█▉        | 2095/11066 [07:42<32:39,  4.58it/s]
                                                    

 19%|█▉        | 2095/11066 [07:42<32:39,  4.58it/s]
 19%|█▉        | 2096/11066 [07:42<32:49,  4.55it/s]
                                                    

 19%|█▉        | 2096/11066 [07:42<32:49,  4.55it/s]
 19%|█▉        | 2097/11066 [07:42<32:40,  4.57it/s]
                                                    

 19%|█▉        | 2097/11066 [07:42<32:40,  4.57it/s]
 19%|█▉        | 2098/11066 [07:42<32:15,  4.63it/s]
                                                    

 19%|█▉        | 2098/11066 [07:42<32:15,  4.63it/s]
 19%|█▉        | 2099/11066 [07:42<32:06,  4.65it/s]
                                                    

 19%|█▉        | 2099/11066 [07:42<32:06,  4.65it/s]
 19%|█▉        | 2100/11066 [07:43<32:12,  4.64it/s]
                                                    

 19%|█▉        | 2100/11066 [07:43<32:12,  4.64it/s]
 19%|█▉        | 2101/11066 [07:43<32:39,  4.58it/s]
                                                    

 19%|█▉        | 2101/11066 [07:43<32:39,  4.58it/s]
 19%|█▉        | 2102/11066 [07:43<32:43,  4.57it/s]
                                                    

 19%|█▉        | 2102/11066 [07:43<32:43,  4.57it/s]
 19%|█▉        | 2103/11066 [07:43<32:40,  4.57it/s]
                                                    

 19%|█▉        | 2103/11066 [07:43<32:40,  4.57it/s]
 19%|█▉        | 2104/11066 [07:44<32:54,  4.54it/s]
                                                    

 19%|█▉        | 2104/11066 [07:44<32:54,  4.54it/s]
 19%|█▉        | 2105/11066 [07:44<32:49,  4.55it/s]
                                                    

 19%|█▉        | 2105/11066 [07:44<32:49,  4.55it/s]
 19%|█▉        | 2106/11066 [07:44<32:21,  4.62it/s]
                                                    

 19%|█▉        | 2106/11066 [07:44<32:21,  4.62it/s]
 19%|█▉        | 2107/11066 [07:44<32:28,  4.60it/s]
                                                    

 19%|█▉        | 2107/11066 [07:44<32:28,  4.60it/s]
 19%|█▉        | 2108/11066 [07:44<32:31,  4.59it/s]
                                                    

 19%|█▉        | 2108/11066 [07:44<32:31,  4.59it/s]
 19%|█▉        | 2109/11066 [07:45<32:11,  4.64it/s]
                                                    

 19%|█▉        | 2109/11066 [07:45<32:11,  4.64it/s]
 19%|█▉        | 2110/11066 [07:45<32:13,  4.63it/s]
                                                    

 19%|█▉        | 2110/11066 [07:45<32:13,  4.63it/s]
 19%|█▉        | 2111/11066 [07:45<32:08,  4.64it/s]
                                                    

 19%|█▉        | 2111/11066 [07:45<32:08,  4.64it/s]
 19%|█▉        | 2112/11066 [07:45<32:31,  4.59it/s]
                                                    

 19%|█▉        | 2112/11066 [07:45<32:31,  4.59it/s]
 19%|█▉        | 2113/11066 [07:45<32:31,  4.59it/s]
                                                    

 19%|█▉        | 2113/11066 [07:45<32:31,  4.59it/s]
 19%|█▉        | 2114/11066 [07:46<32:27,  4.60it/s]
                                                    

 19%|█▉        | 2114/11066 [07:46<32:27,  4.60it/s]
 19%|█▉        | 2115/11066 [07:46<32:37,  4.57it/s]
                                                    

 19%|█▉        | 2115/11066 [07:46<32:37,  4.57it/s]
 19%|█▉        | 2116/11066 [07:46<32:53,  4.54it/s]
                                                    

 19%|█▉        | 2116/11066 [07:46<32:53,  4.54it/s]
 19%|█▉        | 2117/11066 [07:46<32:45,  4.55it/s]
                                                    

 19%|█▉        | 2117/11066 [07:46<32:45,  4.55it/s]
 19%|█▉        | 2118/11066 [07:47<32:49,  4.54it/s]
                                                    

 19%|█▉        | 2118/11066 [07:47<32:49,  4.54it/s]
 19%|█▉        | 2119/11066 [07:47<32:38,  4.57it/s]
                                                    

 19%|█▉        | 2119/11066 [07:47<32:38,  4.57it/s]
 19%|█▉        | 2120/11066 [07:47<32:49,  4.54it/s]
                                                    

 19%|█▉        | 2120/11066 [07:47<32:49,  4.54it/s]
 19%|█▉        | 2121/11066 [07:47<32:55,  4.53it/s]
                                                    

 19%|█▉        | 2121/11066 [07:47<32:55,  4.53it/s]
 19%|█▉        | 2122/11066 [07:47<32:58,  4.52it/s]
                                                    

 19%|█▉        | 2122/11066 [07:47<32:58,  4.52it/s]
 19%|█▉        | 2123/11066 [07:48<33:01,  4.51it/s]
                                                    

 19%|█▉        | 2123/11066 [07:48<33:01,  4.51it/s]
 19%|█▉        | 2124/11066 [07:48<32:48,  4.54it/s]
                                                    

 19%|█▉        | 2124/11066 [07:48<32:48,  4.54it/s]
 19%|█▉        | 2125/11066 [07:48<32:47,  4.55it/s]
                                                    

 19%|█▉        | 2125/11066 [07:48<32:47,  4.55it/s]
 19%|█▉        | 2126/11066 [07:48<32:23,  4.60it/s]
                                                    

 19%|█▉        | 2126/11066 [07:48<32:23,  4.60it/s]
 19%|█▉        | 2127/11066 [07:49<32:34,  4.57it/s]
                                                    

 19%|█▉        | 2127/11066 [07:49<32:34,  4.57it/s]
 19%|█▉        | 2128/11066 [07:49<32:44,  4.55it/s]
                                                    

 19%|█▉        | 2128/11066 [07:49<32:44,  4.55it/s]
 19%|█▉        | 2129/11066 [07:49<32:37,  4.57it/s]
                                                    

 19%|█▉        | 2129/11066 [07:49<32:37,  4.57it/s]
 19%|█▉        | 2130/11066 [07:49<33:24,  4.46it/s]
                                                    

 19%|█▉        | 2130/11066 [07:49<33:24,  4.46it/s]
 19%|█▉        | 2131/11066 [07:49<33:19,  4.47it/s]
                                                    

 19%|█▉        | 2131/11066 [07:49<33:19,  4.47it/s]
 19%|█▉        | 2132/11066 [07:50<33:14,  4.48it/s]
                                                    

 19%|█▉        | 2132/11066 [07:50<33:14,  4.48it/s]
 19%|█▉        | 2133/11066 [07:50<32:57,  4.52it/s]
                                                    

 19%|█▉        | 2133/11066 [07:50<32:57,  4.52it/s]
 19%|█▉        | 2134/11066 [07:50<33:07,  4.49it/s]
                                                    

 19%|█▉        | 2134/11066 [07:50<33:07,  4.49it/s]
 19%|█▉        | 2135/11066 [07:50<32:41,  4.55it/s]
                                                    

 19%|█▉        | 2135/11066 [07:50<32:41,  4.55it/s]
 19%|█▉        | 2136/11066 [07:51<32:51,  4.53it/s]
                                                    

 19%|█▉        | 2136/11066 [07:51<32:51,  4.53it/s]
 19%|█▉        | 2137/11066 [07:51<32:55,  4.52it/s]
                                                    
{'loss': 1.3049, 'learning_rate': 2.45102114585216e-05, 'epoch': 0.37}
{'loss': 1.4896, 'learning_rate': 2.450750045183445e-05, 'epoch': 0.37}
{'loss': 0.9359, 'learning_rate': 2.45047894451473e-05, 'epoch': 0.37}
{'loss': 0.8117, 'learning_rate': 2.450207843846015e-05, 'epoch': 0.37}
{'loss': 0.6928, 'learning_rate': 2.4499367431772996e-05, 'epoch': 0.37}
{'loss': 1.2503, 'learning_rate': 2.4496656425085848e-05, 'epoch': 0.37}
{'loss': 0.8414, 'learning_rate': 2.44939454183987e-05, 'epoch': 0.37}
{'loss': 1.2217, 'learning_rate': 2.4491234411711548e-05, 'epoch': 0.37}
{'loss': 1.1883, 'learning_rate': 2.44885234050244e-05, 'epoch': 0.37}
{'loss': 1.3894, 'learning_rate': 2.4485812398337252e-05, 'epoch': 0.37}
{'loss': 1.3068, 'learning_rate': 2.44831013916501e-05, 'epoch': 0.37}
{'loss': 1.2053, 'learning_rate': 2.4480390384962952e-05, 'epoch': 0.37}
{'loss': 0.9728, 'learning_rate': 2.44776793782758e-05, 'epoch': 0.37}
{'loss': 1.1762, 'learning_rate': 2.447496837158865e-05, 'epoch': 0.37}
{'loss': 1.3626, 'learning_rate': 2.44722573649015e-05, 'epoch': 0.37}
{'loss': 1.4571, 'learning_rate': 2.446954635821435e-05, 'epoch': 0.37}
{'loss': 1.3886, 'learning_rate': 2.44668353515272e-05, 'epoch': 0.37}
{'loss': 0.7049, 'learning_rate': 2.4464124344840053e-05, 'epoch': 0.37}
{'loss': 1.2077, 'learning_rate': 2.44614133381529e-05, 'epoch': 0.37}
{'loss': 1.4998, 'learning_rate': 2.4458702331465753e-05, 'epoch': 0.37}
{'loss': 1.0361, 'learning_rate': 2.44559913247786e-05, 'epoch': 0.37}
{'loss': 1.7911, 'learning_rate': 2.445328031809145e-05, 'epoch': 0.37}
{'loss': 1.1731, 'learning_rate': 2.4450569311404302e-05, 'epoch': 0.37}
{'loss': 1.0849, 'learning_rate': 2.4447858304717154e-05, 'epoch': 0.37}
{'loss': 0.9568, 'learning_rate': 2.4445147298030002e-05, 'epoch': 0.37}
{'loss': 0.8268, 'learning_rate': 2.4442436291342854e-05, 'epoch': 0.37}
{'loss': 1.7054, 'learning_rate': 2.4439725284655702e-05, 'epoch': 0.37}
{'loss': 1.0002, 'learning_rate': 2.4437014277968554e-05, 'epoch': 0.37}
{'loss': 1.7002, 'learning_rate': 2.4434303271281403e-05, 'epoch': 0.37}
{'loss': 1.0973, 'learning_rate': 2.443159226459425e-05, 'epoch': 0.37}
{'loss': 0.9582, 'learning_rate': 2.4428881257907103e-05, 'epoch': 0.37}
{'loss': 0.7233, 'learning_rate': 2.4426170251219955e-05, 'epoch': 0.37}
{'loss': 1.6023, 'learning_rate': 2.4423459244532803e-05, 'epoch': 0.37}
{'loss': 0.9085, 'learning_rate': 2.4420748237845655e-05, 'epoch': 0.37}
{'loss': 1.3297, 'learning_rate': 2.4418037231158507e-05, 'epoch': 0.37}
{'loss': 0.9637, 'learning_rate': 2.4415326224471352e-05, 'epoch': 0.37}
{'loss': 1.2127, 'learning_rate': 2.4412615217784204e-05, 'epoch': 0.37}
{'loss': 1.1051, 'learning_rate': 2.4409904211097052e-05, 'epoch': 0.37}
{'loss': 1.7339, 'learning_rate': 2.4407193204409904e-05, 'epoch': 0.37}
{'loss': 0.8813, 'learning_rate': 2.4404482197722756e-05, 'epoch': 0.37}
{'loss': 1.0552, 'learning_rate': 2.4401771191035604e-05, 'epoch': 0.37}
{'loss': 0.9388, 'learning_rate': 2.4399060184348456e-05, 'epoch': 0.37}
{'loss': 0.6764, 'learning_rate': 2.4396349177661308e-05, 'epoch': 0.37}
{'loss': 1.6658, 'learning_rate': 2.4393638170974153e-05, 'epoch': 0.37}
{'loss': 0.9085, 'learning_rate': 2.4390927164287005e-05, 'epoch': 0.37}
{'loss': 1.3377, 'learning_rate': 2.4388216157599857e-05, 'epoch': 0.37}
{'loss': 2.0475, 'learning_rate': 2.4385505150912705e-05, 'epoch': 0.37}
{'loss': 1.2374, 'learning_rate': 2.4382794144225557e-05, 'epoch': 0.37}
{'loss': 1.5758, 'learning_rate': 2.4380083137538405e-05, 'epoch': 0.37}
{'loss': 1.375, 'learning_rate': 2.4377372130851257e-05, 'epoch': 0.37}
{'loss': 1.3435, 'learning_rate': 2.437466112416411e-05, 'epoch': 0.38}
{'loss': 1.4027, 'learning_rate': 2.4371950117476954e-05, 'epoch': 0.38}
{'loss': 0.7623, 'learning_rate': 2.4369239110789806e-05, 'epoch': 0.38}
{'loss': 1.023, 'learning_rate': 2.4366528104102658e-05, 'epoch': 0.38}
{'loss': 1.1767, 'learning_rate': 2.4363817097415506e-05, 'epoch': 0.38}
{'loss': 1.054, 'learning_rate': 2.4361106090728358e-05, 'epoch': 0.38}
{'loss': 0.834, 'learning_rate': 2.435839508404121e-05, 'epoch': 0.38}
{'loss': 0.8116, 'learning_rate': 2.4355684077354058e-05, 'epoch': 0.38}
{'loss': 1.3115, 'learning_rate': 2.435297307066691e-05, 'epoch': 0.38}
{'loss': 1.5312, 'learning_rate': 2.435026206397976e-05, 'epoch': 0.38}
{'loss': 0.8192, 'learning_rate': 2.4347551057292607e-05, 'epoch': 0.38}
{'loss': 1.4844, 'learning_rate': 2.434484005060546e-05, 'epoch': 0.38}
{'loss': 1.4448, 'learning_rate': 2.4342129043918307e-05, 'epoch': 0.38}
{'loss': 0.7022, 'learning_rate': 2.433941803723116e-05, 'epoch': 0.38}
{'loss': 1.6559, 'learning_rate': 2.433670703054401e-05, 'epoch': 0.38}
{'loss': 1.5535, 'learning_rate': 2.433399602385686e-05, 'epoch': 0.38}
{'loss': 0.9177, 'learning_rate': 2.433128501716971e-05, 'epoch': 0.38}
{'loss': 1.4468, 'learning_rate': 2.432857401048256e-05, 'epoch': 0.38}
{'loss': 0.775, 'learning_rate': 2.4325863003795408e-05, 'epoch': 0.38}
{'loss': 1.4082, 'learning_rate': 2.432315199710826e-05, 'epoch': 0.38}
{'loss': 1.1325, 'learning_rate': 2.432044099042111e-05, 'epoch': 0.38}
{'loss': 1.365, 'learning_rate': 2.431772998373396e-05, 'epoch': 0.38}
{'loss': 0.9558, 'learning_rate': 2.4315018977046812e-05, 'epoch': 0.38}
{'loss': 1.0901, 'learning_rate': 2.431230797035966e-05, 'epoch': 0.38}
{'loss': 1.1875, 'learning_rate': 2.4309596963672512e-05, 'epoch': 0.38}
{'loss': 1.782, 'learning_rate': 2.430688595698536e-05, 'epoch': 0.38}
{'loss': 1.553, 'learning_rate': 2.430417495029821e-05, 'epoch': 0.38}
{'loss': 1.5362, 'learning_rate': 2.430146394361106e-05, 'epoch': 0.38}
{'loss': 1.2558, 'learning_rate': 2.4298752936923913e-05, 'epoch': 0.38}
{'loss': 0.7557, 'learning_rate': 2.429604193023676e-05, 'epoch': 0.38}
{'loss': 1.2201, 'learning_rate': 2.4293330923549613e-05, 'epoch': 0.38}
{'loss': 1.0287, 'learning_rate': 2.4290619916862465e-05, 'epoch': 0.38}
{'loss': 1.6101, 'learning_rate': 2.4287908910175313e-05, 'epoch': 0.38}
{'loss': 1.1532, 'learning_rate': 2.4285197903488162e-05, 'epoch': 0.38}
{'loss': 1.2248, 'learning_rate': 2.428248689680101e-05, 'epoch': 0.38}
{'loss': 0.7936, 'learning_rate': 2.4279775890113862e-05, 'epoch': 0.38}
{'loss': 1.074, 'learning_rate': 2.4277064883426714e-05, 'epoch': 0.38}
{'loss': 1.0821, 'learning_rate': 2.4274353876739562e-05, 'epoch': 0.38}
{'loss': 1.0698, 'learning_rate': 2.4271642870052414e-05, 'epoch': 0.38}
{'loss': 1.1504, 'learning_rate': 2.4268931863365266e-05, 'epoch': 0.38}
{'loss': 0.6582, 'learning_rate': 2.4266220856678114e-05, 'epoch': 0.38}
{'loss': 1.4718, 'learning_rate': 2.4263509849990963e-05, 'epoch': 0.38}
{'loss': 1.2342, 'learning_rate': 2.4260798843303815e-05, 'epoch': 0.38}
{'loss': 1.0043, 'learning_rate': 2.4258087836616663e-05, 'epoch': 0.38}
{'loss': 1.3158, 'learning_rate': 2.4255376829929515e-05, 'epoch': 0.38}
{'loss': 1.0514, 'learning_rate': 2.4252665823242363e-05, 'epoch': 0.38}
{'loss': 1.1588, 'learning_rate': 2.4249954816555215e-05, 'epoch': 0.38}
{'loss': 0.5303, 'learning_rate': 2.4247243809868067e-05, 'epoch': 0.38}
{'loss': 2.1307, 'learning_rate': 2.4244532803180915e-05, 'epoch': 0.38}
{'loss': 1.509, 'learning_rate': 2.4241821796493764e-05, 'epoch': 0.38}
{'loss': 1.0963, 'learning_rate': 2.4239110789806616e-05, 'epoch': 0.38}
{'loss': 1.2594, 'learning_rate': 2.4236399783119464e-05, 'epoch': 0.38}
{'loss': 1.8318, 'learning_rate': 2.4233688776432316e-05, 'epoch': 0.38}
{'loss': 1.2823, 'learning_rate': 2.4230977769745168e-05, 'epoch': 0.38}
{'loss': 1.0145, 'learning_rate': 2.4228266763058016e-05, 'epoch': 0.38}
{'loss': 1.3054, 'learning_rate': 2.4225555756370868e-05, 'epoch': 0.38}
{'loss': 0.8296, 'learning_rate': 2.4222844749683717e-05, 'epoch': 0.39}
{'loss': 1.0242, 'learning_rate': 2.4220133742996565e-05, 'epoch': 0.39}
{'loss': 0.5926, 'learning_rate': 2.4217422736309417e-05, 'epoch': 0.39}
{'loss': 1.2796, 'learning_rate': 2.4214711729622265e-05, 'epoch': 0.39}
{'loss': 1.6548, 'learning_rate': 2.4212000722935117e-05, 'epoch': 0.39}
{'loss': 1.6447, 'learning_rate': 2.420928971624797e-05, 'epoch': 0.39}
{'loss': 0.7154, 'learning_rate': 2.4206578709560817e-05, 'epoch': 0.39}
 19%|█▉        | 2137/11066 [07:51<32:55,  4.52it/s]
 19%|█▉        | 2138/11066 [07:51<32:59,  4.51it/s]
                                                    

 19%|█▉        | 2138/11066 [07:51<32:59,  4.51it/s]
 19%|█▉        | 2139/11066 [07:51<32:49,  4.53it/s]
                                                    

 19%|█▉        | 2139/11066 [07:51<32:49,  4.53it/s]
 19%|█▉        | 2140/11066 [07:51<32:59,  4.51it/s]
                                                    

 19%|█▉        | 2140/11066 [07:51<32:59,  4.51it/s]
 19%|█▉        | 2141/11066 [07:52<32:46,  4.54it/s]
                                                    

 19%|█▉        | 2141/11066 [07:52<32:46,  4.54it/s]
 19%|█▉        | 2142/11066 [07:52<32:36,  4.56it/s]
                                                    

 19%|█▉        | 2142/11066 [07:52<32:36,  4.56it/s]
 19%|█▉        | 2143/11066 [07:52<32:30,  4.57it/s]
                                                    

 19%|█▉        | 2143/11066 [07:52<32:30,  4.57it/s]
 19%|█▉        | 2144/11066 [07:52<32:27,  4.58it/s]
                                                    

 19%|█▉        | 2144/11066 [07:52<32:27,  4.58it/s]
 19%|█▉        | 2145/11066 [07:53<32:35,  4.56it/s]
                                                    

 19%|█▉        | 2145/11066 [07:53<32:35,  4.56it/s]
 19%|█▉        | 2146/11066 [07:53<32:20,  4.60it/s]
                                                    

 19%|█▉        | 2146/11066 [07:53<32:20,  4.60it/s]
 19%|█▉        | 2147/11066 [07:53<32:14,  4.61it/s]
                                                    

 19%|█▉        | 2147/11066 [07:53<32:14,  4.61it/s]
 19%|█▉        | 2148/11066 [07:53<32:33,  4.57it/s]
                                                    

 19%|█▉        | 2148/11066 [07:53<32:33,  4.57it/s]
 19%|█▉        | 2149/11066 [07:53<32:44,  4.54it/s]
                                                    

 19%|█▉        | 2149/11066 [07:53<32:44,  4.54it/s]
 19%|█▉        | 2150/11066 [07:54<32:33,  4.56it/s]
                                                    

 19%|█▉        | 2150/11066 [07:54<32:33,  4.56it/s]
 19%|█▉        | 2151/11066 [07:54<32:18,  4.60it/s]
                                                    

 19%|█▉        | 2151/11066 [07:54<32:18,  4.60it/s]
 19%|█▉        | 2152/11066 [07:54<32:39,  4.55it/s]
                                                    

 19%|█▉        | 2152/11066 [07:54<32:39,  4.55it/s]
 19%|█▉        | 2153/11066 [07:54<32:47,  4.53it/s]
                                                    

 19%|█▉        | 2153/11066 [07:54<32:47,  4.53it/s]
 19%|█▉        | 2154/11066 [07:55<32:25,  4.58it/s]
                                                    

 19%|█▉        | 2154/11066 [07:55<32:25,  4.58it/s]
 19%|█▉        | 2155/11066 [07:55<32:39,  4.55it/s]
                                                    

 19%|█▉        | 2155/11066 [07:55<32:39,  4.55it/s]
 19%|█▉        | 2156/11066 [07:55<32:18,  4.60it/s]
                                                    

 19%|█▉        | 2156/11066 [07:55<32:18,  4.60it/s]
 19%|█▉        | 2157/11066 [07:55<32:35,  4.56it/s]
                                                    

 19%|█▉        | 2157/11066 [07:55<32:35,  4.56it/s]
 20%|█▉        | 2158/11066 [07:55<32:32,  4.56it/s]
                                                    

 20%|█▉        | 2158/11066 [07:55<32:32,  4.56it/s]
 20%|█▉        | 2159/11066 [07:56<32:50,  4.52it/s]
                                                    

 20%|█▉        | 2159/11066 [07:56<32:50,  4.52it/s]
 20%|█▉        | 2160/11066 [07:56<32:43,  4.54it/s]
                                                    

 20%|█▉        | 2160/11066 [07:56<32:43,  4.54it/s]
 20%|█▉        | 2161/11066 [07:56<32:55,  4.51it/s]
                                                    

 20%|█▉        | 2161/11066 [07:56<32:55,  4.51it/s]
 20%|█▉        | 2162/11066 [07:56<32:45,  4.53it/s]
                                                    

 20%|█▉        | 2162/11066 [07:56<32:45,  4.53it/s]
 20%|█▉        | 2163/11066 [07:56<32:11,  4.61it/s]
                                                    

 20%|█▉        | 2163/11066 [07:56<32:11,  4.61it/s]
 20%|█▉        | 2164/11066 [07:57<32:28,  4.57it/s]
                                                    

 20%|█▉        | 2164/11066 [07:57<32:28,  4.57it/s]
 20%|█▉        | 2165/11066 [07:57<32:09,  4.61it/s]
                                                    

 20%|█▉        | 2165/11066 [07:57<32:09,  4.61it/s]
 20%|█▉        | 2166/11066 [07:57<32:24,  4.58it/s]
                                                    

 20%|█▉        | 2166/11066 [07:57<32:24,  4.58it/s]
 20%|█▉        | 2167/11066 [07:57<32:19,  4.59it/s]
                                                    

 20%|█▉        | 2167/11066 [07:57<32:19,  4.59it/s]
 20%|█▉        | 2168/11066 [07:58<32:11,  4.61it/s]
                                                    

 20%|█▉        | 2168/11066 [07:58<32:11,  4.61it/s]
 20%|█▉        | 2169/11066 [07:58<32:13,  4.60it/s]
                                                    

 20%|█▉        | 2169/11066 [07:58<32:13,  4.60it/s]
 20%|█▉        | 2170/11066 [07:58<31:51,  4.65it/s]
                                                    

 20%|█▉        | 2170/11066 [07:58<31:51,  4.65it/s]
 20%|█▉        | 2171/11066 [07:58<32:12,  4.60it/s]
                                                    

 20%|█▉        | 2171/11066 [07:58<32:12,  4.60it/s]
 20%|█▉        | 2172/11066 [07:58<32:28,  4.56it/s]
                                                    

 20%|█▉        | 2172/11066 [07:58<32:28,  4.56it/s]
 20%|█▉        | 2173/11066 [07:59<32:51,  4.51it/s]
                                                    

 20%|█▉        | 2173/11066 [07:59<32:51,  4.51it/s]
 20%|█▉        | 2174/11066 [07:59<33:27,  4.43it/s]
                                                    

 20%|█▉        | 2174/11066 [07:59<33:27,  4.43it/s]
 20%|█▉        | 2175/11066 [07:59<33:19,  4.45it/s]
                                                    

 20%|█▉        | 2175/11066 [07:59<33:19,  4.45it/s]
 20%|█▉        | 2176/11066 [07:59<33:12,  4.46it/s]
                                                    

 20%|█▉        | 2176/11066 [07:59<33:12,  4.46it/s]
 20%|█▉        | 2177/11066 [08:00<33:08,  4.47it/s]
                                                    

 20%|█▉        | 2177/11066 [08:00<33:08,  4.47it/s]
 20%|█▉        | 2178/11066 [08:00<32:40,  4.53it/s]
                                                    

 20%|█▉        | 2178/11066 [08:00<32:40,  4.53it/s]
 20%|█▉        | 2179/11066 [08:00<32:18,  4.58it/s]
                                                    

 20%|█▉        | 2179/11066 [08:00<32:18,  4.58it/s]
 20%|█▉        | 2180/11066 [08:00<32:17,  4.59it/s]
                                                    

 20%|█▉        | 2180/11066 [08:00<32:17,  4.59it/s]
 20%|█▉        | 2181/11066 [08:00<32:29,  4.56it/s]
                                                    

 20%|█▉        | 2181/11066 [08:00<32:29,  4.56it/s]
 20%|█▉        | 2182/11066 [08:01<32:36,  4.54it/s]
                                                    

 20%|█▉        | 2182/11066 [08:01<32:36,  4.54it/s]
 20%|█▉        | 2183/11066 [08:01<32:39,  4.53it/s]
                                                    

 20%|█▉        | 2183/11066 [08:01<32:39,  4.53it/s]
 20%|█▉        | 2184/11066 [08:01<32:26,  4.56it/s]
                                                    

 20%|█▉        | 2184/11066 [08:01<32:26,  4.56it/s]
 20%|█▉        | 2185/11066 [08:01<32:19,  4.58it/s]
                                                    

 20%|█▉        | 2185/11066 [08:01<32:19,  4.58it/s]
 20%|█▉        | 2186/11066 [08:02<32:48,  4.51it/s]
                                                    

 20%|█▉        | 2186/11066 [08:02<32:48,  4.51it/s]
 20%|█▉        | 2187/11066 [08:02<32:54,  4.50it/s]
                                                    

 20%|█▉        | 2187/11066 [08:02<32:54,  4.50it/s]
 20%|█▉        | 2188/11066 [08:02<32:26,  4.56it/s]
                                                    

 20%|█▉        | 2188/11066 [08:02<32:26,  4.56it/s]
 20%|█▉        | 2189/11066 [08:02<32:35,  4.54it/s]
                                                    

 20%|█▉        | 2189/11066 [08:02<32:35,  4.54it/s]
 20%|█▉        | 2190/11066 [08:02<32:12,  4.59it/s]
                                                    

 20%|█▉        | 2190/11066 [08:02<32:12,  4.59it/s]
 20%|█▉        | 2191/11066 [08:03<32:26,  4.56it/s]
                                                    

 20%|█▉        | 2191/11066 [08:03<32:26,  4.56it/s]
 20%|█▉        | 2192/11066 [08:03<32:18,  4.58it/s]
                                                    

 20%|█▉        | 2192/11066 [08:03<32:18,  4.58it/s]
 20%|█▉        | 2193/11066 [08:03<32:21,  4.57it/s]
                                                    

 20%|█▉        | 2193/11066 [08:03<32:21,  4.57it/s]
 20%|█▉        | 2194/11066 [08:03<32:06,  4.60it/s]
                                                    

 20%|█▉        | 2194/11066 [08:03<32:06,  4.60it/s]
 20%|█▉        | 2195/11066 [08:04<32:20,  4.57it/s]
                                                    

 20%|█▉        | 2195/11066 [08:04<32:20,  4.57it/s]
 20%|█▉        | 2196/11066 [08:04<32:08,  4.60it/s]
                                                    

 20%|█▉        | 2196/11066 [08:04<32:08,  4.60it/s]
 20%|█▉        | 2197/11066 [08:04<31:51,  4.64it/s]
                                                    

 20%|█▉        | 2197/11066 [08:04<31:51,  4.64it/s]
 20%|█▉        | 2198/11066 [08:04<32:16,  4.58it/s]
                                                    

 20%|█▉        | 2198/11066 [08:04<32:16,  4.58it/s]
 20%|█▉        | 2199/11066 [08:04<32:16,  4.58it/s]
                                                    

 20%|█▉        | 2199/11066 [08:04<32:16,  4.58it/s]
 20%|█▉        | 2200/11066 [08:05<31:56,  4.63it/s]
                                                    

 20%|█▉        | 2200/11066 [08:05<31:56,  4.63it/s]
 20%|█▉        | 2201/11066 [08:05<31:48,  4.64it/s]
                                                    

 20%|█▉        | 2201/11066 [08:05<31:48,  4.64it/s]
 20%|█▉        | 2202/11066 [08:05<31:42,  4.66it/s]
                                                    

 20%|█▉        | 2202/11066 [08:05<31:42,  4.66it/s]
 20%|█▉        | 2203/11066 [08:05<31:49,  4.64it/s]
                                                    

 20%|█▉        | 2203/11066 [08:05<31:49,  4.64it/s]
 20%|█▉        | 2204/11066 [08:05<32:10,  4.59it/s]
                                                    

 20%|█▉        | 2204/11066 [08:05<32:10,  4.59it/s]
 20%|█▉        | 2205/11066 [08:06<31:59,  4.62it/s]
                                                    

 20%|█▉        | 2205/11066 [08:06<31:59,  4.62it/s]
 20%|█▉        | 2206/11066 [08:06<32:12,  4.58it/s]
                                                    

 20%|█▉        | 2206/11066 [08:06<32:12,  4.58it/s]
 20%|█▉        | 2207/11066 [08:06<32:25,  4.55it/s]
                                                    

 20%|█▉        | 2207/11066 [08:06<32:25,  4.55it/s]
 20%|█▉        | 2208/11066 [08:06<32:30,  4.54it/s]
                                                    

 20%|█▉        | 2208/11066 [08:06<32:30,  4.54it/s]
 20%|█▉        | 2209/11066 [08:07<32:07,  4.59it/s]
                                                    

 20%|█▉        | 2209/11066 [08:07<32:07,  4.59it/s]
 20%|█▉        | 2210/11066 [08:07<32:22,  4.56it/s]
                                                    

 20%|█▉        | 2210/11066 [08:07<32:22,  4.56it/s]
 20%|█▉        | 2211/11066 [08:07<32:05,  4.60it/s]
                                                    

 20%|█▉        | 2211/11066 [08:07<32:05,  4.60it/s]
 20%|█▉        | 2212/11066 [08:07<32:03,  4.60it/s]
                                                    

 20%|█▉        | 2212/11066 [08:07<32:03,  4.60it/s]
 20%|█▉        | 2213/11066 [08:07<32:19,  4.57it/s]
                                                    

 20%|█▉        | 2213/11066 [08:07<32:19,  4.57it/s]
 20%|██        | 2214/11066 [08:08<31:54,  4.62it/s]
                                                    

 20%|██        | 2214/11066 [08:08<31:54,  4.62it/s]
 20%|██        | 2215/11066 [08:08<33:09,  4.45it/s]
                                                    

 20%|██        | 2215/11066 [08:08<33:09,  4.45it/s]
 20%|██        | 2216/11066 [08:08<33:14,  4.44it/s]
                                                    

 20%|██        | 2216/11066 [08:08<33:14,  4.44it/s]
 20%|██        | 2217/11066 [08:08<33:07,  4.45it/s]
                                                    

 20%|██        | 2217/11066 [08:08<33:07,  4.45it/s]
 20%|██        | 2218/11066 [08:09<33:01,  4.46it/s]
                                                    

 20%|██        | 2218/11066 [08:09<33:01,  4.46it/s]
 20%|██        | 2219/11066 [08:09<32:47,  4.50it/s]
                                                    

 20%|██        | 2219/11066 [08:09<32:47,  4.50it/s]
 20%|██        | 2220/11066 [08:09<32:47,  4.50it/s]
                                                    

 20%|██        | 2220/11066 [08:09<32:47,  4.50it/s]
 20%|██        | 2221/11066 [08:09<32:38,  4.52it/s]
                                                    

 20%|██        | 2221/11066 [08:09<32:38,  4.52it/s]
 20%|██        | 2222/11066 [08:09<32:44,  4.50it/s]
                                                    

 20%|██        | 2222/11066 [08:09<32:44,  4.50it/s]
 20%|██        | 2223/11066 [08:10<32:34,  4.53it/s]
                                                    

 20%|██        | 2223/11066 [08:10<32:34,  4.53it/s]
 20%|██        | 2224/11066 [08:10<32:20,  4.56it/s]
                                                    

 20%|██        | 2224/11066 [08:10<32:20,  4.56it/s]
 20%|██        | 2225/11066 [08:10<32:35,  4.52it/s]
                                                    

 20%|██        | 2225/11066 [08:10<32:35,  4.52it/s]
 20%|██        | 2226/11066 [08:10<32:25,  4.54it/s]
                                                    

 20%|██        | 2226/11066 [08:10<32:25,  4.54it/s]
 20%|██        | 2227/11066 [08:11<32:19,  4.56it/s]
                                                    

 20%|██        | 2227/11066 [08:11<32:19,  4.56it/s]
 20%|██        | 2228/11066 [08:11<32:33,  4.52it/s]
                                                    

 20%|██        | 2228/11066 [08:11<32:33,  4.52it/s]
 20%|██        | 2229/11066 [08:11<32:37,  4.51it/s]
                                                    

 20%|██        | 2229/11066 [08:11<32:37,  4.51it/s]
 20%|██        | 2230/11066 [08:11<32:39,  4.51it/s]
                                                    

 20%|██        | 2230/11066 [08:11<32:39,  4.51it/s]
 20%|██        | 2231/11066 [08:11<32:29,  4.53it/s]
                                                    

 20%|██        | 2231/11066 [08:11<32:29,  4.53it/s]
 20%|██        | 2232/11066 [08:12<32:12,  4.57it/s]
                                                    

 20%|██        | 2232/11066 [08:12<32:12,  4.57it/s]
 20%|██        | 2233/11066 [08:12<32:10,  4.58it/s]
                                                    

 20%|██        | 2233/11066 [08:12<32:10,  4.58it/s]
 20%|██        | 2234/11066 [08:12<32:17,  4.56it/s]
                                                    

 20%|██        | 2234/11066 [08:12<32:17,  4.56it/s]
 20%|██        | 2235/11066 [08:12<31:56,  4.61it/s]
                                                    

 20%|██        | 2235/11066 [08:12<31:56,  4.61it/s]
 20%|██        | 2236/11066 [08:13<32:10,  4.58it/s]
                                                    

 20%|██        | 2236/11066 [08:13<32:10,  4.58it/s]
 20%|██        | 2237/11066 [08:13<31:53,  4.62it/s]
                                                    

 20%|██        | 2237/11066 [08:13<31:53,  4.62it/s]
 20%|██        | 2238/11066 [08:13<31:55,  4.61it/s]
                                                    

 20%|██        | 2238/11066 [08:13<31:55,  4.61it/s]
 20%|██        | 2239/11066 [08:13<31:49,  4.62it/s]
                                                    

 20%|██        | 2239/11066 [08:13<31:49,  4.62it/s]
 20%|██        | 2240/11066 [08:13<31:54,  4.61it/s]
                                                    

 20%|██        | 2240/11066 [08:13<31:54,  4.61it/s]
 20%|██        | 2241/11066 [08:14<32:07,  4.58it/s]
                                                    

 20%|██        | 2241/11066 [08:14<32:07,  4.58it/s]
 20%|██        | 2242/11066 [08:14<32:22,  4.54it/s]
                                                    

 20%|██        | 2242/11066 [08:14<32:22,  4.54it/s]
 20%|██        | 2243/11066 [08:14<32:33,  4.52it/s]
                                                    

 20%|██        | 2243/11066 [08:14<32:33,  4.52it/s]
 20%|██        | 2244/11066 [08:14<32:46,  4.49it/s]
                                                    

 20%|██        | 2244/11066 [08:14<32:46,  4.49it/s]
 20%|██        | 2245/11066 [08:14<32:47,  4.48it/s]
                                                    

 20%|██        | 2245/11066 [08:15<32:47,  4.48it/s]
 20%|██        | 2246/11066 [08:15<32:47,  4.48it/s]
                                                    

 20%|██        | 2246/11066 [08:15<32:47,  4.48it/s]
 20%|██        | 2247/11066 [08:15<32:45,  4.49it/s]
                                                    

 20%|██        | 2247/11066 [08:15<32:45,  4.49it/s]
 20%|██        | 2248/11066 [08:15<32:44,  4.49it/s]
                                                    

 20%|██        | 2248/11066 [08:15<32:44,  4.49it/s]
 20%|██        | 2249/11066 [08:15<32:43,  4.49it/s]
                                                    

 20%|██        | 2249/11066 [08:15<32:43,  4.49it/s]
 20%|██        | 2250/11066 [08:16<32:43,  4.49it/s]
                                                    

 20%|██        | 2250/11066 [08:16<32:43,  4.49it/s]
 20%|██        | 2251/11066 [08:16<32:43,  4.49it/s]
                                                    
{'loss': 1.4078, 'learning_rate': 2.420386770287367e-05, 'epoch': 0.39}
{'loss': 1.1202, 'learning_rate': 2.420115669618652e-05, 'epoch': 0.39}
{'loss': 0.5693, 'learning_rate': 2.4198445689499366e-05, 'epoch': 0.39}
{'loss': 1.2453, 'learning_rate': 2.4195734682812218e-05, 'epoch': 0.39}
{'loss': 1.2984, 'learning_rate': 2.4193023676125066e-05, 'epoch': 0.39}
{'loss': 1.5564, 'learning_rate': 2.4190312669437918e-05, 'epoch': 0.39}
{'loss': 1.6073, 'learning_rate': 2.418760166275077e-05, 'epoch': 0.39}
{'loss': 1.4399, 'learning_rate': 2.418489065606362e-05, 'epoch': 0.39}
{'loss': 1.7798, 'learning_rate': 2.418217964937647e-05, 'epoch': 0.39}
{'loss': 1.02, 'learning_rate': 2.4179468642689322e-05, 'epoch': 0.39}
{'loss': 1.1867, 'learning_rate': 2.4176757636002167e-05, 'epoch': 0.39}
{'loss': 1.2824, 'learning_rate': 2.417404662931502e-05, 'epoch': 0.39}
{'loss': 1.2157, 'learning_rate': 2.417133562262787e-05, 'epoch': 0.39}
{'loss': 1.2818, 'learning_rate': 2.416862461594072e-05, 'epoch': 0.39}
{'loss': 1.0538, 'learning_rate': 2.416591360925357e-05, 'epoch': 0.39}
{'loss': 1.1994, 'learning_rate': 2.416320260256642e-05, 'epoch': 0.39}
{'loss': 1.2114, 'learning_rate': 2.416049159587927e-05, 'epoch': 0.39}
{'loss': 0.8309, 'learning_rate': 2.4157780589192123e-05, 'epoch': 0.39}
{'loss': 1.9156, 'learning_rate': 2.4155069582504968e-05, 'epoch': 0.39}
{'loss': 1.2494, 'learning_rate': 2.415235857581782e-05, 'epoch': 0.39}
{'loss': 0.6158, 'learning_rate': 2.4149647569130672e-05, 'epoch': 0.39}
{'loss': 1.2505, 'learning_rate': 2.414693656244352e-05, 'epoch': 0.39}
{'loss': 0.623, 'learning_rate': 2.4144225555756372e-05, 'epoch': 0.39}
{'loss': 1.8813, 'learning_rate': 2.4141514549069224e-05, 'epoch': 0.39}
{'loss': 0.9891, 'learning_rate': 2.4138803542382072e-05, 'epoch': 0.39}
{'loss': 1.0912, 'learning_rate': 2.4136092535694924e-05, 'epoch': 0.39}
{'loss': 1.2862, 'learning_rate': 2.413338152900777e-05, 'epoch': 0.39}
{'loss': 1.5618, 'learning_rate': 2.413067052232062e-05, 'epoch': 0.39}
{'loss': 0.9929, 'learning_rate': 2.4127959515633473e-05, 'epoch': 0.39}
{'loss': 1.3252, 'learning_rate': 2.412524850894632e-05, 'epoch': 0.39}
{'loss': 1.7251, 'learning_rate': 2.4122537502259173e-05, 'epoch': 0.39}
{'loss': 1.6687, 'learning_rate': 2.4119826495572025e-05, 'epoch': 0.39}
{'loss': 1.9936, 'learning_rate': 2.4117115488884873e-05, 'epoch': 0.39}
{'loss': 1.2977, 'learning_rate': 2.4114404482197725e-05, 'epoch': 0.39}
{'loss': 1.3784, 'learning_rate': 2.4111693475510574e-05, 'epoch': 0.39}
{'loss': 0.8416, 'learning_rate': 2.4108982468823422e-05, 'epoch': 0.39}
{'loss': 0.4672, 'learning_rate': 2.4106271462136274e-05, 'epoch': 0.39}
{'loss': 1.4769, 'learning_rate': 2.4103560455449122e-05, 'epoch': 0.39}
{'loss': 0.7983, 'learning_rate': 2.4100849448761974e-05, 'epoch': 0.39}
{'loss': 1.4203, 'learning_rate': 2.4098138442074826e-05, 'epoch': 0.39}
{'loss': 1.2469, 'learning_rate': 2.4095427435387675e-05, 'epoch': 0.39}
{'loss': 1.2625, 'learning_rate': 2.4092716428700526e-05, 'epoch': 0.39}
{'loss': 1.5468, 'learning_rate': 2.4090005422013375e-05, 'epoch': 0.39}
{'loss': 0.8464, 'learning_rate': 2.4087294415326223e-05, 'epoch': 0.39}
{'loss': 1.0478, 'learning_rate': 2.4084583408639075e-05, 'epoch': 0.39}
{'loss': 1.3646, 'learning_rate': 2.4081872401951927e-05, 'epoch': 0.39}
{'loss': 0.9235, 'learning_rate': 2.4079161395264775e-05, 'epoch': 0.39}
{'loss': 1.1486, 'learning_rate': 2.4076450388577627e-05, 'epoch': 0.39}
{'loss': 0.5875, 'learning_rate': 2.4073739381890476e-05, 'epoch': 0.4}
{'loss': 0.8181, 'learning_rate': 2.4071028375203327e-05, 'epoch': 0.4}
{'loss': 1.5728, 'learning_rate': 2.4068317368516176e-05, 'epoch': 0.4}
{'loss': 0.9413, 'learning_rate': 2.4065606361829024e-05, 'epoch': 0.4}
{'loss': 1.3664, 'learning_rate': 2.4062895355141876e-05, 'epoch': 0.4}
{'loss': 2.0352, 'learning_rate': 2.4060184348454728e-05, 'epoch': 0.4}
{'loss': 1.5712, 'learning_rate': 2.4057473341767576e-05, 'epoch': 0.4}
{'loss': 1.2458, 'learning_rate': 2.4054762335080428e-05, 'epoch': 0.4}
{'loss': 0.4059, 'learning_rate': 2.405205132839328e-05, 'epoch': 0.4}
{'loss': 1.1423, 'learning_rate': 2.4049340321706125e-05, 'epoch': 0.4}
{'loss': 0.9882, 'learning_rate': 2.4046629315018977e-05, 'epoch': 0.4}
{'loss': 1.1364, 'learning_rate': 2.4043918308331825e-05, 'epoch': 0.4}
{'loss': 1.0111, 'learning_rate': 2.4041207301644677e-05, 'epoch': 0.4}
{'loss': 0.8417, 'learning_rate': 2.403849629495753e-05, 'epoch': 0.4}
{'loss': 0.5473, 'learning_rate': 2.4035785288270377e-05, 'epoch': 0.4}
{'loss': 1.8869, 'learning_rate': 2.403307428158323e-05, 'epoch': 0.4}
{'loss': 0.8166, 'learning_rate': 2.403036327489608e-05, 'epoch': 0.4}
{'loss': 1.572, 'learning_rate': 2.4027652268208926e-05, 'epoch': 0.4}
{'loss': 1.2963, 'learning_rate': 2.4024941261521778e-05, 'epoch': 0.4}
{'loss': 0.806, 'learning_rate': 2.402223025483463e-05, 'epoch': 0.4}
{'loss': 1.3091, 'learning_rate': 2.4019519248147478e-05, 'epoch': 0.4}
{'loss': 0.7697, 'learning_rate': 2.401680824146033e-05, 'epoch': 0.4}
{'loss': 0.5964, 'learning_rate': 2.401409723477318e-05, 'epoch': 0.4}
{'loss': 1.8209, 'learning_rate': 2.401138622808603e-05, 'epoch': 0.4}
{'loss': 0.5016, 'learning_rate': 2.4008675221398882e-05, 'epoch': 0.4}
{'loss': 0.6549, 'learning_rate': 2.4005964214711727e-05, 'epoch': 0.4}
{'loss': 1.2623, 'learning_rate': 2.400325320802458e-05, 'epoch': 0.4}
{'loss': 1.748, 'learning_rate': 2.400054220133743e-05, 'epoch': 0.4}
{'loss': 1.0977, 'learning_rate': 2.399783119465028e-05, 'epoch': 0.4}
{'loss': 1.1477, 'learning_rate': 2.399512018796313e-05, 'epoch': 0.4}
{'loss': 1.1651, 'learning_rate': 2.3992409181275983e-05, 'epoch': 0.4}
{'loss': 0.5238, 'learning_rate': 2.398969817458883e-05, 'epoch': 0.4}
{'loss': 0.9948, 'learning_rate': 2.3986987167901683e-05, 'epoch': 0.4}
{'loss': 1.0966, 'learning_rate': 2.3984276161214532e-05, 'epoch': 0.4}
{'loss': 0.8436, 'learning_rate': 2.398156515452738e-05, 'epoch': 0.4}
{'loss': 1.0425, 'learning_rate': 2.3978854147840232e-05, 'epoch': 0.4}
{'loss': 0.9452, 'learning_rate': 2.397614314115308e-05, 'epoch': 0.4}
{'loss': 0.8566, 'learning_rate': 2.3973432134465932e-05, 'epoch': 0.4}
{'loss': 1.2939, 'learning_rate': 2.3970721127778784e-05, 'epoch': 0.4}
{'loss': 0.7339, 'learning_rate': 2.3968010121091633e-05, 'epoch': 0.4}
{'loss': 1.3667, 'learning_rate': 2.3965299114404484e-05, 'epoch': 0.4}
{'loss': 1.5799, 'learning_rate': 2.3962588107717333e-05, 'epoch': 0.4}
{'loss': 1.4564, 'learning_rate': 2.395987710103018e-05, 'epoch': 0.4}
{'loss': 0.7972, 'learning_rate': 2.3957166094343033e-05, 'epoch': 0.4}
{'loss': 0.9817, 'learning_rate': 2.3954455087655885e-05, 'epoch': 0.4}
{'loss': 1.6074, 'learning_rate': 2.3951744080968733e-05, 'epoch': 0.4}
{'loss': 0.9172, 'learning_rate': 2.3949033074281585e-05, 'epoch': 0.4}
{'loss': 1.3537, 'learning_rate': 2.3946322067594434e-05, 'epoch': 0.4}
{'loss': 1.0103, 'learning_rate': 2.3943611060907285e-05, 'epoch': 0.4}
{'loss': 1.4013, 'learning_rate': 2.3940900054220134e-05, 'epoch': 0.4}
{'loss': 1.469, 'learning_rate': 2.3938189047532982e-05, 'epoch': 0.4}
{'loss': 0.4735, 'learning_rate': 2.3935478040845834e-05, 'epoch': 0.4}
{'loss': 2.148, 'learning_rate': 2.3932767034158686e-05, 'epoch': 0.4}
{'loss': 1.2625, 'learning_rate': 2.3930056027471534e-05, 'epoch': 0.4}
{'loss': 1.4482, 'learning_rate': 2.3927345020784386e-05, 'epoch': 0.4}
{'loss': 1.1109, 'learning_rate': 2.3924634014097238e-05, 'epoch': 0.41}
{'loss': 1.5921, 'learning_rate': 2.3921923007410087e-05, 'epoch': 0.41}
{'loss': 0.7212, 'learning_rate': 2.3919212000722935e-05, 'epoch': 0.41}
{'loss': 1.4481, 'learning_rate': 2.3916500994035783e-05, 'epoch': 0.41}
{'loss': 1.4787, 'learning_rate': 2.3913789987348635e-05, 'epoch': 0.41}
{'loss': 1.2271, 'learning_rate': 2.3911078980661487e-05, 'epoch': 0.41}
{'loss': 1.4152, 'learning_rate': 2.3908367973974335e-05, 'epoch': 0.41}
{'loss': 1.7165, 'learning_rate': 2.3905656967287187e-05, 'epoch': 0.41}
{'loss': 1.0711, 'learning_rate': 2.390294596060004e-05, 'epoch': 0.41}
{'loss': 0.9369, 'learning_rate': 2.3900234953912888e-05, 'epoch': 0.41}

 20%|██        | 2251/11066 [08:16<32:43,  4.49it/s]
 20%|██        | 2252/11066 [08:16<32:44,  4.49it/s]
                                                    

 20%|██        | 2252/11066 [08:16<32:44,  4.49it/s]
 20%|██        | 2253/11066 [08:16<32:41,  4.49it/s]
                                                    

 20%|██        | 2253/11066 [08:16<32:41,  4.49it/s]
 20%|██        | 2254/11066 [08:17<32:40,  4.49it/s]
                                                    

 20%|██        | 2254/11066 [08:17<32:40,  4.49it/s]
 20%|██        | 2255/11066 [08:17<32:40,  4.49it/s]
                                                    

 20%|██        | 2255/11066 [08:17<32:40,  4.49it/s]
 20%|██        | 2256/11066 [08:17<32:34,  4.51it/s]
                                                    

 20%|██        | 2256/11066 [08:17<32:34,  4.51it/s]
 20%|██        | 2257/11066 [08:17<32:39,  4.50it/s]
                                                    

 20%|██        | 2257/11066 [08:17<32:39,  4.50it/s]
 20%|██        | 2258/11066 [08:17<32:40,  4.49it/s]
                                                    

 20%|██        | 2258/11066 [08:17<32:40,  4.49it/s]
 20%|██        | 2259/11066 [08:18<32:39,  4.49it/s]
                                                    

 20%|██        | 2259/11066 [08:18<32:39,  4.49it/s]
 20%|██        | 2260/11066 [08:18<32:37,  4.50it/s]
                                                    

 20%|██        | 2260/11066 [08:18<32:37,  4.50it/s]
 20%|██        | 2261/11066 [08:18<32:38,  4.50it/s]
                                                    

 20%|██        | 2261/11066 [08:18<32:38,  4.50it/s]
 20%|██        | 2262/11066 [08:18<32:37,  4.50it/s]
                                                    

 20%|██        | 2262/11066 [08:18<32:37,  4.50it/s]
 20%|██        | 2263/11066 [08:19<32:37,  4.50it/s]
                                                    

 20%|██        | 2263/11066 [08:19<32:37,  4.50it/s]
 20%|██        | 2264/11066 [08:19<32:36,  4.50it/s]
                                                    

 20%|██        | 2264/11066 [08:19<32:36,  4.50it/s]
 20%|██        | 2265/11066 [08:19<32:35,  4.50it/s]
                                                    

 20%|██        | 2265/11066 [08:19<32:35,  4.50it/s]
 20%|██        | 2266/11066 [08:19<32:35,  4.50it/s]
                                                    

 20%|██        | 2266/11066 [08:19<32:35,  4.50it/s]
 20%|██        | 2267/11066 [08:19<32:20,  4.54it/s]
                                                    

 20%|██        | 2267/11066 [08:19<32:20,  4.54it/s]
 20%|██        | 2268/11066 [08:20<31:59,  4.58it/s]
                                                    

 20%|██        | 2268/11066 [08:20<31:59,  4.58it/s]
 21%|██        | 2269/11066 [08:20<31:45,  4.62it/s]
                                                    

 21%|██        | 2269/11066 [08:20<31:45,  4.62it/s]
 21%|██        | 2270/11066 [08:20<31:43,  4.62it/s]
                                                    

 21%|██        | 2270/11066 [08:20<31:43,  4.62it/s]
 21%|██        | 2271/11066 [08:20<32:01,  4.58it/s]
                                                    

 21%|██        | 2271/11066 [08:20<32:01,  4.58it/s]
 21%|██        | 2272/11066 [08:20<32:12,  4.55it/s]
                                                    

 21%|██        | 2272/11066 [08:20<32:12,  4.55it/s]
 21%|██        | 2273/11066 [08:21<32:19,  4.53it/s]
                                                    

 21%|██        | 2273/11066 [08:21<32:19,  4.53it/s]
 21%|██        | 2274/11066 [08:21<32:23,  4.52it/s]
                                                    

 21%|██        | 2274/11066 [08:21<32:23,  4.52it/s]
 21%|██        | 2275/11066 [08:21<32:27,  4.51it/s]
                                                    

 21%|██        | 2275/11066 [08:21<32:27,  4.51it/s]
 21%|██        | 2276/11066 [08:21<32:29,  4.51it/s]
                                                    

 21%|██        | 2276/11066 [08:21<32:29,  4.51it/s]
 21%|██        | 2277/11066 [08:22<32:05,  4.56it/s]
                                                    

 21%|██        | 2277/11066 [08:22<32:05,  4.56it/s]
 21%|██        | 2278/11066 [08:22<32:07,  4.56it/s]
                                                    

 21%|██        | 2278/11066 [08:22<32:07,  4.56it/s]
 21%|██        | 2279/11066 [08:22<31:47,  4.61it/s]
                                                    

 21%|██        | 2279/11066 [08:22<31:47,  4.61it/s]
 21%|██        | 2280/11066 [08:22<32:05,  4.56it/s]
                                                    

 21%|██        | 2280/11066 [08:22<32:05,  4.56it/s]
 21%|██        | 2281/11066 [08:22<32:01,  4.57it/s]
                                                    

 21%|██        | 2281/11066 [08:22<32:01,  4.57it/s]
 21%|██        | 2282/11066 [08:23<32:14,  4.54it/s]
                                                    

 21%|██        | 2282/11066 [08:23<32:14,  4.54it/s]
 21%|██        | 2283/11066 [08:23<32:20,  4.53it/s]
                                                    

 21%|██        | 2283/11066 [08:23<32:20,  4.53it/s]
 21%|██        | 2284/11066 [08:23<32:03,  4.57it/s]
                                                    

 21%|██        | 2284/11066 [08:23<32:03,  4.57it/s]
 21%|██        | 2285/11066 [08:23<32:16,  4.53it/s]
                                                    

 21%|██        | 2285/11066 [08:23<32:16,  4.53it/s]
 21%|██        | 2286/11066 [08:24<32:22,  4.52it/s]
                                                    

 21%|██        | 2286/11066 [08:24<32:22,  4.52it/s]
 21%|██        | 2287/11066 [08:24<32:25,  4.51it/s]
                                                    

 21%|██        | 2287/11066 [08:24<32:25,  4.51it/s]
 21%|██        | 2288/11066 [08:24<32:12,  4.54it/s]
                                                    

 21%|██        | 2288/11066 [08:24<32:12,  4.54it/s]
 21%|██        | 2289/11066 [08:24<31:55,  4.58it/s]
                                                    

 21%|██        | 2289/11066 [08:24<31:55,  4.58it/s]
 21%|██        | 2290/11066 [08:24<31:50,  4.59it/s]
                                                    

 21%|██        | 2290/11066 [08:24<31:50,  4.59it/s]
 21%|██        | 2291/11066 [08:25<31:46,  4.60it/s]
                                                    

 21%|██        | 2291/11066 [08:25<31:46,  4.60it/s]
 21%|██        | 2292/11066 [08:25<31:52,  4.59it/s]
                                                    

 21%|██        | 2292/11066 [08:25<31:52,  4.59it/s]
 21%|██        | 2293/11066 [08:25<31:48,  4.60it/s]
                                                    

 21%|██        | 2293/11066 [08:25<31:48,  4.60it/s]
 21%|██        | 2294/11066 [08:25<32:06,  4.55it/s]
                                                    

 21%|██        | 2294/11066 [08:25<32:06,  4.55it/s]
 21%|██        | 2295/11066 [08:26<32:14,  4.53it/s]
                                                    

 21%|██        | 2295/11066 [08:26<32:14,  4.53it/s]
 21%|██        | 2296/11066 [08:26<32:22,  4.52it/s]
                                                    

 21%|██        | 2296/11066 [08:26<32:22,  4.52it/s]
 21%|██        | 2297/11066 [08:26<31:58,  4.57it/s]
                                                    

 21%|██        | 2297/11066 [08:26<31:58,  4.57it/s]
 21%|██        | 2298/11066 [08:26<32:14,  4.53it/s]
                                                    

 21%|██        | 2298/11066 [08:26<32:14,  4.53it/s]
 21%|██        | 2299/11066 [08:26<32:23,  4.51it/s]
                                                    

 21%|██        | 2299/11066 [08:26<32:23,  4.51it/s]
 21%|██        | 2300/11066 [08:27<31:56,  4.57it/s]
                                                    

 21%|██        | 2300/11066 [08:27<31:56,  4.57it/s]
 21%|██        | 2301/11066 [08:27<32:17,  4.52it/s]
                                                    

 21%|██        | 2301/11066 [08:27<32:17,  4.52it/s]
 21%|██        | 2302/11066 [08:27<32:07,  4.55it/s]
                                                    

 21%|██        | 2302/11066 [08:27<32:07,  4.55it/s]
 21%|██        | 2303/11066 [08:27<32:21,  4.51it/s]
                                                    

 21%|██        | 2303/11066 [08:27<32:21,  4.51it/s]
 21%|██        | 2304/11066 [08:28<32:27,  4.50it/s]
                                                    

 21%|██        | 2304/11066 [08:28<32:27,  4.50it/s]
 21%|██        | 2305/11066 [08:28<32:16,  4.53it/s]
                                                    

 21%|██        | 2305/11066 [08:28<32:16,  4.53it/s]
 21%|██        | 2306/11066 [08:28<32:07,  4.54it/s]
                                                    

 21%|██        | 2306/11066 [08:28<32:07,  4.54it/s]
 21%|██        | 2307/11066 [08:28<31:56,  4.57it/s]
                                                    

 21%|██        | 2307/11066 [08:28<31:56,  4.57it/s]
 21%|██        | 2308/11066 [08:28<32:05,  4.55it/s]
                                                    

 21%|██        | 2308/11066 [08:28<32:05,  4.55it/s]
 21%|██        | 2309/11066 [08:29<32:17,  4.52it/s]
                                                    

 21%|██        | 2309/11066 [08:29<32:17,  4.52it/s]
 21%|██        | 2310/11066 [08:29<32:16,  4.52it/s]
                                                    

 21%|██        | 2310/11066 [08:29<32:16,  4.52it/s]
 21%|██        | 2311/11066 [08:29<32:06,  4.55it/s]
                                                    

 21%|██        | 2311/11066 [08:29<32:06,  4.55it/s]
 21%|██        | 2312/11066 [08:29<31:50,  4.58it/s]
                                                    

 21%|██        | 2312/11066 [08:29<31:50,  4.58it/s]
 21%|██        | 2313/11066 [08:29<32:08,  4.54it/s]
                                                    

 21%|██        | 2313/11066 [08:29<32:08,  4.54it/s]
 21%|██        | 2314/11066 [08:30<32:16,  4.52it/s]
                                                    

 21%|██        | 2314/11066 [08:30<32:16,  4.52it/s]
 21%|██        | 2315/11066 [08:30<32:18,  4.51it/s]
                                                    

 21%|██        | 2315/11066 [08:30<32:18,  4.51it/s]
 21%|██        | 2316/11066 [08:30<32:19,  4.51it/s]
                                                    

 21%|██        | 2316/11066 [08:30<32:19,  4.51it/s]
 21%|██        | 2317/11066 [08:30<32:04,  4.55it/s]
                                                    

 21%|██        | 2317/11066 [08:30<32:04,  4.55it/s]
 21%|██        | 2318/11066 [08:31<32:03,  4.55it/s]
                                                    

 21%|██        | 2318/11066 [08:31<32:03,  4.55it/s]
 21%|██        | 2319/11066 [08:31<32:10,  4.53it/s]
                                                    

 21%|██        | 2319/11066 [08:31<32:10,  4.53it/s]
 21%|██        | 2320/11066 [08:31<32:19,  4.51it/s]
                                                    

 21%|██        | 2320/11066 [08:31<32:19,  4.51it/s]
 21%|██        | 2321/11066 [08:31<32:27,  4.49it/s]
                                                    

 21%|██        | 2321/11066 [08:31<32:27,  4.49it/s]
 21%|██        | 2322/11066 [08:31<32:27,  4.49it/s]
                                                    

 21%|██        | 2322/11066 [08:31<32:27,  4.49it/s]
 21%|██        | 2323/11066 [08:32<32:26,  4.49it/s]
                                                    

 21%|██        | 2323/11066 [08:32<32:26,  4.49it/s]
 21%|██        | 2324/11066 [08:32<32:24,  4.49it/s]
                                                    

 21%|██        | 2324/11066 [08:32<32:24,  4.49it/s]
 21%|██        | 2325/11066 [08:32<32:24,  4.50it/s]
                                                    

 21%|██        | 2325/11066 [08:32<32:24,  4.50it/s]
 21%|██        | 2326/11066 [08:32<32:31,  4.48it/s]
                                                    

 21%|██        | 2326/11066 [08:32<32:31,  4.48it/s]
 21%|██        | 2327/11066 [08:33<32:29,  4.48it/s]
                                                    

 21%|██        | 2327/11066 [08:33<32:29,  4.48it/s]
 21%|██        | 2328/11066 [08:33<32:36,  4.47it/s]
                                                    

 21%|██        | 2328/11066 [08:33<32:36,  4.47it/s]
 21%|██        | 2329/11066 [08:33<32:42,  4.45it/s]
                                                    

 21%|██        | 2329/11066 [08:33<32:42,  4.45it/s]
 21%|██        | 2330/11066 [08:33<33:06,  4.40it/s]
                                                    

 21%|██        | 2330/11066 [08:33<33:06,  4.40it/s]
 21%|██        | 2331/11066 [08:34<33:11,  4.39it/s]
                                                    

 21%|██        | 2331/11066 [08:34<33:11,  4.39it/s]
 21%|██        | 2332/11066 [08:34<32:57,  4.42it/s]
                                                    

 21%|██        | 2332/11066 [08:34<32:57,  4.42it/s]
 21%|██        | 2333/11066 [08:34<32:46,  4.44it/s]
                                                    

 21%|██        | 2333/11066 [08:34<32:46,  4.44it/s]
 21%|██        | 2334/11066 [08:34<32:43,  4.45it/s]
                                                    

 21%|██        | 2334/11066 [08:34<32:43,  4.45it/s]
 21%|██        | 2335/11066 [08:34<32:50,  4.43it/s]
                                                    

 21%|██        | 2335/11066 [08:34<32:50,  4.43it/s]
 21%|██        | 2336/11066 [08:35<32:48,  4.44it/s]
                                                    

 21%|██        | 2336/11066 [08:35<32:48,  4.44it/s]
 21%|██        | 2337/11066 [08:35<32:24,  4.49it/s]
                                                    

 21%|██        | 2337/11066 [08:35<32:24,  4.49it/s]
 21%|██        | 2338/11066 [08:35<32:02,  4.54it/s]
                                                    

 21%|██        | 2338/11066 [08:35<32:02,  4.54it/s]
 21%|██        | 2339/11066 [08:35<32:09,  4.52it/s]
                                                    

 21%|██        | 2339/11066 [08:35<32:09,  4.52it/s]
 21%|██        | 2340/11066 [08:36<32:18,  4.50it/s]
                                                    

 21%|██        | 2340/11066 [08:36<32:18,  4.50it/s]
 21%|██        | 2341/11066 [08:36<32:17,  4.50it/s]
                                                    

 21%|██        | 2341/11066 [08:36<32:17,  4.50it/s]
 21%|██        | 2342/11066 [08:36<32:01,  4.54it/s]
                                                    

 21%|██        | 2342/11066 [08:36<32:01,  4.54it/s]
 21%|██        | 2343/11066 [08:36<31:46,  4.58it/s]
                                                    

 21%|██        | 2343/11066 [08:36<31:46,  4.58it/s]
 21%|██        | 2344/11066 [08:36<31:58,  4.55it/s]
                                                    

 21%|██        | 2344/11066 [08:36<31:58,  4.55it/s]
 21%|██        | 2345/11066 [08:37<32:08,  4.52it/s]
                                                    

 21%|██        | 2345/11066 [08:37<32:08,  4.52it/s]
 21%|██        | 2346/11066 [08:37<32:10,  4.52it/s]
                                                    

 21%|██        | 2346/11066 [08:37<32:10,  4.52it/s]
 21%|██        | 2347/11066 [08:37<31:56,  4.55it/s]
                                                    

 21%|██        | 2347/11066 [08:37<31:56,  4.55it/s]
 21%|██        | 2348/11066 [08:37<31:41,  4.58it/s]
                                                    

 21%|██        | 2348/11066 [08:37<31:41,  4.58it/s]
 21%|██        | 2349/11066 [08:37<31:56,  4.55it/s]
                                                    

 21%|██        | 2349/11066 [08:37<31:56,  4.55it/s]
 21%|██        | 2350/11066 [08:38<32:05,  4.53it/s]
                                                    

 21%|██        | 2350/11066 [08:38<32:05,  4.53it/s]
 21%|██        | 2351/11066 [08:38<32:08,  4.52it/s]
                                                    

 21%|██        | 2351/11066 [08:38<32:08,  4.52it/s]
 21%|██▏       | 2352/11066 [08:38<32:09,  4.52it/s]
                                                    

 21%|██▏       | 2352/11066 [08:38<32:09,  4.52it/s]
 21%|██▏       | 2353/11066 [08:38<31:55,  4.55it/s]
                                                    

 21%|██▏       | 2353/11066 [08:38<31:55,  4.55it/s]
 21%|██▏       | 2354/11066 [08:39<31:40,  4.58it/s]
                                                    

 21%|██▏       | 2354/11066 [08:39<31:40,  4.58it/s]
 21%|██▏       | 2355/11066 [08:39<32:01,  4.53it/s]
                                                    

 21%|██▏       | 2355/11066 [08:39<32:01,  4.53it/s]
 21%|██▏       | 2356/11066 [08:39<32:10,  4.51it/s]
                                                    

 21%|██▏       | 2356/11066 [08:39<32:10,  4.51it/s]
 21%|██▏       | 2357/11066 [08:39<31:52,  4.55it/s]
                                                    

 21%|██▏       | 2357/11066 [08:39<31:52,  4.55it/s]
 21%|██▏       | 2358/11066 [08:39<31:47,  4.56it/s]
                                                    

 21%|██▏       | 2358/11066 [08:39<31:47,  4.56it/s]
 21%|██▏       | 2359/11066 [08:40<31:58,  4.54it/s]
                                                    

 21%|██▏       | 2359/11066 [08:40<31:58,  4.54it/s]
 21%|██▏       | 2360/11066 [08:40<31:41,  4.58it/s]
                                                    

 21%|██▏       | 2360/11066 [08:40<31:41,  4.58it/s]
 21%|██▏       | 2361/11066 [08:40<31:57,  4.54it/s]
                                                    

 21%|██▏       | 2361/11066 [08:40<31:57,  4.54it/s]
 21%|██▏       | 2362/11066 [08:40<32:03,  4.52it/s]
                                                    

 21%|██▏       | 2362/11066 [08:40<32:03,  4.52it/s]
 21%|██▏       | 2363/11066 [08:41<32:08,  4.51it/s]
                                                    

 21%|██▏       | 2363/11066 [08:41<32:08,  4.51it/s]
 21%|██▏       | 2364/11066 [08:41<32:11,  4.51it/s]
                                                    
{'loss': 1.4862, 'learning_rate': 2.3897523947225736e-05, 'epoch': 0.41}
{'loss': 1.3677, 'learning_rate': 2.3894812940538588e-05, 'epoch': 0.41}
{'loss': 1.4574, 'learning_rate': 2.3892101933851436e-05, 'epoch': 0.41}
{'loss': 1.0956, 'learning_rate': 2.3889390927164288e-05, 'epoch': 0.41}
{'loss': 1.7279, 'learning_rate': 2.3886679920477137e-05, 'epoch': 0.41}
{'loss': 0.8231, 'learning_rate': 2.388396891378999e-05, 'epoch': 0.41}
{'loss': 1.5255, 'learning_rate': 2.388125790710284e-05, 'epoch': 0.41}
{'loss': 1.5622, 'learning_rate': 2.387854690041569e-05, 'epoch': 0.41}
{'loss': 1.1532, 'learning_rate': 2.3875835893728537e-05, 'epoch': 0.41}
{'loss': 1.3246, 'learning_rate': 2.387312488704139e-05, 'epoch': 0.41}
{'loss': 2.099, 'learning_rate': 2.3870413880354237e-05, 'epoch': 0.41}
{'loss': 0.9531, 'learning_rate': 2.386770287366709e-05, 'epoch': 0.41}
{'loss': 1.454, 'learning_rate': 2.386499186697994e-05, 'epoch': 0.41}
{'loss': 1.2043, 'learning_rate': 2.386228086029279e-05, 'epoch': 0.41}
{'loss': 0.9555, 'learning_rate': 2.385956985360564e-05, 'epoch': 0.41}
{'loss': 1.2246, 'learning_rate': 2.385685884691849e-05, 'epoch': 0.41}
{'loss': 1.6236, 'learning_rate': 2.3854147840231338e-05, 'epoch': 0.41}
{'loss': 1.2358, 'learning_rate': 2.385143683354419e-05, 'epoch': 0.41}
{'loss': 1.1675, 'learning_rate': 2.384872582685704e-05, 'epoch': 0.41}
{'loss': 1.1806, 'learning_rate': 2.384601482016989e-05, 'epoch': 0.41}
{'loss': 0.9505, 'learning_rate': 2.3843303813482742e-05, 'epoch': 0.41}
{'loss': 1.1672, 'learning_rate': 2.384059280679559e-05, 'epoch': 0.41}
{'loss': 2.185, 'learning_rate': 2.3837881800108442e-05, 'epoch': 0.41}
{'loss': 1.0071, 'learning_rate': 2.3835170793421294e-05, 'epoch': 0.41}
{'loss': 1.3398, 'learning_rate': 2.383245978673414e-05, 'epoch': 0.41}
{'loss': 1.3656, 'learning_rate': 2.382974878004699e-05, 'epoch': 0.41}
{'loss': 1.3683, 'learning_rate': 2.382703777335984e-05, 'epoch': 0.41}
{'loss': 1.0329, 'learning_rate': 2.382432676667269e-05, 'epoch': 0.41}
{'loss': 1.182, 'learning_rate': 2.3821615759985543e-05, 'epoch': 0.41}
{'loss': 1.9082, 'learning_rate': 2.381890475329839e-05, 'epoch': 0.41}
{'loss': 1.591, 'learning_rate': 2.3816193746611243e-05, 'epoch': 0.41}
{'loss': 1.397, 'learning_rate': 2.3813482739924095e-05, 'epoch': 0.41}
{'loss': 0.9524, 'learning_rate': 2.381077173323694e-05, 'epoch': 0.41}
{'loss': 0.6558, 'learning_rate': 2.3808060726549792e-05, 'epoch': 0.41}
{'loss': 1.3888, 'learning_rate': 2.3805349719862644e-05, 'epoch': 0.41}
{'loss': 0.799, 'learning_rate': 2.3802638713175492e-05, 'epoch': 0.41}
{'loss': 1.2298, 'learning_rate': 2.3799927706488344e-05, 'epoch': 0.41}
{'loss': 1.437, 'learning_rate': 2.3797216699801193e-05, 'epoch': 0.41}
{'loss': 1.1332, 'learning_rate': 2.3794505693114045e-05, 'epoch': 0.41}
{'loss': 1.0847, 'learning_rate': 2.3791794686426896e-05, 'epoch': 0.41}
{'loss': 1.5278, 'learning_rate': 2.378908367973974e-05, 'epoch': 0.41}
{'loss': 1.1832, 'learning_rate': 2.3786372673052593e-05, 'epoch': 0.41}
{'loss': 1.2184, 'learning_rate': 2.3783661666365445e-05, 'epoch': 0.41}
{'loss': 1.2552, 'learning_rate': 2.3780950659678293e-05, 'epoch': 0.41}
{'loss': 1.9193, 'learning_rate': 2.3778239652991145e-05, 'epoch': 0.41}
{'loss': 0.5525, 'learning_rate': 2.3775528646303997e-05, 'epoch': 0.41}
{'loss': 1.1558, 'learning_rate': 2.3772817639616846e-05, 'epoch': 0.42}
{'loss': 0.8142, 'learning_rate': 2.3770106632929697e-05, 'epoch': 0.42}
{'loss': 0.6157, 'learning_rate': 2.3767395626242542e-05, 'epoch': 0.42}
{'loss': 0.6937, 'learning_rate': 2.3764684619555394e-05, 'epoch': 0.42}
{'loss': 1.5899, 'learning_rate': 2.3761973612868246e-05, 'epoch': 0.42}
{'loss': 1.4488, 'learning_rate': 2.3759262606181095e-05, 'epoch': 0.42}
{'loss': 1.0313, 'learning_rate': 2.3756551599493946e-05, 'epoch': 0.42}
{'loss': 1.4468, 'learning_rate': 2.3753840592806798e-05, 'epoch': 0.42}
{'loss': 1.7909, 'learning_rate': 2.3751129586119647e-05, 'epoch': 0.42}
{'loss': 1.1526, 'learning_rate': 2.37484185794325e-05, 'epoch': 0.42}
{'loss': 0.9367, 'learning_rate': 2.3745707572745347e-05, 'epoch': 0.42}
{'loss': 1.3155, 'learning_rate': 2.3742996566058195e-05, 'epoch': 0.42}
{'loss': 1.8858, 'learning_rate': 2.3740285559371047e-05, 'epoch': 0.42}
{'loss': 0.7563, 'learning_rate': 2.3737574552683896e-05, 'epoch': 0.42}
{'loss': 1.9904, 'learning_rate': 2.3734863545996747e-05, 'epoch': 0.42}
{'loss': 1.2404, 'learning_rate': 2.37321525393096e-05, 'epoch': 0.42}
{'loss': 1.5479, 'learning_rate': 2.3729441532622448e-05, 'epoch': 0.42}
{'loss': 0.5804, 'learning_rate': 2.37267305259353e-05, 'epoch': 0.42}
{'loss': 0.7561, 'learning_rate': 2.3724019519248148e-05, 'epoch': 0.42}
{'loss': 0.4602, 'learning_rate': 2.3721308512560996e-05, 'epoch': 0.42}
{'loss': 1.0947, 'learning_rate': 2.3718597505873848e-05, 'epoch': 0.42}
{'loss': 1.8721, 'learning_rate': 2.37158864991867e-05, 'epoch': 0.42}
{'loss': 0.8899, 'learning_rate': 2.371317549249955e-05, 'epoch': 0.42}
{'loss': 1.2732, 'learning_rate': 2.37104644858124e-05, 'epoch': 0.42}
{'loss': 1.3942, 'learning_rate': 2.370775347912525e-05, 'epoch': 0.42}
{'loss': 0.7586, 'learning_rate': 2.3705042472438097e-05, 'epoch': 0.42}
{'loss': 1.1311, 'learning_rate': 2.370233146575095e-05, 'epoch': 0.42}
{'loss': 0.996, 'learning_rate': 2.3699620459063798e-05, 'epoch': 0.42}
{'loss': 0.6677, 'learning_rate': 2.369690945237665e-05, 'epoch': 0.42}
{'loss': 0.7442, 'learning_rate': 2.36941984456895e-05, 'epoch': 0.42}
{'loss': 1.1012, 'learning_rate': 2.369148743900235e-05, 'epoch': 0.42}
{'loss': 0.993, 'learning_rate': 2.36887764323152e-05, 'epoch': 0.42}
{'loss': 1.9037, 'learning_rate': 2.3686065425628053e-05, 'epoch': 0.42}
{'loss': 1.5857, 'learning_rate': 2.36833544189409e-05, 'epoch': 0.42}
{'loss': 1.3356, 'learning_rate': 2.368064341225375e-05, 'epoch': 0.42}
{'loss': 2.1125, 'learning_rate': 2.36779324055666e-05, 'epoch': 0.42}
{'loss': 1.1604, 'learning_rate': 2.367522139887945e-05, 'epoch': 0.42}
{'loss': 1.1784, 'learning_rate': 2.3672510392192302e-05, 'epoch': 0.42}
{'loss': 0.9955, 'learning_rate': 2.366979938550515e-05, 'epoch': 0.42}
{'loss': 1.8163, 'learning_rate': 2.3667088378818003e-05, 'epoch': 0.42}
{'loss': 1.5226, 'learning_rate': 2.3664377372130854e-05, 'epoch': 0.42}
{'loss': 1.2592, 'learning_rate': 2.36616663654437e-05, 'epoch': 0.42}
{'loss': 0.8219, 'learning_rate': 2.365895535875655e-05, 'epoch': 0.42}
{'loss': 1.2998, 'learning_rate': 2.3656244352069403e-05, 'epoch': 0.42}
{'loss': 0.5786, 'learning_rate': 2.365353334538225e-05, 'epoch': 0.42}
{'loss': 0.7553, 'learning_rate': 2.3650822338695103e-05, 'epoch': 0.42}
{'loss': 0.8261, 'learning_rate': 2.3648111332007952e-05, 'epoch': 0.42}
{'loss': 0.8902, 'learning_rate': 2.3645400325320804e-05, 'epoch': 0.42}
{'loss': 1.4218, 'learning_rate': 2.3642689318633655e-05, 'epoch': 0.42}
{'loss': 2.0535, 'learning_rate': 2.36399783119465e-05, 'epoch': 0.42}
{'loss': 1.106, 'learning_rate': 2.3637267305259352e-05, 'epoch': 0.42}
{'loss': 0.9401, 'learning_rate': 2.3634556298572204e-05, 'epoch': 0.42}
{'loss': 1.1768, 'learning_rate': 2.3631845291885053e-05, 'epoch': 0.42}
{'loss': 1.1693, 'learning_rate': 2.3629134285197904e-05, 'epoch': 0.42}
{'loss': 1.5217, 'learning_rate': 2.3626423278510756e-05, 'epoch': 0.42}
{'loss': 1.3653, 'learning_rate': 2.3623712271823605e-05, 'epoch': 0.43}
{'loss': 1.1751, 'learning_rate': 2.3621001265136456e-05, 'epoch': 0.43}
{'loss': 0.6026, 'learning_rate': 2.36182902584493e-05, 'epoch': 0.43}
{'loss': 1.0704, 'learning_rate': 2.3615579251762153e-05, 'epoch': 0.43}
{'loss': 0.6952, 'learning_rate': 2.3612868245075005e-05, 'epoch': 0.43}
{'loss': 1.0285, 'learning_rate': 2.3610157238387854e-05, 'epoch': 0.43}
{'loss': 0.8762, 'learning_rate': 2.3607446231700705e-05, 'epoch': 0.43}
{'loss': 1.2487, 'learning_rate': 2.3604735225013557e-05, 'epoch': 0.43}
{'loss': 1.5772, 'learning_rate': 2.3602024218326406e-05, 'epoch': 0.43}
{'loss': 1.4174, 'learning_rate': 2.3599313211639258e-05, 'epoch': 0.43}
{'loss': 0.9224, 'learning_rate': 2.3596602204952106e-05, 'epoch': 0.43}
{'loss': 1.2349, 'learning_rate': 2.3593891198264954e-05, 'epoch': 0.43}

 21%|██▏       | 2364/11066 [08:41<32:11,  4.51it/s]
 21%|██▏       | 2365/11066 [08:41<32:13,  4.50it/s]
                                                    

 21%|██▏       | 2365/11066 [08:41<32:13,  4.50it/s]
 21%|██▏       | 2366/11066 [08:41<31:58,  4.53it/s]
                                                    

 21%|██▏       | 2366/11066 [08:41<31:58,  4.53it/s]
 21%|██▏       | 2367/11066 [08:41<32:11,  4.50it/s]
                                                    

 21%|██▏       | 2367/11066 [08:41<32:11,  4.50it/s]
 21%|██▏       | 2368/11066 [08:42<31:37,  4.58it/s]
                                                    

 21%|██▏       | 2368/11066 [08:42<31:37,  4.58it/s]
 21%|██▏       | 2369/11066 [08:42<32:00,  4.53it/s]
                                                    

 21%|██▏       | 2369/11066 [08:42<32:00,  4.53it/s]
 21%|██▏       | 2370/11066 [08:42<32:06,  4.51it/s]
                                                    

 21%|██▏       | 2370/11066 [08:42<32:06,  4.51it/s]
 21%|██▏       | 2371/11066 [08:42<32:10,  4.51it/s]
                                                    

 21%|██▏       | 2371/11066 [08:42<32:10,  4.51it/s]
 21%|██▏       | 2372/11066 [08:43<31:43,  4.57it/s]
                                                    

 21%|██▏       | 2372/11066 [08:43<31:43,  4.57it/s]
 21%|██▏       | 2373/11066 [08:43<31:53,  4.54it/s]
                                                    

 21%|██▏       | 2373/11066 [08:43<31:53,  4.54it/s]
 21%|██▏       | 2374/11066 [08:43<31:31,  4.59it/s]
                                                    

 21%|██▏       | 2374/11066 [08:43<31:31,  4.59it/s]
 21%|██▏       | 2375/11066 [08:43<31:44,  4.56it/s]
                                                    

 21%|██▏       | 2375/11066 [08:43<31:44,  4.56it/s]
 21%|██▏       | 2376/11066 [08:43<31:55,  4.54it/s]
                                                    

 21%|██▏       | 2376/11066 [08:43<31:55,  4.54it/s]
 21%|██▏       | 2377/11066 [08:44<31:59,  4.53it/s]
                                                    

 21%|██▏       | 2377/11066 [08:44<31:59,  4.53it/s]
 21%|██▏       | 2378/11066 [08:44<31:36,  4.58it/s]
                                                    

 21%|██▏       | 2378/11066 [08:44<31:36,  4.58it/s]
 21%|██▏       | 2379/11066 [08:44<31:51,  4.55it/s]
                                                    

 21%|██▏       | 2379/11066 [08:44<31:51,  4.55it/s]
 22%|██▏       | 2380/11066 [08:44<31:45,  4.56it/s]
                                                    

 22%|██▏       | 2380/11066 [08:44<31:45,  4.56it/s]
 22%|██▏       | 2381/11066 [08:45<31:41,  4.57it/s]
                                                    

 22%|██▏       | 2381/11066 [08:45<31:41,  4.57it/s]
 22%|██▏       | 2382/11066 [08:45<31:53,  4.54it/s]
                                                    

 22%|██▏       | 2382/11066 [08:45<31:53,  4.54it/s]
 22%|██▏       | 2383/11066 [08:45<32:09,  4.50it/s]
                                                    

 22%|██▏       | 2383/11066 [08:45<32:09,  4.50it/s]
 22%|██▏       | 2384/11066 [08:45<32:37,  4.44it/s]
                                                    

 22%|██▏       | 2384/11066 [08:45<32:37,  4.44it/s]
 22%|██▏       | 2385/11066 [08:45<32:56,  4.39it/s]
                                                    

 22%|██▏       | 2385/11066 [08:45<32:56,  4.39it/s]
 22%|██▏       | 2386/11066 [08:46<33:09,  4.36it/s]
                                                    

 22%|██▏       | 2386/11066 [08:46<33:09,  4.36it/s]
 22%|██▏       | 2387/11066 [08:46<32:45,  4.41it/s]
                                                    

 22%|██▏       | 2387/11066 [08:46<32:45,  4.41it/s]
 22%|██▏       | 2388/11066 [08:46<32:42,  4.42it/s]
                                                    

 22%|██▏       | 2388/11066 [08:46<32:42,  4.42it/s]
 22%|██▏       | 2389/11066 [08:46<32:36,  4.44it/s]
                                                    

 22%|██▏       | 2389/11066 [08:46<32:36,  4.44it/s]
 22%|██▏       | 2390/11066 [08:47<32:30,  4.45it/s]
                                                    

 22%|██▏       | 2390/11066 [08:47<32:30,  4.45it/s]
 22%|██▏       | 2391/11066 [08:47<32:25,  4.46it/s]
                                                    

 22%|██▏       | 2391/11066 [08:47<32:25,  4.46it/s]
 22%|██▏       | 2392/11066 [08:47<32:19,  4.47it/s]
                                                    

 22%|██▏       | 2392/11066 [08:47<32:19,  4.47it/s]
 22%|██▏       | 2393/11066 [08:47<32:16,  4.48it/s]
                                                    

 22%|██▏       | 2393/11066 [08:47<32:16,  4.48it/s]
 22%|██▏       | 2394/11066 [08:47<32:15,  4.48it/s]
                                                    

 22%|██▏       | 2394/11066 [08:47<32:15,  4.48it/s]
 22%|██▏       | 2395/11066 [08:48<32:15,  4.48it/s]
                                                    

 22%|██▏       | 2395/11066 [08:48<32:15,  4.48it/s]
 22%|██▏       | 2396/11066 [08:48<32:17,  4.47it/s]
                                                    

 22%|██▏       | 2396/11066 [08:48<32:17,  4.47it/s]
 22%|██▏       | 2397/11066 [08:48<32:14,  4.48it/s]
                                                    

 22%|██▏       | 2397/11066 [08:48<32:14,  4.48it/s]
 22%|██▏       | 2398/11066 [08:48<32:11,  4.49it/s]
                                                    

 22%|██▏       | 2398/11066 [08:48<32:11,  4.49it/s]
 22%|██▏       | 2399/11066 [08:49<32:12,  4.49it/s]
                                                    

 22%|██▏       | 2399/11066 [08:49<32:12,  4.49it/s]
 22%|██▏       | 2400/11066 [08:49<32:12,  4.49it/s]
                                                    

 22%|██▏       | 2400/11066 [08:49<32:12,  4.49it/s]
 22%|██▏       | 2401/11066 [08:49<31:44,  4.55it/s]
                                                    

 22%|██▏       | 2401/11066 [08:49<31:44,  4.55it/s]
 22%|██▏       | 2402/11066 [08:49<31:51,  4.53it/s]
                                                    

 22%|██▏       | 2402/11066 [08:49<31:51,  4.53it/s]
 22%|██▏       | 2403/11066 [08:49<31:56,  4.52it/s]
                                                    

 22%|██▏       | 2403/11066 [08:49<31:56,  4.52it/s]
 22%|██▏       | 2404/11066 [08:50<31:43,  4.55it/s]
                                                    

 22%|██▏       | 2404/11066 [08:50<31:43,  4.55it/s]
 22%|██▏       | 2405/11066 [08:50<31:30,  4.58it/s]
                                                    

 22%|██▏       | 2405/11066 [08:50<31:30,  4.58it/s]
 22%|██▏       | 2406/11066 [08:50<31:44,  4.55it/s]
                                                    

 22%|██▏       | 2406/11066 [08:50<31:44,  4.55it/s]
 22%|██▏       | 2407/11066 [08:50<31:37,  4.56it/s]
                                                    

 22%|██▏       | 2407/11066 [08:50<31:37,  4.56it/s]
 22%|██▏       | 2408/11066 [08:51<31:34,  4.57it/s]
                                                    

 22%|██▏       | 2408/11066 [08:51<31:34,  4.57it/s]
 22%|██▏       | 2409/11066 [08:51<31:45,  4.54it/s]
                                                    

 22%|██▏       | 2409/11066 [08:51<31:45,  4.54it/s]
 22%|██▏       | 2410/11066 [08:51<31:54,  4.52it/s]
                                                    

 22%|██▏       | 2410/11066 [08:51<31:54,  4.52it/s]
 22%|██▏       | 2411/11066 [08:51<31:34,  4.57it/s]
                                                    

 22%|██▏       | 2411/11066 [08:51<31:34,  4.57it/s]
 22%|██▏       | 2412/11066 [08:51<31:42,  4.55it/s]
                                                    

 22%|██▏       | 2412/11066 [08:51<31:42,  4.55it/s]
 22%|██▏       | 2413/11066 [08:52<31:32,  4.57it/s]
                                                    

 22%|██▏       | 2413/11066 [08:52<31:32,  4.57it/s]
 22%|██▏       | 2414/11066 [08:52<31:29,  4.58it/s]
                                                    

 22%|██▏       | 2414/11066 [08:52<31:29,  4.58it/s]
 22%|██▏       | 2415/11066 [08:52<31:41,  4.55it/s]
                                                    

 22%|██▏       | 2415/11066 [08:52<31:41,  4.55it/s]
 22%|██▏       | 2416/11066 [08:52<31:33,  4.57it/s]
                                                    

 22%|██▏       | 2416/11066 [08:52<31:33,  4.57it/s]
 22%|██▏       | 2417/11066 [08:53<31:19,  4.60it/s]
                                                    

 22%|██▏       | 2417/11066 [08:53<31:19,  4.60it/s]
 22%|██▏       | 2418/11066 [08:53<31:09,  4.63it/s]
                                                    

 22%|██▏       | 2418/11066 [08:53<31:09,  4.63it/s]
 22%|██▏       | 2419/11066 [08:53<31:08,  4.63it/s]
                                                    

 22%|██▏       | 2419/11066 [08:53<31:08,  4.63it/s]
 22%|██▏       | 2420/11066 [08:53<31:27,  4.58it/s]
                                                    

 22%|██▏       | 2420/11066 [08:53<31:27,  4.58it/s]
 22%|██▏       | 2421/11066 [08:53<31:39,  4.55it/s]
                                                    

 22%|██▏       | 2421/11066 [08:53<31:39,  4.55it/s]
 22%|██▏       | 2422/11066 [08:54<31:45,  4.54it/s]
                                                    

 22%|██▏       | 2422/11066 [08:54<31:45,  4.54it/s]
 22%|██▏       | 2423/11066 [08:54<31:36,  4.56it/s]
                                                    

 22%|██▏       | 2423/11066 [08:54<31:36,  4.56it/s]
 22%|██▏       | 2424/11066 [08:54<31:18,  4.60it/s]
                                                    

 22%|██▏       | 2424/11066 [08:54<31:18,  4.60it/s]
 22%|██▏       | 2425/11066 [08:54<31:38,  4.55it/s]
                                                    

 22%|██▏       | 2425/11066 [08:54<31:38,  4.55it/s]
 22%|██▏       | 2426/11066 [08:55<31:51,  4.52it/s]
                                                    

 22%|██▏       | 2426/11066 [08:55<31:51,  4.52it/s]
 22%|██▏       | 2427/11066 [08:55<31:57,  4.51it/s]
                                                    

 22%|██▏       | 2427/11066 [08:55<31:57,  4.51it/s]
 22%|██▏       | 2428/11066 [08:55<31:31,  4.57it/s]
                                                    

 22%|██▏       | 2428/11066 [08:55<31:31,  4.57it/s]
 22%|██▏       | 2429/11066 [08:55<31:40,  4.54it/s]
                                                    

 22%|██▏       | 2429/11066 [08:55<31:40,  4.54it/s]
 22%|██▏       | 2430/11066 [08:55<31:21,  4.59it/s]
                                                    

 22%|██▏       | 2430/11066 [08:55<31:21,  4.59it/s]
 22%|██▏       | 2431/11066 [08:56<31:31,  4.56it/s]
                                                    

 22%|██▏       | 2431/11066 [08:56<31:31,  4.56it/s]
 22%|██▏       | 2432/11066 [08:56<31:16,  4.60it/s]
                                                    

 22%|██▏       | 2432/11066 [08:56<31:16,  4.60it/s]
 22%|██▏       | 2433/11066 [08:56<31:31,  4.56it/s]
                                                    

 22%|██▏       | 2433/11066 [08:56<31:31,  4.56it/s]
 22%|██▏       | 2434/11066 [08:56<31:34,  4.56it/s]
                                                    

 22%|██▏       | 2434/11066 [08:56<31:34,  4.56it/s]
 22%|██▏       | 2435/11066 [08:56<31:45,  4.53it/s]
                                                    

 22%|██▏       | 2435/11066 [08:56<31:45,  4.53it/s]
 22%|██▏       | 2436/11066 [08:57<31:24,  4.58it/s]
                                                    

 22%|██▏       | 2436/11066 [08:57<31:24,  4.58it/s]
 22%|██▏       | 2437/11066 [08:57<31:09,  4.62it/s]
                                                    

 22%|██▏       | 2437/11066 [08:57<31:09,  4.62it/s]
 22%|██▏       | 2438/11066 [08:57<30:59,  4.64it/s]
                                                    

 22%|██▏       | 2438/11066 [08:57<30:59,  4.64it/s]
 22%|██▏       | 2439/11066 [08:57<31:21,  4.58it/s]
                                                    

 22%|██▏       | 2439/11066 [08:57<31:21,  4.58it/s]
 22%|██▏       | 2440/11066 [08:58<31:33,  4.56it/s]
                                                    

 22%|██▏       | 2440/11066 [08:58<31:33,  4.56it/s]
 22%|██▏       | 2441/11066 [08:58<31:25,  4.57it/s]
                                                    

 22%|██▏       | 2441/11066 [08:58<31:25,  4.57it/s]
 22%|██▏       | 2442/11066 [08:58<31:00,  4.64it/s]
                                                    

 22%|██▏       | 2442/11066 [08:58<31:00,  4.64it/s]
 22%|██▏       | 2443/11066 [08:58<31:08,  4.62it/s]
                                                    

 22%|██▏       | 2443/11066 [08:58<31:08,  4.62it/s]
 22%|██▏       | 2444/11066 [08:58<30:56,  4.64it/s]
                                                    

 22%|██▏       | 2444/11066 [08:58<30:56,  4.64it/s]
 22%|██▏       | 2445/11066 [08:59<31:23,  4.58it/s]
                                                    

 22%|██▏       | 2445/11066 [08:59<31:23,  4.58it/s]
 22%|██▏       | 2446/11066 [08:59<31:35,  4.55it/s]
                                                    

 22%|██▏       | 2446/11066 [08:59<31:35,  4.55it/s]
 22%|██▏       | 2447/11066 [08:59<31:43,  4.53it/s]
                                                    

 22%|██▏       | 2447/11066 [08:59<31:43,  4.53it/s]
 22%|██▏       | 2448/11066 [08:59<31:25,  4.57it/s]
                                                    

 22%|██▏       | 2448/11066 [08:59<31:25,  4.57it/s]
 22%|██▏       | 2449/11066 [09:00<31:27,  4.57it/s]
                                                    

 22%|██▏       | 2449/11066 [09:00<31:27,  4.57it/s]
 22%|██▏       | 2450/11066 [09:00<31:12,  4.60it/s]
                                                    

 22%|██▏       | 2450/11066 [09:00<31:12,  4.60it/s]
 22%|██▏       | 2451/11066 [09:00<31:28,  4.56it/s]
                                                    

 22%|██▏       | 2451/11066 [09:00<31:28,  4.56it/s]
 22%|██▏       | 2452/11066 [09:00<31:39,  4.53it/s]
                                                    

 22%|██▏       | 2452/11066 [09:00<31:39,  4.53it/s]
 22%|██▏       | 2453/11066 [09:00<32:11,  4.46it/s]
                                                    

 22%|██▏       | 2453/11066 [09:00<32:11,  4.46it/s]
 22%|██▏       | 2454/11066 [09:01<32:07,  4.47it/s]
                                                    

 22%|██▏       | 2454/11066 [09:01<32:07,  4.47it/s]
 22%|██▏       | 2455/11066 [09:01<32:02,  4.48it/s]
                                                    

 22%|██▏       | 2455/11066 [09:01<32:02,  4.48it/s]
 22%|██▏       | 2456/11066 [09:01<31:43,  4.52it/s]
                                                    

 22%|██▏       | 2456/11066 [09:01<31:43,  4.52it/s]
 22%|██▏       | 2457/11066 [09:01<31:24,  4.57it/s]
                                                    

 22%|██▏       | 2457/11066 [09:01<31:24,  4.57it/s]
 22%|██▏       | 2458/11066 [09:02<31:38,  4.54it/s]
                                                    

 22%|██▏       | 2458/11066 [09:02<31:38,  4.54it/s]
 22%|██▏       | 2459/11066 [09:02<31:45,  4.52it/s]
                                                    

 22%|██▏       | 2459/11066 [09:02<31:45,  4.52it/s]
 22%|██▏       | 2460/11066 [09:02<31:51,  4.50it/s]
                                                    

 22%|██▏       | 2460/11066 [09:02<31:51,  4.50it/s]
 22%|██▏       | 2461/11066 [09:02<31:54,  4.50it/s]
                                                    

 22%|██▏       | 2461/11066 [09:02<31:54,  4.50it/s]
 22%|██▏       | 2462/11066 [09:02<31:34,  4.54it/s]
                                                    

 22%|██▏       | 2462/11066 [09:02<31:34,  4.54it/s]
 22%|██▏       | 2463/11066 [09:03<31:42,  4.52it/s]
                                                    

 22%|██▏       | 2463/11066 [09:03<31:42,  4.52it/s]
 22%|██▏       | 2464/11066 [09:03<31:47,  4.51it/s]
                                                    

 22%|██▏       | 2464/11066 [09:03<31:47,  4.51it/s]
 22%|██▏       | 2465/11066 [09:03<31:47,  4.51it/s]
                                                    

 22%|██▏       | 2465/11066 [09:03<31:47,  4.51it/s]
 22%|██▏       | 2466/11066 [09:03<31:37,  4.53it/s]
                                                    

 22%|██▏       | 2466/11066 [09:03<31:37,  4.53it/s]
 22%|██▏       | 2467/11066 [09:04<31:52,  4.50it/s]
                                                    

 22%|██▏       | 2467/11066 [09:04<31:52,  4.50it/s]
 22%|██▏       | 2468/11066 [09:04<31:51,  4.50it/s]
                                                    

 22%|██▏       | 2468/11066 [09:04<31:51,  4.50it/s]
 22%|██▏       | 2469/11066 [09:04<31:53,  4.49it/s]
                                                    

 22%|██▏       | 2469/11066 [09:04<31:53,  4.49it/s]
 22%|██▏       | 2470/11066 [09:04<31:29,  4.55it/s]
                                                    

 22%|██▏       | 2470/11066 [09:04<31:29,  4.55it/s]
 22%|██▏       | 2471/11066 [09:04<31:27,  4.55it/s]
                                                    

 22%|██▏       | 2471/11066 [09:04<31:27,  4.55it/s]
 22%|██▏       | 2472/11066 [09:05<31:18,  4.57it/s]
                                                    

 22%|██▏       | 2472/11066 [09:05<31:18,  4.57it/s]
 22%|██▏       | 2473/11066 [09:05<31:34,  4.54it/s]
                                                    

 22%|██▏       | 2473/11066 [09:05<31:34,  4.54it/s]
 22%|██▏       | 2474/11066 [09:05<31:39,  4.52it/s]
                                                    

 22%|██▏       | 2474/11066 [09:05<31:39,  4.52it/s]
 22%|██▏       | 2475/11066 [09:05<31:44,  4.51it/s]
                                                    

 22%|██▏       | 2475/11066 [09:05<31:44,  4.51it/s]
 22%|██▏       | 2476/11066 [09:06<31:30,  4.54it/s]
                                                    

 22%|██▏       | 2476/11066 [09:06<31:30,  4.54it/s]
 22%|██▏       | 2477/11066 [09:06<31:13,  4.58it/s]
                                                    
{'loss': 0.9831, 'learning_rate': 2.3591180191577806e-05, 'epoch': 0.43}
{'loss': 0.8056, 'learning_rate': 2.3588469184890655e-05, 'epoch': 0.43}
{'loss': 0.8357, 'learning_rate': 2.3585758178203507e-05, 'epoch': 0.43}
{'loss': 1.8032, 'learning_rate': 2.358304717151636e-05, 'epoch': 0.43}
{'loss': 1.4574, 'learning_rate': 2.3580336164829207e-05, 'epoch': 0.43}
{'loss': 1.0022, 'learning_rate': 2.357762515814206e-05, 'epoch': 0.43}
{'loss': 2.7011, 'learning_rate': 2.3574914151454907e-05, 'epoch': 0.43}
{'loss': 1.3247, 'learning_rate': 2.3572203144767756e-05, 'epoch': 0.43}
{'loss': 1.3479, 'learning_rate': 2.3569492138080607e-05, 'epoch': 0.43}
{'loss': 1.1369, 'learning_rate': 2.356678113139346e-05, 'epoch': 0.43}
{'loss': 0.927, 'learning_rate': 2.3564070124706308e-05, 'epoch': 0.43}
{'loss': 1.6194, 'learning_rate': 2.356135911801916e-05, 'epoch': 0.43}
{'loss': 1.6716, 'learning_rate': 2.3558648111332008e-05, 'epoch': 0.43}
{'loss': 1.3711, 'learning_rate': 2.355593710464486e-05, 'epoch': 0.43}
{'loss': 1.3161, 'learning_rate': 2.3553226097957708e-05, 'epoch': 0.43}
{'loss': 1.923, 'learning_rate': 2.3550515091270557e-05, 'epoch': 0.43}
{'loss': 1.018, 'learning_rate': 2.354780408458341e-05, 'epoch': 0.43}
{'loss': 0.9533, 'learning_rate': 2.354509307789626e-05, 'epoch': 0.43}
{'loss': 1.6427, 'learning_rate': 2.354238207120911e-05, 'epoch': 0.43}
{'loss': 1.7822, 'learning_rate': 2.353967106452196e-05, 'epoch': 0.43}
{'loss': 1.1497, 'learning_rate': 2.3536960057834812e-05, 'epoch': 0.43}
{'loss': 1.1434, 'learning_rate': 2.353424905114766e-05, 'epoch': 0.43}
{'loss': 1.343, 'learning_rate': 2.353153804446051e-05, 'epoch': 0.43}
{'loss': 0.659, 'learning_rate': 2.352882703777336e-05, 'epoch': 0.43}
{'loss': 1.2358, 'learning_rate': 2.352611603108621e-05, 'epoch': 0.43}
{'loss': 1.0148, 'learning_rate': 2.352340502439906e-05, 'epoch': 0.43}
{'loss': 1.0435, 'learning_rate': 2.352069401771191e-05, 'epoch': 0.43}
{'loss': 0.6263, 'learning_rate': 2.351798301102476e-05, 'epoch': 0.43}
{'loss': 1.5884, 'learning_rate': 2.3515272004337613e-05, 'epoch': 0.43}
{'loss': 0.7568, 'learning_rate': 2.3512560997650462e-05, 'epoch': 0.43}
{'loss': 0.9756, 'learning_rate': 2.350984999096331e-05, 'epoch': 0.43}
{'loss': 1.2026, 'learning_rate': 2.3507138984276162e-05, 'epoch': 0.43}
{'loss': 1.0988, 'learning_rate': 2.350442797758901e-05, 'epoch': 0.43}
{'loss': 0.9797, 'learning_rate': 2.3501716970901862e-05, 'epoch': 0.43}
{'loss': 1.2356, 'learning_rate': 2.3499005964214714e-05, 'epoch': 0.43}
{'loss': 0.9085, 'learning_rate': 2.3496294957527563e-05, 'epoch': 0.43}
{'loss': 1.3297, 'learning_rate': 2.3493583950840414e-05, 'epoch': 0.43}
{'loss': 0.8318, 'learning_rate': 2.3490872944153263e-05, 'epoch': 0.43}
{'loss': 1.0876, 'learning_rate': 2.348816193746611e-05, 'epoch': 0.43}
{'loss': 1.3799, 'learning_rate': 2.3485450930778963e-05, 'epoch': 0.43}
{'loss': 1.83, 'learning_rate': 2.348273992409181e-05, 'epoch': 0.43}
{'loss': 1.8694, 'learning_rate': 2.3480028917404663e-05, 'epoch': 0.43}
{'loss': 1.3406, 'learning_rate': 2.3477317910717515e-05, 'epoch': 0.43}
{'loss': 1.4933, 'learning_rate': 2.3474606904030364e-05, 'epoch': 0.44}
{'loss': 1.1008, 'learning_rate': 2.3471895897343216e-05, 'epoch': 0.44}
{'loss': 1.688, 'learning_rate': 2.3469184890656067e-05, 'epoch': 0.44}
{'loss': 0.7195, 'learning_rate': 2.3466473883968912e-05, 'epoch': 0.44}
{'loss': 1.2534, 'learning_rate': 2.3463762877281764e-05, 'epoch': 0.44}
{'loss': 1.1997, 'learning_rate': 2.3461051870594613e-05, 'epoch': 0.44}
{'loss': 1.089, 'learning_rate': 2.3458340863907465e-05, 'epoch': 0.44}
{'loss': 2.0519, 'learning_rate': 2.3455629857220316e-05, 'epoch': 0.44}
{'loss': 1.2082, 'learning_rate': 2.3452918850533165e-05, 'epoch': 0.44}
{'loss': 1.1277, 'learning_rate': 2.3450207843846017e-05, 'epoch': 0.44}
{'loss': 0.9234, 'learning_rate': 2.344749683715887e-05, 'epoch': 0.44}
{'loss': 1.5067, 'learning_rate': 2.3444785830471714e-05, 'epoch': 0.44}
{'loss': 1.1323, 'learning_rate': 2.3442074823784565e-05, 'epoch': 0.44}
{'loss': 1.0997, 'learning_rate': 2.3439363817097417e-05, 'epoch': 0.44}
{'loss': 1.2511, 'learning_rate': 2.3436652810410266e-05, 'epoch': 0.44}
{'loss': 1.1347, 'learning_rate': 2.3433941803723117e-05, 'epoch': 0.44}
{'loss': 1.1108, 'learning_rate': 2.3431230797035966e-05, 'epoch': 0.44}
{'loss': 1.4562, 'learning_rate': 2.3428519790348818e-05, 'epoch': 0.44}
{'loss': 1.5261, 'learning_rate': 2.342580878366167e-05, 'epoch': 0.44}
{'loss': 1.6823, 'learning_rate': 2.3423097776974515e-05, 'epoch': 0.44}
{'loss': 1.0256, 'learning_rate': 2.3420386770287366e-05, 'epoch': 0.44}
{'loss': 0.8976, 'learning_rate': 2.3417675763600218e-05, 'epoch': 0.44}
{'loss': 0.9809, 'learning_rate': 2.3414964756913067e-05, 'epoch': 0.44}
{'loss': 1.3989, 'learning_rate': 2.341225375022592e-05, 'epoch': 0.44}
{'loss': 1.0022, 'learning_rate': 2.340954274353877e-05, 'epoch': 0.44}
{'loss': 0.9726, 'learning_rate': 2.340683173685162e-05, 'epoch': 0.44}
{'loss': 1.3563, 'learning_rate': 2.340412073016447e-05, 'epoch': 0.44}
{'loss': 2.009, 'learning_rate': 2.3401409723477316e-05, 'epoch': 0.44}
{'loss': 1.0674, 'learning_rate': 2.3398698716790168e-05, 'epoch': 0.44}
{'loss': 0.9326, 'learning_rate': 2.339598771010302e-05, 'epoch': 0.44}
{'loss': 1.3494, 'learning_rate': 2.3393276703415868e-05, 'epoch': 0.44}
{'loss': 0.5545, 'learning_rate': 2.339056569672872e-05, 'epoch': 0.44}
{'loss': 0.5226, 'learning_rate': 2.338785469004157e-05, 'epoch': 0.44}
{'loss': 0.9466, 'learning_rate': 2.338514368335442e-05, 'epoch': 0.44}
{'loss': 1.41, 'learning_rate': 2.3382432676667272e-05, 'epoch': 0.44}
{'loss': 1.3288, 'learning_rate': 2.337972166998012e-05, 'epoch': 0.44}
{'loss': 1.1152, 'learning_rate': 2.337701066329297e-05, 'epoch': 0.44}
{'loss': 1.3215, 'learning_rate': 2.337429965660582e-05, 'epoch': 0.44}
{'loss': 0.8241, 'learning_rate': 2.337158864991867e-05, 'epoch': 0.44}
{'loss': 0.8262, 'learning_rate': 2.336887764323152e-05, 'epoch': 0.44}
{'loss': 1.5372, 'learning_rate': 2.3366166636544373e-05, 'epoch': 0.44}
{'loss': 1.6053, 'learning_rate': 2.336345562985722e-05, 'epoch': 0.44}
{'loss': 1.5333, 'learning_rate': 2.336074462317007e-05, 'epoch': 0.44}
{'loss': 1.6691, 'learning_rate': 2.335803361648292e-05, 'epoch': 0.44}
{'loss': 1.4022, 'learning_rate': 2.335532260979577e-05, 'epoch': 0.44}
{'loss': 1.8385, 'learning_rate': 2.335261160310862e-05, 'epoch': 0.44}
{'loss': 1.2039, 'learning_rate': 2.3349900596421473e-05, 'epoch': 0.44}
{'loss': 1.3524, 'learning_rate': 2.3347189589734322e-05, 'epoch': 0.44}
{'loss': 1.0112, 'learning_rate': 2.3344478583047174e-05, 'epoch': 0.44}
{'loss': 1.6196, 'learning_rate': 2.3341767576360022e-05, 'epoch': 0.44}
{'loss': 1.1512, 'learning_rate': 2.333905656967287e-05, 'epoch': 0.44}
{'loss': 1.3548, 'learning_rate': 2.3336345562985722e-05, 'epoch': 0.44}
{'loss': 1.4898, 'learning_rate': 2.333363455629857e-05, 'epoch': 0.44}
{'loss': 1.545, 'learning_rate': 2.3330923549611423e-05, 'epoch': 0.44}
{'loss': 0.7086, 'learning_rate': 2.3328212542924274e-05, 'epoch': 0.44}
{'loss': 1.124, 'learning_rate': 2.3325501536237123e-05, 'epoch': 0.44}
{'loss': 1.2361, 'learning_rate': 2.3322790529549975e-05, 'epoch': 0.45}
{'loss': 1.2221, 'learning_rate': 2.3320079522862826e-05, 'epoch': 0.45}
{'loss': 1.0439, 'learning_rate': 2.331736851617567e-05, 'epoch': 0.45}
{'loss': 1.0238, 'learning_rate': 2.3314657509488523e-05, 'epoch': 0.45}
{'loss': 1.368, 'learning_rate': 2.3311946502801372e-05, 'epoch': 0.45}
{'loss': 0.9674, 'learning_rate': 2.3309235496114224e-05, 'epoch': 0.45}
{'loss': 1.3677, 'learning_rate': 2.3306524489427075e-05, 'epoch': 0.45}
{'loss': 1.2976, 'learning_rate': 2.3303813482739924e-05, 'epoch': 0.45}
{'loss': 0.6421, 'learning_rate': 2.3301102476052776e-05, 'epoch': 0.45}
{'loss': 1.0993, 'learning_rate': 2.3298391469365628e-05, 'epoch': 0.45}
{'loss': 0.7451, 'learning_rate': 2.3295680462678473e-05, 'epoch': 0.45}
{'loss': 1.2589, 'learning_rate': 2.3292969455991324e-05, 'epoch': 0.45}
{'loss': 1.3327, 'learning_rate': 2.3290258449304176e-05, 'epoch': 0.45}
{'loss': 1.2164, 'learning_rate': 2.3287547442617025e-05, 'epoch': 0.45}

 22%|██▏       | 2477/11066 [09:06<31:13,  4.58it/s]
 22%|██▏       | 2478/11066 [09:06<31:28,  4.55it/s]
                                                    

 22%|██▏       | 2478/11066 [09:06<31:28,  4.55it/s]
 22%|██▏       | 2479/11066 [09:06<31:35,  4.53it/s]
                                                    

 22%|██▏       | 2479/11066 [09:06<31:35,  4.53it/s]
 22%|██▏       | 2480/11066 [09:06<31:42,  4.51it/s]
                                                    

 22%|██▏       | 2480/11066 [09:06<31:42,  4.51it/s]
 22%|██▏       | 2481/11066 [09:07<31:48,  4.50it/s]
                                                    

 22%|██▏       | 2481/11066 [09:07<31:48,  4.50it/s]
 22%|██▏       | 2482/11066 [09:07<31:52,  4.49it/s]
                                                    

 22%|██▏       | 2482/11066 [09:07<31:52,  4.49it/s]
 22%|██▏       | 2483/11066 [09:07<32:00,  4.47it/s]
                                                    

 22%|██▏       | 2483/11066 [09:07<32:00,  4.47it/s]
 22%|██▏       | 2484/11066 [09:07<32:01,  4.47it/s]
                                                    

 22%|██▏       | 2484/11066 [09:07<32:01,  4.47it/s]
 22%|██▏       | 2485/11066 [09:08<31:59,  4.47it/s]
                                                    

 22%|██▏       | 2485/11066 [09:08<31:59,  4.47it/s]
 22%|██▏       | 2486/11066 [09:08<31:57,  4.48it/s]
                                                    

 22%|██▏       | 2486/11066 [09:08<31:57,  4.48it/s]
 22%|██▏       | 2487/11066 [09:08<31:54,  4.48it/s]
                                                    

 22%|██▏       | 2487/11066 [09:08<31:54,  4.48it/s]
 22%|██▏       | 2488/11066 [09:08<31:52,  4.48it/s]
                                                    

 22%|██▏       | 2488/11066 [09:08<31:52,  4.48it/s]
 22%|██▏       | 2489/11066 [09:08<31:50,  4.49it/s]
                                                    

 22%|██▏       | 2489/11066 [09:08<31:50,  4.49it/s]
 23%|██▎       | 2490/11066 [09:09<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2490/11066 [09:09<31:49,  4.49it/s]
 23%|██▎       | 2491/11066 [09:09<31:50,  4.49it/s]
                                                    

 23%|██▎       | 2491/11066 [09:09<31:50,  4.49it/s]
 23%|██▎       | 2492/11066 [09:09<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2492/11066 [09:09<31:49,  4.49it/s]
 23%|██▎       | 2493/11066 [09:09<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2493/11066 [09:09<31:49,  4.49it/s]
 23%|██▎       | 2494/11066 [09:10<31:51,  4.49it/s]
                                                    

 23%|██▎       | 2494/11066 [09:10<31:51,  4.49it/s]
 23%|██▎       | 2495/11066 [09:10<31:50,  4.49it/s]
                                                    

 23%|██▎       | 2495/11066 [09:10<31:50,  4.49it/s]
 23%|██▎       | 2496/11066 [09:10<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2496/11066 [09:10<31:49,  4.49it/s]
 23%|██▎       | 2497/11066 [09:10<31:47,  4.49it/s]
                                                    

 23%|██▎       | 2497/11066 [09:10<31:47,  4.49it/s]
 23%|██▎       | 2498/11066 [09:10<31:47,  4.49it/s]
                                                    

 23%|██▎       | 2498/11066 [09:10<31:47,  4.49it/s]
 23%|██▎       | 2499/11066 [09:11<31:48,  4.49it/s]
                                                    

 23%|██▎       | 2499/11066 [09:11<31:48,  4.49it/s]
 23%|██▎       | 2500/11066 [09:11<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2500/11066 [09:11<31:49,  4.49it/s]
 23%|██▎       | 2501/11066 [09:11<31:45,  4.49it/s]
                                                    

 23%|██▎       | 2501/11066 [09:11<31:45,  4.49it/s]
 23%|██▎       | 2502/11066 [09:11<31:46,  4.49it/s]
                                                    

 23%|██▎       | 2502/11066 [09:11<31:46,  4.49it/s]
 23%|██▎       | 2503/11066 [09:12<31:48,  4.49it/s]
                                                    

 23%|██▎       | 2503/11066 [09:12<31:48,  4.49it/s]
 23%|██▎       | 2504/11066 [09:12<31:49,  4.49it/s]
                                                    

 23%|██▎       | 2504/11066 [09:12<31:49,  4.49it/s]
 23%|██▎       | 2505/11066 [09:12<31:48,  4.49it/s]
                                                    

 23%|██▎       | 2505/11066 [09:12<31:48,  4.49it/s]
 23%|██▎       | 2506/11066 [09:12<31:47,  4.49it/s]
                                                    

 23%|██▎       | 2506/11066 [09:12<31:47,  4.49it/s]
 23%|██▎       | 2507/11066 [09:12<31:44,  4.50it/s]
                                                    

 23%|██▎       | 2507/11066 [09:12<31:44,  4.50it/s]
 23%|██▎       | 2508/11066 [09:13<31:46,  4.49it/s]
                                                    

 23%|██▎       | 2508/11066 [09:13<31:46,  4.49it/s]
 23%|██▎       | 2509/11066 [09:13<31:44,  4.49it/s]
                                                    

 23%|██▎       | 2509/11066 [09:13<31:44,  4.49it/s]
 23%|██▎       | 2510/11066 [09:13<31:42,  4.50it/s]
                                                    

 23%|██▎       | 2510/11066 [09:13<31:42,  4.50it/s]
 23%|██▎       | 2511/11066 [09:13<31:18,  4.55it/s]
                                                    

 23%|██▎       | 2511/11066 [09:13<31:18,  4.55it/s]
 23%|██▎       | 2512/11066 [09:14<31:22,  4.54it/s]
                                                    

 23%|██▎       | 2512/11066 [09:14<31:22,  4.54it/s]
 23%|██▎       | 2513/11066 [09:14<31:26,  4.53it/s]
                                                    

 23%|██▎       | 2513/11066 [09:14<31:26,  4.53it/s]
 23%|██▎       | 2514/11066 [09:14<31:16,  4.56it/s]
                                                    

 23%|██▎       | 2514/11066 [09:14<31:16,  4.56it/s]
 23%|██▎       | 2515/11066 [09:14<31:01,  4.59it/s]
                                                    

 23%|██▎       | 2515/11066 [09:14<31:01,  4.59it/s]
 23%|██▎       | 2516/11066 [09:14<30:45,  4.63it/s]
                                                    

 23%|██▎       | 2516/11066 [09:14<30:45,  4.63it/s]
 23%|██▎       | 2517/11066 [09:15<30:40,  4.65it/s]
                                                    

 23%|██▎       | 2517/11066 [09:15<30:40,  4.65it/s]
 23%|██▎       | 2518/11066 [09:15<30:53,  4.61it/s]
                                                    

 23%|██▎       | 2518/11066 [09:15<30:53,  4.61it/s]
 23%|██▎       | 2519/11066 [09:15<30:48,  4.62it/s]
                                                    

 23%|██▎       | 2519/11066 [09:15<30:48,  4.62it/s]
 23%|██▎       | 2520/11066 [09:15<30:35,  4.66it/s]
                                                    

 23%|██▎       | 2520/11066 [09:15<30:35,  4.66it/s]
 23%|██▎       | 2521/11066 [09:15<30:47,  4.63it/s]
                                                    

 23%|██▎       | 2521/11066 [09:15<30:47,  4.63it/s]
 23%|██▎       | 2522/11066 [09:16<30:28,  4.67it/s]
                                                    

 23%|██▎       | 2522/11066 [09:16<30:28,  4.67it/s]
 23%|██▎       | 2523/11066 [09:16<30:56,  4.60it/s]
                                                    

 23%|██▎       | 2523/11066 [09:16<30:56,  4.60it/s]
 23%|██▎       | 2524/11066 [09:16<30:54,  4.60it/s]
                                                    

 23%|██▎       | 2524/11066 [09:16<30:54,  4.60it/s]
 23%|██▎       | 2525/11066 [09:16<31:03,  4.58it/s]
                                                    

 23%|██▎       | 2525/11066 [09:16<31:03,  4.58it/s]
 23%|██▎       | 2526/11066 [09:17<31:20,  4.54it/s]
                                                    

 23%|██▎       | 2526/11066 [09:17<31:20,  4.54it/s]
 23%|██▎       | 2527/11066 [09:17<31:00,  4.59it/s]
                                                    

 23%|██▎       | 2527/11066 [09:17<31:00,  4.59it/s]
 23%|██▎       | 2528/11066 [09:17<30:54,  4.60it/s]
                                                    

 23%|██▎       | 2528/11066 [09:17<30:54,  4.60it/s]
 23%|██▎       | 2529/11066 [09:17<31:09,  4.57it/s]
                                                    

 23%|██▎       | 2529/11066 [09:17<31:09,  4.57it/s]
 23%|██▎       | 2530/11066 [09:17<31:04,  4.58it/s]
                                                    

 23%|██▎       | 2530/11066 [09:17<31:04,  4.58it/s]
 23%|██▎       | 2531/11066 [09:18<30:53,  4.61it/s]
                                                    

 23%|██▎       | 2531/11066 [09:18<30:53,  4.61it/s]
 23%|██▎       | 2532/11066 [09:18<30:54,  4.60it/s]
                                                    

 23%|██▎       | 2532/11066 [09:18<30:54,  4.60it/s]
 23%|██▎       | 2533/11066 [09:18<31:06,  4.57it/s]
                                                    

 23%|██▎       | 2533/11066 [09:18<31:06,  4.57it/s]
 23%|██▎       | 2534/11066 [09:18<31:09,  4.56it/s]
                                                    

 23%|██▎       | 2534/11066 [09:18<31:09,  4.56it/s]
 23%|██▎       | 2535/11066 [09:19<31:20,  4.54it/s]
                                                    

 23%|██▎       | 2535/11066 [09:19<31:20,  4.54it/s]
 23%|██▎       | 2536/11066 [09:19<31:24,  4.53it/s]
                                                    

 23%|██▎       | 2536/11066 [09:19<31:24,  4.53it/s]
 23%|██▎       | 2537/11066 [09:19<31:34,  4.50it/s]
                                                    

 23%|██▎       | 2537/11066 [09:19<31:34,  4.50it/s]
 23%|██▎       | 2538/11066 [09:19<31:22,  4.53it/s]
                                                    

 23%|██▎       | 2538/11066 [09:19<31:22,  4.53it/s]
 23%|██▎       | 2539/11066 [09:19<31:06,  4.57it/s]
                                                    

 23%|██▎       | 2539/11066 [09:19<31:06,  4.57it/s]
 23%|██▎       | 2540/11066 [09:20<31:19,  4.54it/s]
                                                    

 23%|██▎       | 2540/11066 [09:20<31:19,  4.54it/s]
 23%|██▎       | 2541/11066 [09:20<31:10,  4.56it/s]
                                                    

 23%|██▎       | 2541/11066 [09:20<31:10,  4.56it/s]
 23%|██▎       | 2542/11066 [09:20<30:56,  4.59it/s]
                                                    

 23%|██▎       | 2542/11066 [09:20<30:56,  4.59it/s]
 23%|██▎       | 2543/11066 [09:20<30:48,  4.61it/s]
                                                    

 23%|██▎       | 2543/11066 [09:20<30:48,  4.61it/s]
 23%|██▎       | 2544/11066 [09:20<30:50,  4.61it/s]
                                                    

 23%|██▎       | 2544/11066 [09:20<30:50,  4.61it/s]
 23%|██▎       | 2545/11066 [09:21<30:40,  4.63it/s]
                                                    

 23%|██▎       | 2545/11066 [09:21<30:40,  4.63it/s]
 23%|██▎       | 2546/11066 [09:21<30:46,  4.61it/s]
                                                    

 23%|██▎       | 2546/11066 [09:21<30:46,  4.61it/s]
 23%|██▎       | 2547/11066 [09:21<30:59,  4.58it/s]
                                                    

 23%|██▎       | 2547/11066 [09:21<30:59,  4.58it/s]
 23%|██▎       | 2548/11066 [09:21<31:03,  4.57it/s]
                                                    

 23%|██▎       | 2548/11066 [09:21<31:03,  4.57it/s]
 23%|██▎       | 2549/11066 [09:22<30:49,  4.61it/s]
                                                    

 23%|██▎       | 2549/11066 [09:22<30:49,  4.61it/s]
 23%|██▎       | 2550/11066 [09:22<30:37,  4.63it/s]
                                                    

 23%|██▎       | 2550/11066 [09:22<30:37,  4.63it/s]
 23%|██▎       | 2551/11066 [09:22<30:56,  4.59it/s]
                                                    

 23%|██▎       | 2551/11066 [09:22<30:56,  4.59it/s]
 23%|██▎       | 2552/11066 [09:22<31:07,  4.56it/s]
                                                    

 23%|██▎       | 2552/11066 [09:22<31:07,  4.56it/s]
 23%|██▎       | 2553/11066 [09:22<31:14,  4.54it/s]
                                                    

 23%|██▎       | 2553/11066 [09:22<31:14,  4.54it/s]
 23%|██▎       | 2554/11066 [09:23<31:19,  4.53it/s]
                                                    

 23%|██▎       | 2554/11066 [09:23<31:19,  4.53it/s]
 23%|██▎       | 2555/11066 [09:23<30:58,  4.58it/s]
                                                    

 23%|██▎       | 2555/11066 [09:23<30:58,  4.58it/s]
 23%|██▎       | 2556/11066 [09:23<31:07,  4.56it/s]
                                                    

 23%|██▎       | 2556/11066 [09:23<31:07,  4.56it/s]
 23%|██▎       | 2557/11066 [09:23<30:59,  4.58it/s]
                                                    

 23%|██▎       | 2557/11066 [09:23<30:59,  4.58it/s]
 23%|██▎       | 2558/11066 [09:24<30:46,  4.61it/s]
                                                    

 23%|██▎       | 2558/11066 [09:24<30:46,  4.61it/s]
 23%|██▎       | 2559/11066 [09:24<31:06,  4.56it/s]
                                                    

 23%|██▎       | 2559/11066 [09:24<31:06,  4.56it/s]
 23%|██▎       | 2560/11066 [09:24<31:02,  4.57it/s]
                                                    

 23%|██▎       | 2560/11066 [09:24<31:02,  4.57it/s]
 23%|██▎       | 2561/11066 [09:24<31:15,  4.53it/s]
                                                    

 23%|██▎       | 2561/11066 [09:24<31:15,  4.53it/s]
 23%|██▎       | 2562/11066 [09:24<30:54,  4.59it/s]
                                                    

 23%|██▎       | 2562/11066 [09:24<30:54,  4.59it/s]
 23%|██▎       | 2563/11066 [09:25<30:35,  4.63it/s]
                                                    

 23%|██▎       | 2563/11066 [09:25<30:35,  4.63it/s]
 23%|██▎       | 2564/11066 [09:25<30:16,  4.68it/s]
                                                    

 23%|██▎       | 2564/11066 [09:25<30:16,  4.68it/s]
 23%|██▎       | 2565/11066 [09:25<30:44,  4.61it/s]
                                                    

 23%|██▎       | 2565/11066 [09:25<30:44,  4.61it/s]
 23%|██▎       | 2566/11066 [09:25<30:58,  4.57it/s]
                                                    

 23%|██▎       | 2566/11066 [09:25<30:58,  4.57it/s]
 23%|██▎       | 2567/11066 [09:26<31:07,  4.55it/s]
                                                    

 23%|██▎       | 2567/11066 [09:26<31:07,  4.55it/s]
 23%|██▎       | 2568/11066 [09:26<31:12,  4.54it/s]
                                                    

 23%|██▎       | 2568/11066 [09:26<31:12,  4.54it/s]
 23%|██▎       | 2569/11066 [09:26<30:50,  4.59it/s]
                                                    

 23%|██▎       | 2569/11066 [09:26<30:50,  4.59it/s]
 23%|██▎       | 2570/11066 [09:26<31:03,  4.56it/s]
                                                    

 23%|██▎       | 2570/11066 [09:26<31:03,  4.56it/s]
 23%|██▎       | 2571/11066 [09:26<31:13,  4.54it/s]
                                                    

 23%|██▎       | 2571/11066 [09:26<31:13,  4.54it/s]
 23%|██▎       | 2572/11066 [09:27<31:18,  4.52it/s]
                                                    

 23%|██▎       | 2572/11066 [09:27<31:18,  4.52it/s]
 23%|██▎       | 2573/11066 [09:27<31:20,  4.52it/s]
                                                    

 23%|██▎       | 2573/11066 [09:27<31:20,  4.52it/s]
 23%|██▎       | 2574/11066 [09:27<31:23,  4.51it/s]
                                                    

 23%|██▎       | 2574/11066 [09:27<31:23,  4.51it/s]
 23%|██▎       | 2575/11066 [09:27<31:25,  4.50it/s]
                                                    

 23%|██▎       | 2575/11066 [09:27<31:25,  4.50it/s]
 23%|██▎       | 2576/11066 [09:27<31:28,  4.50it/s]
                                                    

 23%|██▎       | 2576/11066 [09:27<31:28,  4.50it/s]
 23%|██▎       | 2577/11066 [09:28<31:30,  4.49it/s]
                                                    

 23%|██▎       | 2577/11066 [09:28<31:30,  4.49it/s]
 23%|██▎       | 2578/11066 [09:28<31:30,  4.49it/s]
                                                    

 23%|██▎       | 2578/11066 [09:28<31:30,  4.49it/s]
 23%|██▎       | 2579/11066 [09:28<31:32,  4.48it/s]
                                                    

 23%|██▎       | 2579/11066 [09:28<31:32,  4.48it/s]
 23%|██▎       | 2580/11066 [09:28<31:35,  4.48it/s]
                                                    

 23%|██▎       | 2580/11066 [09:28<31:35,  4.48it/s]
 23%|██▎       | 2581/11066 [09:29<31:41,  4.46it/s]
                                                    

 23%|██▎       | 2581/11066 [09:29<31:41,  4.46it/s]
 23%|██▎       | 2582/11066 [09:29<31:39,  4.47it/s]
                                                    

 23%|██▎       | 2582/11066 [09:29<31:39,  4.47it/s]
 23%|██▎       | 2583/11066 [09:29<31:31,  4.48it/s]
                                                    

 23%|██▎       | 2583/11066 [09:29<31:31,  4.48it/s]
 23%|██▎       | 2584/11066 [09:29<31:34,  4.48it/s]
                                                    

 23%|██▎       | 2584/11066 [09:29<31:34,  4.48it/s]
 23%|██▎       | 2585/11066 [09:30<31:35,  4.47it/s]
                                                    

 23%|██▎       | 2585/11066 [09:30<31:35,  4.47it/s]
 23%|██▎       | 2586/11066 [09:30<31:32,  4.48it/s]
                                                    

 23%|██▎       | 2586/11066 [09:30<31:32,  4.48it/s]
 23%|██▎       | 2587/11066 [09:30<31:09,  4.54it/s]
                                                    

 23%|██▎       | 2587/11066 [09:30<31:09,  4.54it/s]
 23%|██▎       | 2588/11066 [09:30<30:48,  4.59it/s]
                                                    

 23%|██▎       | 2588/11066 [09:30<30:48,  4.59it/s]
 23%|██▎       | 2589/11066 [09:30<30:43,  4.60it/s]
                                                    
{'loss': 1.4598, 'learning_rate': 2.3284836435929877e-05, 'epoch': 0.45}
{'loss': 1.0097, 'learning_rate': 2.3282125429242725e-05, 'epoch': 0.45}
{'loss': 0.9791, 'learning_rate': 2.3279414422555577e-05, 'epoch': 0.45}
{'loss': 1.3603, 'learning_rate': 2.327670341586843e-05, 'epoch': 0.45}
{'loss': 1.0052, 'learning_rate': 2.3273992409181274e-05, 'epoch': 0.45}
{'loss': 1.3255, 'learning_rate': 2.3271281402494126e-05, 'epoch': 0.45}
{'loss': 0.8956, 'learning_rate': 2.3268570395806977e-05, 'epoch': 0.45}
{'loss': 0.9221, 'learning_rate': 2.3265859389119826e-05, 'epoch': 0.45}
{'loss': 1.1468, 'learning_rate': 2.3263148382432678e-05, 'epoch': 0.45}
{'loss': 1.5179, 'learning_rate': 2.326043737574553e-05, 'epoch': 0.45}
{'loss': 1.0728, 'learning_rate': 2.3257726369058378e-05, 'epoch': 0.45}
{'loss': 0.9659, 'learning_rate': 2.325501536237123e-05, 'epoch': 0.45}
{'loss': 1.2329, 'learning_rate': 2.3252304355684075e-05, 'epoch': 0.45}
{'loss': 1.0801, 'learning_rate': 2.3249593348996927e-05, 'epoch': 0.45}
{'loss': 1.1115, 'learning_rate': 2.324688234230978e-05, 'epoch': 0.45}
{'loss': 0.8596, 'learning_rate': 2.3244171335622627e-05, 'epoch': 0.45}
{'loss': 0.969, 'learning_rate': 2.324146032893548e-05, 'epoch': 0.45}
{'loss': 2.0738, 'learning_rate': 2.323874932224833e-05, 'epoch': 0.45}
{'loss': 0.8447, 'learning_rate': 2.323603831556118e-05, 'epoch': 0.45}
{'loss': 1.284, 'learning_rate': 2.323332730887403e-05, 'epoch': 0.45}
{'loss': 1.0287, 'learning_rate': 2.323061630218688e-05, 'epoch': 0.45}
{'loss': 2.33, 'learning_rate': 2.3227905295499728e-05, 'epoch': 0.45}
{'loss': 0.7537, 'learning_rate': 2.322519428881258e-05, 'epoch': 0.45}
{'loss': 0.9814, 'learning_rate': 2.3222483282125428e-05, 'epoch': 0.45}
{'loss': 0.9191, 'learning_rate': 2.321977227543828e-05, 'epoch': 0.45}
{'loss': 1.7856, 'learning_rate': 2.321706126875113e-05, 'epoch': 0.45}
{'loss': 0.8673, 'learning_rate': 2.321435026206398e-05, 'epoch': 0.45}
{'loss': 1.1204, 'learning_rate': 2.3211639255376832e-05, 'epoch': 0.45}
{'loss': 1.7684, 'learning_rate': 2.320892824868968e-05, 'epoch': 0.45}
{'loss': 1.1761, 'learning_rate': 2.320621724200253e-05, 'epoch': 0.45}
{'loss': 1.063, 'learning_rate': 2.320350623531538e-05, 'epoch': 0.45}
{'loss': 1.3832, 'learning_rate': 2.3200795228628232e-05, 'epoch': 0.45}
{'loss': 1.3464, 'learning_rate': 2.319808422194108e-05, 'epoch': 0.45}
{'loss': 1.2805, 'learning_rate': 2.3195373215253933e-05, 'epoch': 0.45}
{'loss': 1.3078, 'learning_rate': 2.319266220856678e-05, 'epoch': 0.45}
{'loss': 1.5248, 'learning_rate': 2.3189951201879633e-05, 'epoch': 0.45}
{'loss': 0.7933, 'learning_rate': 2.318724019519248e-05, 'epoch': 0.45}
{'loss': 1.4914, 'learning_rate': 2.318452918850533e-05, 'epoch': 0.45}
{'loss': 0.7121, 'learning_rate': 2.318181818181818e-05, 'epoch': 0.45}
{'loss': 1.1224, 'learning_rate': 2.3179107175131033e-05, 'epoch': 0.45}
{'loss': 0.9486, 'learning_rate': 2.3176396168443882e-05, 'epoch': 0.45}
{'loss': 1.4888, 'learning_rate': 2.3173685161756734e-05, 'epoch': 0.46}
{'loss': 1.2805, 'learning_rate': 2.3170974155069586e-05, 'epoch': 0.46}
{'loss': 0.7885, 'learning_rate': 2.3168263148382434e-05, 'epoch': 0.46}
{'loss': 1.5259, 'learning_rate': 2.3165552141695282e-05, 'epoch': 0.46}
{'loss': 1.2773, 'learning_rate': 2.3162841135008134e-05, 'epoch': 0.46}
{'loss': 1.0892, 'learning_rate': 2.3160130128320983e-05, 'epoch': 0.46}
{'loss': 1.1343, 'learning_rate': 2.3157419121633835e-05, 'epoch': 0.46}
{'loss': 1.2165, 'learning_rate': 2.3154708114946683e-05, 'epoch': 0.46}
{'loss': 1.2809, 'learning_rate': 2.3151997108259535e-05, 'epoch': 0.46}
{'loss': 1.1479, 'learning_rate': 2.3149286101572387e-05, 'epoch': 0.46}
{'loss': 0.8648, 'learning_rate': 2.3146575094885235e-05, 'epoch': 0.46}
{'loss': 1.487, 'learning_rate': 2.3143864088198084e-05, 'epoch': 0.46}
{'loss': 1.0891, 'learning_rate': 2.3141153081510935e-05, 'epoch': 0.46}
{'loss': 1.8268, 'learning_rate': 2.3138442074823784e-05, 'epoch': 0.46}
{'loss': 1.9328, 'learning_rate': 2.3135731068136636e-05, 'epoch': 0.46}
{'loss': 2.0673, 'learning_rate': 2.3133020061449487e-05, 'epoch': 0.46}
{'loss': 1.3955, 'learning_rate': 2.3130309054762336e-05, 'epoch': 0.46}
{'loss': 1.1761, 'learning_rate': 2.3127598048075188e-05, 'epoch': 0.46}
{'loss': 1.2405, 'learning_rate': 2.3124887041388036e-05, 'epoch': 0.46}
{'loss': 1.1013, 'learning_rate': 2.3122176034700885e-05, 'epoch': 0.46}
{'loss': 1.1936, 'learning_rate': 2.3119465028013736e-05, 'epoch': 0.46}
{'loss': 1.0171, 'learning_rate': 2.3116754021326585e-05, 'epoch': 0.46}
{'loss': 1.074, 'learning_rate': 2.3114043014639437e-05, 'epoch': 0.46}
{'loss': 0.9175, 'learning_rate': 2.311133200795229e-05, 'epoch': 0.46}
{'loss': 1.0123, 'learning_rate': 2.3108621001265137e-05, 'epoch': 0.46}
{'loss': 0.8281, 'learning_rate': 2.310590999457799e-05, 'epoch': 0.46}
{'loss': 1.4192, 'learning_rate': 2.310319898789084e-05, 'epoch': 0.46}
{'loss': 0.9169, 'learning_rate': 2.3100487981203686e-05, 'epoch': 0.46}
{'loss': 0.8404, 'learning_rate': 2.3097776974516537e-05, 'epoch': 0.46}
{'loss': 1.1723, 'learning_rate': 2.3095065967829386e-05, 'epoch': 0.46}
{'loss': 1.0385, 'learning_rate': 2.3092354961142238e-05, 'epoch': 0.46}
{'loss': 1.6477, 'learning_rate': 2.308964395445509e-05, 'epoch': 0.46}
{'loss': 1.2986, 'learning_rate': 2.3086932947767938e-05, 'epoch': 0.46}
{'loss': 1.7164, 'learning_rate': 2.308422194108079e-05, 'epoch': 0.46}
{'loss': 1.5366, 'learning_rate': 2.308151093439364e-05, 'epoch': 0.46}
{'loss': 1.1967, 'learning_rate': 2.3078799927706487e-05, 'epoch': 0.46}
{'loss': 0.9932, 'learning_rate': 2.307608892101934e-05, 'epoch': 0.46}
{'loss': 1.1254, 'learning_rate': 2.307337791433219e-05, 'epoch': 0.46}
{'loss': 1.6888, 'learning_rate': 2.307066690764504e-05, 'epoch': 0.46}
{'loss': 1.6402, 'learning_rate': 2.306795590095789e-05, 'epoch': 0.46}
{'loss': 1.0731, 'learning_rate': 2.306524489427074e-05, 'epoch': 0.46}
{'loss': 1.1868, 'learning_rate': 2.306253388758359e-05, 'epoch': 0.46}
{'loss': 0.8945, 'learning_rate': 2.3059822880896443e-05, 'epoch': 0.46}
{'loss': 1.0833, 'learning_rate': 2.3057111874209288e-05, 'epoch': 0.46}
{'loss': 1.6174, 'learning_rate': 2.305440086752214e-05, 'epoch': 0.46}
{'loss': 1.4126, 'learning_rate': 2.305168986083499e-05, 'epoch': 0.46}
{'loss': 1.0266, 'learning_rate': 2.304897885414784e-05, 'epoch': 0.46}
{'loss': 1.3593, 'learning_rate': 2.3046267847460692e-05, 'epoch': 0.46}
{'loss': 0.8148, 'learning_rate': 2.3043556840773544e-05, 'epoch': 0.46}
{'loss': 1.19, 'learning_rate': 2.3040845834086392e-05, 'epoch': 0.46}
{'loss': 1.1812, 'learning_rate': 2.3038134827399244e-05, 'epoch': 0.46}
{'loss': 1.1793, 'learning_rate': 2.303542382071209e-05, 'epoch': 0.46}
{'loss': 0.8835, 'learning_rate': 2.303271281402494e-05, 'epoch': 0.46}
{'loss': 0.8831, 'learning_rate': 2.3030001807337793e-05, 'epoch': 0.46}
{'loss': 1.2524, 'learning_rate': 2.302729080065064e-05, 'epoch': 0.46}
{'loss': 1.1729, 'learning_rate': 2.3024579793963493e-05, 'epoch': 0.47}
{'loss': 0.6382, 'learning_rate': 2.3021868787276345e-05, 'epoch': 0.47}
{'loss': 1.1642, 'learning_rate': 2.3019157780589193e-05, 'epoch': 0.47}
{'loss': 1.2007, 'learning_rate': 2.301644677390204e-05, 'epoch': 0.47}
{'loss': 1.1283, 'learning_rate': 2.3013735767214893e-05, 'epoch': 0.47}
{'loss': 0.4128, 'learning_rate': 2.3011024760527742e-05, 'epoch': 0.47}
{'loss': 0.7594, 'learning_rate': 2.3008313753840594e-05, 'epoch': 0.47}
{'loss': 0.8315, 'learning_rate': 2.3005602747153442e-05, 'epoch': 0.47}
{'loss': 0.3069, 'learning_rate': 2.3002891740466294e-05, 'epoch': 0.47}
{'loss': 1.2659, 'learning_rate': 2.3000180733779146e-05, 'epoch': 0.47}
{'loss': 0.9657, 'learning_rate': 2.2997469727091994e-05, 'epoch': 0.47}
{'loss': 1.5858, 'learning_rate': 2.2994758720404843e-05, 'epoch': 0.47}
{'loss': 1.5045, 'learning_rate': 2.2992047713717694e-05, 'epoch': 0.47}
{'loss': 1.2794, 'learning_rate': 2.2989336707030543e-05, 'epoch': 0.47}
{'loss': 0.7852, 'learning_rate': 2.2986625700343395e-05, 'epoch': 0.47}
{'loss': 1.0453, 'learning_rate': 2.2983914693656247e-05, 'epoch': 0.47}

 23%|██▎       | 2589/11066 [09:30<30:43,  4.60it/s]
 23%|██▎       | 2590/11066 [09:31<30:50,  4.58it/s]
                                                    

 23%|██▎       | 2590/11066 [09:31<30:50,  4.58it/s]
 23%|██▎       | 2591/11066 [09:31<31:06,  4.54it/s]
                                                    

 23%|██▎       | 2591/11066 [09:31<31:06,  4.54it/s]
 23%|██▎       | 2592/11066 [09:31<30:47,  4.59it/s]
                                                    

 23%|██▎       | 2592/11066 [09:31<30:47,  4.59it/s]
 23%|██▎       | 2593/11066 [09:31<31:08,  4.54it/s]
                                                    

 23%|██▎       | 2593/11066 [09:31<31:08,  4.54it/s]
 23%|██▎       | 2594/11066 [09:31<31:16,  4.52it/s]
                                                    

 23%|██▎       | 2594/11066 [09:31<31:16,  4.52it/s]
 23%|██▎       | 2595/11066 [09:32<31:17,  4.51it/s]
                                                    

 23%|██▎       | 2595/11066 [09:32<31:17,  4.51it/s]
 23%|██▎       | 2596/11066 [09:32<31:19,  4.51it/s]
                                                    

 23%|██▎       | 2596/11066 [09:32<31:19,  4.51it/s]
 23%|██▎       | 2597/11066 [09:32<31:19,  4.50it/s]
                                                    

 23%|██▎       | 2597/11066 [09:32<31:19,  4.50it/s]
 23%|██▎       | 2598/11066 [09:32<31:21,  4.50it/s]
                                                    

 23%|██▎       | 2598/11066 [09:32<31:21,  4.50it/s]
 23%|██▎       | 2599/11066 [09:33<31:03,  4.54it/s]
                                                    

 23%|██▎       | 2599/11066 [09:33<31:03,  4.54it/s]
 23%|██▎       | 2600/11066 [09:33<30:33,  4.62it/s]
                                                    

 23%|██▎       | 2600/11066 [09:33<30:33,  4.62it/s]
 24%|██▎       | 2601/11066 [09:33<30:26,  4.63it/s]
                                                    

 24%|██▎       | 2601/11066 [09:33<30:26,  4.63it/s]
 24%|██▎       | 2602/11066 [09:33<30:26,  4.63it/s]
                                                    

 24%|██▎       | 2602/11066 [09:33<30:26,  4.63it/s]
 24%|██▎       | 2603/11066 [09:33<30:40,  4.60it/s]
                                                    

 24%|██▎       | 2603/11066 [09:33<30:40,  4.60it/s]
 24%|██▎       | 2604/11066 [09:34<30:52,  4.57it/s]
                                                    

 24%|██▎       | 2604/11066 [09:34<30:52,  4.57it/s]
 24%|██▎       | 2605/11066 [09:34<30:48,  4.58it/s]
                                                    

 24%|██▎       | 2605/11066 [09:34<30:48,  4.58it/s]
 24%|██▎       | 2606/11066 [09:34<30:38,  4.60it/s]
                                                    

 24%|██▎       | 2606/11066 [09:34<30:38,  4.60it/s]
 24%|██▎       | 2607/11066 [09:34<30:21,  4.64it/s]
                                                    

 24%|██▎       | 2607/11066 [09:34<30:21,  4.64it/s]
 24%|██▎       | 2608/11066 [09:35<30:51,  4.57it/s]
                                                    

 24%|██▎       | 2608/11066 [09:35<30:51,  4.57it/s]
 24%|██▎       | 2609/11066 [09:35<31:20,  4.50it/s]
                                                    

 24%|██▎       | 2609/11066 [09:35<31:20,  4.50it/s]
 24%|██▎       | 2610/11066 [09:35<31:40,  4.45it/s]
                                                    

 24%|██▎       | 2610/11066 [09:35<31:40,  4.45it/s]
 24%|██▎       | 2611/11066 [09:35<31:39,  4.45it/s]
                                                    

 24%|██▎       | 2611/11066 [09:35<31:39,  4.45it/s]
 24%|██▎       | 2612/11066 [09:35<31:54,  4.41it/s]
                                                    

 24%|██▎       | 2612/11066 [09:35<31:54,  4.41it/s]
 24%|██▎       | 2613/11066 [09:36<32:04,  4.39it/s]
                                                    

 24%|██▎       | 2613/11066 [09:36<32:04,  4.39it/s]
 24%|██▎       | 2614/11066 [09:36<31:19,  4.50it/s]
                                                    

 24%|██▎       | 2614/11066 [09:36<31:19,  4.50it/s]
 24%|██▎       | 2615/11066 [09:36<31:28,  4.47it/s]
                                                    

 24%|██▎       | 2615/11066 [09:36<31:28,  4.47it/s]
 24%|██▎       | 2616/11066 [09:36<31:41,  4.44it/s]
                                                    

 24%|██▎       | 2616/11066 [09:36<31:41,  4.44it/s]
 24%|██▎       | 2617/11066 [09:37<32:02,  4.39it/s]
                                                    

 24%|██▎       | 2617/11066 [09:37<32:02,  4.39it/s]
 24%|██▎       | 2618/11066 [09:37<31:51,  4.42it/s]
                                                    

 24%|██▎       | 2618/11066 [09:37<31:51,  4.42it/s]
 24%|██▎       | 2619/11066 [09:37<31:40,  4.44it/s]
                                                    

 24%|██▎       | 2619/11066 [09:37<31:40,  4.44it/s]
 24%|██▎       | 2620/11066 [09:37<31:35,  4.46it/s]
                                                    

 24%|██▎       | 2620/11066 [09:37<31:35,  4.46it/s]
 24%|██▎       | 2621/11066 [09:37<32:13,  4.37it/s]
                                                    

 24%|██▎       | 2621/11066 [09:37<32:13,  4.37it/s]
 24%|██▎       | 2622/11066 [09:38<31:57,  4.40it/s]
                                                    

 24%|██▎       | 2622/11066 [09:38<31:57,  4.40it/s]
 24%|██▎       | 2623/11066 [09:38<31:47,  4.43it/s]
                                                    

 24%|██▎       | 2623/11066 [09:38<31:47,  4.43it/s]
 24%|██▎       | 2624/11066 [09:38<31:38,  4.45it/s]
                                                    

 24%|██▎       | 2624/11066 [09:38<31:38,  4.45it/s]
 24%|██▎       | 2625/11066 [09:38<31:32,  4.46it/s]
                                                    

 24%|██▎       | 2625/11066 [09:38<31:32,  4.46it/s]
 24%|██▎       | 2626/11066 [09:39<31:27,  4.47it/s]
                                                    

 24%|██▎       | 2626/11066 [09:39<31:27,  4.47it/s]
 24%|██▎       | 2627/11066 [09:39<31:21,  4.48it/s]
                                                    

 24%|██▎       | 2627/11066 [09:39<31:21,  4.48it/s]
 24%|██▎       | 2628/11066 [09:39<31:21,  4.48it/s]
                                                    

 24%|██▎       | 2628/11066 [09:39<31:21,  4.48it/s]
 24%|██▍       | 2629/11066 [09:39<31:20,  4.49it/s]
                                                    

 24%|██▍       | 2629/11066 [09:39<31:20,  4.49it/s]
 24%|██▍       | 2630/11066 [09:39<31:19,  4.49it/s]
                                                    

 24%|██▍       | 2630/11066 [09:39<31:19,  4.49it/s]
 24%|██▍       | 2631/11066 [09:40<31:00,  4.53it/s]
                                                    

 24%|██▍       | 2631/11066 [09:40<31:00,  4.53it/s]
 24%|██▍       | 2632/11066 [09:40<31:05,  4.52it/s]
                                                    

 24%|██▍       | 2632/11066 [09:40<31:05,  4.52it/s]
 24%|██▍       | 2633/11066 [09:40<31:13,  4.50it/s]
                                                    

 24%|██▍       | 2633/11066 [09:40<31:13,  4.50it/s]
 24%|██▍       | 2634/11066 [09:40<31:26,  4.47it/s]
                                                    

 24%|██▍       | 2634/11066 [09:40<31:26,  4.47it/s]
 24%|██▍       | 2635/11066 [09:41<31:13,  4.50it/s]
                                                    

 24%|██▍       | 2635/11066 [09:41<31:13,  4.50it/s]
 24%|██▍       | 2636/11066 [09:41<31:20,  4.48it/s]
                                                    

 24%|██▍       | 2636/11066 [09:41<31:20,  4.48it/s]
 24%|██▍       | 2637/11066 [09:41<31:21,  4.48it/s]
                                                    

 24%|██▍       | 2637/11066 [09:41<31:21,  4.48it/s]
 24%|██▍       | 2638/11066 [09:41<31:21,  4.48it/s]
                                                    

 24%|██▍       | 2638/11066 [09:41<31:21,  4.48it/s]
 24%|██▍       | 2639/11066 [09:41<31:20,  4.48it/s]
                                                    

 24%|██▍       | 2639/11066 [09:41<31:20,  4.48it/s]
 24%|██▍       | 2640/11066 [09:42<31:18,  4.49it/s]
                                                    

 24%|██▍       | 2640/11066 [09:42<31:18,  4.49it/s]
 24%|██▍       | 2641/11066 [09:42<31:17,  4.49it/s]
                                                    

 24%|██▍       | 2641/11066 [09:42<31:17,  4.49it/s]
 24%|██▍       | 2642/11066 [09:42<31:16,  4.49it/s]
                                                    

 24%|██▍       | 2642/11066 [09:42<31:16,  4.49it/s]
 24%|██▍       | 2643/11066 [09:42<31:16,  4.49it/s]
                                                    

 24%|██▍       | 2643/11066 [09:42<31:16,  4.49it/s]
 24%|██▍       | 2644/11066 [09:43<31:16,  4.49it/s]
                                                    

 24%|██▍       | 2644/11066 [09:43<31:16,  4.49it/s]
 24%|██▍       | 2645/11066 [09:43<31:15,  4.49it/s]
                                                    

 24%|██▍       | 2645/11066 [09:43<31:15,  4.49it/s]
 24%|██▍       | 2646/11066 [09:43<31:14,  4.49it/s]
                                                    

 24%|██▍       | 2646/11066 [09:43<31:14,  4.49it/s]
 24%|██▍       | 2647/11066 [09:43<31:14,  4.49it/s]
                                                    

 24%|██▍       | 2647/11066 [09:43<31:14,  4.49it/s]
 24%|██▍       | 2648/11066 [09:43<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2648/11066 [09:43<31:09,  4.50it/s]
 24%|██▍       | 2649/11066 [09:44<31:14,  4.49it/s]
                                                    

 24%|██▍       | 2649/11066 [09:44<31:14,  4.49it/s]
 24%|██▍       | 2650/11066 [09:44<31:15,  4.49it/s]
                                                    

 24%|██▍       | 2650/11066 [09:44<31:15,  4.49it/s]
 24%|██▍       | 2651/11066 [09:44<31:14,  4.49it/s]
                                                    

 24%|██▍       | 2651/11066 [09:44<31:14,  4.49it/s]
 24%|██▍       | 2652/11066 [09:44<31:11,  4.50it/s]
                                                    

 24%|██▍       | 2652/11066 [09:44<31:11,  4.50it/s]
 24%|██▍       | 2653/11066 [09:45<31:12,  4.49it/s]
                                                    

 24%|██▍       | 2653/11066 [09:45<31:12,  4.49it/s]
 24%|██▍       | 2654/11066 [09:45<31:12,  4.49it/s]
                                                    

 24%|██▍       | 2654/11066 [09:45<31:12,  4.49it/s]
 24%|██▍       | 2655/11066 [09:45<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2655/11066 [09:45<31:09,  4.50it/s]
 24%|██▍       | 2656/11066 [09:45<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2656/11066 [09:45<31:09,  4.50it/s]
 24%|██▍       | 2657/11066 [09:45<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2657/11066 [09:46<31:09,  4.50it/s]
 24%|██▍       | 2658/11066 [09:46<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2658/11066 [09:46<31:09,  4.50it/s]
 24%|██▍       | 2659/11066 [09:46<31:07,  4.50it/s]
                                                    

 24%|██▍       | 2659/11066 [09:46<31:07,  4.50it/s]
 24%|██▍       | 2660/11066 [09:46<31:09,  4.50it/s]
                                                    

 24%|██▍       | 2660/11066 [09:46<31:09,  4.50it/s]
 24%|██▍       | 2661/11066 [09:46<31:08,  4.50it/s]
                                                    

 24%|██▍       | 2661/11066 [09:46<31:08,  4.50it/s]
 24%|██▍       | 2662/11066 [09:47<31:24,  4.46it/s]
                                                    

 24%|██▍       | 2662/11066 [09:47<31:24,  4.46it/s]
 24%|██▍       | 2663/11066 [09:47<31:31,  4.44it/s]
                                                    

 24%|██▍       | 2663/11066 [09:47<31:31,  4.44it/s]
 24%|██▍       | 2664/11066 [09:47<31:12,  4.49it/s]
                                                    

 24%|██▍       | 2664/11066 [09:47<31:12,  4.49it/s]
 24%|██▍       | 2665/11066 [09:47<31:19,  4.47it/s]
                                                    

 24%|██▍       | 2665/11066 [09:47<31:19,  4.47it/s]
 24%|██▍       | 2666/11066 [09:48<31:19,  4.47it/s]
                                                    

 24%|██▍       | 2666/11066 [09:48<31:19,  4.47it/s]
 24%|██▍       | 2667/11066 [09:48<31:16,  4.48it/s]
                                                    

 24%|██▍       | 2667/11066 [09:48<31:16,  4.48it/s]
 24%|██▍       | 2668/11066 [09:48<31:00,  4.51it/s]
                                                    

 24%|██▍       | 2668/11066 [09:48<31:00,  4.51it/s]
 24%|██▍       | 2669/11066 [09:48<31:10,  4.49it/s]
                                                    

 24%|██▍       | 2669/11066 [09:48<31:10,  4.49it/s]
 24%|██▍       | 2670/11066 [09:48<31:12,  4.48it/s]
                                                    

 24%|██▍       | 2670/11066 [09:48<31:12,  4.48it/s]
 24%|██▍       | 2671/11066 [09:49<31:13,  4.48it/s]
                                                    

 24%|██▍       | 2671/11066 [09:49<31:13,  4.48it/s]
 24%|██▍       | 2672/11066 [09:49<31:12,  4.48it/s]
                                                    

 24%|██▍       | 2672/11066 [09:49<31:12,  4.48it/s]
 24%|██▍       | 2673/11066 [09:49<30:58,  4.52it/s]
                                                    

 24%|██▍       | 2673/11066 [09:49<30:58,  4.52it/s]
 24%|██▍       | 2674/11066 [09:49<31:03,  4.50it/s]
                                                    

 24%|██▍       | 2674/11066 [09:49<31:03,  4.50it/s]
 24%|██▍       | 2675/11066 [09:50<31:11,  4.48it/s]
                                                    

 24%|██▍       | 2675/11066 [09:50<31:11,  4.48it/s]
 24%|██▍       | 2676/11066 [09:50<31:16,  4.47it/s]
                                                    

 24%|██▍       | 2676/11066 [09:50<31:16,  4.47it/s]
 24%|██▍       | 2677/11066 [09:50<31:13,  4.48it/s]
                                                    

 24%|██▍       | 2677/11066 [09:50<31:13,  4.48it/s]
 24%|██▍       | 2678/11066 [09:50<31:11,  4.48it/s]
                                                    

 24%|██▍       | 2678/11066 [09:50<31:11,  4.48it/s]
 24%|██▍       | 2679/11066 [09:50<31:08,  4.49it/s]
                                                    

 24%|██▍       | 2679/11066 [09:50<31:08,  4.49it/s]
 24%|██▍       | 2680/11066 [09:51<31:05,  4.49it/s]
                                                    

 24%|██▍       | 2680/11066 [09:51<31:05,  4.49it/s]
 24%|██▍       | 2681/11066 [09:51<31:05,  4.49it/s]
                                                    

 24%|██▍       | 2681/11066 [09:51<31:05,  4.49it/s]
 24%|██▍       | 2682/11066 [09:51<30:50,  4.53it/s]
                                                    

 24%|██▍       | 2682/11066 [09:51<30:50,  4.53it/s]
 24%|██▍       | 2683/11066 [09:51<31:01,  4.50it/s]
                                                    

 24%|██▍       | 2683/11066 [09:51<31:01,  4.50it/s]
 24%|██▍       | 2684/11066 [09:52<31:02,  4.50it/s]
                                                    

 24%|██▍       | 2684/11066 [09:52<31:02,  4.50it/s]
 24%|██▍       | 2685/11066 [09:52<31:05,  4.49it/s]
                                                    

 24%|██▍       | 2685/11066 [09:52<31:05,  4.49it/s]
 24%|██▍       | 2686/11066 [09:52<30:49,  4.53it/s]
                                                    

 24%|██▍       | 2686/11066 [09:52<30:49,  4.53it/s]
 24%|██▍       | 2687/11066 [09:52<30:32,  4.57it/s]
                                                    

 24%|██▍       | 2687/11066 [09:52<30:32,  4.57it/s]
 24%|██▍       | 2688/11066 [09:52<30:47,  4.54it/s]
                                                    

 24%|██▍       | 2688/11066 [09:52<30:47,  4.54it/s]
 24%|██▍       | 2689/11066 [09:53<30:53,  4.52it/s]
                                                    

 24%|██▍       | 2689/11066 [09:53<30:53,  4.52it/s]
 24%|██▍       | 2690/11066 [09:53<30:58,  4.51it/s]
                                                    

 24%|██▍       | 2690/11066 [09:53<30:58,  4.51it/s]
 24%|██▍       | 2691/11066 [09:53<30:46,  4.54it/s]
                                                    

 24%|██▍       | 2691/11066 [09:53<30:46,  4.54it/s]
 24%|██▍       | 2692/11066 [09:53<30:34,  4.57it/s]
                                                    

 24%|██▍       | 2692/11066 [09:53<30:34,  4.57it/s]
 24%|██▍       | 2693/11066 [09:53<30:44,  4.54it/s]
                                                    

 24%|██▍       | 2693/11066 [09:53<30:44,  4.54it/s]
 24%|██▍       | 2694/11066 [09:54<30:51,  4.52it/s]
                                                    

 24%|██▍       | 2694/11066 [09:54<30:51,  4.52it/s]
 24%|██▍       | 2695/11066 [09:54<30:53,  4.52it/s]
                                                    

 24%|██▍       | 2695/11066 [09:54<30:53,  4.52it/s]
 24%|██▍       | 2696/11066 [09:54<30:41,  4.55it/s]
                                                    

 24%|██▍       | 2696/11066 [09:54<30:41,  4.55it/s]
 24%|██▍       | 2697/11066 [09:54<30:26,  4.58it/s]
                                                    

 24%|██▍       | 2697/11066 [09:54<30:26,  4.58it/s]
 24%|██▍       | 2698/11066 [09:55<30:37,  4.55it/s]
                                                    

 24%|██▍       | 2698/11066 [09:55<30:37,  4.55it/s]
 24%|██▍       | 2699/11066 [09:55<30:50,  4.52it/s]
                                                    

 24%|██▍       | 2699/11066 [09:55<30:50,  4.52it/s]
 24%|██▍       | 2700/11066 [09:55<30:55,  4.51it/s]
                                                    

 24%|██▍       | 2700/11066 [09:55<30:55,  4.51it/s]
 24%|██▍       | 2701/11066 [09:55<30:57,  4.50it/s]
                                                    
{'loss': 0.7578, 'learning_rate': 2.2981203686969095e-05, 'epoch': 0.47}
{'loss': 0.8432, 'learning_rate': 2.2978492680281947e-05, 'epoch': 0.47}
{'loss': 1.0325, 'learning_rate': 2.2975781673594795e-05, 'epoch': 0.47}
{'loss': 1.4529, 'learning_rate': 2.2973070666907644e-05, 'epoch': 0.47}
{'loss': 0.9481, 'learning_rate': 2.2970359660220495e-05, 'epoch': 0.47}
{'loss': 0.7675, 'learning_rate': 2.2967648653533344e-05, 'epoch': 0.47}
{'loss': 0.8807, 'learning_rate': 2.2964937646846196e-05, 'epoch': 0.47}
{'loss': 0.8559, 'learning_rate': 2.2962226640159048e-05, 'epoch': 0.47}
{'loss': 0.5845, 'learning_rate': 2.2959515633471896e-05, 'epoch': 0.47}
{'loss': 1.7292, 'learning_rate': 2.2956804626784748e-05, 'epoch': 0.47}
{'loss': 1.5098, 'learning_rate': 2.29540936200976e-05, 'epoch': 0.47}
{'loss': 1.3042, 'learning_rate': 2.2951382613410445e-05, 'epoch': 0.47}
{'loss': 0.9294, 'learning_rate': 2.2948671606723297e-05, 'epoch': 0.47}
{'loss': 0.8091, 'learning_rate': 2.2945960600036145e-05, 'epoch': 0.47}
{'loss': 1.0391, 'learning_rate': 2.2943249593348997e-05, 'epoch': 0.47}
{'loss': 1.5594, 'learning_rate': 2.294053858666185e-05, 'epoch': 0.47}
{'loss': 1.0532, 'learning_rate': 2.2937827579974697e-05, 'epoch': 0.47}
{'loss': 1.774, 'learning_rate': 2.293511657328755e-05, 'epoch': 0.47}
{'loss': 0.9467, 'learning_rate': 2.29324055666004e-05, 'epoch': 0.47}
{'loss': 1.7616, 'learning_rate': 2.2929694559913246e-05, 'epoch': 0.47}
{'loss': 1.2328, 'learning_rate': 2.2926983553226098e-05, 'epoch': 0.47}
{'loss': 1.2486, 'learning_rate': 2.292427254653895e-05, 'epoch': 0.47}
{'loss': 0.7373, 'learning_rate': 2.2921561539851798e-05, 'epoch': 0.47}
{'loss': 1.1546, 'learning_rate': 2.291885053316465e-05, 'epoch': 0.47}
{'loss': 1.4478, 'learning_rate': 2.2916139526477498e-05, 'epoch': 0.47}
{'loss': 0.7097, 'learning_rate': 2.291342851979035e-05, 'epoch': 0.47}
{'loss': 1.1594, 'learning_rate': 2.2910717513103202e-05, 'epoch': 0.47}
{'loss': 1.4498, 'learning_rate': 2.2908006506416047e-05, 'epoch': 0.47}
{'loss': 1.2365, 'learning_rate': 2.29052954997289e-05, 'epoch': 0.47}
{'loss': 1.2301, 'learning_rate': 2.290258449304175e-05, 'epoch': 0.47}
{'loss': 1.1628, 'learning_rate': 2.28998734863546e-05, 'epoch': 0.47}
{'loss': 1.8171, 'learning_rate': 2.289716247966745e-05, 'epoch': 0.47}
{'loss': 1.7916, 'learning_rate': 2.2894451472980303e-05, 'epoch': 0.47}
{'loss': 1.3967, 'learning_rate': 2.289174046629315e-05, 'epoch': 0.47}
{'loss': 0.5457, 'learning_rate': 2.2889029459606003e-05, 'epoch': 0.47}
{'loss': 1.6054, 'learning_rate': 2.2886318452918848e-05, 'epoch': 0.47}
{'loss': 1.5075, 'learning_rate': 2.28836074462317e-05, 'epoch': 0.47}
{'loss': 0.5689, 'learning_rate': 2.288089643954455e-05, 'epoch': 0.47}
{'loss': 1.1938, 'learning_rate': 2.28781854328574e-05, 'epoch': 0.47}
{'loss': 0.6357, 'learning_rate': 2.2875474426170252e-05, 'epoch': 0.47}
{'loss': 0.9684, 'learning_rate': 2.2872763419483104e-05, 'epoch': 0.48}
{'loss': 0.581, 'learning_rate': 2.2870052412795952e-05, 'epoch': 0.48}
{'loss': 0.8185, 'learning_rate': 2.2867341406108804e-05, 'epoch': 0.48}
{'loss': 1.1678, 'learning_rate': 2.2864630399421652e-05, 'epoch': 0.48}
{'loss': 1.1385, 'learning_rate': 2.28619193927345e-05, 'epoch': 0.48}
{'loss': 1.7497, 'learning_rate': 2.2859208386047353e-05, 'epoch': 0.48}
{'loss': 1.0074, 'learning_rate': 2.28564973793602e-05, 'epoch': 0.48}
{'loss': 1.1658, 'learning_rate': 2.2853786372673053e-05, 'epoch': 0.48}
{'loss': 0.6113, 'learning_rate': 2.2851075365985905e-05, 'epoch': 0.48}
{'loss': 1.1769, 'learning_rate': 2.2848364359298753e-05, 'epoch': 0.48}
{'loss': 0.9724, 'learning_rate': 2.2845653352611605e-05, 'epoch': 0.48}
{'loss': 1.1804, 'learning_rate': 2.2842942345924454e-05, 'epoch': 0.48}
{'loss': 0.5754, 'learning_rate': 2.2840231339237302e-05, 'epoch': 0.48}
{'loss': 1.9807, 'learning_rate': 2.2837520332550154e-05, 'epoch': 0.48}
{'loss': 0.4841, 'learning_rate': 2.2834809325863006e-05, 'epoch': 0.48}
{'loss': 1.1221, 'learning_rate': 2.2832098319175854e-05, 'epoch': 0.48}
{'loss': 1.3306, 'learning_rate': 2.2829387312488706e-05, 'epoch': 0.48}
{'loss': 0.9189, 'learning_rate': 2.2826676305801554e-05, 'epoch': 0.48}
{'loss': 0.6892, 'learning_rate': 2.2823965299114406e-05, 'epoch': 0.48}
{'loss': 1.3046, 'learning_rate': 2.2821254292427255e-05, 'epoch': 0.48}
{'loss': 1.0688, 'learning_rate': 2.2818543285740103e-05, 'epoch': 0.48}
{'loss': 0.8203, 'learning_rate': 2.2815832279052955e-05, 'epoch': 0.48}
{'loss': 1.843, 'learning_rate': 2.2813121272365807e-05, 'epoch': 0.48}
{'loss': 1.1329, 'learning_rate': 2.2810410265678655e-05, 'epoch': 0.48}
{'loss': 2.1101, 'learning_rate': 2.2807699258991507e-05, 'epoch': 0.48}
{'loss': 1.2624, 'learning_rate': 2.280498825230436e-05, 'epoch': 0.48}
{'loss': 0.717, 'learning_rate': 2.2802277245617207e-05, 'epoch': 0.48}
{'loss': 2.0108, 'learning_rate': 2.2799566238930056e-05, 'epoch': 0.48}
{'loss': 0.7684, 'learning_rate': 2.2796855232242907e-05, 'epoch': 0.48}
{'loss': 1.6446, 'learning_rate': 2.2794144225555756e-05, 'epoch': 0.48}
{'loss': 1.0892, 'learning_rate': 2.2791433218868608e-05, 'epoch': 0.48}
{'loss': 1.5776, 'learning_rate': 2.2788722212181456e-05, 'epoch': 0.48}
{'loss': 0.5545, 'learning_rate': 2.2786011205494308e-05, 'epoch': 0.48}
{'loss': 0.9295, 'learning_rate': 2.278330019880716e-05, 'epoch': 0.48}
{'loss': 1.1234, 'learning_rate': 2.2780589192120008e-05, 'epoch': 0.48}
{'loss': 1.627, 'learning_rate': 2.2777878185432857e-05, 'epoch': 0.48}
{'loss': 1.0762, 'learning_rate': 2.277516717874571e-05, 'epoch': 0.48}
{'loss': 1.6484, 'learning_rate': 2.2772456172058557e-05, 'epoch': 0.48}
{'loss': 1.0249, 'learning_rate': 2.276974516537141e-05, 'epoch': 0.48}
{'loss': 0.7531, 'learning_rate': 2.276703415868426e-05, 'epoch': 0.48}
{'loss': 1.3454, 'learning_rate': 2.276432315199711e-05, 'epoch': 0.48}
{'loss': 1.4199, 'learning_rate': 2.276161214530996e-05, 'epoch': 0.48}
{'loss': 0.9429, 'learning_rate': 2.275890113862281e-05, 'epoch': 0.48}
{'loss': 1.3103, 'learning_rate': 2.2756190131935658e-05, 'epoch': 0.48}
{'loss': 0.7981, 'learning_rate': 2.275347912524851e-05, 'epoch': 0.48}
{'loss': 1.0778, 'learning_rate': 2.2750768118561358e-05, 'epoch': 0.48}
{'loss': 0.7832, 'learning_rate': 2.274805711187421e-05, 'epoch': 0.48}
{'loss': 1.2617, 'learning_rate': 2.2745346105187062e-05, 'epoch': 0.48}
{'loss': 1.0401, 'learning_rate': 2.274263509849991e-05, 'epoch': 0.48}
{'loss': 1.0455, 'learning_rate': 2.2739924091812762e-05, 'epoch': 0.48}
{'loss': 1.3311, 'learning_rate': 2.2737213085125614e-05, 'epoch': 0.48}
{'loss': 0.9609, 'learning_rate': 2.273450207843846e-05, 'epoch': 0.48}
{'loss': 1.2156, 'learning_rate': 2.273179107175131e-05, 'epoch': 0.48}
{'loss': 1.498, 'learning_rate': 2.272908006506416e-05, 'epoch': 0.48}
{'loss': 1.5096, 'learning_rate': 2.272636905837701e-05, 'epoch': 0.48}
{'loss': 1.4701, 'learning_rate': 2.2723658051689863e-05, 'epoch': 0.49}
{'loss': 1.336, 'learning_rate': 2.272094704500271e-05, 'epoch': 0.49}
{'loss': 0.9846, 'learning_rate': 2.2718236038315563e-05, 'epoch': 0.49}
{'loss': 1.1262, 'learning_rate': 2.2715525031628415e-05, 'epoch': 0.49}
{'loss': 0.8643, 'learning_rate': 2.271281402494126e-05, 'epoch': 0.49}
{'loss': 1.214, 'learning_rate': 2.2710103018254112e-05, 'epoch': 0.49}
{'loss': 0.8235, 'learning_rate': 2.2707392011566964e-05, 'epoch': 0.49}
{'loss': 1.8499, 'learning_rate': 2.2704681004879812e-05, 'epoch': 0.49}
{'loss': 1.1244, 'learning_rate': 2.2701969998192664e-05, 'epoch': 0.49}
{'loss': 2.2244, 'learning_rate': 2.2699258991505512e-05, 'epoch': 0.49}
{'loss': 1.3113, 'learning_rate': 2.2696547984818364e-05, 'epoch': 0.49}
{'loss': 1.0602, 'learning_rate': 2.2693836978131216e-05, 'epoch': 0.49}
{'loss': 1.9117, 'learning_rate': 2.269112597144406e-05, 'epoch': 0.49}
{'loss': 0.9877, 'learning_rate': 2.2688414964756913e-05, 'epoch': 0.49}
{'loss': 1.2872, 'learning_rate': 2.2685703958069765e-05, 'epoch': 0.49}
{'loss': 0.7006, 'learning_rate': 2.2682992951382613e-05, 'epoch': 0.49}
{'loss': 1.6356, 'learning_rate': 2.2680281944695465e-05, 'epoch': 0.49}

 24%|██▍       | 2701/11066 [09:55<30:57,  4.50it/s]
 24%|██▍       | 2702/11066 [09:55<30:43,  4.54it/s]
                                                    

 24%|██▍       | 2702/11066 [09:55<30:43,  4.54it/s]
 24%|██▍       | 2703/11066 [09:56<30:52,  4.51it/s]
                                                    

 24%|██▍       | 2703/11066 [09:56<30:52,  4.51it/s]
 24%|██▍       | 2704/11066 [09:56<31:02,  4.49it/s]
                                                    

 24%|██▍       | 2704/11066 [09:56<31:02,  4.49it/s]
 24%|██▍       | 2705/11066 [09:56<31:03,  4.49it/s]
                                                    

 24%|██▍       | 2705/11066 [09:56<31:03,  4.49it/s]
 24%|██▍       | 2706/11066 [09:56<31:01,  4.49it/s]
                                                    

 24%|██▍       | 2706/11066 [09:56<31:01,  4.49it/s]
 24%|██▍       | 2707/11066 [09:57<30:59,  4.49it/s]
                                                    

 24%|██▍       | 2707/11066 [09:57<30:59,  4.49it/s]
 24%|██▍       | 2708/11066 [09:57<30:57,  4.50it/s]
                                                    

 24%|██▍       | 2708/11066 [09:57<30:57,  4.50it/s]
 24%|██▍       | 2709/11066 [09:57<30:57,  4.50it/s]
                                                    

 24%|██▍       | 2709/11066 [09:57<30:57,  4.50it/s]
 24%|██▍       | 2710/11066 [09:57<30:42,  4.53it/s]
                                                    

 24%|██▍       | 2710/11066 [09:57<30:42,  4.53it/s]
 24%|██▍       | 2711/11066 [09:57<30:53,  4.51it/s]
                                                    

 24%|██▍       | 2711/11066 [09:57<30:53,  4.51it/s]
 25%|██▍       | 2712/11066 [09:58<30:59,  4.49it/s]
                                                    

 25%|██▍       | 2712/11066 [09:58<30:59,  4.49it/s]
 25%|██▍       | 2713/11066 [09:58<30:58,  4.50it/s]
                                                    

 25%|██▍       | 2713/11066 [09:58<30:58,  4.50it/s]
 25%|██▍       | 2714/11066 [09:58<30:56,  4.50it/s]
                                                    

 25%|██▍       | 2714/11066 [09:58<30:56,  4.50it/s]
 25%|██▍       | 2715/11066 [09:58<30:57,  4.50it/s]
                                                    

 25%|██▍       | 2715/11066 [09:58<30:57,  4.50it/s]
 25%|██▍       | 2716/11066 [09:59<30:56,  4.50it/s]
                                                    

 25%|██▍       | 2716/11066 [09:59<30:56,  4.50it/s]
 25%|██▍       | 2717/11066 [09:59<30:57,  4.49it/s]
                                                    

 25%|██▍       | 2717/11066 [09:59<30:57,  4.49it/s]
 25%|██▍       | 2718/11066 [09:59<31:00,  4.49it/s]
                                                    

 25%|██▍       | 2718/11066 [09:59<31:00,  4.49it/s]
 25%|██▍       | 2719/11066 [09:59<30:59,  4.49it/s]
                                                    

 25%|██▍       | 2719/11066 [09:59<30:59,  4.49it/s]
 25%|██▍       | 2720/11066 [09:59<30:56,  4.49it/s]
                                                    

 25%|██▍       | 2720/11066 [09:59<30:56,  4.49it/s]
 25%|██▍       | 2721/11066 [10:00<30:55,  4.50it/s]
                                                    

 25%|██▍       | 2721/11066 [10:00<30:55,  4.50it/s]
 25%|██▍       | 2722/11066 [10:00<30:53,  4.50it/s]
                                                    

 25%|██▍       | 2722/11066 [10:00<30:53,  4.50it/s]
 25%|██▍       | 2723/11066 [10:00<30:53,  4.50it/s]
                                                    

 25%|██▍       | 2723/11066 [10:00<30:53,  4.50it/s]
 25%|██▍       | 2724/11066 [10:00<30:52,  4.50it/s]
                                                    

 25%|██▍       | 2724/11066 [10:00<30:52,  4.50it/s]
 25%|██▍       | 2725/11066 [10:01<30:51,  4.50it/s]
                                                    

 25%|██▍       | 2725/11066 [10:01<30:51,  4.50it/s]
 25%|██▍       | 2726/11066 [10:01<30:52,  4.50it/s]
                                                    

 25%|██▍       | 2726/11066 [10:01<30:52,  4.50it/s]
 25%|██▍       | 2727/11066 [10:01<30:51,  4.50it/s]
                                                    

 25%|██▍       | 2727/11066 [10:01<30:51,  4.50it/s]
 25%|██▍       | 2728/11066 [10:01<30:52,  4.50it/s]
                                                    

 25%|██▍       | 2728/11066 [10:01<30:52,  4.50it/s]
 25%|██▍       | 2729/11066 [10:01<30:37,  4.54it/s]
                                                    

 25%|██▍       | 2729/11066 [10:01<30:37,  4.54it/s]
 25%|██▍       | 2730/11066 [10:02<30:48,  4.51it/s]
                                                    

 25%|██▍       | 2730/11066 [10:02<30:48,  4.51it/s]
 25%|██▍       | 2731/11066 [10:02<30:53,  4.50it/s]
                                                    

 25%|██▍       | 2731/11066 [10:02<30:53,  4.50it/s]
 25%|██▍       | 2732/11066 [10:02<30:24,  4.57it/s]
                                                    

 25%|██▍       | 2732/11066 [10:02<30:24,  4.57it/s]
 25%|██▍       | 2733/11066 [10:02<30:29,  4.55it/s]
                                                    

 25%|██▍       | 2733/11066 [10:02<30:29,  4.55it/s]
 25%|██▍       | 2734/11066 [10:03<30:27,  4.56it/s]
                                                    

 25%|██▍       | 2734/11066 [10:03<30:27,  4.56it/s]
 25%|██▍       | 2735/11066 [10:03<30:39,  4.53it/s]
                                                    

 25%|██▍       | 2735/11066 [10:03<30:39,  4.53it/s]
 25%|██▍       | 2736/11066 [10:03<30:44,  4.52it/s]
                                                    

 25%|██▍       | 2736/11066 [10:03<30:44,  4.52it/s]
 25%|██▍       | 2737/11066 [10:03<30:51,  4.50it/s]
                                                    

 25%|██▍       | 2737/11066 [10:03<30:51,  4.50it/s]
 25%|██▍       | 2738/11066 [10:03<30:38,  4.53it/s]
                                                    

 25%|██▍       | 2738/11066 [10:03<30:38,  4.53it/s]
 25%|██▍       | 2739/11066 [10:04<30:51,  4.50it/s]
                                                    

 25%|██▍       | 2739/11066 [10:04<30:51,  4.50it/s]
 25%|██▍       | 2740/11066 [10:04<30:27,  4.55it/s]
                                                    

 25%|██▍       | 2740/11066 [10:04<30:27,  4.55it/s]
 25%|██▍       | 2741/11066 [10:04<30:09,  4.60it/s]
                                                    

 25%|██▍       | 2741/11066 [10:04<30:09,  4.60it/s]
 25%|██▍       | 2742/11066 [10:04<29:58,  4.63it/s]
                                                    

 25%|██▍       | 2742/11066 [10:04<29:58,  4.63it/s]
 25%|██▍       | 2743/11066 [10:05<30:03,  4.61it/s]
                                                    

 25%|██▍       | 2743/11066 [10:05<30:03,  4.61it/s]
 25%|██▍       | 2744/11066 [10:05<29:42,  4.67it/s]
                                                    

 25%|██▍       | 2744/11066 [10:05<29:42,  4.67it/s]
 25%|██▍       | 2745/11066 [10:05<29:40,  4.67it/s]
                                                    

 25%|██▍       | 2745/11066 [10:05<29:40,  4.67it/s]
 25%|██▍       | 2746/11066 [10:05<30:05,  4.61it/s]
                                                    

 25%|██▍       | 2746/11066 [10:05<30:05,  4.61it/s]
 25%|██▍       | 2747/11066 [10:05<29:54,  4.64it/s]
                                                    

 25%|██▍       | 2747/11066 [10:05<29:54,  4.64it/s]
 25%|██▍       | 2748/11066 [10:06<30:10,  4.59it/s]
                                                    

 25%|██▍       | 2748/11066 [10:06<30:10,  4.59it/s]
 25%|██▍       | 2749/11066 [10:06<29:58,  4.63it/s]
                                                    

 25%|██▍       | 2749/11066 [10:06<29:58,  4.63it/s]
 25%|██▍       | 2750/11066 [10:06<29:50,  4.65it/s]
                                                    

 25%|██▍       | 2750/11066 [10:06<29:50,  4.65it/s]
 25%|██▍       | 2751/11066 [10:06<29:45,  4.66it/s]
                                                    

 25%|██▍       | 2751/11066 [10:06<29:45,  4.66it/s]
 25%|██▍       | 2752/11066 [10:06<29:37,  4.68it/s]
                                                    

 25%|██▍       | 2752/11066 [10:06<29:37,  4.68it/s]
 25%|██▍       | 2753/11066 [10:07<29:56,  4.63it/s]
                                                    

 25%|██▍       | 2753/11066 [10:07<29:56,  4.63it/s]
 25%|██▍       | 2754/11066 [10:07<29:46,  4.65it/s]
                                                    

 25%|██▍       | 2754/11066 [10:07<29:46,  4.65it/s]
 25%|██▍       | 2755/11066 [10:07<29:40,  4.67it/s]
                                                    

 25%|██▍       | 2755/11066 [10:07<29:40,  4.67it/s]
 25%|██▍       | 2756/11066 [10:07<29:34,  4.68it/s]
                                                    

 25%|██▍       | 2756/11066 [10:07<29:34,  4.68it/s]
 25%|██▍       | 2757/11066 [10:08<30:00,  4.62it/s]
                                                    

 25%|██▍       | 2757/11066 [10:08<30:00,  4.62it/s]
 25%|██▍       | 2758/11066 [10:08<29:55,  4.63it/s]
                                                    

 25%|██▍       | 2758/11066 [10:08<29:55,  4.63it/s]
 25%|██▍       | 2759/11066 [10:08<29:44,  4.65it/s]
                                                    

 25%|██▍       | 2759/11066 [10:08<29:44,  4.65it/s]
 25%|██▍       | 2760/11066 [10:08<29:34,  4.68it/s]
                                                    

 25%|██▍       | 2760/11066 [10:08<29:34,  4.68it/s]
 25%|██▍       | 2761/11066 [10:08<29:57,  4.62it/s]
                                                    

 25%|██▍       | 2761/11066 [10:08<29:57,  4.62it/s]
 25%|██▍       | 2762/11066 [10:09<30:11,  4.58it/s]
                                                    

 25%|██▍       | 2762/11066 [10:09<30:11,  4.58it/s]
 25%|██▍       | 2763/11066 [10:09<30:23,  4.55it/s]
                                                    

 25%|██▍       | 2763/11066 [10:09<30:23,  4.55it/s]
 25%|██▍       | 2764/11066 [10:09<30:05,  4.60it/s]
                                                    

 25%|██▍       | 2764/11066 [10:09<30:05,  4.60it/s]
 25%|██▍       | 2765/11066 [10:09<29:52,  4.63it/s]
                                                    

 25%|██▍       | 2765/11066 [10:09<29:52,  4.63it/s]
 25%|██▍       | 2766/11066 [10:10<29:43,  4.65it/s]
                                                    

 25%|██▍       | 2766/11066 [10:10<29:43,  4.65it/s]
 25%|██▌       | 2767/11066 [10:10<29:45,  4.65it/s]
                                                    

 25%|██▌       | 2767/11066 [10:10<29:45,  4.65it/s]
 25%|██▌       | 2768/11066 [10:10<29:34,  4.68it/s]
                                                    

 25%|██▌       | 2768/11066 [10:10<29:34,  4.68it/s]
 25%|██▌       | 2769/11066 [10:10<29:30,  4.69it/s]
                                                    

 25%|██▌       | 2769/11066 [10:10<29:30,  4.69it/s]
 25%|██▌       | 2770/11066 [10:10<29:25,  4.70it/s]
                                                    

 25%|██▌       | 2770/11066 [10:10<29:25,  4.70it/s]
 25%|██▌       | 2771/11066 [10:11<29:47,  4.64it/s]
                                                    

 25%|██▌       | 2771/11066 [10:11<29:47,  4.64it/s]
 25%|██▌       | 2772/11066 [10:11<30:02,  4.60it/s]
                                                    

 25%|██▌       | 2772/11066 [10:11<30:02,  4.60it/s]
 25%|██▌       | 2773/11066 [10:11<29:48,  4.64it/s]
                                                    

 25%|██▌       | 2773/11066 [10:11<29:48,  4.64it/s]
 25%|██▌       | 2774/11066 [10:11<29:40,  4.66it/s]
                                                    

 25%|██▌       | 2774/11066 [10:11<29:40,  4.66it/s]
 25%|██▌       | 2775/11066 [10:11<30:01,  4.60it/s]
                                                    

 25%|██▌       | 2775/11066 [10:11<30:01,  4.60it/s]
 25%|██▌       | 2776/11066 [10:12<30:13,  4.57it/s]
                                                    

 25%|██▌       | 2776/11066 [10:12<30:13,  4.57it/s]
 25%|██▌       | 2777/11066 [10:12<29:57,  4.61it/s]
                                                    

 25%|██▌       | 2777/11066 [10:12<29:57,  4.61it/s]
 25%|██▌       | 2778/11066 [10:12<29:45,  4.64it/s]
                                                    

 25%|██▌       | 2778/11066 [10:12<29:45,  4.64it/s]
 25%|██▌       | 2779/11066 [10:12<29:37,  4.66it/s]
                                                    

 25%|██▌       | 2779/11066 [10:12<29:37,  4.66it/s]
 25%|██▌       | 2780/11066 [10:13<29:31,  4.68it/s]
                                                    

 25%|██▌       | 2780/11066 [10:13<29:31,  4.68it/s]
 25%|██▌       | 2781/11066 [10:13<29:28,  4.69it/s]
                                                    

 25%|██▌       | 2781/11066 [10:13<29:28,  4.69it/s]
 25%|██▌       | 2782/11066 [10:13<29:22,  4.70it/s]
                                                    

 25%|██▌       | 2782/11066 [10:13<29:22,  4.70it/s]
 25%|██▌       | 2783/11066 [10:13<29:22,  4.70it/s]
                                                    

 25%|██▌       | 2783/11066 [10:13<29:22,  4.70it/s]
 25%|██▌       | 2784/11066 [10:13<29:21,  4.70it/s]
                                                    

 25%|██▌       | 2784/11066 [10:13<29:21,  4.70it/s]
 25%|██▌       | 2785/11066 [10:14<29:45,  4.64it/s]
                                                    

 25%|██▌       | 2785/11066 [10:14<29:45,  4.64it/s]
 25%|██▌       | 2786/11066 [10:14<29:49,  4.63it/s]
                                                    

 25%|██▌       | 2786/11066 [10:14<29:49,  4.63it/s]
 25%|██▌       | 2787/11066 [10:14<29:33,  4.67it/s]
                                                    

 25%|██▌       | 2787/11066 [10:14<29:33,  4.67it/s]
 25%|██▌       | 2788/11066 [10:14<29:37,  4.66it/s]
                                                    

 25%|██▌       | 2788/11066 [10:14<29:37,  4.66it/s]
 25%|██▌       | 2789/11066 [10:14<29:58,  4.60it/s]
                                                    

 25%|██▌       | 2789/11066 [10:14<29:58,  4.60it/s]
 25%|██▌       | 2790/11066 [10:15<30:18,  4.55it/s]
                                                    

 25%|██▌       | 2790/11066 [10:15<30:18,  4.55it/s]
 25%|██▌       | 2791/11066 [10:15<30:39,  4.50it/s]
                                                    

 25%|██▌       | 2791/11066 [10:15<30:39,  4.50it/s]
 25%|██▌       | 2792/11066 [10:15<30:46,  4.48it/s]
                                                    

 25%|██▌       | 2792/11066 [10:15<30:46,  4.48it/s]
 25%|██▌       | 2793/11066 [10:15<30:46,  4.48it/s]
                                                    

 25%|██▌       | 2793/11066 [10:15<30:46,  4.48it/s]
 25%|██▌       | 2794/11066 [10:16<30:45,  4.48it/s]
                                                    

 25%|██▌       | 2794/11066 [10:16<30:45,  4.48it/s]
 25%|██▌       | 2795/11066 [10:16<30:45,  4.48it/s]
                                                    

 25%|██▌       | 2795/11066 [10:16<30:45,  4.48it/s]
 25%|██▌       | 2796/11066 [10:16<30:43,  4.48it/s]
                                                    

 25%|██▌       | 2796/11066 [10:16<30:43,  4.48it/s]
 25%|██▌       | 2797/11066 [10:16<30:43,  4.49it/s]
                                                    

 25%|██▌       | 2797/11066 [10:16<30:43,  4.49it/s]
 25%|██▌       | 2798/11066 [10:16<30:41,  4.49it/s]
                                                    

 25%|██▌       | 2798/11066 [10:16<30:41,  4.49it/s]
 25%|██▌       | 2799/11066 [10:17<30:40,  4.49it/s]
                                                    

 25%|██▌       | 2799/11066 [10:17<30:40,  4.49it/s]
 25%|██▌       | 2800/11066 [10:17<30:27,  4.52it/s]
                                                    

 25%|██▌       | 2800/11066 [10:17<30:27,  4.52it/s]
 25%|██▌       | 2801/11066 [10:17<30:31,  4.51it/s]
                                                    

 25%|██▌       | 2801/11066 [10:17<30:31,  4.51it/s]
 25%|██▌       | 2802/11066 [10:17<30:38,  4.49it/s]
                                                    

 25%|██▌       | 2802/11066 [10:17<30:38,  4.49it/s]
 25%|██▌       | 2803/11066 [10:18<30:42,  4.49it/s]
                                                    

 25%|██▌       | 2803/11066 [10:18<30:42,  4.49it/s]
 25%|██▌       | 2804/11066 [10:18<30:17,  4.55it/s]
                                                    

 25%|██▌       | 2804/11066 [10:18<30:17,  4.55it/s]
 25%|██▌       | 2805/11066 [10:18<29:56,  4.60it/s]
                                                    

 25%|██▌       | 2805/11066 [10:18<29:56,  4.60it/s]
 25%|██▌       | 2806/11066 [10:18<29:42,  4.63it/s]
                                                    

 25%|██▌       | 2806/11066 [10:18<29:42,  4.63it/s]
 25%|██▌       | 2807/11066 [10:18<29:31,  4.66it/s]
                                                    

 25%|██▌       | 2807/11066 [10:18<29:31,  4.66it/s]
 25%|██▌       | 2808/11066 [10:19<29:25,  4.68it/s]
                                                    

 25%|██▌       | 2808/11066 [10:19<29:25,  4.68it/s]
 25%|██▌       | 2809/11066 [10:19<29:33,  4.65it/s]
                                                    

 25%|██▌       | 2809/11066 [10:19<29:33,  4.65it/s]
 25%|██▌       | 2810/11066 [10:19<29:21,  4.69it/s]
                                                    

 25%|██▌       | 2810/11066 [10:19<29:21,  4.69it/s]
 25%|██▌       | 2811/11066 [10:19<29:08,  4.72it/s]
                                                    

 25%|██▌       | 2811/11066 [10:19<29:08,  4.72it/s]
 25%|██▌       | 2812/11066 [10:19<29:14,  4.71it/s]
                                                    

 25%|██▌       | 2812/11066 [10:19<29:14,  4.71it/s]
 25%|██▌       | 2813/11066 [10:20<29:25,  4.67it/s]
                                                    

 25%|██▌       | 2813/11066 [10:20<29:25,  4.67it/s]
 25%|██▌       | 2814/11066 [10:20<29:20,  4.69it/s]
                                                    
{'loss': 1.4323, 'learning_rate': 2.2677570938008317e-05, 'epoch': 0.49}
{'loss': 0.9458, 'learning_rate': 2.2674859931321165e-05, 'epoch': 0.49}
{'loss': 1.1537, 'learning_rate': 2.2672148924634014e-05, 'epoch': 0.49}
{'loss': 1.0647, 'learning_rate': 2.2669437917946862e-05, 'epoch': 0.49}
{'loss': 1.1344, 'learning_rate': 2.2666726911259714e-05, 'epoch': 0.49}
{'loss': 1.541, 'learning_rate': 2.2664015904572566e-05, 'epoch': 0.49}
{'loss': 1.5436, 'learning_rate': 2.2661304897885414e-05, 'epoch': 0.49}
{'loss': 1.2083, 'learning_rate': 2.2658593891198266e-05, 'epoch': 0.49}
{'loss': 1.0746, 'learning_rate': 2.2655882884511118e-05, 'epoch': 0.49}
{'loss': 0.5945, 'learning_rate': 2.2653171877823966e-05, 'epoch': 0.49}
{'loss': 0.9751, 'learning_rate': 2.2650460871136815e-05, 'epoch': 0.49}
{'loss': 1.4879, 'learning_rate': 2.2647749864449667e-05, 'epoch': 0.49}
{'loss': 1.4742, 'learning_rate': 2.2645038857762515e-05, 'epoch': 0.49}
{'loss': 1.1639, 'learning_rate': 2.2642327851075367e-05, 'epoch': 0.49}
{'loss': 2.2402, 'learning_rate': 2.2639616844388215e-05, 'epoch': 0.49}
{'loss': 1.844, 'learning_rate': 2.2636905837701067e-05, 'epoch': 0.49}
{'loss': 1.3859, 'learning_rate': 2.263419483101392e-05, 'epoch': 0.49}
{'loss': 0.8465, 'learning_rate': 2.2631483824326767e-05, 'epoch': 0.49}
{'loss': 1.3929, 'learning_rate': 2.2628772817639616e-05, 'epoch': 0.49}
{'loss': 0.6815, 'learning_rate': 2.2626061810952468e-05, 'epoch': 0.49}
{'loss': 0.8552, 'learning_rate': 2.2623350804265316e-05, 'epoch': 0.49}
{'loss': 0.7843, 'learning_rate': 2.2620639797578168e-05, 'epoch': 0.49}
{'loss': 0.8342, 'learning_rate': 2.261792879089102e-05, 'epoch': 0.49}
{'loss': 1.2083, 'learning_rate': 2.2615217784203868e-05, 'epoch': 0.49}
{'loss': 1.3473, 'learning_rate': 2.261250677751672e-05, 'epoch': 0.49}
{'loss': 1.0745, 'learning_rate': 2.260979577082957e-05, 'epoch': 0.49}
{'loss': 0.956, 'learning_rate': 2.2607084764142417e-05, 'epoch': 0.49}
{'loss': 1.1845, 'learning_rate': 2.260437375745527e-05, 'epoch': 0.49}
{'loss': 1.2661, 'learning_rate': 2.2601662750768117e-05, 'epoch': 0.49}
{'loss': 0.7601, 'learning_rate': 2.259895174408097e-05, 'epoch': 0.49}
{'loss': 0.9305, 'learning_rate': 2.259624073739382e-05, 'epoch': 0.49}
{'loss': 1.1569, 'learning_rate': 2.259352973070667e-05, 'epoch': 0.49}
{'loss': 1.3495, 'learning_rate': 2.259081872401952e-05, 'epoch': 0.49}
{'loss': 1.1909, 'learning_rate': 2.2588107717332373e-05, 'epoch': 0.49}
{'loss': 0.9159, 'learning_rate': 2.2585396710645218e-05, 'epoch': 0.49}
{'loss': 0.6867, 'learning_rate': 2.258268570395807e-05, 'epoch': 0.49}
{'loss': 1.101, 'learning_rate': 2.2579974697270918e-05, 'epoch': 0.49}
{'loss': 0.947, 'learning_rate': 2.257726369058377e-05, 'epoch': 0.49}
{'loss': 1.0144, 'learning_rate': 2.2574552683896622e-05, 'epoch': 0.5}
{'loss': 0.7859, 'learning_rate': 2.257184167720947e-05, 'epoch': 0.5}
{'loss': 1.5625, 'learning_rate': 2.2569130670522322e-05, 'epoch': 0.5}
{'loss': 0.9716, 'learning_rate': 2.2566419663835174e-05, 'epoch': 0.5}
{'loss': 1.8594, 'learning_rate': 2.256370865714802e-05, 'epoch': 0.5}
{'loss': 1.1613, 'learning_rate': 2.256099765046087e-05, 'epoch': 0.5}
{'loss': 1.4764, 'learning_rate': 2.2558286643773723e-05, 'epoch': 0.5}
{'loss': 1.1649, 'learning_rate': 2.255557563708657e-05, 'epoch': 0.5}
{'loss': 1.2833, 'learning_rate': 2.2552864630399423e-05, 'epoch': 0.5}
{'loss': 0.6972, 'learning_rate': 2.255015362371227e-05, 'epoch': 0.5}
{'loss': 1.0133, 'learning_rate': 2.2547442617025123e-05, 'epoch': 0.5}
{'loss': 1.1573, 'learning_rate': 2.2544731610337975e-05, 'epoch': 0.5}
{'loss': 0.9214, 'learning_rate': 2.254202060365082e-05, 'epoch': 0.5}
{'loss': 1.364, 'learning_rate': 2.2539309596963672e-05, 'epoch': 0.5}
{'loss': 0.8611, 'learning_rate': 2.2536598590276524e-05, 'epoch': 0.5}
{'loss': 1.9025, 'learning_rate': 2.2533887583589372e-05, 'epoch': 0.5}
{'loss': 1.6231, 'learning_rate': 2.2531176576902224e-05, 'epoch': 0.5}
{'loss': 0.5948, 'learning_rate': 2.2528465570215076e-05, 'epoch': 0.5}
{'loss': 1.6562, 'learning_rate': 2.2525754563527924e-05, 'epoch': 0.5}
{'loss': 0.9437, 'learning_rate': 2.2523043556840776e-05, 'epoch': 0.5}
{'loss': 1.201, 'learning_rate': 2.252033255015362e-05, 'epoch': 0.5}
{'loss': 1.2754, 'learning_rate': 2.2517621543466473e-05, 'epoch': 0.5}
{'loss': 1.1685, 'learning_rate': 2.2514910536779325e-05, 'epoch': 0.5}
{'loss': 1.0006, 'learning_rate': 2.2512199530092173e-05, 'epoch': 0.5}
{'loss': 1.07, 'learning_rate': 2.2509488523405025e-05, 'epoch': 0.5}
{'loss': 1.2641, 'learning_rate': 2.2506777516717877e-05, 'epoch': 0.5}
{'loss': 1.1196, 'learning_rate': 2.2504066510030725e-05, 'epoch': 0.5}
{'loss': 1.7994, 'learning_rate': 2.2501355503343577e-05, 'epoch': 0.5}
{'loss': 1.6871, 'learning_rate': 2.2498644496656426e-05, 'epoch': 0.5}
{'loss': 1.2453, 'learning_rate': 2.2495933489969274e-05, 'epoch': 0.5}
{'loss': 1.71, 'learning_rate': 2.2493222483282126e-05, 'epoch': 0.5}
{'loss': 0.7197, 'learning_rate': 2.2490511476594974e-05, 'epoch': 0.5}
{'loss': 1.0904, 'learning_rate': 2.2487800469907826e-05, 'epoch': 0.5}
{'loss': 1.1329, 'learning_rate': 2.2485089463220678e-05, 'epoch': 0.5}
{'loss': 0.7769, 'learning_rate': 2.2482378456533526e-05, 'epoch': 0.5}
{'loss': 0.9858, 'learning_rate': 2.2479667449846378e-05, 'epoch': 0.5}
{'loss': 0.8735, 'learning_rate': 2.2476956443159227e-05, 'epoch': 0.5}
{'loss': 0.9711, 'learning_rate': 2.2474245436472075e-05, 'epoch': 0.5}
{'loss': 1.0851, 'learning_rate': 2.2471534429784927e-05, 'epoch': 0.5}
{'loss': 0.8491, 'learning_rate': 2.246882342309778e-05, 'epoch': 0.5}
{'loss': 1.1438, 'learning_rate': 2.2466112416410627e-05, 'epoch': 0.5}
{'loss': 0.9458, 'learning_rate': 2.246340140972348e-05, 'epoch': 0.5}
{'loss': 0.9925, 'learning_rate': 2.2460690403036328e-05, 'epoch': 0.5}
{'loss': 1.2869, 'learning_rate': 2.245797939634918e-05, 'epoch': 0.5}
{'loss': 1.6554, 'learning_rate': 2.2455268389662028e-05, 'epoch': 0.5}
{'loss': 1.071, 'learning_rate': 2.2452557382974876e-05, 'epoch': 0.5}
{'loss': 1.3779, 'learning_rate': 2.2449846376287728e-05, 'epoch': 0.5}
{'loss': 0.8727, 'learning_rate': 2.244713536960058e-05, 'epoch': 0.5}
{'loss': 1.0708, 'learning_rate': 2.244442436291343e-05, 'epoch': 0.5}
{'loss': 0.6878, 'learning_rate': 2.244171335622628e-05, 'epoch': 0.5}
{'loss': 1.2369, 'learning_rate': 2.2439002349539132e-05, 'epoch': 0.5}
{'loss': 0.8881, 'learning_rate': 2.243629134285198e-05, 'epoch': 0.5}
{'loss': 1.1966, 'learning_rate': 2.243358033616483e-05, 'epoch': 0.5}
{'loss': 1.2627, 'learning_rate': 2.2430869329477677e-05, 'epoch': 0.5}
{'loss': 2.1045, 'learning_rate': 2.242815832279053e-05, 'epoch': 0.5}
{'loss': 1.5591, 'learning_rate': 2.242544731610338e-05, 'epoch': 0.5}
{'loss': 1.2934, 'learning_rate': 2.242273630941623e-05, 'epoch': 0.51}
{'loss': 1.1859, 'learning_rate': 2.242002530272908e-05, 'epoch': 0.51}
{'loss': 1.1705, 'learning_rate': 2.2417314296041933e-05, 'epoch': 0.51}
{'loss': 1.0475, 'learning_rate': 2.241460328935478e-05, 'epoch': 0.51}
{'loss': 0.7045, 'learning_rate': 2.241189228266763e-05, 'epoch': 0.51}
{'loss': 0.7889, 'learning_rate': 2.2409181275980482e-05, 'epoch': 0.51}
{'loss': 0.8758, 'learning_rate': 2.240647026929333e-05, 'epoch': 0.51}
{'loss': 0.523, 'learning_rate': 2.2403759262606182e-05, 'epoch': 0.51}
{'loss': 1.5045, 'learning_rate': 2.240104825591903e-05, 'epoch': 0.51}
{'loss': 0.8713, 'learning_rate': 2.2398337249231882e-05, 'epoch': 0.51}
{'loss': 0.9667, 'learning_rate': 2.2395626242544734e-05, 'epoch': 0.51}
{'loss': 1.2602, 'learning_rate': 2.2392915235857583e-05, 'epoch': 0.51}
{'loss': 1.1728, 'learning_rate': 2.239020422917043e-05, 'epoch': 0.51}
{'loss': 1.3302, 'learning_rate': 2.2387493222483283e-05, 'epoch': 0.51}
{'loss': 0.5874, 'learning_rate': 2.238478221579613e-05, 'epoch': 0.51}
{'loss': 1.0306, 'learning_rate': 2.2382071209108983e-05, 'epoch': 0.51}
{'loss': 1.5271, 'learning_rate': 2.2379360202421835e-05, 'epoch': 0.51}
{'loss': 0.9787, 'learning_rate': 2.2376649195734683e-05, 'epoch': 0.51}
{'loss': 0.777, 'learning_rate': 2.2373938189047535e-05, 'epoch': 0.51}

 25%|██▌       | 2814/11066 [10:20<29:20,  4.69it/s]
 25%|██▌       | 2815/11066 [10:20<29:22,  4.68it/s]
                                                    

 25%|██▌       | 2815/11066 [10:20<29:22,  4.68it/s]
 25%|██▌       | 2816/11066 [10:20<29:32,  4.66it/s]
                                                    

 25%|██▌       | 2816/11066 [10:20<29:32,  4.66it/s]
 25%|██▌       | 2817/11066 [10:21<30:06,  4.57it/s]
                                                    

 25%|██▌       | 2817/11066 [10:21<30:06,  4.57it/s]
 25%|██▌       | 2818/11066 [10:21<30:40,  4.48it/s]
                                                    

 25%|██▌       | 2818/11066 [10:21<30:40,  4.48it/s]
 25%|██▌       | 2819/11066 [10:21<30:24,  4.52it/s]
                                                    

 25%|██▌       | 2819/11066 [10:21<30:24,  4.52it/s]
 25%|██▌       | 2820/11066 [10:21<30:35,  4.49it/s]
                                                    

 25%|██▌       | 2820/11066 [10:21<30:35,  4.49it/s]
 25%|██▌       | 2821/11066 [10:21<30:22,  4.52it/s]
                                                    

 25%|██▌       | 2821/11066 [10:21<30:22,  4.52it/s]
 26%|██▌       | 2822/11066 [10:22<30:16,  4.54it/s]
                                                    

 26%|██▌       | 2822/11066 [10:22<30:16,  4.54it/s]
 26%|██▌       | 2823/11066 [10:22<30:05,  4.57it/s]
                                                    

 26%|██▌       | 2823/11066 [10:22<30:05,  4.57it/s]
 26%|██▌       | 2824/11066 [10:22<29:55,  4.59it/s]
                                                    

 26%|██▌       | 2824/11066 [10:22<29:55,  4.59it/s]
 26%|██▌       | 2825/11066 [10:22<30:10,  4.55it/s]
                                                    

 26%|██▌       | 2825/11066 [10:22<30:10,  4.55it/s]
 26%|██▌       | 2826/11066 [10:23<30:17,  4.53it/s]
                                                    

 26%|██▌       | 2826/11066 [10:23<30:17,  4.53it/s]
 26%|██▌       | 2827/11066 [10:23<30:21,  4.52it/s]
                                                    

 26%|██▌       | 2827/11066 [10:23<30:21,  4.52it/s]
 26%|██▌       | 2828/11066 [10:23<30:11,  4.55it/s]
                                                    

 26%|██▌       | 2828/11066 [10:23<30:11,  4.55it/s]
 26%|██▌       | 2829/11066 [10:23<30:10,  4.55it/s]
                                                    

 26%|██▌       | 2829/11066 [10:23<30:10,  4.55it/s]
 26%|██▌       | 2830/11066 [10:23<29:59,  4.58it/s]
                                                    

 26%|██▌       | 2830/11066 [10:23<29:59,  4.58it/s]
 26%|██▌       | 2831/11066 [10:24<30:20,  4.52it/s]
                                                    

 26%|██▌       | 2831/11066 [10:24<30:20,  4.52it/s]
 26%|██▌       | 2832/11066 [10:24<30:26,  4.51it/s]
                                                    

 26%|██▌       | 2832/11066 [10:24<30:26,  4.51it/s]
 26%|██▌       | 2833/11066 [10:24<30:25,  4.51it/s]
                                                    

 26%|██▌       | 2833/11066 [10:24<30:25,  4.51it/s]
 26%|██▌       | 2834/11066 [10:24<30:11,  4.54it/s]
                                                    

 26%|██▌       | 2834/11066 [10:24<30:11,  4.54it/s]
 26%|██▌       | 2835/11066 [10:25<29:57,  4.58it/s]
                                                    

 26%|██▌       | 2835/11066 [10:25<29:57,  4.58it/s]
 26%|██▌       | 2836/11066 [10:25<29:57,  4.58it/s]
                                                    

 26%|██▌       | 2836/11066 [10:25<29:57,  4.58it/s]
 26%|██▌       | 2837/11066 [10:25<29:34,  4.64it/s]
                                                    

 26%|██▌       | 2837/11066 [10:25<29:34,  4.64it/s]
 26%|██▌       | 2838/11066 [10:25<29:29,  4.65it/s]
                                                    

 26%|██▌       | 2838/11066 [10:25<29:29,  4.65it/s]
 26%|██▌       | 2839/11066 [10:25<29:12,  4.69it/s]
                                                    

 26%|██▌       | 2839/11066 [10:25<29:12,  4.69it/s]
 26%|██▌       | 2840/11066 [10:26<29:23,  4.66it/s]
                                                    

 26%|██▌       | 2840/11066 [10:26<29:23,  4.66it/s]
 26%|██▌       | 2841/11066 [10:26<29:11,  4.70it/s]
                                                    

 26%|██▌       | 2841/11066 [10:26<29:11,  4.70it/s]
 26%|██▌       | 2842/11066 [10:26<29:10,  4.70it/s]
                                                    

 26%|██▌       | 2842/11066 [10:26<29:10,  4.70it/s]
 26%|██▌       | 2843/11066 [10:26<29:21,  4.67it/s]
                                                    

 26%|██▌       | 2843/11066 [10:26<29:21,  4.67it/s]
 26%|██▌       | 2844/11066 [10:26<29:16,  4.68it/s]
                                                    

 26%|██▌       | 2844/11066 [10:26<29:16,  4.68it/s]
 26%|██▌       | 2845/11066 [10:27<30:12,  4.54it/s]
                                                    

 26%|██▌       | 2845/11066 [10:27<30:12,  4.54it/s]
 26%|██▌       | 2846/11066 [10:27<30:31,  4.49it/s]
                                                    

 26%|██▌       | 2846/11066 [10:27<30:31,  4.49it/s]
 26%|██▌       | 2847/11066 [10:27<30:38,  4.47it/s]
                                                    

 26%|██▌       | 2847/11066 [10:27<30:38,  4.47it/s]
 26%|██▌       | 2848/11066 [10:27<30:48,  4.45it/s]
                                                    

 26%|██▌       | 2848/11066 [10:27<30:48,  4.45it/s]
 26%|██▌       | 2849/11066 [10:28<30:27,  4.50it/s]
                                                    

 26%|██▌       | 2849/11066 [10:28<30:27,  4.50it/s]
 26%|██▌       | 2850/11066 [10:28<30:13,  4.53it/s]
                                                    

 26%|██▌       | 2850/11066 [10:28<30:13,  4.53it/s]
 26%|██▌       | 2851/11066 [10:28<29:45,  4.60it/s]
                                                    

 26%|██▌       | 2851/11066 [10:28<29:45,  4.60it/s]
 26%|██▌       | 2852/11066 [10:28<29:35,  4.63it/s]
                                                    

 26%|██▌       | 2852/11066 [10:28<29:35,  4.63it/s]
 26%|██▌       | 2853/11066 [10:28<29:15,  4.68it/s]
                                                    

 26%|██▌       | 2853/11066 [10:28<29:15,  4.68it/s]
 26%|██▌       | 2854/11066 [10:29<29:25,  4.65it/s]
                                                    

 26%|██▌       | 2854/11066 [10:29<29:25,  4.65it/s]
 26%|██▌       | 2855/11066 [10:29<29:47,  4.59it/s]
                                                    

 26%|██▌       | 2855/11066 [10:29<29:47,  4.59it/s]
 26%|██▌       | 2856/11066 [10:29<29:37,  4.62it/s]
                                                    

 26%|██▌       | 2856/11066 [10:29<29:37,  4.62it/s]
 26%|██▌       | 2857/11066 [10:29<29:26,  4.65it/s]
                                                    

 26%|██▌       | 2857/11066 [10:29<29:26,  4.65it/s]
 26%|██▌       | 2858/11066 [10:30<29:19,  4.66it/s]
                                                    

 26%|██▌       | 2858/11066 [10:30<29:19,  4.66it/s]
 26%|██▌       | 2859/11066 [10:30<29:44,  4.60it/s]
                                                    

 26%|██▌       | 2859/11066 [10:30<29:44,  4.60it/s]
 26%|██▌       | 2860/11066 [10:30<29:58,  4.56it/s]
                                                    

 26%|██▌       | 2860/11066 [10:30<29:58,  4.56it/s]
 26%|██▌       | 2861/11066 [10:30<30:05,  4.54it/s]
                                                    

 26%|██▌       | 2861/11066 [10:30<30:05,  4.54it/s]
 26%|██▌       | 2862/11066 [10:30<29:47,  4.59it/s]
                                                    

 26%|██▌       | 2862/11066 [10:30<29:47,  4.59it/s]
 26%|██▌       | 2863/11066 [10:31<29:34,  4.62it/s]
                                                    

 26%|██▌       | 2863/11066 [10:31<29:34,  4.62it/s]
 26%|██▌       | 2864/11066 [10:31<29:36,  4.62it/s]
                                                    

 26%|██▌       | 2864/11066 [10:31<29:36,  4.62it/s]
 26%|██▌       | 2865/11066 [10:31<29:25,  4.65it/s]
                                                    

 26%|██▌       | 2865/11066 [10:31<29:25,  4.65it/s]
 26%|██▌       | 2866/11066 [10:31<29:24,  4.65it/s]
                                                    

 26%|██▌       | 2866/11066 [10:31<29:24,  4.65it/s]
 26%|██▌       | 2867/11066 [10:31<29:17,  4.67it/s]
                                                    

 26%|██▌       | 2867/11066 [10:31<29:17,  4.67it/s]
 26%|██▌       | 2868/11066 [10:32<29:24,  4.65it/s]
                                                    

 26%|██▌       | 2868/11066 [10:32<29:24,  4.65it/s]
 26%|██▌       | 2869/11066 [10:32<29:08,  4.69it/s]
                                                    

 26%|██▌       | 2869/11066 [10:32<29:08,  4.69it/s]
 26%|██▌       | 2870/11066 [10:32<29:06,  4.69it/s]
                                                    

 26%|██▌       | 2870/11066 [10:32<29:06,  4.69it/s]
 26%|██▌       | 2871/11066 [10:32<29:04,  4.70it/s]
                                                    

 26%|██▌       | 2871/11066 [10:32<29:04,  4.70it/s]
 26%|██▌       | 2872/11066 [10:33<29:13,  4.67it/s]
                                                    

 26%|██▌       | 2872/11066 [10:33<29:13,  4.67it/s]
 26%|██▌       | 2873/11066 [10:33<29:11,  4.68it/s]
                                                    

 26%|██▌       | 2873/11066 [10:33<29:11,  4.68it/s]
 26%|██▌       | 2874/11066 [10:33<29:41,  4.60it/s]
                                                    

 26%|██▌       | 2874/11066 [10:33<29:41,  4.60it/s]
 26%|██▌       | 2875/11066 [10:33<29:30,  4.63it/s]
                                                    

 26%|██▌       | 2875/11066 [10:33<29:30,  4.63it/s]
 26%|██▌       | 2876/11066 [10:33<29:20,  4.65it/s]
                                                    

 26%|██▌       | 2876/11066 [10:33<29:20,  4.65it/s]
 26%|██▌       | 2877/11066 [10:34<29:14,  4.67it/s]
                                                    

 26%|██▌       | 2877/11066 [10:34<29:14,  4.67it/s]
 26%|██▌       | 2878/11066 [10:34<29:35,  4.61it/s]
                                                    

 26%|██▌       | 2878/11066 [10:34<29:35,  4.61it/s]
 26%|██▌       | 2879/11066 [10:34<29:22,  4.64it/s]
                                                    

 26%|██▌       | 2879/11066 [10:34<29:22,  4.64it/s]
 26%|██▌       | 2880/11066 [10:34<29:15,  4.66it/s]
                                                    

 26%|██▌       | 2880/11066 [10:34<29:15,  4.66it/s]
 26%|██▌       | 2881/11066 [10:34<29:09,  4.68it/s]
                                                    

 26%|██▌       | 2881/11066 [10:34<29:09,  4.68it/s]
 26%|██▌       | 2882/11066 [10:35<29:33,  4.62it/s]
                                                    

 26%|██▌       | 2882/11066 [10:35<29:33,  4.62it/s]
 26%|██▌       | 2883/11066 [10:35<29:34,  4.61it/s]
                                                    

 26%|██▌       | 2883/11066 [10:35<29:34,  4.61it/s]
 26%|██▌       | 2884/11066 [10:35<29:14,  4.66it/s]
                                                    

 26%|██▌       | 2884/11066 [10:35<29:14,  4.66it/s]
 26%|██▌       | 2885/11066 [10:35<29:12,  4.67it/s]
                                                    

 26%|██▌       | 2885/11066 [10:35<29:12,  4.67it/s]
 26%|██▌       | 2886/11066 [10:36<29:06,  4.68it/s]
                                                    

 26%|██▌       | 2886/11066 [10:36<29:06,  4.68it/s]
 26%|██▌       | 2887/11066 [10:36<29:12,  4.67it/s]
                                                    

 26%|██▌       | 2887/11066 [10:36<29:12,  4.67it/s]
 26%|██▌       | 2888/11066 [10:36<29:46,  4.58it/s]
                                                    

 26%|██▌       | 2888/11066 [10:36<29:46,  4.58it/s]
 26%|██▌       | 2889/11066 [10:36<29:58,  4.55it/s]
                                                    

 26%|██▌       | 2889/11066 [10:36<29:58,  4.55it/s]
 26%|██▌       | 2890/11066 [10:36<29:40,  4.59it/s]
                                                    

 26%|██▌       | 2890/11066 [10:36<29:40,  4.59it/s]
 26%|██▌       | 2891/11066 [10:37<29:17,  4.65it/s]
                                                    

 26%|██▌       | 2891/11066 [10:37<29:17,  4.65it/s]
 26%|██▌       | 2892/11066 [10:37<29:12,  4.66it/s]
                                                    

 26%|██▌       | 2892/11066 [10:37<29:12,  4.66it/s]
 26%|██▌       | 2893/11066 [10:37<29:06,  4.68it/s]
                                                    

 26%|██▌       | 2893/11066 [10:37<29:06,  4.68it/s]
 26%|██▌       | 2894/11066 [10:37<29:02,  4.69it/s]
                                                    

 26%|██▌       | 2894/11066 [10:37<29:02,  4.69it/s]
 26%|██▌       | 2895/11066 [10:38<29:00,  4.69it/s]
                                                    

 26%|██▌       | 2895/11066 [10:38<29:00,  4.69it/s]
 26%|██▌       | 2896/11066 [10:38<29:09,  4.67it/s]
                                                    

 26%|██▌       | 2896/11066 [10:38<29:09,  4.67it/s]
 26%|██▌       | 2897/11066 [10:38<29:00,  4.69it/s]
                                                    

 26%|██▌       | 2897/11066 [10:38<29:00,  4.69it/s]
 26%|██▌       | 2898/11066 [10:38<29:00,  4.69it/s]
                                                    

 26%|██▌       | 2898/11066 [10:38<29:00,  4.69it/s]
 26%|██▌       | 2899/11066 [10:38<28:50,  4.72it/s]
                                                    

 26%|██▌       | 2899/11066 [10:38<28:50,  4.72it/s]
 26%|██▌       | 2900/11066 [10:39<28:43,  4.74it/s]
                                                    

 26%|██▌       | 2900/11066 [10:39<28:43,  4.74it/s]
 26%|██▌       | 2901/11066 [10:39<29:15,  4.65it/s]
                                                    

 26%|██▌       | 2901/11066 [10:39<29:15,  4.65it/s]
 26%|██▌       | 2902/11066 [10:39<29:09,  4.67it/s]
                                                    

 26%|██▌       | 2902/11066 [10:39<29:09,  4.67it/s]
 26%|██▌       | 2903/11066 [10:39<29:30,  4.61it/s]
                                                    

 26%|██▌       | 2903/11066 [10:39<29:30,  4.61it/s]
 26%|██▌       | 2904/11066 [10:39<29:19,  4.64it/s]
                                                    

 26%|██▌       | 2904/11066 [10:39<29:19,  4.64it/s]
 26%|██▋       | 2905/11066 [10:40<29:09,  4.66it/s]
                                                    

 26%|██▋       | 2905/11066 [10:40<29:09,  4.66it/s]
 26%|██▋       | 2906/11066 [10:40<29:03,  4.68it/s]
                                                    

 26%|██▋       | 2906/11066 [10:40<29:03,  4.68it/s]
 26%|██▋       | 2907/11066 [10:40<28:59,  4.69it/s]
                                                    

 26%|██▋       | 2907/11066 [10:40<28:59,  4.69it/s]
 26%|██▋       | 2908/11066 [10:40<28:56,  4.70it/s]
                                                    

 26%|██▋       | 2908/11066 [10:40<28:56,  4.70it/s]
 26%|██▋       | 2909/11066 [10:40<28:55,  4.70it/s]
                                                    

 26%|██▋       | 2909/11066 [10:40<28:55,  4.70it/s]
 26%|██▋       | 2910/11066 [10:41<28:53,  4.70it/s]
                                                    

 26%|██▋       | 2910/11066 [10:41<28:53,  4.70it/s]
 26%|██▋       | 2911/11066 [10:41<29:20,  4.63it/s]
                                                    

 26%|██▋       | 2911/11066 [10:41<29:20,  4.63it/s]
 26%|██▋       | 2912/11066 [10:41<29:37,  4.59it/s]
                                                    

 26%|██▋       | 2912/11066 [10:41<29:37,  4.59it/s]
 26%|██▋       | 2913/11066 [10:41<29:46,  4.56it/s]
                                                    

 26%|██▋       | 2913/11066 [10:41<29:46,  4.56it/s]
 26%|██▋       | 2914/11066 [10:42<29:30,  4.61it/s]
                                                    

 26%|██▋       | 2914/11066 [10:42<29:30,  4.61it/s]
 26%|██▋       | 2915/11066 [10:42<29:28,  4.61it/s]
                                                    

 26%|██▋       | 2915/11066 [10:42<29:28,  4.61it/s]
 26%|██▋       | 2916/11066 [10:42<29:10,  4.66it/s]
                                                    

 26%|██▋       | 2916/11066 [10:42<29:10,  4.66it/s]
 26%|██▋       | 2917/11066 [10:42<29:17,  4.64it/s]
                                                    

 26%|██▋       | 2917/11066 [10:42<29:17,  4.64it/s]
 26%|██▋       | 2918/11066 [10:42<29:39,  4.58it/s]
                                                    

 26%|██▋       | 2918/11066 [10:42<29:39,  4.58it/s]
 26%|██▋       | 2919/11066 [10:43<29:24,  4.62it/s]
                                                    

 26%|██▋       | 2919/11066 [10:43<29:24,  4.62it/s]
 26%|██▋       | 2920/11066 [10:43<29:15,  4.64it/s]
                                                    

 26%|██▋       | 2920/11066 [10:43<29:15,  4.64it/s]
 26%|██▋       | 2921/11066 [10:43<29:06,  4.66it/s]
                                                    

 26%|██▋       | 2921/11066 [10:43<29:06,  4.66it/s]
 26%|██▋       | 2922/11066 [10:43<29:01,  4.68it/s]
                                                    

 26%|██▋       | 2922/11066 [10:43<29:01,  4.68it/s]
 26%|██▋       | 2923/11066 [10:44<28:55,  4.69it/s]
                                                    

 26%|██▋       | 2923/11066 [10:44<28:55,  4.69it/s]
 26%|██▋       | 2924/11066 [10:44<29:06,  4.66it/s]
                                                    

 26%|██▋       | 2924/11066 [10:44<29:06,  4.66it/s]
 26%|██▋       | 2925/11066 [10:44<29:29,  4.60it/s]
                                                    

 26%|██▋       | 2925/11066 [10:44<29:29,  4.60it/s]
 26%|██▋       | 2926/11066 [10:44<29:28,  4.60it/s]
                                                    

 26%|██▋       | 2926/11066 [10:44<29:28,  4.60it/s]
 26%|██▋       | 2927/11066 [10:44<29:15,  4.64it/s]
                                                    
{'loss': 1.1083, 'learning_rate': 2.2371227182360384e-05, 'epoch': 0.51}
{'loss': 0.8653, 'learning_rate': 2.2368516175673232e-05, 'epoch': 0.51}
{'loss': 1.397, 'learning_rate': 2.2365805168986084e-05, 'epoch': 0.51}
{'loss': 1.0673, 'learning_rate': 2.2363094162298932e-05, 'epoch': 0.51}
{'loss': 1.037, 'learning_rate': 2.2360383155611784e-05, 'epoch': 0.51}
{'loss': 1.0714, 'learning_rate': 2.2357672148924636e-05, 'epoch': 0.51}
{'loss': 1.2925, 'learning_rate': 2.2354961142237484e-05, 'epoch': 0.51}
{'loss': 1.4657, 'learning_rate': 2.2352250135550336e-05, 'epoch': 0.51}
{'loss': 1.3895, 'learning_rate': 2.2349539128863188e-05, 'epoch': 0.51}
{'loss': 1.5961, 'learning_rate': 2.2346828122176033e-05, 'epoch': 0.51}
{'loss': 0.9422, 'learning_rate': 2.2344117115488885e-05, 'epoch': 0.51}
{'loss': 1.045, 'learning_rate': 2.2341406108801737e-05, 'epoch': 0.51}
{'loss': 1.0587, 'learning_rate': 2.2338695102114585e-05, 'epoch': 0.51}
{'loss': 1.314, 'learning_rate': 2.2335984095427437e-05, 'epoch': 0.51}
{'loss': 0.8567, 'learning_rate': 2.2333273088740286e-05, 'epoch': 0.51}
{'loss': 1.0555, 'learning_rate': 2.2330562082053137e-05, 'epoch': 0.51}
{'loss': 1.2103, 'learning_rate': 2.232785107536599e-05, 'epoch': 0.51}
{'loss': 0.8395, 'learning_rate': 2.2325140068678834e-05, 'epoch': 0.51}
{'loss': 0.7501, 'learning_rate': 2.2322429061991686e-05, 'epoch': 0.51}
{'loss': 1.7479, 'learning_rate': 2.2319718055304538e-05, 'epoch': 0.51}
{'loss': 0.8401, 'learning_rate': 2.2317007048617386e-05, 'epoch': 0.51}
{'loss': 0.4739, 'learning_rate': 2.2314296041930238e-05, 'epoch': 0.51}
{'loss': 0.5916, 'learning_rate': 2.231158503524309e-05, 'epoch': 0.51}
{'loss': 1.0268, 'learning_rate': 2.230887402855594e-05, 'epoch': 0.51}
{'loss': 1.0316, 'learning_rate': 2.2306163021868787e-05, 'epoch': 0.51}
{'loss': 2.02, 'learning_rate': 2.2303452015181635e-05, 'epoch': 0.51}
{'loss': 1.0642, 'learning_rate': 2.2300741008494487e-05, 'epoch': 0.51}
{'loss': 1.0758, 'learning_rate': 2.229803000180734e-05, 'epoch': 0.51}
{'loss': 1.1164, 'learning_rate': 2.2295318995120187e-05, 'epoch': 0.51}
{'loss': 0.3823, 'learning_rate': 2.229260798843304e-05, 'epoch': 0.51}
{'loss': 1.7754, 'learning_rate': 2.228989698174589e-05, 'epoch': 0.51}
{'loss': 1.3162, 'learning_rate': 2.228718597505874e-05, 'epoch': 0.51}
{'loss': 0.8049, 'learning_rate': 2.2284474968371588e-05, 'epoch': 0.51}
{'loss': 1.0828, 'learning_rate': 2.228176396168444e-05, 'epoch': 0.51}
{'loss': 1.1998, 'learning_rate': 2.2279052954997288e-05, 'epoch': 0.51}
{'loss': 1.3491, 'learning_rate': 2.227634194831014e-05, 'epoch': 0.51}
{'loss': 0.7326, 'learning_rate': 2.227363094162299e-05, 'epoch': 0.52}
{'loss': 1.0348, 'learning_rate': 2.227091993493584e-05, 'epoch': 0.52}
{'loss': 1.0651, 'learning_rate': 2.2268208928248692e-05, 'epoch': 0.52}
{'loss': 1.5366, 'learning_rate': 2.226549792156154e-05, 'epoch': 0.52}
{'loss': 1.2118, 'learning_rate': 2.226278691487439e-05, 'epoch': 0.52}
{'loss': 1.2921, 'learning_rate': 2.226007590818724e-05, 'epoch': 0.52}
{'loss': 1.0864, 'learning_rate': 2.225736490150009e-05, 'epoch': 0.52}
{'loss': 1.2245, 'learning_rate': 2.225465389481294e-05, 'epoch': 0.52}
{'loss': 1.4224, 'learning_rate': 2.2251942888125793e-05, 'epoch': 0.52}
{'loss': 0.9809, 'learning_rate': 2.224923188143864e-05, 'epoch': 0.52}
{'loss': 1.9378, 'learning_rate': 2.2246520874751493e-05, 'epoch': 0.52}
{'loss': 1.1902, 'learning_rate': 2.224380986806434e-05, 'epoch': 0.52}
{'loss': 1.2968, 'learning_rate': 2.224109886137719e-05, 'epoch': 0.52}
{'loss': 0.9618, 'learning_rate': 2.2238387854690042e-05, 'epoch': 0.52}
{'loss': 1.0969, 'learning_rate': 2.223567684800289e-05, 'epoch': 0.52}
{'loss': 1.1247, 'learning_rate': 2.2232965841315742e-05, 'epoch': 0.52}
{'loss': 0.7749, 'learning_rate': 2.2230254834628594e-05, 'epoch': 0.52}
{'loss': 1.2687, 'learning_rate': 2.2227543827941442e-05, 'epoch': 0.52}
{'loss': 0.8778, 'learning_rate': 2.2224832821254294e-05, 'epoch': 0.52}
{'loss': 1.0632, 'learning_rate': 2.2222121814567146e-05, 'epoch': 0.52}
{'loss': 0.7937, 'learning_rate': 2.221941080787999e-05, 'epoch': 0.52}
{'loss': 1.2775, 'learning_rate': 2.2216699801192843e-05, 'epoch': 0.52}
{'loss': 1.7353, 'learning_rate': 2.221398879450569e-05, 'epoch': 0.52}
{'loss': 1.0878, 'learning_rate': 2.2211277787818543e-05, 'epoch': 0.52}
{'loss': 1.258, 'learning_rate': 2.2208566781131395e-05, 'epoch': 0.52}
{'loss': 1.5433, 'learning_rate': 2.2205855774444244e-05, 'epoch': 0.52}
{'loss': 0.7939, 'learning_rate': 2.2203144767757095e-05, 'epoch': 0.52}
{'loss': 0.6046, 'learning_rate': 2.2200433761069947e-05, 'epoch': 0.52}
{'loss': 1.1023, 'learning_rate': 2.2197722754382792e-05, 'epoch': 0.52}
{'loss': 1.32, 'learning_rate': 2.2195011747695644e-05, 'epoch': 0.52}
{'loss': 1.2482, 'learning_rate': 2.2192300741008496e-05, 'epoch': 0.52}
{'loss': 0.5129, 'learning_rate': 2.2189589734321344e-05, 'epoch': 0.52}
{'loss': 1.5711, 'learning_rate': 2.2186878727634196e-05, 'epoch': 0.52}
{'loss': 1.4724, 'learning_rate': 2.2184167720947045e-05, 'epoch': 0.52}
{'loss': 0.8942, 'learning_rate': 2.2181456714259896e-05, 'epoch': 0.52}
{'loss': 1.5246, 'learning_rate': 2.2178745707572748e-05, 'epoch': 0.52}
{'loss': 0.7355, 'learning_rate': 2.2176034700885593e-05, 'epoch': 0.52}
{'loss': 0.5699, 'learning_rate': 2.2173323694198445e-05, 'epoch': 0.52}
{'loss': 0.9849, 'learning_rate': 2.2170612687511297e-05, 'epoch': 0.52}
{'loss': 1.6791, 'learning_rate': 2.2167901680824145e-05, 'epoch': 0.52}
{'loss': 0.8512, 'learning_rate': 2.2165190674136997e-05, 'epoch': 0.52}
{'loss': 0.4472, 'learning_rate': 2.216247966744985e-05, 'epoch': 0.52}
{'loss': 1.3965, 'learning_rate': 2.2159768660762698e-05, 'epoch': 0.52}
{'loss': 1.684, 'learning_rate': 2.215705765407555e-05, 'epoch': 0.52}
{'loss': 0.6206, 'learning_rate': 2.2154346647388394e-05, 'epoch': 0.52}
{'loss': 0.9334, 'learning_rate': 2.2151635640701246e-05, 'epoch': 0.52}
{'loss': 0.8117, 'learning_rate': 2.2148924634014098e-05, 'epoch': 0.52}
{'loss': 1.0192, 'learning_rate': 2.2146213627326946e-05, 'epoch': 0.52}
{'loss': 1.2857, 'learning_rate': 2.21435026206398e-05, 'epoch': 0.52}
{'loss': 0.7117, 'learning_rate': 2.214079161395265e-05, 'epoch': 0.52}
{'loss': 0.8905, 'learning_rate': 2.21380806072655e-05, 'epoch': 0.52}
{'loss': 0.5292, 'learning_rate': 2.213536960057835e-05, 'epoch': 0.52}
{'loss': 1.1926, 'learning_rate': 2.21326585938912e-05, 'epoch': 0.52}
{'loss': 1.3373, 'learning_rate': 2.2129947587204047e-05, 'epoch': 0.52}
{'loss': 1.8868, 'learning_rate': 2.21272365805169e-05, 'epoch': 0.52}
{'loss': 0.9239, 'learning_rate': 2.2124525573829748e-05, 'epoch': 0.53}
{'loss': 1.1332, 'learning_rate': 2.21218145671426e-05, 'epoch': 0.53}
{'loss': 0.9563, 'learning_rate': 2.211910356045545e-05, 'epoch': 0.53}
{'loss': 1.2724, 'learning_rate': 2.21163925537683e-05, 'epoch': 0.53}
{'loss': 2.0656, 'learning_rate': 2.211368154708115e-05, 'epoch': 0.53}
{'loss': 1.0206, 'learning_rate': 2.2110970540394e-05, 'epoch': 0.53}
{'loss': 0.49, 'learning_rate': 2.210825953370685e-05, 'epoch': 0.53}
{'loss': 0.7558, 'learning_rate': 2.21055485270197e-05, 'epoch': 0.53}
{'loss': 0.8732, 'learning_rate': 2.2102837520332552e-05, 'epoch': 0.53}
{'loss': 0.9655, 'learning_rate': 2.21001265136454e-05, 'epoch': 0.53}
{'loss': 1.4663, 'learning_rate': 2.2097415506958252e-05, 'epoch': 0.53}
{'loss': 0.8722, 'learning_rate': 2.20947045002711e-05, 'epoch': 0.53}
{'loss': 0.942, 'learning_rate': 2.2091993493583953e-05, 'epoch': 0.53}
{'loss': 1.9171, 'learning_rate': 2.20892824868968e-05, 'epoch': 0.53}
{'loss': 1.7415, 'learning_rate': 2.208657148020965e-05, 'epoch': 0.53}
{'loss': 0.9103, 'learning_rate': 2.20838604735225e-05, 'epoch': 0.53}
{'loss': 1.3583, 'learning_rate': 2.2081149466835353e-05, 'epoch': 0.53}
{'loss': 1.2745, 'learning_rate': 2.20784384601482e-05, 'epoch': 0.53}
{'loss': 0.921, 'learning_rate': 2.2075727453461053e-05, 'epoch': 0.53}
{'loss': 2.0519, 'learning_rate': 2.2073016446773905e-05, 'epoch': 0.53}
{'loss': 1.2331, 'learning_rate': 2.2070305440086754e-05, 'epoch': 0.53}
{'loss': 0.8287, 'learning_rate': 2.2067594433399602e-05, 'epoch': 0.53}

 26%|██▋       | 2927/11066 [10:44<29:15,  4.64it/s]
 26%|██▋       | 2928/11066 [10:45<29:10,  4.65it/s]
                                                    

 26%|██▋       | 2928/11066 [10:45<29:10,  4.65it/s]
 26%|██▋       | 2929/11066 [10:45<29:02,  4.67it/s]
                                                    

 26%|██▋       | 2929/11066 [10:45<29:02,  4.67it/s]
 26%|██▋       | 2930/11066 [10:45<29:08,  4.65it/s]
                                                    

 26%|██▋       | 2930/11066 [10:45<29:08,  4.65it/s]
 26%|██▋       | 2931/11066 [10:45<29:29,  4.60it/s]
                                                    

 26%|██▋       | 2931/11066 [10:45<29:29,  4.60it/s]
 26%|██▋       | 2932/11066 [10:45<29:50,  4.54it/s]
                                                    

 26%|██▋       | 2932/11066 [10:45<29:50,  4.54it/s]
 27%|██▋       | 2933/11066 [10:46<30:24,  4.46it/s]
                                                    

 27%|██▋       | 2933/11066 [10:46<30:24,  4.46it/s]
 27%|██▋       | 2934/11066 [10:46<30:54,  4.38it/s]
                                                    

 27%|██▋       | 2934/11066 [10:46<30:54,  4.38it/s]
 27%|██▋       | 2935/11066 [10:46<31:15,  4.34it/s]
                                                    

 27%|██▋       | 2935/11066 [10:46<31:15,  4.34it/s]
 27%|██▋       | 2936/11066 [10:46<30:58,  4.37it/s]
                                                    

 27%|██▋       | 2936/11066 [10:46<30:58,  4.37it/s]
 27%|██▋       | 2937/11066 [10:47<30:44,  4.41it/s]
                                                    

 27%|██▋       | 2937/11066 [10:47<30:44,  4.41it/s]
 27%|██▋       | 2938/11066 [10:47<30:12,  4.49it/s]
                                                    

 27%|██▋       | 2938/11066 [10:47<30:12,  4.49it/s]
 27%|██▋       | 2939/11066 [10:47<29:45,  4.55it/s]
                                                    

 27%|██▋       | 2939/11066 [10:47<29:45,  4.55it/s]
 27%|██▋       | 2940/11066 [10:47<29:28,  4.60it/s]
                                                    

 27%|██▋       | 2940/11066 [10:47<29:28,  4.60it/s]
 27%|██▋       | 2941/11066 [10:47<29:14,  4.63it/s]
                                                    

 27%|██▋       | 2941/11066 [10:47<29:14,  4.63it/s]
 27%|██▋       | 2942/11066 [10:48<29:04,  4.66it/s]
                                                    

 27%|██▋       | 2942/11066 [10:48<29:04,  4.66it/s]
 27%|██▋       | 2943/11066 [10:48<28:58,  4.67it/s]
                                                    

 27%|██▋       | 2943/11066 [10:48<28:58,  4.67it/s]
 27%|██▋       | 2944/11066 [10:48<28:53,  4.69it/s]
                                                    

 27%|██▋       | 2944/11066 [10:48<28:53,  4.69it/s]
 27%|██▋       | 2945/11066 [10:48<29:17,  4.62it/s]
                                                    

 27%|██▋       | 2945/11066 [10:48<29:17,  4.62it/s]
 27%|██▋       | 2946/11066 [10:49<29:32,  4.58it/s]
                                                    

 27%|██▋       | 2946/11066 [10:49<29:32,  4.58it/s]
 27%|██▋       | 2947/11066 [10:49<29:42,  4.55it/s]
                                                    

 27%|██▋       | 2947/11066 [10:49<29:42,  4.55it/s]
 27%|██▋       | 2948/11066 [10:49<29:48,  4.54it/s]
                                                    

 27%|██▋       | 2948/11066 [10:49<29:48,  4.54it/s]
 27%|██▋       | 2949/11066 [10:49<29:53,  4.53it/s]
                                                    

 27%|██▋       | 2949/11066 [10:49<29:53,  4.53it/s]
 27%|██▋       | 2950/11066 [10:49<29:42,  4.55it/s]
                                                    

 27%|██▋       | 2950/11066 [10:49<29:42,  4.55it/s]
 27%|██▋       | 2951/11066 [10:50<29:41,  4.55it/s]
                                                    

 27%|██▋       | 2951/11066 [10:50<29:41,  4.55it/s]
 27%|██▋       | 2952/11066 [10:50<29:32,  4.58it/s]
                                                    

 27%|██▋       | 2952/11066 [10:50<29:32,  4.58it/s]
 27%|██▋       | 2953/11066 [10:50<29:43,  4.55it/s]
                                                    

 27%|██▋       | 2953/11066 [10:50<29:43,  4.55it/s]
 27%|██▋       | 2954/11066 [10:50<29:57,  4.51it/s]
                                                    

 27%|██▋       | 2954/11066 [10:50<29:57,  4.51it/s]
 27%|██▋       | 2955/11066 [10:51<30:02,  4.50it/s]
                                                    

 27%|██▋       | 2955/11066 [10:51<30:02,  4.50it/s]
 27%|██▋       | 2956/11066 [10:51<30:03,  4.50it/s]
                                                    

 27%|██▋       | 2956/11066 [10:51<30:03,  4.50it/s]
 27%|██▋       | 2957/11066 [10:51<30:02,  4.50it/s]
                                                    

 27%|██▋       | 2957/11066 [10:51<30:02,  4.50it/s]
 27%|██▋       | 2958/11066 [10:51<30:04,  4.49it/s]
                                                    

 27%|██▋       | 2958/11066 [10:51<30:04,  4.49it/s]
 27%|██▋       | 2959/11066 [10:51<30:12,  4.47it/s]
                                                    

 27%|██▋       | 2959/11066 [10:51<30:12,  4.47it/s]
 27%|██▋       | 2960/11066 [10:52<29:44,  4.54it/s]
                                                    

 27%|██▋       | 2960/11066 [10:52<29:44,  4.54it/s]
 27%|██▋       | 2961/11066 [10:52<29:48,  4.53it/s]
                                                    

 27%|██▋       | 2961/11066 [10:52<29:48,  4.53it/s]
 27%|██▋       | 2962/11066 [10:52<29:26,  4.59it/s]
                                                    

 27%|██▋       | 2962/11066 [10:52<29:26,  4.59it/s]
 27%|██▋       | 2963/11066 [10:52<29:11,  4.63it/s]
                                                    

 27%|██▋       | 2963/11066 [10:52<29:11,  4.63it/s]
 27%|██▋       | 2964/11066 [10:53<29:13,  4.62it/s]
                                                    

 27%|██▋       | 2964/11066 [10:53<29:13,  4.62it/s]
 27%|██▋       | 2965/11066 [10:53<28:56,  4.67it/s]
                                                    

 27%|██▋       | 2965/11066 [10:53<28:56,  4.67it/s]
 27%|██▋       | 2966/11066 [10:53<28:51,  4.68it/s]
                                                    

 27%|██▋       | 2966/11066 [10:53<28:51,  4.68it/s]
 27%|██▋       | 2967/11066 [10:53<29:10,  4.63it/s]
                                                    

 27%|██▋       | 2967/11066 [10:53<29:10,  4.63it/s]
 27%|██▋       | 2968/11066 [10:53<29:11,  4.62it/s]
                                                    

 27%|██▋       | 2968/11066 [10:53<29:11,  4.62it/s]
 27%|██▋       | 2969/11066 [10:54<28:58,  4.66it/s]
                                                    

 27%|██▋       | 2969/11066 [10:54<28:58,  4.66it/s]
 27%|██▋       | 2970/11066 [10:54<29:21,  4.60it/s]
                                                    

 27%|██▋       | 2970/11066 [10:54<29:21,  4.60it/s]
 27%|██▋       | 2971/11066 [10:54<29:23,  4.59it/s]
                                                    

 27%|██▋       | 2971/11066 [10:54<29:23,  4.59it/s]
 27%|██▋       | 2972/11066 [10:54<29:18,  4.60it/s]
                                                    

 27%|██▋       | 2972/11066 [10:54<29:18,  4.60it/s]
 27%|██▋       | 2973/11066 [10:54<29:32,  4.57it/s]
                                                    

 27%|██▋       | 2973/11066 [10:54<29:32,  4.57it/s]
 27%|██▋       | 2974/11066 [10:55<29:49,  4.52it/s]
                                                    

 27%|██▋       | 2974/11066 [10:55<29:49,  4.52it/s]
 27%|██▋       | 2975/11066 [10:55<29:55,  4.51it/s]
                                                    

 27%|██▋       | 2975/11066 [10:55<29:55,  4.51it/s]
 27%|██▋       | 2976/11066 [10:55<29:44,  4.53it/s]
                                                    

 27%|██▋       | 2976/11066 [10:55<29:44,  4.53it/s]
 27%|██▋       | 2977/11066 [10:55<29:37,  4.55it/s]
                                                    

 27%|██▋       | 2977/11066 [10:55<29:37,  4.55it/s]
 27%|██▋       | 2978/11066 [10:56<29:29,  4.57it/s]
                                                    

 27%|██▋       | 2978/11066 [10:56<29:29,  4.57it/s]
 27%|██▋       | 2979/11066 [10:56<29:31,  4.57it/s]
                                                    

 27%|██▋       | 2979/11066 [10:56<29:31,  4.57it/s]
 27%|██▋       | 2980/11066 [10:56<29:13,  4.61it/s]
                                                    

 27%|██▋       | 2980/11066 [10:56<29:13,  4.61it/s]
 27%|██▋       | 2981/11066 [10:56<29:01,  4.64it/s]
                                                    

 27%|██▋       | 2981/11066 [10:56<29:01,  4.64it/s]
 27%|██▋       | 2982/11066 [10:56<29:03,  4.64it/s]
                                                    

 27%|██▋       | 2982/11066 [10:56<29:03,  4.64it/s]
 27%|██▋       | 2983/11066 [10:57<28:49,  4.67it/s]
                                                    

 27%|██▋       | 2983/11066 [10:57<28:49,  4.67it/s]
 27%|██▋       | 2984/11066 [10:57<29:06,  4.63it/s]
                                                    

 27%|██▋       | 2984/11066 [10:57<29:06,  4.63it/s]
 27%|██▋       | 2985/11066 [10:57<28:55,  4.66it/s]
                                                    

 27%|██▋       | 2985/11066 [10:57<28:55,  4.66it/s]
 27%|██▋       | 2986/11066 [10:57<29:00,  4.64it/s]
                                                    

 27%|██▋       | 2986/11066 [10:57<29:00,  4.64it/s]
 27%|██▋       | 2987/11066 [10:58<29:29,  4.56it/s]
                                                    

 27%|██▋       | 2987/11066 [10:58<29:29,  4.56it/s]
 27%|██▋       | 2988/11066 [10:58<29:39,  4.54it/s]
                                                    

 27%|██▋       | 2988/11066 [10:58<29:39,  4.54it/s]
 27%|██▋       | 2989/11066 [10:58<29:44,  4.53it/s]
                                                    

 27%|██▋       | 2989/11066 [10:58<29:44,  4.53it/s]
 27%|██▋       | 2990/11066 [10:58<30:00,  4.49it/s]
                                                    

 27%|██▋       | 2990/11066 [10:58<30:00,  4.49it/s]
 27%|██▋       | 2991/11066 [10:58<30:04,  4.48it/s]
                                                    

 27%|██▋       | 2991/11066 [10:58<30:04,  4.48it/s]
 27%|██▋       | 2992/11066 [10:59<30:02,  4.48it/s]
                                                    

 27%|██▋       | 2992/11066 [10:59<30:02,  4.48it/s]
 27%|██▋       | 2993/11066 [10:59<30:03,  4.48it/s]
                                                    

 27%|██▋       | 2993/11066 [10:59<30:03,  4.48it/s]
 27%|██▋       | 2994/11066 [10:59<29:34,  4.55it/s]
                                                    

 27%|██▋       | 2994/11066 [10:59<29:34,  4.55it/s]
 27%|██▋       | 2995/11066 [10:59<29:28,  4.56it/s]
                                                    

 27%|██▋       | 2995/11066 [10:59<29:28,  4.56it/s]
 27%|██▋       | 2996/11066 [11:00<29:14,  4.60it/s]
                                                    

 27%|██▋       | 2996/11066 [11:00<29:14,  4.60it/s]
 27%|██▋       | 2997/11066 [11:00<28:53,  4.65it/s]
                                                    

 27%|██▋       | 2997/11066 [11:00<28:53,  4.65it/s]
 27%|██▋       | 2998/11066 [11:00<28:58,  4.64it/s]
                                                    

 27%|██▋       | 2998/11066 [11:00<28:58,  4.64it/s]
 27%|██▋       | 2999/11066 [11:00<28:48,  4.67it/s]
                                                    

 27%|██▋       | 2999/11066 [11:00<28:48,  4.67it/s]
 27%|██▋       | 3000/11066 [11:00<29:06,  4.62it/s]
                                                    

 27%|██▋       | 3000/11066 [11:00<29:06,  4.62it/s]
 27%|██▋       | 3001/11066 [11:01<29:01,  4.63it/s]
                                                    

 27%|██▋       | 3001/11066 [11:01<29:01,  4.63it/s]
 27%|██▋       | 3002/11066 [11:01<28:56,  4.64it/s]
                                                    

 27%|██▋       | 3002/11066 [11:01<28:56,  4.64it/s]
 27%|██▋       | 3003/11066 [11:01<29:17,  4.59it/s]
                                                    

 27%|██▋       | 3003/11066 [11:01<29:17,  4.59it/s]
 27%|██▋       | 3004/11066 [11:01<29:17,  4.59it/s]
                                                    

 27%|██▋       | 3004/11066 [11:01<29:17,  4.59it/s]
 27%|██▋       | 3005/11066 [11:01<29:10,  4.61it/s]
                                                    

 27%|██▋       | 3005/11066 [11:01<29:10,  4.61it/s]
 27%|██▋       | 3006/11066 [11:02<29:26,  4.56it/s]
                                                    

 27%|██▋       | 3006/11066 [11:02<29:26,  4.56it/s]
 27%|██▋       | 3007/11066 [11:02<29:09,  4.61it/s]
                                                    

 27%|██▋       | 3007/11066 [11:02<29:09,  4.61it/s]
 27%|██▋       | 3008/11066 [11:02<28:56,  4.64it/s]
                                                    

 27%|██▋       | 3008/11066 [11:02<28:56,  4.64it/s]
 27%|██▋       | 3009/11066 [11:02<28:47,  4.66it/s]
                                                    

 27%|██▋       | 3009/11066 [11:02<28:47,  4.66it/s]
 27%|██▋       | 3010/11066 [11:03<28:54,  4.64it/s]
                                                    

 27%|██▋       | 3010/11066 [11:03<28:54,  4.64it/s]
 27%|██▋       | 3011/11066 [11:03<29:01,  4.63it/s]
                                                    

 27%|██▋       | 3011/11066 [11:03<29:01,  4.63it/s]
 27%|██▋       | 3012/11066 [11:03<29:02,  4.62it/s]
                                                    

 27%|██▋       | 3012/11066 [11:03<29:02,  4.62it/s]
 27%|██▋       | 3013/11066 [11:03<28:43,  4.67it/s]
                                                    

 27%|██▋       | 3013/11066 [11:03<28:43,  4.67it/s]
 27%|██▋       | 3014/11066 [11:03<28:38,  4.69it/s]
                                                    

 27%|██▋       | 3014/11066 [11:03<28:38,  4.69it/s]
 27%|██▋       | 3015/11066 [11:04<28:35,  4.69it/s]
                                                    

 27%|██▋       | 3015/11066 [11:04<28:35,  4.69it/s]
 27%|██▋       | 3016/11066 [11:04<28:59,  4.63it/s]
                                                    

 27%|██▋       | 3016/11066 [11:04<28:59,  4.63it/s]
 27%|██▋       | 3017/11066 [11:04<29:13,  4.59it/s]
                                                    

 27%|██▋       | 3017/11066 [11:04<29:13,  4.59it/s]
 27%|██▋       | 3018/11066 [11:04<28:58,  4.63it/s]
                                                    

 27%|██▋       | 3018/11066 [11:04<28:58,  4.63it/s]
 27%|██▋       | 3019/11066 [11:04<29:12,  4.59it/s]
                                                    

 27%|██▋       | 3019/11066 [11:04<29:12,  4.59it/s]
 27%|██▋       | 3020/11066 [11:05<29:09,  4.60it/s]
                                                    

 27%|██▋       | 3020/11066 [11:05<29:09,  4.60it/s]
 27%|██▋       | 3021/11066 [11:05<28:48,  4.65it/s]
                                                    

 27%|██▋       | 3021/11066 [11:05<28:48,  4.65it/s]
 27%|██▋       | 3022/11066 [11:05<29:06,  4.61it/s]
                                                    

 27%|██▋       | 3022/11066 [11:05<29:06,  4.61it/s]
 27%|██▋       | 3023/11066 [11:05<28:54,  4.64it/s]
                                                    

 27%|██▋       | 3023/11066 [11:05<28:54,  4.64it/s]
 27%|██▋       | 3024/11066 [11:06<28:55,  4.64it/s]
                                                    

 27%|██▋       | 3024/11066 [11:06<28:55,  4.64it/s]
 27%|██▋       | 3025/11066 [11:06<28:42,  4.67it/s]
                                                    

 27%|██▋       | 3025/11066 [11:06<28:42,  4.67it/s]
 27%|██▋       | 3026/11066 [11:06<28:28,  4.71it/s]
                                                    

 27%|██▋       | 3026/11066 [11:06<28:28,  4.71it/s]
 27%|██▋       | 3027/11066 [11:06<28:21,  4.73it/s]
                                                    

 27%|██▋       | 3027/11066 [11:06<28:21,  4.73it/s]
 27%|██▋       | 3028/11066 [11:06<28:50,  4.64it/s]
                                                    

 27%|██▋       | 3028/11066 [11:06<28:50,  4.64it/s]
 27%|██▋       | 3029/11066 [11:07<29:06,  4.60it/s]
                                                    

 27%|██▋       | 3029/11066 [11:07<29:06,  4.60it/s]
 27%|██▋       | 3030/11066 [11:07<29:20,  4.57it/s]
                                                    

 27%|██▋       | 3030/11066 [11:07<29:20,  4.57it/s]
 27%|██▋       | 3031/11066 [11:07<29:28,  4.54it/s]
                                                    

 27%|██▋       | 3031/11066 [11:07<29:28,  4.54it/s]
 27%|██▋       | 3032/11066 [11:07<29:19,  4.57it/s]
                                                    

 27%|██▋       | 3032/11066 [11:07<29:19,  4.57it/s]
 27%|██▋       | 3033/11066 [11:08<29:04,  4.60it/s]
                                                    

 27%|██▋       | 3033/11066 [11:08<29:04,  4.60it/s]
 27%|██▋       | 3034/11066 [11:08<28:46,  4.65it/s]
                                                    

 27%|██▋       | 3034/11066 [11:08<28:46,  4.65it/s]
 27%|██▋       | 3035/11066 [11:08<29:02,  4.61it/s]
                                                    

 27%|██▋       | 3035/11066 [11:08<29:02,  4.61it/s]
 27%|██▋       | 3036/11066 [11:08<28:49,  4.64it/s]
                                                    

 27%|██▋       | 3036/11066 [11:08<28:49,  4.64it/s]
 27%|██▋       | 3037/11066 [11:08<28:31,  4.69it/s]
                                                    

 27%|██▋       | 3037/11066 [11:08<28:31,  4.69it/s]
 27%|██▋       | 3038/11066 [11:09<28:58,  4.62it/s]
                                                    

 27%|██▋       | 3038/11066 [11:09<28:58,  4.62it/s]
 27%|██▋       | 3039/11066 [11:09<29:07,  4.59it/s]
                                                    
{'loss': 2.0217, 'learning_rate': 2.206488342671245e-05, 'epoch': 0.53}
{'loss': 1.1362, 'learning_rate': 2.2062172420025302e-05, 'epoch': 0.53}
{'loss': 1.2753, 'learning_rate': 2.2059461413338154e-05, 'epoch': 0.53}
{'loss': 0.706, 'learning_rate': 2.2056750406651003e-05, 'epoch': 0.53}
{'loss': 1.299, 'learning_rate': 2.2054039399963854e-05, 'epoch': 0.53}
{'loss': 1.2175, 'learning_rate': 2.2051328393276706e-05, 'epoch': 0.53}
{'loss': 0.7148, 'learning_rate': 2.2048617386589555e-05, 'epoch': 0.53}
{'loss': 0.7652, 'learning_rate': 2.2045906379902403e-05, 'epoch': 0.53}
{'loss': 1.0376, 'learning_rate': 2.2043195373215255e-05, 'epoch': 0.53}
{'loss': 1.1558, 'learning_rate': 2.2040484366528103e-05, 'epoch': 0.53}
{'loss': 1.3665, 'learning_rate': 2.2037773359840955e-05, 'epoch': 0.53}
{'loss': 0.8624, 'learning_rate': 2.2035062353153804e-05, 'epoch': 0.53}
{'loss': 0.8083, 'learning_rate': 2.2032351346466656e-05, 'epoch': 0.53}
{'loss': 1.4162, 'learning_rate': 2.2029640339779507e-05, 'epoch': 0.53}
{'loss': 1.4274, 'learning_rate': 2.2026929333092356e-05, 'epoch': 0.53}
{'loss': 0.7836, 'learning_rate': 2.2024218326405204e-05, 'epoch': 0.53}
{'loss': 0.5605, 'learning_rate': 2.2021507319718056e-05, 'epoch': 0.53}
{'loss': 1.0585, 'learning_rate': 2.2018796313030904e-05, 'epoch': 0.53}
{'loss': 1.1949, 'learning_rate': 2.2016085306343756e-05, 'epoch': 0.53}
{'loss': 0.6535, 'learning_rate': 2.2013374299656608e-05, 'epoch': 0.53}
{'loss': 0.6094, 'learning_rate': 2.2010663292969457e-05, 'epoch': 0.53}
{'loss': 1.0031, 'learning_rate': 2.200795228628231e-05, 'epoch': 0.53}
{'loss': 1.9643, 'learning_rate': 2.2005241279595157e-05, 'epoch': 0.53}
{'loss': 1.1095, 'learning_rate': 2.2002530272908005e-05, 'epoch': 0.53}
{'loss': 0.7009, 'learning_rate': 2.1999819266220857e-05, 'epoch': 0.53}
{'loss': 1.3671, 'learning_rate': 2.1997108259533706e-05, 'epoch': 0.53}
{'loss': 0.7613, 'learning_rate': 2.1994397252846557e-05, 'epoch': 0.53}
{'loss': 1.1691, 'learning_rate': 2.199168624615941e-05, 'epoch': 0.53}
{'loss': 1.2319, 'learning_rate': 2.1988975239472258e-05, 'epoch': 0.53}
{'loss': 0.9527, 'learning_rate': 2.198626423278511e-05, 'epoch': 0.53}
{'loss': 1.3602, 'learning_rate': 2.198355322609796e-05, 'epoch': 0.53}
{'loss': 1.7027, 'learning_rate': 2.1980842219410806e-05, 'epoch': 0.53}
{'loss': 1.0628, 'learning_rate': 2.1978131212723658e-05, 'epoch': 0.53}
{'loss': 1.2119, 'learning_rate': 2.197542020603651e-05, 'epoch': 0.53}
{'loss': 1.4021, 'learning_rate': 2.197270919934936e-05, 'epoch': 0.54}
{'loss': 0.792, 'learning_rate': 2.196999819266221e-05, 'epoch': 0.54}
{'loss': 1.1217, 'learning_rate': 2.196728718597506e-05, 'epoch': 0.54}
{'loss': 1.0014, 'learning_rate': 2.196457617928791e-05, 'epoch': 0.54}
{'loss': 1.2547, 'learning_rate': 2.196186517260076e-05, 'epoch': 0.54}
{'loss': 0.8004, 'learning_rate': 2.1959154165913607e-05, 'epoch': 0.54}
{'loss': 0.8958, 'learning_rate': 2.195644315922646e-05, 'epoch': 0.54}
{'loss': 1.0376, 'learning_rate': 2.195373215253931e-05, 'epoch': 0.54}
{'loss': 1.6509, 'learning_rate': 2.195102114585216e-05, 'epoch': 0.54}
{'loss': 0.5054, 'learning_rate': 2.194831013916501e-05, 'epoch': 0.54}
{'loss': 1.2597, 'learning_rate': 2.1945599132477863e-05, 'epoch': 0.54}
{'loss': 0.9387, 'learning_rate': 2.194288812579071e-05, 'epoch': 0.54}
{'loss': 1.0279, 'learning_rate': 2.194017711910356e-05, 'epoch': 0.54}
{'loss': 1.2189, 'learning_rate': 2.193746611241641e-05, 'epoch': 0.54}
{'loss': 1.4721, 'learning_rate': 2.193475510572926e-05, 'epoch': 0.54}
{'loss': 1.2638, 'learning_rate': 2.1932044099042112e-05, 'epoch': 0.54}
{'loss': 1.0106, 'learning_rate': 2.192933309235496e-05, 'epoch': 0.54}
{'loss': 1.5666, 'learning_rate': 2.1926622085667812e-05, 'epoch': 0.54}
{'loss': 0.709, 'learning_rate': 2.1923911078980664e-05, 'epoch': 0.54}
{'loss': 1.0123, 'learning_rate': 2.1921200072293513e-05, 'epoch': 0.54}
{'loss': 1.4001, 'learning_rate': 2.191848906560636e-05, 'epoch': 0.54}
{'loss': 1.5693, 'learning_rate': 2.1915778058919213e-05, 'epoch': 0.54}
{'loss': 1.5753, 'learning_rate': 2.191306705223206e-05, 'epoch': 0.54}
{'loss': 2.1441, 'learning_rate': 2.1910356045544913e-05, 'epoch': 0.54}
{'loss': 1.3234, 'learning_rate': 2.190764503885776e-05, 'epoch': 0.54}
{'loss': 1.3043, 'learning_rate': 2.1904934032170614e-05, 'epoch': 0.54}
{'loss': 0.7331, 'learning_rate': 2.1902223025483465e-05, 'epoch': 0.54}
{'loss': 1.3138, 'learning_rate': 2.1899512018796314e-05, 'epoch': 0.54}
{'loss': 0.6274, 'learning_rate': 2.1896801012109162e-05, 'epoch': 0.54}
{'loss': 0.716, 'learning_rate': 2.1894090005422014e-05, 'epoch': 0.54}
{'loss': 0.913, 'learning_rate': 2.1891378998734862e-05, 'epoch': 0.54}
{'loss': 0.8352, 'learning_rate': 2.1888667992047714e-05, 'epoch': 0.54}
{'loss': 0.7715, 'learning_rate': 2.1885956985360566e-05, 'epoch': 0.54}
{'loss': 1.582, 'learning_rate': 2.1883245978673415e-05, 'epoch': 0.54}
{'loss': 1.2387, 'learning_rate': 2.1880534971986266e-05, 'epoch': 0.54}
{'loss': 1.5785, 'learning_rate': 2.1877823965299115e-05, 'epoch': 0.54}
{'loss': 0.7255, 'learning_rate': 2.1875112958611963e-05, 'epoch': 0.54}
{'loss': 1.8531, 'learning_rate': 2.1872401951924815e-05, 'epoch': 0.54}
{'loss': 0.9536, 'learning_rate': 2.1869690945237664e-05, 'epoch': 0.54}
{'loss': 1.9245, 'learning_rate': 2.1866979938550515e-05, 'epoch': 0.54}
{'loss': 1.7439, 'learning_rate': 2.1864268931863367e-05, 'epoch': 0.54}
{'loss': 0.9687, 'learning_rate': 2.1861557925176216e-05, 'epoch': 0.54}
{'loss': 0.6568, 'learning_rate': 2.1858846918489067e-05, 'epoch': 0.54}
{'loss': 1.4576, 'learning_rate': 2.185613591180192e-05, 'epoch': 0.54}
{'loss': 1.1933, 'learning_rate': 2.1853424905114764e-05, 'epoch': 0.54}
{'loss': 1.1139, 'learning_rate': 2.1850713898427616e-05, 'epoch': 0.54}
{'loss': 1.6975, 'learning_rate': 2.1848002891740465e-05, 'epoch': 0.54}
{'loss': 0.8295, 'learning_rate': 2.1845291885053316e-05, 'epoch': 0.54}
{'loss': 1.2251, 'learning_rate': 2.1842580878366168e-05, 'epoch': 0.54}
{'loss': 1.1892, 'learning_rate': 2.1839869871679017e-05, 'epoch': 0.54}
{'loss': 1.6769, 'learning_rate': 2.183715886499187e-05, 'epoch': 0.54}
{'loss': 1.3387, 'learning_rate': 2.183444785830472e-05, 'epoch': 0.54}
{'loss': 1.1882, 'learning_rate': 2.1831736851617565e-05, 'epoch': 0.54}
{'loss': 0.8529, 'learning_rate': 2.1829025844930417e-05, 'epoch': 0.54}
{'loss': 0.4764, 'learning_rate': 2.182631483824327e-05, 'epoch': 0.54}
{'loss': 1.1067, 'learning_rate': 2.1823603831556118e-05, 'epoch': 0.55}
{'loss': 0.8623, 'learning_rate': 2.182089282486897e-05, 'epoch': 0.55}
{'loss': 1.6177, 'learning_rate': 2.1818181818181818e-05, 'epoch': 0.55}
{'loss': 1.4498, 'learning_rate': 2.181547081149467e-05, 'epoch': 0.55}
{'loss': 1.397, 'learning_rate': 2.181275980480752e-05, 'epoch': 0.55}
{'loss': 1.1543, 'learning_rate': 2.1810048798120367e-05, 'epoch': 0.55}
{'loss': 0.7869, 'learning_rate': 2.180733779143322e-05, 'epoch': 0.55}
{'loss': 0.9198, 'learning_rate': 2.180462678474607e-05, 'epoch': 0.55}
{'loss': 1.2333, 'learning_rate': 2.180191577805892e-05, 'epoch': 0.55}
{'loss': 1.1389, 'learning_rate': 2.179920477137177e-05, 'epoch': 0.55}
{'loss': 0.5293, 'learning_rate': 2.1796493764684622e-05, 'epoch': 0.55}
{'loss': 1.0109, 'learning_rate': 2.179378275799747e-05, 'epoch': 0.55}
{'loss': 0.816, 'learning_rate': 2.1791071751310323e-05, 'epoch': 0.55}
{'loss': 1.187, 'learning_rate': 2.1788360744623168e-05, 'epoch': 0.55}
{'loss': 1.4009, 'learning_rate': 2.178564973793602e-05, 'epoch': 0.55}
{'loss': 0.751, 'learning_rate': 2.178293873124887e-05, 'epoch': 0.55}
{'loss': 0.989, 'learning_rate': 2.178022772456172e-05, 'epoch': 0.55}
{'loss': 1.5859, 'learning_rate': 2.177751671787457e-05, 'epoch': 0.55}
{'loss': 1.178, 'learning_rate': 2.1774805711187423e-05, 'epoch': 0.55}
{'loss': 0.8491, 'learning_rate': 2.1772094704500272e-05, 'epoch': 0.55}
{'loss': 1.2169, 'learning_rate': 2.1769383697813124e-05, 'epoch': 0.55}
{'loss': 1.0945, 'learning_rate': 2.1766672691125972e-05, 'epoch': 0.55}
{'loss': 1.6336, 'learning_rate': 2.176396168443882e-05, 'epoch': 0.55}

 27%|██▋       | 3039/11066 [11:09<29:07,  4.59it/s]
 27%|██▋       | 3040/11066 [11:09<29:26,  4.54it/s]
                                                    

 27%|██▋       | 3040/11066 [11:09<29:26,  4.54it/s]
 27%|██▋       | 3041/11066 [11:09<29:55,  4.47it/s]
                                                    

 27%|██▋       | 3041/11066 [11:09<29:55,  4.47it/s]
 27%|██▋       | 3042/11066 [11:09<29:51,  4.48it/s]
                                                    

 27%|██▋       | 3042/11066 [11:09<29:51,  4.48it/s]
 27%|██▋       | 3043/11066 [11:10<29:48,  4.49it/s]
                                                    

 27%|██▋       | 3043/11066 [11:10<29:48,  4.49it/s]
 28%|██▊       | 3044/11066 [11:10<29:45,  4.49it/s]
                                                    

 28%|██▊       | 3044/11066 [11:10<29:45,  4.49it/s]
 28%|██▊       | 3045/11066 [11:10<29:45,  4.49it/s]
                                                    

 28%|██▊       | 3045/11066 [11:10<29:45,  4.49it/s]
 28%|██▊       | 3046/11066 [11:10<29:31,  4.53it/s]
                                                    

 28%|██▊       | 3046/11066 [11:10<29:31,  4.53it/s]
 28%|██▊       | 3047/11066 [11:11<29:17,  4.56it/s]
                                                    

 28%|██▊       | 3047/11066 [11:11<29:17,  4.56it/s]
 28%|██▊       | 3048/11066 [11:11<29:28,  4.53it/s]
                                                    

 28%|██▊       | 3048/11066 [11:11<29:28,  4.53it/s]
 28%|██▊       | 3049/11066 [11:11<29:09,  4.58it/s]
                                                    

 28%|██▊       | 3049/11066 [11:11<29:09,  4.58it/s]
 28%|██▊       | 3050/11066 [11:11<29:03,  4.60it/s]
                                                    

 28%|██▊       | 3050/11066 [11:11<29:03,  4.60it/s]
 28%|██▊       | 3051/11066 [11:11<29:07,  4.59it/s]
                                                    

 28%|██▊       | 3051/11066 [11:11<29:07,  4.59it/s]
 28%|██▊       | 3052/11066 [11:12<29:05,  4.59it/s]
                                                    

 28%|██▊       | 3052/11066 [11:12<29:05,  4.59it/s]
 28%|██▊       | 3053/11066 [11:12<29:20,  4.55it/s]
                                                    

 28%|██▊       | 3053/11066 [11:12<29:20,  4.55it/s]
 28%|██▊       | 3054/11066 [11:12<29:03,  4.60it/s]
                                                    

 28%|██▊       | 3054/11066 [11:12<29:03,  4.60it/s]
 28%|██▊       | 3055/11066 [11:12<28:51,  4.63it/s]
                                                    

 28%|██▊       | 3055/11066 [11:12<28:51,  4.63it/s]
 28%|██▊       | 3056/11066 [11:13<28:52,  4.62it/s]
                                                    

 28%|██▊       | 3056/11066 [11:13<28:52,  4.62it/s]
 28%|██▊       | 3057/11066 [11:13<29:00,  4.60it/s]
                                                    

 28%|██▊       | 3057/11066 [11:13<29:00,  4.60it/s]
 28%|██▊       | 3058/11066 [11:13<28:49,  4.63it/s]
                                                    

 28%|██▊       | 3058/11066 [11:13<28:49,  4.63it/s]
 28%|██▊       | 3059/11066 [11:13<29:11,  4.57it/s]
                                                    

 28%|██▊       | 3059/11066 [11:13<29:11,  4.57it/s]
 28%|██▊       | 3060/11066 [11:13<29:23,  4.54it/s]
                                                    

 28%|██▊       | 3060/11066 [11:13<29:23,  4.54it/s]
 28%|██▊       | 3061/11066 [11:14<29:18,  4.55it/s]
                                                    

 28%|██▊       | 3061/11066 [11:14<29:18,  4.55it/s]
 28%|██▊       | 3062/11066 [11:14<29:26,  4.53it/s]
                                                    

 28%|██▊       | 3062/11066 [11:14<29:26,  4.53it/s]
 28%|██▊       | 3063/11066 [11:14<29:01,  4.60it/s]
                                                    

 28%|██▊       | 3063/11066 [11:14<29:01,  4.60it/s]
 28%|██▊       | 3064/11066 [11:14<28:58,  4.60it/s]
                                                    

 28%|██▊       | 3064/11066 [11:14<28:58,  4.60it/s]
 28%|██▊       | 3065/11066 [11:15<28:59,  4.60it/s]
                                                    

 28%|██▊       | 3065/11066 [11:15<28:59,  4.60it/s]
 28%|██▊       | 3066/11066 [11:15<29:14,  4.56it/s]
                                                    

 28%|██▊       | 3066/11066 [11:15<29:14,  4.56it/s]
 28%|██▊       | 3067/11066 [11:15<29:01,  4.59it/s]
                                                    

 28%|██▊       | 3067/11066 [11:15<29:01,  4.59it/s]
 28%|██▊       | 3068/11066 [11:15<28:44,  4.64it/s]
                                                    

 28%|██▊       | 3068/11066 [11:15<28:44,  4.64it/s]
 28%|██▊       | 3069/11066 [11:15<28:39,  4.65it/s]
                                                    

 28%|██▊       | 3069/11066 [11:15<28:39,  4.65it/s]
 28%|██▊       | 3070/11066 [11:16<28:29,  4.68it/s]
                                                    

 28%|██▊       | 3070/11066 [11:16<28:29,  4.68it/s]
 28%|██▊       | 3071/11066 [11:16<28:48,  4.63it/s]
                                                    

 28%|██▊       | 3071/11066 [11:16<28:48,  4.63it/s]
 28%|██▊       | 3072/11066 [11:16<28:40,  4.64it/s]
                                                    

 28%|██▊       | 3072/11066 [11:16<28:40,  4.64it/s]
 28%|██▊       | 3073/11066 [11:16<28:38,  4.65it/s]
                                                    

 28%|██▊       | 3073/11066 [11:16<28:38,  4.65it/s]
 28%|██▊       | 3074/11066 [11:16<28:44,  4.63it/s]
                                                    

 28%|██▊       | 3074/11066 [11:16<28:44,  4.63it/s]
 28%|██▊       | 3075/11066 [11:17<28:43,  4.64it/s]
                                                    

 28%|██▊       | 3075/11066 [11:17<28:43,  4.64it/s]
 28%|██▊       | 3076/11066 [11:17<28:50,  4.62it/s]
                                                    

 28%|██▊       | 3076/11066 [11:17<28:50,  4.62it/s]
 28%|██▊       | 3077/11066 [11:17<28:35,  4.66it/s]
                                                    

 28%|██▊       | 3077/11066 [11:17<28:35,  4.66it/s]
 28%|██▊       | 3078/11066 [11:17<28:33,  4.66it/s]
                                                    

 28%|██▊       | 3078/11066 [11:17<28:33,  4.66it/s]
 28%|██▊       | 3079/11066 [11:18<28:35,  4.66it/s]
                                                    

 28%|██▊       | 3079/11066 [11:18<28:35,  4.66it/s]
 28%|██▊       | 3080/11066 [11:18<28:40,  4.64it/s]
                                                    

 28%|██▊       | 3080/11066 [11:18<28:40,  4.64it/s]
 28%|██▊       | 3081/11066 [11:18<28:27,  4.68it/s]
                                                    

 28%|██▊       | 3081/11066 [11:18<28:27,  4.68it/s]
 28%|██▊       | 3082/11066 [11:18<28:26,  4.68it/s]
                                                    

 28%|██▊       | 3082/11066 [11:18<28:26,  4.68it/s]
 28%|██▊       | 3083/11066 [11:18<28:27,  4.67it/s]
                                                    

 28%|██▊       | 3083/11066 [11:18<28:27,  4.67it/s]
 28%|██▊       | 3084/11066 [11:19<28:37,  4.65it/s]
                                                    

 28%|██▊       | 3084/11066 [11:19<28:37,  4.65it/s]
 28%|██▊       | 3085/11066 [11:19<28:45,  4.62it/s]
                                                    

 28%|██▊       | 3085/11066 [11:19<28:45,  4.62it/s]
 28%|██▊       | 3086/11066 [11:19<28:35,  4.65it/s]
                                                    

 28%|██▊       | 3086/11066 [11:19<28:35,  4.65it/s]
 28%|██▊       | 3087/11066 [11:19<28:55,  4.60it/s]
                                                    

 28%|██▊       | 3087/11066 [11:19<28:55,  4.60it/s]
 28%|██▊       | 3088/11066 [11:19<29:06,  4.57it/s]
                                                    

 28%|██▊       | 3088/11066 [11:19<29:06,  4.57it/s]
 28%|██▊       | 3089/11066 [11:20<29:00,  4.58it/s]
                                                    

 28%|██▊       | 3089/11066 [11:20<29:00,  4.58it/s]
 28%|██▊       | 3090/11066 [11:20<28:52,  4.60it/s]
                                                    

 28%|██▊       | 3090/11066 [11:20<28:52,  4.60it/s]
 28%|██▊       | 3091/11066 [11:20<28:41,  4.63it/s]
                                                    

 28%|██▊       | 3091/11066 [11:20<28:41,  4.63it/s]
 28%|██▊       | 3092/11066 [11:20<28:31,  4.66it/s]
                                                    

 28%|██▊       | 3092/11066 [11:20<28:31,  4.66it/s]
 28%|██▊       | 3093/11066 [11:21<28:50,  4.61it/s]
                                                    

 28%|██▊       | 3093/11066 [11:21<28:50,  4.61it/s]
 28%|██▊       | 3094/11066 [11:21<28:39,  4.64it/s]
                                                    

 28%|██▊       | 3094/11066 [11:21<28:39,  4.64it/s]
 28%|██▊       | 3095/11066 [11:21<28:40,  4.63it/s]
                                                    

 28%|██▊       | 3095/11066 [11:21<28:40,  4.63it/s]
 28%|██▊       | 3096/11066 [11:21<28:26,  4.67it/s]
                                                    

 28%|██▊       | 3096/11066 [11:21<28:26,  4.67it/s]
 28%|██▊       | 3097/11066 [11:21<28:24,  4.68it/s]
                                                    

 28%|██▊       | 3097/11066 [11:21<28:24,  4.68it/s]
 28%|██▊       | 3098/11066 [11:22<28:22,  4.68it/s]
                                                    

 28%|██▊       | 3098/11066 [11:22<28:22,  4.68it/s]
 28%|██▊       | 3099/11066 [11:22<28:16,  4.70it/s]
                                                    

 28%|██▊       | 3099/11066 [11:22<28:16,  4.70it/s]
 28%|██▊       | 3100/11066 [11:22<28:18,  4.69it/s]
                                                    

 28%|██▊       | 3100/11066 [11:22<28:18,  4.69it/s]
 28%|██▊       | 3101/11066 [11:22<28:09,  4.71it/s]
                                                    

 28%|██▊       | 3101/11066 [11:22<28:09,  4.71it/s]
 28%|██▊       | 3102/11066 [11:22<28:42,  4.62it/s]
                                                    

 28%|██▊       | 3102/11066 [11:22<28:42,  4.62it/s]
 28%|██▊       | 3103/11066 [11:23<29:00,  4.58it/s]
                                                    

 28%|██▊       | 3103/11066 [11:23<29:00,  4.58it/s]
 28%|██▊       | 3104/11066 [11:23<29:10,  4.55it/s]
                                                    

 28%|██▊       | 3104/11066 [11:23<29:10,  4.55it/s]
 28%|██▊       | 3105/11066 [11:23<28:50,  4.60it/s]
                                                    

 28%|██▊       | 3105/11066 [11:23<28:50,  4.60it/s]
 28%|██▊       | 3106/11066 [11:23<29:00,  4.57it/s]
                                                    

 28%|██▊       | 3106/11066 [11:23<29:00,  4.57it/s]
 28%|██▊       | 3107/11066 [11:24<28:55,  4.59it/s]
                                                    

 28%|██▊       | 3107/11066 [11:24<28:55,  4.59it/s]
 28%|██▊       | 3108/11066 [11:24<28:37,  4.63it/s]
                                                    

 28%|██▊       | 3108/11066 [11:24<28:37,  4.63it/s]
 28%|██▊       | 3109/11066 [11:24<28:20,  4.68it/s]
                                                    

 28%|██▊       | 3109/11066 [11:24<28:20,  4.68it/s]
 28%|██▊       | 3110/11066 [11:24<28:46,  4.61it/s]
                                                    

 28%|██▊       | 3110/11066 [11:24<28:46,  4.61it/s]
 28%|██▊       | 3111/11066 [11:24<29:06,  4.55it/s]
                                                    

 28%|██▊       | 3111/11066 [11:24<29:06,  4.55it/s]
 28%|██▊       | 3112/11066 [11:25<29:22,  4.51it/s]
                                                    

 28%|██▊       | 3112/11066 [11:25<29:22,  4.51it/s]
 28%|██▊       | 3113/11066 [11:25<29:14,  4.53it/s]
                                                    

 28%|██▊       | 3113/11066 [11:25<29:14,  4.53it/s]
 28%|██▊       | 3114/11066 [11:25<29:22,  4.51it/s]
                                                    

 28%|██▊       | 3114/11066 [11:25<29:22,  4.51it/s]
 28%|██▊       | 3115/11066 [11:25<28:53,  4.59it/s]
                                                    

 28%|██▊       | 3115/11066 [11:25<28:53,  4.59it/s]
 28%|██▊       | 3116/11066 [11:26<29:22,  4.51it/s]
                                                    

 28%|██▊       | 3116/11066 [11:26<29:22,  4.51it/s]
 28%|██▊       | 3117/11066 [11:26<29:27,  4.50it/s]
                                                    

 28%|██▊       | 3117/11066 [11:26<29:27,  4.50it/s]
 28%|██▊       | 3118/11066 [11:26<29:55,  4.43it/s]
                                                    

 28%|██▊       | 3118/11066 [11:26<29:55,  4.43it/s]
 28%|██▊       | 3119/11066 [11:26<29:57,  4.42it/s]
                                                    

 28%|██▊       | 3119/11066 [11:26<29:57,  4.42it/s]
 28%|██▊       | 3120/11066 [11:26<29:48,  4.44it/s]
                                                    

 28%|██▊       | 3120/11066 [11:26<29:48,  4.44it/s]
 28%|██▊       | 3121/11066 [11:27<29:41,  4.46it/s]
                                                    

 28%|██▊       | 3121/11066 [11:27<29:41,  4.46it/s]
 28%|██▊       | 3122/11066 [11:27<29:19,  4.52it/s]
                                                    

 28%|██▊       | 3122/11066 [11:27<29:19,  4.52it/s]
 28%|██▊       | 3123/11066 [11:27<28:57,  4.57it/s]
                                                    

 28%|██▊       | 3123/11066 [11:27<28:57,  4.57it/s]
 28%|██▊       | 3124/11066 [11:27<28:31,  4.64it/s]
                                                    

 28%|██▊       | 3124/11066 [11:27<28:31,  4.64it/s]
 28%|██▊       | 3125/11066 [11:28<28:28,  4.65it/s]
                                                    

 28%|██▊       | 3125/11066 [11:28<28:28,  4.65it/s]
 28%|██▊       | 3126/11066 [11:28<28:45,  4.60it/s]
                                                    

 28%|██▊       | 3126/11066 [11:28<28:45,  4.60it/s]
 28%|██▊       | 3127/11066 [11:28<28:39,  4.62it/s]
                                                    

 28%|██▊       | 3127/11066 [11:28<28:39,  4.62it/s]
 28%|██▊       | 3128/11066 [11:28<28:27,  4.65it/s]
                                                    

 28%|██▊       | 3128/11066 [11:28<28:27,  4.65it/s]
 28%|██▊       | 3129/11066 [11:28<28:45,  4.60it/s]
                                                    

 28%|██▊       | 3129/11066 [11:28<28:45,  4.60it/s]
 28%|██▊       | 3130/11066 [11:29<28:56,  4.57it/s]
                                                    

 28%|██▊       | 3130/11066 [11:29<28:56,  4.57it/s]
 28%|██▊       | 3131/11066 [11:29<28:40,  4.61it/s]
                                                    

 28%|██▊       | 3131/11066 [11:29<28:40,  4.61it/s]
 28%|██▊       | 3132/11066 [11:29<28:28,  4.64it/s]
                                                    

 28%|██▊       | 3132/11066 [11:29<28:28,  4.64it/s]
 28%|██▊       | 3133/11066 [11:29<28:31,  4.63it/s]
                                                    

 28%|██▊       | 3133/11066 [11:29<28:31,  4.63it/s]
 28%|██▊       | 3134/11066 [11:29<28:18,  4.67it/s]
                                                    

 28%|██▊       | 3134/11066 [11:29<28:18,  4.67it/s]
 28%|██▊       | 3135/11066 [11:30<28:12,  4.69it/s]
                                                    

 28%|██▊       | 3135/11066 [11:30<28:12,  4.69it/s]
 28%|██▊       | 3136/11066 [11:30<28:31,  4.63it/s]
                                                    

 28%|██▊       | 3136/11066 [11:30<28:31,  4.63it/s]
 28%|██▊       | 3137/11066 [11:30<28:23,  4.66it/s]
                                                    

 28%|██▊       | 3137/11066 [11:30<28:23,  4.66it/s]
 28%|██▊       | 3138/11066 [11:30<28:18,  4.67it/s]
                                                    

 28%|██▊       | 3138/11066 [11:30<28:18,  4.67it/s]
 28%|██▊       | 3139/11066 [11:31<28:14,  4.68it/s]
                                                    

 28%|██▊       | 3139/11066 [11:31<28:14,  4.68it/s]
 28%|██▊       | 3140/11066 [11:31<28:35,  4.62it/s]
                                                    

 28%|██▊       | 3140/11066 [11:31<28:35,  4.62it/s]
 28%|██▊       | 3141/11066 [11:31<28:26,  4.64it/s]
                                                    

 28%|██▊       | 3141/11066 [11:31<28:26,  4.64it/s]
 28%|██▊       | 3142/11066 [11:31<28:18,  4.67it/s]
                                                    

 28%|██▊       | 3142/11066 [11:31<28:18,  4.67it/s]
 28%|██▊       | 3143/11066 [11:31<28:15,  4.67it/s]
                                                    

 28%|██▊       | 3143/11066 [11:31<28:15,  4.67it/s]
 28%|██▊       | 3144/11066 [11:32<28:38,  4.61it/s]
                                                    

 28%|██▊       | 3144/11066 [11:32<28:38,  4.61it/s]
 28%|██▊       | 3145/11066 [11:32<28:36,  4.61it/s]
                                                    

 28%|██▊       | 3145/11066 [11:32<28:36,  4.61it/s]
 28%|██▊       | 3146/11066 [11:32<28:21,  4.65it/s]
                                                    

 28%|██▊       | 3146/11066 [11:32<28:21,  4.65it/s]
 28%|██▊       | 3147/11066 [11:32<28:15,  4.67it/s]
                                                    

 28%|██▊       | 3147/11066 [11:32<28:15,  4.67it/s]
 28%|██▊       | 3148/11066 [11:32<28:12,  4.68it/s]
                                                    

 28%|██▊       | 3148/11066 [11:32<28:12,  4.68it/s]
 28%|██▊       | 3149/11066 [11:33<28:20,  4.66it/s]
                                                    

 28%|██▊       | 3149/11066 [11:33<28:20,  4.66it/s]
 28%|██▊       | 3150/11066 [11:33<28:14,  4.67it/s]
                                                    

 28%|██▊       | 3150/11066 [11:33<28:14,  4.67it/s]
 28%|██▊       | 3151/11066 [11:33<28:09,  4.69it/s]
                                                    
{'loss': 1.2394, 'learning_rate': 2.1761250677751672e-05, 'epoch': 0.55}
{'loss': 0.6624, 'learning_rate': 2.175853967106452e-05, 'epoch': 0.55}
{'loss': 0.9287, 'learning_rate': 2.1755828664377373e-05, 'epoch': 0.55}
{'loss': 1.3069, 'learning_rate': 2.1753117657690224e-05, 'epoch': 0.55}
{'loss': 0.8948, 'learning_rate': 2.1750406651003073e-05, 'epoch': 0.55}
{'loss': 1.1573, 'learning_rate': 2.1747695644315925e-05, 'epoch': 0.55}
{'loss': 1.1402, 'learning_rate': 2.1744984637628773e-05, 'epoch': 0.55}
{'loss': 0.7158, 'learning_rate': 2.174227363094162e-05, 'epoch': 0.55}
{'loss': 0.7714, 'learning_rate': 2.1739562624254473e-05, 'epoch': 0.55}
{'loss': 1.2003, 'learning_rate': 2.1736851617567325e-05, 'epoch': 0.55}
{'loss': 0.8763, 'learning_rate': 2.1734140610880174e-05, 'epoch': 0.55}
{'loss': 0.6484, 'learning_rate': 2.1731429604193025e-05, 'epoch': 0.55}
{'loss': 0.4154, 'learning_rate': 2.1728718597505874e-05, 'epoch': 0.55}
{'loss': 1.2448, 'learning_rate': 2.1726007590818726e-05, 'epoch': 0.55}
{'loss': 0.9251, 'learning_rate': 2.1723296584131574e-05, 'epoch': 0.55}
{'loss': 1.5072, 'learning_rate': 2.1720585577444423e-05, 'epoch': 0.55}
{'loss': 1.1441, 'learning_rate': 2.1717874570757274e-05, 'epoch': 0.55}
{'loss': 1.2719, 'learning_rate': 2.1715163564070126e-05, 'epoch': 0.55}
{'loss': 0.9455, 'learning_rate': 2.1712452557382975e-05, 'epoch': 0.55}
{'loss': 1.2311, 'learning_rate': 2.1709741550695827e-05, 'epoch': 0.55}
{'loss': 1.3236, 'learning_rate': 2.170703054400868e-05, 'epoch': 0.55}
{'loss': 0.9978, 'learning_rate': 2.1704319537321527e-05, 'epoch': 0.55}
{'loss': 1.0554, 'learning_rate': 2.1701608530634375e-05, 'epoch': 0.55}
{'loss': 0.5062, 'learning_rate': 2.1698897523947224e-05, 'epoch': 0.55}
{'loss': 0.8602, 'learning_rate': 2.1696186517260076e-05, 'epoch': 0.55}
{'loss': 0.7589, 'learning_rate': 2.1693475510572927e-05, 'epoch': 0.55}
{'loss': 0.8269, 'learning_rate': 2.1690764503885776e-05, 'epoch': 0.55}
{'loss': 1.209, 'learning_rate': 2.1688053497198628e-05, 'epoch': 0.55}
{'loss': 1.2394, 'learning_rate': 2.168534249051148e-05, 'epoch': 0.55}
{'loss': 1.3134, 'learning_rate': 2.1682631483824328e-05, 'epoch': 0.55}
{'loss': 1.0344, 'learning_rate': 2.1679920477137176e-05, 'epoch': 0.55}
{'loss': 0.98, 'learning_rate': 2.1677209470450028e-05, 'epoch': 0.55}
{'loss': 1.1698, 'learning_rate': 2.1674498463762877e-05, 'epoch': 0.56}
{'loss': 1.7238, 'learning_rate': 2.167178745707573e-05, 'epoch': 0.56}
{'loss': 1.0837, 'learning_rate': 2.1669076450388577e-05, 'epoch': 0.56}
{'loss': 0.8278, 'learning_rate': 2.166636544370143e-05, 'epoch': 0.56}
{'loss': 0.6957, 'learning_rate': 2.166365443701428e-05, 'epoch': 0.56}
{'loss': 0.4411, 'learning_rate': 2.166094343032713e-05, 'epoch': 0.56}
{'loss': 1.1785, 'learning_rate': 2.1658232423639977e-05, 'epoch': 0.56}
{'loss': 0.9394, 'learning_rate': 2.165552141695283e-05, 'epoch': 0.56}
{'loss': 0.7096, 'learning_rate': 2.1652810410265678e-05, 'epoch': 0.56}
{'loss': 0.7523, 'learning_rate': 2.165009940357853e-05, 'epoch': 0.56}
{'loss': 1.1642, 'learning_rate': 2.164738839689138e-05, 'epoch': 0.56}
{'loss': 0.7022, 'learning_rate': 2.164467739020423e-05, 'epoch': 0.56}
{'loss': 1.7923, 'learning_rate': 2.164196638351708e-05, 'epoch': 0.56}
{'loss': 0.9748, 'learning_rate': 2.163925537682993e-05, 'epoch': 0.56}
{'loss': 0.7188, 'learning_rate': 2.163654437014278e-05, 'epoch': 0.56}
{'loss': 0.6758, 'learning_rate': 2.163383336345563e-05, 'epoch': 0.56}
{'loss': 0.7185, 'learning_rate': 2.163112235676848e-05, 'epoch': 0.56}
{'loss': 1.7332, 'learning_rate': 2.162841135008133e-05, 'epoch': 0.56}
{'loss': 1.3405, 'learning_rate': 2.1625700343394182e-05, 'epoch': 0.56}
{'loss': 0.3282, 'learning_rate': 2.162298933670703e-05, 'epoch': 0.56}
{'loss': 0.9142, 'learning_rate': 2.1620278330019883e-05, 'epoch': 0.56}
{'loss': 1.4252, 'learning_rate': 2.161756732333273e-05, 'epoch': 0.56}
{'loss': 1.172, 'learning_rate': 2.161485631664558e-05, 'epoch': 0.56}
{'loss': 1.0124, 'learning_rate': 2.161214530995843e-05, 'epoch': 0.56}
{'loss': 0.8948, 'learning_rate': 2.1609434303271283e-05, 'epoch': 0.56}
{'loss': 1.6762, 'learning_rate': 2.160672329658413e-05, 'epoch': 0.56}
{'loss': 0.8871, 'learning_rate': 2.1604012289896984e-05, 'epoch': 0.56}
{'loss': 1.4385, 'learning_rate': 2.1601301283209832e-05, 'epoch': 0.56}
{'loss': 1.0284, 'learning_rate': 2.1598590276522684e-05, 'epoch': 0.56}
{'loss': 1.1597, 'learning_rate': 2.1595879269835532e-05, 'epoch': 0.56}
{'loss': 1.0411, 'learning_rate': 2.159316826314838e-05, 'epoch': 0.56}
{'loss': 1.0185, 'learning_rate': 2.1590457256461232e-05, 'epoch': 0.56}
{'loss': 0.9167, 'learning_rate': 2.1587746249774084e-05, 'epoch': 0.56}
{'loss': 0.6924, 'learning_rate': 2.1585035243086933e-05, 'epoch': 0.56}
{'loss': 1.1227, 'learning_rate': 2.1582324236399785e-05, 'epoch': 0.56}
{'loss': 1.5394, 'learning_rate': 2.1579613229712636e-05, 'epoch': 0.56}
{'loss': 1.1203, 'learning_rate': 2.1576902223025485e-05, 'epoch': 0.56}
{'loss': 1.3883, 'learning_rate': 2.1574191216338333e-05, 'epoch': 0.56}
{'loss': 0.9308, 'learning_rate': 2.1571480209651182e-05, 'epoch': 0.56}
{'loss': 0.9264, 'learning_rate': 2.1568769202964034e-05, 'epoch': 0.56}
{'loss': 0.8648, 'learning_rate': 2.1566058196276885e-05, 'epoch': 0.56}
{'loss': 0.7224, 'learning_rate': 2.1563347189589734e-05, 'epoch': 0.56}
{'loss': 0.8179, 'learning_rate': 2.1560636182902586e-05, 'epoch': 0.56}
{'loss': 1.2663, 'learning_rate': 2.1557925176215437e-05, 'epoch': 0.56}
{'loss': 0.8658, 'learning_rate': 2.1555214169528286e-05, 'epoch': 0.56}
{'loss': 0.9581, 'learning_rate': 2.1552503162841134e-05, 'epoch': 0.56}
{'loss': 1.1434, 'learning_rate': 2.1549792156153986e-05, 'epoch': 0.56}
{'loss': 1.3513, 'learning_rate': 2.1547081149466835e-05, 'epoch': 0.56}
{'loss': 0.7452, 'learning_rate': 2.1544370142779686e-05, 'epoch': 0.56}
{'loss': 0.5634, 'learning_rate': 2.1541659136092535e-05, 'epoch': 0.56}
{'loss': 0.9787, 'learning_rate': 2.1538948129405387e-05, 'epoch': 0.56}
{'loss': 1.2245, 'learning_rate': 2.153623712271824e-05, 'epoch': 0.56}
{'loss': 1.8836, 'learning_rate': 2.1533526116031087e-05, 'epoch': 0.56}
{'loss': 0.7448, 'learning_rate': 2.1530815109343935e-05, 'epoch': 0.56}
{'loss': 1.7999, 'learning_rate': 2.1528104102656787e-05, 'epoch': 0.56}
{'loss': 0.9918, 'learning_rate': 2.1525393095969636e-05, 'epoch': 0.56}
{'loss': 1.0073, 'learning_rate': 2.1522682089282488e-05, 'epoch': 0.57}
{'loss': 0.5542, 'learning_rate': 2.151997108259534e-05, 'epoch': 0.57}
{'loss': 0.7866, 'learning_rate': 2.1517260075908188e-05, 'epoch': 0.57}
{'loss': 0.9478, 'learning_rate': 2.151454906922104e-05, 'epoch': 0.57}
{'loss': 1.4503, 'learning_rate': 2.1511838062533888e-05, 'epoch': 0.57}
{'loss': 0.959, 'learning_rate': 2.1509127055846737e-05, 'epoch': 0.57}
{'loss': 1.4657, 'learning_rate': 2.150641604915959e-05, 'epoch': 0.57}
{'loss': 1.0293, 'learning_rate': 2.1503705042472437e-05, 'epoch': 0.57}
{'loss': 1.1509, 'learning_rate': 2.150099403578529e-05, 'epoch': 0.57}
{'loss': 0.8585, 'learning_rate': 2.149828302909814e-05, 'epoch': 0.57}
{'loss': 0.6931, 'learning_rate': 2.149557202241099e-05, 'epoch': 0.57}
{'loss': 1.4469, 'learning_rate': 2.149286101572384e-05, 'epoch': 0.57}
{'loss': 0.6549, 'learning_rate': 2.1490150009036693e-05, 'epoch': 0.57}
{'loss': 0.7261, 'learning_rate': 2.1487439002349538e-05, 'epoch': 0.57}
{'loss': 2.2247, 'learning_rate': 2.148472799566239e-05, 'epoch': 0.57}
{'loss': 0.5169, 'learning_rate': 2.1482016988975238e-05, 'epoch': 0.57}
{'loss': 1.0405, 'learning_rate': 2.147930598228809e-05, 'epoch': 0.57}
{'loss': 0.4712, 'learning_rate': 2.147659497560094e-05, 'epoch': 0.57}
{'loss': 1.2003, 'learning_rate': 2.147388396891379e-05, 'epoch': 0.57}
{'loss': 1.2177, 'learning_rate': 2.1471172962226642e-05, 'epoch': 0.57}
{'loss': 1.6578, 'learning_rate': 2.1468461955539494e-05, 'epoch': 0.57}
{'loss': 1.0064, 'learning_rate': 2.146575094885234e-05, 'epoch': 0.57}
{'loss': 0.8489, 'learning_rate': 2.146303994216519e-05, 'epoch': 0.57}
{'loss': 1.0613, 'learning_rate': 2.1460328935478042e-05, 'epoch': 0.57}

 28%|██▊       | 3151/11066 [11:33<28:09,  4.69it/s]
 28%|██▊       | 3152/11066 [11:33<28:05,  4.69it/s]
                                                    

 28%|██▊       | 3152/11066 [11:33<28:05,  4.69it/s]
 28%|██▊       | 3153/11066 [11:34<28:04,  4.70it/s]
                                                    

 28%|██▊       | 3153/11066 [11:34<28:04,  4.70it/s]
 29%|██▊       | 3154/11066 [11:34<28:03,  4.70it/s]
                                                    

 29%|██▊       | 3154/11066 [11:34<28:03,  4.70it/s]
 29%|██▊       | 3155/11066 [11:34<28:31,  4.62it/s]
                                                    

 29%|██▊       | 3155/11066 [11:34<28:31,  4.62it/s]
 29%|██▊       | 3156/11066 [11:34<28:21,  4.65it/s]
                                                    

 29%|██▊       | 3156/11066 [11:34<28:21,  4.65it/s]
 29%|██▊       | 3157/11066 [11:34<28:14,  4.67it/s]
                                                    

 29%|██▊       | 3157/11066 [11:34<28:14,  4.67it/s]
 29%|██▊       | 3158/11066 [11:35<28:40,  4.60it/s]
                                                    

 29%|██▊       | 3158/11066 [11:35<28:40,  4.60it/s]
 29%|██▊       | 3159/11066 [11:35<28:30,  4.62it/s]
                                                    

 29%|██▊       | 3159/11066 [11:35<28:30,  4.62it/s]
 29%|██▊       | 3160/11066 [11:35<28:19,  4.65it/s]
                                                    

 29%|██▊       | 3160/11066 [11:35<28:19,  4.65it/s]
 29%|██▊       | 3161/11066 [11:35<28:13,  4.67it/s]
                                                    

 29%|██▊       | 3161/11066 [11:35<28:13,  4.67it/s]
 29%|██▊       | 3162/11066 [11:35<28:07,  4.68it/s]
                                                    

 29%|██▊       | 3162/11066 [11:35<28:07,  4.68it/s]
 29%|██▊       | 3163/11066 [11:36<28:04,  4.69it/s]
                                                    

 29%|██▊       | 3163/11066 [11:36<28:04,  4.69it/s]
 29%|██▊       | 3164/11066 [11:36<28:13,  4.67it/s]
                                                    

 29%|██▊       | 3164/11066 [11:36<28:13,  4.67it/s]
 29%|██▊       | 3165/11066 [11:36<28:03,  4.69it/s]
                                                    

 29%|██▊       | 3165/11066 [11:36<28:03,  4.69it/s]
 29%|██▊       | 3166/11066 [11:36<27:58,  4.71it/s]
                                                    

 29%|██▊       | 3166/11066 [11:36<27:58,  4.71it/s]
 29%|██▊       | 3167/11066 [11:37<28:07,  4.68it/s]
                                                    

 29%|██▊       | 3167/11066 [11:37<28:07,  4.68it/s]
 29%|██▊       | 3168/11066 [11:37<27:56,  4.71it/s]
                                                    

 29%|██▊       | 3168/11066 [11:37<27:56,  4.71it/s]
 29%|██▊       | 3169/11066 [11:37<28:08,  4.68it/s]
                                                    

 29%|██▊       | 3169/11066 [11:37<28:08,  4.68it/s]
 29%|██▊       | 3170/11066 [11:37<28:14,  4.66it/s]
                                                    

 29%|██▊       | 3170/11066 [11:37<28:14,  4.66it/s]
 29%|██▊       | 3171/11066 [11:37<28:07,  4.68it/s]
                                                    

 29%|██▊       | 3171/11066 [11:37<28:07,  4.68it/s]
 29%|██▊       | 3172/11066 [11:38<28:16,  4.65it/s]
                                                    

 29%|██▊       | 3172/11066 [11:38<28:16,  4.65it/s]
 29%|██▊       | 3173/11066 [11:38<28:41,  4.58it/s]
                                                    

 29%|██▊       | 3173/11066 [11:38<28:41,  4.58it/s]
 29%|██▊       | 3174/11066 [11:38<28:43,  4.58it/s]
                                                    

 29%|██▊       | 3174/11066 [11:38<28:43,  4.58it/s]
 29%|██▊       | 3175/11066 [11:38<28:31,  4.61it/s]
                                                    

 29%|██▊       | 3175/11066 [11:38<28:31,  4.61it/s]
 29%|██▊       | 3176/11066 [11:38<28:20,  4.64it/s]
                                                    

 29%|██▊       | 3176/11066 [11:38<28:20,  4.64it/s]
 29%|██▊       | 3177/11066 [11:39<28:39,  4.59it/s]
                                                    

 29%|██▊       | 3177/11066 [11:39<28:39,  4.59it/s]
 29%|██▊       | 3178/11066 [11:39<28:56,  4.54it/s]
                                                    

 29%|██▊       | 3178/11066 [11:39<28:56,  4.54it/s]
 29%|██▊       | 3179/11066 [11:39<28:51,  4.56it/s]
                                                    

 29%|██▊       | 3179/11066 [11:39<28:51,  4.56it/s]
 29%|██▊       | 3180/11066 [11:39<28:27,  4.62it/s]
                                                    

 29%|██▊       | 3180/11066 [11:39<28:27,  4.62it/s]
 29%|██▊       | 3181/11066 [11:40<28:26,  4.62it/s]
                                                    

 29%|██▊       | 3181/11066 [11:40<28:26,  4.62it/s]
 29%|██▉       | 3182/11066 [11:40<28:11,  4.66it/s]
                                                    

 29%|██▉       | 3182/11066 [11:40<28:11,  4.66it/s]
 29%|██▉       | 3183/11066 [11:40<27:58,  4.70it/s]
                                                    

 29%|██▉       | 3183/11066 [11:40<27:58,  4.70it/s]
 29%|██▉       | 3184/11066 [11:40<27:56,  4.70it/s]
                                                    

 29%|██▉       | 3184/11066 [11:40<27:56,  4.70it/s]
 29%|██▉       | 3185/11066 [11:40<27:53,  4.71it/s]
                                                    

 29%|██▉       | 3185/11066 [11:40<27:53,  4.71it/s]
 29%|██▉       | 3186/11066 [11:41<28:05,  4.68it/s]
                                                    

 29%|██▉       | 3186/11066 [11:41<28:05,  4.68it/s]
 29%|██▉       | 3187/11066 [11:41<28:32,  4.60it/s]
                                                    

 29%|██▉       | 3187/11066 [11:41<28:32,  4.60it/s]
 29%|██▉       | 3188/11066 [11:41<28:35,  4.59it/s]
                                                    

 29%|██▉       | 3188/11066 [11:41<28:35,  4.59it/s]
 29%|██▉       | 3189/11066 [11:41<28:16,  4.64it/s]
                                                    

 29%|██▉       | 3189/11066 [11:41<28:16,  4.64it/s]
 29%|██▉       | 3190/11066 [11:42<28:18,  4.64it/s]
                                                    

 29%|██▉       | 3190/11066 [11:42<28:18,  4.64it/s]
 29%|██▉       | 3191/11066 [11:42<28:05,  4.67it/s]
                                                    

 29%|██▉       | 3191/11066 [11:42<28:05,  4.67it/s]
 29%|██▉       | 3192/11066 [11:42<27:59,  4.69it/s]
                                                    

 29%|██▉       | 3192/11066 [11:42<27:59,  4.69it/s]
 29%|██▉       | 3193/11066 [11:42<28:08,  4.66it/s]
                                                    

 29%|██▉       | 3193/11066 [11:42<28:08,  4.66it/s]
 29%|██▉       | 3194/11066 [11:42<27:58,  4.69it/s]
                                                    

 29%|██▉       | 3194/11066 [11:42<27:58,  4.69it/s]
 29%|██▉       | 3195/11066 [11:43<27:47,  4.72it/s]
                                                    

 29%|██▉       | 3195/11066 [11:43<27:47,  4.72it/s]
 29%|██▉       | 3196/11066 [11:43<28:14,  4.64it/s]
                                                    

 29%|██▉       | 3196/11066 [11:43<28:14,  4.64it/s]
 29%|██▉       | 3197/11066 [11:43<28:06,  4.66it/s]
                                                    

 29%|██▉       | 3197/11066 [11:43<28:06,  4.66it/s]
 29%|██▉       | 3198/11066 [11:43<28:11,  4.65it/s]
                                                    

 29%|██▉       | 3198/11066 [11:43<28:11,  4.65it/s]
 29%|██▉       | 3199/11066 [11:43<27:57,  4.69it/s]
                                                    

 29%|██▉       | 3199/11066 [11:43<27:57,  4.69it/s]
 29%|██▉       | 3200/11066 [11:44<28:18,  4.63it/s]
                                                    

 29%|██▉       | 3200/11066 [11:44<28:18,  4.63it/s]
 29%|██▉       | 3201/11066 [11:44<28:35,  4.59it/s]
                                                    

 29%|██▉       | 3201/11066 [11:44<28:35,  4.59it/s]
 29%|██▉       | 3202/11066 [11:44<28:21,  4.62it/s]
                                                    

 29%|██▉       | 3202/11066 [11:44<28:21,  4.62it/s]
 29%|██▉       | 3203/11066 [11:44<28:10,  4.65it/s]
                                                    

 29%|██▉       | 3203/11066 [11:44<28:10,  4.65it/s]
 29%|██▉       | 3204/11066 [11:45<28:12,  4.64it/s]
                                                    

 29%|██▉       | 3204/11066 [11:45<28:12,  4.64it/s]
 29%|██▉       | 3205/11066 [11:45<28:06,  4.66it/s]
                                                    

 29%|██▉       | 3205/11066 [11:45<28:06,  4.66it/s]
 29%|██▉       | 3206/11066 [11:45<27:55,  4.69it/s]
                                                    

 29%|██▉       | 3206/11066 [11:45<27:55,  4.69it/s]
 29%|██▉       | 3207/11066 [11:45<27:53,  4.70it/s]
                                                    

 29%|██▉       | 3207/11066 [11:45<27:53,  4.70it/s]
 29%|██▉       | 3208/11066 [11:45<27:41,  4.73it/s]
                                                    

 29%|██▉       | 3208/11066 [11:45<27:41,  4.73it/s]
 29%|██▉       | 3209/11066 [11:46<27:43,  4.72it/s]
                                                    

 29%|██▉       | 3209/11066 [11:46<27:43,  4.72it/s]
 29%|██▉       | 3210/11066 [11:46<27:55,  4.69it/s]
                                                    

 29%|██▉       | 3210/11066 [11:46<27:55,  4.69it/s]
 29%|██▉       | 3211/11066 [11:46<27:54,  4.69it/s]
                                                    

 29%|██▉       | 3211/11066 [11:46<27:54,  4.69it/s]
 29%|██▉       | 3212/11066 [11:46<28:15,  4.63it/s]
                                                    

 29%|██▉       | 3212/11066 [11:46<28:15,  4.63it/s]
 29%|██▉       | 3213/11066 [11:46<28:23,  4.61it/s]
                                                    

 29%|██▉       | 3213/11066 [11:46<28:23,  4.61it/s]
 29%|██▉       | 3214/11066 [11:47<28:35,  4.58it/s]
                                                    

 29%|██▉       | 3214/11066 [11:47<28:35,  4.58it/s]
 29%|██▉       | 3215/11066 [11:47<28:11,  4.64it/s]
                                                    

 29%|██▉       | 3215/11066 [11:47<28:11,  4.64it/s]
 29%|██▉       | 3216/11066 [11:47<28:21,  4.61it/s]
                                                    

 29%|██▉       | 3216/11066 [11:47<28:21,  4.61it/s]
 29%|██▉       | 3217/11066 [11:47<28:25,  4.60it/s]
                                                    

 29%|██▉       | 3217/11066 [11:47<28:25,  4.60it/s]
 29%|██▉       | 3218/11066 [11:48<28:38,  4.57it/s]
                                                    

 29%|██▉       | 3218/11066 [11:48<28:38,  4.57it/s]
 29%|██▉       | 3219/11066 [11:48<28:47,  4.54it/s]
                                                    

 29%|██▉       | 3219/11066 [11:48<28:47,  4.54it/s]
 29%|██▉       | 3220/11066 [11:48<28:29,  4.59it/s]
                                                    

 29%|██▉       | 3220/11066 [11:48<28:29,  4.59it/s]
 29%|██▉       | 3221/11066 [11:48<28:28,  4.59it/s]
                                                    

 29%|██▉       | 3221/11066 [11:48<28:28,  4.59it/s]
 29%|██▉       | 3222/11066 [11:48<28:09,  4.64it/s]
                                                    

 29%|██▉       | 3222/11066 [11:48<28:09,  4.64it/s]
 29%|██▉       | 3223/11066 [11:49<28:39,  4.56it/s]
                                                    

 29%|██▉       | 3223/11066 [11:49<28:39,  4.56it/s]
 29%|██▉       | 3224/11066 [11:49<28:46,  4.54it/s]
                                                    

 29%|██▉       | 3224/11066 [11:49<28:46,  4.54it/s]
 29%|██▉       | 3225/11066 [11:49<28:57,  4.51it/s]
                                                    

 29%|██▉       | 3225/11066 [11:49<28:57,  4.51it/s]
 29%|██▉       | 3226/11066 [11:49<29:02,  4.50it/s]
                                                    

 29%|██▉       | 3226/11066 [11:49<29:02,  4.50it/s]
 29%|██▉       | 3227/11066 [11:50<29:02,  4.50it/s]
                                                    

 29%|██▉       | 3227/11066 [11:50<29:02,  4.50it/s]
 29%|██▉       | 3228/11066 [11:50<28:50,  4.53it/s]
                                                    

 29%|██▉       | 3228/11066 [11:50<28:50,  4.53it/s]
 29%|██▉       | 3229/11066 [11:50<28:35,  4.57it/s]
                                                    

 29%|██▉       | 3229/11066 [11:50<28:35,  4.57it/s]
 29%|██▉       | 3230/11066 [11:50<28:50,  4.53it/s]
                                                    

 29%|██▉       | 3230/11066 [11:50<28:50,  4.53it/s]
 29%|██▉       | 3231/11066 [11:50<29:21,  4.45it/s]
                                                    

 29%|██▉       | 3231/11066 [11:50<29:21,  4.45it/s]
 29%|██▉       | 3232/11066 [11:51<29:16,  4.46it/s]
                                                    

 29%|██▉       | 3232/11066 [11:51<29:16,  4.46it/s]
 29%|██▉       | 3233/11066 [11:51<29:10,  4.48it/s]
                                                    

 29%|██▉       | 3233/11066 [11:51<29:10,  4.48it/s]
 29%|██▉       | 3234/11066 [11:51<29:07,  4.48it/s]
                                                    

 29%|██▉       | 3234/11066 [11:51<29:07,  4.48it/s]
 29%|██▉       | 3235/11066 [11:51<29:06,  4.48it/s]
                                                    

 29%|██▉       | 3235/11066 [11:51<29:06,  4.48it/s]
 29%|██▉       | 3236/11066 [11:52<29:05,  4.49it/s]
                                                    

 29%|██▉       | 3236/11066 [11:52<29:05,  4.49it/s]
 29%|██▉       | 3237/11066 [11:52<28:41,  4.55it/s]
                                                    

 29%|██▉       | 3237/11066 [11:52<28:41,  4.55it/s]
 29%|██▉       | 3238/11066 [11:52<28:48,  4.53it/s]
                                                    

 29%|██▉       | 3238/11066 [11:52<28:48,  4.53it/s]
 29%|██▉       | 3239/11066 [11:52<28:38,  4.55it/s]
                                                    

 29%|██▉       | 3239/11066 [11:52<28:38,  4.55it/s]
 29%|██▉       | 3240/11066 [11:52<28:38,  4.55it/s]
                                                    

 29%|██▉       | 3240/11066 [11:52<28:38,  4.55it/s]
 29%|██▉       | 3241/11066 [11:53<28:36,  4.56it/s]
                                                    

 29%|██▉       | 3241/11066 [11:53<28:36,  4.56it/s]
 29%|██▉       | 3242/11066 [11:53<28:44,  4.54it/s]
                                                    

 29%|██▉       | 3242/11066 [11:53<28:44,  4.54it/s]
 29%|██▉       | 3243/11066 [11:53<28:18,  4.61it/s]
                                                    

 29%|██▉       | 3243/11066 [11:53<28:18,  4.61it/s]
 29%|██▉       | 3244/11066 [11:53<29:32,  4.41it/s]
                                                    

 29%|██▉       | 3244/11066 [11:53<29:32,  4.41it/s]
 29%|██▉       | 3245/11066 [11:54<29:51,  4.37it/s]
                                                    

 29%|██▉       | 3245/11066 [11:54<29:51,  4.37it/s]
 29%|██▉       | 3246/11066 [11:54<29:40,  4.39it/s]
                                                    

 29%|██▉       | 3246/11066 [11:54<29:40,  4.39it/s]
 29%|██▉       | 3247/11066 [11:54<29:31,  4.41it/s]
                                                    

 29%|██▉       | 3247/11066 [11:54<29:31,  4.41it/s]
 29%|██▉       | 3248/11066 [11:54<29:20,  4.44it/s]
                                                    

 29%|██▉       | 3248/11066 [11:54<29:20,  4.44it/s]
 29%|██▉       | 3249/11066 [11:54<29:01,  4.49it/s]
                                                    

 29%|██▉       | 3249/11066 [11:54<29:01,  4.49it/s]
 29%|██▉       | 3250/11066 [11:55<29:07,  4.47it/s]
                                                    

 29%|██▉       | 3250/11066 [11:55<29:07,  4.47it/s]
 29%|██▉       | 3251/11066 [11:55<29:31,  4.41it/s]
                                                    

 29%|██▉       | 3251/11066 [11:55<29:31,  4.41it/s]
 29%|██▉       | 3252/11066 [11:55<29:08,  4.47it/s]
                                                    

 29%|██▉       | 3252/11066 [11:55<29:08,  4.47it/s]
 29%|██▉       | 3253/11066 [11:55<29:03,  4.48it/s]
                                                    

 29%|██▉       | 3253/11066 [11:55<29:03,  4.48it/s]
 29%|██▉       | 3254/11066 [11:56<28:43,  4.53it/s]
                                                    

 29%|██▉       | 3254/11066 [11:56<28:43,  4.53it/s]
 29%|██▉       | 3255/11066 [11:56<28:26,  4.58it/s]
                                                    

 29%|██▉       | 3255/11066 [11:56<28:26,  4.58it/s]
 29%|██▉       | 3256/11066 [11:56<28:36,  4.55it/s]
                                                    

 29%|██▉       | 3256/11066 [11:56<28:36,  4.55it/s]
 29%|██▉       | 3257/11066 [11:56<28:45,  4.53it/s]
                                                    

 29%|██▉       | 3257/11066 [11:56<28:45,  4.53it/s]
 29%|██▉       | 3258/11066 [11:56<28:23,  4.58it/s]
                                                    

 29%|██▉       | 3258/11066 [11:56<28:23,  4.58it/s]
 29%|██▉       | 3259/11066 [11:57<28:10,  4.62it/s]
                                                    

 29%|██▉       | 3259/11066 [11:57<28:10,  4.62it/s]
 29%|██▉       | 3260/11066 [11:57<27:59,  4.65it/s]
                                                    

 29%|██▉       | 3260/11066 [11:57<27:59,  4.65it/s]
 29%|██▉       | 3261/11066 [11:57<28:02,  4.64it/s]
                                                    

 29%|██▉       | 3261/11066 [11:57<28:02,  4.64it/s]
 29%|██▉       | 3262/11066 [11:57<27:47,  4.68it/s]
                                                    

 29%|██▉       | 3262/11066 [11:57<27:47,  4.68it/s]
 29%|██▉       | 3263/11066 [11:57<27:54,  4.66it/s]
                                                    

 29%|██▉       | 3263/11066 [11:57<27:54,  4.66it/s]
 29%|██▉       | 3264/11066 [11:58<27:42,  4.69it/s]
                                                    
{'loss': 0.9721, 'learning_rate': 2.145761792879089e-05, 'epoch': 0.57}
{'loss': 1.0083, 'learning_rate': 2.1454906922103743e-05, 'epoch': 0.57}
{'loss': 1.1089, 'learning_rate': 2.145219591541659e-05, 'epoch': 0.57}
{'loss': 1.4667, 'learning_rate': 2.1449484908729443e-05, 'epoch': 0.57}
{'loss': 1.093, 'learning_rate': 2.1446773902042295e-05, 'epoch': 0.57}
{'loss': 2.34, 'learning_rate': 2.144406289535514e-05, 'epoch': 0.57}
{'loss': 1.7171, 'learning_rate': 2.144135188866799e-05, 'epoch': 0.57}
{'loss': 1.5607, 'learning_rate': 2.1438640881980843e-05, 'epoch': 0.57}
{'loss': 0.7553, 'learning_rate': 2.1435929875293692e-05, 'epoch': 0.57}
{'loss': 0.9305, 'learning_rate': 2.1433218868606544e-05, 'epoch': 0.57}
{'loss': 1.1169, 'learning_rate': 2.1430507861919395e-05, 'epoch': 0.57}
{'loss': 1.3446, 'learning_rate': 2.1427796855232244e-05, 'epoch': 0.57}
{'loss': 1.7467, 'learning_rate': 2.1425085848545096e-05, 'epoch': 0.57}
{'loss': 0.7248, 'learning_rate': 2.142237484185794e-05, 'epoch': 0.57}
{'loss': 0.4572, 'learning_rate': 2.1419663835170793e-05, 'epoch': 0.57}
{'loss': 1.1811, 'learning_rate': 2.1416952828483644e-05, 'epoch': 0.57}
{'loss': 0.5321, 'learning_rate': 2.1414241821796493e-05, 'epoch': 0.57}
{'loss': 1.3098, 'learning_rate': 2.1411530815109345e-05, 'epoch': 0.57}
{'loss': 1.1535, 'learning_rate': 2.1408819808422197e-05, 'epoch': 0.57}
{'loss': 1.1779, 'learning_rate': 2.1406108801735045e-05, 'epoch': 0.57}
{'loss': 0.8619, 'learning_rate': 2.1403397795047897e-05, 'epoch': 0.57}
{'loss': 1.0569, 'learning_rate': 2.1400686788360745e-05, 'epoch': 0.57}
{'loss': 0.9686, 'learning_rate': 2.1397975781673594e-05, 'epoch': 0.57}
{'loss': 1.1947, 'learning_rate': 2.1395264774986446e-05, 'epoch': 0.57}
{'loss': 1.0008, 'learning_rate': 2.1392553768299294e-05, 'epoch': 0.57}
{'loss': 0.9364, 'learning_rate': 2.1389842761612146e-05, 'epoch': 0.57}
{'loss': 1.0304, 'learning_rate': 2.1387131754924998e-05, 'epoch': 0.57}
{'loss': 1.079, 'learning_rate': 2.1384420748237846e-05, 'epoch': 0.57}
{'loss': 0.8914, 'learning_rate': 2.1381709741550698e-05, 'epoch': 0.57}
{'loss': 1.0938, 'learning_rate': 2.1378998734863546e-05, 'epoch': 0.57}
{'loss': 0.813, 'learning_rate': 2.1376287728176395e-05, 'epoch': 0.57}
{'loss': 1.2219, 'learning_rate': 2.1373576721489247e-05, 'epoch': 0.58}
{'loss': 1.5664, 'learning_rate': 2.13708657148021e-05, 'epoch': 0.58}
{'loss': 1.481, 'learning_rate': 2.1368154708114947e-05, 'epoch': 0.58}
{'loss': 1.4211, 'learning_rate': 2.13654437014278e-05, 'epoch': 0.58}
{'loss': 1.6001, 'learning_rate': 2.1362732694740647e-05, 'epoch': 0.58}
{'loss': 0.7866, 'learning_rate': 2.13600216880535e-05, 'epoch': 0.58}
{'loss': 0.5483, 'learning_rate': 2.1357310681366347e-05, 'epoch': 0.58}
{'loss': 1.4259, 'learning_rate': 2.1354599674679196e-05, 'epoch': 0.58}
{'loss': 0.6448, 'learning_rate': 2.1351888667992048e-05, 'epoch': 0.58}
{'loss': 0.6042, 'learning_rate': 2.13491776613049e-05, 'epoch': 0.58}
{'loss': 1.1506, 'learning_rate': 2.1346466654617748e-05, 'epoch': 0.58}
{'loss': 1.782, 'learning_rate': 2.13437556479306e-05, 'epoch': 0.58}
{'loss': 1.5897, 'learning_rate': 2.134104464124345e-05, 'epoch': 0.58}
{'loss': 1.5026, 'learning_rate': 2.13383336345563e-05, 'epoch': 0.58}
{'loss': 0.6999, 'learning_rate': 2.133562262786915e-05, 'epoch': 0.58}
{'loss': 0.7414, 'learning_rate': 2.1332911621181997e-05, 'epoch': 0.58}
{'loss': 0.7156, 'learning_rate': 2.133020061449485e-05, 'epoch': 0.58}
{'loss': 0.9523, 'learning_rate': 2.13274896078077e-05, 'epoch': 0.58}
{'loss': 0.839, 'learning_rate': 2.132477860112055e-05, 'epoch': 0.58}
{'loss': 0.6559, 'learning_rate': 2.13220675944334e-05, 'epoch': 0.58}
{'loss': 0.7158, 'learning_rate': 2.1319356587746253e-05, 'epoch': 0.58}
{'loss': 1.2256, 'learning_rate': 2.13166455810591e-05, 'epoch': 0.58}
{'loss': 1.1799, 'learning_rate': 2.131393457437195e-05, 'epoch': 0.58}
{'loss': 1.4566, 'learning_rate': 2.13112235676848e-05, 'epoch': 0.58}
{'loss': 1.11, 'learning_rate': 2.130851256099765e-05, 'epoch': 0.58}
{'loss': 0.9933, 'learning_rate': 2.13058015543105e-05, 'epoch': 0.58}
{'loss': 0.5365, 'learning_rate': 2.130309054762335e-05, 'epoch': 0.58}
{'loss': 1.9083, 'learning_rate': 2.1300379540936202e-05, 'epoch': 0.58}
{'loss': 1.2911, 'learning_rate': 2.1297668534249054e-05, 'epoch': 0.58}
{'loss': 0.5806, 'learning_rate': 2.1294957527561902e-05, 'epoch': 0.58}
{'loss': 1.1521, 'learning_rate': 2.129224652087475e-05, 'epoch': 0.58}
{'loss': 0.7978, 'learning_rate': 2.1289535514187602e-05, 'epoch': 0.58}
{'loss': 0.4929, 'learning_rate': 2.128682450750045e-05, 'epoch': 0.58}
{'loss': 0.9789, 'learning_rate': 2.1284113500813303e-05, 'epoch': 0.58}
{'loss': 0.6801, 'learning_rate': 2.1281402494126155e-05, 'epoch': 0.58}
{'loss': 0.8488, 'learning_rate': 2.1278691487439003e-05, 'epoch': 0.58}
{'loss': 0.9293, 'learning_rate': 2.1275980480751855e-05, 'epoch': 0.58}
{'loss': 2.012, 'learning_rate': 2.12732694740647e-05, 'epoch': 0.58}
{'loss': 1.565, 'learning_rate': 2.1270558467377552e-05, 'epoch': 0.58}
{'loss': 0.9762, 'learning_rate': 2.1267847460690404e-05, 'epoch': 0.58}
{'loss': 0.6194, 'learning_rate': 2.1265136454003252e-05, 'epoch': 0.58}
{'loss': 0.8901, 'learning_rate': 2.1262425447316104e-05, 'epoch': 0.58}
{'loss': 1.4618, 'learning_rate': 2.1259714440628956e-05, 'epoch': 0.58}
{'loss': 1.0463, 'learning_rate': 2.1257003433941804e-05, 'epoch': 0.58}
{'loss': 1.1777, 'learning_rate': 2.1254292427254656e-05, 'epoch': 0.58}
{'loss': 1.0263, 'learning_rate': 2.1251581420567504e-05, 'epoch': 0.58}
{'loss': 1.8811, 'learning_rate': 2.1248870413880353e-05, 'epoch': 0.58}
{'loss': 1.9334, 'learning_rate': 2.1246159407193205e-05, 'epoch': 0.58}
{'loss': 1.0355, 'learning_rate': 2.1243448400506053e-05, 'epoch': 0.58}
{'loss': 0.6356, 'learning_rate': 2.1240737393818905e-05, 'epoch': 0.58}
{'loss': 0.9367, 'learning_rate': 2.1238026387131757e-05, 'epoch': 0.58}
{'loss': 1.1926, 'learning_rate': 2.1235315380444605e-05, 'epoch': 0.58}
{'loss': 1.218, 'learning_rate': 2.1232604373757457e-05, 'epoch': 0.58}
{'loss': 1.5409, 'learning_rate': 2.1229893367070305e-05, 'epoch': 0.58}
{'loss': 1.4854, 'learning_rate': 2.1227182360383154e-05, 'epoch': 0.58}
{'loss': 0.9461, 'learning_rate': 2.1224471353696006e-05, 'epoch': 0.59}
{'loss': 0.9321, 'learning_rate': 2.1221760347008858e-05, 'epoch': 0.59}
{'loss': 1.4536, 'learning_rate': 2.1219049340321706e-05, 'epoch': 0.59}
{'loss': 1.0371, 'learning_rate': 2.1216338333634558e-05, 'epoch': 0.59}
{'loss': 1.493, 'learning_rate': 2.121362732694741e-05, 'epoch': 0.59}
{'loss': 0.9621, 'learning_rate': 2.1210916320260258e-05, 'epoch': 0.59}
{'loss': 1.3227, 'learning_rate': 2.1208205313573106e-05, 'epoch': 0.59}
{'loss': 1.3034, 'learning_rate': 2.1205494306885955e-05, 'epoch': 0.59}
{'loss': 1.0614, 'learning_rate': 2.1202783300198807e-05, 'epoch': 0.59}
{'loss': 1.4969, 'learning_rate': 2.120007229351166e-05, 'epoch': 0.59}
{'loss': 1.2753, 'learning_rate': 2.1197361286824507e-05, 'epoch': 0.59}
{'loss': 1.1021, 'learning_rate': 2.119465028013736e-05, 'epoch': 0.59}
{'loss': 1.0957, 'learning_rate': 2.119193927345021e-05, 'epoch': 0.59}
{'loss': 0.8463, 'learning_rate': 2.118922826676306e-05, 'epoch': 0.59}
{'loss': 1.2886, 'learning_rate': 2.1186517260075908e-05, 'epoch': 0.59}
{'loss': 1.596, 'learning_rate': 2.118380625338876e-05, 'epoch': 0.59}
{'loss': 1.2522, 'learning_rate': 2.1181095246701608e-05, 'epoch': 0.59}
{'loss': 1.7282, 'learning_rate': 2.117838424001446e-05, 'epoch': 0.59}
{'loss': 0.9257, 'learning_rate': 2.1175673233327308e-05, 'epoch': 0.59}
{'loss': 0.7881, 'learning_rate': 2.117296222664016e-05, 'epoch': 0.59}
{'loss': 0.917, 'learning_rate': 2.1170251219953012e-05, 'epoch': 0.59}
{'loss': 0.8564, 'learning_rate': 2.116754021326586e-05, 'epoch': 0.59}
{'loss': 0.9394, 'learning_rate': 2.116482920657871e-05, 'epoch': 0.59}
{'loss': 0.8649, 'learning_rate': 2.116211819989156e-05, 'epoch': 0.59}
{'loss': 1.209, 'learning_rate': 2.115940719320441e-05, 'epoch': 0.59}
{'loss': 0.9743, 'learning_rate': 2.115669618651726e-05, 'epoch': 0.59}
{'loss': 1.2655, 'learning_rate': 2.1153985179830113e-05, 'epoch': 0.59}

 29%|██▉       | 3264/11066 [11:58<27:42,  4.69it/s]
 30%|██▉       | 3265/11066 [11:58<27:49,  4.67it/s]
                                                    

 30%|██▉       | 3265/11066 [11:58<27:49,  4.67it/s]
 30%|██▉       | 3266/11066 [11:58<27:40,  4.70it/s]
                                                    

 30%|██▉       | 3266/11066 [11:58<27:40,  4.70it/s]
 30%|██▉       | 3267/11066 [11:58<27:36,  4.71it/s]
                                                    

 30%|██▉       | 3267/11066 [11:58<27:36,  4.71it/s]
 30%|██▉       | 3268/11066 [11:59<27:45,  4.68it/s]
                                                    

 30%|██▉       | 3268/11066 [11:59<27:45,  4.68it/s]
 30%|██▉       | 3269/11066 [11:59<28:08,  4.62it/s]
                                                    

 30%|██▉       | 3269/11066 [11:59<28:08,  4.62it/s]
 30%|██▉       | 3270/11066 [11:59<28:30,  4.56it/s]
                                                    

 30%|██▉       | 3270/11066 [11:59<28:30,  4.56it/s]
 30%|██▉       | 3271/11066 [11:59<28:46,  4.51it/s]
                                                    

 30%|██▉       | 3271/11066 [11:59<28:46,  4.51it/s]
 30%|██▉       | 3272/11066 [11:59<28:17,  4.59it/s]
                                                    

 30%|██▉       | 3272/11066 [11:59<28:17,  4.59it/s]
 30%|██▉       | 3273/11066 [12:00<28:27,  4.56it/s]
                                                    

 30%|██▉       | 3273/11066 [12:00<28:27,  4.56it/s]
 30%|██▉       | 3274/11066 [12:00<28:24,  4.57it/s]
                                                    

 30%|██▉       | 3274/11066 [12:00<28:24,  4.57it/s]
 30%|██▉       | 3275/11066 [12:00<28:14,  4.60it/s]
                                                    

 30%|██▉       | 3275/11066 [12:00<28:14,  4.60it/s]
 30%|██▉       | 3276/11066 [12:00<28:03,  4.63it/s]
                                                    

 30%|██▉       | 3276/11066 [12:00<28:03,  4.63it/s]
 30%|██▉       | 3277/11066 [12:01<27:55,  4.65it/s]
                                                    

 30%|██▉       | 3277/11066 [12:01<27:55,  4.65it/s]
 30%|██▉       | 3278/11066 [12:01<28:00,  4.63it/s]
                                                    

 30%|██▉       | 3278/11066 [12:01<28:00,  4.63it/s]
 30%|██▉       | 3279/11066 [12:01<27:47,  4.67it/s]
                                                    

 30%|██▉       | 3279/11066 [12:01<27:47,  4.67it/s]
 30%|██▉       | 3280/11066 [12:01<27:36,  4.70it/s]
                                                    

 30%|██▉       | 3280/11066 [12:01<27:36,  4.70it/s]
 30%|██▉       | 3281/11066 [12:01<27:37,  4.70it/s]
                                                    

 30%|██▉       | 3281/11066 [12:01<27:37,  4.70it/s]
 30%|██▉       | 3282/11066 [12:02<27:36,  4.70it/s]
                                                    

 30%|██▉       | 3282/11066 [12:02<27:36,  4.70it/s]
 30%|██▉       | 3283/11066 [12:02<27:34,  4.70it/s]
                                                    

 30%|██▉       | 3283/11066 [12:02<27:34,  4.70it/s]
 30%|██▉       | 3284/11066 [12:02<28:00,  4.63it/s]
                                                    

 30%|██▉       | 3284/11066 [12:02<28:00,  4.63it/s]
 30%|██▉       | 3285/11066 [12:02<28:18,  4.58it/s]
                                                    

 30%|██▉       | 3285/11066 [12:02<28:18,  4.58it/s]
 30%|██▉       | 3286/11066 [12:02<28:31,  4.55it/s]
                                                    

 30%|██▉       | 3286/11066 [12:02<28:31,  4.55it/s]
 30%|██▉       | 3287/11066 [12:03<28:38,  4.53it/s]
                                                    

 30%|██▉       | 3287/11066 [12:03<28:38,  4.53it/s]
 30%|██▉       | 3288/11066 [12:03<28:41,  4.52it/s]
                                                    

 30%|██▉       | 3288/11066 [12:03<28:41,  4.52it/s]
 30%|██▉       | 3289/11066 [12:03<28:43,  4.51it/s]
                                                    

 30%|██▉       | 3289/11066 [12:03<28:43,  4.51it/s]
 30%|██▉       | 3290/11066 [12:03<29:04,  4.46it/s]
                                                    

 30%|██▉       | 3290/11066 [12:03<29:04,  4.46it/s]
 30%|██▉       | 3291/11066 [12:04<28:55,  4.48it/s]
                                                    

 30%|██▉       | 3291/11066 [12:04<28:55,  4.48it/s]
 30%|██▉       | 3292/11066 [12:04<28:27,  4.55it/s]
                                                    

 30%|██▉       | 3292/11066 [12:04<28:27,  4.55it/s]
 30%|██▉       | 3293/11066 [12:04<28:40,  4.52it/s]
                                                    

 30%|██▉       | 3293/11066 [12:04<28:40,  4.52it/s]
 30%|██▉       | 3294/11066 [12:04<28:45,  4.50it/s]
                                                    

 30%|██▉       | 3294/11066 [12:04<28:45,  4.50it/s]
 30%|██▉       | 3295/11066 [12:04<28:47,  4.50it/s]
                                                    

 30%|██▉       | 3295/11066 [12:04<28:47,  4.50it/s]
 30%|██▉       | 3296/11066 [12:05<28:42,  4.51it/s]
                                                    

 30%|██▉       | 3296/11066 [12:05<28:42,  4.51it/s]
 30%|██▉       | 3297/11066 [12:05<28:46,  4.50it/s]
                                                    

 30%|██▉       | 3297/11066 [12:05<28:46,  4.50it/s]
 30%|██▉       | 3298/11066 [12:05<28:50,  4.49it/s]
                                                    

 30%|██▉       | 3298/11066 [12:05<28:50,  4.49it/s]
 30%|██▉       | 3299/11066 [12:05<28:48,  4.49it/s]
                                                    

 30%|██▉       | 3299/11066 [12:05<28:48,  4.49it/s]
 30%|██▉       | 3300/11066 [12:06<28:38,  4.52it/s]
                                                    

 30%|██▉       | 3300/11066 [12:06<28:38,  4.52it/s]
 30%|██▉       | 3301/11066 [12:06<28:25,  4.55it/s]
                                                    

 30%|██▉       | 3301/11066 [12:06<28:25,  4.55it/s]
 30%|██▉       | 3302/11066 [12:06<28:20,  4.57it/s]
                                                    

 30%|██▉       | 3302/11066 [12:06<28:20,  4.57it/s]
 30%|██▉       | 3303/11066 [12:06<28:07,  4.60it/s]
                                                    

 30%|██▉       | 3303/11066 [12:06<28:07,  4.60it/s]
 30%|██▉       | 3304/11066 [12:06<27:48,  4.65it/s]
                                                    

 30%|██▉       | 3304/11066 [12:06<27:48,  4.65it/s]
 30%|██▉       | 3305/11066 [12:07<27:54,  4.63it/s]
                                                    

 30%|██▉       | 3305/11066 [12:07<27:54,  4.63it/s]
 30%|██▉       | 3306/11066 [12:07<27:47,  4.65it/s]
                                                    

 30%|██▉       | 3306/11066 [12:07<27:47,  4.65it/s]
 30%|██▉       | 3307/11066 [12:07<28:06,  4.60it/s]
                                                    

 30%|██▉       | 3307/11066 [12:07<28:06,  4.60it/s]
 30%|██▉       | 3308/11066 [12:07<28:06,  4.60it/s]
                                                    

 30%|██▉       | 3308/11066 [12:07<28:06,  4.60it/s]
 30%|██▉       | 3309/11066 [12:08<28:24,  4.55it/s]
                                                    

 30%|██▉       | 3309/11066 [12:08<28:24,  4.55it/s]
 30%|██▉       | 3310/11066 [12:08<28:09,  4.59it/s]
                                                    

 30%|██▉       | 3310/11066 [12:08<28:09,  4.59it/s]
 30%|██▉       | 3311/11066 [12:08<28:23,  4.55it/s]
                                                    

 30%|██▉       | 3311/11066 [12:08<28:23,  4.55it/s]
 30%|██▉       | 3312/11066 [12:08<28:30,  4.53it/s]
                                                    

 30%|██▉       | 3312/11066 [12:08<28:30,  4.53it/s]
 30%|██▉       | 3313/11066 [12:08<28:34,  4.52it/s]
                                                    

 30%|██▉       | 3313/11066 [12:08<28:34,  4.52it/s]
 30%|██▉       | 3314/11066 [12:09<28:38,  4.51it/s]
                                                    

 30%|██▉       | 3314/11066 [12:09<28:38,  4.51it/s]
 30%|██▉       | 3315/11066 [12:09<28:17,  4.57it/s]
                                                    

 30%|██▉       | 3315/11066 [12:09<28:17,  4.57it/s]
 30%|██▉       | 3316/11066 [12:09<28:24,  4.55it/s]
                                                    

 30%|██▉       | 3316/11066 [12:09<28:24,  4.55it/s]
 30%|██▉       | 3317/11066 [12:09<28:06,  4.60it/s]
                                                    

 30%|██▉       | 3317/11066 [12:09<28:06,  4.60it/s]
 30%|██▉       | 3318/11066 [12:09<28:16,  4.57it/s]
                                                    

 30%|██▉       | 3318/11066 [12:09<28:16,  4.57it/s]
 30%|██▉       | 3319/11066 [12:10<28:00,  4.61it/s]
                                                    

 30%|██▉       | 3319/11066 [12:10<28:00,  4.61it/s]
 30%|███       | 3320/11066 [12:10<28:07,  4.59it/s]
                                                    

 30%|███       | 3320/11066 [12:10<28:07,  4.59it/s]
 30%|███       | 3321/11066 [12:10<28:19,  4.56it/s]
                                                    

 30%|███       | 3321/11066 [12:10<28:19,  4.56it/s]
 30%|███       | 3322/11066 [12:10<28:15,  4.57it/s]
                                                    

 30%|███       | 3322/11066 [12:10<28:15,  4.57it/s]
 30%|███       | 3323/11066 [12:11<28:02,  4.60it/s]
                                                    

 30%|███       | 3323/11066 [12:11<28:02,  4.60it/s]
 30%|███       | 3324/11066 [12:11<28:17,  4.56it/s]
                                                    

 30%|███       | 3324/11066 [12:11<28:17,  4.56it/s]
 30%|███       | 3325/11066 [12:11<28:13,  4.57it/s]
                                                    

 30%|███       | 3325/11066 [12:11<28:13,  4.57it/s]
 30%|███       | 3326/11066 [12:11<28:21,  4.55it/s]
                                                    

 30%|███       | 3326/11066 [12:11<28:21,  4.55it/s]
 30%|███       | 3327/11066 [12:11<28:13,  4.57it/s]
                                                    

 30%|███       | 3327/11066 [12:11<28:13,  4.57it/s]
 30%|███       | 3328/11066 [12:12<28:26,  4.54it/s]
                                                    

 30%|███       | 3328/11066 [12:12<28:26,  4.54it/s]
 30%|███       | 3329/11066 [12:12<28:37,  4.51it/s]
                                                    

 30%|███       | 3329/11066 [12:12<28:37,  4.51it/s]
 30%|███       | 3330/11066 [12:12<28:40,  4.50it/s]
                                                    

 30%|███       | 3330/11066 [12:12<28:40,  4.50it/s]
 30%|███       | 3331/11066 [12:12<28:33,  4.51it/s]
                                                    

 30%|███       | 3331/11066 [12:12<28:33,  4.51it/s]
 30%|███       | 3332/11066 [12:13<28:41,  4.49it/s]
                                                    

 30%|███       | 3332/11066 [12:13<28:41,  4.49it/s]
 30%|███       | 3333/11066 [12:13<28:24,  4.54it/s]
                                                    

 30%|███       | 3333/11066 [12:13<28:24,  4.54it/s]
 30%|███       | 3334/11066 [12:13<28:17,  4.55it/s]
                                                    

 30%|███       | 3334/11066 [12:13<28:17,  4.55it/s]
 30%|███       | 3335/11066 [12:13<28:26,  4.53it/s]
                                                    

 30%|███       | 3335/11066 [12:13<28:26,  4.53it/s]
 30%|███       | 3336/11066 [12:13<28:32,  4.51it/s]
                                                    

 30%|███       | 3336/11066 [12:13<28:32,  4.51it/s]
 30%|███       | 3337/11066 [12:14<28:36,  4.50it/s]
                                                    

 30%|███       | 3337/11066 [12:14<28:36,  4.50it/s]
 30%|███       | 3338/11066 [12:14<28:23,  4.54it/s]
                                                    

 30%|███       | 3338/11066 [12:14<28:23,  4.54it/s]
 30%|███       | 3339/11066 [12:14<28:35,  4.50it/s]
                                                    

 30%|███       | 3339/11066 [12:14<28:35,  4.50it/s]
 30%|███       | 3340/11066 [12:14<28:27,  4.53it/s]
                                                    

 30%|███       | 3340/11066 [12:14<28:27,  4.53it/s]
 30%|███       | 3341/11066 [12:15<28:13,  4.56it/s]
                                                    

 30%|███       | 3341/11066 [12:15<28:13,  4.56it/s]
 30%|███       | 3342/11066 [12:15<28:25,  4.53it/s]
                                                    

 30%|███       | 3342/11066 [12:15<28:25,  4.53it/s]
 30%|███       | 3343/11066 [12:15<28:16,  4.55it/s]
                                                    

 30%|███       | 3343/11066 [12:15<28:16,  4.55it/s]
 30%|███       | 3344/11066 [12:15<28:14,  4.56it/s]
                                                    

 30%|███       | 3344/11066 [12:15<28:14,  4.56it/s]
 30%|███       | 3345/11066 [12:15<28:08,  4.57it/s]
                                                    

 30%|███       | 3345/11066 [12:15<28:08,  4.57it/s]
 30%|███       | 3346/11066 [12:16<27:54,  4.61it/s]
                                                    

 30%|███       | 3346/11066 [12:16<27:54,  4.61it/s]
 30%|███       | 3347/11066 [12:16<27:44,  4.64it/s]
                                                    

 30%|███       | 3347/11066 [12:16<27:44,  4.64it/s]
 30%|███       | 3348/11066 [12:16<27:35,  4.66it/s]
                                                    

 30%|███       | 3348/11066 [12:16<27:35,  4.66it/s]
 30%|███       | 3349/11066 [12:16<27:56,  4.60it/s]
                                                    

 30%|███       | 3349/11066 [12:16<27:56,  4.60it/s]
 30%|███       | 3350/11066 [12:17<28:10,  4.56it/s]
                                                    

 30%|███       | 3350/11066 [12:17<28:10,  4.56it/s]
 30%|███       | 3351/11066 [12:17<28:17,  4.54it/s]
                                                    

 30%|███       | 3351/11066 [12:17<28:17,  4.54it/s]
 30%|███       | 3352/11066 [12:17<28:22,  4.53it/s]
                                                    

 30%|███       | 3352/11066 [12:17<28:22,  4.53it/s]
 30%|███       | 3353/11066 [12:17<28:24,  4.53it/s]
                                                    

 30%|███       | 3353/11066 [12:17<28:24,  4.53it/s]
 30%|███       | 3354/11066 [12:17<28:27,  4.52it/s]
                                                    

 30%|███       | 3354/11066 [12:17<28:27,  4.52it/s]
 30%|███       | 3355/11066 [12:18<28:30,  4.51it/s]
                                                    

 30%|███       | 3355/11066 [12:18<28:30,  4.51it/s]
 30%|███       | 3356/11066 [12:18<28:34,  4.50it/s]
                                                    

 30%|███       | 3356/11066 [12:18<28:34,  4.50it/s]
 30%|███       | 3357/11066 [12:18<28:33,  4.50it/s]
                                                    

 30%|███       | 3357/11066 [12:18<28:33,  4.50it/s]
 30%|███       | 3358/11066 [12:18<28:33,  4.50it/s]
                                                    

 30%|███       | 3358/11066 [12:18<28:33,  4.50it/s]
 30%|███       | 3359/11066 [12:19<28:31,  4.50it/s]
                                                    

 30%|███       | 3359/11066 [12:19<28:31,  4.50it/s]
 30%|███       | 3360/11066 [12:19<28:32,  4.50it/s]
                                                    

 30%|███       | 3360/11066 [12:19<28:32,  4.50it/s]
 30%|███       | 3361/11066 [12:19<28:32,  4.50it/s]
                                                    

 30%|███       | 3361/11066 [12:19<28:32,  4.50it/s]
 30%|███       | 3362/11066 [12:19<28:32,  4.50it/s]
                                                    

 30%|███       | 3362/11066 [12:19<28:32,  4.50it/s]
 30%|███       | 3363/11066 [12:19<28:31,  4.50it/s]
                                                    

 30%|███       | 3363/11066 [12:19<28:31,  4.50it/s]
 30%|███       | 3364/11066 [12:20<28:31,  4.50it/s]
                                                    

 30%|███       | 3364/11066 [12:20<28:31,  4.50it/s]
 30%|███       | 3365/11066 [12:20<28:31,  4.50it/s]
                                                    

 30%|███       | 3365/11066 [12:20<28:31,  4.50it/s]
 30%|███       | 3366/11066 [12:20<28:30,  4.50it/s]
                                                    

 30%|███       | 3366/11066 [12:20<28:30,  4.50it/s]
 30%|███       | 3367/11066 [12:20<28:29,  4.50it/s]
                                                    

 30%|███       | 3367/11066 [12:20<28:29,  4.50it/s]
 30%|███       | 3368/11066 [12:21<28:30,  4.50it/s]
                                                    

 30%|███       | 3368/11066 [12:21<28:30,  4.50it/s]
 30%|███       | 3369/11066 [12:21<28:30,  4.50it/s]
                                                    

 30%|███       | 3369/11066 [12:21<28:30,  4.50it/s]
 30%|███       | 3370/11066 [12:21<29:10,  4.40it/s]
                                                    

 30%|███       | 3370/11066 [12:21<29:10,  4.40it/s]
 30%|███       | 3371/11066 [12:21<29:02,  4.42it/s]
                                                    

 30%|███       | 3371/11066 [12:21<29:02,  4.42it/s]
 30%|███       | 3372/11066 [12:21<29:12,  4.39it/s]
                                                    

 30%|███       | 3372/11066 [12:21<29:12,  4.39it/s]
 30%|███       | 3373/11066 [12:22<29:02,  4.41it/s]
                                                    

 30%|███       | 3373/11066 [12:22<29:02,  4.41it/s]
 30%|███       | 3374/11066 [12:22<28:53,  4.44it/s]
                                                    

 30%|███       | 3374/11066 [12:22<28:53,  4.44it/s]
 30%|███       | 3375/11066 [12:22<28:47,  4.45it/s]
                                                    

 30%|███       | 3375/11066 [12:22<28:47,  4.45it/s]
 31%|███       | 3376/11066 [12:22<28:41,  4.47it/s]
                                                    

 31%|███       | 3376/11066 [12:22<28:41,  4.47it/s]
 31%|███       | 3377/11066 [12:23<28:35,  4.48it/s]
                                                    
{'loss': 0.3595, 'learning_rate': 2.115127417314296e-05, 'epoch': 0.59}
{'loss': 1.1327, 'learning_rate': 2.1148563166455813e-05, 'epoch': 0.59}
{'loss': 1.075, 'learning_rate': 2.114585215976866e-05, 'epoch': 0.59}
{'loss': 0.7423, 'learning_rate': 2.114314115308151e-05, 'epoch': 0.59}
{'loss': 1.4075, 'learning_rate': 2.114043014639436e-05, 'epoch': 0.59}
{'loss': 1.0945, 'learning_rate': 2.113771913970721e-05, 'epoch': 0.59}
{'loss': 1.0845, 'learning_rate': 2.1135008133020062e-05, 'epoch': 0.59}
{'loss': 1.0856, 'learning_rate': 2.1132297126332914e-05, 'epoch': 0.59}
{'loss': 1.4097, 'learning_rate': 2.1129586119645762e-05, 'epoch': 0.59}
{'loss': 1.7163, 'learning_rate': 2.1126875112958614e-05, 'epoch': 0.59}
{'loss': 1.1001, 'learning_rate': 2.1124164106271466e-05, 'epoch': 0.59}
{'loss': 0.8026, 'learning_rate': 2.112145309958431e-05, 'epoch': 0.59}
{'loss': 1.0456, 'learning_rate': 2.1118742092897163e-05, 'epoch': 0.59}
{'loss': 0.7903, 'learning_rate': 2.111603108621001e-05, 'epoch': 0.59}
{'loss': 0.748, 'learning_rate': 2.1113320079522863e-05, 'epoch': 0.59}
{'loss': 1.6543, 'learning_rate': 2.1110609072835715e-05, 'epoch': 0.59}
{'loss': 1.4999, 'learning_rate': 2.1107898066148563e-05, 'epoch': 0.59}
{'loss': 1.4714, 'learning_rate': 2.1105187059461415e-05, 'epoch': 0.59}
{'loss': 0.7203, 'learning_rate': 2.1102476052774267e-05, 'epoch': 0.59}
{'loss': 0.4269, 'learning_rate': 2.1099765046087112e-05, 'epoch': 0.59}
{'loss': 1.5728, 'learning_rate': 2.1097054039399964e-05, 'epoch': 0.59}
{'loss': 1.2004, 'learning_rate': 2.1094343032712816e-05, 'epoch': 0.59}
{'loss': 0.805, 'learning_rate': 2.1091632026025664e-05, 'epoch': 0.59}
{'loss': 1.1509, 'learning_rate': 2.1088921019338516e-05, 'epoch': 0.59}
{'loss': 1.0825, 'learning_rate': 2.1086210012651364e-05, 'epoch': 0.59}
{'loss': 1.6732, 'learning_rate': 2.1083499005964216e-05, 'epoch': 0.59}
{'loss': 0.9405, 'learning_rate': 2.1080787999277068e-05, 'epoch': 0.59}
{'loss': 0.7807, 'learning_rate': 2.1078076992589913e-05, 'epoch': 0.59}
{'loss': 0.6019, 'learning_rate': 2.1075365985902765e-05, 'epoch': 0.59}
{'loss': 0.9395, 'learning_rate': 2.1072654979215617e-05, 'epoch': 0.6}
{'loss': 0.9578, 'learning_rate': 2.1069943972528465e-05, 'epoch': 0.6}
{'loss': 1.1064, 'learning_rate': 2.1067232965841317e-05, 'epoch': 0.6}
{'loss': 0.541, 'learning_rate': 2.106452195915417e-05, 'epoch': 0.6}
{'loss': 1.5081, 'learning_rate': 2.1061810952467017e-05, 'epoch': 0.6}
{'loss': 0.5629, 'learning_rate': 2.105909994577987e-05, 'epoch': 0.6}
{'loss': 1.3447, 'learning_rate': 2.1056388939092714e-05, 'epoch': 0.6}
{'loss': 0.7994, 'learning_rate': 2.1053677932405566e-05, 'epoch': 0.6}
{'loss': 1.4431, 'learning_rate': 2.1050966925718418e-05, 'epoch': 0.6}
{'loss': 0.712, 'learning_rate': 2.1048255919031266e-05, 'epoch': 0.6}
{'loss': 1.2973, 'learning_rate': 2.1045544912344118e-05, 'epoch': 0.6}
{'loss': 0.9633, 'learning_rate': 2.104283390565697e-05, 'epoch': 0.6}
{'loss': 0.8663, 'learning_rate': 2.1040122898969818e-05, 'epoch': 0.6}
{'loss': 0.8544, 'learning_rate': 2.103741189228267e-05, 'epoch': 0.6}
{'loss': 0.9926, 'learning_rate': 2.103470088559552e-05, 'epoch': 0.6}
{'loss': 0.911, 'learning_rate': 2.1031989878908367e-05, 'epoch': 0.6}
{'loss': 1.6048, 'learning_rate': 2.102927887222122e-05, 'epoch': 0.6}
{'loss': 1.2664, 'learning_rate': 2.1026567865534067e-05, 'epoch': 0.6}
{'loss': 0.7902, 'learning_rate': 2.102385685884692e-05, 'epoch': 0.6}
{'loss': 1.0517, 'learning_rate': 2.102114585215977e-05, 'epoch': 0.6}
{'loss': 1.2808, 'learning_rate': 2.101843484547262e-05, 'epoch': 0.6}
{'loss': 1.3929, 'learning_rate': 2.101572383878547e-05, 'epoch': 0.6}
{'loss': 0.6119, 'learning_rate': 2.101301283209832e-05, 'epoch': 0.6}
{'loss': 0.6693, 'learning_rate': 2.1010301825411168e-05, 'epoch': 0.6}
{'loss': 1.8007, 'learning_rate': 2.100759081872402e-05, 'epoch': 0.6}
{'loss': 0.9462, 'learning_rate': 2.100487981203687e-05, 'epoch': 0.6}
{'loss': 0.7892, 'learning_rate': 2.100216880534972e-05, 'epoch': 0.6}
{'loss': 0.9151, 'learning_rate': 2.0999457798662572e-05, 'epoch': 0.6}
{'loss': 1.3854, 'learning_rate': 2.099674679197542e-05, 'epoch': 0.6}
{'loss': 0.6304, 'learning_rate': 2.0994035785288272e-05, 'epoch': 0.6}
{'loss': 1.0213, 'learning_rate': 2.099132477860112e-05, 'epoch': 0.6}
{'loss': 1.0603, 'learning_rate': 2.098861377191397e-05, 'epoch': 0.6}
{'loss': 1.5936, 'learning_rate': 2.098590276522682e-05, 'epoch': 0.6}
{'loss': 1.1177, 'learning_rate': 2.0983191758539673e-05, 'epoch': 0.6}
{'loss': 0.9335, 'learning_rate': 2.098048075185252e-05, 'epoch': 0.6}
{'loss': 0.9477, 'learning_rate': 2.0977769745165373e-05, 'epoch': 0.6}
{'loss': 0.7928, 'learning_rate': 2.0975058738478225e-05, 'epoch': 0.6}
{'loss': 1.4592, 'learning_rate': 2.0972347731791073e-05, 'epoch': 0.6}
{'loss': 0.5197, 'learning_rate': 2.0969636725103922e-05, 'epoch': 0.6}
{'loss': 0.6507, 'learning_rate': 2.096692571841677e-05, 'epoch': 0.6}
{'loss': 1.019, 'learning_rate': 2.0964214711729622e-05, 'epoch': 0.6}
{'loss': 0.745, 'learning_rate': 2.0961503705042474e-05, 'epoch': 0.6}
{'loss': 1.224, 'learning_rate': 2.0958792698355322e-05, 'epoch': 0.6}
{'loss': 1.4343, 'learning_rate': 2.0956081691668174e-05, 'epoch': 0.6}
{'loss': 1.378, 'learning_rate': 2.0953370684981026e-05, 'epoch': 0.6}
{'loss': 1.1295, 'learning_rate': 2.0950659678293874e-05, 'epoch': 0.6}
{'loss': 1.4274, 'learning_rate': 2.0947948671606723e-05, 'epoch': 0.6}
{'loss': 0.9234, 'learning_rate': 2.0945237664919575e-05, 'epoch': 0.6}
{'loss': 1.4343, 'learning_rate': 2.0942526658232423e-05, 'epoch': 0.6}
{'loss': 1.6079, 'learning_rate': 2.0939815651545275e-05, 'epoch': 0.6}
{'loss': 1.2017, 'learning_rate': 2.0937104644858123e-05, 'epoch': 0.6}
{'loss': 0.7711, 'learning_rate': 2.0934393638170975e-05, 'epoch': 0.6}
{'loss': 1.7588, 'learning_rate': 2.0931682631483827e-05, 'epoch': 0.6}
{'loss': 0.7621, 'learning_rate': 2.0928971624796672e-05, 'epoch': 0.6}
{'loss': 1.2343, 'learning_rate': 2.0926260618109524e-05, 'epoch': 0.6}
{'loss': 1.5275, 'learning_rate': 2.0923549611422376e-05, 'epoch': 0.61}
{'loss': 0.7572, 'learning_rate': 2.0920838604735224e-05, 'epoch': 0.61}
{'loss': 0.8793, 'learning_rate': 2.0918127598048076e-05, 'epoch': 0.61}
{'loss': 1.0444, 'learning_rate': 2.0915416591360928e-05, 'epoch': 0.61}
{'loss': 1.3012, 'learning_rate': 2.0912705584673776e-05, 'epoch': 0.61}
{'loss': 0.7841, 'learning_rate': 2.0909994577986628e-05, 'epoch': 0.61}
{'loss': 0.9415, 'learning_rate': 2.0907283571299473e-05, 'epoch': 0.61}
{'loss': 1.0005, 'learning_rate': 2.0904572564612325e-05, 'epoch': 0.61}
{'loss': 1.366, 'learning_rate': 2.0901861557925177e-05, 'epoch': 0.61}
{'loss': 0.9817, 'learning_rate': 2.0899150551238025e-05, 'epoch': 0.61}
{'loss': 1.0284, 'learning_rate': 2.0896439544550877e-05, 'epoch': 0.61}
{'loss': 0.8626, 'learning_rate': 2.089372853786373e-05, 'epoch': 0.61}
{'loss': 0.7846, 'learning_rate': 2.0891017531176577e-05, 'epoch': 0.61}
{'loss': 1.0374, 'learning_rate': 2.088830652448943e-05, 'epoch': 0.61}
{'loss': 1.3026, 'learning_rate': 2.0885595517802278e-05, 'epoch': 0.61}
{'loss': 1.4062, 'learning_rate': 2.0882884511115126e-05, 'epoch': 0.61}
{'loss': 1.1251, 'learning_rate': 2.0880173504427978e-05, 'epoch': 0.61}
{'loss': 1.151, 'learning_rate': 2.0877462497740826e-05, 'epoch': 0.61}
{'loss': 0.8404, 'learning_rate': 2.0874751491053678e-05, 'epoch': 0.61}
{'loss': 1.1557, 'learning_rate': 2.087204048436653e-05, 'epoch': 0.61}
{'loss': 0.8615, 'learning_rate': 2.086932947767938e-05, 'epoch': 0.61}
{'loss': 1.0396, 'learning_rate': 2.086661847099223e-05, 'epoch': 0.61}
{'loss': 0.9555, 'learning_rate': 2.086390746430508e-05, 'epoch': 0.61}
{'loss': 0.5523, 'learning_rate': 2.0861196457617927e-05, 'epoch': 0.61}
{'loss': 1.1664, 'learning_rate': 2.085848545093078e-05, 'epoch': 0.61}
{'loss': 1.1253, 'learning_rate': 2.085577444424363e-05, 'epoch': 0.61}
{'loss': 1.7582, 'learning_rate': 2.085306343755648e-05, 'epoch': 0.61}
{'loss': 0.755, 'learning_rate': 2.085035243086933e-05, 'epoch': 0.61}
{'loss': 0.8542, 'learning_rate': 2.084764142418218e-05, 'epoch': 0.61}

 31%|███       | 3377/11066 [12:23<28:35,  4.48it/s]
 31%|███       | 3378/11066 [12:23<28:33,  4.49it/s]
                                                    

 31%|███       | 3378/11066 [12:23<28:33,  4.49it/s]
 31%|███       | 3379/11066 [12:23<28:30,  4.49it/s]
                                                    

 31%|███       | 3379/11066 [12:23<28:30,  4.49it/s]
 31%|███       | 3380/11066 [12:23<28:29,  4.50it/s]
                                                    

 31%|███       | 3380/11066 [12:23<28:29,  4.50it/s]
 31%|███       | 3381/11066 [12:23<28:27,  4.50it/s]
                                                    

 31%|███       | 3381/11066 [12:23<28:27,  4.50it/s]
 31%|███       | 3382/11066 [12:24<28:27,  4.50it/s]
                                                    

 31%|███       | 3382/11066 [12:24<28:27,  4.50it/s]
 31%|███       | 3383/11066 [12:24<27:59,  4.57it/s]
                                                    

 31%|███       | 3383/11066 [12:24<27:59,  4.57it/s]
 31%|███       | 3384/11066 [12:24<28:00,  4.57it/s]
                                                    

 31%|███       | 3384/11066 [12:24<28:00,  4.57it/s]
 31%|███       | 3385/11066 [12:24<27:53,  4.59it/s]
                                                    

 31%|███       | 3385/11066 [12:24<27:53,  4.59it/s]
 31%|███       | 3386/11066 [12:25<27:52,  4.59it/s]
                                                    

 31%|███       | 3386/11066 [12:25<27:52,  4.59it/s]
 31%|███       | 3387/11066 [12:25<27:32,  4.65it/s]
                                                    

 31%|███       | 3387/11066 [12:25<27:32,  4.65it/s]
 31%|███       | 3388/11066 [12:25<27:50,  4.59it/s]
                                                    

 31%|███       | 3388/11066 [12:25<27:50,  4.59it/s]
 31%|███       | 3389/11066 [12:25<27:48,  4.60it/s]
                                                    

 31%|███       | 3389/11066 [12:25<27:48,  4.60it/s]
 31%|███       | 3390/11066 [12:25<27:30,  4.65it/s]
                                                    

 31%|███       | 3390/11066 [12:25<27:30,  4.65it/s]
 31%|███       | 3391/11066 [12:26<27:24,  4.67it/s]
                                                    

 31%|███       | 3391/11066 [12:26<27:24,  4.67it/s]
 31%|███       | 3392/11066 [12:26<27:19,  4.68it/s]
                                                    

 31%|███       | 3392/11066 [12:26<27:19,  4.68it/s]
 31%|███       | 3393/11066 [12:26<27:29,  4.65it/s]
                                                    

 31%|███       | 3393/11066 [12:26<27:29,  4.65it/s]
 31%|███       | 3394/11066 [12:26<27:35,  4.63it/s]
                                                    

 31%|███       | 3394/11066 [12:26<27:35,  4.63it/s]
 31%|███       | 3395/11066 [12:26<27:27,  4.66it/s]
                                                    

 31%|███       | 3395/11066 [12:26<27:27,  4.66it/s]
 31%|███       | 3396/11066 [12:27<27:30,  4.65it/s]
                                                    

 31%|███       | 3396/11066 [12:27<27:30,  4.65it/s]
 31%|███       | 3397/11066 [12:27<27:22,  4.67it/s]
                                                    

 31%|███       | 3397/11066 [12:27<27:22,  4.67it/s]
 31%|███       | 3398/11066 [12:27<28:13,  4.53it/s]
                                                    

 31%|███       | 3398/11066 [12:27<28:13,  4.53it/s]
 31%|███       | 3399/11066 [12:27<27:56,  4.57it/s]
                                                    

 31%|███       | 3399/11066 [12:27<27:56,  4.57it/s]
 31%|███       | 3400/11066 [12:28<28:07,  4.54it/s]
                                                    

 31%|███       | 3400/11066 [12:28<28:07,  4.54it/s]
 31%|███       | 3401/11066 [12:28<27:49,  4.59it/s]
                                                    

 31%|███       | 3401/11066 [12:28<27:49,  4.59it/s]
 31%|███       | 3402/11066 [12:28<28:02,  4.55it/s]
                                                    

 31%|███       | 3402/11066 [12:28<28:02,  4.55it/s]
 31%|███       | 3403/11066 [12:28<28:10,  4.53it/s]
                                                    

 31%|███       | 3403/11066 [12:28<28:10,  4.53it/s]
 31%|███       | 3404/11066 [12:28<28:02,  4.55it/s]
                                                    

 31%|███       | 3404/11066 [12:28<28:02,  4.55it/s]
 31%|███       | 3405/11066 [12:29<27:58,  4.56it/s]
                                                    

 31%|███       | 3405/11066 [12:29<27:58,  4.56it/s]
 31%|███       | 3406/11066 [12:29<27:43,  4.61it/s]
                                                    

 31%|███       | 3406/11066 [12:29<27:43,  4.61it/s]
 31%|███       | 3407/11066 [12:29<27:56,  4.57it/s]
                                                    

 31%|███       | 3407/11066 [12:29<27:56,  4.57it/s]
 31%|███       | 3408/11066 [12:29<27:51,  4.58it/s]
                                                    

 31%|███       | 3408/11066 [12:29<27:51,  4.58it/s]
 31%|███       | 3409/11066 [12:30<28:06,  4.54it/s]
                                                    

 31%|███       | 3409/11066 [12:30<28:06,  4.54it/s]
 31%|███       | 3410/11066 [12:30<27:59,  4.56it/s]
                                                    

 31%|███       | 3410/11066 [12:30<27:59,  4.56it/s]
 31%|███       | 3411/11066 [12:30<28:07,  4.54it/s]
                                                    

 31%|███       | 3411/11066 [12:30<28:07,  4.54it/s]
 31%|███       | 3412/11066 [12:30<28:07,  4.54it/s]
                                                    

 31%|███       | 3412/11066 [12:30<28:07,  4.54it/s]
 31%|███       | 3413/11066 [12:30<27:47,  4.59it/s]
                                                    

 31%|███       | 3413/11066 [12:30<27:47,  4.59it/s]
 31%|███       | 3414/11066 [12:31<27:55,  4.57it/s]
                                                    

 31%|███       | 3414/11066 [12:31<27:55,  4.57it/s]
 31%|███       | 3415/11066 [12:31<27:49,  4.58it/s]
                                                    

 31%|███       | 3415/11066 [12:31<27:49,  4.58it/s]
 31%|███       | 3416/11066 [12:31<27:40,  4.61it/s]
                                                    

 31%|███       | 3416/11066 [12:31<27:40,  4.61it/s]
 31%|███       | 3417/11066 [12:31<27:57,  4.56it/s]
                                                    

 31%|███       | 3417/11066 [12:31<27:57,  4.56it/s]
 31%|███       | 3418/11066 [12:31<27:54,  4.57it/s]
                                                    

 31%|███       | 3418/11066 [12:31<27:54,  4.57it/s]
 31%|███       | 3419/11066 [12:32<27:34,  4.62it/s]
                                                    

 31%|███       | 3419/11066 [12:32<27:34,  4.62it/s]
 31%|███       | 3420/11066 [12:32<27:49,  4.58it/s]
                                                    

 31%|███       | 3420/11066 [12:32<27:49,  4.58it/s]
 31%|███       | 3421/11066 [12:32<27:55,  4.56it/s]
                                                    

 31%|███       | 3421/11066 [12:32<27:55,  4.56it/s]
 31%|███       | 3422/11066 [12:32<27:32,  4.62it/s]
                                                    

 31%|███       | 3422/11066 [12:32<27:32,  4.62it/s]
 31%|███       | 3423/11066 [12:33<27:48,  4.58it/s]
                                                    

 31%|███       | 3423/11066 [12:33<27:48,  4.58it/s]
 31%|███       | 3424/11066 [12:33<27:33,  4.62it/s]
                                                    

 31%|███       | 3424/11066 [12:33<27:33,  4.62it/s]
 31%|███       | 3425/11066 [12:33<27:46,  4.58it/s]
                                                    

 31%|███       | 3425/11066 [12:33<27:46,  4.58it/s]
 31%|███       | 3426/11066 [12:33<27:58,  4.55it/s]
                                                    

 31%|███       | 3426/11066 [12:33<27:58,  4.55it/s]
 31%|███       | 3427/11066 [12:33<27:40,  4.60it/s]
                                                    

 31%|███       | 3427/11066 [12:33<27:40,  4.60it/s]
 31%|███       | 3428/11066 [12:34<27:51,  4.57it/s]
                                                    

 31%|███       | 3428/11066 [12:34<27:51,  4.57it/s]
 31%|███       | 3429/11066 [12:34<27:56,  4.55it/s]
                                                    

 31%|███       | 3429/11066 [12:34<27:56,  4.55it/s]
 31%|███       | 3430/11066 [12:34<28:02,  4.54it/s]
                                                    

 31%|███       | 3430/11066 [12:34<28:02,  4.54it/s]
 31%|███       | 3431/11066 [12:34<27:46,  4.58it/s]
                                                    

 31%|███       | 3431/11066 [12:34<27:46,  4.58it/s]
 31%|███       | 3432/11066 [12:35<27:23,  4.65it/s]
                                                    

 31%|███       | 3432/11066 [12:35<27:23,  4.65it/s]
 31%|███       | 3433/11066 [12:35<27:42,  4.59it/s]
                                                    

 31%|███       | 3433/11066 [12:35<27:42,  4.59it/s]
 31%|███       | 3434/11066 [12:35<27:51,  4.56it/s]
                                                    

 31%|███       | 3434/11066 [12:35<27:51,  4.56it/s]
 31%|███       | 3435/11066 [12:35<27:58,  4.55it/s]
                                                    

 31%|███       | 3435/11066 [12:35<27:58,  4.55it/s]
 31%|███       | 3436/11066 [12:35<27:57,  4.55it/s]
                                                    

 31%|███       | 3436/11066 [12:35<27:57,  4.55it/s]
 31%|███       | 3437/11066 [12:36<27:54,  4.56it/s]
                                                    

 31%|███       | 3437/11066 [12:36<27:54,  4.56it/s]
 31%|███       | 3438/11066 [12:36<27:30,  4.62it/s]
                                                    

 31%|███       | 3438/11066 [12:36<27:30,  4.62it/s]
 31%|███       | 3439/11066 [12:36<27:44,  4.58it/s]
                                                    

 31%|███       | 3439/11066 [12:36<27:44,  4.58it/s]
 31%|███       | 3440/11066 [12:36<27:55,  4.55it/s]
                                                    

 31%|███       | 3440/11066 [12:36<27:55,  4.55it/s]
 31%|███       | 3441/11066 [12:37<28:00,  4.54it/s]
                                                    

 31%|███       | 3441/11066 [12:37<28:00,  4.54it/s]
 31%|███       | 3442/11066 [12:37<28:02,  4.53it/s]
                                                    

 31%|███       | 3442/11066 [12:37<28:02,  4.53it/s]
 31%|███       | 3443/11066 [12:37<28:04,  4.52it/s]
                                                    

 31%|███       | 3443/11066 [12:37<28:04,  4.52it/s]
 31%|███       | 3444/11066 [12:37<28:08,  4.51it/s]
                                                    

 31%|███       | 3444/11066 [12:37<28:08,  4.51it/s]
 31%|███       | 3445/11066 [12:37<27:59,  4.54it/s]
                                                    

 31%|███       | 3445/11066 [12:37<27:59,  4.54it/s]
 31%|███       | 3446/11066 [12:38<27:40,  4.59it/s]
                                                    

 31%|███       | 3446/11066 [12:38<27:40,  4.59it/s]
 31%|███       | 3447/11066 [12:38<27:24,  4.63it/s]
                                                    

 31%|███       | 3447/11066 [12:38<27:24,  4.63it/s]
 31%|███       | 3448/11066 [12:38<27:32,  4.61it/s]
                                                    

 31%|███       | 3448/11066 [12:38<27:32,  4.61it/s]
 31%|███       | 3449/11066 [12:38<27:20,  4.64it/s]
                                                    

 31%|███       | 3449/11066 [12:38<27:20,  4.64it/s]
 31%|███       | 3450/11066 [12:38<27:04,  4.69it/s]
                                                    

 31%|███       | 3450/11066 [12:38<27:04,  4.69it/s]
 31%|███       | 3451/11066 [12:39<27:28,  4.62it/s]
                                                    

 31%|███       | 3451/11066 [12:39<27:28,  4.62it/s]
 31%|███       | 3452/11066 [12:39<27:28,  4.62it/s]
                                                    

 31%|███       | 3452/11066 [12:39<27:28,  4.62it/s]
 31%|███       | 3453/11066 [12:39<27:22,  4.64it/s]
                                                    

 31%|███       | 3453/11066 [12:39<27:22,  4.64it/s]
 31%|███       | 3454/11066 [12:39<27:44,  4.57it/s]
                                                    

 31%|███       | 3454/11066 [12:39<27:44,  4.57it/s]
 31%|███       | 3455/11066 [12:40<27:52,  4.55it/s]
                                                    

 31%|███       | 3455/11066 [12:40<27:52,  4.55it/s]
 31%|███       | 3456/11066 [12:40<27:58,  4.53it/s]
                                                    

 31%|███       | 3456/11066 [12:40<27:58,  4.53it/s]
 31%|███       | 3457/11066 [12:40<28:02,  4.52it/s]
                                                    

 31%|███       | 3457/11066 [12:40<28:02,  4.52it/s]
 31%|███       | 3458/11066 [12:40<28:05,  4.51it/s]
                                                    

 31%|███       | 3458/11066 [12:40<28:05,  4.51it/s]
 31%|███▏      | 3459/11066 [12:40<28:08,  4.50it/s]
                                                    

 31%|███▏      | 3459/11066 [12:40<28:08,  4.50it/s]
 31%|███▏      | 3460/11066 [12:41<28:08,  4.50it/s]
                                                    

 31%|███▏      | 3460/11066 [12:41<28:08,  4.50it/s]
 31%|███▏      | 3461/11066 [12:41<28:09,  4.50it/s]
                                                    

 31%|███▏      | 3461/11066 [12:41<28:09,  4.50it/s]
 31%|███▏      | 3462/11066 [12:41<28:10,  4.50it/s]
                                                    

 31%|███▏      | 3462/11066 [12:41<28:10,  4.50it/s]
 31%|███▏      | 3463/11066 [12:41<28:09,  4.50it/s]
                                                    

 31%|███▏      | 3463/11066 [12:41<28:09,  4.50it/s]
 31%|███▏      | 3464/11066 [12:42<27:47,  4.56it/s]
                                                    

 31%|███▏      | 3464/11066 [12:42<27:47,  4.56it/s]
 31%|███▏      | 3465/11066 [12:42<27:41,  4.57it/s]
                                                    

 31%|███▏      | 3465/11066 [12:42<27:41,  4.57it/s]
 31%|███▏      | 3466/11066 [12:42<27:54,  4.54it/s]
                                                    

 31%|███▏      | 3466/11066 [12:42<27:54,  4.54it/s]
 31%|███▏      | 3467/11066 [12:42<27:50,  4.55it/s]
                                                    

 31%|███▏      | 3467/11066 [12:42<27:50,  4.55it/s]
 31%|███▏      | 3468/11066 [12:42<28:00,  4.52it/s]
                                                    

 31%|███▏      | 3468/11066 [12:42<28:00,  4.52it/s]
 31%|███▏      | 3469/11066 [12:43<28:09,  4.50it/s]
                                                    

 31%|███▏      | 3469/11066 [12:43<28:09,  4.50it/s]
 31%|███▏      | 3470/11066 [12:43<28:10,  4.49it/s]
                                                    

 31%|███▏      | 3470/11066 [12:43<28:10,  4.49it/s]
 31%|███▏      | 3471/11066 [12:43<28:09,  4.50it/s]
                                                    

 31%|███▏      | 3471/11066 [12:43<28:09,  4.50it/s]
 31%|███▏      | 3472/11066 [12:43<28:09,  4.49it/s]
                                                    

 31%|███▏      | 3472/11066 [12:43<28:09,  4.49it/s]
 31%|███▏      | 3473/11066 [12:44<28:06,  4.50it/s]
                                                    

 31%|███▏      | 3473/11066 [12:44<28:06,  4.50it/s]
 31%|███▏      | 3474/11066 [12:44<27:54,  4.53it/s]
                                                    

 31%|███▏      | 3474/11066 [12:44<27:54,  4.53it/s]
 31%|███▏      | 3475/11066 [12:44<27:59,  4.52it/s]
                                                    

 31%|███▏      | 3475/11066 [12:44<27:59,  4.52it/s]
 31%|███▏      | 3476/11066 [12:44<27:55,  4.53it/s]
                                                    

 31%|███▏      | 3476/11066 [12:44<27:55,  4.53it/s]
 31%|███▏      | 3477/11066 [12:44<27:43,  4.56it/s]
                                                    

 31%|███▏      | 3477/11066 [12:44<27:43,  4.56it/s]
 31%|███▏      | 3478/11066 [12:45<27:57,  4.52it/s]
                                                    

 31%|███▏      | 3478/11066 [12:45<27:57,  4.52it/s]
 31%|███▏      | 3479/11066 [12:45<28:04,  4.50it/s]
                                                    

 31%|███▏      | 3479/11066 [12:45<28:04,  4.50it/s]
 31%|███▏      | 3480/11066 [12:45<28:06,  4.50it/s]
                                                    

 31%|███▏      | 3480/11066 [12:45<28:06,  4.50it/s]
 31%|███▏      | 3481/11066 [12:45<28:10,  4.49it/s]
                                                    

 31%|███▏      | 3481/11066 [12:45<28:10,  4.49it/s]
 31%|███▏      | 3482/11066 [12:46<28:10,  4.49it/s]
                                                    

 31%|███▏      | 3482/11066 [12:46<28:10,  4.49it/s]
 31%|███▏      | 3483/11066 [12:46<28:07,  4.49it/s]
                                                    

 31%|███▏      | 3483/11066 [12:46<28:07,  4.49it/s]
 31%|███▏      | 3484/11066 [12:46<28:08,  4.49it/s]
                                                    

 31%|███▏      | 3484/11066 [12:46<28:08,  4.49it/s]
 31%|███▏      | 3485/11066 [12:46<28:07,  4.49it/s]
                                                    

 31%|███▏      | 3485/11066 [12:46<28:07,  4.49it/s]
 32%|███▏      | 3486/11066 [12:46<28:06,  4.49it/s]
                                                    

 32%|███▏      | 3486/11066 [12:46<28:06,  4.49it/s]
 32%|███▏      | 3487/11066 [12:47<28:04,  4.50it/s]
                                                    

 32%|███▏      | 3487/11066 [12:47<28:04,  4.50it/s]
 32%|███▏      | 3488/11066 [12:47<28:02,  4.50it/s]
                                                    

 32%|███▏      | 3488/11066 [12:47<28:02,  4.50it/s]
 32%|███▏      | 3489/11066 [12:47<28:02,  4.50it/s]
                                                    
{'loss': 0.3727, 'learning_rate': 2.084493041749503e-05, 'epoch': 0.61}
{'loss': 0.7129, 'learning_rate': 2.084221941080788e-05, 'epoch': 0.61}
{'loss': 0.6944, 'learning_rate': 2.0839508404120728e-05, 'epoch': 0.61}
{'loss': 0.5392, 'learning_rate': 2.083679739743358e-05, 'epoch': 0.61}
{'loss': 1.4523, 'learning_rate': 2.0834086390746432e-05, 'epoch': 0.61}
{'loss': 0.9858, 'learning_rate': 2.083137538405928e-05, 'epoch': 0.61}
{'loss': 1.1177, 'learning_rate': 2.0828664377372132e-05, 'epoch': 0.61}
{'loss': 1.4077, 'learning_rate': 2.0825953370684984e-05, 'epoch': 0.61}
{'loss': 0.814, 'learning_rate': 2.0823242363997832e-05, 'epoch': 0.61}
{'loss': 1.2457, 'learning_rate': 2.082053135731068e-05, 'epoch': 0.61}
{'loss': 0.9667, 'learning_rate': 2.0817820350623533e-05, 'epoch': 0.61}
{'loss': 1.5132, 'learning_rate': 2.081510934393638e-05, 'epoch': 0.61}
{'loss': 1.1758, 'learning_rate': 2.0812398337249233e-05, 'epoch': 0.61}
{'loss': 0.4334, 'learning_rate': 2.080968733056208e-05, 'epoch': 0.61}
{'loss': 1.1875, 'learning_rate': 2.0806976323874933e-05, 'epoch': 0.61}
{'loss': 1.3782, 'learning_rate': 2.0804265317187785e-05, 'epoch': 0.61}
{'loss': 1.0704, 'learning_rate': 2.0801554310500633e-05, 'epoch': 0.61}
{'loss': 1.3556, 'learning_rate': 2.0798843303813482e-05, 'epoch': 0.61}
{'loss': 0.7563, 'learning_rate': 2.0796132297126334e-05, 'epoch': 0.61}
{'loss': 0.9992, 'learning_rate': 2.0793421290439182e-05, 'epoch': 0.61}
{'loss': 0.773, 'learning_rate': 2.0790710283752034e-05, 'epoch': 0.61}
{'loss': 0.6794, 'learning_rate': 2.0787999277064886e-05, 'epoch': 0.61}
{'loss': 1.0613, 'learning_rate': 2.0785288270377734e-05, 'epoch': 0.61}
{'loss': 0.6604, 'learning_rate': 2.0782577263690586e-05, 'epoch': 0.61}
{'loss': 1.1398, 'learning_rate': 2.0779866257003434e-05, 'epoch': 0.61}
{'loss': 1.3313, 'learning_rate': 2.0777155250316283e-05, 'epoch': 0.61}
{'loss': 1.0045, 'learning_rate': 2.0774444243629135e-05, 'epoch': 0.62}
{'loss': 1.4629, 'learning_rate': 2.0771733236941983e-05, 'epoch': 0.62}
{'loss': 1.0273, 'learning_rate': 2.0769022230254835e-05, 'epoch': 0.62}
{'loss': 0.6382, 'learning_rate': 2.0766311223567687e-05, 'epoch': 0.62}
{'loss': 0.9502, 'learning_rate': 2.0763600216880535e-05, 'epoch': 0.62}
{'loss': 1.0106, 'learning_rate': 2.0760889210193387e-05, 'epoch': 0.62}
{'loss': 1.1508, 'learning_rate': 2.075817820350624e-05, 'epoch': 0.62}
{'loss': 0.5907, 'learning_rate': 2.0755467196819084e-05, 'epoch': 0.62}
{'loss': 1.1414, 'learning_rate': 2.0752756190131936e-05, 'epoch': 0.62}
{'loss': 0.5278, 'learning_rate': 2.0750045183444784e-05, 'epoch': 0.62}
{'loss': 1.2906, 'learning_rate': 2.0747334176757636e-05, 'epoch': 0.62}
{'loss': 1.5898, 'learning_rate': 2.0744623170070488e-05, 'epoch': 0.62}
{'loss': 0.9212, 'learning_rate': 2.0741912163383336e-05, 'epoch': 0.62}
{'loss': 0.9523, 'learning_rate': 2.0739201156696188e-05, 'epoch': 0.62}
{'loss': 1.0968, 'learning_rate': 2.073649015000904e-05, 'epoch': 0.62}
{'loss': 1.2949, 'learning_rate': 2.0733779143321885e-05, 'epoch': 0.62}
{'loss': 0.8415, 'learning_rate': 2.0731068136634737e-05, 'epoch': 0.62}
{'loss': 0.4212, 'learning_rate': 2.072835712994759e-05, 'epoch': 0.62}
{'loss': 0.6548, 'learning_rate': 2.0725646123260437e-05, 'epoch': 0.62}
{'loss': 1.1268, 'learning_rate': 2.072293511657329e-05, 'epoch': 0.62}
{'loss': 0.8852, 'learning_rate': 2.0720224109886137e-05, 'epoch': 0.62}
{'loss': 1.2319, 'learning_rate': 2.071751310319899e-05, 'epoch': 0.62}
{'loss': 0.9522, 'learning_rate': 2.071480209651184e-05, 'epoch': 0.62}
{'loss': 0.8172, 'learning_rate': 2.0712091089824686e-05, 'epoch': 0.62}
{'loss': 1.1703, 'learning_rate': 2.0709380083137538e-05, 'epoch': 0.62}
{'loss': 1.1332, 'learning_rate': 2.070666907645039e-05, 'epoch': 0.62}
{'loss': 1.3144, 'learning_rate': 2.0703958069763238e-05, 'epoch': 0.62}
{'loss': 1.261, 'learning_rate': 2.070124706307609e-05, 'epoch': 0.62}
{'loss': 0.9735, 'learning_rate': 2.0698536056388942e-05, 'epoch': 0.62}
{'loss': 0.6355, 'learning_rate': 2.069582504970179e-05, 'epoch': 0.62}
{'loss': 1.225, 'learning_rate': 2.0693114043014642e-05, 'epoch': 0.62}
{'loss': 0.8805, 'learning_rate': 2.0690403036327487e-05, 'epoch': 0.62}
{'loss': 1.6727, 'learning_rate': 2.068769202964034e-05, 'epoch': 0.62}
{'loss': 1.335, 'learning_rate': 2.068498102295319e-05, 'epoch': 0.62}
{'loss': 1.0886, 'learning_rate': 2.068227001626604e-05, 'epoch': 0.62}
{'loss': 0.6521, 'learning_rate': 2.067955900957889e-05, 'epoch': 0.62}
{'loss': 0.9213, 'learning_rate': 2.0676848002891743e-05, 'epoch': 0.62}
{'loss': 1.6397, 'learning_rate': 2.067413699620459e-05, 'epoch': 0.62}
{'loss': 1.2038, 'learning_rate': 2.0671425989517443e-05, 'epoch': 0.62}
{'loss': 0.7556, 'learning_rate': 2.066871498283029e-05, 'epoch': 0.62}
{'loss': 1.7865, 'learning_rate': 2.066600397614314e-05, 'epoch': 0.62}
{'loss': 1.2091, 'learning_rate': 2.0663292969455992e-05, 'epoch': 0.62}
{'loss': 0.6642, 'learning_rate': 2.066058196276884e-05, 'epoch': 0.62}
{'loss': 0.8466, 'learning_rate': 2.0657870956081692e-05, 'epoch': 0.62}
{'loss': 0.9253, 'learning_rate': 2.0655159949394544e-05, 'epoch': 0.62}
{'loss': 0.6411, 'learning_rate': 2.0652448942707392e-05, 'epoch': 0.62}
{'loss': 1.3187, 'learning_rate': 2.0649737936020244e-05, 'epoch': 0.62}
{'loss': 0.8677, 'learning_rate': 2.0647026929333093e-05, 'epoch': 0.62}
{'loss': 0.7702, 'learning_rate': 2.064431592264594e-05, 'epoch': 0.62}
{'loss': 0.5456, 'learning_rate': 2.0641604915958793e-05, 'epoch': 0.62}
{'loss': 0.8948, 'learning_rate': 2.0638893909271645e-05, 'epoch': 0.62}
{'loss': 0.6605, 'learning_rate': 2.0636182902584493e-05, 'epoch': 0.62}
{'loss': 1.1267, 'learning_rate': 2.0633471895897345e-05, 'epoch': 0.62}
{'loss': 1.0637, 'learning_rate': 2.0630760889210194e-05, 'epoch': 0.62}
{'loss': 0.5561, 'learning_rate': 2.0628049882523045e-05, 'epoch': 0.62}
{'loss': 0.5923, 'learning_rate': 2.0625338875835894e-05, 'epoch': 0.62}
{'loss': 0.7312, 'learning_rate': 2.0622627869148742e-05, 'epoch': 0.63}
{'loss': 0.9911, 'learning_rate': 2.0619916862461594e-05, 'epoch': 0.63}
{'loss': 0.7742, 'learning_rate': 2.0617205855774446e-05, 'epoch': 0.63}
{'loss': 1.3984, 'learning_rate': 2.0614494849087294e-05, 'epoch': 0.63}
{'loss': 1.5618, 'learning_rate': 2.0611783842400146e-05, 'epoch': 0.63}
{'loss': 1.247, 'learning_rate': 2.0609072835712998e-05, 'epoch': 0.63}
{'loss': 1.4109, 'learning_rate': 2.0606361829025846e-05, 'epoch': 0.63}
{'loss': 1.5626, 'learning_rate': 2.0603650822338695e-05, 'epoch': 0.63}
{'loss': 0.7101, 'learning_rate': 2.0600939815651543e-05, 'epoch': 0.63}
{'loss': 0.9821, 'learning_rate': 2.0598228808964395e-05, 'epoch': 0.63}
{'loss': 1.9671, 'learning_rate': 2.0595517802277247e-05, 'epoch': 0.63}
{'loss': 0.7168, 'learning_rate': 2.0592806795590095e-05, 'epoch': 0.63}
{'loss': 0.9813, 'learning_rate': 2.0590095788902947e-05, 'epoch': 0.63}
{'loss': 0.7714, 'learning_rate': 2.05873847822158e-05, 'epoch': 0.63}
{'loss': 0.7837, 'learning_rate': 2.0584673775528648e-05, 'epoch': 0.63}
{'loss': 0.8505, 'learning_rate': 2.0581962768841496e-05, 'epoch': 0.63}
{'loss': 0.5281, 'learning_rate': 2.0579251762154348e-05, 'epoch': 0.63}
{'loss': 0.4116, 'learning_rate': 2.0576540755467196e-05, 'epoch': 0.63}
{'loss': 1.0766, 'learning_rate': 2.0573829748780048e-05, 'epoch': 0.63}
{'loss': 1.2112, 'learning_rate': 2.0571118742092897e-05, 'epoch': 0.63}
{'loss': 0.7084, 'learning_rate': 2.056840773540575e-05, 'epoch': 0.63}
{'loss': 1.4651, 'learning_rate': 2.05656967287186e-05, 'epoch': 0.63}
{'loss': 1.215, 'learning_rate': 2.0562985722031445e-05, 'epoch': 0.63}
{'loss': 1.0493, 'learning_rate': 2.0560274715344297e-05, 'epoch': 0.63}
{'loss': 1.5412, 'learning_rate': 2.055756370865715e-05, 'epoch': 0.63}
{'loss': 0.8539, 'learning_rate': 2.0554852701969997e-05, 'epoch': 0.63}
{'loss': 0.8703, 'learning_rate': 2.055214169528285e-05, 'epoch': 0.63}
{'loss': 1.5589, 'learning_rate': 2.05494306885957e-05, 'epoch': 0.63}
{'loss': 0.9223, 'learning_rate': 2.054671968190855e-05, 'epoch': 0.63}
{'loss': 1.1912, 'learning_rate': 2.05440086752214e-05, 'epoch': 0.63}

 32%|███▏      | 3489/11066 [12:47<28:02,  4.50it/s]
 32%|███▏      | 3490/11066 [12:47<28:24,  4.45it/s]
                                                    

 32%|███▏      | 3490/11066 [12:47<28:24,  4.45it/s]
 32%|███▏      | 3491/11066 [12:48<28:35,  4.41it/s]
                                                    

 32%|███▏      | 3491/11066 [12:48<28:35,  4.41it/s]
 32%|███▏      | 3492/11066 [12:48<28:29,  4.43it/s]
                                                    

 32%|███▏      | 3492/11066 [12:48<28:29,  4.43it/s]
 32%|███▏      | 3493/11066 [12:48<28:22,  4.45it/s]
                                                    

 32%|███▏      | 3493/11066 [12:48<28:22,  4.45it/s]
 32%|███▏      | 3494/11066 [12:48<28:17,  4.46it/s]
                                                    

 32%|███▏      | 3494/11066 [12:48<28:17,  4.46it/s]
 32%|███▏      | 3495/11066 [12:48<27:45,  4.55it/s]
                                                    

 32%|███▏      | 3495/11066 [12:48<27:45,  4.55it/s]
 32%|███▏      | 3496/11066 [12:49<27:53,  4.52it/s]
                                                    

 32%|███▏      | 3496/11066 [12:49<27:53,  4.52it/s]
 32%|███▏      | 3497/11066 [12:49<27:56,  4.51it/s]
                                                    

 32%|███▏      | 3497/11066 [12:49<27:56,  4.51it/s]
 32%|███▏      | 3498/11066 [12:49<27:57,  4.51it/s]
                                                    

 32%|███▏      | 3498/11066 [12:49<27:57,  4.51it/s]
 32%|███▏      | 3499/11066 [12:49<27:35,  4.57it/s]
                                                    

 32%|███▏      | 3499/11066 [12:49<27:35,  4.57it/s]
 32%|███▏      | 3500/11066 [12:50<27:39,  4.56it/s]
                                                    

 32%|███▏      | 3500/11066 [12:50<27:39,  4.56it/s]
 32%|███▏      | 3501/11066 [12:50<27:35,  4.57it/s]
                                                    

 32%|███▏      | 3501/11066 [12:50<27:35,  4.57it/s]
 32%|███▏      | 3502/11066 [12:50<27:45,  4.54it/s]
                                                    

 32%|███▏      | 3502/11066 [12:50<27:45,  4.54it/s]
 32%|███▏      | 3503/11066 [12:50<27:40,  4.55it/s]
                                                    

 32%|███▏      | 3503/11066 [12:50<27:40,  4.55it/s]
 32%|███▏      | 3504/11066 [12:50<27:22,  4.61it/s]
                                                    

 32%|███▏      | 3504/11066 [12:50<27:22,  4.61it/s]
 32%|███▏      | 3505/11066 [12:51<27:34,  4.57it/s]
                                                    

 32%|███▏      | 3505/11066 [12:51<27:34,  4.57it/s]
 32%|███▏      | 3506/11066 [12:51<27:21,  4.61it/s]
                                                    

 32%|███▏      | 3506/11066 [12:51<27:21,  4.61it/s]
 32%|███▏      | 3507/11066 [12:51<27:18,  4.61it/s]
                                                    

 32%|███▏      | 3507/11066 [12:51<27:18,  4.61it/s]
 32%|███▏      | 3508/11066 [12:51<27:14,  4.62it/s]
                                                    

 32%|███▏      | 3508/11066 [12:51<27:14,  4.62it/s]
 32%|███▏      | 3509/11066 [12:52<27:31,  4.58it/s]
                                                    

 32%|███▏      | 3509/11066 [12:52<27:31,  4.58it/s]
 32%|███▏      | 3510/11066 [12:52<27:27,  4.59it/s]
                                                    

 32%|███▏      | 3510/11066 [12:52<27:27,  4.59it/s]
 32%|███▏      | 3511/11066 [12:52<27:33,  4.57it/s]
                                                    

 32%|███▏      | 3511/11066 [12:52<27:33,  4.57it/s]
 32%|███▏      | 3512/11066 [12:52<27:25,  4.59it/s]
                                                    

 32%|███▏      | 3512/11066 [12:52<27:25,  4.59it/s]
 32%|███▏      | 3513/11066 [12:52<27:12,  4.63it/s]
                                                    

 32%|███▏      | 3513/11066 [12:52<27:12,  4.63it/s]
 32%|███▏      | 3514/11066 [12:53<27:29,  4.58it/s]
                                                    

 32%|███▏      | 3514/11066 [12:53<27:29,  4.58it/s]
 32%|███▏      | 3515/11066 [12:53<27:15,  4.62it/s]
                                                    

 32%|███▏      | 3515/11066 [12:53<27:15,  4.62it/s]
 32%|███▏      | 3516/11066 [12:53<27:30,  4.58it/s]
                                                    

 32%|███▏      | 3516/11066 [12:53<27:30,  4.58it/s]
 32%|███▏      | 3517/11066 [12:53<27:37,  4.55it/s]
                                                    

 32%|███▏      | 3517/11066 [12:53<27:37,  4.55it/s]
 32%|███▏      | 3518/11066 [12:53<27:43,  4.54it/s]
                                                    

 32%|███▏      | 3518/11066 [12:53<27:43,  4.54it/s]
 32%|███▏      | 3519/11066 [12:54<27:35,  4.56it/s]
                                                    

 32%|███▏      | 3519/11066 [12:54<27:35,  4.56it/s]
 32%|███▏      | 3520/11066 [12:54<27:48,  4.52it/s]
                                                    

 32%|███▏      | 3520/11066 [12:54<27:48,  4.52it/s]
 32%|███▏      | 3521/11066 [12:54<27:55,  4.50it/s]
                                                    

 32%|███▏      | 3521/11066 [12:54<27:55,  4.50it/s]
 32%|███▏      | 3522/11066 [12:54<27:32,  4.56it/s]
                                                    

 32%|███▏      | 3522/11066 [12:54<27:32,  4.56it/s]
 32%|███▏      | 3523/11066 [12:55<27:08,  4.63it/s]
                                                    

 32%|███▏      | 3523/11066 [12:55<27:08,  4.63it/s]
 32%|███▏      | 3524/11066 [12:55<27:30,  4.57it/s]
                                                    

 32%|███▏      | 3524/11066 [12:55<27:30,  4.57it/s]
 32%|███▏      | 3525/11066 [12:55<27:39,  4.54it/s]
                                                    

 32%|███▏      | 3525/11066 [12:55<27:39,  4.54it/s]
 32%|███▏      | 3526/11066 [12:55<28:23,  4.43it/s]
                                                    

 32%|███▏      | 3526/11066 [12:55<28:23,  4.43it/s]
 32%|███▏      | 3527/11066 [12:55<28:24,  4.42it/s]
                                                    

 32%|███▏      | 3527/11066 [12:55<28:24,  4.42it/s]
 32%|███▏      | 3528/11066 [12:56<28:26,  4.42it/s]
                                                    

 32%|███▏      | 3528/11066 [12:56<28:26,  4.42it/s]
 32%|███▏      | 3529/11066 [12:56<28:23,  4.42it/s]
                                                    

 32%|███▏      | 3529/11066 [12:56<28:23,  4.42it/s]
 32%|███▏      | 3530/11066 [12:56<28:18,  4.44it/s]
                                                    

 32%|███▏      | 3530/11066 [12:56<28:18,  4.44it/s]
 32%|███▏      | 3531/11066 [12:56<27:58,  4.49it/s]
                                                    

 32%|███▏      | 3531/11066 [12:56<27:58,  4.49it/s]
 32%|███▏      | 3532/11066 [12:57<27:30,  4.57it/s]
                                                    

 32%|███▏      | 3532/11066 [12:57<27:30,  4.57it/s]
 32%|███▏      | 3533/11066 [12:57<27:05,  4.63it/s]
                                                    

 32%|███▏      | 3533/11066 [12:57<27:05,  4.63it/s]
 32%|███▏      | 3534/11066 [12:57<27:22,  4.59it/s]
                                                    

 32%|███▏      | 3534/11066 [12:57<27:22,  4.59it/s]
 32%|███▏      | 3535/11066 [12:57<27:30,  4.56it/s]
                                                    

 32%|███▏      | 3535/11066 [12:57<27:30,  4.56it/s]
 32%|███▏      | 3536/11066 [12:57<27:25,  4.58it/s]
                                                    

 32%|███▏      | 3536/11066 [12:57<27:25,  4.58it/s]
 32%|███▏      | 3537/11066 [12:58<26:59,  4.65it/s]
                                                    

 32%|███▏      | 3537/11066 [12:58<26:59,  4.65it/s]
 32%|███▏      | 3538/11066 [12:58<26:58,  4.65it/s]
                                                    

 32%|███▏      | 3538/11066 [12:58<26:58,  4.65it/s]
 32%|███▏      | 3539/11066 [12:58<27:03,  4.64it/s]
                                                    

 32%|███▏      | 3539/11066 [12:58<27:03,  4.64it/s]
 32%|███▏      | 3540/11066 [12:58<27:08,  4.62it/s]
                                                    

 32%|███▏      | 3540/11066 [12:58<27:08,  4.62it/s]
 32%|███▏      | 3541/11066 [12:59<27:01,  4.64it/s]
                                                    

 32%|███▏      | 3541/11066 [12:59<27:01,  4.64it/s]
 32%|███▏      | 3542/11066 [12:59<27:22,  4.58it/s]
                                                    

 32%|███▏      | 3542/11066 [12:59<27:22,  4.58it/s]
 32%|███▏      | 3543/11066 [12:59<27:39,  4.53it/s]
                                                    

 32%|███▏      | 3543/11066 [12:59<27:39,  4.53it/s]
 32%|███▏      | 3544/11066 [12:59<27:42,  4.52it/s]
                                                    

 32%|███▏      | 3544/11066 [12:59<27:42,  4.52it/s]
 32%|███▏      | 3545/11066 [12:59<27:43,  4.52it/s]
                                                    

 32%|███▏      | 3545/11066 [12:59<27:43,  4.52it/s]
 32%|███▏      | 3546/11066 [13:00<27:20,  4.58it/s]
                                                    

 32%|███▏      | 3546/11066 [13:00<27:20,  4.58it/s]
 32%|███▏      | 3547/11066 [13:00<27:16,  4.59it/s]
                                                    

 32%|███▏      | 3547/11066 [13:00<27:16,  4.59it/s]
 32%|███▏      | 3548/11066 [13:00<27:32,  4.55it/s]
                                                    

 32%|███▏      | 3548/11066 [13:00<27:32,  4.55it/s]
 32%|███▏      | 3549/11066 [13:00<27:27,  4.56it/s]
                                                    

 32%|███▏      | 3549/11066 [13:00<27:27,  4.56it/s]
 32%|███▏      | 3550/11066 [13:00<27:01,  4.63it/s]
                                                    

 32%|███▏      | 3550/11066 [13:00<27:01,  4.63it/s]
 32%|███▏      | 3551/11066 [13:01<27:23,  4.57it/s]
                                                    

 32%|███▏      | 3551/11066 [13:01<27:23,  4.57it/s]
 32%|███▏      | 3552/11066 [13:01<27:31,  4.55it/s]
                                                    

 32%|███▏      | 3552/11066 [13:01<27:31,  4.55it/s]
 32%|███▏      | 3553/11066 [13:01<27:35,  4.54it/s]
                                                    

 32%|███▏      | 3553/11066 [13:01<27:35,  4.54it/s]
 32%|███▏      | 3554/11066 [13:01<27:25,  4.56it/s]
                                                    

 32%|███▏      | 3554/11066 [13:01<27:25,  4.56it/s]
 32%|███▏      | 3555/11066 [13:02<27:29,  4.55it/s]
                                                    

 32%|███▏      | 3555/11066 [13:02<27:29,  4.55it/s]
 32%|███▏      | 3556/11066 [13:02<27:04,  4.62it/s]
                                                    

 32%|███▏      | 3556/11066 [13:02<27:04,  4.62it/s]
 32%|███▏      | 3557/11066 [13:02<27:21,  4.58it/s]
                                                    

 32%|███▏      | 3557/11066 [13:02<27:21,  4.58it/s]
 32%|███▏      | 3558/11066 [13:02<27:31,  4.55it/s]
                                                    

 32%|███▏      | 3558/11066 [13:02<27:31,  4.55it/s]
 32%|███▏      | 3559/11066 [13:02<27:13,  4.60it/s]
                                                    

 32%|███▏      | 3559/11066 [13:02<27:13,  4.60it/s]
 32%|███▏      | 3560/11066 [13:03<27:24,  4.56it/s]
                                                    

 32%|███▏      | 3560/11066 [13:03<27:24,  4.56it/s]
 32%|███▏      | 3561/11066 [13:03<27:09,  4.61it/s]
                                                    

 32%|███▏      | 3561/11066 [13:03<27:09,  4.61it/s]
 32%|███▏      | 3562/11066 [13:03<26:59,  4.63it/s]
                                                    

 32%|███▏      | 3562/11066 [13:03<26:59,  4.63it/s]
 32%|███▏      | 3563/11066 [13:03<27:02,  4.62it/s]
                                                    

 32%|███▏      | 3563/11066 [13:03<27:02,  4.62it/s]
 32%|███▏      | 3564/11066 [13:04<26:55,  4.64it/s]
                                                    

 32%|███▏      | 3564/11066 [13:04<26:55,  4.64it/s]
 32%|███▏      | 3565/11066 [13:04<26:52,  4.65it/s]
                                                    

 32%|███▏      | 3565/11066 [13:04<26:52,  4.65it/s]
 32%|███▏      | 3566/11066 [13:04<27:16,  4.58it/s]
                                                    

 32%|███▏      | 3566/11066 [13:04<27:16,  4.58it/s]
 32%|███▏      | 3567/11066 [13:04<27:05,  4.61it/s]
                                                    

 32%|███▏      | 3567/11066 [13:04<27:05,  4.61it/s]
 32%|███▏      | 3568/11066 [13:04<27:06,  4.61it/s]
                                                    

 32%|███▏      | 3568/11066 [13:04<27:06,  4.61it/s]
 32%|███▏      | 3569/11066 [13:05<26:58,  4.63it/s]
                                                    

 32%|███▏      | 3569/11066 [13:05<26:58,  4.63it/s]
 32%|███▏      | 3570/11066 [13:05<26:44,  4.67it/s]
                                                    

 32%|███▏      | 3570/11066 [13:05<26:44,  4.67it/s]
 32%|███▏      | 3571/11066 [13:05<27:02,  4.62it/s]
                                                    

 32%|███▏      | 3571/11066 [13:05<27:02,  4.62it/s]
 32%|███▏      | 3572/11066 [13:05<26:52,  4.65it/s]
                                                    

 32%|███▏      | 3572/11066 [13:05<26:52,  4.65it/s]
 32%|███▏      | 3573/11066 [13:05<26:46,  4.66it/s]
                                                    

 32%|███▏      | 3573/11066 [13:05<26:46,  4.66it/s]
 32%|███▏      | 3574/11066 [13:06<26:43,  4.67it/s]
                                                    

 32%|███▏      | 3574/11066 [13:06<26:43,  4.67it/s]
 32%|███▏      | 3575/11066 [13:06<26:37,  4.69it/s]
                                                    

 32%|███▏      | 3575/11066 [13:06<26:37,  4.69it/s]
 32%|███▏      | 3576/11066 [13:06<26:44,  4.67it/s]
                                                    

 32%|███▏      | 3576/11066 [13:06<26:44,  4.67it/s]
 32%|███▏      | 3577/11066 [13:06<26:32,  4.70it/s]
                                                    

 32%|███▏      | 3577/11066 [13:06<26:32,  4.70it/s]
 32%|███▏      | 3578/11066 [13:07<26:31,  4.70it/s]
                                                    

 32%|███▏      | 3578/11066 [13:07<26:31,  4.70it/s]
 32%|███▏      | 3579/11066 [13:07<26:52,  4.64it/s]
                                                    

 32%|███▏      | 3579/11066 [13:07<26:52,  4.64it/s]
 32%|███▏      | 3580/11066 [13:07<27:11,  4.59it/s]
                                                    

 32%|███▏      | 3580/11066 [13:07<27:11,  4.59it/s]
 32%|███▏      | 3581/11066 [13:07<26:58,  4.62it/s]
                                                    

 32%|███▏      | 3581/11066 [13:07<26:58,  4.62it/s]
 32%|███▏      | 3582/11066 [13:07<26:48,  4.65it/s]
                                                    

 32%|███▏      | 3582/11066 [13:07<26:48,  4.65it/s]
 32%|███▏      | 3583/11066 [13:08<26:51,  4.64it/s]
                                                    

 32%|███▏      | 3583/11066 [13:08<26:51,  4.64it/s]
 32%|███▏      | 3584/11066 [13:08<26:41,  4.67it/s]
                                                    

 32%|███▏      | 3584/11066 [13:08<26:41,  4.67it/s]
 32%|███▏      | 3585/11066 [13:08<26:39,  4.68it/s]
                                                    

 32%|███▏      | 3585/11066 [13:08<26:39,  4.68it/s]
 32%|███▏      | 3586/11066 [13:08<26:48,  4.65it/s]
                                                    

 32%|███▏      | 3586/11066 [13:08<26:48,  4.65it/s]
 32%|███▏      | 3587/11066 [13:08<26:43,  4.66it/s]
                                                    

 32%|███▏      | 3587/11066 [13:08<26:43,  4.66it/s]
 32%|███▏      | 3588/11066 [13:09<26:48,  4.65it/s]
                                                    

 32%|███▏      | 3588/11066 [13:09<26:48,  4.65it/s]
 32%|███▏      | 3589/11066 [13:09<26:35,  4.69it/s]
                                                    

 32%|███▏      | 3589/11066 [13:09<26:35,  4.69it/s]
 32%|███▏      | 3590/11066 [13:09<26:55,  4.63it/s]
                                                    

 32%|███▏      | 3590/11066 [13:09<26:55,  4.63it/s]
 32%|███▏      | 3591/11066 [13:09<26:56,  4.62it/s]
                                                    

 32%|███▏      | 3591/11066 [13:09<26:56,  4.62it/s]
 32%|███▏      | 3592/11066 [13:10<27:02,  4.61it/s]
                                                    

 32%|███▏      | 3592/11066 [13:10<27:02,  4.61it/s]
 32%|███▏      | 3593/11066 [13:10<26:51,  4.64it/s]
                                                    

 32%|███▏      | 3593/11066 [13:10<26:51,  4.64it/s]
 32%|███▏      | 3594/11066 [13:10<27:31,  4.52it/s]
                                                    

 32%|███▏      | 3594/11066 [13:10<27:31,  4.52it/s]
 32%|███▏      | 3595/11066 [13:10<27:14,  4.57it/s]
                                                    

 32%|███▏      | 3595/11066 [13:10<27:14,  4.57it/s]
 32%|███▏      | 3596/11066 [13:10<27:04,  4.60it/s]
                                                    

 32%|███▏      | 3596/11066 [13:10<27:04,  4.60it/s]
 33%|███▎      | 3597/11066 [13:11<26:54,  4.63it/s]
                                                    

 33%|███▎      | 3597/11066 [13:11<26:54,  4.63it/s]
 33%|███▎      | 3598/11066 [13:11<26:46,  4.65it/s]
                                                    

 33%|███▎      | 3598/11066 [13:11<26:46,  4.65it/s]
 33%|███▎      | 3599/11066 [13:11<26:40,  4.66it/s]
                                                    

 33%|███▎      | 3599/11066 [13:11<26:40,  4.66it/s]
 33%|███▎      | 3600/11066 [13:11<26:35,  4.68it/s]
                                                    

 33%|███▎      | 3600/11066 [13:11<26:35,  4.68it/s]
 33%|███▎      | 3601/11066 [13:12<26:32,  4.69it/s]
                                                    
{'loss': 1.2405, 'learning_rate': 2.0541297668534246e-05, 'epoch': 0.63}
{'loss': 1.2682, 'learning_rate': 2.0538586661847098e-05, 'epoch': 0.63}
{'loss': 0.8639, 'learning_rate': 2.053587565515995e-05, 'epoch': 0.63}
{'loss': 0.3881, 'learning_rate': 2.05331646484728e-05, 'epoch': 0.63}
{'loss': 1.1806, 'learning_rate': 2.053045364178565e-05, 'epoch': 0.63}
{'loss': 1.0377, 'learning_rate': 2.0527742635098502e-05, 'epoch': 0.63}
{'loss': 1.4751, 'learning_rate': 2.052503162841135e-05, 'epoch': 0.63}
{'loss': 1.5216, 'learning_rate': 2.0522320621724202e-05, 'epoch': 0.63}
{'loss': 0.7185, 'learning_rate': 2.051960961503705e-05, 'epoch': 0.63}
{'loss': 0.9607, 'learning_rate': 2.05168986083499e-05, 'epoch': 0.63}
{'loss': 1.0594, 'learning_rate': 2.051418760166275e-05, 'epoch': 0.63}
{'loss': 1.0368, 'learning_rate': 2.05114765949756e-05, 'epoch': 0.63}
{'loss': 1.4737, 'learning_rate': 2.050876558828845e-05, 'epoch': 0.63}
{'loss': 0.8493, 'learning_rate': 2.0506054581601303e-05, 'epoch': 0.63}
{'loss': 0.9163, 'learning_rate': 2.050334357491415e-05, 'epoch': 0.63}
{'loss': 2.0134, 'learning_rate': 2.0500632568227003e-05, 'epoch': 0.63}
{'loss': 1.1078, 'learning_rate': 2.0497921561539852e-05, 'epoch': 0.63}
{'loss': 0.768, 'learning_rate': 2.04952105548527e-05, 'epoch': 0.63}
{'loss': 1.3386, 'learning_rate': 2.0492499548165552e-05, 'epoch': 0.63}
{'loss': 1.3482, 'learning_rate': 2.0489788541478404e-05, 'epoch': 0.63}
{'loss': 1.8138, 'learning_rate': 2.0487077534791252e-05, 'epoch': 0.63}
{'loss': 1.4171, 'learning_rate': 2.0484366528104104e-05, 'epoch': 0.63}
{'loss': 0.522, 'learning_rate': 2.0481655521416953e-05, 'epoch': 0.63}
{'loss': 1.1614, 'learning_rate': 2.0478944514729804e-05, 'epoch': 0.63}
{'loss': 1.0401, 'learning_rate': 2.0476233508042653e-05, 'epoch': 0.63}
{'loss': 1.5474, 'learning_rate': 2.04735225013555e-05, 'epoch': 0.64}
{'loss': 0.9819, 'learning_rate': 2.0470811494668353e-05, 'epoch': 0.64}
{'loss': 1.5093, 'learning_rate': 2.0468100487981205e-05, 'epoch': 0.64}
{'loss': 0.8226, 'learning_rate': 2.0465389481294053e-05, 'epoch': 0.64}
{'loss': 0.7087, 'learning_rate': 2.0462678474606905e-05, 'epoch': 0.64}
{'loss': 1.0719, 'learning_rate': 2.0459967467919757e-05, 'epoch': 0.64}
{'loss': 1.8979, 'learning_rate': 2.0457256461232606e-05, 'epoch': 0.64}
{'loss': 0.884, 'learning_rate': 2.0454545454545454e-05, 'epoch': 0.64}
{'loss': 1.2079, 'learning_rate': 2.0451834447858306e-05, 'epoch': 0.64}
{'loss': 1.4106, 'learning_rate': 2.0449123441171154e-05, 'epoch': 0.64}
{'loss': 1.3836, 'learning_rate': 2.0446412434484006e-05, 'epoch': 0.64}
{'loss': 0.3169, 'learning_rate': 2.0443701427796855e-05, 'epoch': 0.64}
{'loss': 1.3256, 'learning_rate': 2.0440990421109706e-05, 'epoch': 0.64}
{'loss': 1.4159, 'learning_rate': 2.0438279414422558e-05, 'epoch': 0.64}
{'loss': 1.5456, 'learning_rate': 2.0435568407735407e-05, 'epoch': 0.64}
{'loss': 0.818, 'learning_rate': 2.0432857401048255e-05, 'epoch': 0.64}
{'loss': 1.4478, 'learning_rate': 2.0430146394361107e-05, 'epoch': 0.64}
{'loss': 0.4572, 'learning_rate': 2.0427435387673955e-05, 'epoch': 0.64}
{'loss': 1.4433, 'learning_rate': 2.0424724380986807e-05, 'epoch': 0.64}
{'loss': 0.8517, 'learning_rate': 2.042201337429966e-05, 'epoch': 0.64}
{'loss': 0.7079, 'learning_rate': 2.0419302367612507e-05, 'epoch': 0.64}
{'loss': 1.7292, 'learning_rate': 2.041659136092536e-05, 'epoch': 0.64}
{'loss': 1.2975, 'learning_rate': 2.0413880354238208e-05, 'epoch': 0.64}
{'loss': 0.8975, 'learning_rate': 2.0411169347551056e-05, 'epoch': 0.64}
{'loss': 1.8126, 'learning_rate': 2.0408458340863908e-05, 'epoch': 0.64}
{'loss': 1.3394, 'learning_rate': 2.0405747334176756e-05, 'epoch': 0.64}
{'loss': 1.1765, 'learning_rate': 2.0403036327489608e-05, 'epoch': 0.64}
{'loss': 1.161, 'learning_rate': 2.040032532080246e-05, 'epoch': 0.64}
{'loss': 1.0989, 'learning_rate': 2.039761431411531e-05, 'epoch': 0.64}
{'loss': 1.2807, 'learning_rate': 2.039490330742816e-05, 'epoch': 0.64}
{'loss': 0.833, 'learning_rate': 2.0392192300741012e-05, 'epoch': 0.64}
{'loss': 0.7306, 'learning_rate': 2.0389481294053857e-05, 'epoch': 0.64}
{'loss': 0.7282, 'learning_rate': 2.038677028736671e-05, 'epoch': 0.64}
{'loss': 0.7799, 'learning_rate': 2.0384059280679557e-05, 'epoch': 0.64}
{'loss': 0.7586, 'learning_rate': 2.038134827399241e-05, 'epoch': 0.64}
{'loss': 0.8173, 'learning_rate': 2.037863726730526e-05, 'epoch': 0.64}
{'loss': 1.2999, 'learning_rate': 2.037592626061811e-05, 'epoch': 0.64}
{'loss': 1.1455, 'learning_rate': 2.037321525393096e-05, 'epoch': 0.64}
{'loss': 1.1488, 'learning_rate': 2.0370504247243813e-05, 'epoch': 0.64}
{'loss': 1.1661, 'learning_rate': 2.0367793240556658e-05, 'epoch': 0.64}
{'loss': 0.8837, 'learning_rate': 2.036508223386951e-05, 'epoch': 0.64}
{'loss': 0.9838, 'learning_rate': 2.0362371227182362e-05, 'epoch': 0.64}
{'loss': 0.835, 'learning_rate': 2.035966022049521e-05, 'epoch': 0.64}
{'loss': 1.5615, 'learning_rate': 2.0356949213808062e-05, 'epoch': 0.64}
{'loss': 0.6445, 'learning_rate': 2.035423820712091e-05, 'epoch': 0.64}
{'loss': 0.6797, 'learning_rate': 2.0351527200433762e-05, 'epoch': 0.64}
{'loss': 0.7464, 'learning_rate': 2.0348816193746614e-05, 'epoch': 0.64}
{'loss': 1.3786, 'learning_rate': 2.034610518705946e-05, 'epoch': 0.64}
{'loss': 1.1244, 'learning_rate': 2.034339418037231e-05, 'epoch': 0.64}
{'loss': 1.7654, 'learning_rate': 2.0340683173685163e-05, 'epoch': 0.64}
{'loss': 0.6305, 'learning_rate': 2.033797216699801e-05, 'epoch': 0.64}
{'loss': 1.0371, 'learning_rate': 2.0335261160310863e-05, 'epoch': 0.64}
{'loss': 1.3299, 'learning_rate': 2.0332550153623715e-05, 'epoch': 0.64}
{'loss': 1.1249, 'learning_rate': 2.0329839146936564e-05, 'epoch': 0.64}
{'loss': 1.0815, 'learning_rate': 2.0327128140249415e-05, 'epoch': 0.64}
{'loss': 1.0021, 'learning_rate': 2.032441713356226e-05, 'epoch': 0.65}
{'loss': 1.3505, 'learning_rate': 2.0321706126875112e-05, 'epoch': 0.65}
{'loss': 0.8733, 'learning_rate': 2.0318995120187964e-05, 'epoch': 0.65}
{'loss': 1.5493, 'learning_rate': 2.0316284113500813e-05, 'epoch': 0.65}
{'loss': 1.2247, 'learning_rate': 2.0313573106813664e-05, 'epoch': 0.65}
{'loss': 1.4848, 'learning_rate': 2.0310862100126516e-05, 'epoch': 0.65}
{'loss': 1.4827, 'learning_rate': 2.0308151093439365e-05, 'epoch': 0.65}
{'loss': 1.3206, 'learning_rate': 2.0305440086752216e-05, 'epoch': 0.65}
{'loss': 1.24, 'learning_rate': 2.0302729080065065e-05, 'epoch': 0.65}
{'loss': 1.4466, 'learning_rate': 2.0300018073377913e-05, 'epoch': 0.65}
{'loss': 1.1962, 'learning_rate': 2.0297307066690765e-05, 'epoch': 0.65}
{'loss': 1.4631, 'learning_rate': 2.0294596060003614e-05, 'epoch': 0.65}
{'loss': 0.65, 'learning_rate': 2.0291885053316465e-05, 'epoch': 0.65}
{'loss': 0.7068, 'learning_rate': 2.0289174046629317e-05, 'epoch': 0.65}
{'loss': 1.3252, 'learning_rate': 2.0286463039942166e-05, 'epoch': 0.65}
{'loss': 0.8861, 'learning_rate': 2.0283752033255018e-05, 'epoch': 0.65}
{'loss': 0.7568, 'learning_rate': 2.0281041026567866e-05, 'epoch': 0.65}
{'loss': 0.7004, 'learning_rate': 2.0278330019880714e-05, 'epoch': 0.65}
{'loss': 1.1659, 'learning_rate': 2.0275619013193566e-05, 'epoch': 0.65}
{'loss': 1.2604, 'learning_rate': 2.0272908006506418e-05, 'epoch': 0.65}
{'loss': 1.1533, 'learning_rate': 2.0270196999819267e-05, 'epoch': 0.65}
{'loss': 1.6119, 'learning_rate': 2.026748599313212e-05, 'epoch': 0.65}
{'loss': 1.2304, 'learning_rate': 2.0264774986444967e-05, 'epoch': 0.65}
{'loss': 1.4198, 'learning_rate': 2.026206397975782e-05, 'epoch': 0.65}
{'loss': 1.2144, 'learning_rate': 2.0259352973070667e-05, 'epoch': 0.65}
{'loss': 1.5157, 'learning_rate': 2.0256641966383515e-05, 'epoch': 0.65}
{'loss': 1.3676, 'learning_rate': 2.0253930959696367e-05, 'epoch': 0.65}
{'loss': 1.3213, 'learning_rate': 2.025121995300922e-05, 'epoch': 0.65}
{'loss': 1.2879, 'learning_rate': 2.0248508946322068e-05, 'epoch': 0.65}
{'loss': 1.2519, 'learning_rate': 2.024579793963492e-05, 'epoch': 0.65}
{'loss': 1.2649, 'learning_rate': 2.024308693294777e-05, 'epoch': 0.65}
{'loss': 0.8982, 'learning_rate': 2.024037592626062e-05, 'epoch': 0.65}

 33%|███▎      | 3601/11066 [13:12<26:32,  4.69it/s]
 33%|███▎      | 3602/11066 [13:12<26:30,  4.69it/s]
                                                    

 33%|███▎      | 3602/11066 [13:12<26:30,  4.69it/s]
 33%|███▎      | 3603/11066 [13:12<26:29,  4.70it/s]
                                                    

 33%|███▎      | 3603/11066 [13:12<26:29,  4.70it/s]
 33%|███▎      | 3604/11066 [13:12<26:37,  4.67it/s]
                                                    

 33%|███▎      | 3604/11066 [13:12<26:37,  4.67it/s]
 33%|███▎      | 3605/11066 [13:12<26:23,  4.71it/s]
                                                    

 33%|███▎      | 3605/11066 [13:12<26:23,  4.71it/s]
 33%|███▎      | 3606/11066 [13:13<26:35,  4.67it/s]
                                                    

 33%|███▎      | 3606/11066 [13:13<26:35,  4.67it/s]
 33%|███▎      | 3607/11066 [13:13<26:24,  4.71it/s]
                                                    

 33%|███▎      | 3607/11066 [13:13<26:24,  4.71it/s]
 33%|███▎      | 3608/11066 [13:13<26:19,  4.72it/s]
                                                    

 33%|███▎      | 3608/11066 [13:13<26:19,  4.72it/s]
 33%|███▎      | 3609/11066 [13:13<27:04,  4.59it/s]
                                                    

 33%|███▎      | 3609/11066 [13:13<27:04,  4.59it/s]
 33%|███▎      | 3610/11066 [13:13<27:20,  4.54it/s]
                                                    

 33%|███▎      | 3610/11066 [13:13<27:20,  4.54it/s]
 33%|███▎      | 3611/11066 [13:14<27:26,  4.53it/s]
                                                    

 33%|███▎      | 3611/11066 [13:14<27:26,  4.53it/s]
 33%|███▎      | 3612/11066 [13:14<27:29,  4.52it/s]
                                                    

 33%|███▎      | 3612/11066 [13:14<27:29,  4.52it/s]
 33%|███▎      | 3613/11066 [13:14<27:32,  4.51it/s]
                                                    

 33%|███▎      | 3613/11066 [13:14<27:32,  4.51it/s]
 33%|███▎      | 3614/11066 [13:14<27:22,  4.54it/s]
                                                    

 33%|███▎      | 3614/11066 [13:14<27:22,  4.54it/s]
 33%|███▎      | 3615/11066 [13:15<27:08,  4.57it/s]
                                                    

 33%|███▎      | 3615/11066 [13:15<27:08,  4.57it/s]
 33%|███▎      | 3616/11066 [13:15<27:20,  4.54it/s]
                                                    

 33%|███▎      | 3616/11066 [13:15<27:20,  4.54it/s]
 33%|███▎      | 3617/11066 [13:15<27:03,  4.59it/s]
                                                    

 33%|███▎      | 3617/11066 [13:15<27:03,  4.59it/s]
 33%|███▎      | 3618/11066 [13:15<27:01,  4.59it/s]
                                                    

 33%|███▎      | 3618/11066 [13:15<27:01,  4.59it/s]
 33%|███▎      | 3619/11066 [13:15<26:51,  4.62it/s]
                                                    

 33%|███▎      | 3619/11066 [13:15<26:51,  4.62it/s]
 33%|███▎      | 3620/11066 [13:16<26:51,  4.62it/s]
                                                    

 33%|███▎      | 3620/11066 [13:16<26:51,  4.62it/s]
 33%|███▎      | 3621/11066 [13:16<26:42,  4.65it/s]
                                                    

 33%|███▎      | 3621/11066 [13:16<26:42,  4.65it/s]
 33%|███▎      | 3622/11066 [13:16<27:00,  4.59it/s]
                                                    

 33%|███▎      | 3622/11066 [13:16<27:00,  4.59it/s]
 33%|███▎      | 3623/11066 [13:16<26:58,  4.60it/s]
                                                    

 33%|███▎      | 3623/11066 [13:16<26:58,  4.60it/s]
 33%|███▎      | 3624/11066 [13:17<26:57,  4.60it/s]
                                                    

 33%|███▎      | 3624/11066 [13:17<26:57,  4.60it/s]
 33%|███▎      | 3625/11066 [13:17<27:08,  4.57it/s]
                                                    

 33%|███▎      | 3625/11066 [13:17<27:08,  4.57it/s]
 33%|███▎      | 3626/11066 [13:17<26:53,  4.61it/s]
                                                    

 33%|███▎      | 3626/11066 [13:17<26:53,  4.61it/s]
 33%|███▎      | 3627/11066 [13:17<27:04,  4.58it/s]
                                                    

 33%|███▎      | 3627/11066 [13:17<27:04,  4.58it/s]
 33%|███▎      | 3628/11066 [13:17<26:59,  4.59it/s]
                                                    

 33%|███▎      | 3628/11066 [13:17<26:59,  4.59it/s]
 33%|███▎      | 3629/11066 [13:18<27:06,  4.57it/s]
                                                    

 33%|███▎      | 3629/11066 [13:18<27:06,  4.57it/s]
 33%|███▎      | 3630/11066 [13:18<26:58,  4.60it/s]
                                                    

 33%|███▎      | 3630/11066 [13:18<26:58,  4.60it/s]
 33%|███▎      | 3631/11066 [13:18<26:58,  4.59it/s]
                                                    

 33%|███▎      | 3631/11066 [13:18<26:58,  4.59it/s]
 33%|███▎      | 3632/11066 [13:18<26:48,  4.62it/s]
                                                    

 33%|███▎      | 3632/11066 [13:18<26:48,  4.62it/s]
 33%|███▎      | 3633/11066 [13:18<26:33,  4.66it/s]
                                                    

 33%|███▎      | 3633/11066 [13:18<26:33,  4.66it/s]
 33%|███▎      | 3634/11066 [13:19<26:52,  4.61it/s]
                                                    

 33%|███▎      | 3634/11066 [13:19<26:52,  4.61it/s]
 33%|███▎      | 3635/11066 [13:19<27:06,  4.57it/s]
                                                    

 33%|███▎      | 3635/11066 [13:19<27:06,  4.57it/s]
 33%|███▎      | 3636/11066 [13:19<27:23,  4.52it/s]
                                                    

 33%|███▎      | 3636/11066 [13:19<27:23,  4.52it/s]
 33%|███▎      | 3637/11066 [13:19<27:30,  4.50it/s]
                                                    

 33%|███▎      | 3637/11066 [13:19<27:30,  4.50it/s]
 33%|███▎      | 3638/11066 [13:20<27:29,  4.50it/s]
                                                    

 33%|███▎      | 3638/11066 [13:20<27:29,  4.50it/s]
 33%|███▎      | 3639/11066 [13:20<27:28,  4.50it/s]
                                                    

 33%|███▎      | 3639/11066 [13:20<27:28,  4.50it/s]
 33%|███▎      | 3640/11066 [13:20<27:29,  4.50it/s]
                                                    

 33%|███▎      | 3640/11066 [13:20<27:29,  4.50it/s]
 33%|███▎      | 3641/11066 [13:20<27:30,  4.50it/s]
                                                    

 33%|███▎      | 3641/11066 [13:20<27:30,  4.50it/s]
 33%|███▎      | 3642/11066 [13:20<27:28,  4.50it/s]
                                                    

 33%|███▎      | 3642/11066 [13:20<27:28,  4.50it/s]
 33%|███▎      | 3643/11066 [13:21<27:28,  4.50it/s]
                                                    

 33%|███▎      | 3643/11066 [13:21<27:28,  4.50it/s]
 33%|███▎      | 3644/11066 [13:21<27:05,  4.57it/s]
                                                    

 33%|███▎      | 3644/11066 [13:21<27:05,  4.57it/s]
 33%|███▎      | 3645/11066 [13:21<27:12,  4.54it/s]
                                                    

 33%|███▎      | 3645/11066 [13:21<27:12,  4.54it/s]
 33%|███▎      | 3646/11066 [13:21<27:05,  4.56it/s]
                                                    

 33%|███▎      | 3646/11066 [13:21<27:05,  4.56it/s]
 33%|███▎      | 3647/11066 [13:22<26:48,  4.61it/s]
                                                    

 33%|███▎      | 3647/11066 [13:22<26:48,  4.61it/s]
 33%|███▎      | 3648/11066 [13:22<26:42,  4.63it/s]
                                                    

 33%|███▎      | 3648/11066 [13:22<26:42,  4.63it/s]
 33%|███▎      | 3649/11066 [13:22<26:35,  4.65it/s]
                                                    

 33%|███▎      | 3649/11066 [13:22<26:35,  4.65it/s]
 33%|███▎      | 3650/11066 [13:22<27:22,  4.52it/s]
                                                    

 33%|███▎      | 3650/11066 [13:22<27:22,  4.52it/s]
 33%|███▎      | 3651/11066 [13:22<27:26,  4.50it/s]
                                                    

 33%|███▎      | 3651/11066 [13:22<27:26,  4.50it/s]
 33%|███▎      | 3652/11066 [13:23<27:36,  4.48it/s]
                                                    

 33%|███▎      | 3652/11066 [13:23<27:36,  4.48it/s]
 33%|███▎      | 3653/11066 [13:23<27:10,  4.55it/s]
                                                    

 33%|███▎      | 3653/11066 [13:23<27:10,  4.55it/s]
 33%|███▎      | 3654/11066 [13:23<27:20,  4.52it/s]
                                                    

 33%|███▎      | 3654/11066 [13:23<27:20,  4.52it/s]
 33%|███▎      | 3655/11066 [13:23<27:22,  4.51it/s]
                                                    

 33%|███▎      | 3655/11066 [13:23<27:22,  4.51it/s]
 33%|███▎      | 3656/11066 [13:24<27:24,  4.51it/s]
                                                    

 33%|███▎      | 3656/11066 [13:24<27:24,  4.51it/s]
 33%|███▎      | 3657/11066 [13:24<27:26,  4.50it/s]
                                                    

 33%|███▎      | 3657/11066 [13:24<27:26,  4.50it/s]
 33%|███▎      | 3658/11066 [13:24<27:26,  4.50it/s]
                                                    

 33%|███▎      | 3658/11066 [13:24<27:26,  4.50it/s]
 33%|███▎      | 3659/11066 [13:24<27:46,  4.44it/s]
                                                    

 33%|███▎      | 3659/11066 [13:24<27:46,  4.44it/s]
 33%|███▎      | 3660/11066 [13:24<27:43,  4.45it/s]
                                                    

 33%|███▎      | 3660/11066 [13:24<27:43,  4.45it/s]
 33%|███▎      | 3661/11066 [13:25<27:16,  4.52it/s]
                                                    

 33%|███▎      | 3661/11066 [13:25<27:16,  4.52it/s]
 33%|███▎      | 3662/11066 [13:25<26:56,  4.58it/s]
                                                    

 33%|███▎      | 3662/11066 [13:25<26:56,  4.58it/s]
 33%|███▎      | 3663/11066 [13:25<26:43,  4.62it/s]
                                                    

 33%|███▎      | 3663/11066 [13:25<26:43,  4.62it/s]
 33%|███▎      | 3664/11066 [13:25<27:00,  4.57it/s]
                                                    

 33%|███▎      | 3664/11066 [13:25<27:00,  4.57it/s]
 33%|███▎      | 3665/11066 [13:26<26:56,  4.58it/s]
                                                    

 33%|███▎      | 3665/11066 [13:26<26:56,  4.58it/s]
 33%|███▎      | 3666/11066 [13:26<26:39,  4.63it/s]
                                                    

 33%|███▎      | 3666/11066 [13:26<26:39,  4.63it/s]
 33%|███▎      | 3667/11066 [13:26<26:42,  4.62it/s]
                                                    

 33%|███▎      | 3667/11066 [13:26<26:42,  4.62it/s]
 33%|███▎      | 3668/11066 [13:26<26:57,  4.57it/s]
                                                    

 33%|███▎      | 3668/11066 [13:26<26:57,  4.57it/s]
 33%|███▎      | 3669/11066 [13:26<27:05,  4.55it/s]
                                                    

 33%|███▎      | 3669/11066 [13:26<27:05,  4.55it/s]
 33%|███▎      | 3670/11066 [13:27<27:13,  4.53it/s]
                                                    

 33%|███▎      | 3670/11066 [13:27<27:13,  4.53it/s]
 33%|███▎      | 3671/11066 [13:27<27:17,  4.52it/s]
                                                    

 33%|███▎      | 3671/11066 [13:27<27:17,  4.52it/s]
 33%|███▎      | 3672/11066 [13:27<27:18,  4.51it/s]
                                                    

 33%|███▎      | 3672/11066 [13:27<27:18,  4.51it/s]
 33%|███▎      | 3673/11066 [13:27<27:20,  4.51it/s]
                                                    

 33%|███▎      | 3673/11066 [13:27<27:20,  4.51it/s]
 33%|███▎      | 3674/11066 [13:28<27:21,  4.50it/s]
                                                    

 33%|███▎      | 3674/11066 [13:28<27:21,  4.50it/s]
 33%|███▎      | 3675/11066 [13:28<27:22,  4.50it/s]
                                                    

 33%|███▎      | 3675/11066 [13:28<27:22,  4.50it/s]
 33%|███▎      | 3676/11066 [13:28<27:09,  4.54it/s]
                                                    

 33%|███▎      | 3676/11066 [13:28<27:09,  4.54it/s]
 33%|███▎      | 3677/11066 [13:28<26:57,  4.57it/s]
                                                    

 33%|███▎      | 3677/11066 [13:28<26:57,  4.57it/s]
 33%|███▎      | 3678/11066 [13:28<27:11,  4.53it/s]
                                                    

 33%|███▎      | 3678/11066 [13:28<27:11,  4.53it/s]
 33%|███▎      | 3679/11066 [13:29<26:53,  4.58it/s]
                                                    

 33%|███▎      | 3679/11066 [13:29<26:53,  4.58it/s]
 33%|███▎      | 3680/11066 [13:29<26:39,  4.62it/s]
                                                    

 33%|███▎      | 3680/11066 [13:29<26:39,  4.62it/s]
 33%|███▎      | 3681/11066 [13:29<26:38,  4.62it/s]
                                                    

 33%|███▎      | 3681/11066 [13:29<26:38,  4.62it/s]
 33%|███▎      | 3682/11066 [13:29<26:25,  4.66it/s]
                                                    

 33%|███▎      | 3682/11066 [13:29<26:25,  4.66it/s]
 33%|███▎      | 3683/11066 [13:29<26:32,  4.64it/s]
                                                    

 33%|███▎      | 3683/11066 [13:29<26:32,  4.64it/s]
 33%|███▎      | 3684/11066 [13:30<26:25,  4.66it/s]
                                                    

 33%|███▎      | 3684/11066 [13:30<26:25,  4.66it/s]
 33%|███▎      | 3685/11066 [13:30<26:31,  4.64it/s]
                                                    

 33%|███▎      | 3685/11066 [13:30<26:31,  4.64it/s]
 33%|███▎      | 3686/11066 [13:30<26:39,  4.61it/s]
                                                    

 33%|███▎      | 3686/11066 [13:30<26:39,  4.61it/s]
 33%|███▎      | 3687/11066 [13:30<26:27,  4.65it/s]
                                                    

 33%|███▎      | 3687/11066 [13:30<26:27,  4.65it/s]
 33%|███▎      | 3688/11066 [13:31<26:29,  4.64it/s]
                                                    

 33%|███▎      | 3688/11066 [13:31<26:29,  4.64it/s]
 33%|███▎      | 3689/11066 [13:31<26:38,  4.62it/s]
                                                    

 33%|███▎      | 3689/11066 [13:31<26:38,  4.62it/s]
 33%|███▎      | 3690/11066 [13:31<26:35,  4.62it/s]
                                                    

 33%|███▎      | 3690/11066 [13:31<26:35,  4.62it/s]
 33%|███▎      | 3691/11066 [13:31<26:41,  4.60it/s]
                                                    

 33%|███▎      | 3691/11066 [13:31<26:41,  4.60it/s]
 33%|███▎      | 3692/11066 [13:31<26:52,  4.57it/s]
                                                    

 33%|███▎      | 3692/11066 [13:31<26:52,  4.57it/s]
 33%|███▎      | 3693/11066 [13:32<26:47,  4.59it/s]
                                                    

 33%|███▎      | 3693/11066 [13:32<26:47,  4.59it/s]
 33%|███▎      | 3694/11066 [13:32<26:33,  4.63it/s]
                                                    

 33%|███▎      | 3694/11066 [13:32<26:33,  4.63it/s]
 33%|███▎      | 3695/11066 [13:32<26:36,  4.62it/s]
                                                    

 33%|███▎      | 3695/11066 [13:32<26:36,  4.62it/s]
 33%|███▎      | 3696/11066 [13:32<26:35,  4.62it/s]
                                                    

 33%|███▎      | 3696/11066 [13:32<26:35,  4.62it/s]
 33%|███▎      | 3697/11066 [13:32<26:20,  4.66it/s]
                                                    

 33%|███▎      | 3697/11066 [13:32<26:20,  4.66it/s]
 33%|███▎      | 3698/11066 [13:33<26:22,  4.66it/s]
                                                    

 33%|███▎      | 3698/11066 [13:33<26:22,  4.66it/s]
 33%|███▎      | 3699/11066 [13:33<26:24,  4.65it/s]
                                                    

 33%|███▎      | 3699/11066 [13:33<26:24,  4.65it/s]
 33%|███▎      | 3700/11066 [13:33<26:18,  4.67it/s]
                                                    

 33%|███▎      | 3700/11066 [13:33<26:18,  4.67it/s]
 33%|███▎      | 3701/11066 [13:33<26:14,  4.68it/s]
                                                    

 33%|███▎      | 3701/11066 [13:33<26:14,  4.68it/s]
 33%|███▎      | 3702/11066 [13:34<26:21,  4.65it/s]
                                                    

 33%|███▎      | 3702/11066 [13:34<26:21,  4.65it/s]
 33%|███▎      | 3703/11066 [13:34<26:07,  4.70it/s]
                                                    

 33%|███▎      | 3703/11066 [13:34<26:07,  4.70it/s]
 33%|███▎      | 3704/11066 [13:34<26:10,  4.69it/s]
                                                    

 33%|███▎      | 3704/11066 [13:34<26:10,  4.69it/s]
 33%|███▎      | 3705/11066 [13:34<26:17,  4.67it/s]
                                                    

 33%|███▎      | 3705/11066 [13:34<26:17,  4.67it/s]
 33%|███▎      | 3706/11066 [13:34<26:13,  4.68it/s]
                                                    

 33%|███▎      | 3706/11066 [13:34<26:13,  4.68it/s]
 33%|███▎      | 3707/11066 [13:35<26:39,  4.60it/s]
                                                    

 33%|███▎      | 3707/11066 [13:35<26:39,  4.60it/s]
 34%|███▎      | 3708/11066 [13:35<26:30,  4.62it/s]
                                                    

 34%|███▎      | 3708/11066 [13:35<26:30,  4.62it/s]
 34%|███▎      | 3709/11066 [13:35<26:31,  4.62it/s]
                                                    

 34%|███▎      | 3709/11066 [13:35<26:31,  4.62it/s]
 34%|███▎      | 3710/11066 [13:35<26:13,  4.67it/s]
                                                    

 34%|███▎      | 3710/11066 [13:35<26:13,  4.67it/s]
 34%|███▎      | 3711/11066 [13:35<26:20,  4.65it/s]
                                                    

 34%|███▎      | 3711/11066 [13:35<26:20,  4.65it/s]
 34%|███▎      | 3712/11066 [13:36<26:10,  4.68it/s]
                                                    

 34%|███▎      | 3712/11066 [13:36<26:10,  4.68it/s]
 34%|███▎      | 3713/11066 [13:36<25:59,  4.71it/s]
                                                    
{'loss': 1.5512, 'learning_rate': 2.0237664919573468e-05, 'epoch': 0.65}
{'loss': 1.7909, 'learning_rate': 2.0234953912886317e-05, 'epoch': 0.65}
{'loss': 1.0944, 'learning_rate': 2.023224290619917e-05, 'epoch': 0.65}
{'loss': 0.8527, 'learning_rate': 2.022953189951202e-05, 'epoch': 0.65}
{'loss': 1.0548, 'learning_rate': 2.022682089282487e-05, 'epoch': 0.65}
{'loss': 0.7332, 'learning_rate': 2.022410988613772e-05, 'epoch': 0.65}
{'loss': 1.2988, 'learning_rate': 2.0221398879450572e-05, 'epoch': 0.65}
{'loss': 1.2426, 'learning_rate': 2.0218687872763417e-05, 'epoch': 0.65}
{'loss': 1.1944, 'learning_rate': 2.021597686607627e-05, 'epoch': 0.65}
{'loss': 1.1323, 'learning_rate': 2.021326585938912e-05, 'epoch': 0.65}
{'loss': 1.7349, 'learning_rate': 2.021055485270197e-05, 'epoch': 0.65}
{'loss': 1.7982, 'learning_rate': 2.020784384601482e-05, 'epoch': 0.65}
{'loss': 1.3135, 'learning_rate': 2.020513283932767e-05, 'epoch': 0.65}
{'loss': 1.017, 'learning_rate': 2.020242183264052e-05, 'epoch': 0.65}
{'loss': 1.0909, 'learning_rate': 2.0199710825953373e-05, 'epoch': 0.65}
{'loss': 1.02, 'learning_rate': 2.019699981926622e-05, 'epoch': 0.65}
{'loss': 1.1153, 'learning_rate': 2.019428881257907e-05, 'epoch': 0.65}
{'loss': 1.1785, 'learning_rate': 2.0191577805891922e-05, 'epoch': 0.65}
{'loss': 1.7016, 'learning_rate': 2.018886679920477e-05, 'epoch': 0.65}
{'loss': 1.8671, 'learning_rate': 2.0186155792517622e-05, 'epoch': 0.65}
{'loss': 2.3902, 'learning_rate': 2.0183444785830474e-05, 'epoch': 0.65}
{'loss': 0.9382, 'learning_rate': 2.0180733779143323e-05, 'epoch': 0.65}
{'loss': 0.993, 'learning_rate': 2.0178022772456174e-05, 'epoch': 0.65}
{'loss': 0.9339, 'learning_rate': 2.017531176576902e-05, 'epoch': 0.65}
{'loss': 1.1157, 'learning_rate': 2.017260075908187e-05, 'epoch': 0.66}
{'loss': 1.6316, 'learning_rate': 2.0169889752394723e-05, 'epoch': 0.66}
{'loss': 0.8353, 'learning_rate': 2.016717874570757e-05, 'epoch': 0.66}
{'loss': 1.2622, 'learning_rate': 2.0164467739020423e-05, 'epoch': 0.66}
{'loss': 1.1541, 'learning_rate': 2.0161756732333275e-05, 'epoch': 0.66}
{'loss': 0.8347, 'learning_rate': 2.0159045725646124e-05, 'epoch': 0.66}
{'loss': 0.716, 'learning_rate': 2.0156334718958976e-05, 'epoch': 0.66}
{'loss': 0.7632, 'learning_rate': 2.0153623712271824e-05, 'epoch': 0.66}
{'loss': 2.0456, 'learning_rate': 2.0150912705584672e-05, 'epoch': 0.66}
{'loss': 0.6377, 'learning_rate': 2.0148201698897524e-05, 'epoch': 0.66}
{'loss': 0.9711, 'learning_rate': 2.0145490692210373e-05, 'epoch': 0.66}
{'loss': 0.7942, 'learning_rate': 2.0142779685523225e-05, 'epoch': 0.66}
{'loss': 1.4861, 'learning_rate': 2.0140068678836076e-05, 'epoch': 0.66}
{'loss': 1.3111, 'learning_rate': 2.0137357672148925e-05, 'epoch': 0.66}
{'loss': 1.9785, 'learning_rate': 2.0134646665461777e-05, 'epoch': 0.66}
{'loss': 1.0455, 'learning_rate': 2.0131935658774625e-05, 'epoch': 0.66}
{'loss': 0.5749, 'learning_rate': 2.0129224652087473e-05, 'epoch': 0.66}
{'loss': 1.3891, 'learning_rate': 2.0126513645400325e-05, 'epoch': 0.66}
{'loss': 0.7461, 'learning_rate': 2.0123802638713177e-05, 'epoch': 0.66}
{'loss': 0.7936, 'learning_rate': 2.0121091632026026e-05, 'epoch': 0.66}
{'loss': 0.6865, 'learning_rate': 2.0118380625338877e-05, 'epoch': 0.66}
{'loss': 1.0683, 'learning_rate': 2.0115669618651726e-05, 'epoch': 0.66}
{'loss': 0.9281, 'learning_rate': 2.0112958611964578e-05, 'epoch': 0.66}
{'loss': 0.9059, 'learning_rate': 2.0110247605277426e-05, 'epoch': 0.66}
{'loss': 0.7708, 'learning_rate': 2.0107536598590275e-05, 'epoch': 0.66}
{'loss': 1.0112, 'learning_rate': 2.0104825591903126e-05, 'epoch': 0.66}
{'loss': 0.8516, 'learning_rate': 2.0102114585215978e-05, 'epoch': 0.66}
{'loss': 0.7029, 'learning_rate': 2.0099403578528827e-05, 'epoch': 0.66}
{'loss': 0.7266, 'learning_rate': 2.009669257184168e-05, 'epoch': 0.66}
{'loss': 1.4128, 'learning_rate': 2.009398156515453e-05, 'epoch': 0.66}
{'loss': 0.7282, 'learning_rate': 2.009127055846738e-05, 'epoch': 0.66}
{'loss': 1.7294, 'learning_rate': 2.0088559551780227e-05, 'epoch': 0.66}
{'loss': 0.7275, 'learning_rate': 2.008584854509308e-05, 'epoch': 0.66}
{'loss': 1.4397, 'learning_rate': 2.0083137538405927e-05, 'epoch': 0.66}
{'loss': 1.4077, 'learning_rate': 2.008042653171878e-05, 'epoch': 0.66}
{'loss': 1.05, 'learning_rate': 2.0077715525031628e-05, 'epoch': 0.66}
{'loss': 1.3948, 'learning_rate': 2.007500451834448e-05, 'epoch': 0.66}
{'loss': 1.5731, 'learning_rate': 2.007229351165733e-05, 'epoch': 0.66}
{'loss': 0.8805, 'learning_rate': 2.006958250497018e-05, 'epoch': 0.66}
{'loss': 1.622, 'learning_rate': 2.0066871498283028e-05, 'epoch': 0.66}
{'loss': 0.9625, 'learning_rate': 2.006416049159588e-05, 'epoch': 0.66}
{'loss': 1.5329, 'learning_rate': 2.006144948490873e-05, 'epoch': 0.66}
{'loss': 1.1283, 'learning_rate': 2.005873847822158e-05, 'epoch': 0.66}
{'loss': 1.0333, 'learning_rate': 2.0056027471534432e-05, 'epoch': 0.66}
{'loss': 0.6907, 'learning_rate': 2.005331646484728e-05, 'epoch': 0.66}
{'loss': 0.89, 'learning_rate': 2.0050605458160132e-05, 'epoch': 0.66}
{'loss': 1.4768, 'learning_rate': 2.004789445147298e-05, 'epoch': 0.66}
{'loss': 1.1558, 'learning_rate': 2.004518344478583e-05, 'epoch': 0.66}
{'loss': 0.6401, 'learning_rate': 2.004247243809868e-05, 'epoch': 0.66}
{'loss': 1.0333, 'learning_rate': 2.003976143141153e-05, 'epoch': 0.66}
{'loss': 0.8987, 'learning_rate': 2.003705042472438e-05, 'epoch': 0.66}
{'loss': 0.6736, 'learning_rate': 2.0034339418037233e-05, 'epoch': 0.66}
{'loss': 0.8723, 'learning_rate': 2.0031628411350082e-05, 'epoch': 0.66}
{'loss': 0.66, 'learning_rate': 2.0028917404662934e-05, 'epoch': 0.66}
{'loss': 0.9167, 'learning_rate': 2.0026206397975785e-05, 'epoch': 0.66}
{'loss': 0.9237, 'learning_rate': 2.002349539128863e-05, 'epoch': 0.67}
{'loss': 1.4225, 'learning_rate': 2.0020784384601482e-05, 'epoch': 0.67}
{'loss': 0.8092, 'learning_rate': 2.001807337791433e-05, 'epoch': 0.67}
{'loss': 0.9835, 'learning_rate': 2.0015362371227183e-05, 'epoch': 0.67}
{'loss': 0.7454, 'learning_rate': 2.0012651364540034e-05, 'epoch': 0.67}
{'loss': 0.6463, 'learning_rate': 2.0009940357852883e-05, 'epoch': 0.67}
{'loss': 1.7042, 'learning_rate': 2.0007229351165735e-05, 'epoch': 0.67}
{'loss': 0.8608, 'learning_rate': 2.0004518344478586e-05, 'epoch': 0.67}
{'loss': 0.8677, 'learning_rate': 2.000180733779143e-05, 'epoch': 0.67}
{'loss': 1.0433, 'learning_rate': 1.9999096331104283e-05, 'epoch': 0.67}
{'loss': 1.1645, 'learning_rate': 1.9996385324417135e-05, 'epoch': 0.67}
{'loss': 0.6941, 'learning_rate': 1.9993674317729984e-05, 'epoch': 0.67}
{'loss': 1.1219, 'learning_rate': 1.9990963311042835e-05, 'epoch': 0.67}
{'loss': 0.7059, 'learning_rate': 1.9988252304355684e-05, 'epoch': 0.67}
{'loss': 0.8843, 'learning_rate': 1.9985541297668536e-05, 'epoch': 0.67}
{'loss': 1.5204, 'learning_rate': 1.9982830290981388e-05, 'epoch': 0.67}
{'loss': 0.8513, 'learning_rate': 1.9980119284294233e-05, 'epoch': 0.67}
{'loss': 1.0107, 'learning_rate': 1.9977408277607084e-05, 'epoch': 0.67}
{'loss': 1.1234, 'learning_rate': 1.9974697270919936e-05, 'epoch': 0.67}
{'loss': 0.8458, 'learning_rate': 1.9971986264232785e-05, 'epoch': 0.67}
{'loss': 1.3555, 'learning_rate': 1.9969275257545636e-05, 'epoch': 0.67}
{'loss': 2.0302, 'learning_rate': 1.996656425085849e-05, 'epoch': 0.67}
{'loss': 1.2269, 'learning_rate': 1.9963853244171337e-05, 'epoch': 0.67}
{'loss': 1.8074, 'learning_rate': 1.996114223748419e-05, 'epoch': 0.67}
{'loss': 0.7036, 'learning_rate': 1.9958431230797034e-05, 'epoch': 0.67}
{'loss': 1.4765, 'learning_rate': 1.9955720224109885e-05, 'epoch': 0.67}
{'loss': 0.8694, 'learning_rate': 1.9953009217422737e-05, 'epoch': 0.67}
{'loss': 0.8117, 'learning_rate': 1.9950298210735586e-05, 'epoch': 0.67}
{'loss': 0.7407, 'learning_rate': 1.9947587204048438e-05, 'epoch': 0.67}
{'loss': 1.18, 'learning_rate': 1.994487619736129e-05, 'epoch': 0.67}
{'loss': 0.7556, 'learning_rate': 1.9942165190674138e-05, 'epoch': 0.67}
{'loss': 0.8502, 'learning_rate': 1.993945418398699e-05, 'epoch': 0.67}
{'loss': 0.5981, 'learning_rate': 1.9936743177299838e-05, 'epoch': 0.67}

 34%|███▎      | 3713/11066 [13:36<25:59,  4.71it/s]
 34%|███▎      | 3714/11066 [13:36<26:17,  4.66it/s]
                                                    

 34%|███▎      | 3714/11066 [13:36<26:17,  4.66it/s]
 34%|███▎      | 3715/11066 [13:36<26:13,  4.67it/s]
                                                    

 34%|███▎      | 3715/11066 [13:36<26:13,  4.67it/s]
 34%|███▎      | 3716/11066 [13:37<26:21,  4.65it/s]
                                                    

 34%|███▎      | 3716/11066 [13:37<26:21,  4.65it/s]
 34%|███▎      | 3717/11066 [13:37<26:08,  4.69it/s]
                                                    

 34%|███▎      | 3717/11066 [13:37<26:08,  4.69it/s]
 34%|███▎      | 3718/11066 [13:37<25:58,  4.71it/s]
                                                    

 34%|███▎      | 3718/11066 [13:37<25:58,  4.71it/s]
 34%|███▎      | 3719/11066 [13:37<26:02,  4.70it/s]
                                                    

 34%|███▎      | 3719/11066 [13:37<26:02,  4.70it/s]
 34%|███▎      | 3720/11066 [13:37<26:09,  4.68it/s]
                                                    

 34%|███▎      | 3720/11066 [13:37<26:09,  4.68it/s]
 34%|███▎      | 3721/11066 [13:38<26:02,  4.70it/s]
                                                    

 34%|███▎      | 3721/11066 [13:38<26:02,  4.70it/s]
 34%|███▎      | 3722/11066 [13:38<26:27,  4.63it/s]
                                                    

 34%|███▎      | 3722/11066 [13:38<26:27,  4.63it/s]
 34%|███▎      | 3723/11066 [13:38<26:47,  4.57it/s]
                                                    

 34%|███▎      | 3723/11066 [13:38<26:47,  4.57it/s]
 34%|███▎      | 3724/11066 [13:38<26:55,  4.54it/s]
                                                    

 34%|███▎      | 3724/11066 [13:38<26:55,  4.54it/s]
 34%|███▎      | 3725/11066 [13:39<26:39,  4.59it/s]
                                                    

 34%|███▎      | 3725/11066 [13:39<26:39,  4.59it/s]
 34%|███▎      | 3726/11066 [13:39<26:51,  4.56it/s]
                                                    

 34%|███▎      | 3726/11066 [13:39<26:51,  4.56it/s]
 34%|███▎      | 3727/11066 [13:39<26:35,  4.60it/s]
                                                    

 34%|███▎      | 3727/11066 [13:39<26:35,  4.60it/s]
 34%|███▎      | 3728/11066 [13:39<26:48,  4.56it/s]
                                                    

 34%|███▎      | 3728/11066 [13:39<26:48,  4.56it/s]
 34%|███▎      | 3729/11066 [13:39<26:32,  4.61it/s]
                                                    

 34%|███▎      | 3729/11066 [13:39<26:32,  4.61it/s]
 34%|███▎      | 3730/11066 [13:40<26:21,  4.64it/s]
                                                    

 34%|███▎      | 3730/11066 [13:40<26:21,  4.64it/s]
 34%|███▎      | 3731/11066 [13:40<26:37,  4.59it/s]
                                                    

 34%|███▎      | 3731/11066 [13:40<26:37,  4.59it/s]
 34%|███▎      | 3732/11066 [13:40<26:48,  4.56it/s]
                                                    

 34%|███▎      | 3732/11066 [13:40<26:48,  4.56it/s]
 34%|███▎      | 3733/11066 [13:40<26:33,  4.60it/s]
                                                    

 34%|███▎      | 3733/11066 [13:40<26:33,  4.60it/s]
 34%|███▎      | 3734/11066 [13:40<27:21,  4.47it/s]
                                                    

 34%|███▎      | 3734/11066 [13:40<27:21,  4.47it/s]
 34%|███▍      | 3735/11066 [13:41<27:00,  4.52it/s]
                                                    

 34%|███▍      | 3735/11066 [13:41<27:00,  4.52it/s]
 34%|███▍      | 3736/11066 [13:41<27:10,  4.50it/s]
                                                    

 34%|███▍      | 3736/11066 [13:41<27:10,  4.50it/s]
 34%|███▍      | 3737/11066 [13:41<27:10,  4.49it/s]
                                                    

 34%|███▍      | 3737/11066 [13:41<27:10,  4.49it/s]
 34%|███▍      | 3738/11066 [13:41<26:41,  4.58it/s]
                                                    

 34%|███▍      | 3738/11066 [13:41<26:41,  4.58it/s]
 34%|███▍      | 3739/11066 [13:42<26:30,  4.61it/s]
                                                    

 34%|███▍      | 3739/11066 [13:42<26:30,  4.61it/s]
 34%|███▍      | 3740/11066 [13:42<26:18,  4.64it/s]
                                                    

 34%|███▍      | 3740/11066 [13:42<26:18,  4.64it/s]
 34%|███▍      | 3741/11066 [13:42<26:10,  4.67it/s]
                                                    

 34%|███▍      | 3741/11066 [13:42<26:10,  4.67it/s]
 34%|███▍      | 3742/11066 [13:42<26:11,  4.66it/s]
                                                    

 34%|███▍      | 3742/11066 [13:42<26:11,  4.66it/s]
 34%|███▍      | 3743/11066 [13:42<26:00,  4.69it/s]
                                                    

 34%|███▍      | 3743/11066 [13:42<26:00,  4.69it/s]
 34%|███▍      | 3744/11066 [13:43<26:09,  4.66it/s]
                                                    

 34%|███▍      | 3744/11066 [13:43<26:09,  4.66it/s]
 34%|███▍      | 3745/11066 [13:43<25:58,  4.70it/s]
                                                    

 34%|███▍      | 3745/11066 [13:43<25:58,  4.70it/s]
 34%|███▍      | 3746/11066 [13:43<25:59,  4.70it/s]
                                                    

 34%|███▍      | 3746/11066 [13:43<25:59,  4.70it/s]
 34%|███▍      | 3747/11066 [13:43<26:05,  4.68it/s]
                                                    

 34%|███▍      | 3747/11066 [13:43<26:05,  4.68it/s]
 34%|███▍      | 3748/11066 [13:43<26:00,  4.69it/s]
                                                    

 34%|███▍      | 3748/11066 [13:43<26:00,  4.69it/s]
 34%|███▍      | 3749/11066 [13:44<25:58,  4.69it/s]
                                                    

 34%|███▍      | 3749/11066 [13:44<25:58,  4.69it/s]
 34%|███▍      | 3750/11066 [13:44<26:24,  4.62it/s]
                                                    

 34%|███▍      | 3750/11066 [13:44<26:24,  4.62it/s]
 34%|███▍      | 3751/11066 [13:44<26:38,  4.58it/s]
                                                    

 34%|███▍      | 3751/11066 [13:44<26:38,  4.58it/s]
 34%|███▍      | 3752/11066 [13:44<26:58,  4.52it/s]
                                                    

 34%|███▍      | 3752/11066 [13:44<26:58,  4.52it/s]
 34%|███▍      | 3753/11066 [13:45<27:04,  4.50it/s]
                                                    

 34%|███▍      | 3753/11066 [13:45<27:04,  4.50it/s]
 34%|███▍      | 3754/11066 [13:45<27:07,  4.49it/s]
                                                    

 34%|███▍      | 3754/11066 [13:45<27:07,  4.49it/s]
 34%|███▍      | 3755/11066 [13:45<27:08,  4.49it/s]
                                                    

 34%|███▍      | 3755/11066 [13:45<27:08,  4.49it/s]
 34%|███▍      | 3756/11066 [13:45<27:08,  4.49it/s]
                                                    

 34%|███▍      | 3756/11066 [13:45<27:08,  4.49it/s]
 34%|███▍      | 3757/11066 [13:45<27:07,  4.49it/s]
                                                    

 34%|███▍      | 3757/11066 [13:46<27:07,  4.49it/s]
 34%|███▍      | 3758/11066 [13:46<27:22,  4.45it/s]
                                                    

 34%|███▍      | 3758/11066 [13:46<27:22,  4.45it/s]
 34%|███▍      | 3759/11066 [13:46<27:31,  4.42it/s]
                                                    

 34%|███▍      | 3759/11066 [13:46<27:31,  4.42it/s]
 34%|███▍      | 3760/11066 [13:46<27:09,  4.48it/s]
                                                    

 34%|███▍      | 3760/11066 [13:46<27:09,  4.48it/s]
 34%|███▍      | 3761/11066 [13:46<27:13,  4.47it/s]
                                                    

 34%|███▍      | 3761/11066 [13:46<27:13,  4.47it/s]
 34%|███▍      | 3762/11066 [13:47<27:13,  4.47it/s]
                                                    

 34%|███▍      | 3762/11066 [13:47<27:13,  4.47it/s]
 34%|███▍      | 3763/11066 [13:47<27:13,  4.47it/s]
                                                    

 34%|███▍      | 3763/11066 [13:47<27:13,  4.47it/s]
 34%|███▍      | 3764/11066 [13:47<27:09,  4.48it/s]
                                                    

 34%|███▍      | 3764/11066 [13:47<27:09,  4.48it/s]
 34%|███▍      | 3765/11066 [13:47<27:07,  4.49it/s]
                                                    

 34%|███▍      | 3765/11066 [13:47<27:07,  4.49it/s]
 34%|███▍      | 3766/11066 [13:48<27:04,  4.49it/s]
                                                    

 34%|███▍      | 3766/11066 [13:48<27:04,  4.49it/s]
 34%|███▍      | 3767/11066 [13:48<27:02,  4.50it/s]
                                                    

 34%|███▍      | 3767/11066 [13:48<27:02,  4.50it/s]
 34%|███▍      | 3768/11066 [13:48<27:02,  4.50it/s]
                                                    

 34%|███▍      | 3768/11066 [13:48<27:02,  4.50it/s]
 34%|███▍      | 3769/11066 [13:48<27:04,  4.49it/s]
                                                    

 34%|███▍      | 3769/11066 [13:48<27:04,  4.49it/s]
 34%|███▍      | 3770/11066 [13:48<27:03,  4.49it/s]
                                                    

 34%|███▍      | 3770/11066 [13:48<27:03,  4.49it/s]
 34%|███▍      | 3771/11066 [13:49<26:49,  4.53it/s]
                                                    

 34%|███▍      | 3771/11066 [13:49<26:49,  4.53it/s]
 34%|███▍      | 3772/11066 [13:49<26:59,  4.50it/s]
                                                    

 34%|███▍      | 3772/11066 [13:49<26:59,  4.50it/s]
 34%|███▍      | 3773/11066 [13:49<27:04,  4.49it/s]
                                                    

 34%|███▍      | 3773/11066 [13:49<27:04,  4.49it/s]
 34%|███▍      | 3774/11066 [13:49<27:04,  4.49it/s]
                                                    

 34%|███▍      | 3774/11066 [13:49<27:04,  4.49it/s]
 34%|███▍      | 3775/11066 [13:50<27:03,  4.49it/s]
                                                    

 34%|███▍      | 3775/11066 [13:50<27:03,  4.49it/s]
 34%|███▍      | 3776/11066 [13:50<27:02,  4.49it/s]
                                                    

 34%|███▍      | 3776/11066 [13:50<27:02,  4.49it/s]
 34%|███▍      | 3777/11066 [13:50<27:03,  4.49it/s]
                                                    

 34%|███▍      | 3777/11066 [13:50<27:03,  4.49it/s]
 34%|███▍      | 3778/11066 [13:50<27:02,  4.49it/s]
                                                    

 34%|███▍      | 3778/11066 [13:50<27:02,  4.49it/s]
 34%|███▍      | 3779/11066 [13:50<27:00,  4.50it/s]
                                                    

 34%|███▍      | 3779/11066 [13:50<27:00,  4.50it/s]
 34%|███▍      | 3780/11066 [13:51<26:49,  4.53it/s]
                                                    

 34%|███▍      | 3780/11066 [13:51<26:49,  4.53it/s]
 34%|███▍      | 3781/11066 [13:51<27:03,  4.49it/s]
                                                    

 34%|███▍      | 3781/11066 [13:51<27:03,  4.49it/s]
 34%|███▍      | 3782/11066 [13:51<27:00,  4.49it/s]
                                                    

 34%|███▍      | 3782/11066 [13:51<27:00,  4.49it/s]
 34%|███▍      | 3783/11066 [13:51<27:01,  4.49it/s]
                                                    

 34%|███▍      | 3783/11066 [13:51<27:01,  4.49it/s]
 34%|███▍      | 3784/11066 [13:52<27:00,  4.49it/s]
                                                    

 34%|███▍      | 3784/11066 [13:52<27:00,  4.49it/s]
 34%|███▍      | 3785/11066 [13:52<27:01,  4.49it/s]
                                                    

 34%|███▍      | 3785/11066 [13:52<27:01,  4.49it/s]
 34%|███▍      | 3786/11066 [13:52<27:06,  4.48it/s]
                                                    

 34%|███▍      | 3786/11066 [13:52<27:06,  4.48it/s]
 34%|███▍      | 3787/11066 [13:52<27:09,  4.47it/s]
                                                    

 34%|███▍      | 3787/11066 [13:52<27:09,  4.47it/s]
 34%|███▍      | 3788/11066 [13:52<27:07,  4.47it/s]
                                                    

 34%|███▍      | 3788/11066 [13:52<27:07,  4.47it/s]
 34%|███▍      | 3789/11066 [13:53<26:59,  4.49it/s]
                                                    

 34%|███▍      | 3789/11066 [13:53<26:59,  4.49it/s]
 34%|███▍      | 3790/11066 [13:53<27:02,  4.48it/s]
                                                    

 34%|███▍      | 3790/11066 [13:53<27:02,  4.48it/s]
 34%|███▍      | 3791/11066 [13:53<27:02,  4.48it/s]
                                                    

 34%|███▍      | 3791/11066 [13:53<27:02,  4.48it/s]
 34%|███▍      | 3792/11066 [13:53<27:29,  4.41it/s]
                                                    

 34%|███▍      | 3792/11066 [13:53<27:29,  4.41it/s]
 34%|███▍      | 3793/11066 [13:54<27:28,  4.41it/s]
                                                    

 34%|███▍      | 3793/11066 [13:54<27:28,  4.41it/s]
 34%|███▍      | 3794/11066 [13:54<27:39,  4.38it/s]
                                                    

 34%|███▍      | 3794/11066 [13:54<27:39,  4.38it/s]
 34%|███▍      | 3795/11066 [13:54<27:15,  4.45it/s]
                                                    

 34%|███▍      | 3795/11066 [13:54<27:15,  4.45it/s]
 34%|███▍      | 3796/11066 [13:54<26:49,  4.52it/s]
                                                    

 34%|███▍      | 3796/11066 [13:54<26:49,  4.52it/s]
 34%|███▍      | 3797/11066 [13:54<26:30,  4.57it/s]
                                                    

 34%|███▍      | 3797/11066 [13:54<26:30,  4.57it/s]
 34%|███▍      | 3798/11066 [13:55<26:07,  4.64it/s]
                                                    

 34%|███▍      | 3798/11066 [13:55<26:07,  4.64it/s]
 34%|███▍      | 3799/11066 [13:55<26:17,  4.61it/s]
                                                    

 34%|███▍      | 3799/11066 [13:55<26:17,  4.61it/s]
 34%|███▍      | 3800/11066 [13:55<26:18,  4.60it/s]
                                                    

 34%|███▍      | 3800/11066 [13:55<26:18,  4.60it/s]
 34%|███▍      | 3801/11066 [13:55<26:00,  4.65it/s]
                                                    

 34%|███▍      | 3801/11066 [13:55<26:00,  4.65it/s]
 34%|███▍      | 3802/11066 [13:55<26:06,  4.64it/s]
                                                    

 34%|███▍      | 3802/11066 [13:55<26:06,  4.64it/s]
 34%|███▍      | 3803/11066 [13:56<25:50,  4.68it/s]
                                                    

 34%|███▍      | 3803/11066 [13:56<25:50,  4.68it/s]
 34%|███▍      | 3804/11066 [13:56<26:07,  4.63it/s]
                                                    

 34%|███▍      | 3804/11066 [13:56<26:07,  4.63it/s]
 34%|███▍      | 3805/11066 [13:56<26:28,  4.57it/s]
                                                    

 34%|███▍      | 3805/11066 [13:56<26:28,  4.57it/s]
 34%|███▍      | 3806/11066 [13:56<26:14,  4.61it/s]
                                                    

 34%|███▍      | 3806/11066 [13:56<26:14,  4.61it/s]
 34%|███▍      | 3807/11066 [13:57<26:04,  4.64it/s]
                                                    

 34%|███▍      | 3807/11066 [13:57<26:04,  4.64it/s]
 34%|███▍      | 3808/11066 [13:57<26:08,  4.63it/s]
                                                    

 34%|███▍      | 3808/11066 [13:57<26:08,  4.63it/s]
 34%|███▍      | 3809/11066 [13:57<25:56,  4.66it/s]
                                                    

 34%|███▍      | 3809/11066 [13:57<25:56,  4.66it/s]
 34%|███▍      | 3810/11066 [13:57<25:49,  4.68it/s]
                                                    

 34%|███▍      | 3810/11066 [13:57<25:49,  4.68it/s]
 34%|███▍      | 3811/11066 [13:57<26:07,  4.63it/s]
                                                    

 34%|███▍      | 3811/11066 [13:57<26:07,  4.63it/s]
 34%|███▍      | 3812/11066 [13:58<25:59,  4.65it/s]
                                                    

 34%|███▍      | 3812/11066 [13:58<25:59,  4.65it/s]
 34%|███▍      | 3813/11066 [13:58<25:53,  4.67it/s]
                                                    

 34%|███▍      | 3813/11066 [13:58<25:53,  4.67it/s]
 34%|███▍      | 3814/11066 [13:58<25:49,  4.68it/s]
                                                    

 34%|███▍      | 3814/11066 [13:58<25:49,  4.68it/s]
 34%|███▍      | 3815/11066 [13:58<25:45,  4.69it/s]
                                                    

 34%|███▍      | 3815/11066 [13:58<25:45,  4.69it/s]
 34%|███▍      | 3816/11066 [13:58<25:42,  4.70it/s]
                                                    

 34%|███▍      | 3816/11066 [13:58<25:42,  4.70it/s]
 34%|███▍      | 3817/11066 [13:59<26:06,  4.63it/s]
                                                    

 34%|███▍      | 3817/11066 [13:59<26:06,  4.63it/s]
 35%|███▍      | 3818/11066 [13:59<25:58,  4.65it/s]
                                                    

 35%|███▍      | 3818/11066 [13:59<25:58,  4.65it/s]
 35%|███▍      | 3819/11066 [13:59<26:16,  4.60it/s]
                                                    

 35%|███▍      | 3819/11066 [13:59<26:16,  4.60it/s]
 35%|███▍      | 3820/11066 [13:59<26:16,  4.60it/s]
                                                    

 35%|███▍      | 3820/11066 [13:59<26:16,  4.60it/s]
 35%|███▍      | 3821/11066 [14:00<26:18,  4.59it/s]
                                                    

 35%|███▍      | 3821/11066 [14:00<26:18,  4.59it/s]
 35%|███▍      | 3822/11066 [14:00<26:05,  4.63it/s]
                                                    

 35%|███▍      | 3822/11066 [14:00<26:05,  4.63it/s]
 35%|███▍      | 3823/11066 [14:00<25:55,  4.66it/s]
                                                    

 35%|███▍      | 3823/11066 [14:00<25:55,  4.66it/s]
 35%|███▍      | 3824/11066 [14:00<26:12,  4.61it/s]
                                                    

 35%|███▍      | 3824/11066 [14:00<26:12,  4.61it/s]
 35%|███▍      | 3825/11066 [14:00<26:00,  4.64it/s]
                                                    

 35%|███▍      | 3825/11066 [14:00<26:00,  4.64it/s]
 35%|███▍      | 3826/11066 [14:01<25:52,  4.66it/s]
                                                    
{'loss': 1.5343, 'learning_rate': 1.9934032170612687e-05, 'epoch': 0.67}
{'loss': 1.7154, 'learning_rate': 1.993132116392554e-05, 'epoch': 0.67}
{'loss': 1.0356, 'learning_rate': 1.9928610157238387e-05, 'epoch': 0.67}
{'loss': 0.5032, 'learning_rate': 1.992589915055124e-05, 'epoch': 0.67}
{'loss': 0.9331, 'learning_rate': 1.992318814386409e-05, 'epoch': 0.67}
{'loss': 1.1515, 'learning_rate': 1.992047713717694e-05, 'epoch': 0.67}
{'loss': 1.2783, 'learning_rate': 1.991776613048979e-05, 'epoch': 0.67}
{'loss': 1.1145, 'learning_rate': 1.991505512380264e-05, 'epoch': 0.67}
{'loss': 0.9458, 'learning_rate': 1.9912344117115488e-05, 'epoch': 0.67}
{'loss': 1.265, 'learning_rate': 1.990963311042834e-05, 'epoch': 0.67}
{'loss': 1.3359, 'learning_rate': 1.990692210374119e-05, 'epoch': 0.67}
{'loss': 1.1038, 'learning_rate': 1.990421109705404e-05, 'epoch': 0.67}
{'loss': 1.7429, 'learning_rate': 1.990150009036689e-05, 'epoch': 0.67}
{'loss': 0.5978, 'learning_rate': 1.989878908367974e-05, 'epoch': 0.67}
{'loss': 1.4628, 'learning_rate': 1.9896078076992592e-05, 'epoch': 0.67}
{'loss': 0.7541, 'learning_rate': 1.989336707030544e-05, 'epoch': 0.67}
{'loss': 0.8658, 'learning_rate': 1.989065606361829e-05, 'epoch': 0.67}
{'loss': 0.8625, 'learning_rate': 1.988794505693114e-05, 'epoch': 0.67}
{'loss': 0.7895, 'learning_rate': 1.9885234050243992e-05, 'epoch': 0.67}
{'loss': 1.194, 'learning_rate': 1.988252304355684e-05, 'epoch': 0.67}
{'loss': 0.9372, 'learning_rate': 1.9879812036869693e-05, 'epoch': 0.67}
{'loss': 1.0075, 'learning_rate': 1.9877101030182544e-05, 'epoch': 0.67}
{'loss': 1.344, 'learning_rate': 1.987439002349539e-05, 'epoch': 0.68}
{'loss': 0.6528, 'learning_rate': 1.987167901680824e-05, 'epoch': 0.68}
{'loss': 0.5607, 'learning_rate': 1.986896801012109e-05, 'epoch': 0.68}
{'loss': 1.2331, 'learning_rate': 1.986625700343394e-05, 'epoch': 0.68}
{'loss': 0.9794, 'learning_rate': 1.9863545996746793e-05, 'epoch': 0.68}
{'loss': 1.0068, 'learning_rate': 1.9860834990059642e-05, 'epoch': 0.68}
{'loss': 1.5656, 'learning_rate': 1.9858123983372494e-05, 'epoch': 0.68}
{'loss': 1.5748, 'learning_rate': 1.9855412976685346e-05, 'epoch': 0.68}
{'loss': 1.0757, 'learning_rate': 1.985270196999819e-05, 'epoch': 0.68}
{'loss': 1.5369, 'learning_rate': 1.9849990963311042e-05, 'epoch': 0.68}
{'loss': 1.2089, 'learning_rate': 1.9847279956623894e-05, 'epoch': 0.68}
{'loss': 0.6986, 'learning_rate': 1.9844568949936743e-05, 'epoch': 0.68}
{'loss': 0.9283, 'learning_rate': 1.9841857943249594e-05, 'epoch': 0.68}
{'loss': 2.0622, 'learning_rate': 1.9839146936562443e-05, 'epoch': 0.68}
{'loss': 0.8607, 'learning_rate': 1.9836435929875295e-05, 'epoch': 0.68}
{'loss': 0.9245, 'learning_rate': 1.9833724923188147e-05, 'epoch': 0.68}
{'loss': 0.9548, 'learning_rate': 1.983101391650099e-05, 'epoch': 0.68}
{'loss': 0.7727, 'learning_rate': 1.9828302909813843e-05, 'epoch': 0.68}
{'loss': 1.1521, 'learning_rate': 1.9825591903126695e-05, 'epoch': 0.68}
{'loss': 1.1703, 'learning_rate': 1.9822880896439544e-05, 'epoch': 0.68}
{'loss': 1.644, 'learning_rate': 1.9820169889752396e-05, 'epoch': 0.68}
{'loss': 1.186, 'learning_rate': 1.9817458883065247e-05, 'epoch': 0.68}
{'loss': 0.6417, 'learning_rate': 1.9814747876378096e-05, 'epoch': 0.68}
{'loss': 0.8381, 'learning_rate': 1.9812036869690948e-05, 'epoch': 0.68}
{'loss': 0.4992, 'learning_rate': 1.9809325863003793e-05, 'epoch': 0.68}
{'loss': 1.2858, 'learning_rate': 1.9806614856316645e-05, 'epoch': 0.68}
{'loss': 1.3896, 'learning_rate': 1.9803903849629496e-05, 'epoch': 0.68}
{'loss': 1.6097, 'learning_rate': 1.9801192842942345e-05, 'epoch': 0.68}
{'loss': 1.1619, 'learning_rate': 1.9798481836255197e-05, 'epoch': 0.68}
{'loss': 1.8957, 'learning_rate': 1.979577082956805e-05, 'epoch': 0.68}
{'loss': 1.0039, 'learning_rate': 1.9793059822880897e-05, 'epoch': 0.68}
{'loss': 0.6757, 'learning_rate': 1.979034881619375e-05, 'epoch': 0.68}
{'loss': 1.832, 'learning_rate': 1.9787637809506597e-05, 'epoch': 0.68}
{'loss': 1.1423, 'learning_rate': 1.9784926802819446e-05, 'epoch': 0.68}
{'loss': 1.0356, 'learning_rate': 1.9782215796132297e-05, 'epoch': 0.68}
{'loss': 1.4206, 'learning_rate': 1.9779504789445146e-05, 'epoch': 0.68}
{'loss': 1.1189, 'learning_rate': 1.9776793782757998e-05, 'epoch': 0.68}
{'loss': 0.8766, 'learning_rate': 1.977408277607085e-05, 'epoch': 0.68}
{'loss': 0.4699, 'learning_rate': 1.9771371769383698e-05, 'epoch': 0.68}
{'loss': 1.5267, 'learning_rate': 1.976866076269655e-05, 'epoch': 0.68}
{'loss': 0.9998, 'learning_rate': 1.9765949756009398e-05, 'epoch': 0.68}
{'loss': 1.1473, 'learning_rate': 1.9763238749322247e-05, 'epoch': 0.68}
{'loss': 1.0678, 'learning_rate': 1.97605277426351e-05, 'epoch': 0.68}
{'loss': 0.982, 'learning_rate': 1.975781673594795e-05, 'epoch': 0.68}
{'loss': 1.2674, 'learning_rate': 1.97551057292608e-05, 'epoch': 0.68}
{'loss': 0.814, 'learning_rate': 1.975239472257365e-05, 'epoch': 0.68}
{'loss': 1.7516, 'learning_rate': 1.97496837158865e-05, 'epoch': 0.68}
{'loss': 0.8262, 'learning_rate': 1.974697270919935e-05, 'epoch': 0.68}
{'loss': 0.8391, 'learning_rate': 1.97442617025122e-05, 'epoch': 0.68}
{'loss': 0.7029, 'learning_rate': 1.9741550695825048e-05, 'epoch': 0.68}
{'loss': 0.8976, 'learning_rate': 1.97388396891379e-05, 'epoch': 0.68}
{'loss': 1.0556, 'learning_rate': 1.973612868245075e-05, 'epoch': 0.68}
{'loss': 0.7749, 'learning_rate': 1.97334176757636e-05, 'epoch': 0.68}
{'loss': 0.9961, 'learning_rate': 1.9730706669076452e-05, 'epoch': 0.68}
{'loss': 1.0159, 'learning_rate': 1.9727995662389304e-05, 'epoch': 0.68}
{'loss': 1.0764, 'learning_rate': 1.9725284655702152e-05, 'epoch': 0.68}
{'loss': 1.3712, 'learning_rate': 1.9722573649015e-05, 'epoch': 0.69}
{'loss': 0.4004, 'learning_rate': 1.971986264232785e-05, 'epoch': 0.69}
{'loss': 1.3471, 'learning_rate': 1.97171516356407e-05, 'epoch': 0.69}
{'loss': 1.0559, 'learning_rate': 1.9714440628953553e-05, 'epoch': 0.69}
{'loss': 1.4032, 'learning_rate': 1.97117296222664e-05, 'epoch': 0.69}
{'loss': 0.7082, 'learning_rate': 1.9709018615579253e-05, 'epoch': 0.69}
{'loss': 0.8234, 'learning_rate': 1.9706307608892105e-05, 'epoch': 0.69}
{'loss': 1.0415, 'learning_rate': 1.9703596602204953e-05, 'epoch': 0.69}
{'loss': 1.0271, 'learning_rate': 1.97008855955178e-05, 'epoch': 0.69}
{'loss': 0.95, 'learning_rate': 1.9698174588830653e-05, 'epoch': 0.69}
{'loss': 1.0266, 'learning_rate': 1.9695463582143502e-05, 'epoch': 0.69}
{'loss': 0.8429, 'learning_rate': 1.9692752575456354e-05, 'epoch': 0.69}
{'loss': 0.9637, 'learning_rate': 1.9690041568769202e-05, 'epoch': 0.69}
{'loss': 1.8121, 'learning_rate': 1.9687330562082054e-05, 'epoch': 0.69}
{'loss': 0.9268, 'learning_rate': 1.9684619555394906e-05, 'epoch': 0.69}
{'loss': 0.8463, 'learning_rate': 1.9681908548707754e-05, 'epoch': 0.69}
{'loss': 1.5033, 'learning_rate': 1.9679197542020603e-05, 'epoch': 0.69}
{'loss': 1.2861, 'learning_rate': 1.9676486535333454e-05, 'epoch': 0.69}
{'loss': 0.8522, 'learning_rate': 1.9673775528646303e-05, 'epoch': 0.69}
{'loss': 1.3782, 'learning_rate': 1.9671064521959155e-05, 'epoch': 0.69}
{'loss': 1.0024, 'learning_rate': 1.9668353515272006e-05, 'epoch': 0.69}
{'loss': 0.9942, 'learning_rate': 1.9665642508584855e-05, 'epoch': 0.69}
{'loss': 1.3379, 'learning_rate': 1.9662931501897707e-05, 'epoch': 0.69}
{'loss': 0.9784, 'learning_rate': 1.9660220495210555e-05, 'epoch': 0.69}
{'loss': 1.4604, 'learning_rate': 1.9657509488523404e-05, 'epoch': 0.69}
{'loss': 0.8767, 'learning_rate': 1.9654798481836255e-05, 'epoch': 0.69}
{'loss': 1.1462, 'learning_rate': 1.9652087475149104e-05, 'epoch': 0.69}
{'loss': 1.2224, 'learning_rate': 1.9649376468461956e-05, 'epoch': 0.69}
{'loss': 1.4932, 'learning_rate': 1.9646665461774808e-05, 'epoch': 0.69}
{'loss': 0.874, 'learning_rate': 1.9643954455087656e-05, 'epoch': 0.69}
{'loss': 1.2282, 'learning_rate': 1.9641243448400508e-05, 'epoch': 0.69}
{'loss': 0.7201, 'learning_rate': 1.963853244171336e-05, 'epoch': 0.69}
{'loss': 1.1135, 'learning_rate': 1.9635821435026205e-05, 'epoch': 0.69}
{'loss': 0.7634, 'learning_rate': 1.9633110428339057e-05, 'epoch': 0.69}
{'loss': 0.9046, 'learning_rate': 1.963039942165191e-05, 'epoch': 0.69}

 35%|███▍      | 3826/11066 [14:01<25:52,  4.66it/s]
 35%|███▍      | 3827/11066 [14:01<25:56,  4.65it/s]
                                                    

 35%|███▍      | 3827/11066 [14:01<25:56,  4.65it/s]
 35%|███▍      | 3828/11066 [14:01<26:08,  4.61it/s]
                                                    

 35%|███▍      | 3828/11066 [14:01<26:08,  4.61it/s]
 35%|███▍      | 3829/11066 [14:01<26:28,  4.56it/s]
                                                    

 35%|███▍      | 3829/11066 [14:01<26:28,  4.56it/s]
 35%|███▍      | 3830/11066 [14:02<26:38,  4.53it/s]
                                                    

 35%|███▍      | 3830/11066 [14:02<26:38,  4.53it/s]
 35%|███▍      | 3831/11066 [14:02<26:41,  4.52it/s]
                                                    

 35%|███▍      | 3831/11066 [14:02<26:41,  4.52it/s]
 35%|███▍      | 3832/11066 [14:02<26:45,  4.51it/s]
                                                    

 35%|███▍      | 3832/11066 [14:02<26:45,  4.51it/s]
 35%|███▍      | 3833/11066 [14:02<26:49,  4.49it/s]
                                                    

 35%|███▍      | 3833/11066 [14:02<26:49,  4.49it/s]
 35%|███▍      | 3834/11066 [14:02<26:37,  4.53it/s]
                                                    

 35%|███▍      | 3834/11066 [14:02<26:37,  4.53it/s]
 35%|███▍      | 3835/11066 [14:03<26:44,  4.51it/s]
                                                    

 35%|███▍      | 3835/11066 [14:03<26:44,  4.51it/s]
 35%|███▍      | 3836/11066 [14:03<26:36,  4.53it/s]
                                                    

 35%|███▍      | 3836/11066 [14:03<26:36,  4.53it/s]
 35%|███▍      | 3837/11066 [14:03<26:18,  4.58it/s]
                                                    

 35%|███▍      | 3837/11066 [14:03<26:18,  4.58it/s]
 35%|███▍      | 3838/11066 [14:03<26:26,  4.56it/s]
                                                    

 35%|███▍      | 3838/11066 [14:03<26:26,  4.56it/s]
 35%|███▍      | 3839/11066 [14:04<26:36,  4.53it/s]
                                                    

 35%|███▍      | 3839/11066 [14:04<26:36,  4.53it/s]
 35%|███▍      | 3840/11066 [14:04<26:47,  4.50it/s]
                                                    

 35%|███▍      | 3840/11066 [14:04<26:47,  4.50it/s]
 35%|███▍      | 3841/11066 [14:04<26:49,  4.49it/s]
                                                    

 35%|███▍      | 3841/11066 [14:04<26:49,  4.49it/s]
 35%|███▍      | 3842/11066 [14:04<26:50,  4.49it/s]
                                                    

 35%|███▍      | 3842/11066 [14:04<26:50,  4.49it/s]
 35%|███▍      | 3843/11066 [14:04<26:28,  4.55it/s]
                                                    

 35%|███▍      | 3843/11066 [14:04<26:28,  4.55it/s]
 35%|███▍      | 3844/11066 [14:05<26:20,  4.57it/s]
                                                    

 35%|███▍      | 3844/11066 [14:05<26:20,  4.57it/s]
 35%|███▍      | 3845/11066 [14:05<26:01,  4.62it/s]
                                                    

 35%|███▍      | 3845/11066 [14:05<26:01,  4.62it/s]
 35%|███▍      | 3846/11066 [14:05<26:02,  4.62it/s]
                                                    

 35%|███▍      | 3846/11066 [14:05<26:02,  4.62it/s]
 35%|███▍      | 3847/11066 [14:05<26:22,  4.56it/s]
                                                    

 35%|███▍      | 3847/11066 [14:05<26:22,  4.56it/s]
 35%|███▍      | 3848/11066 [14:06<26:23,  4.56it/s]
                                                    

 35%|███▍      | 3848/11066 [14:06<26:23,  4.56it/s]
 35%|███▍      | 3849/11066 [14:06<26:16,  4.58it/s]
                                                    

 35%|███▍      | 3849/11066 [14:06<26:16,  4.58it/s]
 35%|███▍      | 3850/11066 [14:06<26:12,  4.59it/s]
                                                    

 35%|███▍      | 3850/11066 [14:06<26:12,  4.59it/s]
 35%|███▍      | 3851/11066 [14:06<26:27,  4.54it/s]
                                                    

 35%|███▍      | 3851/11066 [14:06<26:27,  4.54it/s]
 35%|███▍      | 3852/11066 [14:06<26:34,  4.53it/s]
                                                    

 35%|███▍      | 3852/11066 [14:06<26:34,  4.53it/s]
 35%|███▍      | 3853/11066 [14:07<26:38,  4.51it/s]
                                                    

 35%|███▍      | 3853/11066 [14:07<26:38,  4.51it/s]
 35%|███▍      | 3854/11066 [14:07<26:42,  4.50it/s]
                                                    

 35%|███▍      | 3854/11066 [14:07<26:42,  4.50it/s]
 35%|███▍      | 3855/11066 [14:07<26:43,  4.50it/s]
                                                    

 35%|███▍      | 3855/11066 [14:07<26:43,  4.50it/s]
 35%|███▍      | 3856/11066 [14:07<26:44,  4.49it/s]
                                                    

 35%|███▍      | 3856/11066 [14:07<26:44,  4.49it/s]
 35%|███▍      | 3857/11066 [14:08<26:44,  4.49it/s]
                                                    

 35%|███▍      | 3857/11066 [14:08<26:44,  4.49it/s]
 35%|███▍      | 3858/11066 [14:08<26:44,  4.49it/s]
                                                    

 35%|███▍      | 3858/11066 [14:08<26:44,  4.49it/s]
 35%|███▍      | 3859/11066 [14:08<26:44,  4.49it/s]
                                                    

 35%|███▍      | 3859/11066 [14:08<26:44,  4.49it/s]
 35%|███▍      | 3860/11066 [14:08<26:43,  4.49it/s]
                                                    

 35%|███▍      | 3860/11066 [14:08<26:43,  4.49it/s]
 35%|███▍      | 3861/11066 [14:08<26:46,  4.49it/s]
                                                    

 35%|███▍      | 3861/11066 [14:08<26:46,  4.49it/s]
 35%|███▍      | 3862/11066 [14:09<27:35,  4.35it/s]
                                                    

 35%|███▍      | 3862/11066 [14:09<27:35,  4.35it/s]
 35%|███▍      | 3863/11066 [14:09<26:59,  4.45it/s]
                                                    

 35%|███▍      | 3863/11066 [14:09<26:59,  4.45it/s]
 35%|███▍      | 3864/11066 [14:09<26:29,  4.53it/s]
                                                    

 35%|███▍      | 3864/11066 [14:09<26:29,  4.53it/s]
 35%|███▍      | 3865/11066 [14:09<26:05,  4.60it/s]
                                                    

 35%|███▍      | 3865/11066 [14:09<26:05,  4.60it/s]
 35%|███▍      | 3866/11066 [14:09<26:03,  4.60it/s]
                                                    

 35%|███▍      | 3866/11066 [14:09<26:03,  4.60it/s]
 35%|███▍      | 3867/11066 [14:10<25:48,  4.65it/s]
                                                    

 35%|███▍      | 3867/11066 [14:10<25:48,  4.65it/s]
 35%|███▍      | 3868/11066 [14:10<25:34,  4.69it/s]
                                                    

 35%|███▍      | 3868/11066 [14:10<25:34,  4.69it/s]
 35%|███▍      | 3869/11066 [14:10<25:46,  4.65it/s]
                                                    

 35%|███▍      | 3869/11066 [14:10<25:46,  4.65it/s]
 35%|███▍      | 3870/11066 [14:10<25:37,  4.68it/s]
                                                    

 35%|███▍      | 3870/11066 [14:10<25:37,  4.68it/s]
 35%|███▍      | 3871/11066 [14:11<25:26,  4.71it/s]
                                                    

 35%|███▍      | 3871/11066 [14:11<25:26,  4.71it/s]
 35%|███▍      | 3872/11066 [14:11<25:49,  4.64it/s]
                                                    

 35%|███▍      | 3872/11066 [14:11<25:49,  4.64it/s]
 35%|███▍      | 3873/11066 [14:11<25:43,  4.66it/s]
                                                    

 35%|███▍      | 3873/11066 [14:11<25:43,  4.66it/s]
 35%|███▌      | 3874/11066 [14:11<25:37,  4.68it/s]
                                                    

 35%|███▌      | 3874/11066 [14:11<25:37,  4.68it/s]
 35%|███▌      | 3875/11066 [14:11<26:00,  4.61it/s]
                                                    

 35%|███▌      | 3875/11066 [14:11<26:00,  4.61it/s]
 35%|███▌      | 3876/11066 [14:12<26:12,  4.57it/s]
                                                    

 35%|███▌      | 3876/11066 [14:12<26:12,  4.57it/s]
 35%|███▌      | 3877/11066 [14:12<25:57,  4.62it/s]
                                                    

 35%|███▌      | 3877/11066 [14:12<25:57,  4.62it/s]
 35%|███▌      | 3878/11066 [14:12<25:46,  4.65it/s]
                                                    

 35%|███▌      | 3878/11066 [14:12<25:46,  4.65it/s]
 35%|███▌      | 3879/11066 [14:12<26:33,  4.51it/s]
                                                    

 35%|███▌      | 3879/11066 [14:12<26:33,  4.51it/s]
 35%|███▌      | 3880/11066 [14:13<26:41,  4.49it/s]
                                                    

 35%|███▌      | 3880/11066 [14:13<26:41,  4.49it/s]
 35%|███▌      | 3881/11066 [14:13<26:30,  4.52it/s]
                                                    

 35%|███▌      | 3881/11066 [14:13<26:30,  4.52it/s]
 35%|███▌      | 3882/11066 [14:13<26:45,  4.47it/s]
                                                    

 35%|███▌      | 3882/11066 [14:13<26:45,  4.47it/s]
 35%|███▌      | 3883/11066 [14:13<26:43,  4.48it/s]
                                                    

 35%|███▌      | 3883/11066 [14:13<26:43,  4.48it/s]
 35%|███▌      | 3884/11066 [14:13<26:54,  4.45it/s]
                                                    

 35%|███▌      | 3884/11066 [14:13<26:54,  4.45it/s]
 35%|███▌      | 3885/11066 [14:14<26:36,  4.50it/s]
                                                    

 35%|███▌      | 3885/11066 [14:14<26:36,  4.50it/s]
 35%|███▌      | 3886/11066 [14:14<26:14,  4.56it/s]
                                                    

 35%|███▌      | 3886/11066 [14:14<26:14,  4.56it/s]
 35%|███▌      | 3887/11066 [14:14<25:58,  4.61it/s]
                                                    

 35%|███▌      | 3887/11066 [14:14<25:58,  4.61it/s]
 35%|███▌      | 3888/11066 [14:14<25:58,  4.61it/s]
                                                    

 35%|███▌      | 3888/11066 [14:14<25:58,  4.61it/s]
 35%|███▌      | 3889/11066 [14:15<26:12,  4.56it/s]
                                                    

 35%|███▌      | 3889/11066 [14:15<26:12,  4.56it/s]
 35%|███▌      | 3890/11066 [14:15<26:27,  4.52it/s]
                                                    

 35%|███▌      | 3890/11066 [14:15<26:27,  4.52it/s]
 35%|███▌      | 3891/11066 [14:15<26:34,  4.50it/s]
                                                    

 35%|███▌      | 3891/11066 [14:15<26:34,  4.50it/s]
 35%|███▌      | 3892/11066 [14:15<26:35,  4.50it/s]
                                                    

 35%|███▌      | 3892/11066 [14:15<26:35,  4.50it/s]
 35%|███▌      | 3893/11066 [14:15<26:34,  4.50it/s]
                                                    

 35%|███▌      | 3893/11066 [14:15<26:34,  4.50it/s]
 35%|███▌      | 3894/11066 [14:16<26:11,  4.56it/s]
                                                    

 35%|███▌      | 3894/11066 [14:16<26:11,  4.56it/s]
 35%|███▌      | 3895/11066 [14:16<25:56,  4.61it/s]
                                                    

 35%|███▌      | 3895/11066 [14:16<25:56,  4.61it/s]
 35%|███▌      | 3896/11066 [14:16<25:45,  4.64it/s]
                                                    

 35%|███▌      | 3896/11066 [14:16<25:45,  4.64it/s]
 35%|███▌      | 3897/11066 [14:16<25:48,  4.63it/s]
                                                    

 35%|███▌      | 3897/11066 [14:16<25:48,  4.63it/s]
 35%|███▌      | 3898/11066 [14:16<25:32,  4.68it/s]
                                                    

 35%|███▌      | 3898/11066 [14:16<25:32,  4.68it/s]
 35%|███▌      | 3899/11066 [14:17<25:41,  4.65it/s]
                                                    

 35%|███▌      | 3899/11066 [14:17<25:41,  4.65it/s]
 35%|███▌      | 3900/11066 [14:17<25:29,  4.68it/s]
                                                    

 35%|███▌      | 3900/11066 [14:17<25:29,  4.68it/s]
 35%|███▌      | 3901/11066 [14:17<25:17,  4.72it/s]
                                                    

 35%|███▌      | 3901/11066 [14:17<25:17,  4.72it/s]
 35%|███▌      | 3902/11066 [14:17<25:22,  4.71it/s]
                                                    

 35%|███▌      | 3902/11066 [14:17<25:22,  4.71it/s]
 35%|███▌      | 3903/11066 [14:18<25:45,  4.64it/s]
                                                    

 35%|███▌      | 3903/11066 [14:18<25:45,  4.64it/s]
 35%|███▌      | 3904/11066 [14:18<25:46,  4.63it/s]
                                                    

 35%|███▌      | 3904/11066 [14:18<25:46,  4.63it/s]
 35%|███▌      | 3905/11066 [14:18<25:36,  4.66it/s]
                                                    

 35%|███▌      | 3905/11066 [14:18<25:36,  4.66it/s]
 35%|███▌      | 3906/11066 [14:18<25:35,  4.66it/s]
                                                    

 35%|███▌      | 3906/11066 [14:18<25:35,  4.66it/s]
 35%|███▌      | 3907/11066 [14:18<25:28,  4.68it/s]
                                                    

 35%|███▌      | 3907/11066 [14:18<25:28,  4.68it/s]
 35%|███▌      | 3908/11066 [14:19<25:24,  4.70it/s]
                                                    

 35%|███▌      | 3908/11066 [14:19<25:24,  4.70it/s]
 35%|███▌      | 3909/11066 [14:19<25:39,  4.65it/s]
                                                    

 35%|███▌      | 3909/11066 [14:19<25:39,  4.65it/s]
 35%|███▌      | 3910/11066 [14:19<25:25,  4.69it/s]
                                                    

 35%|███▌      | 3910/11066 [14:19<25:25,  4.69it/s]
 35%|███▌      | 3911/11066 [14:19<25:34,  4.66it/s]
                                                    

 35%|███▌      | 3911/11066 [14:19<25:34,  4.66it/s]
 35%|███▌      | 3912/11066 [14:19<25:25,  4.69it/s]
                                                    

 35%|███▌      | 3912/11066 [14:19<25:25,  4.69it/s]
 35%|███▌      | 3913/11066 [14:20<25:15,  4.72it/s]
                                                    

 35%|███▌      | 3913/11066 [14:20<25:15,  4.72it/s]
 35%|███▌      | 3914/11066 [14:20<25:19,  4.71it/s]
                                                    

 35%|███▌      | 3914/11066 [14:20<25:19,  4.71it/s]
 35%|███▌      | 3915/11066 [14:20<25:18,  4.71it/s]
                                                    

 35%|███▌      | 3915/11066 [14:20<25:18,  4.71it/s]
 35%|███▌      | 3916/11066 [14:20<25:38,  4.65it/s]
                                                    

 35%|███▌      | 3916/11066 [14:20<25:38,  4.65it/s]
 35%|███▌      | 3917/11066 [14:21<25:55,  4.59it/s]
                                                    

 35%|███▌      | 3917/11066 [14:21<25:55,  4.59it/s]
 35%|███▌      | 3918/11066 [14:21<26:06,  4.56it/s]
                                                    

 35%|███▌      | 3918/11066 [14:21<26:06,  4.56it/s]
 35%|███▌      | 3919/11066 [14:21<26:01,  4.58it/s]
                                                    

 35%|███▌      | 3919/11066 [14:21<26:01,  4.58it/s]
 35%|███▌      | 3920/11066 [14:21<25:53,  4.60it/s]
                                                    

 35%|███▌      | 3920/11066 [14:21<25:53,  4.60it/s]
 35%|███▌      | 3921/11066 [14:21<25:53,  4.60it/s]
                                                    

 35%|███▌      | 3921/11066 [14:21<25:53,  4.60it/s]
 35%|███▌      | 3922/11066 [14:22<25:43,  4.63it/s]
                                                    

 35%|███▌      | 3922/11066 [14:22<25:43,  4.63it/s]
 35%|███▌      | 3923/11066 [14:22<25:28,  4.67it/s]
                                                    

 35%|███▌      | 3923/11066 [14:22<25:28,  4.67it/s]
 35%|███▌      | 3924/11066 [14:22<25:34,  4.65it/s]
                                                    

 35%|███▌      | 3924/11066 [14:22<25:34,  4.65it/s]
 35%|███▌      | 3925/11066 [14:22<25:34,  4.66it/s]
                                                    

 35%|███▌      | 3925/11066 [14:22<25:34,  4.66it/s]
 35%|███▌      | 3926/11066 [14:22<25:40,  4.63it/s]
                                                    

 35%|███▌      | 3926/11066 [14:22<25:40,  4.63it/s]
 35%|███▌      | 3927/11066 [14:23<25:47,  4.61it/s]
                                                    

 35%|███▌      | 3927/11066 [14:23<25:47,  4.61it/s]
 35%|███▌      | 3928/11066 [14:23<25:46,  4.61it/s]
                                                    

 35%|███▌      | 3928/11066 [14:23<25:46,  4.61it/s]
 36%|███▌      | 3929/11066 [14:23<25:35,  4.65it/s]
                                                    

 36%|███▌      | 3929/11066 [14:23<25:35,  4.65it/s]
 36%|███▌      | 3930/11066 [14:23<25:31,  4.66it/s]
                                                    

 36%|███▌      | 3930/11066 [14:23<25:31,  4.66it/s]
 36%|███▌      | 3931/11066 [14:24<25:32,  4.66it/s]
                                                    

 36%|███▌      | 3931/11066 [14:24<25:32,  4.66it/s]
 36%|███▌      | 3932/11066 [14:24<25:53,  4.59it/s]
                                                    

 36%|███▌      | 3932/11066 [14:24<25:53,  4.59it/s]
 36%|███▌      | 3933/11066 [14:24<26:04,  4.56it/s]
                                                    

 36%|███▌      | 3933/11066 [14:24<26:04,  4.56it/s]
 36%|███▌      | 3934/11066 [14:24<26:10,  4.54it/s]
                                                    

 36%|███▌      | 3934/11066 [14:24<26:10,  4.54it/s]
 36%|███▌      | 3935/11066 [14:24<26:02,  4.56it/s]
                                                    

 36%|███▌      | 3935/11066 [14:24<26:02,  4.56it/s]
 36%|███▌      | 3936/11066 [14:25<25:42,  4.62it/s]
                                                    

 36%|███▌      | 3936/11066 [14:25<25:42,  4.62it/s]
 36%|███▌      | 3937/11066 [14:25<25:33,  4.65it/s]
                                                    

 36%|███▌      | 3937/11066 [14:25<25:33,  4.65it/s]
 36%|███▌      | 3938/11066 [14:25<25:19,  4.69it/s]
                                                    

 36%|███▌      | 3938/11066 [14:25<25:19,  4.69it/s]
 36%|███▌      | 3939/11066 [14:25<25:28,  4.66it/s]
                                                    
{'loss': 1.3199, 'learning_rate': 1.9627688414964757e-05, 'epoch': 0.69}
{'loss': 1.0768, 'learning_rate': 1.962497740827761e-05, 'epoch': 0.69}
{'loss': 1.4359, 'learning_rate': 1.9622266401590457e-05, 'epoch': 0.69}
{'loss': 0.7406, 'learning_rate': 1.961955539490331e-05, 'epoch': 0.69}
{'loss': 2.1055, 'learning_rate': 1.961684438821616e-05, 'epoch': 0.69}
{'loss': 0.6902, 'learning_rate': 1.9614133381529006e-05, 'epoch': 0.69}
{'loss': 1.0175, 'learning_rate': 1.9611422374841858e-05, 'epoch': 0.69}
{'loss': 1.3748, 'learning_rate': 1.960871136815471e-05, 'epoch': 0.69}
{'loss': 1.0229, 'learning_rate': 1.9606000361467558e-05, 'epoch': 0.69}
{'loss': 1.3676, 'learning_rate': 1.960328935478041e-05, 'epoch': 0.69}
{'loss': 1.3217, 'learning_rate': 1.960057834809326e-05, 'epoch': 0.69}
{'loss': 0.9154, 'learning_rate': 1.959786734140611e-05, 'epoch': 0.69}
{'loss': 1.4735, 'learning_rate': 1.9595156334718962e-05, 'epoch': 0.69}
{'loss': 0.5877, 'learning_rate': 1.9592445328031807e-05, 'epoch': 0.69}
{'loss': 1.041, 'learning_rate': 1.958973432134466e-05, 'epoch': 0.69}
{'loss': 1.6739, 'learning_rate': 1.958702331465751e-05, 'epoch': 0.69}
{'loss': 1.2322, 'learning_rate': 1.958431230797036e-05, 'epoch': 0.69}
{'loss': 1.5909, 'learning_rate': 1.958160130128321e-05, 'epoch': 0.69}
{'loss': 1.1424, 'learning_rate': 1.9578890294596063e-05, 'epoch': 0.69}
{'loss': 1.3239, 'learning_rate': 1.957617928790891e-05, 'epoch': 0.69}
{'loss': 1.4752, 'learning_rate': 1.9573468281221763e-05, 'epoch': 0.7}
{'loss': 1.3017, 'learning_rate': 1.957075727453461e-05, 'epoch': 0.7}
{'loss': 1.1166, 'learning_rate': 1.956804626784746e-05, 'epoch': 0.7}
{'loss': 0.6359, 'learning_rate': 1.956533526116031e-05, 'epoch': 0.7}
{'loss': 0.8282, 'learning_rate': 1.956262425447316e-05, 'epoch': 0.7}
{'loss': 1.3681, 'learning_rate': 1.9559913247786012e-05, 'epoch': 0.7}
{'loss': 1.2307, 'learning_rate': 1.9557202241098864e-05, 'epoch': 0.7}
{'loss': 1.0592, 'learning_rate': 1.9554491234411712e-05, 'epoch': 0.7}
{'loss': 0.8498, 'learning_rate': 1.9551780227724564e-05, 'epoch': 0.7}
{'loss': 0.8158, 'learning_rate': 1.9549069221037412e-05, 'epoch': 0.7}
{'loss': 0.9665, 'learning_rate': 1.954635821435026e-05, 'epoch': 0.7}
{'loss': 1.0416, 'learning_rate': 1.9543647207663113e-05, 'epoch': 0.7}
{'loss': 1.0196, 'learning_rate': 1.9540936200975964e-05, 'epoch': 0.7}
{'loss': 0.9932, 'learning_rate': 1.9538225194288813e-05, 'epoch': 0.7}
{'loss': 1.0378, 'learning_rate': 1.9535514187601665e-05, 'epoch': 0.7}
{'loss': 0.921, 'learning_rate': 1.9532803180914513e-05, 'epoch': 0.7}
{'loss': 0.8472, 'learning_rate': 1.953009217422736e-05, 'epoch': 0.7}
{'loss': 0.6799, 'learning_rate': 1.9527381167540213e-05, 'epoch': 0.7}
{'loss': 1.5484, 'learning_rate': 1.9524670160853062e-05, 'epoch': 0.7}
{'loss': 0.8046, 'learning_rate': 1.9521959154165914e-05, 'epoch': 0.7}
{'loss': 0.803, 'learning_rate': 1.9519248147478766e-05, 'epoch': 0.7}
{'loss': 2.3273, 'learning_rate': 1.9516537140791614e-05, 'epoch': 0.7}
{'loss': 1.1658, 'learning_rate': 1.9513826134104466e-05, 'epoch': 0.7}
{'loss': 1.3727, 'learning_rate': 1.9511115127417318e-05, 'epoch': 0.7}
{'loss': 0.977, 'learning_rate': 1.9508404120730163e-05, 'epoch': 0.7}
{'loss': 0.7631, 'learning_rate': 1.9505693114043015e-05, 'epoch': 0.7}
{'loss': 0.9046, 'learning_rate': 1.9502982107355863e-05, 'epoch': 0.7}
{'loss': 0.9734, 'learning_rate': 1.9500271100668715e-05, 'epoch': 0.7}
{'loss': 1.6604, 'learning_rate': 1.9497560093981567e-05, 'epoch': 0.7}
{'loss': 0.7932, 'learning_rate': 1.9494849087294415e-05, 'epoch': 0.7}
{'loss': 0.7411, 'learning_rate': 1.9492138080607267e-05, 'epoch': 0.7}
{'loss': 0.9883, 'learning_rate': 1.948942707392012e-05, 'epoch': 0.7}
{'loss': 0.7718, 'learning_rate': 1.9486716067232964e-05, 'epoch': 0.7}
{'loss': 1.4541, 'learning_rate': 1.9484005060545816e-05, 'epoch': 0.7}
{'loss': 0.9717, 'learning_rate': 1.9481294053858667e-05, 'epoch': 0.7}
{'loss': 0.6504, 'learning_rate': 1.9478583047171516e-05, 'epoch': 0.7}
{'loss': 1.0141, 'learning_rate': 1.9475872040484368e-05, 'epoch': 0.7}
{'loss': 1.3702, 'learning_rate': 1.9473161033797216e-05, 'epoch': 0.7}
{'loss': 1.3121, 'learning_rate': 1.9470450027110068e-05, 'epoch': 0.7}
{'loss': 1.5202, 'learning_rate': 1.946773902042292e-05, 'epoch': 0.7}
{'loss': 1.2855, 'learning_rate': 1.9465028013735765e-05, 'epoch': 0.7}
{'loss': 1.7586, 'learning_rate': 1.9462317007048617e-05, 'epoch': 0.7}
{'loss': 0.5615, 'learning_rate': 1.945960600036147e-05, 'epoch': 0.7}
{'loss': 1.62, 'learning_rate': 1.9456894993674317e-05, 'epoch': 0.7}
{'loss': 1.3363, 'learning_rate': 1.945418398698717e-05, 'epoch': 0.7}
{'loss': 0.7385, 'learning_rate': 1.945147298030002e-05, 'epoch': 0.7}
{'loss': 1.283, 'learning_rate': 1.944876197361287e-05, 'epoch': 0.7}
{'loss': 1.3374, 'learning_rate': 1.944605096692572e-05, 'epoch': 0.7}
{'loss': 1.647, 'learning_rate': 1.9443339960238566e-05, 'epoch': 0.7}
{'loss': 1.2666, 'learning_rate': 1.9440628953551418e-05, 'epoch': 0.7}
{'loss': 0.9315, 'learning_rate': 1.943791794686427e-05, 'epoch': 0.7}
{'loss': 1.092, 'learning_rate': 1.9435206940177118e-05, 'epoch': 0.7}
{'loss': 1.3366, 'learning_rate': 1.943249593348997e-05, 'epoch': 0.7}
{'loss': 1.0479, 'learning_rate': 1.942978492680282e-05, 'epoch': 0.7}
{'loss': 0.8157, 'learning_rate': 1.942707392011567e-05, 'epoch': 0.7}
{'loss': 0.72, 'learning_rate': 1.9424362913428522e-05, 'epoch': 0.71}
{'loss': 0.9575, 'learning_rate': 1.942165190674137e-05, 'epoch': 0.71}
{'loss': 0.7445, 'learning_rate': 1.941894090005422e-05, 'epoch': 0.71}
{'loss': 1.0547, 'learning_rate': 1.941622989336707e-05, 'epoch': 0.71}
{'loss': 0.9665, 'learning_rate': 1.941351888667992e-05, 'epoch': 0.71}
{'loss': 1.1723, 'learning_rate': 1.941080787999277e-05, 'epoch': 0.71}
{'loss': 0.9559, 'learning_rate': 1.9408096873305623e-05, 'epoch': 0.71}
{'loss': 1.1658, 'learning_rate': 1.940538586661847e-05, 'epoch': 0.71}
{'loss': 1.465, 'learning_rate': 1.9402674859931323e-05, 'epoch': 0.71}
{'loss': 1.1602, 'learning_rate': 1.939996385324417e-05, 'epoch': 0.71}
{'loss': 1.0362, 'learning_rate': 1.939725284655702e-05, 'epoch': 0.71}
{'loss': 1.1434, 'learning_rate': 1.9394541839869872e-05, 'epoch': 0.71}
{'loss': 1.5449, 'learning_rate': 1.9391830833182724e-05, 'epoch': 0.71}
{'loss': 1.0499, 'learning_rate': 1.9389119826495572e-05, 'epoch': 0.71}
{'loss': 1.0711, 'learning_rate': 1.9386408819808424e-05, 'epoch': 0.71}
{'loss': 1.0556, 'learning_rate': 1.9383697813121272e-05, 'epoch': 0.71}
{'loss': 1.5451, 'learning_rate': 1.9380986806434124e-05, 'epoch': 0.71}
{'loss': 1.3343, 'learning_rate': 1.9378275799746973e-05, 'epoch': 0.71}
{'loss': 0.6553, 'learning_rate': 1.937556479305982e-05, 'epoch': 0.71}
{'loss': 1.2744, 'learning_rate': 1.9372853786372673e-05, 'epoch': 0.71}
{'loss': 1.4696, 'learning_rate': 1.9370142779685525e-05, 'epoch': 0.71}
{'loss': 0.597, 'learning_rate': 1.9367431772998373e-05, 'epoch': 0.71}
{'loss': 0.5027, 'learning_rate': 1.9364720766311225e-05, 'epoch': 0.71}
{'loss': 0.7699, 'learning_rate': 1.9362009759624077e-05, 'epoch': 0.71}
{'loss': 1.9725, 'learning_rate': 1.9359298752936925e-05, 'epoch': 0.71}
{'loss': 1.2395, 'learning_rate': 1.9356587746249774e-05, 'epoch': 0.71}
{'loss': 1.0793, 'learning_rate': 1.9353876739562622e-05, 'epoch': 0.71}
{'loss': 1.2189, 'learning_rate': 1.9351165732875474e-05, 'epoch': 0.71}
{'loss': 1.5831, 'learning_rate': 1.9348454726188326e-05, 'epoch': 0.71}
{'loss': 0.6298, 'learning_rate': 1.9345743719501174e-05, 'epoch': 0.71}
{'loss': 1.7994, 'learning_rate': 1.9343032712814026e-05, 'epoch': 0.71}
{'loss': 0.7811, 'learning_rate': 1.9340321706126878e-05, 'epoch': 0.71}
{'loss': 1.0983, 'learning_rate': 1.9337610699439726e-05, 'epoch': 0.71}
{'loss': 0.7896, 'learning_rate': 1.9334899692752575e-05, 'epoch': 0.71}
{'loss': 1.2125, 'learning_rate': 1.9332188686065427e-05, 'epoch': 0.71}
{'loss': 0.6568, 'learning_rate': 1.9329477679378275e-05, 'epoch': 0.71}
{'loss': 2.0823, 'learning_rate': 1.9326766672691127e-05, 'epoch': 0.71}
{'loss': 1.241, 'learning_rate': 1.9324055666003975e-05, 'epoch': 0.71}

 36%|███▌      | 3939/11066 [14:25<25:28,  4.66it/s]
 36%|███▌      | 3940/11066 [14:26<25:40,  4.62it/s]
                                                    

 36%|███▌      | 3940/11066 [14:26<25:40,  4.62it/s]
 36%|███▌      | 3941/11066 [14:26<25:35,  4.64it/s]
                                                    

 36%|███▌      | 3941/11066 [14:26<25:35,  4.64it/s]
 36%|███▌      | 3942/11066 [14:26<25:19,  4.69it/s]
                                                    

 36%|███▌      | 3942/11066 [14:26<25:19,  4.69it/s]
 36%|███▌      | 3943/11066 [14:26<25:41,  4.62it/s]
                                                    

 36%|███▌      | 3943/11066 [14:26<25:41,  4.62it/s]
 36%|███▌      | 3944/11066 [14:26<25:56,  4.58it/s]
                                                    

 36%|███▌      | 3944/11066 [14:26<25:56,  4.58it/s]
 36%|███▌      | 3945/11066 [14:27<25:51,  4.59it/s]
                                                    

 36%|███▌      | 3945/11066 [14:27<25:51,  4.59it/s]
 36%|███▌      | 3946/11066 [14:27<26:08,  4.54it/s]
                                                    

 36%|███▌      | 3946/11066 [14:27<26:08,  4.54it/s]
 36%|███▌      | 3947/11066 [14:27<26:15,  4.52it/s]
                                                    

 36%|███▌      | 3947/11066 [14:27<26:15,  4.52it/s]
 36%|███▌      | 3948/11066 [14:27<26:18,  4.51it/s]
                                                    

 36%|███▌      | 3948/11066 [14:27<26:18,  4.51it/s]
 36%|███▌      | 3949/11066 [14:27<26:19,  4.51it/s]
                                                    

 36%|███▌      | 3949/11066 [14:27<26:19,  4.51it/s]
 36%|███▌      | 3950/11066 [14:28<26:19,  4.51it/s]
                                                    

 36%|███▌      | 3950/11066 [14:28<26:19,  4.51it/s]
 36%|███▌      | 3951/11066 [14:28<26:22,  4.50it/s]
                                                    

 36%|███▌      | 3951/11066 [14:28<26:22,  4.50it/s]
 36%|███▌      | 3952/11066 [14:28<26:22,  4.50it/s]
                                                    

 36%|███▌      | 3952/11066 [14:28<26:22,  4.50it/s]
 36%|███▌      | 3953/11066 [14:28<26:22,  4.49it/s]
                                                    

 36%|███▌      | 3953/11066 [14:28<26:22,  4.49it/s]
 36%|███▌      | 3954/11066 [14:29<26:27,  4.48it/s]
                                                    

 36%|███▌      | 3954/11066 [14:29<26:27,  4.48it/s]
 36%|███▌      | 3955/11066 [14:29<26:38,  4.45it/s]
                                                    

 36%|███▌      | 3955/11066 [14:29<26:38,  4.45it/s]
 36%|███▌      | 3956/11066 [14:29<26:38,  4.45it/s]
                                                    

 36%|███▌      | 3956/11066 [14:29<26:38,  4.45it/s]
 36%|███▌      | 3957/11066 [14:29<26:51,  4.41it/s]
                                                    

 36%|███▌      | 3957/11066 [14:29<26:51,  4.41it/s]
 36%|███▌      | 3958/11066 [14:30<26:44,  4.43it/s]
                                                    

 36%|███▌      | 3958/11066 [14:30<26:44,  4.43it/s]
 36%|███▌      | 3959/11066 [14:30<26:38,  4.45it/s]
                                                    

 36%|███▌      | 3959/11066 [14:30<26:38,  4.45it/s]
 36%|███▌      | 3960/11066 [14:30<26:21,  4.49it/s]
                                                    

 36%|███▌      | 3960/11066 [14:30<26:21,  4.49it/s]
 36%|███▌      | 3961/11066 [14:30<26:23,  4.49it/s]
                                                    

 36%|███▌      | 3961/11066 [14:30<26:23,  4.49it/s]
 36%|███▌      | 3962/11066 [14:30<26:35,  4.45it/s]
                                                    

 36%|███▌      | 3962/11066 [14:30<26:35,  4.45it/s]
 36%|███▌      | 3963/11066 [14:31<26:43,  4.43it/s]
                                                    

 36%|███▌      | 3963/11066 [14:31<26:43,  4.43it/s]
 36%|███▌      | 3964/11066 [14:31<26:36,  4.45it/s]
                                                    

 36%|███▌      | 3964/11066 [14:31<26:36,  4.45it/s]
 36%|███▌      | 3965/11066 [14:31<26:30,  4.46it/s]
                                                    

 36%|███▌      | 3965/11066 [14:31<26:30,  4.46it/s]
 36%|███▌      | 3966/11066 [14:31<26:26,  4.48it/s]
                                                    

 36%|███▌      | 3966/11066 [14:31<26:26,  4.48it/s]
 36%|███▌      | 3967/11066 [14:32<26:24,  4.48it/s]
                                                    

 36%|███▌      | 3967/11066 [14:32<26:24,  4.48it/s]
 36%|███▌      | 3968/11066 [14:32<26:22,  4.49it/s]
                                                    

 36%|███▌      | 3968/11066 [14:32<26:22,  4.49it/s]
 36%|███▌      | 3969/11066 [14:32<26:21,  4.49it/s]
                                                    

 36%|███▌      | 3969/11066 [14:32<26:21,  4.49it/s]
 36%|███▌      | 3970/11066 [14:32<26:20,  4.49it/s]
                                                    

 36%|███▌      | 3970/11066 [14:32<26:20,  4.49it/s]
 36%|███▌      | 3971/11066 [14:32<26:20,  4.49it/s]
                                                    

 36%|███▌      | 3971/11066 [14:32<26:20,  4.49it/s]
 36%|███▌      | 3972/11066 [14:33<26:08,  4.52it/s]
                                                    

 36%|███▌      | 3972/11066 [14:33<26:08,  4.52it/s]
 36%|███▌      | 3973/11066 [14:33<25:55,  4.56it/s]
                                                    

 36%|███▌      | 3973/11066 [14:33<25:55,  4.56it/s]
 36%|███▌      | 3974/11066 [14:33<26:05,  4.53it/s]
                                                    

 36%|███▌      | 3974/11066 [14:33<26:05,  4.53it/s]
 36%|███▌      | 3975/11066 [14:33<26:08,  4.52it/s]
                                                    

 36%|███▌      | 3975/11066 [14:33<26:08,  4.52it/s]
 36%|███▌      | 3976/11066 [14:34<26:12,  4.51it/s]
                                                    

 36%|███▌      | 3976/11066 [14:34<26:12,  4.51it/s]
 36%|███▌      | 3977/11066 [14:34<25:54,  4.56it/s]
                                                    

 36%|███▌      | 3977/11066 [14:34<25:54,  4.56it/s]
 36%|███▌      | 3978/11066 [14:34<25:39,  4.60it/s]
                                                    

 36%|███▌      | 3978/11066 [14:34<25:39,  4.60it/s]
 36%|███▌      | 3979/11066 [14:34<25:39,  4.60it/s]
                                                    

 36%|███▌      | 3979/11066 [14:34<25:39,  4.60it/s]
 36%|███▌      | 3980/11066 [14:34<25:40,  4.60it/s]
                                                    

 36%|███▌      | 3980/11066 [14:34<25:40,  4.60it/s]
 36%|███▌      | 3981/11066 [14:35<25:22,  4.65it/s]
                                                    

 36%|███▌      | 3981/11066 [14:35<25:22,  4.65it/s]
 36%|███▌      | 3982/11066 [14:35<25:28,  4.63it/s]
                                                    

 36%|███▌      | 3982/11066 [14:35<25:28,  4.63it/s]
 36%|███▌      | 3983/11066 [14:35<25:28,  4.63it/s]
                                                    

 36%|███▌      | 3983/11066 [14:35<25:28,  4.63it/s]
 36%|███▌      | 3984/11066 [14:35<25:30,  4.63it/s]
                                                    

 36%|███▌      | 3984/11066 [14:35<25:30,  4.63it/s]
 36%|███▌      | 3985/11066 [14:35<25:24,  4.64it/s]
                                                    

 36%|███▌      | 3985/11066 [14:35<25:24,  4.64it/s]
 36%|███▌      | 3986/11066 [14:36<25:22,  4.65it/s]
                                                    

 36%|███▌      | 3986/11066 [14:36<25:22,  4.65it/s]
 36%|███▌      | 3987/11066 [14:36<25:44,  4.58it/s]
                                                    

 36%|███▌      | 3987/11066 [14:36<25:44,  4.58it/s]
 36%|███▌      | 3988/11066 [14:36<25:23,  4.64it/s]
                                                    

 36%|███▌      | 3988/11066 [14:36<25:23,  4.64it/s]
 36%|███▌      | 3989/11066 [14:36<25:44,  4.58it/s]
                                                    

 36%|███▌      | 3989/11066 [14:36<25:44,  4.58it/s]
 36%|███▌      | 3990/11066 [14:37<25:53,  4.55it/s]
                                                    

 36%|███▌      | 3990/11066 [14:37<25:53,  4.55it/s]
 36%|███▌      | 3991/11066 [14:37<25:56,  4.54it/s]
                                                    

 36%|███▌      | 3991/11066 [14:37<25:56,  4.54it/s]
 36%|███▌      | 3992/11066 [14:37<26:03,  4.52it/s]
                                                    

 36%|███▌      | 3992/11066 [14:37<26:03,  4.52it/s]
 36%|███▌      | 3993/11066 [14:37<26:06,  4.52it/s]
                                                    

 36%|███▌      | 3993/11066 [14:37<26:06,  4.52it/s]
 36%|███▌      | 3994/11066 [14:37<26:07,  4.51it/s]
                                                    

 36%|███▌      | 3994/11066 [14:37<26:07,  4.51it/s]
 36%|███▌      | 3995/11066 [14:38<26:09,  4.51it/s]
                                                    

 36%|███▌      | 3995/11066 [14:38<26:09,  4.51it/s]
 36%|███▌      | 3996/11066 [14:38<25:48,  4.56it/s]
                                                    

 36%|███▌      | 3996/11066 [14:38<25:48,  4.56it/s]
 36%|███▌      | 3997/11066 [14:38<25:55,  4.54it/s]
                                                    

 36%|███▌      | 3997/11066 [14:38<25:55,  4.54it/s]
 36%|███▌      | 3998/11066 [14:38<25:59,  4.53it/s]
                                                    

 36%|███▌      | 3998/11066 [14:38<25:59,  4.53it/s]
 36%|███▌      | 3999/11066 [14:39<25:57,  4.54it/s]
                                                    

 36%|███▌      | 3999/11066 [14:39<25:57,  4.54it/s]
 36%|███▌      | 4000/11066 [14:39<26:03,  4.52it/s]
                                                    

 36%|███▌      | 4000/11066 [14:39<26:03,  4.52it/s]
 36%|███▌      | 4001/11066 [14:39<25:37,  4.60it/s]
                                                    

 36%|███▌      | 4001/11066 [14:39<25:37,  4.60it/s]
 36%|███▌      | 4002/11066 [14:39<25:54,  4.54it/s]
                                                    

 36%|███▌      | 4002/11066 [14:39<25:54,  4.54it/s]
 36%|███▌      | 4003/11066 [14:39<26:00,  4.53it/s]
                                                    

 36%|███▌      | 4003/11066 [14:39<26:00,  4.53it/s]
 36%|███▌      | 4004/11066 [14:40<26:03,  4.52it/s]
                                                    

 36%|███▌      | 4004/11066 [14:40<26:03,  4.52it/s]
 36%|███▌      | 4005/11066 [14:40<26:07,  4.50it/s]
                                                    

 36%|███▌      | 4005/11066 [14:40<26:07,  4.50it/s]
 36%|███▌      | 4006/11066 [14:40<26:07,  4.50it/s]
                                                    

 36%|███▌      | 4006/11066 [14:40<26:07,  4.50it/s]
 36%|███▌      | 4007/11066 [14:40<26:08,  4.50it/s]
                                                    

 36%|███▌      | 4007/11066 [14:40<26:08,  4.50it/s]
 36%|███▌      | 4008/11066 [14:41<26:10,  4.49it/s]
                                                    

 36%|███▌      | 4008/11066 [14:41<26:10,  4.49it/s]
 36%|███▌      | 4009/11066 [14:41<26:08,  4.50it/s]
                                                    

 36%|███▌      | 4009/11066 [14:41<26:08,  4.50it/s]
 36%|███▌      | 4010/11066 [14:41<26:06,  4.50it/s]
                                                    

 36%|███▌      | 4010/11066 [14:41<26:06,  4.50it/s]
 36%|███▌      | 4011/11066 [14:41<26:08,  4.50it/s]
                                                    

 36%|███▌      | 4011/11066 [14:41<26:08,  4.50it/s]
 36%|███▋      | 4012/11066 [14:41<26:11,  4.49it/s]
                                                    

 36%|███▋      | 4012/11066 [14:41<26:11,  4.49it/s]
 36%|███▋      | 4013/11066 [14:42<26:10,  4.49it/s]
                                                    

 36%|███▋      | 4013/11066 [14:42<26:10,  4.49it/s]
 36%|███▋      | 4014/11066 [14:42<26:10,  4.49it/s]
                                                    

 36%|███▋      | 4014/11066 [14:42<26:10,  4.49it/s]
 36%|███▋      | 4015/11066 [14:42<25:54,  4.54it/s]
                                                    

 36%|███▋      | 4015/11066 [14:42<25:54,  4.54it/s]
 36%|███▋      | 4016/11066 [14:42<26:00,  4.52it/s]
                                                    

 36%|███▋      | 4016/11066 [14:42<26:00,  4.52it/s]
 36%|███▋      | 4017/11066 [14:43<26:07,  4.50it/s]
                                                    

 36%|███▋      | 4017/11066 [14:43<26:07,  4.50it/s]
 36%|███▋      | 4018/11066 [14:43<26:13,  4.48it/s]
                                                    

 36%|███▋      | 4018/11066 [14:43<26:13,  4.48it/s]
 36%|███▋      | 4019/11066 [14:43<26:13,  4.48it/s]
                                                    

 36%|███▋      | 4019/11066 [14:43<26:13,  4.48it/s]
 36%|███▋      | 4020/11066 [14:43<26:12,  4.48it/s]
                                                    

 36%|███▋      | 4020/11066 [14:43<26:12,  4.48it/s]
 36%|███▋      | 4021/11066 [14:43<26:10,  4.49it/s]
                                                    

 36%|███▋      | 4021/11066 [14:43<26:10,  4.49it/s]
 36%|███▋      | 4022/11066 [14:44<26:10,  4.49it/s]
                                                    

 36%|███▋      | 4022/11066 [14:44<26:10,  4.49it/s]
 36%|███▋      | 4023/11066 [14:44<26:09,  4.49it/s]
                                                    

 36%|███▋      | 4023/11066 [14:44<26:09,  4.49it/s]
 36%|███▋      | 4024/11066 [14:44<26:08,  4.49it/s]
                                                    

 36%|███▋      | 4024/11066 [14:44<26:08,  4.49it/s]
 36%|███▋      | 4025/11066 [14:44<26:10,  4.48it/s]
                                                    

 36%|███▋      | 4025/11066 [14:44<26:10,  4.48it/s]
 36%|███▋      | 4026/11066 [14:45<26:06,  4.49it/s]
                                                    

 36%|███▋      | 4026/11066 [14:45<26:06,  4.49it/s]
 36%|███▋      | 4027/11066 [14:45<26:06,  4.49it/s]
                                                    

 36%|███▋      | 4027/11066 [14:45<26:06,  4.49it/s]
 36%|███▋      | 4028/11066 [14:45<26:07,  4.49it/s]
                                                    

 36%|███▋      | 4028/11066 [14:45<26:07,  4.49it/s]
 36%|███▋      | 4029/11066 [14:45<25:55,  4.52it/s]
                                                    

 36%|███▋      | 4029/11066 [14:45<25:55,  4.52it/s]
 36%|███▋      | 4030/11066 [14:45<25:56,  4.52it/s]
                                                    

 36%|███▋      | 4030/11066 [14:45<25:56,  4.52it/s]
 36%|███▋      | 4031/11066 [14:46<26:06,  4.49it/s]
                                                    

 36%|███▋      | 4031/11066 [14:46<26:06,  4.49it/s]
 36%|███▋      | 4032/11066 [14:46<26:09,  4.48it/s]
                                                    

 36%|███▋      | 4032/11066 [14:46<26:09,  4.48it/s]
 36%|███▋      | 4033/11066 [14:46<26:08,  4.48it/s]
                                                    

 36%|███▋      | 4033/11066 [14:46<26:08,  4.48it/s]
 36%|███▋      | 4034/11066 [14:46<26:09,  4.48it/s]
                                                    

 36%|███▋      | 4034/11066 [14:46<26:09,  4.48it/s]
 36%|███▋      | 4035/11066 [14:47<26:08,  4.48it/s]
                                                    

 36%|███▋      | 4035/11066 [14:47<26:08,  4.48it/s]
 36%|███▋      | 4036/11066 [14:47<26:08,  4.48it/s]
                                                    

 36%|███▋      | 4036/11066 [14:47<26:08,  4.48it/s]
 36%|███▋      | 4037/11066 [14:47<26:07,  4.48it/s]
                                                    

 36%|███▋      | 4037/11066 [14:47<26:07,  4.48it/s]
 36%|███▋      | 4038/11066 [14:47<26:07,  4.48it/s]
                                                    

 36%|███▋      | 4038/11066 [14:47<26:07,  4.48it/s]
 36%|███▋      | 4039/11066 [14:47<26:06,  4.48it/s]
                                                    

 36%|███▋      | 4039/11066 [14:47<26:06,  4.48it/s]
 37%|███▋      | 4040/11066 [14:48<26:06,  4.49it/s]
                                                    

 37%|███▋      | 4040/11066 [14:48<26:06,  4.49it/s]
 37%|███▋      | 4041/11066 [14:48<26:04,  4.49it/s]
                                                    

 37%|███▋      | 4041/11066 [14:48<26:04,  4.49it/s]
 37%|███▋      | 4042/11066 [14:48<26:03,  4.49it/s]
                                                    

 37%|███▋      | 4042/11066 [14:48<26:03,  4.49it/s]
 37%|███▋      | 4043/11066 [14:48<26:05,  4.49it/s]
                                                    

 37%|███▋      | 4043/11066 [14:48<26:05,  4.49it/s]
 37%|███▋      | 4044/11066 [14:49<26:06,  4.48it/s]
                                                    

 37%|███▋      | 4044/11066 [14:49<26:06,  4.48it/s]
 37%|███▋      | 4045/11066 [14:49<26:07,  4.48it/s]
                                                    

 37%|███▋      | 4045/11066 [14:49<26:07,  4.48it/s]
 37%|███▋      | 4046/11066 [14:49<26:08,  4.48it/s]
                                                    

 37%|███▋      | 4046/11066 [14:49<26:08,  4.48it/s]
 37%|███▋      | 4047/11066 [14:49<26:13,  4.46it/s]
                                                    

 37%|███▋      | 4047/11066 [14:49<26:13,  4.46it/s]
 37%|███▋      | 4048/11066 [14:49<26:13,  4.46it/s]
                                                    

 37%|███▋      | 4048/11066 [14:49<26:13,  4.46it/s]
 37%|███▋      | 4049/11066 [14:50<26:09,  4.47it/s]
                                                    

 37%|███▋      | 4049/11066 [14:50<26:09,  4.47it/s]
 37%|███▋      | 4050/11066 [14:50<26:06,  4.48it/s]
                                                    

 37%|███▋      | 4050/11066 [14:50<26:06,  4.48it/s]
 37%|███▋      | 4051/11066 [14:50<26:06,  4.48it/s]
                                                    
{'loss': 1.0296, 'learning_rate': 1.9321344659316827e-05, 'epoch': 0.71}
{'loss': 0.9837, 'learning_rate': 1.931863365262968e-05, 'epoch': 0.71}
{'loss': 1.0052, 'learning_rate': 1.9315922645942527e-05, 'epoch': 0.71}
{'loss': 1.2343, 'learning_rate': 1.9313211639255376e-05, 'epoch': 0.71}
{'loss': 1.2475, 'learning_rate': 1.9310500632568228e-05, 'epoch': 0.71}
{'loss': 0.9537, 'learning_rate': 1.9307789625881076e-05, 'epoch': 0.71}
{'loss': 1.0209, 'learning_rate': 1.9305078619193928e-05, 'epoch': 0.71}
{'loss': 0.4511, 'learning_rate': 1.930236761250678e-05, 'epoch': 0.71}
{'loss': 1.5751, 'learning_rate': 1.9299656605819628e-05, 'epoch': 0.71}
{'loss': 1.018, 'learning_rate': 1.929694559913248e-05, 'epoch': 0.71}
{'loss': 1.6488, 'learning_rate': 1.929423459244533e-05, 'epoch': 0.71}
{'loss': 0.9212, 'learning_rate': 1.9291523585758177e-05, 'epoch': 0.71}
{'loss': 0.7322, 'learning_rate': 1.928881257907103e-05, 'epoch': 0.71}
{'loss': 1.5123, 'learning_rate': 1.9286101572383877e-05, 'epoch': 0.71}
{'loss': 1.1912, 'learning_rate': 1.928339056569673e-05, 'epoch': 0.71}
{'loss': 0.9929, 'learning_rate': 1.928067955900958e-05, 'epoch': 0.71}
{'loss': 0.962, 'learning_rate': 1.927796855232243e-05, 'epoch': 0.71}
{'loss': 0.484, 'learning_rate': 1.927525754563528e-05, 'epoch': 0.71}
{'loss': 0.694, 'learning_rate': 1.9272546538948133e-05, 'epoch': 0.72}
{'loss': 0.8535, 'learning_rate': 1.9269835532260978e-05, 'epoch': 0.72}
{'loss': 0.7333, 'learning_rate': 1.926712452557383e-05, 'epoch': 0.72}
{'loss': 1.1163, 'learning_rate': 1.926441351888668e-05, 'epoch': 0.72}
{'loss': 1.1838, 'learning_rate': 1.926170251219953e-05, 'epoch': 0.72}
{'loss': 0.9434, 'learning_rate': 1.9258991505512382e-05, 'epoch': 0.72}
{'loss': 0.9635, 'learning_rate': 1.925628049882523e-05, 'epoch': 0.72}
{'loss': 0.6636, 'learning_rate': 1.9253569492138082e-05, 'epoch': 0.72}
{'loss': 2.2022, 'learning_rate': 1.9250858485450934e-05, 'epoch': 0.72}
{'loss': 1.1621, 'learning_rate': 1.924814747876378e-05, 'epoch': 0.72}
{'loss': 0.993, 'learning_rate': 1.924543647207663e-05, 'epoch': 0.72}
{'loss': 1.3704, 'learning_rate': 1.9242725465389483e-05, 'epoch': 0.72}
{'loss': 0.8394, 'learning_rate': 1.924001445870233e-05, 'epoch': 0.72}
{'loss': 1.7982, 'learning_rate': 1.9237303452015183e-05, 'epoch': 0.72}
{'loss': 1.6057, 'learning_rate': 1.9234592445328035e-05, 'epoch': 0.72}
{'loss': 0.7783, 'learning_rate': 1.9231881438640883e-05, 'epoch': 0.72}
{'loss': 0.9191, 'learning_rate': 1.9229170431953735e-05, 'epoch': 0.72}
{'loss': 0.707, 'learning_rate': 1.922645942526658e-05, 'epoch': 0.72}
{'loss': 1.5708, 'learning_rate': 1.9223748418579432e-05, 'epoch': 0.72}
{'loss': 0.7478, 'learning_rate': 1.9221037411892284e-05, 'epoch': 0.72}
{'loss': 1.7565, 'learning_rate': 1.9218326405205132e-05, 'epoch': 0.72}
{'loss': 0.7325, 'learning_rate': 1.9215615398517984e-05, 'epoch': 0.72}
{'loss': 1.4454, 'learning_rate': 1.9212904391830836e-05, 'epoch': 0.72}
{'loss': 1.2218, 'learning_rate': 1.9210193385143684e-05, 'epoch': 0.72}
{'loss': 1.0243, 'learning_rate': 1.9207482378456536e-05, 'epoch': 0.72}
{'loss': 1.2788, 'learning_rate': 1.9204771371769385e-05, 'epoch': 0.72}
{'loss': 1.9337, 'learning_rate': 1.9202060365082233e-05, 'epoch': 0.72}
{'loss': 1.2044, 'learning_rate': 1.9199349358395085e-05, 'epoch': 0.72}
{'loss': 1.2931, 'learning_rate': 1.9196638351707933e-05, 'epoch': 0.72}
{'loss': 0.9468, 'learning_rate': 1.9193927345020785e-05, 'epoch': 0.72}
{'loss': 1.2431, 'learning_rate': 1.9191216338333637e-05, 'epoch': 0.72}
{'loss': 0.9403, 'learning_rate': 1.9188505331646485e-05, 'epoch': 0.72}
{'loss': 1.0679, 'learning_rate': 1.9185794324959334e-05, 'epoch': 0.72}
{'loss': 1.3353, 'learning_rate': 1.9183083318272186e-05, 'epoch': 0.72}
{'loss': 1.1181, 'learning_rate': 1.9180372311585034e-05, 'epoch': 0.72}
{'loss': 0.7054, 'learning_rate': 1.9177661304897886e-05, 'epoch': 0.72}
{'loss': 1.6698, 'learning_rate': 1.9174950298210738e-05, 'epoch': 0.72}
{'loss': 1.3985, 'learning_rate': 1.9172239291523586e-05, 'epoch': 0.72}
{'loss': 1.1807, 'learning_rate': 1.9169528284836438e-05, 'epoch': 0.72}
{'loss': 1.0632, 'learning_rate': 1.9166817278149286e-05, 'epoch': 0.72}
{'loss': 1.0608, 'learning_rate': 1.9164106271462135e-05, 'epoch': 0.72}
{'loss': 1.2629, 'learning_rate': 1.9161395264774987e-05, 'epoch': 0.72}
{'loss': 0.7905, 'learning_rate': 1.9158684258087835e-05, 'epoch': 0.72}
{'loss': 1.4931, 'learning_rate': 1.9155973251400687e-05, 'epoch': 0.72}
{'loss': 0.9537, 'learning_rate': 1.915326224471354e-05, 'epoch': 0.72}
{'loss': 1.1855, 'learning_rate': 1.9150551238026387e-05, 'epoch': 0.72}
{'loss': 1.2077, 'learning_rate': 1.914784023133924e-05, 'epoch': 0.72}
{'loss': 1.3596, 'learning_rate': 1.914512922465209e-05, 'epoch': 0.72}
{'loss': 0.9903, 'learning_rate': 1.9142418217964936e-05, 'epoch': 0.72}
{'loss': 0.8865, 'learning_rate': 1.9139707211277788e-05, 'epoch': 0.72}
{'loss': 1.1667, 'learning_rate': 1.9136996204590636e-05, 'epoch': 0.72}
{'loss': 0.6299, 'learning_rate': 1.9134285197903488e-05, 'epoch': 0.72}
{'loss': 1.1428, 'learning_rate': 1.913157419121634e-05, 'epoch': 0.72}
{'loss': 1.3083, 'learning_rate': 1.9128863184529188e-05, 'epoch': 0.72}
{'loss': 1.0007, 'learning_rate': 1.912615217784204e-05, 'epoch': 0.72}
{'loss': 0.7108, 'learning_rate': 1.9123441171154892e-05, 'epoch': 0.73}
{'loss': 0.8071, 'learning_rate': 1.9120730164467737e-05, 'epoch': 0.73}
{'loss': 0.6903, 'learning_rate': 1.911801915778059e-05, 'epoch': 0.73}
{'loss': 1.0942, 'learning_rate': 1.911530815109344e-05, 'epoch': 0.73}
{'loss': 1.1092, 'learning_rate': 1.911259714440629e-05, 'epoch': 0.73}
{'loss': 1.6213, 'learning_rate': 1.910988613771914e-05, 'epoch': 0.73}
{'loss': 1.6607, 'learning_rate': 1.910717513103199e-05, 'epoch': 0.73}
{'loss': 1.0253, 'learning_rate': 1.910446412434484e-05, 'epoch': 0.73}
{'loss': 1.3673, 'learning_rate': 1.9101753117657693e-05, 'epoch': 0.73}
{'loss': 1.3775, 'learning_rate': 1.9099042110970538e-05, 'epoch': 0.73}
{'loss': 1.3057, 'learning_rate': 1.909633110428339e-05, 'epoch': 0.73}
{'loss': 0.8943, 'learning_rate': 1.9093620097596242e-05, 'epoch': 0.73}
{'loss': 1.4115, 'learning_rate': 1.909090909090909e-05, 'epoch': 0.73}
{'loss': 0.9618, 'learning_rate': 1.9088198084221942e-05, 'epoch': 0.73}
{'loss': 1.5904, 'learning_rate': 1.9085487077534794e-05, 'epoch': 0.73}
{'loss': 1.3625, 'learning_rate': 1.9082776070847642e-05, 'epoch': 0.73}
{'loss': 1.0466, 'learning_rate': 1.9080065064160494e-05, 'epoch': 0.73}
{'loss': 1.0959, 'learning_rate': 1.907735405747334e-05, 'epoch': 0.73}
{'loss': 0.8278, 'learning_rate': 1.907464305078619e-05, 'epoch': 0.73}
{'loss': 0.9809, 'learning_rate': 1.9071932044099043e-05, 'epoch': 0.73}
{'loss': 0.8774, 'learning_rate': 1.906922103741189e-05, 'epoch': 0.73}
{'loss': 1.3126, 'learning_rate': 1.9066510030724743e-05, 'epoch': 0.73}
{'loss': 1.8258, 'learning_rate': 1.9063799024037595e-05, 'epoch': 0.73}
{'loss': 1.1314, 'learning_rate': 1.9061088017350443e-05, 'epoch': 0.73}
{'loss': 1.2836, 'learning_rate': 1.9058377010663295e-05, 'epoch': 0.73}
{'loss': 0.778, 'learning_rate': 1.9055666003976144e-05, 'epoch': 0.73}
{'loss': 0.8445, 'learning_rate': 1.9052954997288992e-05, 'epoch': 0.73}
{'loss': 0.8307, 'learning_rate': 1.9050243990601844e-05, 'epoch': 0.73}
{'loss': 0.8397, 'learning_rate': 1.9047532983914692e-05, 'epoch': 0.73}
{'loss': 0.8399, 'learning_rate': 1.9044821977227544e-05, 'epoch': 0.73}
{'loss': 0.8318, 'learning_rate': 1.9042110970540396e-05, 'epoch': 0.73}
{'loss': 1.4683, 'learning_rate': 1.9039399963853244e-05, 'epoch': 0.73}
{'loss': 0.6677, 'learning_rate': 1.9036688957166096e-05, 'epoch': 0.73}
{'loss': 0.8368, 'learning_rate': 1.9033977950478945e-05, 'epoch': 0.73}
{'loss': 1.7353, 'learning_rate': 1.9031266943791793e-05, 'epoch': 0.73}
{'loss': 0.9286, 'learning_rate': 1.9028555937104645e-05, 'epoch': 0.73}
{'loss': 1.3322, 'learning_rate': 1.9025844930417497e-05, 'epoch': 0.73}
{'loss': 1.0779, 'learning_rate': 1.9023133923730345e-05, 'epoch': 0.73}
{'loss': 0.987, 'learning_rate': 1.9020422917043197e-05, 'epoch': 0.73}

 37%|███▋      | 4051/11066 [14:50<26:06,  4.48it/s]
 37%|███▋      | 4052/11066 [14:50<26:03,  4.49it/s]
                                                    

 37%|███▋      | 4052/11066 [14:50<26:03,  4.49it/s]
 37%|███▋      | 4053/11066 [14:51<26:03,  4.49it/s]
                                                    

 37%|███▋      | 4053/11066 [14:51<26:03,  4.49it/s]
 37%|███▋      | 4054/11066 [14:51<26:02,  4.49it/s]
                                                    

 37%|███▋      | 4054/11066 [14:51<26:02,  4.49it/s]
 37%|███▋      | 4055/11066 [14:51<26:03,  4.48it/s]
                                                    

 37%|███▋      | 4055/11066 [14:51<26:03,  4.48it/s]
 37%|███▋      | 4056/11066 [14:51<26:23,  4.43it/s]
                                                    

 37%|███▋      | 4056/11066 [14:51<26:23,  4.43it/s]
 37%|███▋      | 4057/11066 [14:51<26:29,  4.41it/s]
                                                    

 37%|███▋      | 4057/11066 [14:51<26:29,  4.41it/s]
 37%|███▋      | 4058/11066 [14:52<26:26,  4.42it/s]
                                                    

 37%|███▋      | 4058/11066 [14:52<26:26,  4.42it/s]
 37%|███▋      | 4059/11066 [14:52<26:20,  4.43it/s]
                                                    

 37%|███▋      | 4059/11066 [14:52<26:20,  4.43it/s]
 37%|███▋      | 4060/11066 [14:52<26:14,  4.45it/s]
                                                    

 37%|███▋      | 4060/11066 [14:52<26:14,  4.45it/s]
 37%|███▋      | 4061/11066 [14:52<26:10,  4.46it/s]
                                                    

 37%|███▋      | 4061/11066 [14:52<26:10,  4.46it/s]
 37%|███▋      | 4062/11066 [14:53<26:07,  4.47it/s]
                                                    

 37%|███▋      | 4062/11066 [14:53<26:07,  4.47it/s]
 37%|███▋      | 4063/11066 [14:53<26:04,  4.48it/s]
                                                    

 37%|███▋      | 4063/11066 [14:53<26:04,  4.48it/s]
 37%|███▋      | 4064/11066 [14:53<26:01,  4.48it/s]
                                                    

 37%|███▋      | 4064/11066 [14:53<26:01,  4.48it/s]
 37%|███▋      | 4065/11066 [14:53<26:01,  4.48it/s]
                                                    

 37%|███▋      | 4065/11066 [14:53<26:01,  4.48it/s]
 37%|███▋      | 4066/11066 [14:53<25:59,  4.49it/s]
                                                    

 37%|███▋      | 4066/11066 [14:53<25:59,  4.49it/s]
 37%|███▋      | 4067/11066 [14:54<25:59,  4.49it/s]
                                                    

 37%|███▋      | 4067/11066 [14:54<25:59,  4.49it/s]
 37%|███▋      | 4068/11066 [14:54<25:58,  4.49it/s]
                                                    

 37%|███▋      | 4068/11066 [14:54<25:58,  4.49it/s]
 37%|███▋      | 4069/11066 [14:54<25:59,  4.49it/s]
                                                    

 37%|███▋      | 4069/11066 [14:54<25:59,  4.49it/s]
 37%|███▋      | 4070/11066 [14:54<25:27,  4.58it/s]
                                                    

 37%|███▋      | 4070/11066 [14:54<25:27,  4.58it/s]
 37%|███▋      | 4071/11066 [14:55<25:43,  4.53it/s]
                                                    

 37%|███▋      | 4071/11066 [14:55<25:43,  4.53it/s]
 37%|███▋      | 4072/11066 [14:55<25:47,  4.52it/s]
                                                    

 37%|███▋      | 4072/11066 [14:55<25:47,  4.52it/s]
 37%|███▋      | 4073/11066 [14:55<25:49,  4.51it/s]
                                                    

 37%|███▋      | 4073/11066 [14:55<25:49,  4.51it/s]
 37%|███▋      | 4074/11066 [14:55<25:51,  4.51it/s]
                                                    

 37%|███▋      | 4074/11066 [14:55<25:51,  4.51it/s]
 37%|███▋      | 4075/11066 [14:55<25:53,  4.50it/s]
                                                    

 37%|███▋      | 4075/11066 [14:55<25:53,  4.50it/s]
 37%|███▋      | 4076/11066 [14:56<25:54,  4.50it/s]
                                                    

 37%|███▋      | 4076/11066 [14:56<25:54,  4.50it/s]
 37%|███▋      | 4077/11066 [14:56<25:54,  4.50it/s]
                                                    

 37%|███▋      | 4077/11066 [14:56<25:54,  4.50it/s]
 37%|███▋      | 4078/11066 [14:56<25:54,  4.50it/s]
                                                    

 37%|███▋      | 4078/11066 [14:56<25:54,  4.50it/s]
 37%|███▋      | 4079/11066 [14:56<25:53,  4.50it/s]
                                                    

 37%|███▋      | 4079/11066 [14:56<25:53,  4.50it/s]
 37%|███▋      | 4080/11066 [14:57<25:51,  4.50it/s]
                                                    

 37%|███▋      | 4080/11066 [14:57<25:51,  4.50it/s]
 37%|███▋      | 4081/11066 [14:57<25:52,  4.50it/s]
                                                    

 37%|███▋      | 4081/11066 [14:57<25:52,  4.50it/s]
 37%|███▋      | 4082/11066 [14:57<25:45,  4.52it/s]
                                                    

 37%|███▋      | 4082/11066 [14:57<25:45,  4.52it/s]
 37%|███▋      | 4083/11066 [14:57<25:56,  4.49it/s]
                                                    

 37%|███▋      | 4083/11066 [14:57<25:56,  4.49it/s]
 37%|███▋      | 4084/11066 [14:57<25:50,  4.50it/s]
                                                    

 37%|███▋      | 4084/11066 [14:57<25:50,  4.50it/s]
 37%|███▋      | 4085/11066 [14:58<25:52,  4.50it/s]
                                                    

 37%|███▋      | 4085/11066 [14:58<25:52,  4.50it/s]
 37%|███▋      | 4086/11066 [14:58<25:30,  4.56it/s]
                                                    

 37%|███▋      | 4086/11066 [14:58<25:30,  4.56it/s]
 37%|███▋      | 4087/11066 [14:58<25:15,  4.60it/s]
                                                    

 37%|███▋      | 4087/11066 [14:58<25:15,  4.60it/s]
 37%|███▋      | 4088/11066 [14:58<25:16,  4.60it/s]
                                                    

 37%|███▋      | 4088/11066 [14:58<25:16,  4.60it/s]
 37%|███▋      | 4089/11066 [14:59<25:11,  4.62it/s]
                                                    

 37%|███▋      | 4089/11066 [14:59<25:11,  4.62it/s]
 37%|███▋      | 4090/11066 [14:59<25:26,  4.57it/s]
                                                    

 37%|███▋      | 4090/11066 [14:59<25:26,  4.57it/s]
 37%|███▋      | 4091/11066 [14:59<25:12,  4.61it/s]
                                                    

 37%|███▋      | 4091/11066 [14:59<25:12,  4.61it/s]
 37%|███▋      | 4092/11066 [14:59<25:11,  4.61it/s]
                                                    

 37%|███▋      | 4092/11066 [14:59<25:11,  4.61it/s]
 37%|███▋      | 4093/11066 [14:59<24:57,  4.66it/s]
                                                    

 37%|███▋      | 4093/11066 [14:59<24:57,  4.66it/s]
 37%|███▋      | 4094/11066 [15:00<24:50,  4.68it/s]
                                                    

 37%|███▋      | 4094/11066 [15:00<24:50,  4.68it/s]
 37%|███▋      | 4095/11066 [15:00<24:46,  4.69it/s]
                                                    

 37%|███▋      | 4095/11066 [15:00<24:46,  4.69it/s]
 37%|███▋      | 4096/11066 [15:00<24:44,  4.70it/s]
                                                    

 37%|███▋      | 4096/11066 [15:00<24:44,  4.70it/s]
 37%|███▋      | 4097/11066 [15:00<24:50,  4.67it/s]
                                                    

 37%|███▋      | 4097/11066 [15:00<24:50,  4.67it/s]
 37%|███▋      | 4098/11066 [15:00<25:04,  4.63it/s]
                                                    

 37%|███▋      | 4098/11066 [15:00<25:04,  4.63it/s]
 37%|███▋      | 4099/11066 [15:01<25:26,  4.56it/s]
                                                    

 37%|███▋      | 4099/11066 [15:01<25:26,  4.56it/s]
 37%|███▋      | 4100/11066 [15:01<25:36,  4.53it/s]
                                                    

 37%|███▋      | 4100/11066 [15:01<25:36,  4.53it/s]
 37%|███▋      | 4101/11066 [15:01<25:41,  4.52it/s]
                                                    

 37%|███▋      | 4101/11066 [15:01<25:41,  4.52it/s]
 37%|███▋      | 4102/11066 [15:01<25:42,  4.52it/s]
                                                    

 37%|███▋      | 4102/11066 [15:01<25:42,  4.52it/s]
 37%|███▋      | 4103/11066 [15:02<25:44,  4.51it/s]
                                                    

 37%|███▋      | 4103/11066 [15:02<25:44,  4.51it/s]
 37%|███▋      | 4104/11066 [15:02<25:47,  4.50it/s]
                                                    

 37%|███▋      | 4104/11066 [15:02<25:47,  4.50it/s]
 37%|███▋      | 4105/11066 [15:02<25:47,  4.50it/s]
                                                    

 37%|███▋      | 4105/11066 [15:02<25:47,  4.50it/s]
 37%|███▋      | 4106/11066 [15:02<25:48,  4.49it/s]
                                                    

 37%|███▋      | 4106/11066 [15:02<25:48,  4.49it/s]
 37%|███▋      | 4107/11066 [15:02<25:26,  4.56it/s]
                                                    

 37%|███▋      | 4107/11066 [15:02<25:26,  4.56it/s]
 37%|███▋      | 4108/11066 [15:03<25:33,  4.54it/s]
                                                    

 37%|███▋      | 4108/11066 [15:03<25:33,  4.54it/s]
 37%|███▋      | 4109/11066 [15:03<25:16,  4.59it/s]
                                                    

 37%|███▋      | 4109/11066 [15:03<25:16,  4.59it/s]
 37%|███▋      | 4110/11066 [15:03<25:05,  4.62it/s]
                                                    

 37%|███▋      | 4110/11066 [15:03<25:05,  4.62it/s]
 37%|███▋      | 4111/11066 [15:03<24:55,  4.65it/s]
                                                    

 37%|███▋      | 4111/11066 [15:03<24:55,  4.65it/s]
 37%|███▋      | 4112/11066 [15:04<25:12,  4.60it/s]
                                                    

 37%|███▋      | 4112/11066 [15:04<25:12,  4.60it/s]
 37%|███▋      | 4113/11066 [15:04<25:18,  4.58it/s]
                                                    

 37%|███▋      | 4113/11066 [15:04<25:18,  4.58it/s]
 37%|███▋      | 4114/11066 [15:04<25:09,  4.61it/s]
                                                    

 37%|███▋      | 4114/11066 [15:04<25:09,  4.61it/s]
 37%|███▋      | 4115/11066 [15:04<25:24,  4.56it/s]
                                                    

 37%|███▋      | 4115/11066 [15:04<25:24,  4.56it/s]
 37%|███▋      | 4116/11066 [15:04<25:36,  4.52it/s]
                                                    

 37%|███▋      | 4116/11066 [15:04<25:36,  4.52it/s]
 37%|███▋      | 4117/11066 [15:05<25:47,  4.49it/s]
                                                    

 37%|███▋      | 4117/11066 [15:05<25:47,  4.49it/s]
 37%|███▋      | 4118/11066 [15:05<26:08,  4.43it/s]
                                                    

 37%|███▋      | 4118/11066 [15:05<26:08,  4.43it/s]
 37%|███▋      | 4119/11066 [15:05<26:01,  4.45it/s]
                                                    

 37%|███▋      | 4119/11066 [15:05<26:01,  4.45it/s]
 37%|███▋      | 4120/11066 [15:05<26:14,  4.41it/s]
                                                    

 37%|███▋      | 4120/11066 [15:05<26:14,  4.41it/s]
 37%|███▋      | 4121/11066 [15:06<26:00,  4.45it/s]
                                                    

 37%|███▋      | 4121/11066 [15:06<26:00,  4.45it/s]
 37%|███▋      | 4122/11066 [15:06<25:46,  4.49it/s]
                                                    

 37%|███▋      | 4122/11066 [15:06<25:46,  4.49it/s]
 37%|███▋      | 4123/11066 [15:06<25:49,  4.48it/s]
                                                    

 37%|███▋      | 4123/11066 [15:06<25:49,  4.48it/s]
 37%|███▋      | 4124/11066 [15:06<25:54,  4.47it/s]
                                                    

 37%|███▋      | 4124/11066 [15:06<25:54,  4.47it/s]
 37%|███▋      | 4125/11066 [15:06<25:41,  4.50it/s]
                                                    

 37%|███▋      | 4125/11066 [15:06<25:41,  4.50it/s]
 37%|███▋      | 4126/11066 [15:07<25:51,  4.47it/s]
                                                    

 37%|███▋      | 4126/11066 [15:07<25:51,  4.47it/s]
 37%|███▋      | 4127/11066 [15:07<25:31,  4.53it/s]
                                                    

 37%|███▋      | 4127/11066 [15:07<25:31,  4.53it/s]
 37%|███▋      | 4128/11066 [15:07<25:16,  4.58it/s]
                                                    

 37%|███▋      | 4128/11066 [15:07<25:16,  4.58it/s]
 37%|███▋      | 4129/11066 [15:07<25:01,  4.62it/s]
                                                    

 37%|███▋      | 4129/11066 [15:07<25:01,  4.62it/s]
 37%|███▋      | 4130/11066 [15:08<24:52,  4.65it/s]
                                                    

 37%|███▋      | 4130/11066 [15:08<24:52,  4.65it/s]
 37%|███▋      | 4131/11066 [15:08<24:51,  4.65it/s]
                                                    

 37%|███▋      | 4131/11066 [15:08<24:51,  4.65it/s]
 37%|███▋      | 4132/11066 [15:08<24:38,  4.69it/s]
                                                    

 37%|███▋      | 4132/11066 [15:08<24:38,  4.69it/s]
 37%|███▋      | 4133/11066 [15:08<24:59,  4.62it/s]
                                                    

 37%|███▋      | 4133/11066 [15:08<24:59,  4.62it/s]
 37%|███▋      | 4134/11066 [15:08<25:36,  4.51it/s]
                                                    

 37%|███▋      | 4134/11066 [15:08<25:36,  4.51it/s]
 37%|███▋      | 4135/11066 [15:09<25:34,  4.52it/s]
                                                    

 37%|███▋      | 4135/11066 [15:09<25:34,  4.52it/s]
 37%|███▋      | 4136/11066 [15:09<25:38,  4.50it/s]
                                                    

 37%|███▋      | 4136/11066 [15:09<25:38,  4.50it/s]
 37%|███▋      | 4137/11066 [15:09<26:04,  4.43it/s]
                                                    

 37%|███▋      | 4137/11066 [15:09<26:04,  4.43it/s]
 37%|███▋      | 4138/11066 [15:09<26:16,  4.39it/s]
                                                    

 37%|███▋      | 4138/11066 [15:09<26:16,  4.39it/s]
 37%|███▋      | 4139/11066 [15:10<25:38,  4.50it/s]
                                                    

 37%|███▋      | 4139/11066 [15:10<25:38,  4.50it/s]
 37%|███▋      | 4140/11066 [15:10<25:22,  4.55it/s]
                                                    

 37%|███▋      | 4140/11066 [15:10<25:22,  4.55it/s]
 37%|███▋      | 4141/11066 [15:10<25:01,  4.61it/s]
                                                    

 37%|███▋      | 4141/11066 [15:10<25:01,  4.61it/s]
 37%|███▋      | 4142/11066 [15:10<24:53,  4.63it/s]
                                                    

 37%|███▋      | 4142/11066 [15:10<24:53,  4.63it/s]
 37%|███▋      | 4143/11066 [15:10<24:59,  4.62it/s]
                                                    

 37%|███▋      | 4143/11066 [15:10<24:59,  4.62it/s]
 37%|███▋      | 4144/11066 [15:11<24:49,  4.65it/s]
                                                    

 37%|███▋      | 4144/11066 [15:11<24:49,  4.65it/s]
 37%|███▋      | 4145/11066 [15:11<25:07,  4.59it/s]
                                                    

 37%|███▋      | 4145/11066 [15:11<25:07,  4.59it/s]
 37%|███▋      | 4146/11066 [15:11<24:54,  4.63it/s]
                                                    

 37%|███▋      | 4146/11066 [15:11<24:54,  4.63it/s]
 37%|███▋      | 4147/11066 [15:11<24:46,  4.65it/s]
                                                    

 37%|███▋      | 4147/11066 [15:11<24:46,  4.65it/s]
 37%|███▋      | 4148/11066 [15:11<24:40,  4.67it/s]
                                                    

 37%|███▋      | 4148/11066 [15:11<24:40,  4.67it/s]
 37%|███▋      | 4149/11066 [15:12<24:36,  4.69it/s]
                                                    

 37%|███▋      | 4149/11066 [15:12<24:36,  4.69it/s]
 38%|███▊      | 4150/11066 [15:12<24:33,  4.69it/s]
                                                    

 38%|███▊      | 4150/11066 [15:12<24:33,  4.69it/s]
 38%|███▊      | 4151/11066 [15:12<24:31,  4.70it/s]
                                                    

 38%|███▊      | 4151/11066 [15:12<24:31,  4.70it/s]
 38%|███▊      | 4152/11066 [15:12<24:40,  4.67it/s]
                                                    

 38%|███▊      | 4152/11066 [15:12<24:40,  4.67it/s]
 38%|███▊      | 4153/11066 [15:13<24:47,  4.65it/s]
                                                    

 38%|███▊      | 4153/11066 [15:13<24:47,  4.65it/s]
 38%|███▊      | 4154/11066 [15:13<24:43,  4.66it/s]
                                                    

 38%|███▊      | 4154/11066 [15:13<24:43,  4.66it/s]
 38%|███▊      | 4155/11066 [15:13<25:02,  4.60it/s]
                                                    

 38%|███▊      | 4155/11066 [15:13<25:02,  4.60it/s]
 38%|███▊      | 4156/11066 [15:13<25:12,  4.57it/s]
                                                    

 38%|███▊      | 4156/11066 [15:13<25:12,  4.57it/s]
 38%|███▊      | 4157/11066 [15:13<25:07,  4.58it/s]
                                                    

 38%|███▊      | 4157/11066 [15:13<25:07,  4.58it/s]
 38%|███▊      | 4158/11066 [15:14<24:50,  4.63it/s]
                                                    

 38%|███▊      | 4158/11066 [15:14<24:50,  4.63it/s]
 38%|███▊      | 4159/11066 [15:14<24:45,  4.65it/s]
                                                    

 38%|███▊      | 4159/11066 [15:14<24:45,  4.65it/s]
 38%|███▊      | 4160/11066 [15:14<24:31,  4.69it/s]
                                                    

 38%|███▊      | 4160/11066 [15:14<24:31,  4.69it/s]
 38%|███▊      | 4161/11066 [15:14<24:52,  4.63it/s]
                                                    

 38%|███▊      | 4161/11066 [15:14<24:52,  4.63it/s]
 38%|███▊      | 4162/11066 [15:14<24:42,  4.66it/s]
                                                    

 38%|███▊      | 4162/11066 [15:14<24:42,  4.66it/s]
 38%|███▊      | 4163/11066 [15:15<24:58,  4.61it/s]
                                                    

 38%|███▊      | 4163/11066 [15:15<24:58,  4.61it/s]
 38%|███▊      | 4164/11066 [15:15<24:47,  4.64it/s]
                                                    
{'loss': 1.2969, 'learning_rate': 1.9017711910356045e-05, 'epoch': 0.73}
{'loss': 1.9701, 'learning_rate': 1.9015000903668897e-05, 'epoch': 0.73}
{'loss': 0.9566, 'learning_rate': 1.9012289896981746e-05, 'epoch': 0.73}
{'loss': 0.544, 'learning_rate': 1.9009578890294594e-05, 'epoch': 0.73}
{'loss': 1.1464, 'learning_rate': 1.9006867883607446e-05, 'epoch': 0.73}
{'loss': 1.4729, 'learning_rate': 1.9004156876920298e-05, 'epoch': 0.73}
{'loss': 1.131, 'learning_rate': 1.9001445870233146e-05, 'epoch': 0.73}
{'loss': 0.994, 'learning_rate': 1.8998734863545998e-05, 'epoch': 0.73}
{'loss': 0.6982, 'learning_rate': 1.899602385685885e-05, 'epoch': 0.73}
{'loss': 1.6543, 'learning_rate': 1.89933128501717e-05, 'epoch': 0.73}
{'loss': 1.5743, 'learning_rate': 1.8990601843484547e-05, 'epoch': 0.73}
{'loss': 1.7055, 'learning_rate': 1.8987890836797395e-05, 'epoch': 0.73}
{'loss': 1.1897, 'learning_rate': 1.8985179830110247e-05, 'epoch': 0.73}
{'loss': 1.6874, 'learning_rate': 1.89824688234231e-05, 'epoch': 0.73}
{'loss': 1.0816, 'learning_rate': 1.8979757816735947e-05, 'epoch': 0.73}
{'loss': 0.8552, 'learning_rate': 1.89770468100488e-05, 'epoch': 0.73}
{'loss': 1.1093, 'learning_rate': 1.897433580336165e-05, 'epoch': 0.74}
{'loss': 1.2928, 'learning_rate': 1.89716247966745e-05, 'epoch': 0.74}
{'loss': 1.0201, 'learning_rate': 1.8968913789987348e-05, 'epoch': 0.74}
{'loss': 1.3667, 'learning_rate': 1.89662027833002e-05, 'epoch': 0.74}
{'loss': 1.068, 'learning_rate': 1.8963491776613048e-05, 'epoch': 0.74}
{'loss': 1.3521, 'learning_rate': 1.89607807699259e-05, 'epoch': 0.74}
{'loss': 0.8441, 'learning_rate': 1.895806976323875e-05, 'epoch': 0.74}
{'loss': 1.1148, 'learning_rate': 1.89553587565516e-05, 'epoch': 0.74}
{'loss': 0.5434, 'learning_rate': 1.8952647749864452e-05, 'epoch': 0.74}
{'loss': 1.5676, 'learning_rate': 1.89499367431773e-05, 'epoch': 0.74}
{'loss': 0.9449, 'learning_rate': 1.894722573649015e-05, 'epoch': 0.74}
{'loss': 1.0002, 'learning_rate': 1.8944514729803e-05, 'epoch': 0.74}
{'loss': 0.8795, 'learning_rate': 1.894180372311585e-05, 'epoch': 0.74}
{'loss': 0.8081, 'learning_rate': 1.89390927164287e-05, 'epoch': 0.74}
{'loss': 0.7566, 'learning_rate': 1.8936381709741553e-05, 'epoch': 0.74}
{'loss': 0.7675, 'learning_rate': 1.89336707030544e-05, 'epoch': 0.74}
{'loss': 1.404, 'learning_rate': 1.8930959696367253e-05, 'epoch': 0.74}
{'loss': 0.967, 'learning_rate': 1.89282486896801e-05, 'epoch': 0.74}
{'loss': 0.9925, 'learning_rate': 1.892553768299295e-05, 'epoch': 0.74}
{'loss': 1.064, 'learning_rate': 1.8922826676305802e-05, 'epoch': 0.74}
{'loss': 0.8018, 'learning_rate': 1.892011566961865e-05, 'epoch': 0.74}
{'loss': 1.0773, 'learning_rate': 1.8917404662931502e-05, 'epoch': 0.74}
{'loss': 1.0949, 'learning_rate': 1.8914693656244354e-05, 'epoch': 0.74}
{'loss': 1.0855, 'learning_rate': 1.8911982649557202e-05, 'epoch': 0.74}
{'loss': 0.9051, 'learning_rate': 1.8909271642870054e-05, 'epoch': 0.74}
{'loss': 1.0342, 'learning_rate': 1.8906560636182906e-05, 'epoch': 0.74}
{'loss': 1.246, 'learning_rate': 1.890384962949575e-05, 'epoch': 0.74}
{'loss': 0.9919, 'learning_rate': 1.8901138622808603e-05, 'epoch': 0.74}
{'loss': 1.9156, 'learning_rate': 1.8898427616121455e-05, 'epoch': 0.74}
{'loss': 1.0148, 'learning_rate': 1.8895716609434303e-05, 'epoch': 0.74}
{'loss': 0.6305, 'learning_rate': 1.8893005602747155e-05, 'epoch': 0.74}
{'loss': 0.8766, 'learning_rate': 1.8890294596060003e-05, 'epoch': 0.74}
{'loss': 1.1614, 'learning_rate': 1.8887583589372855e-05, 'epoch': 0.74}
{'loss': 1.2272, 'learning_rate': 1.8884872582685707e-05, 'epoch': 0.74}
{'loss': 0.7604, 'learning_rate': 1.8882161575998552e-05, 'epoch': 0.74}
{'loss': 1.0257, 'learning_rate': 1.8879450569311404e-05, 'epoch': 0.74}
{'loss': 1.1084, 'learning_rate': 1.8876739562624256e-05, 'epoch': 0.74}
{'loss': 1.6394, 'learning_rate': 1.8874028555937104e-05, 'epoch': 0.74}
{'loss': 1.358, 'learning_rate': 1.8871317549249956e-05, 'epoch': 0.74}
{'loss': 1.3384, 'learning_rate': 1.8868606542562808e-05, 'epoch': 0.74}
{'loss': 0.9843, 'learning_rate': 1.8865895535875656e-05, 'epoch': 0.74}
{'loss': 1.0821, 'learning_rate': 1.8863184529188508e-05, 'epoch': 0.74}
{'loss': 0.9494, 'learning_rate': 1.8860473522501353e-05, 'epoch': 0.74}
{'loss': 1.5904, 'learning_rate': 1.8857762515814205e-05, 'epoch': 0.74}
{'loss': 0.7814, 'learning_rate': 1.8855051509127057e-05, 'epoch': 0.74}
{'loss': 1.3541, 'learning_rate': 1.8852340502439905e-05, 'epoch': 0.74}
{'loss': 1.4688, 'learning_rate': 1.8849629495752757e-05, 'epoch': 0.74}
{'loss': 0.7477, 'learning_rate': 1.884691848906561e-05, 'epoch': 0.74}
{'loss': 0.7241, 'learning_rate': 1.8844207482378457e-05, 'epoch': 0.74}
{'loss': 1.0155, 'learning_rate': 1.884149647569131e-05, 'epoch': 0.74}
{'loss': 1.2676, 'learning_rate': 1.8838785469004158e-05, 'epoch': 0.74}
{'loss': 0.6602, 'learning_rate': 1.8836074462317006e-05, 'epoch': 0.74}
{'loss': 0.8138, 'learning_rate': 1.8833363455629858e-05, 'epoch': 0.74}
{'loss': 0.7063, 'learning_rate': 1.8830652448942706e-05, 'epoch': 0.74}
{'loss': 0.9549, 'learning_rate': 1.8827941442255558e-05, 'epoch': 0.74}
{'loss': 1.5397, 'learning_rate': 1.882523043556841e-05, 'epoch': 0.74}
{'loss': 1.9312, 'learning_rate': 1.882251942888126e-05, 'epoch': 0.75}
{'loss': 1.7265, 'learning_rate': 1.8819808422194107e-05, 'epoch': 0.75}
{'loss': 0.9665, 'learning_rate': 1.881709741550696e-05, 'epoch': 0.75}
{'loss': 1.2353, 'learning_rate': 1.8814386408819807e-05, 'epoch': 0.75}
{'loss': 1.7221, 'learning_rate': 1.881167540213266e-05, 'epoch': 0.75}
{'loss': 0.3966, 'learning_rate': 1.880896439544551e-05, 'epoch': 0.75}
{'loss': 0.8913, 'learning_rate': 1.880625338875836e-05, 'epoch': 0.75}
{'loss': 0.707, 'learning_rate': 1.880354238207121e-05, 'epoch': 0.75}
{'loss': 1.1635, 'learning_rate': 1.880083137538406e-05, 'epoch': 0.75}
{'loss': 0.8502, 'learning_rate': 1.8798120368696908e-05, 'epoch': 0.75}
{'loss': 1.124, 'learning_rate': 1.879540936200976e-05, 'epoch': 0.75}
{'loss': 0.9938, 'learning_rate': 1.879269835532261e-05, 'epoch': 0.75}
{'loss': 0.9543, 'learning_rate': 1.878998734863546e-05, 'epoch': 0.75}
{'loss': 1.2232, 'learning_rate': 1.8787276341948312e-05, 'epoch': 0.75}
{'loss': 1.5025, 'learning_rate': 1.878456533526116e-05, 'epoch': 0.75}
{'loss': 0.5931, 'learning_rate': 1.8781854328574012e-05, 'epoch': 0.75}
{'loss': 1.4356, 'learning_rate': 1.8779143321886864e-05, 'epoch': 0.75}
{'loss': 2.3294, 'learning_rate': 1.877643231519971e-05, 'epoch': 0.75}
{'loss': 1.0618, 'learning_rate': 1.877372130851256e-05, 'epoch': 0.75}
{'loss': 0.8148, 'learning_rate': 1.877101030182541e-05, 'epoch': 0.75}
{'loss': 1.1325, 'learning_rate': 1.876829929513826e-05, 'epoch': 0.75}
{'loss': 1.0747, 'learning_rate': 1.8765588288451113e-05, 'epoch': 0.75}
{'loss': 1.1443, 'learning_rate': 1.876287728176396e-05, 'epoch': 0.75}
{'loss': 0.6908, 'learning_rate': 1.8760166275076813e-05, 'epoch': 0.75}
{'loss': 1.1958, 'learning_rate': 1.8757455268389665e-05, 'epoch': 0.75}
{'loss': 2.0696, 'learning_rate': 1.875474426170251e-05, 'epoch': 0.75}
{'loss': 1.4314, 'learning_rate': 1.8752033255015362e-05, 'epoch': 0.75}
{'loss': 1.0035, 'learning_rate': 1.8749322248328214e-05, 'epoch': 0.75}
{'loss': 0.7965, 'learning_rate': 1.8746611241641062e-05, 'epoch': 0.75}
{'loss': 1.6436, 'learning_rate': 1.8743900234953914e-05, 'epoch': 0.75}
{'loss': 1.4065, 'learning_rate': 1.8741189228266763e-05, 'epoch': 0.75}
{'loss': 1.3834, 'learning_rate': 1.8738478221579614e-05, 'epoch': 0.75}
{'loss': 1.2043, 'learning_rate': 1.8735767214892466e-05, 'epoch': 0.75}
{'loss': 0.5839, 'learning_rate': 1.873305620820531e-05, 'epoch': 0.75}
{'loss': 1.3701, 'learning_rate': 1.8730345201518163e-05, 'epoch': 0.75}
{'loss': 0.8201, 'learning_rate': 1.8727634194831015e-05, 'epoch': 0.75}
{'loss': 1.0926, 'learning_rate': 1.8724923188143863e-05, 'epoch': 0.75}
{'loss': 1.1272, 'learning_rate': 1.8722212181456715e-05, 'epoch': 0.75}
{'loss': 0.698, 'learning_rate': 1.8719501174769567e-05, 'epoch': 0.75}
{'loss': 1.2859, 'learning_rate': 1.8716790168082415e-05, 'epoch': 0.75}
{'loss': 0.8272, 'learning_rate': 1.8714079161395267e-05, 'epoch': 0.75}

 38%|███▊      | 4164/11066 [15:15<24:47,  4.64it/s]
 38%|███▊      | 4165/11066 [15:15<24:40,  4.66it/s]
                                                    

 38%|███▊      | 4165/11066 [15:15<24:40,  4.66it/s]
 38%|███▊      | 4166/11066 [15:15<24:34,  4.68it/s]
                                                    

 38%|███▊      | 4166/11066 [15:15<24:34,  4.68it/s]
 38%|███▊      | 4167/11066 [15:16<24:30,  4.69it/s]
                                                    

 38%|███▊      | 4167/11066 [15:16<24:30,  4.69it/s]
 38%|███▊      | 4168/11066 [15:16<24:30,  4.69it/s]
                                                    

 38%|███▊      | 4168/11066 [15:16<24:30,  4.69it/s]
 38%|███▊      | 4169/11066 [15:16<24:31,  4.69it/s]
                                                    

 38%|███▊      | 4169/11066 [15:16<24:31,  4.69it/s]
 38%|███▊      | 4170/11066 [15:16<24:29,  4.69it/s]
                                                    

 38%|███▊      | 4170/11066 [15:16<24:29,  4.69it/s]
 38%|███▊      | 4171/11066 [15:16<24:27,  4.70it/s]
                                                    

 38%|███▊      | 4171/11066 [15:16<24:27,  4.70it/s]
 38%|███▊      | 4172/11066 [15:17<24:26,  4.70it/s]
                                                    

 38%|███▊      | 4172/11066 [15:17<24:26,  4.70it/s]
 38%|███▊      | 4173/11066 [15:17<24:49,  4.63it/s]
                                                    

 38%|███▊      | 4173/11066 [15:17<24:49,  4.63it/s]
 38%|███▊      | 4174/11066 [15:17<24:44,  4.64it/s]
                                                    

 38%|███▊      | 4174/11066 [15:17<24:44,  4.64it/s]
 38%|███▊      | 4175/11066 [15:17<24:57,  4.60it/s]
                                                    

 38%|███▊      | 4175/11066 [15:17<24:57,  4.60it/s]
 38%|███▊      | 4176/11066 [15:18<25:06,  4.57it/s]
                                                    

 38%|███▊      | 4176/11066 [15:18<25:06,  4.57it/s]
 38%|███▊      | 4177/11066 [15:18<25:14,  4.55it/s]
                                                    

 38%|███▊      | 4177/11066 [15:18<25:14,  4.55it/s]
 38%|███▊      | 4178/11066 [15:18<25:18,  4.54it/s]
                                                    

 38%|███▊      | 4178/11066 [15:18<25:18,  4.54it/s]
 38%|███▊      | 4179/11066 [15:18<25:23,  4.52it/s]
                                                    

 38%|███▊      | 4179/11066 [15:18<25:23,  4.52it/s]
 38%|███▊      | 4180/11066 [15:18<25:25,  4.51it/s]
                                                    

 38%|███▊      | 4180/11066 [15:18<25:25,  4.51it/s]
 38%|███▊      | 4181/11066 [15:19<25:05,  4.57it/s]
                                                    

 38%|███▊      | 4181/11066 [15:19<25:05,  4.57it/s]
 38%|███▊      | 4182/11066 [15:19<25:15,  4.54it/s]
                                                    

 38%|███▊      | 4182/11066 [15:19<25:15,  4.54it/s]
 38%|███▊      | 4183/11066 [15:19<25:02,  4.58it/s]
                                                    

 38%|███▊      | 4183/11066 [15:19<25:02,  4.58it/s]
 38%|███▊      | 4184/11066 [15:19<24:54,  4.61it/s]
                                                    

 38%|███▊      | 4184/11066 [15:19<24:54,  4.61it/s]
 38%|███▊      | 4185/11066 [15:19<24:39,  4.65it/s]
                                                    

 38%|███▊      | 4185/11066 [15:19<24:39,  4.65it/s]
 38%|███▊      | 4186/11066 [15:20<24:25,  4.69it/s]
                                                    

 38%|███▊      | 4186/11066 [15:20<24:25,  4.69it/s]
 38%|███▊      | 4187/11066 [15:20<24:36,  4.66it/s]
                                                    

 38%|███▊      | 4187/11066 [15:20<24:36,  4.66it/s]
 38%|███▊      | 4188/11066 [15:20<24:23,  4.70it/s]
                                                    

 38%|███▊      | 4188/11066 [15:20<24:23,  4.70it/s]
 38%|███▊      | 4189/11066 [15:20<24:33,  4.67it/s]
                                                    

 38%|███▊      | 4189/11066 [15:20<24:33,  4.67it/s]
 38%|███▊      | 4190/11066 [15:21<24:51,  4.61it/s]
                                                    

 38%|███▊      | 4190/11066 [15:21<24:51,  4.61it/s]
 38%|███▊      | 4191/11066 [15:21<24:53,  4.60it/s]
                                                    

 38%|███▊      | 4191/11066 [15:21<24:53,  4.60it/s]
 38%|███▊      | 4192/11066 [15:21<24:35,  4.66it/s]
                                                    

 38%|███▊      | 4192/11066 [15:21<24:35,  4.66it/s]
 38%|███▊      | 4193/11066 [15:21<25:01,  4.58it/s]
                                                    

 38%|███▊      | 4193/11066 [15:21<25:01,  4.58it/s]
 38%|███▊      | 4194/11066 [15:21<24:44,  4.63it/s]
                                                    

 38%|███▊      | 4194/11066 [15:21<24:44,  4.63it/s]
 38%|███▊      | 4195/11066 [15:22<24:48,  4.62it/s]
                                                    

 38%|███▊      | 4195/11066 [15:22<24:48,  4.62it/s]
 38%|███▊      | 4196/11066 [15:22<24:48,  4.62it/s]
                                                    

 38%|███▊      | 4196/11066 [15:22<24:48,  4.62it/s]
 38%|███▊      | 4197/11066 [15:22<25:02,  4.57it/s]
                                                    

 38%|███▊      | 4197/11066 [15:22<25:02,  4.57it/s]
 38%|███▊      | 4198/11066 [15:22<25:10,  4.55it/s]
                                                    

 38%|███▊      | 4198/11066 [15:22<25:10,  4.55it/s]
 38%|███▊      | 4199/11066 [15:23<24:55,  4.59it/s]
                                                    

 38%|███▊      | 4199/11066 [15:23<24:55,  4.59it/s]
 38%|███▊      | 4200/11066 [15:23<25:01,  4.57it/s]
                                                    

 38%|███▊      | 4200/11066 [15:23<25:01,  4.57it/s]
 38%|███▊      | 4201/11066 [15:23<24:53,  4.60it/s]
                                                    

 38%|███▊      | 4201/11066 [15:23<24:53,  4.60it/s]
 38%|███▊      | 4202/11066 [15:23<24:42,  4.63it/s]
                                                    

 38%|███▊      | 4202/11066 [15:23<24:42,  4.63it/s]
 38%|███▊      | 4203/11066 [15:23<24:34,  4.65it/s]
                                                    

 38%|███▊      | 4203/11066 [15:23<24:34,  4.65it/s]
 38%|███▊      | 4204/11066 [15:24<24:40,  4.63it/s]
                                                    

 38%|███▊      | 4204/11066 [15:24<24:40,  4.63it/s]
 38%|███▊      | 4205/11066 [15:24<25:29,  4.49it/s]
                                                    

 38%|███▊      | 4205/11066 [15:24<25:29,  4.49it/s]
 38%|███▊      | 4206/11066 [15:24<25:36,  4.47it/s]
                                                    

 38%|███▊      | 4206/11066 [15:24<25:36,  4.47it/s]
 38%|███▊      | 4207/11066 [15:24<25:29,  4.48it/s]
                                                    

 38%|███▊      | 4207/11066 [15:24<25:29,  4.48it/s]
 38%|███▊      | 4208/11066 [15:24<25:05,  4.55it/s]
                                                    

 38%|███▊      | 4208/11066 [15:24<25:05,  4.55it/s]
 38%|███▊      | 4209/11066 [15:25<25:11,  4.54it/s]
                                                    

 38%|███▊      | 4209/11066 [15:25<25:11,  4.54it/s]
 38%|███▊      | 4210/11066 [15:25<25:04,  4.56it/s]
                                                    

 38%|███▊      | 4210/11066 [15:25<25:04,  4.56it/s]
 38%|███▊      | 4211/11066 [15:25<25:19,  4.51it/s]
                                                    

 38%|███▊      | 4211/11066 [15:25<25:19,  4.51it/s]
 38%|███▊      | 4212/11066 [15:25<25:11,  4.54it/s]
                                                    

 38%|███▊      | 4212/11066 [15:25<25:11,  4.54it/s]
 38%|███▊      | 4213/11066 [15:26<25:11,  4.53it/s]
                                                    

 38%|███▊      | 4213/11066 [15:26<25:11,  4.53it/s]
 38%|███▊      | 4214/11066 [15:26<24:59,  4.57it/s]
                                                    

 38%|███▊      | 4214/11066 [15:26<24:59,  4.57it/s]
 38%|███▊      | 4215/11066 [15:26<24:46,  4.61it/s]
                                                    

 38%|███▊      | 4215/11066 [15:26<24:46,  4.61it/s]
 38%|███▊      | 4216/11066 [15:26<25:01,  4.56it/s]
                                                    

 38%|███▊      | 4216/11066 [15:26<25:01,  4.56it/s]
 38%|███▊      | 4217/11066 [15:26<24:47,  4.60it/s]
                                                    

 38%|███▊      | 4217/11066 [15:26<24:47,  4.60it/s]
 38%|███▊      | 4218/11066 [15:27<24:58,  4.57it/s]
                                                    

 38%|███▊      | 4218/11066 [15:27<24:58,  4.57it/s]
 38%|███▊      | 4219/11066 [15:27<24:44,  4.61it/s]
                                                    

 38%|███▊      | 4219/11066 [15:27<24:44,  4.61it/s]
 38%|███▊      | 4220/11066 [15:27<24:43,  4.61it/s]
                                                    

 38%|███▊      | 4220/11066 [15:27<24:43,  4.61it/s]
 38%|███▊      | 4221/11066 [15:27<24:28,  4.66it/s]
                                                    

 38%|███▊      | 4221/11066 [15:27<24:28,  4.66it/s]
 38%|███▊      | 4222/11066 [15:28<24:31,  4.65it/s]
                                                    

 38%|███▊      | 4222/11066 [15:28<24:31,  4.65it/s]
 38%|███▊      | 4223/11066 [15:28<24:45,  4.61it/s]
                                                    

 38%|███▊      | 4223/11066 [15:28<24:45,  4.61it/s]
 38%|███▊      | 4224/11066 [15:28<24:37,  4.63it/s]
                                                    

 38%|███▊      | 4224/11066 [15:28<24:37,  4.63it/s]
 38%|███▊      | 4225/11066 [15:28<24:55,  4.57it/s]
                                                    

 38%|███▊      | 4225/11066 [15:28<24:55,  4.57it/s]
 38%|███▊      | 4226/11066 [15:28<24:43,  4.61it/s]
                                                    

 38%|███▊      | 4226/11066 [15:28<24:43,  4.61it/s]
 38%|███▊      | 4227/11066 [15:29<24:42,  4.61it/s]
                                                    

 38%|███▊      | 4227/11066 [15:29<24:42,  4.61it/s]
 38%|███▊      | 4228/11066 [15:29<24:56,  4.57it/s]
                                                    

 38%|███▊      | 4228/11066 [15:29<24:56,  4.57it/s]
 38%|███▊      | 4229/11066 [15:29<25:06,  4.54it/s]
                                                    

 38%|███▊      | 4229/11066 [15:29<25:06,  4.54it/s]
 38%|███▊      | 4230/11066 [15:29<25:10,  4.53it/s]
                                                    

 38%|███▊      | 4230/11066 [15:29<25:10,  4.53it/s]
 38%|███▊      | 4231/11066 [15:30<25:12,  4.52it/s]
                                                    

 38%|███▊      | 4231/11066 [15:30<25:12,  4.52it/s]
 38%|███▊      | 4232/11066 [15:30<25:13,  4.51it/s]
                                                    

 38%|███▊      | 4232/11066 [15:30<25:13,  4.51it/s]
 38%|███▊      | 4233/11066 [15:30<25:16,  4.51it/s]
                                                    

 38%|███▊      | 4233/11066 [15:30<25:16,  4.51it/s]
 38%|███▊      | 4234/11066 [15:30<25:16,  4.51it/s]
                                                    

 38%|███▊      | 4234/11066 [15:30<25:16,  4.51it/s]
 38%|███▊      | 4235/11066 [15:30<25:03,  4.54it/s]
                                                    

 38%|███▊      | 4235/11066 [15:30<25:03,  4.54it/s]
 38%|███▊      | 4236/11066 [15:31<25:02,  4.55it/s]
                                                    

 38%|███▊      | 4236/11066 [15:31<25:02,  4.55it/s]
 38%|███▊      | 4237/11066 [15:31<25:08,  4.53it/s]
                                                    

 38%|███▊      | 4237/11066 [15:31<25:08,  4.53it/s]
 38%|███▊      | 4238/11066 [15:31<25:01,  4.55it/s]
                                                    

 38%|███▊      | 4238/11066 [15:31<25:01,  4.55it/s]
 38%|███▊      | 4239/11066 [15:31<25:12,  4.51it/s]
                                                    

 38%|███▊      | 4239/11066 [15:31<25:12,  4.51it/s]
 38%|███▊      | 4240/11066 [15:31<25:14,  4.51it/s]
                                                    

 38%|███▊      | 4240/11066 [15:31<25:14,  4.51it/s]
 38%|███▊      | 4241/11066 [15:32<25:13,  4.51it/s]
                                                    

 38%|███▊      | 4241/11066 [15:32<25:13,  4.51it/s]
 38%|███▊      | 4242/11066 [15:32<25:13,  4.51it/s]
                                                    

 38%|███▊      | 4242/11066 [15:32<25:13,  4.51it/s]
 38%|███▊      | 4243/11066 [15:32<25:13,  4.51it/s]
                                                    

 38%|███▊      | 4243/11066 [15:32<25:13,  4.51it/s]
 38%|███▊      | 4244/11066 [15:32<25:14,  4.50it/s]
                                                    

 38%|███▊      | 4244/11066 [15:32<25:14,  4.50it/s]
 38%|███▊      | 4245/11066 [15:33<25:15,  4.50it/s]
                                                    

 38%|███▊      | 4245/11066 [15:33<25:15,  4.50it/s]
 38%|███▊      | 4246/11066 [15:33<25:03,  4.54it/s]
                                                    

 38%|███▊      | 4246/11066 [15:33<25:03,  4.54it/s]
 38%|███▊      | 4247/11066 [15:33<25:12,  4.51it/s]
                                                    

 38%|███▊      | 4247/11066 [15:33<25:12,  4.51it/s]
 38%|███▊      | 4248/11066 [15:33<25:16,  4.50it/s]
                                                    

 38%|███▊      | 4248/11066 [15:33<25:16,  4.50it/s]
 38%|███▊      | 4249/11066 [15:33<25:16,  4.50it/s]
                                                    

 38%|███▊      | 4249/11066 [15:33<25:16,  4.50it/s]
 38%|███▊      | 4250/11066 [15:34<25:14,  4.50it/s]
                                                    

 38%|███▊      | 4250/11066 [15:34<25:14,  4.50it/s]
 38%|███▊      | 4251/11066 [15:34<25:02,  4.54it/s]
                                                    

 38%|███▊      | 4251/11066 [15:34<25:02,  4.54it/s]
 38%|███▊      | 4252/11066 [15:34<25:12,  4.50it/s]
                                                    

 38%|███▊      | 4252/11066 [15:34<25:12,  4.50it/s]
 38%|███▊      | 4253/11066 [15:34<25:17,  4.49it/s]
                                                    

 38%|███▊      | 4253/11066 [15:34<25:17,  4.49it/s]
 38%|███▊      | 4254/11066 [15:35<25:15,  4.49it/s]
                                                    

 38%|███▊      | 4254/11066 [15:35<25:15,  4.49it/s]
 38%|███▊      | 4255/11066 [15:35<25:14,  4.50it/s]
                                                    

 38%|███▊      | 4255/11066 [15:35<25:14,  4.50it/s]
 38%|███▊      | 4256/11066 [15:35<25:12,  4.50it/s]
                                                    

 38%|███▊      | 4256/11066 [15:35<25:12,  4.50it/s]
 38%|███▊      | 4257/11066 [15:35<24:59,  4.54it/s]
                                                    

 38%|███▊      | 4257/11066 [15:35<24:59,  4.54it/s]
 38%|███▊      | 4258/11066 [15:35<24:58,  4.54it/s]
                                                    

 38%|███▊      | 4258/11066 [15:35<24:58,  4.54it/s]
 38%|███▊      | 4259/11066 [15:36<24:35,  4.61it/s]
                                                    

 38%|███▊      | 4259/11066 [15:36<24:35,  4.61it/s]
 38%|███▊      | 4260/11066 [15:36<24:28,  4.64it/s]
                                                    

 38%|███▊      | 4260/11066 [15:36<24:28,  4.64it/s]
 39%|███▊      | 4261/11066 [15:36<24:23,  4.65it/s]
                                                    

 39%|███▊      | 4261/11066 [15:36<24:23,  4.65it/s]
 39%|███▊      | 4262/11066 [15:36<24:13,  4.68it/s]
                                                    

 39%|███▊      | 4262/11066 [15:36<24:13,  4.68it/s]
 39%|███▊      | 4263/11066 [15:37<24:34,  4.61it/s]
                                                    

 39%|███▊      | 4263/11066 [15:37<24:34,  4.61it/s]
 39%|███▊      | 4264/11066 [15:37<24:26,  4.64it/s]
                                                    

 39%|███▊      | 4264/11066 [15:37<24:26,  4.64it/s]
 39%|███▊      | 4265/11066 [15:37<24:40,  4.59it/s]
                                                    

 39%|███▊      | 4265/11066 [15:37<24:40,  4.59it/s]
 39%|███▊      | 4266/11066 [15:37<24:32,  4.62it/s]
                                                    

 39%|███▊      | 4266/11066 [15:37<24:32,  4.62it/s]
 39%|███▊      | 4267/11066 [15:37<24:48,  4.57it/s]
                                                    

 39%|███▊      | 4267/11066 [15:37<24:48,  4.57it/s]
 39%|███▊      | 4268/11066 [15:38<24:43,  4.58it/s]
                                                    

 39%|███▊      | 4268/11066 [15:38<24:43,  4.58it/s]
 39%|███▊      | 4269/11066 [15:38<24:55,  4.54it/s]
                                                    

 39%|███▊      | 4269/11066 [15:38<24:55,  4.54it/s]
 39%|███▊      | 4270/11066 [15:38<24:50,  4.56it/s]
                                                    

 39%|███▊      | 4270/11066 [15:38<24:50,  4.56it/s]
 39%|███▊      | 4271/11066 [15:38<24:31,  4.62it/s]
                                                    

 39%|███▊      | 4271/11066 [15:38<24:31,  4.62it/s]
 39%|███▊      | 4272/11066 [15:39<24:45,  4.57it/s]
                                                    

 39%|███▊      | 4272/11066 [15:39<24:45,  4.57it/s]
 39%|███▊      | 4273/11066 [15:39<24:59,  4.53it/s]
                                                    

 39%|███▊      | 4273/11066 [15:39<24:59,  4.53it/s]
 39%|███▊      | 4274/11066 [15:39<25:05,  4.51it/s]
                                                    

 39%|███▊      | 4274/11066 [15:39<25:05,  4.51it/s]
 39%|███▊      | 4275/11066 [15:39<24:55,  4.54it/s]
                                                    

 39%|███▊      | 4275/11066 [15:39<24:55,  4.54it/s]
 39%|███▊      | 4276/11066 [15:39<25:06,  4.51it/s]
                                                    
{'loss': 0.8738, 'learning_rate': 1.8711368154708112e-05, 'epoch': 0.75}
{'loss': 1.0421, 'learning_rate': 1.8708657148020964e-05, 'epoch': 0.75}
{'loss': 0.9787, 'learning_rate': 1.8705946141333816e-05, 'epoch': 0.75}
{'loss': 1.2029, 'learning_rate': 1.8703235134646664e-05, 'epoch': 0.75}
{'loss': 1.0998, 'learning_rate': 1.8700524127959516e-05, 'epoch': 0.75}
{'loss': 1.1193, 'learning_rate': 1.8697813121272368e-05, 'epoch': 0.75}
{'loss': 1.3004, 'learning_rate': 1.8695102114585217e-05, 'epoch': 0.75}
{'loss': 0.8194, 'learning_rate': 1.869239110789807e-05, 'epoch': 0.75}
{'loss': 1.0888, 'learning_rate': 1.8689680101210917e-05, 'epoch': 0.75}
{'loss': 1.2701, 'learning_rate': 1.8686969094523765e-05, 'epoch': 0.75}
{'loss': 1.294, 'learning_rate': 1.8684258087836617e-05, 'epoch': 0.75}
{'loss': 0.9969, 'learning_rate': 1.8681547081149466e-05, 'epoch': 0.75}
{'loss': 1.3942, 'learning_rate': 1.8678836074462317e-05, 'epoch': 0.75}
{'loss': 1.0515, 'learning_rate': 1.867612506777517e-05, 'epoch': 0.75}
{'loss': 1.3677, 'learning_rate': 1.8673414061088018e-05, 'epoch': 0.76}
{'loss': 0.7796, 'learning_rate': 1.867070305440087e-05, 'epoch': 0.76}
{'loss': 0.7902, 'learning_rate': 1.8667992047713718e-05, 'epoch': 0.76}
{'loss': 0.7968, 'learning_rate': 1.8665281041026566e-05, 'epoch': 0.76}
{'loss': 0.6289, 'learning_rate': 1.8662570034339418e-05, 'epoch': 0.76}
{'loss': 1.1148, 'learning_rate': 1.865985902765227e-05, 'epoch': 0.76}
{'loss': 1.8155, 'learning_rate': 1.865714802096512e-05, 'epoch': 0.76}
{'loss': 0.6225, 'learning_rate': 1.865443701427797e-05, 'epoch': 0.76}
{'loss': 1.1766, 'learning_rate': 1.865172600759082e-05, 'epoch': 0.76}
{'loss': 1.1404, 'learning_rate': 1.864901500090367e-05, 'epoch': 0.76}
{'loss': 1.1526, 'learning_rate': 1.864630399421652e-05, 'epoch': 0.76}
{'loss': 1.5008, 'learning_rate': 1.8643592987529367e-05, 'epoch': 0.76}
{'loss': 1.8709, 'learning_rate': 1.864088198084222e-05, 'epoch': 0.76}
{'loss': 1.2361, 'learning_rate': 1.863817097415507e-05, 'epoch': 0.76}
{'loss': 1.0664, 'learning_rate': 1.863545996746792e-05, 'epoch': 0.76}
{'loss': 0.638, 'learning_rate': 1.863274896078077e-05, 'epoch': 0.76}
{'loss': 0.6465, 'learning_rate': 1.8630037954093623e-05, 'epoch': 0.76}
{'loss': 1.2751, 'learning_rate': 1.862732694740647e-05, 'epoch': 0.76}
{'loss': 1.0229, 'learning_rate': 1.862461594071932e-05, 'epoch': 0.76}
{'loss': 0.9281, 'learning_rate': 1.862190493403217e-05, 'epoch': 0.76}
{'loss': 0.8675, 'learning_rate': 1.861919392734502e-05, 'epoch': 0.76}
{'loss': 0.5485, 'learning_rate': 1.8616482920657872e-05, 'epoch': 0.76}
{'loss': 1.3977, 'learning_rate': 1.861377191397072e-05, 'epoch': 0.76}
{'loss': 0.7601, 'learning_rate': 1.8611060907283572e-05, 'epoch': 0.76}
{'loss': 0.5618, 'learning_rate': 1.8608349900596424e-05, 'epoch': 0.76}
{'loss': 0.5934, 'learning_rate': 1.8605638893909273e-05, 'epoch': 0.76}
{'loss': 1.6908, 'learning_rate': 1.860292788722212e-05, 'epoch': 0.76}
{'loss': 0.6517, 'learning_rate': 1.8600216880534973e-05, 'epoch': 0.76}
{'loss': 1.4908, 'learning_rate': 1.859750587384782e-05, 'epoch': 0.76}
{'loss': 0.851, 'learning_rate': 1.8594794867160673e-05, 'epoch': 0.76}
{'loss': 0.72, 'learning_rate': 1.859208386047352e-05, 'epoch': 0.76}
{'loss': 1.2055, 'learning_rate': 1.8589372853786373e-05, 'epoch': 0.76}
{'loss': 1.821, 'learning_rate': 1.8586661847099225e-05, 'epoch': 0.76}
{'loss': 1.1098, 'learning_rate': 1.8583950840412074e-05, 'epoch': 0.76}
{'loss': 1.4492, 'learning_rate': 1.8581239833724922e-05, 'epoch': 0.76}
{'loss': 1.4953, 'learning_rate': 1.8578528827037774e-05, 'epoch': 0.76}
{'loss': 1.3702, 'learning_rate': 1.8575817820350622e-05, 'epoch': 0.76}
{'loss': 1.5406, 'learning_rate': 1.8573106813663474e-05, 'epoch': 0.76}
{'loss': 0.8064, 'learning_rate': 1.8570395806976326e-05, 'epoch': 0.76}
{'loss': 0.891, 'learning_rate': 1.8567684800289175e-05, 'epoch': 0.76}
{'loss': 0.5757, 'learning_rate': 1.8564973793602026e-05, 'epoch': 0.76}
{'loss': 0.9051, 'learning_rate': 1.8562262786914875e-05, 'epoch': 0.76}
{'loss': 1.3779, 'learning_rate': 1.8559551780227723e-05, 'epoch': 0.76}
{'loss': 1.2026, 'learning_rate': 1.8556840773540575e-05, 'epoch': 0.76}
{'loss': 0.9599, 'learning_rate': 1.8554129766853424e-05, 'epoch': 0.76}
{'loss': 0.9706, 'learning_rate': 1.8551418760166275e-05, 'epoch': 0.76}
{'loss': 1.2327, 'learning_rate': 1.8548707753479127e-05, 'epoch': 0.76}
{'loss': 2.0394, 'learning_rate': 1.8545996746791976e-05, 'epoch': 0.76}
{'loss': 1.3096, 'learning_rate': 1.8543285740104827e-05, 'epoch': 0.76}
{'loss': 0.6357, 'learning_rate': 1.854057473341768e-05, 'epoch': 0.76}
{'loss': 1.4146, 'learning_rate': 1.8537863726730524e-05, 'epoch': 0.76}
{'loss': 1.1033, 'learning_rate': 1.8535152720043376e-05, 'epoch': 0.76}
{'loss': 1.1678, 'learning_rate': 1.8532441713356225e-05, 'epoch': 0.76}
{'loss': 1.0214, 'learning_rate': 1.8529730706669076e-05, 'epoch': 0.76}
{'loss': 1.1439, 'learning_rate': 1.8527019699981928e-05, 'epoch': 0.76}
{'loss': 1.2791, 'learning_rate': 1.8524308693294777e-05, 'epoch': 0.77}
{'loss': 0.8565, 'learning_rate': 1.852159768660763e-05, 'epoch': 0.77}
{'loss': 1.0165, 'learning_rate': 1.851888667992048e-05, 'epoch': 0.77}
{'loss': 1.4325, 'learning_rate': 1.8516175673233325e-05, 'epoch': 0.77}
{'loss': 0.8627, 'learning_rate': 1.8513464666546177e-05, 'epoch': 0.77}
{'loss': 1.4789, 'learning_rate': 1.851075365985903e-05, 'epoch': 0.77}
{'loss': 1.2126, 'learning_rate': 1.8508042653171878e-05, 'epoch': 0.77}
{'loss': 1.7906, 'learning_rate': 1.850533164648473e-05, 'epoch': 0.77}
{'loss': 0.9936, 'learning_rate': 1.8502620639797578e-05, 'epoch': 0.77}
{'loss': 1.0173, 'learning_rate': 1.849990963311043e-05, 'epoch': 0.77}
{'loss': 0.964, 'learning_rate': 1.849719862642328e-05, 'epoch': 0.77}
{'loss': 0.6267, 'learning_rate': 1.8494487619736126e-05, 'epoch': 0.77}
{'loss': 0.5763, 'learning_rate': 1.8491776613048978e-05, 'epoch': 0.77}
{'loss': 1.2983, 'learning_rate': 1.848906560636183e-05, 'epoch': 0.77}
{'loss': 0.5374, 'learning_rate': 1.848635459967468e-05, 'epoch': 0.77}
{'loss': 0.6969, 'learning_rate': 1.848364359298753e-05, 'epoch': 0.77}
{'loss': 1.2343, 'learning_rate': 1.8480932586300382e-05, 'epoch': 0.77}
{'loss': 1.276, 'learning_rate': 1.847822157961323e-05, 'epoch': 0.77}
{'loss': 1.4366, 'learning_rate': 1.847551057292608e-05, 'epoch': 0.77}
{'loss': 0.4237, 'learning_rate': 1.847279956623893e-05, 'epoch': 0.77}
{'loss': 1.362, 'learning_rate': 1.847008855955178e-05, 'epoch': 0.77}
{'loss': 1.6428, 'learning_rate': 1.846737755286463e-05, 'epoch': 0.77}
{'loss': 0.9694, 'learning_rate': 1.846466654617748e-05, 'epoch': 0.77}
{'loss': 1.0922, 'learning_rate': 1.846195553949033e-05, 'epoch': 0.77}
{'loss': 0.5934, 'learning_rate': 1.8459244532803183e-05, 'epoch': 0.77}
{'loss': 0.5442, 'learning_rate': 1.8456533526116032e-05, 'epoch': 0.77}
{'loss': 1.1124, 'learning_rate': 1.845382251942888e-05, 'epoch': 0.77}
{'loss': 1.4212, 'learning_rate': 1.8451111512741732e-05, 'epoch': 0.77}
{'loss': 0.8321, 'learning_rate': 1.844840050605458e-05, 'epoch': 0.77}
{'loss': 1.4919, 'learning_rate': 1.8445689499367432e-05, 'epoch': 0.77}
{'loss': 0.5961, 'learning_rate': 1.8442978492680284e-05, 'epoch': 0.77}
{'loss': 1.4431, 'learning_rate': 1.8440267485993133e-05, 'epoch': 0.77}
{'loss': 0.8581, 'learning_rate': 1.8437556479305984e-05, 'epoch': 0.77}
{'loss': 1.1713, 'learning_rate': 1.8434845472618833e-05, 'epoch': 0.77}
{'loss': 0.7302, 'learning_rate': 1.843213446593168e-05, 'epoch': 0.77}
{'loss': 0.7104, 'learning_rate': 1.8429423459244533e-05, 'epoch': 0.77}
{'loss': 0.739, 'learning_rate': 1.842671245255738e-05, 'epoch': 0.77}
{'loss': 1.0571, 'learning_rate': 1.8424001445870233e-05, 'epoch': 0.77}
{'loss': 1.122, 'learning_rate': 1.8421290439183085e-05, 'epoch': 0.77}
{'loss': 1.2705, 'learning_rate': 1.8418579432495934e-05, 'epoch': 0.77}
{'loss': 0.7409, 'learning_rate': 1.8415868425808785e-05, 'epoch': 0.77}
{'loss': 1.6146, 'learning_rate': 1.8413157419121637e-05, 'epoch': 0.77}
{'loss': 1.2217, 'learning_rate': 1.8410446412434482e-05, 'epoch': 0.77}

 39%|███▊      | 4276/11066 [15:39<25:06,  4.51it/s]
 39%|███▊      | 4277/11066 [15:40<25:09,  4.50it/s]
                                                    

 39%|███▊      | 4277/11066 [15:40<25:09,  4.50it/s]
 39%|███▊      | 4278/11066 [15:40<24:57,  4.53it/s]
                                                    

 39%|███▊      | 4278/11066 [15:40<24:57,  4.53it/s]
 39%|███▊      | 4279/11066 [15:40<24:46,  4.57it/s]
                                                    

 39%|███▊      | 4279/11066 [15:40<24:46,  4.57it/s]
 39%|███▊      | 4280/11066 [15:40<24:34,  4.60it/s]
                                                    

 39%|███▊      | 4280/11066 [15:40<24:34,  4.60it/s]
 39%|███▊      | 4281/11066 [15:41<24:35,  4.60it/s]
                                                    

 39%|███▊      | 4281/11066 [15:41<24:35,  4.60it/s]
 39%|███▊      | 4282/11066 [15:41<24:24,  4.63it/s]
                                                    

 39%|███▊      | 4282/11066 [15:41<24:24,  4.63it/s]
 39%|███▊      | 4283/11066 [15:41<24:24,  4.63it/s]
                                                    

 39%|███▊      | 4283/11066 [15:41<24:24,  4.63it/s]
 39%|███▊      | 4284/11066 [15:41<24:37,  4.59it/s]
                                                    

 39%|███▊      | 4284/11066 [15:41<24:37,  4.59it/s]
 39%|███▊      | 4285/11066 [15:41<24:25,  4.63it/s]
                                                    

 39%|███▊      | 4285/11066 [15:41<24:25,  4.63it/s]
 39%|███▊      | 4286/11066 [15:42<24:38,  4.59it/s]
                                                    

 39%|███▊      | 4286/11066 [15:42<24:38,  4.59it/s]
 39%|███▊      | 4287/11066 [15:42<24:44,  4.57it/s]
                                                    

 39%|███▊      | 4287/11066 [15:42<24:44,  4.57it/s]
 39%|███▊      | 4288/11066 [15:42<24:38,  4.59it/s]
                                                    

 39%|███▊      | 4288/11066 [15:42<24:38,  4.59it/s]
 39%|███▉      | 4289/11066 [15:42<24:20,  4.64it/s]
                                                    

 39%|███▉      | 4289/11066 [15:42<24:20,  4.64it/s]
 39%|███▉      | 4290/11066 [15:42<24:06,  4.68it/s]
                                                    

 39%|███▉      | 4290/11066 [15:42<24:06,  4.68it/s]
 39%|███▉      | 4291/11066 [15:43<24:26,  4.62it/s]
                                                    

 39%|███▉      | 4291/11066 [15:43<24:26,  4.62it/s]
 39%|███▉      | 4292/11066 [15:43<24:18,  4.64it/s]
                                                    

 39%|███▉      | 4292/11066 [15:43<24:18,  4.64it/s]
 39%|███▉      | 4293/11066 [15:43<24:32,  4.60it/s]
                                                    

 39%|███▉      | 4293/11066 [15:43<24:32,  4.60it/s]
 39%|███▉      | 4294/11066 [15:43<24:22,  4.63it/s]
                                                    

 39%|███▉      | 4294/11066 [15:43<24:22,  4.63it/s]
 39%|███▉      | 4295/11066 [15:44<24:35,  4.59it/s]
                                                    

 39%|███▉      | 4295/11066 [15:44<24:35,  4.59it/s]
 39%|███▉      | 4296/11066 [15:44<24:47,  4.55it/s]
                                                    

 39%|███▉      | 4296/11066 [15:44<24:47,  4.55it/s]
 39%|███▉      | 4297/11066 [15:44<24:37,  4.58it/s]
                                                    

 39%|███▉      | 4297/11066 [15:44<24:37,  4.58it/s]
 39%|███▉      | 4298/11066 [15:44<24:47,  4.55it/s]
                                                    

 39%|███▉      | 4298/11066 [15:44<24:47,  4.55it/s]
 39%|███▉      | 4299/11066 [15:44<24:42,  4.57it/s]
                                                    

 39%|███▉      | 4299/11066 [15:44<24:42,  4.57it/s]
 39%|███▉      | 4300/11066 [15:45<24:41,  4.57it/s]
                                                    

 39%|███▉      | 4300/11066 [15:45<24:41,  4.57it/s]
 39%|███▉      | 4301/11066 [15:45<24:50,  4.54it/s]
                                                    

 39%|███▉      | 4301/11066 [15:45<24:50,  4.54it/s]
 39%|███▉      | 4302/11066 [15:45<24:57,  4.52it/s]
                                                    

 39%|███▉      | 4302/11066 [15:45<24:57,  4.52it/s]
 39%|███▉      | 4303/11066 [15:45<24:55,  4.52it/s]
                                                    

 39%|███▉      | 4303/11066 [15:45<24:55,  4.52it/s]
 39%|███▉      | 4304/11066 [15:46<24:38,  4.57it/s]
                                                    

 39%|███▉      | 4304/11066 [15:46<24:38,  4.57it/s]
 39%|███▉      | 4305/11066 [15:46<24:50,  4.54it/s]
                                                    

 39%|███▉      | 4305/11066 [15:46<24:50,  4.54it/s]
 39%|███▉      | 4306/11066 [15:46<24:35,  4.58it/s]
                                                    

 39%|███▉      | 4306/11066 [15:46<24:35,  4.58it/s]
 39%|███▉      | 4307/11066 [15:46<24:35,  4.58it/s]
                                                    

 39%|███▉      | 4307/11066 [15:46<24:35,  4.58it/s]
 39%|███▉      | 4308/11066 [15:46<24:16,  4.64it/s]
                                                    

 39%|███▉      | 4308/11066 [15:46<24:16,  4.64it/s]
 39%|███▉      | 4309/11066 [15:47<24:33,  4.59it/s]
                                                    

 39%|███▉      | 4309/11066 [15:47<24:33,  4.59it/s]
 39%|███▉      | 4310/11066 [15:47<24:41,  4.56it/s]
                                                    

 39%|███▉      | 4310/11066 [15:47<24:41,  4.56it/s]
 39%|███▉      | 4311/11066 [15:47<24:46,  4.54it/s]
                                                    

 39%|███▉      | 4311/11066 [15:47<24:46,  4.54it/s]
 39%|███▉      | 4312/11066 [15:47<24:49,  4.54it/s]
                                                    

 39%|███▉      | 4312/11066 [15:47<24:49,  4.54it/s]
 39%|███▉      | 4313/11066 [15:47<24:40,  4.56it/s]
                                                    

 39%|███▉      | 4313/11066 [15:47<24:40,  4.56it/s]
 39%|███▉      | 4314/11066 [15:48<24:52,  4.52it/s]
                                                    

 39%|███▉      | 4314/11066 [15:48<24:52,  4.52it/s]
 39%|███▉      | 4315/11066 [15:48<24:35,  4.57it/s]
                                                    

 39%|███▉      | 4315/11066 [15:48<24:35,  4.57it/s]
 39%|███▉      | 4316/11066 [15:48<24:42,  4.55it/s]
                                                    

 39%|███▉      | 4316/11066 [15:48<24:42,  4.55it/s]
 39%|███▉      | 4317/11066 [15:48<24:35,  4.57it/s]
                                                    

 39%|███▉      | 4317/11066 [15:48<24:35,  4.57it/s]
 39%|███▉      | 4318/11066 [15:49<24:39,  4.56it/s]
                                                    

 39%|███▉      | 4318/11066 [15:49<24:39,  4.56it/s]
 39%|███▉      | 4319/11066 [15:49<24:38,  4.56it/s]
                                                    

 39%|███▉      | 4319/11066 [15:49<24:38,  4.56it/s]
 39%|███▉      | 4320/11066 [15:49<24:43,  4.55it/s]
                                                    

 39%|███▉      | 4320/11066 [15:49<24:43,  4.55it/s]
 39%|███▉      | 4321/11066 [15:49<24:47,  4.53it/s]
                                                    

 39%|███▉      | 4321/11066 [15:49<24:47,  4.53it/s]
 39%|███▉      | 4322/11066 [15:49<24:52,  4.52it/s]
                                                    

 39%|███▉      | 4322/11066 [15:49<24:52,  4.52it/s]
 39%|███▉      | 4323/11066 [15:50<24:59,  4.50it/s]
                                                    

 39%|███▉      | 4323/11066 [15:50<24:59,  4.50it/s]
 39%|███▉      | 4324/11066 [15:50<25:08,  4.47it/s]
                                                    

 39%|███▉      | 4324/11066 [15:50<25:08,  4.47it/s]
 39%|███▉      | 4325/11066 [15:50<24:38,  4.56it/s]
                                                    

 39%|███▉      | 4325/11066 [15:50<24:38,  4.56it/s]
 39%|███▉      | 4326/11066 [15:50<24:53,  4.51it/s]
                                                    

 39%|███▉      | 4326/11066 [15:50<24:53,  4.51it/s]
 39%|███▉      | 4327/11066 [15:51<25:00,  4.49it/s]
                                                    

 39%|███▉      | 4327/11066 [15:51<25:00,  4.49it/s]
 39%|███▉      | 4328/11066 [15:51<25:04,  4.48it/s]
                                                    

 39%|███▉      | 4328/11066 [15:51<25:04,  4.48it/s]
 39%|███▉      | 4329/11066 [15:51<25:11,  4.46it/s]
                                                    

 39%|███▉      | 4329/11066 [15:51<25:11,  4.46it/s]
 39%|███▉      | 4330/11066 [15:51<24:48,  4.53it/s]
                                                    

 39%|███▉      | 4330/11066 [15:51<24:48,  4.53it/s]
 39%|███▉      | 4331/11066 [15:51<24:55,  4.50it/s]
                                                    

 39%|███▉      | 4331/11066 [15:51<24:55,  4.50it/s]
 39%|███▉      | 4332/11066 [15:52<24:56,  4.50it/s]
                                                    

 39%|███▉      | 4332/11066 [15:52<24:56,  4.50it/s]
 39%|███▉      | 4333/11066 [15:52<25:09,  4.46it/s]
                                                    

 39%|███▉      | 4333/11066 [15:52<25:09,  4.46it/s]
 39%|███▉      | 4334/11066 [15:52<25:13,  4.45it/s]
                                                    

 39%|███▉      | 4334/11066 [15:52<25:13,  4.45it/s]
 39%|███▉      | 4335/11066 [15:52<25:33,  4.39it/s]
                                                    

 39%|███▉      | 4335/11066 [15:52<25:33,  4.39it/s]
 39%|███▉      | 4336/11066 [15:53<25:30,  4.40it/s]
                                                    

 39%|███▉      | 4336/11066 [15:53<25:30,  4.40it/s]
 39%|███▉      | 4337/11066 [15:53<25:21,  4.42it/s]
                                                    

 39%|███▉      | 4337/11066 [15:53<25:21,  4.42it/s]
 39%|███▉      | 4338/11066 [15:53<25:15,  4.44it/s]
                                                    

 39%|███▉      | 4338/11066 [15:53<25:15,  4.44it/s]
 39%|███▉      | 4339/11066 [15:53<25:10,  4.45it/s]
                                                    

 39%|███▉      | 4339/11066 [15:53<25:10,  4.45it/s]
 39%|███▉      | 4340/11066 [15:53<24:56,  4.49it/s]
                                                    

 39%|███▉      | 4340/11066 [15:53<24:56,  4.49it/s]
 39%|███▉      | 4341/11066 [15:54<24:47,  4.52it/s]
                                                    

 39%|███▉      | 4341/11066 [15:54<24:47,  4.52it/s]
 39%|███▉      | 4342/11066 [15:54<24:23,  4.59it/s]
                                                    

 39%|███▉      | 4342/11066 [15:54<24:23,  4.59it/s]
 39%|███▉      | 4343/11066 [15:54<24:13,  4.62it/s]
                                                    

 39%|███▉      | 4343/11066 [15:54<24:13,  4.62it/s]
 39%|███▉      | 4344/11066 [15:54<24:25,  4.59it/s]
                                                    

 39%|███▉      | 4344/11066 [15:54<24:25,  4.59it/s]
 39%|███▉      | 4345/11066 [15:55<24:22,  4.59it/s]
                                                    

 39%|███▉      | 4345/11066 [15:55<24:22,  4.59it/s]
 39%|███▉      | 4346/11066 [15:55<24:34,  4.56it/s]
                                                    

 39%|███▉      | 4346/11066 [15:55<24:34,  4.56it/s]
 39%|███▉      | 4347/11066 [15:55<24:32,  4.56it/s]
                                                    

 39%|███▉      | 4347/11066 [15:55<24:32,  4.56it/s]
 39%|███▉      | 4348/11066 [15:55<24:31,  4.57it/s]
                                                    

 39%|███▉      | 4348/11066 [15:55<24:31,  4.57it/s]
 39%|███▉      | 4349/11066 [15:55<24:29,  4.57it/s]
                                                    

 39%|███▉      | 4349/11066 [15:55<24:29,  4.57it/s]
 39%|███▉      | 4350/11066 [15:56<24:09,  4.63it/s]
                                                    

 39%|███▉      | 4350/11066 [15:56<24:09,  4.63it/s]
 39%|███▉      | 4351/11066 [15:56<24:33,  4.56it/s]
                                                    

 39%|███▉      | 4351/11066 [15:56<24:33,  4.56it/s]
 39%|███▉      | 4352/11066 [15:56<24:42,  4.53it/s]
                                                    

 39%|███▉      | 4352/11066 [15:56<24:42,  4.53it/s]
 39%|███▉      | 4353/11066 [15:56<24:44,  4.52it/s]
                                                    

 39%|███▉      | 4353/11066 [15:56<24:44,  4.52it/s]
 39%|███▉      | 4354/11066 [15:57<24:45,  4.52it/s]
                                                    

 39%|███▉      | 4354/11066 [15:57<24:45,  4.52it/s]
 39%|███▉      | 4355/11066 [15:57<24:26,  4.58it/s]
                                                    

 39%|███▉      | 4355/11066 [15:57<24:26,  4.58it/s]
 39%|███▉      | 4356/11066 [15:57<24:33,  4.55it/s]
                                                    

 39%|███▉      | 4356/11066 [15:57<24:33,  4.55it/s]
 39%|███▉      | 4357/11066 [15:57<24:17,  4.60it/s]
                                                    

 39%|███▉      | 4357/11066 [15:57<24:17,  4.60it/s]
 39%|███▉      | 4358/11066 [15:57<24:28,  4.57it/s]
                                                    

 39%|███▉      | 4358/11066 [15:57<24:28,  4.57it/s]
 39%|███▉      | 4359/11066 [15:58<24:23,  4.58it/s]
                                                    

 39%|███▉      | 4359/11066 [15:58<24:23,  4.58it/s]
 39%|███▉      | 4360/11066 [15:58<24:28,  4.57it/s]
                                                    

 39%|███▉      | 4360/11066 [15:58<24:28,  4.57it/s]
 39%|███▉      | 4361/11066 [15:58<24:14,  4.61it/s]
                                                    

 39%|███▉      | 4361/11066 [15:58<24:14,  4.61it/s]
 39%|███▉      | 4362/11066 [15:58<24:01,  4.65it/s]
                                                    

 39%|███▉      | 4362/11066 [15:58<24:01,  4.65it/s]
 39%|███▉      | 4363/11066 [15:58<23:49,  4.69it/s]
                                                    

 39%|███▉      | 4363/11066 [15:58<23:49,  4.69it/s]
 39%|███▉      | 4364/11066 [15:59<24:11,  4.62it/s]
                                                    

 39%|███▉      | 4364/11066 [15:59<24:11,  4.62it/s]
 39%|███▉      | 4365/11066 [15:59<24:22,  4.58it/s]
                                                    

 39%|███▉      | 4365/11066 [15:59<24:22,  4.58it/s]
 39%|███▉      | 4366/11066 [15:59<24:29,  4.56it/s]
                                                    

 39%|███▉      | 4366/11066 [15:59<24:29,  4.56it/s]
 39%|███▉      | 4367/11066 [15:59<24:34,  4.54it/s]
                                                    

 39%|███▉      | 4367/11066 [15:59<24:34,  4.54it/s]
 39%|███▉      | 4368/11066 [16:00<24:18,  4.59it/s]
                                                    

 39%|███▉      | 4368/11066 [16:00<24:18,  4.59it/s]
 39%|███▉      | 4369/11066 [16:00<24:15,  4.60it/s]
                                                    

 39%|███▉      | 4369/11066 [16:00<24:15,  4.60it/s]
 39%|███▉      | 4370/11066 [16:00<24:14,  4.60it/s]
                                                    

 39%|███▉      | 4370/11066 [16:00<24:14,  4.60it/s]
 39%|███▉      | 4371/11066 [16:00<24:04,  4.63it/s]
                                                    

 39%|███▉      | 4371/11066 [16:00<24:04,  4.63it/s]
 40%|███▉      | 4372/11066 [16:00<24:16,  4.60it/s]
                                                    

 40%|███▉      | 4372/11066 [16:00<24:16,  4.60it/s]
 40%|███▉      | 4373/11066 [16:01<24:24,  4.57it/s]
                                                    

 40%|███▉      | 4373/11066 [16:01<24:24,  4.57it/s]
 40%|███▉      | 4374/11066 [16:01<24:31,  4.55it/s]
                                                    

 40%|███▉      | 4374/11066 [16:01<24:31,  4.55it/s]
 40%|███▉      | 4375/11066 [16:01<24:36,  4.53it/s]
                                                    

 40%|███▉      | 4375/11066 [16:01<24:36,  4.53it/s]
 40%|███▉      | 4376/11066 [16:01<24:38,  4.53it/s]
                                                    

 40%|███▉      | 4376/11066 [16:01<24:38,  4.53it/s]
 40%|███▉      | 4377/11066 [16:02<24:24,  4.57it/s]
                                                    

 40%|███▉      | 4377/11066 [16:02<24:24,  4.57it/s]
 40%|███▉      | 4378/11066 [16:02<24:27,  4.56it/s]
                                                    

 40%|███▉      | 4378/11066 [16:02<24:27,  4.56it/s]
 40%|███▉      | 4379/11066 [16:02<24:58,  4.46it/s]
                                                    

 40%|███▉      | 4379/11066 [16:02<24:58,  4.46it/s]
 40%|███▉      | 4380/11066 [16:02<24:59,  4.46it/s]
                                                    

 40%|███▉      | 4380/11066 [16:02<24:59,  4.46it/s]
 40%|███▉      | 4381/11066 [16:02<25:00,  4.46it/s]
                                                    

 40%|███▉      | 4381/11066 [16:02<25:00,  4.46it/s]
 40%|███▉      | 4382/11066 [16:03<24:56,  4.47it/s]
                                                    

 40%|███▉      | 4382/11066 [16:03<24:56,  4.47it/s]
 40%|███▉      | 4383/11066 [16:03<24:51,  4.48it/s]
                                                    

 40%|███▉      | 4383/11066 [16:03<24:51,  4.48it/s]
 40%|███▉      | 4384/11066 [16:03<24:51,  4.48it/s]
                                                    

 40%|███▉      | 4384/11066 [16:03<24:51,  4.48it/s]
 40%|███▉      | 4385/11066 [16:03<24:48,  4.49it/s]
                                                    

 40%|███▉      | 4385/11066 [16:03<24:48,  4.49it/s]
 40%|███▉      | 4386/11066 [16:04<24:40,  4.51it/s]
                                                    

 40%|███▉      | 4386/11066 [16:04<24:40,  4.51it/s]
 40%|███▉      | 4387/11066 [16:04<24:45,  4.50it/s]
                                                    

 40%|███▉      | 4387/11066 [16:04<24:45,  4.50it/s]
 40%|███▉      | 4388/11066 [16:04<24:46,  4.49it/s]
                                                    

 40%|███▉      | 4388/11066 [16:04<24:46,  4.49it/s]
 40%|███▉      | 4389/11066 [16:04<24:45,  4.49it/s]
                                                    
{'loss': 1.4253, 'learning_rate': 1.8407735405747334e-05, 'epoch': 0.77}
{'loss': 1.1224, 'learning_rate': 1.8405024399060183e-05, 'epoch': 0.77}
{'loss': 0.7487, 'learning_rate': 1.8402313392373034e-05, 'epoch': 0.77}
{'loss': 1.4264, 'learning_rate': 1.8399602385685886e-05, 'epoch': 0.77}
{'loss': 1.1208, 'learning_rate': 1.8396891378998735e-05, 'epoch': 0.77}
{'loss': 1.3596, 'learning_rate': 1.8394180372311587e-05, 'epoch': 0.77}
{'loss': 1.268, 'learning_rate': 1.839146936562444e-05, 'epoch': 0.77}
{'loss': 0.5843, 'learning_rate': 1.8388758358937283e-05, 'epoch': 0.77}
{'loss': 1.3829, 'learning_rate': 1.8386047352250135e-05, 'epoch': 0.77}
{'loss': 1.2514, 'learning_rate': 1.8383336345562987e-05, 'epoch': 0.77}
{'loss': 1.3679, 'learning_rate': 1.8380625338875836e-05, 'epoch': 0.77}
{'loss': 1.0779, 'learning_rate': 1.8377914332188687e-05, 'epoch': 0.77}
{'loss': 1.1515, 'learning_rate': 1.8375203325501536e-05, 'epoch': 0.77}
{'loss': 1.5945, 'learning_rate': 1.8372492318814388e-05, 'epoch': 0.78}
{'loss': 1.1297, 'learning_rate': 1.836978131212724e-05, 'epoch': 0.78}
{'loss': 0.8146, 'learning_rate': 1.8367070305440084e-05, 'epoch': 0.78}
{'loss': 0.5189, 'learning_rate': 1.8364359298752936e-05, 'epoch': 0.78}
{'loss': 1.027, 'learning_rate': 1.8361648292065788e-05, 'epoch': 0.78}
{'loss': 1.3715, 'learning_rate': 1.8358937285378637e-05, 'epoch': 0.78}
{'loss': 0.6385, 'learning_rate': 1.835622627869149e-05, 'epoch': 0.78}
{'loss': 1.1151, 'learning_rate': 1.835351527200434e-05, 'epoch': 0.78}
{'loss': 0.9086, 'learning_rate': 1.835080426531719e-05, 'epoch': 0.78}
{'loss': 0.9816, 'learning_rate': 1.834809325863004e-05, 'epoch': 0.78}
{'loss': 0.6504, 'learning_rate': 1.8345382251942886e-05, 'epoch': 0.78}
{'loss': 0.8519, 'learning_rate': 1.8342671245255737e-05, 'epoch': 0.78}
{'loss': 0.6331, 'learning_rate': 1.833996023856859e-05, 'epoch': 0.78}
{'loss': 1.629, 'learning_rate': 1.8337249231881438e-05, 'epoch': 0.78}
{'loss': 1.1911, 'learning_rate': 1.833453822519429e-05, 'epoch': 0.78}
{'loss': 1.9639, 'learning_rate': 1.833182721850714e-05, 'epoch': 0.78}
{'loss': 1.0587, 'learning_rate': 1.832911621181999e-05, 'epoch': 0.78}
{'loss': 0.8219, 'learning_rate': 1.832640520513284e-05, 'epoch': 0.78}
{'loss': 1.5406, 'learning_rate': 1.832369419844569e-05, 'epoch': 0.78}
{'loss': 1.138, 'learning_rate': 1.832098319175854e-05, 'epoch': 0.78}
{'loss': 1.0084, 'learning_rate': 1.831827218507139e-05, 'epoch': 0.78}
{'loss': 1.0953, 'learning_rate': 1.831556117838424e-05, 'epoch': 0.78}
{'loss': 0.8653, 'learning_rate': 1.831285017169709e-05, 'epoch': 0.78}
{'loss': 1.1015, 'learning_rate': 1.8310139165009942e-05, 'epoch': 0.78}
{'loss': 0.7257, 'learning_rate': 1.830742815832279e-05, 'epoch': 0.78}
{'loss': 1.2965, 'learning_rate': 1.8304717151635643e-05, 'epoch': 0.78}
{'loss': 1.2147, 'learning_rate': 1.830200614494849e-05, 'epoch': 0.78}
{'loss': 0.5823, 'learning_rate': 1.829929513826134e-05, 'epoch': 0.78}
{'loss': 1.0227, 'learning_rate': 1.829658413157419e-05, 'epoch': 0.78}
{'loss': 0.9248, 'learning_rate': 1.8293873124887043e-05, 'epoch': 0.78}
{'loss': 0.8707, 'learning_rate': 1.829116211819989e-05, 'epoch': 0.78}
{'loss': 2.2306, 'learning_rate': 1.8288451111512743e-05, 'epoch': 0.78}
{'loss': 0.5393, 'learning_rate': 1.8285740104825592e-05, 'epoch': 0.78}
{'loss': 0.9625, 'learning_rate': 1.8283029098138444e-05, 'epoch': 0.78}
{'loss': 0.8994, 'learning_rate': 1.8280318091451292e-05, 'epoch': 0.78}
{'loss': 0.6064, 'learning_rate': 1.827760708476414e-05, 'epoch': 0.78}
{'loss': 2.0444, 'learning_rate': 1.8274896078076992e-05, 'epoch': 0.78}
{'loss': 0.9139, 'learning_rate': 1.8272185071389844e-05, 'epoch': 0.78}
{'loss': 0.8183, 'learning_rate': 1.8269474064702693e-05, 'epoch': 0.78}
{'loss': 0.8431, 'learning_rate': 1.8266763058015545e-05, 'epoch': 0.78}
{'loss': 1.4326, 'learning_rate': 1.8264052051328396e-05, 'epoch': 0.78}
{'loss': 0.8422, 'learning_rate': 1.8261341044641245e-05, 'epoch': 0.78}
{'loss': 1.0096, 'learning_rate': 1.8258630037954093e-05, 'epoch': 0.78}
{'loss': 0.6654, 'learning_rate': 1.825591903126694e-05, 'epoch': 0.78}
{'loss': 1.3655, 'learning_rate': 1.8253208024579794e-05, 'epoch': 0.78}
{'loss': 0.6697, 'learning_rate': 1.8250497017892645e-05, 'epoch': 0.78}
{'loss': 1.186, 'learning_rate': 1.8247786011205494e-05, 'epoch': 0.78}
{'loss': 0.909, 'learning_rate': 1.8245075004518346e-05, 'epoch': 0.78}
{'loss': 0.9414, 'learning_rate': 1.8242363997831197e-05, 'epoch': 0.78}
{'loss': 0.77, 'learning_rate': 1.8239652991144046e-05, 'epoch': 0.78}
{'loss': 1.0151, 'learning_rate': 1.8236941984456894e-05, 'epoch': 0.78}
{'loss': 0.8142, 'learning_rate': 1.8234230977769746e-05, 'epoch': 0.78}
{'loss': 2.0465, 'learning_rate': 1.8231519971082595e-05, 'epoch': 0.78}
{'loss': 1.122, 'learning_rate': 1.8228808964395446e-05, 'epoch': 0.78}
{'loss': 1.3653, 'learning_rate': 1.8226097957708295e-05, 'epoch': 0.78}
{'loss': 1.2649, 'learning_rate': 1.8223386951021147e-05, 'epoch': 0.79}
{'loss': 0.5998, 'learning_rate': 1.8220675944334e-05, 'epoch': 0.79}
{'loss': 1.5289, 'learning_rate': 1.8217964937646847e-05, 'epoch': 0.79}
{'loss': 0.8517, 'learning_rate': 1.8215253930959695e-05, 'epoch': 0.79}
{'loss': 0.8784, 'learning_rate': 1.8212542924272547e-05, 'epoch': 0.79}
{'loss': 0.565, 'learning_rate': 1.8209831917585396e-05, 'epoch': 0.79}
{'loss': 0.6475, 'learning_rate': 1.8207120910898247e-05, 'epoch': 0.79}
{'loss': 1.147, 'learning_rate': 1.82044099042111e-05, 'epoch': 0.79}
{'loss': 0.5739, 'learning_rate': 1.8201698897523948e-05, 'epoch': 0.79}
{'loss': 0.9452, 'learning_rate': 1.81989878908368e-05, 'epoch': 0.79}
{'loss': 0.9651, 'learning_rate': 1.8196276884149648e-05, 'epoch': 0.79}
{'loss': 0.8367, 'learning_rate': 1.8193565877462496e-05, 'epoch': 0.79}
{'loss': 0.547, 'learning_rate': 1.8190854870775348e-05, 'epoch': 0.79}
{'loss': 1.0891, 'learning_rate': 1.8188143864088197e-05, 'epoch': 0.79}
{'loss': 1.2991, 'learning_rate': 1.818543285740105e-05, 'epoch': 0.79}
{'loss': 1.1247, 'learning_rate': 1.81827218507139e-05, 'epoch': 0.79}
{'loss': 0.9976, 'learning_rate': 1.818001084402675e-05, 'epoch': 0.79}
{'loss': 1.6211, 'learning_rate': 1.81772998373396e-05, 'epoch': 0.79}
{'loss': 0.76, 'learning_rate': 1.8174588830652452e-05, 'epoch': 0.79}
{'loss': 0.8031, 'learning_rate': 1.8171877823965298e-05, 'epoch': 0.79}
{'loss': 1.2614, 'learning_rate': 1.816916681727815e-05, 'epoch': 0.79}
{'loss': 1.4244, 'learning_rate': 1.8166455810590998e-05, 'epoch': 0.79}
{'loss': 1.2054, 'learning_rate': 1.816374480390385e-05, 'epoch': 0.79}
{'loss': 0.8935, 'learning_rate': 1.81610337972167e-05, 'epoch': 0.79}
{'loss': 0.2763, 'learning_rate': 1.815832279052955e-05, 'epoch': 0.79}
{'loss': 0.6614, 'learning_rate': 1.8155611783842402e-05, 'epoch': 0.79}
{'loss': 1.2757, 'learning_rate': 1.8152900777155254e-05, 'epoch': 0.79}
{'loss': 0.9526, 'learning_rate': 1.81501897704681e-05, 'epoch': 0.79}
{'loss': 1.472, 'learning_rate': 1.814747876378095e-05, 'epoch': 0.79}
{'loss': 0.6655, 'learning_rate': 1.8144767757093802e-05, 'epoch': 0.79}
{'loss': 0.6632, 'learning_rate': 1.814205675040665e-05, 'epoch': 0.79}
{'loss': 0.4186, 'learning_rate': 1.8139345743719503e-05, 'epoch': 0.79}
{'loss': 2.4365, 'learning_rate': 1.813663473703235e-05, 'epoch': 0.79}
{'loss': 0.9592, 'learning_rate': 1.8133923730345203e-05, 'epoch': 0.79}
{'loss': 1.6827, 'learning_rate': 1.813121272365805e-05, 'epoch': 0.79}
{'loss': 0.96, 'learning_rate': 1.81285017169709e-05, 'epoch': 0.79}
{'loss': 0.8843, 'learning_rate': 1.812579071028375e-05, 'epoch': 0.79}
{'loss': 1.1583, 'learning_rate': 1.8123079703596603e-05, 'epoch': 0.79}
{'loss': 0.617, 'learning_rate': 1.8120368696909452e-05, 'epoch': 0.79}
{'loss': 0.5268, 'learning_rate': 1.8117657690222304e-05, 'epoch': 0.79}
{'loss': 1.2809, 'learning_rate': 1.8114946683535155e-05, 'epoch': 0.79}
{'loss': 0.8942, 'learning_rate': 1.8112235676848004e-05, 'epoch': 0.79}
{'loss': 0.9922, 'learning_rate': 1.8109524670160852e-05, 'epoch': 0.79}
{'loss': 1.1683, 'learning_rate': 1.8106813663473704e-05, 'epoch': 0.79}
{'loss': 0.86, 'learning_rate': 1.8104102656786553e-05, 'epoch': 0.79}

 40%|███▉      | 4389/11066 [16:04<24:45,  4.49it/s]
 40%|███▉      | 4390/11066 [16:04<24:46,  4.49it/s]
                                                    

 40%|███▉      | 4390/11066 [16:04<24:46,  4.49it/s]
 40%|███▉      | 4391/11066 [16:05<24:45,  4.49it/s]
                                                    

 40%|███▉      | 4391/11066 [16:05<24:45,  4.49it/s]
 40%|███▉      | 4392/11066 [16:05<24:35,  4.52it/s]
                                                    

 40%|███▉      | 4392/11066 [16:05<24:35,  4.52it/s]
 40%|███▉      | 4393/11066 [16:05<24:43,  4.50it/s]
                                                    

 40%|███▉      | 4393/11066 [16:05<24:43,  4.50it/s]
 40%|███▉      | 4394/11066 [16:05<24:45,  4.49it/s]
                                                    

 40%|███▉      | 4394/11066 [16:05<24:45,  4.49it/s]
 40%|███▉      | 4395/11066 [16:06<24:32,  4.53it/s]
                                                    

 40%|███▉      | 4395/11066 [16:06<24:32,  4.53it/s]
 40%|███▉      | 4396/11066 [16:06<24:28,  4.54it/s]
                                                    

 40%|███▉      | 4396/11066 [16:06<24:28,  4.54it/s]
 40%|███▉      | 4397/11066 [16:06<24:32,  4.53it/s]
                                                    

 40%|███▉      | 4397/11066 [16:06<24:32,  4.53it/s]
 40%|███▉      | 4398/11066 [16:06<24:34,  4.52it/s]
                                                    

 40%|███▉      | 4398/11066 [16:06<24:34,  4.52it/s]
 40%|███▉      | 4399/11066 [16:06<24:36,  4.52it/s]
                                                    

 40%|███▉      | 4399/11066 [16:06<24:36,  4.52it/s]
 40%|███▉      | 4400/11066 [16:07<24:38,  4.51it/s]
                                                    

 40%|███▉      | 4400/11066 [16:07<24:38,  4.51it/s]
 40%|███▉      | 4401/11066 [16:07<24:38,  4.51it/s]
                                                    

 40%|███▉      | 4401/11066 [16:07<24:38,  4.51it/s]
 40%|███▉      | 4402/11066 [16:07<24:39,  4.50it/s]
                                                    

 40%|███▉      | 4402/11066 [16:07<24:39,  4.50it/s]
 40%|███▉      | 4403/11066 [16:07<24:41,  4.50it/s]
                                                    

 40%|███▉      | 4403/11066 [16:07<24:41,  4.50it/s]
 40%|███▉      | 4404/11066 [16:08<24:41,  4.50it/s]
                                                    

 40%|███▉      | 4404/11066 [16:08<24:41,  4.50it/s]
 40%|███▉      | 4405/11066 [16:08<24:34,  4.52it/s]
                                                    

 40%|███▉      | 4405/11066 [16:08<24:34,  4.52it/s]
 40%|███▉      | 4406/11066 [16:08<24:41,  4.50it/s]
                                                    

 40%|███▉      | 4406/11066 [16:08<24:41,  4.50it/s]
 40%|███▉      | 4407/11066 [16:08<24:40,  4.50it/s]
                                                    

 40%|███▉      | 4407/11066 [16:08<24:40,  4.50it/s]
 40%|███▉      | 4408/11066 [16:08<24:39,  4.50it/s]
                                                    

 40%|███▉      | 4408/11066 [16:08<24:39,  4.50it/s]
 40%|███▉      | 4409/11066 [16:09<24:39,  4.50it/s]
                                                    

 40%|███▉      | 4409/11066 [16:09<24:39,  4.50it/s]
 40%|███▉      | 4410/11066 [16:09<24:26,  4.54it/s]
                                                    

 40%|███▉      | 4410/11066 [16:09<24:26,  4.54it/s]
 40%|███▉      | 4411/11066 [16:09<24:12,  4.58it/s]
                                                    

 40%|███▉      | 4411/11066 [16:09<24:12,  4.58it/s]
 40%|███▉      | 4412/11066 [16:09<24:09,  4.59it/s]
                                                    

 40%|███▉      | 4412/11066 [16:09<24:09,  4.59it/s]
 40%|███▉      | 4413/11066 [16:10<24:02,  4.61it/s]
                                                    

 40%|███▉      | 4413/11066 [16:10<24:02,  4.61it/s]
 40%|███▉      | 4414/11066 [16:10<23:51,  4.65it/s]
                                                    

 40%|███▉      | 4414/11066 [16:10<23:51,  4.65it/s]
 40%|███▉      | 4415/11066 [16:10<23:38,  4.69it/s]
                                                    

 40%|███▉      | 4415/11066 [16:10<23:38,  4.69it/s]
 40%|███▉      | 4416/11066 [16:10<24:00,  4.62it/s]
                                                    

 40%|███▉      | 4416/11066 [16:10<24:00,  4.62it/s]
 40%|███▉      | 4417/11066 [16:10<23:51,  4.64it/s]
                                                    

 40%|███▉      | 4417/11066 [16:10<23:51,  4.64it/s]
 40%|███▉      | 4418/11066 [16:11<23:47,  4.66it/s]
                                                    

 40%|███▉      | 4418/11066 [16:11<23:47,  4.66it/s]
 40%|███▉      | 4419/11066 [16:11<23:59,  4.62it/s]
                                                    

 40%|███▉      | 4419/11066 [16:11<23:59,  4.62it/s]
 40%|███▉      | 4420/11066 [16:11<24:01,  4.61it/s]
                                                    

 40%|███▉      | 4420/11066 [16:11<24:01,  4.61it/s]
 40%|███▉      | 4421/11066 [16:11<24:16,  4.56it/s]
                                                    

 40%|███▉      | 4421/11066 [16:11<24:16,  4.56it/s]
 40%|███▉      | 4422/11066 [16:12<24:23,  4.54it/s]
                                                    

 40%|███▉      | 4422/11066 [16:12<24:23,  4.54it/s]
 40%|███▉      | 4423/11066 [16:12<24:17,  4.56it/s]
                                                    

 40%|███▉      | 4423/11066 [16:12<24:17,  4.56it/s]
 40%|███▉      | 4424/11066 [16:12<24:06,  4.59it/s]
                                                    

 40%|███▉      | 4424/11066 [16:12<24:06,  4.59it/s]
 40%|███▉      | 4425/11066 [16:12<23:50,  4.64it/s]
                                                    

 40%|███▉      | 4425/11066 [16:12<23:50,  4.64it/s]
 40%|███▉      | 4426/11066 [16:12<23:36,  4.69it/s]
                                                    

 40%|███▉      | 4426/11066 [16:12<23:36,  4.69it/s]
 40%|████      | 4427/11066 [16:13<23:43,  4.66it/s]
                                                    

 40%|████      | 4427/11066 [16:13<23:43,  4.66it/s]
 40%|████      | 4428/11066 [16:13<23:42,  4.67it/s]
                                                    

 40%|████      | 4428/11066 [16:13<23:42,  4.67it/s]
 40%|████      | 4429/11066 [16:13<24:02,  4.60it/s]
                                                    

 40%|████      | 4429/11066 [16:13<24:02,  4.60it/s]
 40%|████      | 4430/11066 [16:13<24:02,  4.60it/s]
                                                    

 40%|████      | 4430/11066 [16:13<24:02,  4.60it/s]
 40%|████      | 4431/11066 [16:13<24:05,  4.59it/s]
                                                    

 40%|████      | 4431/11066 [16:13<24:05,  4.59it/s]
 40%|████      | 4432/11066 [16:14<24:00,  4.60it/s]
                                                    

 40%|████      | 4432/11066 [16:14<24:00,  4.60it/s]
 40%|████      | 4433/11066 [16:14<24:03,  4.60it/s]
                                                    

 40%|████      | 4433/11066 [16:14<24:03,  4.60it/s]
 40%|████      | 4434/11066 [16:14<23:53,  4.63it/s]
                                                    

 40%|████      | 4434/11066 [16:14<23:53,  4.63it/s]
 40%|████      | 4435/11066 [16:14<24:09,  4.57it/s]
                                                    

 40%|████      | 4435/11066 [16:14<24:09,  4.57it/s]
 40%|████      | 4436/11066 [16:15<23:50,  4.64it/s]
                                                    

 40%|████      | 4436/11066 [16:15<23:50,  4.64it/s]
 40%|████      | 4437/11066 [16:15<24:04,  4.59it/s]
                                                    

 40%|████      | 4437/11066 [16:15<24:04,  4.59it/s]
 40%|████      | 4438/11066 [16:15<24:11,  4.57it/s]
                                                    

 40%|████      | 4438/11066 [16:15<24:11,  4.57it/s]
 40%|████      | 4439/11066 [16:15<24:17,  4.55it/s]
                                                    

 40%|████      | 4439/11066 [16:15<24:17,  4.55it/s]
 40%|████      | 4440/11066 [16:15<24:21,  4.53it/s]
                                                    

 40%|████      | 4440/11066 [16:15<24:21,  4.53it/s]
 40%|████      | 4441/11066 [16:16<24:24,  4.52it/s]
                                                    

 40%|████      | 4441/11066 [16:16<24:24,  4.52it/s]
 40%|████      | 4442/11066 [16:16<24:24,  4.52it/s]
                                                    

 40%|████      | 4442/11066 [16:16<24:24,  4.52it/s]
 40%|████      | 4443/11066 [16:16<24:26,  4.52it/s]
                                                    

 40%|████      | 4443/11066 [16:16<24:26,  4.52it/s]
 40%|████      | 4444/11066 [16:16<24:28,  4.51it/s]
                                                    

 40%|████      | 4444/11066 [16:16<24:28,  4.51it/s]
 40%|████      | 4445/11066 [16:17<24:29,  4.51it/s]
                                                    

 40%|████      | 4445/11066 [16:17<24:29,  4.51it/s]
 40%|████      | 4446/11066 [16:17<24:29,  4.51it/s]
                                                    

 40%|████      | 4446/11066 [16:17<24:29,  4.51it/s]
 40%|████      | 4447/11066 [16:17<24:29,  4.50it/s]
                                                    

 40%|████      | 4447/11066 [16:17<24:29,  4.50it/s]
 40%|████      | 4448/11066 [16:17<24:32,  4.49it/s]
                                                    

 40%|████      | 4448/11066 [16:17<24:32,  4.49it/s]
 40%|████      | 4449/11066 [16:17<24:33,  4.49it/s]
                                                    

 40%|████      | 4449/11066 [16:17<24:33,  4.49it/s]
 40%|████      | 4450/11066 [16:18<24:35,  4.48it/s]
                                                    

 40%|████      | 4450/11066 [16:18<24:35,  4.48it/s]
 40%|████      | 4451/11066 [16:18<24:19,  4.53it/s]
                                                    

 40%|████      | 4451/11066 [16:18<24:19,  4.53it/s]
 40%|████      | 4452/11066 [16:18<23:58,  4.60it/s]
                                                    

 40%|████      | 4452/11066 [16:18<23:58,  4.60it/s]
 40%|████      | 4453/11066 [16:18<23:56,  4.60it/s]
                                                    

 40%|████      | 4453/11066 [16:18<23:56,  4.60it/s]
 40%|████      | 4454/11066 [16:19<24:06,  4.57it/s]
                                                    

 40%|████      | 4454/11066 [16:19<24:06,  4.57it/s]
 40%|████      | 4455/11066 [16:19<24:18,  4.53it/s]
                                                    

 40%|████      | 4455/11066 [16:19<24:18,  4.53it/s]
 40%|████      | 4456/11066 [16:19<24:11,  4.55it/s]
                                                    

 40%|████      | 4456/11066 [16:19<24:11,  4.55it/s]
 40%|████      | 4457/11066 [16:19<23:51,  4.62it/s]
                                                    

 40%|████      | 4457/11066 [16:19<23:51,  4.62it/s]
 40%|████      | 4458/11066 [16:19<24:02,  4.58it/s]
                                                    

 40%|████      | 4458/11066 [16:19<24:02,  4.58it/s]
 40%|████      | 4459/11066 [16:20<24:10,  4.56it/s]
                                                    

 40%|████      | 4459/11066 [16:20<24:10,  4.56it/s]
 40%|████      | 4460/11066 [16:20<24:15,  4.54it/s]
                                                    

 40%|████      | 4460/11066 [16:20<24:15,  4.54it/s]
 40%|████      | 4461/11066 [16:20<24:19,  4.53it/s]
                                                    

 40%|████      | 4461/11066 [16:20<24:19,  4.53it/s]
 40%|████      | 4462/11066 [16:20<24:22,  4.52it/s]
                                                    

 40%|████      | 4462/11066 [16:20<24:22,  4.52it/s]
 40%|████      | 4463/11066 [16:20<24:23,  4.51it/s]
                                                    

 40%|████      | 4463/11066 [16:20<24:23,  4.51it/s]
 40%|████      | 4464/11066 [16:21<24:25,  4.51it/s]
                                                    

 40%|████      | 4464/11066 [16:21<24:25,  4.51it/s]
 40%|████      | 4465/11066 [16:21<24:26,  4.50it/s]
                                                    

 40%|████      | 4465/11066 [16:21<24:26,  4.50it/s]
 40%|████      | 4466/11066 [16:21<24:29,  4.49it/s]
                                                    

 40%|████      | 4466/11066 [16:21<24:29,  4.49it/s]
 40%|████      | 4467/11066 [16:21<24:30,  4.49it/s]
                                                    

 40%|████      | 4467/11066 [16:21<24:30,  4.49it/s]
 40%|████      | 4468/11066 [16:22<24:28,  4.49it/s]
                                                    

 40%|████      | 4468/11066 [16:22<24:28,  4.49it/s]
 40%|████      | 4469/11066 [16:22<24:29,  4.49it/s]
                                                    

 40%|████      | 4469/11066 [16:22<24:29,  4.49it/s]
 40%|████      | 4470/11066 [16:22<24:31,  4.48it/s]
                                                    

 40%|████      | 4470/11066 [16:22<24:31,  4.48it/s]
 40%|████      | 4471/11066 [16:22<24:30,  4.49it/s]
                                                    

 40%|████      | 4471/11066 [16:22<24:30,  4.49it/s]
 40%|████      | 4472/11066 [16:22<24:27,  4.49it/s]
                                                    

 40%|████      | 4472/11066 [16:22<24:27,  4.49it/s]
 40%|████      | 4473/11066 [16:23<24:29,  4.49it/s]
                                                    

 40%|████      | 4473/11066 [16:23<24:29,  4.49it/s]
 40%|████      | 4474/11066 [16:23<24:29,  4.48it/s]
                                                    

 40%|████      | 4474/11066 [16:23<24:29,  4.48it/s]
 40%|████      | 4475/11066 [16:23<24:31,  4.48it/s]
                                                    

 40%|████      | 4475/11066 [16:23<24:31,  4.48it/s]
 40%|████      | 4476/11066 [16:23<24:30,  4.48it/s]
                                                    

 40%|████      | 4476/11066 [16:23<24:30,  4.48it/s]
 40%|████      | 4477/11066 [16:24<24:28,  4.49it/s]
                                                    

 40%|████      | 4477/11066 [16:24<24:28,  4.49it/s]
 40%|████      | 4478/11066 [16:24<24:27,  4.49it/s]
                                                    

 40%|████      | 4478/11066 [16:24<24:27,  4.49it/s]
 40%|████      | 4479/11066 [16:24<24:27,  4.49it/s]
                                                    

 40%|████      | 4479/11066 [16:24<24:27,  4.49it/s]
 40%|████      | 4480/11066 [16:24<24:26,  4.49it/s]
                                                    

 40%|████      | 4480/11066 [16:24<24:26,  4.49it/s]
 40%|████      | 4481/11066 [16:25<24:26,  4.49it/s]
                                                    

 40%|████      | 4481/11066 [16:25<24:26,  4.49it/s]
 41%|████      | 4482/11066 [16:25<24:28,  4.48it/s]
                                                    

 41%|████      | 4482/11066 [16:25<24:28,  4.48it/s]
 41%|████      | 4483/11066 [16:25<24:27,  4.49it/s]
                                                    

 41%|████      | 4483/11066 [16:25<24:27,  4.49it/s]
 41%|████      | 4484/11066 [16:25<24:26,  4.49it/s]
                                                    

 41%|████      | 4484/11066 [16:25<24:26,  4.49it/s]
 41%|████      | 4485/11066 [16:25<24:25,  4.49it/s]
                                                    

 41%|████      | 4485/11066 [16:25<24:25,  4.49it/s]
 41%|████      | 4486/11066 [16:26<24:26,  4.49it/s]
                                                    

 41%|████      | 4486/11066 [16:26<24:26,  4.49it/s]
 41%|████      | 4487/11066 [16:26<24:25,  4.49it/s]
                                                    

 41%|████      | 4487/11066 [16:26<24:25,  4.49it/s]
 41%|████      | 4488/11066 [16:26<24:22,  4.50it/s]
                                                    

 41%|████      | 4488/11066 [16:26<24:22,  4.50it/s]
 41%|████      | 4489/11066 [16:26<24:11,  4.53it/s]
                                                    

 41%|████      | 4489/11066 [16:26<24:11,  4.53it/s]
 41%|████      | 4490/11066 [16:27<24:21,  4.50it/s]
                                                    

 41%|████      | 4490/11066 [16:27<24:21,  4.50it/s]
 41%|████      | 4491/11066 [16:27<24:24,  4.49it/s]
                                                    

 41%|████      | 4491/11066 [16:27<24:24,  4.49it/s]
 41%|████      | 4492/11066 [16:27<24:05,  4.55it/s]
                                                    

 41%|████      | 4492/11066 [16:27<24:05,  4.55it/s]
 41%|████      | 4493/11066 [16:27<23:49,  4.60it/s]
                                                    

 41%|████      | 4493/11066 [16:27<23:49,  4.60it/s]
 41%|████      | 4494/11066 [16:27<23:39,  4.63it/s]
                                                    

 41%|████      | 4494/11066 [16:27<23:39,  4.63it/s]
 41%|████      | 4495/11066 [16:28<23:50,  4.59it/s]
                                                    

 41%|████      | 4495/11066 [16:28<23:50,  4.59it/s]
 41%|████      | 4496/11066 [16:28<24:00,  4.56it/s]
                                                    

 41%|████      | 4496/11066 [16:28<24:00,  4.56it/s]
 41%|████      | 4497/11066 [16:28<24:06,  4.54it/s]
                                                    

 41%|████      | 4497/11066 [16:28<24:06,  4.54it/s]
 41%|████      | 4498/11066 [16:28<24:10,  4.53it/s]
                                                    

 41%|████      | 4498/11066 [16:28<24:10,  4.53it/s]
 41%|████      | 4499/11066 [16:28<24:14,  4.52it/s]
                                                    

 41%|████      | 4499/11066 [16:28<24:14,  4.52it/s]
 41%|████      | 4500/11066 [16:29<24:14,  4.51it/s]
                                                    

 41%|████      | 4500/11066 [16:29<24:14,  4.51it/s]
 41%|████      | 4501/11066 [16:29<24:18,  4.50it/s]
                                                    

 41%|████      | 4501/11066 [16:29<24:18,  4.50it/s]
 41%|████      | 4502/11066 [16:29<24:19,  4.50it/s]
                                                    
{'loss': 0.7063, 'learning_rate': 1.8101391650099404e-05, 'epoch': 0.79}
{'loss': 0.9559, 'learning_rate': 1.8098680643412253e-05, 'epoch': 0.79}
{'loss': 1.4254, 'learning_rate': 1.8095969636725105e-05, 'epoch': 0.79}
{'loss': 1.2093, 'learning_rate': 1.8093258630037957e-05, 'epoch': 0.79}
{'loss': 0.8174, 'learning_rate': 1.8090547623350805e-05, 'epoch': 0.79}
{'loss': 1.2157, 'learning_rate': 1.8087836616663653e-05, 'epoch': 0.79}
{'loss': 1.2371, 'learning_rate': 1.8085125609976505e-05, 'epoch': 0.79}
{'loss': 1.7108, 'learning_rate': 1.8082414603289354e-05, 'epoch': 0.79}
{'loss': 0.8066, 'learning_rate': 1.8079703596602205e-05, 'epoch': 0.79}
{'loss': 1.1828, 'learning_rate': 1.8076992589915057e-05, 'epoch': 0.79}
{'loss': 1.27, 'learning_rate': 1.8074281583227906e-05, 'epoch': 0.8}
{'loss': 0.6907, 'learning_rate': 1.8071570576540758e-05, 'epoch': 0.8}
{'loss': 0.9107, 'learning_rate': 1.8068859569853606e-05, 'epoch': 0.8}
{'loss': 0.7045, 'learning_rate': 1.8066148563166454e-05, 'epoch': 0.8}
{'loss': 1.0304, 'learning_rate': 1.8063437556479306e-05, 'epoch': 0.8}
{'loss': 1.2366, 'learning_rate': 1.8060726549792155e-05, 'epoch': 0.8}
{'loss': 0.8061, 'learning_rate': 1.8058015543105007e-05, 'epoch': 0.8}
{'loss': 1.1401, 'learning_rate': 1.805530453641786e-05, 'epoch': 0.8}
{'loss': 1.1435, 'learning_rate': 1.8052593529730707e-05, 'epoch': 0.8}
{'loss': 1.3847, 'learning_rate': 1.804988252304356e-05, 'epoch': 0.8}
{'loss': 1.6655, 'learning_rate': 1.804717151635641e-05, 'epoch': 0.8}
{'loss': 1.1093, 'learning_rate': 1.8044460509669256e-05, 'epoch': 0.8}
{'loss': 0.9479, 'learning_rate': 1.8041749502982107e-05, 'epoch': 0.8}
{'loss': 1.7696, 'learning_rate': 1.8039038496294956e-05, 'epoch': 0.8}
{'loss': 0.7989, 'learning_rate': 1.8036327489607808e-05, 'epoch': 0.8}
{'loss': 0.9169, 'learning_rate': 1.803361648292066e-05, 'epoch': 0.8}
{'loss': 1.7174, 'learning_rate': 1.8030905476233508e-05, 'epoch': 0.8}
{'loss': 1.2347, 'learning_rate': 1.802819446954636e-05, 'epoch': 0.8}
{'loss': 0.7493, 'learning_rate': 1.802548346285921e-05, 'epoch': 0.8}
{'loss': 0.7018, 'learning_rate': 1.8022772456172057e-05, 'epoch': 0.8}
{'loss': 1.2641, 'learning_rate': 1.802006144948491e-05, 'epoch': 0.8}
{'loss': 0.8615, 'learning_rate': 1.801735044279776e-05, 'epoch': 0.8}
{'loss': 0.7981, 'learning_rate': 1.801463943611061e-05, 'epoch': 0.8}
{'loss': 1.2107, 'learning_rate': 1.801192842942346e-05, 'epoch': 0.8}
{'loss': 1.381, 'learning_rate': 1.800921742273631e-05, 'epoch': 0.8}
{'loss': 1.0947, 'learning_rate': 1.800650641604916e-05, 'epoch': 0.8}
{'loss': 1.1983, 'learning_rate': 1.8003795409362013e-05, 'epoch': 0.8}
{'loss': 0.8163, 'learning_rate': 1.8001084402674858e-05, 'epoch': 0.8}
{'loss': 1.188, 'learning_rate': 1.799837339598771e-05, 'epoch': 0.8}
{'loss': 0.3761, 'learning_rate': 1.799566238930056e-05, 'epoch': 0.8}
{'loss': 0.9463, 'learning_rate': 1.799295138261341e-05, 'epoch': 0.8}
{'loss': 0.8172, 'learning_rate': 1.799024037592626e-05, 'epoch': 0.8}
{'loss': 0.6889, 'learning_rate': 1.7987529369239113e-05, 'epoch': 0.8}
{'loss': 1.0304, 'learning_rate': 1.7984818362551962e-05, 'epoch': 0.8}
{'loss': 0.591, 'learning_rate': 1.7982107355864814e-05, 'epoch': 0.8}
{'loss': 1.4121, 'learning_rate': 1.797939634917766e-05, 'epoch': 0.8}
{'loss': 0.7765, 'learning_rate': 1.797668534249051e-05, 'epoch': 0.8}
{'loss': 0.6924, 'learning_rate': 1.7973974335803362e-05, 'epoch': 0.8}
{'loss': 1.1338, 'learning_rate': 1.797126332911621e-05, 'epoch': 0.8}
{'loss': 1.4003, 'learning_rate': 1.7968552322429063e-05, 'epoch': 0.8}
{'loss': 1.3175, 'learning_rate': 1.7965841315741915e-05, 'epoch': 0.8}
{'loss': 0.718, 'learning_rate': 1.7963130309054763e-05, 'epoch': 0.8}
{'loss': 2.0737, 'learning_rate': 1.7960419302367615e-05, 'epoch': 0.8}
{'loss': 0.526, 'learning_rate': 1.7957708295680463e-05, 'epoch': 0.8}
{'loss': 1.2347, 'learning_rate': 1.795499728899331e-05, 'epoch': 0.8}
{'loss': 0.8449, 'learning_rate': 1.7952286282306163e-05, 'epoch': 0.8}
{'loss': 0.6274, 'learning_rate': 1.7949575275619012e-05, 'epoch': 0.8}
{'loss': 0.9191, 'learning_rate': 1.7946864268931864e-05, 'epoch': 0.8}
{'loss': 1.2571, 'learning_rate': 1.7944153262244716e-05, 'epoch': 0.8}
{'loss': 0.9457, 'learning_rate': 1.7941442255557564e-05, 'epoch': 0.8}
{'loss': 0.7726, 'learning_rate': 1.7938731248870416e-05, 'epoch': 0.8}
{'loss': 1.1323, 'learning_rate': 1.7936020242183264e-05, 'epoch': 0.8}
{'loss': 1.0855, 'learning_rate': 1.7933309235496113e-05, 'epoch': 0.8}
{'loss': 0.4221, 'learning_rate': 1.7930598228808965e-05, 'epoch': 0.8}
{'loss': 0.7875, 'learning_rate': 1.7927887222121816e-05, 'epoch': 0.8}
{'loss': 0.7797, 'learning_rate': 1.7925176215434665e-05, 'epoch': 0.8}
{'loss': 1.2405, 'learning_rate': 1.7922465208747517e-05, 'epoch': 0.81}
{'loss': 1.2233, 'learning_rate': 1.7919754202060365e-05, 'epoch': 0.81}
{'loss': 1.1371, 'learning_rate': 1.7917043195373217e-05, 'epoch': 0.81}
{'loss': 1.5776, 'learning_rate': 1.7914332188686065e-05, 'epoch': 0.81}
{'loss': 1.263, 'learning_rate': 1.7911621181998914e-05, 'epoch': 0.81}
{'loss': 1.3746, 'learning_rate': 1.7908910175311766e-05, 'epoch': 0.81}
{'loss': 0.8386, 'learning_rate': 1.7906199168624617e-05, 'epoch': 0.81}
{'loss': 1.2925, 'learning_rate': 1.7903488161937466e-05, 'epoch': 0.81}
{'loss': 1.5016, 'learning_rate': 1.7900777155250318e-05, 'epoch': 0.81}
{'loss': 0.9947, 'learning_rate': 1.789806614856317e-05, 'epoch': 0.81}
{'loss': 1.0871, 'learning_rate': 1.7895355141876018e-05, 'epoch': 0.81}
{'loss': 0.8877, 'learning_rate': 1.7892644135188866e-05, 'epoch': 0.81}
{'loss': 0.537, 'learning_rate': 1.7889933128501715e-05, 'epoch': 0.81}
{'loss': 1.2409, 'learning_rate': 1.7887222121814567e-05, 'epoch': 0.81}
{'loss': 0.7719, 'learning_rate': 1.788451111512742e-05, 'epoch': 0.81}
{'loss': 1.5367, 'learning_rate': 1.7881800108440267e-05, 'epoch': 0.81}
{'loss': 0.8905, 'learning_rate': 1.787908910175312e-05, 'epoch': 0.81}
{'loss': 0.5374, 'learning_rate': 1.787637809506597e-05, 'epoch': 0.81}
{'loss': 0.4875, 'learning_rate': 1.787366708837882e-05, 'epoch': 0.81}
{'loss': 0.6507, 'learning_rate': 1.7870956081691668e-05, 'epoch': 0.81}
{'loss': 1.0189, 'learning_rate': 1.786824507500452e-05, 'epoch': 0.81}
{'loss': 1.069, 'learning_rate': 1.7865534068317368e-05, 'epoch': 0.81}
{'loss': 1.1652, 'learning_rate': 1.786282306163022e-05, 'epoch': 0.81}
{'loss': 1.7269, 'learning_rate': 1.7860112054943068e-05, 'epoch': 0.81}
{'loss': 0.9838, 'learning_rate': 1.785740104825592e-05, 'epoch': 0.81}
{'loss': 1.3521, 'learning_rate': 1.7854690041568772e-05, 'epoch': 0.81}
{'loss': 1.1756, 'learning_rate': 1.785197903488162e-05, 'epoch': 0.81}
{'loss': 1.7456, 'learning_rate': 1.784926802819447e-05, 'epoch': 0.81}
{'loss': 1.0554, 'learning_rate': 1.784655702150732e-05, 'epoch': 0.81}
{'loss': 1.8781, 'learning_rate': 1.784384601482017e-05, 'epoch': 0.81}
{'loss': 1.0892, 'learning_rate': 1.784113500813302e-05, 'epoch': 0.81}
{'loss': 1.1143, 'learning_rate': 1.7838424001445873e-05, 'epoch': 0.81}
{'loss': 1.8474, 'learning_rate': 1.783571299475872e-05, 'epoch': 0.81}
{'loss': 1.4579, 'learning_rate': 1.7833001988071573e-05, 'epoch': 0.81}
{'loss': 1.4139, 'learning_rate': 1.783029098138442e-05, 'epoch': 0.81}
{'loss': 1.4583, 'learning_rate': 1.782757997469727e-05, 'epoch': 0.81}
{'loss': 1.4062, 'learning_rate': 1.782486896801012e-05, 'epoch': 0.81}
{'loss': 0.8195, 'learning_rate': 1.782215796132297e-05, 'epoch': 0.81}
{'loss': 1.3321, 'learning_rate': 1.7819446954635822e-05, 'epoch': 0.81}
{'loss': 0.825, 'learning_rate': 1.7816735947948674e-05, 'epoch': 0.81}
{'loss': 0.9267, 'learning_rate': 1.7814024941261522e-05, 'epoch': 0.81}
{'loss': 0.9442, 'learning_rate': 1.7811313934574374e-05, 'epoch': 0.81}
{'loss': 0.6047, 'learning_rate': 1.7808602927887226e-05, 'epoch': 0.81}
{'loss': 1.7276, 'learning_rate': 1.780589192120007e-05, 'epoch': 0.81}
{'loss': 1.2077, 'learning_rate': 1.7803180914512923e-05, 'epoch': 0.81}
{'loss': 1.3754, 'learning_rate': 1.780046990782577e-05, 'epoch': 0.81}
{'loss': 0.8203, 'learning_rate': 1.7797758901138623e-05, 'epoch': 0.81}

 41%|████      | 4502/11066 [16:29<24:19,  4.50it/s]
 41%|████      | 4503/11066 [16:29<24:10,  4.52it/s]
                                                    

 41%|████      | 4503/11066 [16:29<24:10,  4.52it/s]
 41%|████      | 4504/11066 [16:30<24:13,  4.51it/s]
                                                    

 41%|████      | 4504/11066 [16:30<24:13,  4.51it/s]
 41%|████      | 4505/11066 [16:30<24:22,  4.49it/s]
                                                    

 41%|████      | 4505/11066 [16:30<24:22,  4.49it/s]
 41%|████      | 4506/11066 [16:30<24:24,  4.48it/s]
                                                    

 41%|████      | 4506/11066 [16:30<24:24,  4.48it/s]
 41%|████      | 4507/11066 [16:30<24:24,  4.48it/s]
                                                    

 41%|████      | 4507/11066 [16:30<24:24,  4.48it/s]
 41%|████      | 4508/11066 [16:30<24:24,  4.48it/s]
                                                    

 41%|████      | 4508/11066 [16:30<24:24,  4.48it/s]
 41%|████      | 4509/11066 [16:31<24:21,  4.49it/s]
                                                    

 41%|████      | 4509/11066 [16:31<24:21,  4.49it/s]
 41%|████      | 4510/11066 [16:31<24:22,  4.48it/s]
                                                    

 41%|████      | 4510/11066 [16:31<24:22,  4.48it/s]
 41%|████      | 4511/11066 [16:31<24:20,  4.49it/s]
                                                    

 41%|████      | 4511/11066 [16:31<24:20,  4.49it/s]
 41%|████      | 4512/11066 [16:31<24:19,  4.49it/s]
                                                    

 41%|████      | 4512/11066 [16:31<24:19,  4.49it/s]
 41%|████      | 4513/11066 [16:32<24:17,  4.50it/s]
                                                    

 41%|████      | 4513/11066 [16:32<24:17,  4.50it/s]
 41%|████      | 4514/11066 [16:32<24:19,  4.49it/s]
                                                    

 41%|████      | 4514/11066 [16:32<24:19,  4.49it/s]
 41%|████      | 4515/11066 [16:32<24:19,  4.49it/s]
                                                    

 41%|████      | 4515/11066 [16:32<24:19,  4.49it/s]
 41%|████      | 4516/11066 [16:32<24:10,  4.52it/s]
                                                    

 41%|████      | 4516/11066 [16:32<24:10,  4.52it/s]
 41%|████      | 4517/11066 [16:32<24:07,  4.52it/s]
                                                    

 41%|████      | 4517/11066 [16:32<24:07,  4.52it/s]
 41%|████      | 4518/11066 [16:33<24:17,  4.49it/s]
                                                    

 41%|████      | 4518/11066 [16:33<24:17,  4.49it/s]
 41%|████      | 4519/11066 [16:33<24:21,  4.48it/s]
                                                    

 41%|████      | 4519/11066 [16:33<24:21,  4.48it/s]
 41%|████      | 4520/11066 [16:33<23:56,  4.56it/s]
                                                    

 41%|████      | 4520/11066 [16:33<23:56,  4.56it/s]
 41%|████      | 4521/11066 [16:33<24:18,  4.49it/s]
                                                    

 41%|████      | 4521/11066 [16:33<24:18,  4.49it/s]
 41%|████      | 4522/11066 [16:34<24:16,  4.49it/s]
                                                    

 41%|████      | 4522/11066 [16:34<24:16,  4.49it/s]
 41%|████      | 4523/11066 [16:34<23:48,  4.58it/s]
                                                    

 41%|████      | 4523/11066 [16:34<23:48,  4.58it/s]
 41%|████      | 4524/11066 [16:34<24:07,  4.52it/s]
                                                    

 41%|████      | 4524/11066 [16:34<24:07,  4.52it/s]
 41%|████      | 4525/11066 [16:34<23:58,  4.55it/s]
                                                    

 41%|████      | 4525/11066 [16:34<23:58,  4.55it/s]
 41%|████      | 4526/11066 [16:34<23:40,  4.61it/s]
                                                    

 41%|████      | 4526/11066 [16:34<23:40,  4.61it/s]
 41%|████      | 4527/11066 [16:35<23:29,  4.64it/s]
                                                    

 41%|████      | 4527/11066 [16:35<23:29,  4.64it/s]
 41%|████      | 4528/11066 [16:35<23:48,  4.58it/s]
                                                    

 41%|████      | 4528/11066 [16:35<23:48,  4.58it/s]
 41%|████      | 4529/11066 [16:35<24:02,  4.53it/s]
                                                    

 41%|████      | 4529/11066 [16:35<24:02,  4.53it/s]
 41%|████      | 4530/11066 [16:35<24:11,  4.50it/s]
                                                    

 41%|████      | 4530/11066 [16:35<24:11,  4.50it/s]
 41%|████      | 4531/11066 [16:36<24:31,  4.44it/s]
                                                    

 41%|████      | 4531/11066 [16:36<24:31,  4.44it/s]
 41%|████      | 4532/11066 [16:36<24:03,  4.53it/s]
                                                    

 41%|████      | 4532/11066 [16:36<24:03,  4.53it/s]
 41%|████      | 4533/11066 [16:36<24:11,  4.50it/s]
                                                    

 41%|████      | 4533/11066 [16:36<24:11,  4.50it/s]
 41%|████      | 4534/11066 [16:36<24:17,  4.48it/s]
                                                    

 41%|████      | 4534/11066 [16:36<24:17,  4.48it/s]
 41%|████      | 4535/11066 [16:36<24:25,  4.46it/s]
                                                    

 41%|████      | 4535/11066 [16:36<24:25,  4.46it/s]
 41%|████      | 4536/11066 [16:37<24:25,  4.46it/s]
                                                    

 41%|████      | 4536/11066 [16:37<24:25,  4.46it/s]
 41%|████      | 4537/11066 [16:37<24:31,  4.44it/s]
                                                    

 41%|████      | 4537/11066 [16:37<24:31,  4.44it/s]
 41%|████      | 4538/11066 [16:37<24:28,  4.44it/s]
                                                    

 41%|████      | 4538/11066 [16:37<24:28,  4.44it/s]
 41%|████      | 4539/11066 [16:37<24:13,  4.49it/s]
                                                    

 41%|████      | 4539/11066 [16:37<24:13,  4.49it/s]
 41%|████      | 4540/11066 [16:38<24:13,  4.49it/s]
                                                    

 41%|████      | 4540/11066 [16:38<24:13,  4.49it/s]
 41%|████      | 4541/11066 [16:38<24:26,  4.45it/s]
                                                    

 41%|████      | 4541/11066 [16:38<24:26,  4.45it/s]
 41%|████      | 4542/11066 [16:38<24:18,  4.47it/s]
                                                    

 41%|████      | 4542/11066 [16:38<24:18,  4.47it/s]
 41%|████      | 4543/11066 [16:38<24:09,  4.50it/s]
                                                    

 41%|████      | 4543/11066 [16:38<24:09,  4.50it/s]
 41%|████      | 4544/11066 [16:38<24:16,  4.48it/s]
                                                    

 41%|████      | 4544/11066 [16:38<24:16,  4.48it/s]
 41%|████      | 4545/11066 [16:39<24:20,  4.46it/s]
                                                    

 41%|████      | 4545/11066 [16:39<24:20,  4.46it/s]
 41%|████      | 4546/11066 [16:39<24:25,  4.45it/s]
                                                    

 41%|████      | 4546/11066 [16:39<24:25,  4.45it/s]
 41%|████      | 4547/11066 [16:39<24:11,  4.49it/s]
                                                    

 41%|████      | 4547/11066 [16:39<24:11,  4.49it/s]
 41%|████      | 4548/11066 [16:39<24:29,  4.44it/s]
                                                    

 41%|████      | 4548/11066 [16:39<24:29,  4.44it/s]
 41%|████      | 4549/11066 [16:40<24:30,  4.43it/s]
                                                    

 41%|████      | 4549/11066 [16:40<24:30,  4.43it/s]
 41%|████      | 4550/11066 [16:40<24:15,  4.48it/s]
                                                    

 41%|████      | 4550/11066 [16:40<24:15,  4.48it/s]
 41%|████      | 4551/11066 [16:40<24:09,  4.49it/s]
                                                    

 41%|████      | 4551/11066 [16:40<24:09,  4.49it/s]
 41%|████      | 4552/11066 [16:40<24:12,  4.49it/s]
                                                    

 41%|████      | 4552/11066 [16:40<24:12,  4.49it/s]
 41%|████      | 4553/11066 [16:40<24:20,  4.46it/s]
                                                    

 41%|████      | 4553/11066 [16:40<24:20,  4.46it/s]
 41%|████      | 4554/11066 [16:41<24:09,  4.49it/s]
                                                    

 41%|████      | 4554/11066 [16:41<24:09,  4.49it/s]
 41%|████      | 4555/11066 [16:41<23:52,  4.54it/s]
                                                    

 41%|████      | 4555/11066 [16:41<23:52,  4.54it/s]
 41%|████      | 4556/11066 [16:41<24:07,  4.50it/s]
                                                    

 41%|████      | 4556/11066 [16:41<24:07,  4.50it/s]
 41%|████      | 4557/11066 [16:41<24:07,  4.50it/s]
                                                    

 41%|████      | 4557/11066 [16:41<24:07,  4.50it/s]
 41%|████      | 4558/11066 [16:42<23:59,  4.52it/s]
                                                    

 41%|████      | 4558/11066 [16:42<23:59,  4.52it/s]
 41%|████      | 4559/11066 [16:42<24:06,  4.50it/s]
                                                    

 41%|████      | 4559/11066 [16:42<24:06,  4.50it/s]
 41%|████      | 4560/11066 [16:42<24:08,  4.49it/s]
                                                    

 41%|████      | 4560/11066 [16:42<24:08,  4.49it/s]
 41%|████      | 4561/11066 [16:42<24:06,  4.50it/s]
                                                    

 41%|████      | 4561/11066 [16:42<24:06,  4.50it/s]
 41%|████      | 4562/11066 [16:42<24:07,  4.49it/s]
                                                    

 41%|████      | 4562/11066 [16:42<24:07,  4.49it/s]
 41%|████      | 4563/11066 [16:43<24:06,  4.50it/s]
                                                    

 41%|████      | 4563/11066 [16:43<24:06,  4.50it/s]
 41%|████      | 4564/11066 [16:43<24:06,  4.50it/s]
                                                    

 41%|████      | 4564/11066 [16:43<24:06,  4.50it/s]
 41%|████▏     | 4565/11066 [16:43<24:06,  4.49it/s]
                                                    

 41%|████▏     | 4565/11066 [16:43<24:06,  4.49it/s]
 41%|████▏     | 4566/11066 [16:43<24:07,  4.49it/s]
                                                    

 41%|████▏     | 4566/11066 [16:43<24:07,  4.49it/s]
 41%|████▏     | 4567/11066 [16:44<24:07,  4.49it/s]
                                                    

 41%|████▏     | 4567/11066 [16:44<24:07,  4.49it/s]
 41%|████▏     | 4568/11066 [16:44<24:05,  4.49it/s]
                                                    

 41%|████▏     | 4568/11066 [16:44<24:05,  4.49it/s]
 41%|████▏     | 4569/11066 [16:44<24:04,  4.50it/s]
                                                    

 41%|████▏     | 4569/11066 [16:44<24:04,  4.50it/s]
 41%|████▏     | 4570/11066 [16:44<24:04,  4.50it/s]
                                                    

 41%|████▏     | 4570/11066 [16:44<24:04,  4.50it/s]
 41%|████▏     | 4571/11066 [16:44<24:05,  4.49it/s]
                                                    

 41%|████▏     | 4571/11066 [16:44<24:05,  4.49it/s]
 41%|████▏     | 4572/11066 [16:45<24:05,  4.49it/s]
                                                    

 41%|████▏     | 4572/11066 [16:45<24:05,  4.49it/s]
 41%|████▏     | 4573/11066 [16:45<24:07,  4.49it/s]
                                                    

 41%|████▏     | 4573/11066 [16:45<24:07,  4.49it/s]
 41%|████▏     | 4574/11066 [16:45<24:10,  4.48it/s]
                                                    

 41%|████▏     | 4574/11066 [16:45<24:10,  4.48it/s]
 41%|████▏     | 4575/11066 [16:45<24:13,  4.46it/s]
                                                    

 41%|████▏     | 4575/11066 [16:45<24:13,  4.46it/s]
 41%|████▏     | 4576/11066 [16:46<24:10,  4.47it/s]
                                                    

 41%|████▏     | 4576/11066 [16:46<24:10,  4.47it/s]
 41%|████▏     | 4577/11066 [16:46<23:56,  4.52it/s]
                                                    

 41%|████▏     | 4577/11066 [16:46<23:56,  4.52it/s]
 41%|████▏     | 4578/11066 [16:46<24:03,  4.50it/s]
                                                    

 41%|████▏     | 4578/11066 [16:46<24:03,  4.50it/s]
 41%|████▏     | 4579/11066 [16:46<24:06,  4.49it/s]
                                                    

 41%|████▏     | 4579/11066 [16:46<24:06,  4.49it/s]
 41%|████▏     | 4580/11066 [16:47<24:05,  4.49it/s]
                                                    

 41%|████▏     | 4580/11066 [16:47<24:05,  4.49it/s]
 41%|████▏     | 4581/11066 [16:47<24:02,  4.49it/s]
                                                    

 41%|████▏     | 4581/11066 [16:47<24:02,  4.49it/s]
 41%|████▏     | 4582/11066 [16:47<24:02,  4.50it/s]
                                                    

 41%|████▏     | 4582/11066 [16:47<24:02,  4.50it/s]
 41%|████▏     | 4583/11066 [16:47<24:03,  4.49it/s]
                                                    

 41%|████▏     | 4583/11066 [16:47<24:03,  4.49it/s]
 41%|████▏     | 4584/11066 [16:47<24:02,  4.49it/s]
                                                    

 41%|████▏     | 4584/11066 [16:47<24:02,  4.49it/s]
 41%|████▏     | 4585/11066 [16:48<24:03,  4.49it/s]
                                                    

 41%|████▏     | 4585/11066 [16:48<24:03,  4.49it/s]
 41%|████▏     | 4586/11066 [16:48<24:03,  4.49it/s]
                                                    

 41%|████▏     | 4586/11066 [16:48<24:03,  4.49it/s]
 41%|████▏     | 4587/11066 [16:48<24:00,  4.50it/s]
                                                    

 41%|████▏     | 4587/11066 [16:48<24:00,  4.50it/s]
 41%|████▏     | 4588/11066 [16:48<23:59,  4.50it/s]
                                                    

 41%|████▏     | 4588/11066 [16:48<23:59,  4.50it/s]
 41%|████▏     | 4589/11066 [16:49<23:58,  4.50it/s]
                                                    

 41%|████▏     | 4589/11066 [16:49<23:58,  4.50it/s]
 41%|████▏     | 4590/11066 [16:49<23:59,  4.50it/s]
                                                    

 41%|████▏     | 4590/11066 [16:49<23:59,  4.50it/s]
 41%|████▏     | 4591/11066 [16:49<23:57,  4.50it/s]
                                                    

 41%|████▏     | 4591/11066 [16:49<23:57,  4.50it/s]
 41%|████▏     | 4592/11066 [16:49<23:57,  4.50it/s]
                                                    

 41%|████▏     | 4592/11066 [16:49<23:57,  4.50it/s]
 42%|████▏     | 4593/11066 [16:49<23:57,  4.50it/s]
                                                    

 42%|████▏     | 4593/11066 [16:49<23:57,  4.50it/s]
 42%|████▏     | 4594/11066 [16:50<23:58,  4.50it/s]
                                                    

 42%|████▏     | 4594/11066 [16:50<23:58,  4.50it/s]
 42%|████▏     | 4595/11066 [16:50<23:52,  4.52it/s]
                                                    

 42%|████▏     | 4595/11066 [16:50<23:52,  4.52it/s]
 42%|████▏     | 4596/11066 [16:50<23:45,  4.54it/s]
                                                    

 42%|████▏     | 4596/11066 [16:50<23:45,  4.54it/s]
 42%|████▏     | 4597/11066 [16:50<23:51,  4.52it/s]
                                                    

 42%|████▏     | 4597/11066 [16:50<23:51,  4.52it/s]
 42%|████▏     | 4598/11066 [16:50<24:01,  4.49it/s]
                                                    

 42%|████▏     | 4598/11066 [16:51<24:01,  4.49it/s]
 42%|████▏     | 4599/11066 [16:51<24:04,  4.48it/s]
                                                    

 42%|████▏     | 4599/11066 [16:51<24:04,  4.48it/s]
 42%|████▏     | 4600/11066 [16:51<24:03,  4.48it/s]
                                                    

 42%|████▏     | 4600/11066 [16:51<24:03,  4.48it/s]
 42%|████▏     | 4601/11066 [16:51<24:01,  4.49it/s]
                                                    

 42%|████▏     | 4601/11066 [16:51<24:01,  4.49it/s]
 42%|████▏     | 4602/11066 [16:51<23:58,  4.49it/s]
                                                    

 42%|████▏     | 4602/11066 [16:51<23:58,  4.49it/s]
 42%|████▏     | 4603/11066 [16:52<23:57,  4.50it/s]
                                                    

 42%|████▏     | 4603/11066 [16:52<23:57,  4.50it/s]
 42%|████▏     | 4604/11066 [16:52<23:55,  4.50it/s]
                                                    

 42%|████▏     | 4604/11066 [16:52<23:55,  4.50it/s]
 42%|████▏     | 4605/11066 [16:52<23:55,  4.50it/s]
                                                    

 42%|████▏     | 4605/11066 [16:52<23:55,  4.50it/s]
 42%|████▏     | 4606/11066 [16:52<23:54,  4.50it/s]
                                                    

 42%|████▏     | 4606/11066 [16:52<23:54,  4.50it/s]
 42%|████▏     | 4607/11066 [16:52<23:53,  4.51it/s]
                                                    

 42%|████▏     | 4607/11066 [16:53<23:53,  4.51it/s]
 42%|████▏     | 4608/11066 [16:53<23:52,  4.51it/s]
                                                    

 42%|████▏     | 4608/11066 [16:53<23:52,  4.51it/s]
 42%|████▏     | 4609/11066 [16:53<23:53,  4.50it/s]
                                                    

 42%|████▏     | 4609/11066 [16:53<23:53,  4.50it/s]
 42%|████▏     | 4610/11066 [16:53<23:54,  4.50it/s]
                                                    

 42%|████▏     | 4610/11066 [16:53<23:54,  4.50it/s]
 42%|████▏     | 4611/11066 [16:53<23:55,  4.50it/s]
                                                    

 42%|████▏     | 4611/11066 [16:53<23:55,  4.50it/s]
 42%|████▏     | 4612/11066 [16:54<23:55,  4.50it/s]
                                                    

 42%|████▏     | 4612/11066 [16:54<23:55,  4.50it/s]
 42%|████▏     | 4613/11066 [16:54<23:58,  4.49it/s]
                                                    

 42%|████▏     | 4613/11066 [16:54<23:58,  4.49it/s]
 42%|████▏     | 4614/11066 [16:54<23:59,  4.48it/s]
                                                    
{'loss': 1.5838, 'learning_rate': 1.7795047894451475e-05, 'epoch': 0.81}
{'loss': 1.3027, 'learning_rate': 1.7792336887764323e-05, 'epoch': 0.81}
{'loss': 1.1864, 'learning_rate': 1.7789625881077175e-05, 'epoch': 0.81}
{'loss': 0.6006, 'learning_rate': 1.7786914874390023e-05, 'epoch': 0.81}
{'loss': 1.6358, 'learning_rate': 1.7784203867702872e-05, 'epoch': 0.81}
{'loss': 1.0484, 'learning_rate': 1.7781492861015724e-05, 'epoch': 0.81}
{'loss': 1.4896, 'learning_rate': 1.7778781854328575e-05, 'epoch': 0.81}
{'loss': 0.9935, 'learning_rate': 1.7776070847641424e-05, 'epoch': 0.81}
{'loss': 1.0999, 'learning_rate': 1.7773359840954276e-05, 'epoch': 0.82}
{'loss': 0.7235, 'learning_rate': 1.7770648834267124e-05, 'epoch': 0.82}
{'loss': 0.9316, 'learning_rate': 1.7767937827579976e-05, 'epoch': 0.82}
{'loss': 0.9655, 'learning_rate': 1.7765226820892824e-05, 'epoch': 0.82}
{'loss': 1.194, 'learning_rate': 1.7762515814205673e-05, 'epoch': 0.82}
{'loss': 0.7268, 'learning_rate': 1.7759804807518525e-05, 'epoch': 0.82}
{'loss': 1.3662, 'learning_rate': 1.7757093800831377e-05, 'epoch': 0.82}
{'loss': 0.7376, 'learning_rate': 1.7754382794144225e-05, 'epoch': 0.82}
{'loss': 1.0793, 'learning_rate': 1.7751671787457077e-05, 'epoch': 0.82}
{'loss': 1.1982, 'learning_rate': 1.774896078076993e-05, 'epoch': 0.82}
{'loss': 0.4049, 'learning_rate': 1.7746249774082777e-05, 'epoch': 0.82}
{'loss': 1.0116, 'learning_rate': 1.7743538767395626e-05, 'epoch': 0.82}
{'loss': 0.9908, 'learning_rate': 1.7740827760708477e-05, 'epoch': 0.82}
{'loss': 1.0823, 'learning_rate': 1.7738116754021326e-05, 'epoch': 0.82}
{'loss': 1.2418, 'learning_rate': 1.7735405747334178e-05, 'epoch': 0.82}
{'loss': 0.4781, 'learning_rate': 1.7732694740647026e-05, 'epoch': 0.82}
{'loss': 0.8269, 'learning_rate': 1.7729983733959878e-05, 'epoch': 0.82}
{'loss': 0.9127, 'learning_rate': 1.772727272727273e-05, 'epoch': 0.82}
{'loss': 0.9925, 'learning_rate': 1.7724561720585578e-05, 'epoch': 0.82}
{'loss': 1.4721, 'learning_rate': 1.7721850713898427e-05, 'epoch': 0.82}
{'loss': 0.7638, 'learning_rate': 1.771913970721128e-05, 'epoch': 0.82}
{'loss': 0.9276, 'learning_rate': 1.7716428700524127e-05, 'epoch': 0.82}
{'loss': 1.2598, 'learning_rate': 1.771371769383698e-05, 'epoch': 0.82}
{'loss': 0.4888, 'learning_rate': 1.771100668714983e-05, 'epoch': 0.82}
{'loss': 1.009, 'learning_rate': 1.770829568046268e-05, 'epoch': 0.82}
{'loss': 0.9235, 'learning_rate': 1.770558467377553e-05, 'epoch': 0.82}
{'loss': 1.4992, 'learning_rate': 1.770287366708838e-05, 'epoch': 0.82}
{'loss': 0.4267, 'learning_rate': 1.7700162660401228e-05, 'epoch': 0.82}
{'loss': 0.7024, 'learning_rate': 1.769745165371408e-05, 'epoch': 0.82}
{'loss': 1.2894, 'learning_rate': 1.7694740647026928e-05, 'epoch': 0.82}
{'loss': 0.9925, 'learning_rate': 1.769202964033978e-05, 'epoch': 0.82}
{'loss': 0.8499, 'learning_rate': 1.768931863365263e-05, 'epoch': 0.82}
{'loss': 1.0042, 'learning_rate': 1.768660762696548e-05, 'epoch': 0.82}
{'loss': 1.618, 'learning_rate': 1.7683896620278332e-05, 'epoch': 0.82}
{'loss': 1.1203, 'learning_rate': 1.7681185613591184e-05, 'epoch': 0.82}
{'loss': 0.9237, 'learning_rate': 1.767847460690403e-05, 'epoch': 0.82}
{'loss': 0.8653, 'learning_rate': 1.767576360021688e-05, 'epoch': 0.82}
{'loss': 1.5441, 'learning_rate': 1.767305259352973e-05, 'epoch': 0.82}
{'loss': 1.0454, 'learning_rate': 1.767034158684258e-05, 'epoch': 0.82}
{'loss': 1.2437, 'learning_rate': 1.7667630580155433e-05, 'epoch': 0.82}
{'loss': 0.6711, 'learning_rate': 1.766491957346828e-05, 'epoch': 0.82}
{'loss': 1.0274, 'learning_rate': 1.7662208566781133e-05, 'epoch': 0.82}
{'loss': 1.3314, 'learning_rate': 1.7659497560093985e-05, 'epoch': 0.82}
{'loss': 1.0322, 'learning_rate': 1.765678655340683e-05, 'epoch': 0.82}
{'loss': 0.9242, 'learning_rate': 1.765407554671968e-05, 'epoch': 0.82}
{'loss': 0.9441, 'learning_rate': 1.7651364540032533e-05, 'epoch': 0.82}
{'loss': 0.8559, 'learning_rate': 1.7648653533345382e-05, 'epoch': 0.82}
{'loss': 1.3913, 'learning_rate': 1.7645942526658234e-05, 'epoch': 0.82}
{'loss': 1.2264, 'learning_rate': 1.7643231519971082e-05, 'epoch': 0.82}
{'loss': 0.8557, 'learning_rate': 1.7640520513283934e-05, 'epoch': 0.82}
{'loss': 1.5583, 'learning_rate': 1.7637809506596786e-05, 'epoch': 0.82}
{'loss': 0.6354, 'learning_rate': 1.763509849990963e-05, 'epoch': 0.82}
{'loss': 0.7293, 'learning_rate': 1.7632387493222483e-05, 'epoch': 0.82}
{'loss': 1.3512, 'learning_rate': 1.7629676486535335e-05, 'epoch': 0.82}
{'loss': 0.6288, 'learning_rate': 1.7626965479848183e-05, 'epoch': 0.82}
{'loss': 1.0428, 'learning_rate': 1.7624254473161035e-05, 'epoch': 0.83}
{'loss': 0.6989, 'learning_rate': 1.7621543466473887e-05, 'epoch': 0.83}
{'loss': 1.0504, 'learning_rate': 1.7618832459786735e-05, 'epoch': 0.83}
{'loss': 0.4123, 'learning_rate': 1.7616121453099587e-05, 'epoch': 0.83}
{'loss': 1.0068, 'learning_rate': 1.7613410446412432e-05, 'epoch': 0.83}
{'loss': 1.1343, 'learning_rate': 1.7610699439725284e-05, 'epoch': 0.83}
{'loss': 0.9047, 'learning_rate': 1.7607988433038136e-05, 'epoch': 0.83}
{'loss': 1.1231, 'learning_rate': 1.7605277426350984e-05, 'epoch': 0.83}
{'loss': 1.2359, 'learning_rate': 1.7602566419663836e-05, 'epoch': 0.83}
{'loss': 0.9265, 'learning_rate': 1.7599855412976688e-05, 'epoch': 0.83}
{'loss': 1.4307, 'learning_rate': 1.7597144406289536e-05, 'epoch': 0.83}
{'loss': 1.0356, 'learning_rate': 1.7594433399602388e-05, 'epoch': 0.83}
{'loss': 0.7226, 'learning_rate': 1.7591722392915236e-05, 'epoch': 0.83}
{'loss': 0.8735, 'learning_rate': 1.7589011386228085e-05, 'epoch': 0.83}
{'loss': 1.1502, 'learning_rate': 1.7586300379540937e-05, 'epoch': 0.83}
{'loss': 1.097, 'learning_rate': 1.7583589372853785e-05, 'epoch': 0.83}
{'loss': 1.1921, 'learning_rate': 1.7580878366166637e-05, 'epoch': 0.83}
{'loss': 0.4772, 'learning_rate': 1.757816735947949e-05, 'epoch': 0.83}
{'loss': 1.1642, 'learning_rate': 1.7575456352792337e-05, 'epoch': 0.83}
{'loss': 0.8066, 'learning_rate': 1.757274534610519e-05, 'epoch': 0.83}
{'loss': 0.8469, 'learning_rate': 1.7570034339418038e-05, 'epoch': 0.83}
{'loss': 0.8983, 'learning_rate': 1.7567323332730886e-05, 'epoch': 0.83}
{'loss': 0.9336, 'learning_rate': 1.7564612326043738e-05, 'epoch': 0.83}
{'loss': 1.0043, 'learning_rate': 1.756190131935659e-05, 'epoch': 0.83}
{'loss': 0.8821, 'learning_rate': 1.7559190312669438e-05, 'epoch': 0.83}
{'loss': 1.2149, 'learning_rate': 1.755647930598229e-05, 'epoch': 0.83}
{'loss': 1.0645, 'learning_rate': 1.755376829929514e-05, 'epoch': 0.83}
{'loss': 0.708, 'learning_rate': 1.755105729260799e-05, 'epoch': 0.83}
{'loss': 1.005, 'learning_rate': 1.754834628592084e-05, 'epoch': 0.83}
{'loss': 1.0898, 'learning_rate': 1.7545635279233687e-05, 'epoch': 0.83}
{'loss': 1.6099, 'learning_rate': 1.754292427254654e-05, 'epoch': 0.83}
{'loss': 0.9139, 'learning_rate': 1.754021326585939e-05, 'epoch': 0.83}
{'loss': 0.7761, 'learning_rate': 1.753750225917224e-05, 'epoch': 0.83}
{'loss': 0.9851, 'learning_rate': 1.753479125248509e-05, 'epoch': 0.83}
{'loss': 0.6468, 'learning_rate': 1.7532080245797943e-05, 'epoch': 0.83}
{'loss': 0.6085, 'learning_rate': 1.752936923911079e-05, 'epoch': 0.83}
{'loss': 1.5047, 'learning_rate': 1.752665823242364e-05, 'epoch': 0.83}
{'loss': 0.636, 'learning_rate': 1.7523947225736488e-05, 'epoch': 0.83}
{'loss': 1.3126, 'learning_rate': 1.752123621904934e-05, 'epoch': 0.83}
{'loss': 1.3003, 'learning_rate': 1.7518525212362192e-05, 'epoch': 0.83}
{'loss': 1.1036, 'learning_rate': 1.751581420567504e-05, 'epoch': 0.83}
{'loss': 0.7883, 'learning_rate': 1.7513103198987892e-05, 'epoch': 0.83}
{'loss': 0.8368, 'learning_rate': 1.7510392192300744e-05, 'epoch': 0.83}
{'loss': 1.2756, 'learning_rate': 1.7507681185613592e-05, 'epoch': 0.83}
{'loss': 0.6788, 'learning_rate': 1.750497017892644e-05, 'epoch': 0.83}
{'loss': 1.4481, 'learning_rate': 1.7502259172239293e-05, 'epoch': 0.83}
{'loss': 1.2022, 'learning_rate': 1.749954816555214e-05, 'epoch': 0.83}
{'loss': 0.7114, 'learning_rate': 1.7496837158864993e-05, 'epoch': 0.83}
{'loss': 0.9125, 'learning_rate': 1.749412615217784e-05, 'epoch': 0.83}

 42%|████▏     | 4614/11066 [16:54<23:59,  4.48it/s]
 42%|████▏     | 4615/11066 [16:54<24:01,  4.47it/s]
                                                    

 42%|████▏     | 4615/11066 [16:54<24:01,  4.47it/s]
 42%|████▏     | 4616/11066 [16:55<24:04,  4.47it/s]
                                                    

 42%|████▏     | 4616/11066 [16:55<24:04,  4.47it/s]
 42%|████▏     | 4617/11066 [16:55<24:03,  4.47it/s]
                                                    

 42%|████▏     | 4617/11066 [16:55<24:03,  4.47it/s]
 42%|████▏     | 4618/11066 [16:55<24:01,  4.47it/s]
                                                    

 42%|████▏     | 4618/11066 [16:55<24:01,  4.47it/s]
 42%|████▏     | 4619/11066 [16:55<23:57,  4.49it/s]
                                                    

 42%|████▏     | 4619/11066 [16:55<23:57,  4.49it/s]
 42%|████▏     | 4620/11066 [16:55<23:55,  4.49it/s]
                                                    

 42%|████▏     | 4620/11066 [16:55<23:55,  4.49it/s]
 42%|████▏     | 4621/11066 [16:56<23:53,  4.49it/s]
                                                    

 42%|████▏     | 4621/11066 [16:56<23:53,  4.49it/s]
 42%|████▏     | 4622/11066 [16:56<23:52,  4.50it/s]
                                                    

 42%|████▏     | 4622/11066 [16:56<23:52,  4.50it/s]
 42%|████▏     | 4623/11066 [16:56<23:48,  4.51it/s]
                                                    

 42%|████▏     | 4623/11066 [16:56<23:48,  4.51it/s]
 42%|████▏     | 4624/11066 [16:56<23:50,  4.50it/s]
                                                    

 42%|████▏     | 4624/11066 [16:56<23:50,  4.50it/s]
 42%|████▏     | 4625/11066 [16:57<23:41,  4.53it/s]
                                                    

 42%|████▏     | 4625/11066 [16:57<23:41,  4.53it/s]
 42%|████▏     | 4626/11066 [16:57<23:50,  4.50it/s]
                                                    

 42%|████▏     | 4626/11066 [16:57<23:50,  4.50it/s]
 42%|████▏     | 4627/11066 [16:57<23:54,  4.49it/s]
                                                    

 42%|████▏     | 4627/11066 [16:57<23:54,  4.49it/s]
 42%|████▏     | 4628/11066 [16:57<23:53,  4.49it/s]
                                                    

 42%|████▏     | 4628/11066 [16:57<23:53,  4.49it/s]
 42%|████▏     | 4629/11066 [16:57<23:53,  4.49it/s]
                                                    

 42%|████▏     | 4629/11066 [16:57<23:53,  4.49it/s]
 42%|████▏     | 4630/11066 [16:58<23:52,  4.49it/s]
                                                    

 42%|████▏     | 4630/11066 [16:58<23:52,  4.49it/s]
 42%|████▏     | 4631/11066 [16:58<23:40,  4.53it/s]
                                                    

 42%|████▏     | 4631/11066 [16:58<23:40,  4.53it/s]
 42%|████▏     | 4632/11066 [16:58<23:31,  4.56it/s]
                                                    

 42%|████▏     | 4632/11066 [16:58<23:31,  4.56it/s]
 42%|████▏     | 4633/11066 [16:58<23:38,  4.54it/s]
                                                    

 42%|████▏     | 4633/11066 [16:58<23:38,  4.54it/s]
 42%|████▏     | 4634/11066 [16:58<23:42,  4.52it/s]
                                                    

 42%|████▏     | 4634/11066 [16:58<23:42,  4.52it/s]
 42%|████▏     | 4635/11066 [16:59<23:43,  4.52it/s]
                                                    

 42%|████▏     | 4635/11066 [16:59<23:43,  4.52it/s]
 42%|████▏     | 4636/11066 [16:59<23:32,  4.55it/s]
                                                    

 42%|████▏     | 4636/11066 [16:59<23:32,  4.55it/s]
 42%|████▏     | 4637/11066 [16:59<23:42,  4.52it/s]
                                                    

 42%|████▏     | 4637/11066 [16:59<23:42,  4.52it/s]
 42%|████▏     | 4638/11066 [16:59<23:46,  4.51it/s]
                                                    

 42%|████▏     | 4638/11066 [16:59<23:46,  4.51it/s]
 42%|████▏     | 4639/11066 [17:00<23:49,  4.50it/s]
                                                    

 42%|████▏     | 4639/11066 [17:00<23:49,  4.50it/s]
 42%|████▏     | 4640/11066 [17:00<23:53,  4.48it/s]
                                                    

 42%|████▏     | 4640/11066 [17:00<23:53,  4.48it/s]
 42%|████▏     | 4641/11066 [17:00<23:26,  4.57it/s]
                                                    

 42%|████▏     | 4641/11066 [17:00<23:26,  4.57it/s]
 42%|████▏     | 4642/11066 [17:00<23:25,  4.57it/s]
                                                    

 42%|████▏     | 4642/11066 [17:00<23:25,  4.57it/s]
 42%|████▏     | 4643/11066 [17:00<23:36,  4.53it/s]
                                                    

 42%|████▏     | 4643/11066 [17:00<23:36,  4.53it/s]
 42%|████▏     | 4644/11066 [17:01<23:43,  4.51it/s]
                                                    

 42%|████▏     | 4644/11066 [17:01<23:43,  4.51it/s]
 42%|████▏     | 4645/11066 [17:01<23:45,  4.51it/s]
                                                    

 42%|████▏     | 4645/11066 [17:01<23:45,  4.51it/s]
 42%|████▏     | 4646/11066 [17:01<23:44,  4.51it/s]
                                                    

 42%|████▏     | 4646/11066 [17:01<23:44,  4.51it/s]
 42%|████▏     | 4647/11066 [17:01<23:34,  4.54it/s]
                                                    

 42%|████▏     | 4647/11066 [17:01<23:34,  4.54it/s]
 42%|████▏     | 4648/11066 [17:02<23:13,  4.61it/s]
                                                    

 42%|████▏     | 4648/11066 [17:02<23:13,  4.61it/s]
 42%|████▏     | 4649/11066 [17:02<23:03,  4.64it/s]
                                                    

 42%|████▏     | 4649/11066 [17:02<23:03,  4.64it/s]
 42%|████▏     | 4650/11066 [17:02<22:50,  4.68it/s]
                                                    

 42%|████▏     | 4650/11066 [17:02<22:50,  4.68it/s]
 42%|████▏     | 4651/11066 [17:02<23:08,  4.62it/s]
                                                    

 42%|████▏     | 4651/11066 [17:02<23:08,  4.62it/s]
 42%|████▏     | 4652/11066 [17:02<23:09,  4.61it/s]
                                                    

 42%|████▏     | 4652/11066 [17:02<23:09,  4.61it/s]
 42%|████▏     | 4653/11066 [17:03<23:04,  4.63it/s]
                                                    

 42%|████▏     | 4653/11066 [17:03<23:04,  4.63it/s]
 42%|████▏     | 4654/11066 [17:03<23:15,  4.60it/s]
                                                    

 42%|████▏     | 4654/11066 [17:03<23:15,  4.60it/s]
 42%|████▏     | 4655/11066 [17:03<23:31,  4.54it/s]
                                                    

 42%|████▏     | 4655/11066 [17:03<23:31,  4.54it/s]
 42%|████▏     | 4656/11066 [17:03<23:18,  4.58it/s]
                                                    

 42%|████▏     | 4656/11066 [17:03<23:18,  4.58it/s]
 42%|████▏     | 4657/11066 [17:04<23:16,  4.59it/s]
                                                    

 42%|████▏     | 4657/11066 [17:04<23:16,  4.59it/s]
 42%|████▏     | 4658/11066 [17:04<23:15,  4.59it/s]
                                                    

 42%|████▏     | 4658/11066 [17:04<23:15,  4.59it/s]
 42%|████▏     | 4659/11066 [17:04<23:05,  4.62it/s]
                                                    

 42%|████▏     | 4659/11066 [17:04<23:05,  4.62it/s]
 42%|████▏     | 4660/11066 [17:04<22:58,  4.65it/s]
                                                    

 42%|████▏     | 4660/11066 [17:04<22:58,  4.65it/s]
 42%|████▏     | 4661/11066 [17:04<22:51,  4.67it/s]
                                                    

 42%|████▏     | 4661/11066 [17:04<22:51,  4.67it/s]
 42%|████▏     | 4662/11066 [17:05<22:55,  4.65it/s]
                                                    

 42%|████▏     | 4662/11066 [17:05<22:55,  4.65it/s]
 42%|████▏     | 4663/11066 [17:05<23:00,  4.64it/s]
                                                    

 42%|████▏     | 4663/11066 [17:05<23:00,  4.64it/s]
 42%|████▏     | 4664/11066 [17:05<22:54,  4.66it/s]
                                                    

 42%|████▏     | 4664/11066 [17:05<22:54,  4.66it/s]
 42%|████▏     | 4665/11066 [17:05<22:58,  4.64it/s]
                                                    

 42%|████▏     | 4665/11066 [17:05<22:58,  4.64it/s]
 42%|████▏     | 4666/11066 [17:05<22:48,  4.68it/s]
                                                    

 42%|████▏     | 4666/11066 [17:05<22:48,  4.68it/s]
 42%|████▏     | 4667/11066 [17:06<22:46,  4.68it/s]
                                                    

 42%|████▏     | 4667/11066 [17:06<22:46,  4.68it/s]
 42%|████▏     | 4668/11066 [17:06<22:37,  4.71it/s]
                                                    

 42%|████▏     | 4668/11066 [17:06<22:37,  4.71it/s]
 42%|████▏     | 4669/11066 [17:06<22:59,  4.64it/s]
                                                    

 42%|████▏     | 4669/11066 [17:06<22:59,  4.64it/s]
 42%|████▏     | 4670/11066 [17:06<22:54,  4.65it/s]
                                                    

 42%|████▏     | 4670/11066 [17:06<22:54,  4.65it/s]
 42%|████▏     | 4671/11066 [17:07<23:00,  4.63it/s]
                                                    

 42%|████▏     | 4671/11066 [17:07<23:00,  4.63it/s]
 42%|████▏     | 4672/11066 [17:07<23:15,  4.58it/s]
                                                    

 42%|████▏     | 4672/11066 [17:07<23:15,  4.58it/s]
 42%|████▏     | 4673/11066 [17:07<23:04,  4.62it/s]
                                                    

 42%|████▏     | 4673/11066 [17:07<23:04,  4.62it/s]
 42%|████▏     | 4674/11066 [17:07<22:56,  4.64it/s]
                                                    

 42%|████▏     | 4674/11066 [17:07<22:56,  4.64it/s]
 42%|████▏     | 4675/11066 [17:07<22:51,  4.66it/s]
                                                    

 42%|████▏     | 4675/11066 [17:07<22:51,  4.66it/s]
 42%|████▏     | 4676/11066 [17:08<22:48,  4.67it/s]
                                                    

 42%|████▏     | 4676/11066 [17:08<22:48,  4.67it/s]
 42%|████▏     | 4677/11066 [17:08<22:44,  4.68it/s]
                                                    

 42%|████▏     | 4677/11066 [17:08<22:44,  4.68it/s]
 42%|████▏     | 4678/11066 [17:08<22:40,  4.70it/s]
                                                    

 42%|████▏     | 4678/11066 [17:08<22:40,  4.70it/s]
 42%|████▏     | 4679/11066 [17:08<22:49,  4.66it/s]
                                                    

 42%|████▏     | 4679/11066 [17:08<22:49,  4.66it/s]
 42%|████▏     | 4680/11066 [17:08<22:50,  4.66it/s]
                                                    

 42%|████▏     | 4680/11066 [17:08<22:50,  4.66it/s]
 42%|████▏     | 4681/11066 [17:09<22:56,  4.64it/s]
                                                    

 42%|████▏     | 4681/11066 [17:09<22:56,  4.64it/s]
 42%|████▏     | 4682/11066 [17:09<22:43,  4.68it/s]
                                                    

 42%|████▏     | 4682/11066 [17:09<22:43,  4.68it/s]
 42%|████▏     | 4683/11066 [17:09<22:45,  4.67it/s]
                                                    

 42%|████▏     | 4683/11066 [17:09<22:45,  4.67it/s]
 42%|████▏     | 4684/11066 [17:09<22:37,  4.70it/s]
                                                    

 42%|████▏     | 4684/11066 [17:09<22:37,  4.70it/s]
 42%|████▏     | 4685/11066 [17:10<23:00,  4.62it/s]
                                                    

 42%|████▏     | 4685/11066 [17:10<23:00,  4.62it/s]
 42%|████▏     | 4686/11066 [17:10<22:45,  4.67it/s]
                                                    

 42%|████▏     | 4686/11066 [17:10<22:45,  4.67it/s]
 42%|████▏     | 4687/11066 [17:10<23:04,  4.61it/s]
                                                    

 42%|████▏     | 4687/11066 [17:10<23:04,  4.61it/s]
 42%|████▏     | 4688/11066 [17:10<23:15,  4.57it/s]
                                                    

 42%|████▏     | 4688/11066 [17:10<23:15,  4.57it/s]
 42%|████▏     | 4689/11066 [17:10<23:11,  4.58it/s]
                                                    

 42%|████▏     | 4689/11066 [17:10<23:11,  4.58it/s]
 42%|████▏     | 4690/11066 [17:11<22:58,  4.63it/s]
                                                    

 42%|████▏     | 4690/11066 [17:11<22:58,  4.63it/s]
 42%|████▏     | 4691/11066 [17:11<22:56,  4.63it/s]
                                                    

 42%|████▏     | 4691/11066 [17:11<22:56,  4.63it/s]
 42%|████▏     | 4692/11066 [17:11<22:57,  4.63it/s]
                                                    

 42%|████▏     | 4692/11066 [17:11<22:57,  4.63it/s]
 42%|████▏     | 4693/11066 [17:11<22:45,  4.67it/s]
                                                    

 42%|████▏     | 4693/11066 [17:11<22:45,  4.67it/s]
 42%|████▏     | 4694/11066 [17:11<22:34,  4.71it/s]
                                                    

 42%|████▏     | 4694/11066 [17:11<22:34,  4.71it/s]
 42%|████▏     | 4695/11066 [17:12<22:43,  4.67it/s]
                                                    

 42%|████▏     | 4695/11066 [17:12<22:43,  4.67it/s]
 42%|████▏     | 4696/11066 [17:12<22:53,  4.64it/s]
                                                    

 42%|████▏     | 4696/11066 [17:12<22:53,  4.64it/s]
 42%|████▏     | 4697/11066 [17:12<22:45,  4.67it/s]
                                                    

 42%|████▏     | 4697/11066 [17:12<22:45,  4.67it/s]
 42%|████▏     | 4698/11066 [17:12<23:07,  4.59it/s]
                                                    

 42%|████▏     | 4698/11066 [17:12<23:07,  4.59it/s]
 42%|████▏     | 4699/11066 [17:13<23:23,  4.54it/s]
                                                    

 42%|████▏     | 4699/11066 [17:13<23:23,  4.54it/s]
 42%|████▏     | 4700/11066 [17:13<23:50,  4.45it/s]
                                                    

 42%|████▏     | 4700/11066 [17:13<23:50,  4.45it/s]
 42%|████▏     | 4701/11066 [17:13<23:30,  4.51it/s]
                                                    

 42%|████▏     | 4701/11066 [17:13<23:30,  4.51it/s]
 42%|████▏     | 4702/11066 [17:13<23:30,  4.51it/s]
                                                    

 42%|████▏     | 4702/11066 [17:13<23:30,  4.51it/s]
 42%|████▏     | 4703/11066 [17:13<23:32,  4.50it/s]
                                                    

 42%|████▏     | 4703/11066 [17:13<23:32,  4.50it/s]
 43%|████▎     | 4704/11066 [17:14<23:32,  4.50it/s]
                                                    

 43%|████▎     | 4704/11066 [17:14<23:32,  4.50it/s]
 43%|████▎     | 4705/11066 [17:14<23:31,  4.51it/s]
                                                    

 43%|████▎     | 4705/11066 [17:14<23:31,  4.51it/s]
 43%|████▎     | 4706/11066 [17:14<23:20,  4.54it/s]
                                                    

 43%|████▎     | 4706/11066 [17:14<23:20,  4.54it/s]
 43%|████▎     | 4707/11066 [17:14<23:19,  4.54it/s]
                                                    

 43%|████▎     | 4707/11066 [17:14<23:19,  4.54it/s]
 43%|████▎     | 4708/11066 [17:15<23:25,  4.52it/s]
                                                    

 43%|████▎     | 4708/11066 [17:15<23:25,  4.52it/s]
 43%|████▎     | 4709/11066 [17:15<23:34,  4.49it/s]
                                                    

 43%|████▎     | 4709/11066 [17:15<23:34,  4.49it/s]
 43%|████▎     | 4710/11066 [17:15<23:37,  4.48it/s]
                                                    

 43%|████▎     | 4710/11066 [17:15<23:37,  4.48it/s]
 43%|████▎     | 4711/11066 [17:15<23:22,  4.53it/s]
                                                    

 43%|████▎     | 4711/11066 [17:15<23:22,  4.53it/s]
 43%|████▎     | 4712/11066 [17:15<23:16,  4.55it/s]
                                                    

 43%|████▎     | 4712/11066 [17:15<23:16,  4.55it/s]
 43%|████▎     | 4713/11066 [17:16<23:24,  4.52it/s]
                                                    

 43%|████▎     | 4713/11066 [17:16<23:24,  4.52it/s]
 43%|████▎     | 4714/11066 [17:16<23:13,  4.56it/s]
                                                    

 43%|████▎     | 4714/11066 [17:16<23:13,  4.56it/s]
 43%|████▎     | 4715/11066 [17:16<23:19,  4.54it/s]
                                                    

 43%|████▎     | 4715/11066 [17:16<23:19,  4.54it/s]
 43%|████▎     | 4716/11066 [17:16<23:00,  4.60it/s]
                                                    

 43%|████▎     | 4716/11066 [17:16<23:00,  4.60it/s]
 43%|████▎     | 4717/11066 [17:17<23:11,  4.56it/s]
                                                    

 43%|████▎     | 4717/11066 [17:17<23:11,  4.56it/s]
 43%|████▎     | 4718/11066 [17:17<23:10,  4.56it/s]
                                                    

 43%|████▎     | 4718/11066 [17:17<23:10,  4.56it/s]
 43%|████▎     | 4719/11066 [17:17<23:16,  4.54it/s]
                                                    

 43%|████▎     | 4719/11066 [17:17<23:16,  4.54it/s]
 43%|████▎     | 4720/11066 [17:17<23:21,  4.53it/s]
                                                    

 43%|████▎     | 4720/11066 [17:17<23:21,  4.53it/s]
 43%|████▎     | 4721/11066 [17:17<23:23,  4.52it/s]
                                                    

 43%|████▎     | 4721/11066 [17:17<23:23,  4.52it/s]
 43%|████▎     | 4722/11066 [17:18<23:25,  4.52it/s]
                                                    

 43%|████▎     | 4722/11066 [17:18<23:25,  4.52it/s]
 43%|████▎     | 4723/11066 [17:18<23:26,  4.51it/s]
                                                    

 43%|████▎     | 4723/11066 [17:18<23:26,  4.51it/s]
 43%|████▎     | 4724/11066 [17:18<23:09,  4.56it/s]
                                                    

 43%|████▎     | 4724/11066 [17:18<23:09,  4.56it/s]
 43%|████▎     | 4725/11066 [17:18<23:08,  4.57it/s]
                                                    

 43%|████▎     | 4725/11066 [17:18<23:08,  4.57it/s]
 43%|████▎     | 4726/11066 [17:19<23:21,  4.52it/s]
                                                    

 43%|████▎     | 4726/11066 [17:19<23:21,  4.52it/s]
 43%|████▎     | 4727/11066 [17:19<23:25,  4.51it/s]
                                                    
{'loss': 0.8512, 'learning_rate': 1.7491415145490693e-05, 'epoch': 0.83}
{'loss': 1.3416, 'learning_rate': 1.7488704138803545e-05, 'epoch': 0.83}
{'loss': 1.4536, 'learning_rate': 1.7485993132116393e-05, 'epoch': 0.83}
{'loss': 0.9174, 'learning_rate': 1.7483282125429242e-05, 'epoch': 0.83}
{'loss': 0.9589, 'learning_rate': 1.7480571118742094e-05, 'epoch': 0.83}
{'loss': 1.4604, 'learning_rate': 1.7477860112054942e-05, 'epoch': 0.83}
{'loss': 1.9218, 'learning_rate': 1.7475149105367794e-05, 'epoch': 0.83}
{'loss': 1.0021, 'learning_rate': 1.7472438098680646e-05, 'epoch': 0.84}
{'loss': 1.3787, 'learning_rate': 1.7469727091993494e-05, 'epoch': 0.84}
{'loss': 0.5256, 'learning_rate': 1.7467016085306346e-05, 'epoch': 0.84}
{'loss': 1.5687, 'learning_rate': 1.7464305078619194e-05, 'epoch': 0.84}
{'loss': 1.1185, 'learning_rate': 1.7461594071932043e-05, 'epoch': 0.84}
{'loss': 1.241, 'learning_rate': 1.7458883065244895e-05, 'epoch': 0.84}
{'loss': 0.848, 'learning_rate': 1.7456172058557743e-05, 'epoch': 0.84}
{'loss': 0.9042, 'learning_rate': 1.7453461051870595e-05, 'epoch': 0.84}
{'loss': 1.4105, 'learning_rate': 1.7450750045183447e-05, 'epoch': 0.84}
{'loss': 0.9124, 'learning_rate': 1.7448039038496295e-05, 'epoch': 0.84}
{'loss': 1.1391, 'learning_rate': 1.7445328031809147e-05, 'epoch': 0.84}
{'loss': 1.213, 'learning_rate': 1.7442617025122e-05, 'epoch': 0.84}
{'loss': 0.7524, 'learning_rate': 1.7439906018434844e-05, 'epoch': 0.84}
{'loss': 1.1746, 'learning_rate': 1.7437195011747696e-05, 'epoch': 0.84}
{'loss': 0.4376, 'learning_rate': 1.7434484005060544e-05, 'epoch': 0.84}
{'loss': 1.1607, 'learning_rate': 1.7431772998373396e-05, 'epoch': 0.84}
{'loss': 0.6289, 'learning_rate': 1.7429061991686248e-05, 'epoch': 0.84}
{'loss': 1.1885, 'learning_rate': 1.7426350984999096e-05, 'epoch': 0.84}
{'loss': 0.8244, 'learning_rate': 1.7423639978311948e-05, 'epoch': 0.84}
{'loss': 1.3661, 'learning_rate': 1.7420928971624797e-05, 'epoch': 0.84}
{'loss': 1.1229, 'learning_rate': 1.7418217964937645e-05, 'epoch': 0.84}
{'loss': 1.6224, 'learning_rate': 1.7415506958250497e-05, 'epoch': 0.84}
{'loss': 0.9307, 'learning_rate': 1.741279595156335e-05, 'epoch': 0.84}
{'loss': 1.1467, 'learning_rate': 1.7410084944876197e-05, 'epoch': 0.84}
{'loss': 1.0854, 'learning_rate': 1.740737393818905e-05, 'epoch': 0.84}
{'loss': 0.84, 'learning_rate': 1.7404662931501897e-05, 'epoch': 0.84}
{'loss': 0.9103, 'learning_rate': 1.740195192481475e-05, 'epoch': 0.84}
{'loss': 0.9581, 'learning_rate': 1.7399240918127598e-05, 'epoch': 0.84}
{'loss': 1.0502, 'learning_rate': 1.7396529911440446e-05, 'epoch': 0.84}
{'loss': 0.8749, 'learning_rate': 1.7393818904753298e-05, 'epoch': 0.84}
{'loss': 1.5861, 'learning_rate': 1.739110789806615e-05, 'epoch': 0.84}
{'loss': 1.4079, 'learning_rate': 1.7388396891378998e-05, 'epoch': 0.84}
{'loss': 1.3503, 'learning_rate': 1.738568588469185e-05, 'epoch': 0.84}
{'loss': 0.5297, 'learning_rate': 1.7382974878004702e-05, 'epoch': 0.84}
{'loss': 1.0633, 'learning_rate': 1.738026387131755e-05, 'epoch': 0.84}
{'loss': 1.0931, 'learning_rate': 1.73775528646304e-05, 'epoch': 0.84}
{'loss': 0.8989, 'learning_rate': 1.7374841857943247e-05, 'epoch': 0.84}
{'loss': 0.5541, 'learning_rate': 1.73721308512561e-05, 'epoch': 0.84}
{'loss': 1.65, 'learning_rate': 1.736941984456895e-05, 'epoch': 0.84}
{'loss': 0.7601, 'learning_rate': 1.73667088378818e-05, 'epoch': 0.84}
{'loss': 1.0323, 'learning_rate': 1.736399783119465e-05, 'epoch': 0.84}
{'loss': 1.4239, 'learning_rate': 1.7361286824507503e-05, 'epoch': 0.84}
{'loss': 1.0541, 'learning_rate': 1.735857581782035e-05, 'epoch': 0.84}
{'loss': 1.6723, 'learning_rate': 1.73558648111332e-05, 'epoch': 0.84}
{'loss': 1.0245, 'learning_rate': 1.735315380444605e-05, 'epoch': 0.84}
{'loss': 0.6822, 'learning_rate': 1.73504427977589e-05, 'epoch': 0.84}
{'loss': 1.3602, 'learning_rate': 1.7347731791071752e-05, 'epoch': 0.84}
{'loss': 1.0967, 'learning_rate': 1.73450207843846e-05, 'epoch': 0.84}
{'loss': 0.7576, 'learning_rate': 1.7342309777697452e-05, 'epoch': 0.84}
{'loss': 1.3642, 'learning_rate': 1.7339598771010304e-05, 'epoch': 0.84}
{'loss': 1.0377, 'learning_rate': 1.7336887764323152e-05, 'epoch': 0.84}
{'loss': 0.6459, 'learning_rate': 1.7334176757636e-05, 'epoch': 0.84}
{'loss': 0.6122, 'learning_rate': 1.7331465750948853e-05, 'epoch': 0.84}
{'loss': 1.1022, 'learning_rate': 1.73287547442617e-05, 'epoch': 0.84}
{'loss': 1.2358, 'learning_rate': 1.7326043737574553e-05, 'epoch': 0.84}
{'loss': 0.6083, 'learning_rate': 1.7323332730887405e-05, 'epoch': 0.85}
{'loss': 0.3541, 'learning_rate': 1.7320621724200253e-05, 'epoch': 0.85}
{'loss': 0.7101, 'learning_rate': 1.7317910717513105e-05, 'epoch': 0.85}
{'loss': 1.2578, 'learning_rate': 1.7315199710825954e-05, 'epoch': 0.85}
{'loss': 0.7378, 'learning_rate': 1.7312488704138802e-05, 'epoch': 0.85}
{'loss': 1.7323, 'learning_rate': 1.7309777697451654e-05, 'epoch': 0.85}
{'loss': 1.116, 'learning_rate': 1.7307066690764502e-05, 'epoch': 0.85}
{'loss': 1.0687, 'learning_rate': 1.7304355684077354e-05, 'epoch': 0.85}
{'loss': 0.6903, 'learning_rate': 1.7301644677390206e-05, 'epoch': 0.85}
{'loss': 1.7352, 'learning_rate': 1.7298933670703054e-05, 'epoch': 0.85}
{'loss': 1.1499, 'learning_rate': 1.7296222664015906e-05, 'epoch': 0.85}
{'loss': 1.494, 'learning_rate': 1.7293511657328758e-05, 'epoch': 0.85}
{'loss': 1.1009, 'learning_rate': 1.7290800650641603e-05, 'epoch': 0.85}
{'loss': 1.0635, 'learning_rate': 1.7288089643954455e-05, 'epoch': 0.85}
{'loss': 1.5619, 'learning_rate': 1.7285378637267307e-05, 'epoch': 0.85}
{'loss': 1.3291, 'learning_rate': 1.7282667630580155e-05, 'epoch': 0.85}
{'loss': 0.6858, 'learning_rate': 1.7279956623893007e-05, 'epoch': 0.85}
{'loss': 1.765, 'learning_rate': 1.7277245617205855e-05, 'epoch': 0.85}
{'loss': 1.8316, 'learning_rate': 1.7274534610518707e-05, 'epoch': 0.85}
{'loss': 0.8618, 'learning_rate': 1.727182360383156e-05, 'epoch': 0.85}
{'loss': 0.8818, 'learning_rate': 1.7269112597144404e-05, 'epoch': 0.85}
{'loss': 0.7021, 'learning_rate': 1.7266401590457256e-05, 'epoch': 0.85}
{'loss': 0.7633, 'learning_rate': 1.7263690583770108e-05, 'epoch': 0.85}
{'loss': 0.7513, 'learning_rate': 1.7260979577082956e-05, 'epoch': 0.85}
{'loss': 0.5514, 'learning_rate': 1.7258268570395808e-05, 'epoch': 0.85}
{'loss': 0.8506, 'learning_rate': 1.725555756370866e-05, 'epoch': 0.85}
{'loss': 0.9183, 'learning_rate': 1.7252846557021508e-05, 'epoch': 0.85}
{'loss': 0.6893, 'learning_rate': 1.725013555033436e-05, 'epoch': 0.85}
{'loss': 1.3491, 'learning_rate': 1.7247424543647205e-05, 'epoch': 0.85}
{'loss': 0.8916, 'learning_rate': 1.7244713536960057e-05, 'epoch': 0.85}
{'loss': 0.8347, 'learning_rate': 1.724200253027291e-05, 'epoch': 0.85}
{'loss': 1.0367, 'learning_rate': 1.7239291523585757e-05, 'epoch': 0.85}
{'loss': 1.1317, 'learning_rate': 1.723658051689861e-05, 'epoch': 0.85}
{'loss': 0.9048, 'learning_rate': 1.723386951021146e-05, 'epoch': 0.85}
{'loss': 1.8, 'learning_rate': 1.723115850352431e-05, 'epoch': 0.85}
{'loss': 1.6862, 'learning_rate': 1.722844749683716e-05, 'epoch': 0.85}
{'loss': 0.9499, 'learning_rate': 1.722573649015001e-05, 'epoch': 0.85}
{'loss': 1.1415, 'learning_rate': 1.7223025483462858e-05, 'epoch': 0.85}
{'loss': 1.0226, 'learning_rate': 1.722031447677571e-05, 'epoch': 0.85}
{'loss': 0.8851, 'learning_rate': 1.721760347008856e-05, 'epoch': 0.85}
{'loss': 0.7617, 'learning_rate': 1.721489246340141e-05, 'epoch': 0.85}
{'loss': 1.0254, 'learning_rate': 1.7212181456714262e-05, 'epoch': 0.85}
{'loss': 1.219, 'learning_rate': 1.720947045002711e-05, 'epoch': 0.85}
{'loss': 0.8698, 'learning_rate': 1.7206759443339962e-05, 'epoch': 0.85}
{'loss': 0.8, 'learning_rate': 1.720404843665281e-05, 'epoch': 0.85}
{'loss': 0.9874, 'learning_rate': 1.720133742996566e-05, 'epoch': 0.85}
{'loss': 0.6884, 'learning_rate': 1.719862642327851e-05, 'epoch': 0.85}
{'loss': 1.1494, 'learning_rate': 1.7195915416591363e-05, 'epoch': 0.85}
{'loss': 0.6089, 'learning_rate': 1.719320440990421e-05, 'epoch': 0.85}
{'loss': 1.2596, 'learning_rate': 1.7190493403217063e-05, 'epoch': 0.85}
{'loss': 0.8194, 'learning_rate': 1.718778239652991e-05, 'epoch': 0.85}

 43%|████▎     | 4727/11066 [17:19<23:25,  4.51it/s]
 43%|████▎     | 4728/11066 [17:19<23:25,  4.51it/s]
                                                    

 43%|████▎     | 4728/11066 [17:19<23:25,  4.51it/s]
 43%|████▎     | 4729/11066 [17:19<23:26,  4.50it/s]
                                                    

 43%|████▎     | 4729/11066 [17:19<23:26,  4.50it/s]
 43%|████▎     | 4730/11066 [17:19<23:27,  4.50it/s]
                                                    

 43%|████▎     | 4730/11066 [17:19<23:27,  4.50it/s]
 43%|████▎     | 4731/11066 [17:20<23:28,  4.50it/s]
                                                    

 43%|████▎     | 4731/11066 [17:20<23:28,  4.50it/s]
 43%|████▎     | 4732/11066 [17:20<23:20,  4.52it/s]
                                                    

 43%|████▎     | 4732/11066 [17:20<23:20,  4.52it/s]
 43%|████▎     | 4733/11066 [17:20<23:04,  4.57it/s]
                                                    

 43%|████▎     | 4733/11066 [17:20<23:04,  4.57it/s]
 43%|████▎     | 4734/11066 [17:20<23:15,  4.54it/s]
                                                    

 43%|████▎     | 4734/11066 [17:20<23:15,  4.54it/s]
 43%|████▎     | 4735/11066 [17:21<23:09,  4.56it/s]
                                                    

 43%|████▎     | 4735/11066 [17:21<23:09,  4.56it/s]
 43%|████▎     | 4736/11066 [17:21<23:18,  4.53it/s]
                                                    

 43%|████▎     | 4736/11066 [17:21<23:18,  4.53it/s]
 43%|████▎     | 4737/11066 [17:21<23:13,  4.54it/s]
                                                    

 43%|████▎     | 4737/11066 [17:21<23:13,  4.54it/s]
 43%|████▎     | 4738/11066 [17:21<22:59,  4.59it/s]
                                                    

 43%|████▎     | 4738/11066 [17:21<22:59,  4.59it/s]
 43%|████▎     | 4739/11066 [17:21<23:11,  4.55it/s]
                                                    

 43%|████▎     | 4739/11066 [17:21<23:11,  4.55it/s]
 43%|████▎     | 4740/11066 [17:22<23:22,  4.51it/s]
                                                    

 43%|████▎     | 4740/11066 [17:22<23:22,  4.51it/s]
 43%|████▎     | 4741/11066 [17:22<23:24,  4.50it/s]
                                                    

 43%|████▎     | 4741/11066 [17:22<23:24,  4.50it/s]
 43%|████▎     | 4742/11066 [17:22<23:25,  4.50it/s]
                                                    

 43%|████▎     | 4742/11066 [17:22<23:25,  4.50it/s]
 43%|████▎     | 4743/11066 [17:22<23:16,  4.53it/s]
                                                    

 43%|████▎     | 4743/11066 [17:22<23:16,  4.53it/s]
 43%|████▎     | 4744/11066 [17:23<23:03,  4.57it/s]
                                                    

 43%|████▎     | 4744/11066 [17:23<23:03,  4.57it/s]
 43%|████▎     | 4745/11066 [17:23<23:13,  4.54it/s]
                                                    

 43%|████▎     | 4745/11066 [17:23<23:13,  4.54it/s]
 43%|████▎     | 4746/11066 [17:23<23:19,  4.52it/s]
                                                    

 43%|████▎     | 4746/11066 [17:23<23:19,  4.52it/s]
 43%|████▎     | 4747/11066 [17:23<23:20,  4.51it/s]
                                                    

 43%|████▎     | 4747/11066 [17:23<23:20,  4.51it/s]
 43%|████▎     | 4748/11066 [17:23<23:22,  4.51it/s]
                                                    

 43%|████▎     | 4748/11066 [17:23<23:22,  4.51it/s]
 43%|████▎     | 4749/11066 [17:24<23:21,  4.51it/s]
                                                    

 43%|████▎     | 4749/11066 [17:24<23:21,  4.51it/s]
 43%|████▎     | 4750/11066 [17:24<23:05,  4.56it/s]
                                                    

 43%|████▎     | 4750/11066 [17:24<23:05,  4.56it/s]
 43%|████▎     | 4751/11066 [17:24<22:53,  4.60it/s]
                                                    

 43%|████▎     | 4751/11066 [17:24<22:53,  4.60it/s]
 43%|████▎     | 4752/11066 [17:24<22:36,  4.65it/s]
                                                    

 43%|████▎     | 4752/11066 [17:24<22:36,  4.65it/s]
 43%|████▎     | 4753/11066 [17:24<22:52,  4.60it/s]
                                                    

 43%|████▎     | 4753/11066 [17:24<22:52,  4.60it/s]
 43%|████▎     | 4754/11066 [17:25<23:03,  4.56it/s]
                                                    

 43%|████▎     | 4754/11066 [17:25<23:03,  4.56it/s]
 43%|████▎     | 4755/11066 [17:25<22:54,  4.59it/s]
                                                    

 43%|████▎     | 4755/11066 [17:25<22:54,  4.59it/s]
 43%|████▎     | 4756/11066 [17:25<22:38,  4.64it/s]
                                                    

 43%|████▎     | 4756/11066 [17:25<22:38,  4.64it/s]
 43%|████▎     | 4757/11066 [17:25<22:42,  4.63it/s]
                                                    

 43%|████▎     | 4757/11066 [17:25<22:42,  4.63it/s]
 43%|████▎     | 4758/11066 [17:26<22:56,  4.58it/s]
                                                    

 43%|████▎     | 4758/11066 [17:26<22:56,  4.58it/s]
 43%|████▎     | 4759/11066 [17:26<23:04,  4.56it/s]
                                                    

 43%|████▎     | 4759/11066 [17:26<23:04,  4.56it/s]
 43%|████▎     | 4760/11066 [17:26<22:59,  4.57it/s]
                                                    

 43%|████▎     | 4760/11066 [17:26<22:59,  4.57it/s]
 43%|████▎     | 4761/11066 [17:26<22:43,  4.62it/s]
                                                    

 43%|████▎     | 4761/11066 [17:26<22:43,  4.62it/s]
 43%|████▎     | 4762/11066 [17:26<22:55,  4.58it/s]
                                                    

 43%|████▎     | 4762/11066 [17:26<22:55,  4.58it/s]
 43%|████▎     | 4763/11066 [17:27<23:09,  4.54it/s]
                                                    

 43%|████▎     | 4763/11066 [17:27<23:09,  4.54it/s]
 43%|████▎     | 4764/11066 [17:27<22:56,  4.58it/s]
                                                    

 43%|████▎     | 4764/11066 [17:27<22:56,  4.58it/s]
 43%|████▎     | 4765/11066 [17:27<22:54,  4.58it/s]
                                                    

 43%|████▎     | 4765/11066 [17:27<22:54,  4.58it/s]
 43%|████▎     | 4766/11066 [17:27<23:32,  4.46it/s]
                                                    

 43%|████▎     | 4766/11066 [17:27<23:32,  4.46it/s]
 43%|████▎     | 4767/11066 [17:28<23:30,  4.47it/s]
                                                    

 43%|████▎     | 4767/11066 [17:28<23:30,  4.47it/s]
 43%|████▎     | 4768/11066 [17:28<23:26,  4.48it/s]
                                                    

 43%|████▎     | 4768/11066 [17:28<23:26,  4.48it/s]
 43%|████▎     | 4769/11066 [17:28<23:24,  4.48it/s]
                                                    

 43%|████▎     | 4769/11066 [17:28<23:24,  4.48it/s]
 43%|████▎     | 4770/11066 [17:28<23:22,  4.49it/s]
                                                    

 43%|████▎     | 4770/11066 [17:28<23:22,  4.49it/s]
 43%|████▎     | 4771/11066 [17:28<23:22,  4.49it/s]
                                                    

 43%|████▎     | 4771/11066 [17:28<23:22,  4.49it/s]
 43%|████▎     | 4772/11066 [17:29<23:17,  4.50it/s]
                                                    

 43%|████▎     | 4772/11066 [17:29<23:17,  4.50it/s]
 43%|████▎     | 4773/11066 [17:29<23:02,  4.55it/s]
                                                    

 43%|████▎     | 4773/11066 [17:29<23:02,  4.55it/s]
 43%|████▎     | 4774/11066 [17:29<22:55,  4.58it/s]
                                                    

 43%|████▎     | 4774/11066 [17:29<22:55,  4.58it/s]
 43%|████▎     | 4775/11066 [17:29<22:39,  4.63it/s]
                                                    

 43%|████▎     | 4775/11066 [17:29<22:39,  4.63it/s]
 43%|████▎     | 4776/11066 [17:30<22:48,  4.60it/s]
                                                    

 43%|████▎     | 4776/11066 [17:30<22:48,  4.60it/s]
 43%|████▎     | 4777/11066 [17:30<22:36,  4.64it/s]
                                                    

 43%|████▎     | 4777/11066 [17:30<22:36,  4.64it/s]
 43%|████▎     | 4778/11066 [17:30<22:30,  4.66it/s]
                                                    

 43%|████▎     | 4778/11066 [17:30<22:30,  4.66it/s]
 43%|████▎     | 4779/11066 [17:30<22:25,  4.67it/s]
                                                    

 43%|████▎     | 4779/11066 [17:30<22:25,  4.67it/s]
 43%|████▎     | 4780/11066 [17:30<22:30,  4.65it/s]
                                                    

 43%|████▎     | 4780/11066 [17:30<22:30,  4.65it/s]
 43%|████▎     | 4781/11066 [17:31<22:49,  4.59it/s]
                                                    

 43%|████▎     | 4781/11066 [17:31<22:49,  4.59it/s]
 43%|████▎     | 4782/11066 [17:31<23:02,  4.55it/s]
                                                    

 43%|████▎     | 4782/11066 [17:31<23:02,  4.55it/s]
 43%|████▎     | 4783/11066 [17:31<22:48,  4.59it/s]
                                                    

 43%|████▎     | 4783/11066 [17:31<22:48,  4.59it/s]
 43%|████▎     | 4784/11066 [17:31<22:37,  4.63it/s]
                                                    

 43%|████▎     | 4784/11066 [17:31<22:37,  4.63it/s]
 43%|████▎     | 4785/11066 [17:31<22:29,  4.65it/s]
                                                    

 43%|████▎     | 4785/11066 [17:31<22:29,  4.65it/s]
 43%|████▎     | 4786/11066 [17:32<22:24,  4.67it/s]
                                                    

 43%|████▎     | 4786/11066 [17:32<22:24,  4.67it/s]
 43%|████▎     | 4787/11066 [17:32<22:20,  4.68it/s]
                                                    

 43%|████▎     | 4787/11066 [17:32<22:20,  4.68it/s]
 43%|████▎     | 4788/11066 [17:32<22:17,  4.69it/s]
                                                    

 43%|████▎     | 4788/11066 [17:32<22:17,  4.69it/s]
 43%|████▎     | 4789/11066 [17:32<22:35,  4.63it/s]
                                                    

 43%|████▎     | 4789/11066 [17:32<22:35,  4.63it/s]
 43%|████▎     | 4790/11066 [17:33<22:48,  4.59it/s]
                                                    

 43%|████▎     | 4790/11066 [17:33<22:48,  4.59it/s]
 43%|████▎     | 4791/11066 [17:33<22:56,  4.56it/s]
                                                    

 43%|████▎     | 4791/11066 [17:33<22:56,  4.56it/s]
 43%|████▎     | 4792/11066 [17:33<23:02,  4.54it/s]
                                                    

 43%|████▎     | 4792/11066 [17:33<23:02,  4.54it/s]
 43%|████▎     | 4793/11066 [17:33<23:06,  4.52it/s]
                                                    

 43%|████▎     | 4793/11066 [17:33<23:06,  4.52it/s]
 43%|████▎     | 4794/11066 [17:33<23:10,  4.51it/s]
                                                    

 43%|████▎     | 4794/11066 [17:33<23:10,  4.51it/s]
 43%|████▎     | 4795/11066 [17:34<23:15,  4.49it/s]
                                                    

 43%|████▎     | 4795/11066 [17:34<23:15,  4.49it/s]
 43%|████▎     | 4796/11066 [17:34<23:21,  4.47it/s]
                                                    

 43%|████▎     | 4796/11066 [17:34<23:21,  4.47it/s]
 43%|████▎     | 4797/11066 [17:34<23:43,  4.41it/s]
                                                    

 43%|████▎     | 4797/11066 [17:34<23:43,  4.41it/s]
 43%|████▎     | 4798/11066 [17:34<23:42,  4.40it/s]
                                                    

 43%|████▎     | 4798/11066 [17:34<23:42,  4.40it/s]
 43%|████▎     | 4799/11066 [17:35<23:58,  4.36it/s]
                                                    

 43%|████▎     | 4799/11066 [17:35<23:58,  4.36it/s]
 43%|████▎     | 4800/11066 [17:35<23:48,  4.39it/s]
                                                    

 43%|████▎     | 4800/11066 [17:35<23:48,  4.39it/s]
 43%|████▎     | 4801/11066 [17:35<23:39,  4.41it/s]
                                                    

 43%|████▎     | 4801/11066 [17:35<23:39,  4.41it/s]
 43%|████▎     | 4802/11066 [17:35<23:31,  4.44it/s]
                                                    

 43%|████▎     | 4802/11066 [17:35<23:31,  4.44it/s]
 43%|████▎     | 4803/11066 [17:35<23:25,  4.46it/s]
                                                    

 43%|████▎     | 4803/11066 [17:35<23:25,  4.46it/s]
 43%|████▎     | 4804/11066 [17:36<23:21,  4.47it/s]
                                                    

 43%|████▎     | 4804/11066 [17:36<23:21,  4.47it/s]
 43%|████▎     | 4805/11066 [17:36<23:19,  4.47it/s]
                                                    

 43%|████▎     | 4805/11066 [17:36<23:19,  4.47it/s]
 43%|████▎     | 4806/11066 [17:36<23:17,  4.48it/s]
                                                    

 43%|████▎     | 4806/11066 [17:36<23:17,  4.48it/s]
 43%|████▎     | 4807/11066 [17:36<23:15,  4.49it/s]
                                                    

 43%|████▎     | 4807/11066 [17:36<23:15,  4.49it/s]
 43%|████▎     | 4808/11066 [17:37<23:14,  4.49it/s]
                                                    

 43%|████▎     | 4808/11066 [17:37<23:14,  4.49it/s]
 43%|████▎     | 4809/11066 [17:37<23:13,  4.49it/s]
                                                    

 43%|████▎     | 4809/11066 [17:37<23:13,  4.49it/s]
 43%|████▎     | 4810/11066 [17:37<23:12,  4.49it/s]
                                                    

 43%|████▎     | 4810/11066 [17:37<23:12,  4.49it/s]
 43%|████▎     | 4811/11066 [17:37<23:11,  4.49it/s]
                                                    

 43%|████▎     | 4811/11066 [17:37<23:11,  4.49it/s]
 43%|████▎     | 4812/11066 [17:37<23:09,  4.50it/s]
                                                    

 43%|████▎     | 4812/11066 [17:37<23:09,  4.50it/s]
 43%|████▎     | 4813/11066 [17:38<23:09,  4.50it/s]
                                                    

 43%|████▎     | 4813/11066 [17:38<23:09,  4.50it/s]
 44%|████▎     | 4814/11066 [17:38<23:08,  4.50it/s]
                                                    

 44%|████▎     | 4814/11066 [17:38<23:08,  4.50it/s]
 44%|████▎     | 4815/11066 [17:38<23:09,  4.50it/s]
                                                    

 44%|████▎     | 4815/11066 [17:38<23:09,  4.50it/s]
 44%|████▎     | 4816/11066 [17:38<23:09,  4.50it/s]
                                                    

 44%|████▎     | 4816/11066 [17:38<23:09,  4.50it/s]
 44%|████▎     | 4817/11066 [17:39<23:10,  4.50it/s]
                                                    

 44%|████▎     | 4817/11066 [17:39<23:10,  4.50it/s]
 44%|████▎     | 4818/11066 [17:39<23:09,  4.50it/s]
                                                    

 44%|████▎     | 4818/11066 [17:39<23:09,  4.50it/s]
 44%|████▎     | 4819/11066 [17:39<23:08,  4.50it/s]
                                                    

 44%|████▎     | 4819/11066 [17:39<23:08,  4.50it/s]
 44%|████▎     | 4820/11066 [17:39<23:09,  4.50it/s]
                                                    

 44%|████▎     | 4820/11066 [17:39<23:09,  4.50it/s]
 44%|████▎     | 4821/11066 [17:39<23:08,  4.50it/s]
                                                    

 44%|████▎     | 4821/11066 [17:39<23:08,  4.50it/s]
 44%|████▎     | 4822/11066 [17:40<22:47,  4.57it/s]
                                                    

 44%|████▎     | 4822/11066 [17:40<22:47,  4.57it/s]
 44%|████▎     | 4823/11066 [17:40<22:36,  4.60it/s]
                                                    

 44%|████▎     | 4823/11066 [17:40<22:36,  4.60it/s]
 44%|████▎     | 4824/11066 [17:40<22:36,  4.60it/s]
                                                    

 44%|████▎     | 4824/11066 [17:40<22:36,  4.60it/s]
 44%|████▎     | 4825/11066 [17:40<22:35,  4.61it/s]
                                                    

 44%|████▎     | 4825/11066 [17:40<22:35,  4.61it/s]
 44%|████▎     | 4826/11066 [17:41<22:44,  4.57it/s]
                                                    

 44%|████▎     | 4826/11066 [17:41<22:44,  4.57it/s]
 44%|████▎     | 4827/11066 [17:41<22:32,  4.61it/s]
                                                    

 44%|████▎     | 4827/11066 [17:41<22:32,  4.61it/s]
 44%|████▎     | 4828/11066 [17:41<22:25,  4.64it/s]
                                                    

 44%|████▎     | 4828/11066 [17:41<22:25,  4.64it/s]
 44%|████▎     | 4829/11066 [17:41<22:26,  4.63it/s]
                                                    

 44%|████▎     | 4829/11066 [17:41<22:26,  4.63it/s]
 44%|████▎     | 4830/11066 [17:41<22:15,  4.67it/s]
                                                    

 44%|████▎     | 4830/11066 [17:41<22:15,  4.67it/s]
 44%|████▎     | 4831/11066 [17:42<22:19,  4.65it/s]
                                                    

 44%|████▎     | 4831/11066 [17:42<22:19,  4.65it/s]
 44%|████▎     | 4832/11066 [17:42<22:11,  4.68it/s]
                                                    

 44%|████▎     | 4832/11066 [17:42<22:11,  4.68it/s]
 44%|████▎     | 4833/11066 [17:42<22:01,  4.72it/s]
                                                    

 44%|████▎     | 4833/11066 [17:42<22:01,  4.72it/s]
 44%|████▎     | 4834/11066 [17:42<22:03,  4.71it/s]
                                                    

 44%|████▎     | 4834/11066 [17:42<22:03,  4.71it/s]
 44%|████▎     | 4835/11066 [17:42<22:21,  4.65it/s]
                                                    

 44%|████▎     | 4835/11066 [17:42<22:21,  4.65it/s]
 44%|████▎     | 4836/11066 [17:43<22:44,  4.57it/s]
                                                    

 44%|████▎     | 4836/11066 [17:43<22:44,  4.57it/s]
 44%|████▎     | 4837/11066 [17:43<22:55,  4.53it/s]
                                                    

 44%|████▎     | 4837/11066 [17:43<22:55,  4.53it/s]
 44%|████▎     | 4838/11066 [17:43<23:01,  4.51it/s]
                                                    

 44%|████▎     | 4838/11066 [17:43<23:01,  4.51it/s]
 44%|████▎     | 4839/11066 [17:43<23:01,  4.51it/s]
                                                    
{'loss': 0.9576, 'learning_rate': 1.7185071389842763e-05, 'epoch': 0.85}
{'loss': 0.7751, 'learning_rate': 1.7182360383155612e-05, 'epoch': 0.85}
{'loss': 0.8206, 'learning_rate': 1.717964937646846e-05, 'epoch': 0.85}
{'loss': 0.6249, 'learning_rate': 1.7176938369781312e-05, 'epoch': 0.85}
{'loss': 0.5834, 'learning_rate': 1.7174227363094164e-05, 'epoch': 0.86}
{'loss': 1.035, 'learning_rate': 1.7171516356407012e-05, 'epoch': 0.86}
{'loss': 0.4106, 'learning_rate': 1.7168805349719864e-05, 'epoch': 0.86}
{'loss': 1.2875, 'learning_rate': 1.7166094343032716e-05, 'epoch': 0.86}
{'loss': 0.3775, 'learning_rate': 1.7163383336345564e-05, 'epoch': 0.86}
{'loss': 0.5558, 'learning_rate': 1.7160672329658413e-05, 'epoch': 0.86}
{'loss': 0.8299, 'learning_rate': 1.715796132297126e-05, 'epoch': 0.86}
{'loss': 1.3059, 'learning_rate': 1.7155250316284113e-05, 'epoch': 0.86}
{'loss': 0.7861, 'learning_rate': 1.7152539309596965e-05, 'epoch': 0.86}
{'loss': 0.9918, 'learning_rate': 1.7149828302909813e-05, 'epoch': 0.86}
{'loss': 1.0345, 'learning_rate': 1.7147117296222665e-05, 'epoch': 0.86}
{'loss': 1.25, 'learning_rate': 1.7144406289535517e-05, 'epoch': 0.86}
{'loss': 0.7712, 'learning_rate': 1.7141695282848366e-05, 'epoch': 0.86}
{'loss': 0.7474, 'learning_rate': 1.7138984276161214e-05, 'epoch': 0.86}
{'loss': 1.4456, 'learning_rate': 1.7136273269474066e-05, 'epoch': 0.86}
{'loss': 1.1951, 'learning_rate': 1.7133562262786914e-05, 'epoch': 0.86}
{'loss': 1.1473, 'learning_rate': 1.7130851256099766e-05, 'epoch': 0.86}
{'loss': 1.1567, 'learning_rate': 1.7128140249412614e-05, 'epoch': 0.86}
{'loss': 0.645, 'learning_rate': 1.7125429242725466e-05, 'epoch': 0.86}
{'loss': 1.1651, 'learning_rate': 1.7122718236038318e-05, 'epoch': 0.86}
{'loss': 0.778, 'learning_rate': 1.7120007229351167e-05, 'epoch': 0.86}
{'loss': 0.7623, 'learning_rate': 1.7117296222664015e-05, 'epoch': 0.86}
{'loss': 0.8656, 'learning_rate': 1.7114585215976867e-05, 'epoch': 0.86}
{'loss': 0.7073, 'learning_rate': 1.7111874209289715e-05, 'epoch': 0.86}
{'loss': 0.8097, 'learning_rate': 1.7109163202602567e-05, 'epoch': 0.86}
{'loss': 1.5955, 'learning_rate': 1.710645219591542e-05, 'epoch': 0.86}
{'loss': 1.4534, 'learning_rate': 1.7103741189228267e-05, 'epoch': 0.86}
{'loss': 0.6405, 'learning_rate': 1.710103018254112e-05, 'epoch': 0.86}
{'loss': 1.123, 'learning_rate': 1.7098319175853968e-05, 'epoch': 0.86}
{'loss': 1.2666, 'learning_rate': 1.7095608169166816e-05, 'epoch': 0.86}
{'loss': 1.297, 'learning_rate': 1.7092897162479668e-05, 'epoch': 0.86}
{'loss': 1.1549, 'learning_rate': 1.7090186155792516e-05, 'epoch': 0.86}
{'loss': 1.7002, 'learning_rate': 1.7087475149105368e-05, 'epoch': 0.86}
{'loss': 0.818, 'learning_rate': 1.708476414241822e-05, 'epoch': 0.86}
{'loss': 1.1864, 'learning_rate': 1.708205313573107e-05, 'epoch': 0.86}
{'loss': 0.7844, 'learning_rate': 1.707934212904392e-05, 'epoch': 0.86}
{'loss': 0.9548, 'learning_rate': 1.707663112235677e-05, 'epoch': 0.86}
{'loss': 0.5466, 'learning_rate': 1.7073920115669617e-05, 'epoch': 0.86}
{'loss': 0.9263, 'learning_rate': 1.707120910898247e-05, 'epoch': 0.86}
{'loss': 1.1059, 'learning_rate': 1.7068498102295317e-05, 'epoch': 0.86}
{'loss': 0.8236, 'learning_rate': 1.706578709560817e-05, 'epoch': 0.86}
{'loss': 1.3797, 'learning_rate': 1.706307608892102e-05, 'epoch': 0.86}
{'loss': 0.6193, 'learning_rate': 1.706036508223387e-05, 'epoch': 0.86}
{'loss': 0.9856, 'learning_rate': 1.705765407554672e-05, 'epoch': 0.86}
{'loss': 0.97, 'learning_rate': 1.705494306885957e-05, 'epoch': 0.86}
{'loss': 0.845, 'learning_rate': 1.7052232062172418e-05, 'epoch': 0.86}
{'loss': 0.907, 'learning_rate': 1.704952105548527e-05, 'epoch': 0.86}
{'loss': 1.0505, 'learning_rate': 1.7046810048798122e-05, 'epoch': 0.86}
{'loss': 0.3676, 'learning_rate': 1.704409904211097e-05, 'epoch': 0.86}
{'loss': 1.0944, 'learning_rate': 1.7041388035423822e-05, 'epoch': 0.86}
{'loss': 1.0597, 'learning_rate': 1.703867702873667e-05, 'epoch': 0.86}
{'loss': 0.7349, 'learning_rate': 1.7035966022049522e-05, 'epoch': 0.86}
{'loss': 0.9958, 'learning_rate': 1.703325501536237e-05, 'epoch': 0.86}
{'loss': 0.8659, 'learning_rate': 1.703054400867522e-05, 'epoch': 0.86}
{'loss': 1.5973, 'learning_rate': 1.702783300198807e-05, 'epoch': 0.86}
{'loss': 0.8172, 'learning_rate': 1.7025121995300923e-05, 'epoch': 0.86}
{'loss': 0.5419, 'learning_rate': 1.702241098861377e-05, 'epoch': 0.87}
{'loss': 1.3502, 'learning_rate': 1.7019699981926623e-05, 'epoch': 0.87}
{'loss': 1.4353, 'learning_rate': 1.7016988975239475e-05, 'epoch': 0.87}
{'loss': 1.5014, 'learning_rate': 1.7014277968552324e-05, 'epoch': 0.87}
{'loss': 0.9939, 'learning_rate': 1.7011566961865172e-05, 'epoch': 0.87}
{'loss': 0.9973, 'learning_rate': 1.700885595517802e-05, 'epoch': 0.87}
{'loss': 1.0742, 'learning_rate': 1.7006144948490872e-05, 'epoch': 0.87}
{'loss': 1.3112, 'learning_rate': 1.7003433941803724e-05, 'epoch': 0.87}
{'loss': 1.0476, 'learning_rate': 1.7000722935116572e-05, 'epoch': 0.87}
{'loss': 0.5298, 'learning_rate': 1.6998011928429424e-05, 'epoch': 0.87}
{'loss': 0.7054, 'learning_rate': 1.6995300921742276e-05, 'epoch': 0.87}
{'loss': 0.6539, 'learning_rate': 1.6992589915055125e-05, 'epoch': 0.87}
{'loss': 1.2498, 'learning_rate': 1.6989878908367973e-05, 'epoch': 0.87}
{'loss': 0.9033, 'learning_rate': 1.6987167901680825e-05, 'epoch': 0.87}
{'loss': 1.3983, 'learning_rate': 1.6984456894993673e-05, 'epoch': 0.87}
{'loss': 0.6962, 'learning_rate': 1.6981745888306525e-05, 'epoch': 0.87}
{'loss': 1.2198, 'learning_rate': 1.6979034881619374e-05, 'epoch': 0.87}
{'loss': 1.0254, 'learning_rate': 1.6976323874932225e-05, 'epoch': 0.87}
{'loss': 1.1439, 'learning_rate': 1.6973612868245077e-05, 'epoch': 0.87}
{'loss': 0.9676, 'learning_rate': 1.6970901861557926e-05, 'epoch': 0.87}
{'loss': 1.1937, 'learning_rate': 1.6968190854870774e-05, 'epoch': 0.87}
{'loss': 1.0055, 'learning_rate': 1.6965479848183626e-05, 'epoch': 0.87}
{'loss': 1.0342, 'learning_rate': 1.6962768841496474e-05, 'epoch': 0.87}
{'loss': 0.858, 'learning_rate': 1.6960057834809326e-05, 'epoch': 0.87}
{'loss': 1.0247, 'learning_rate': 1.6957346828122178e-05, 'epoch': 0.87}
{'loss': 0.9037, 'learning_rate': 1.6954635821435026e-05, 'epoch': 0.87}
{'loss': 0.4737, 'learning_rate': 1.6951924814747878e-05, 'epoch': 0.87}
{'loss': 1.062, 'learning_rate': 1.6949213808060727e-05, 'epoch': 0.87}
{'loss': 0.8617, 'learning_rate': 1.6946502801373575e-05, 'epoch': 0.87}
{'loss': 1.0945, 'learning_rate': 1.6943791794686427e-05, 'epoch': 0.87}
{'loss': 1.1956, 'learning_rate': 1.6941080787999275e-05, 'epoch': 0.87}
{'loss': 1.3248, 'learning_rate': 1.6938369781312127e-05, 'epoch': 0.87}
{'loss': 0.9391, 'learning_rate': 1.693565877462498e-05, 'epoch': 0.87}
{'loss': 1.0622, 'learning_rate': 1.6932947767937828e-05, 'epoch': 0.87}
{'loss': 2.2351, 'learning_rate': 1.693023676125068e-05, 'epoch': 0.87}
{'loss': 1.6395, 'learning_rate': 1.692752575456353e-05, 'epoch': 0.87}
{'loss': 1.3244, 'learning_rate': 1.6924814747876376e-05, 'epoch': 0.87}
{'loss': 1.2545, 'learning_rate': 1.6922103741189228e-05, 'epoch': 0.87}
{'loss': 1.1751, 'learning_rate': 1.691939273450208e-05, 'epoch': 0.87}
{'loss': 1.2472, 'learning_rate': 1.691668172781493e-05, 'epoch': 0.87}
{'loss': 1.0651, 'learning_rate': 1.691397072112778e-05, 'epoch': 0.87}
{'loss': 0.7773, 'learning_rate': 1.691125971444063e-05, 'epoch': 0.87}
{'loss': 1.1124, 'learning_rate': 1.690854870775348e-05, 'epoch': 0.87}
{'loss': 1.1527, 'learning_rate': 1.6905837701066332e-05, 'epoch': 0.87}
{'loss': 1.4963, 'learning_rate': 1.6903126694379177e-05, 'epoch': 0.87}
{'loss': 1.6689, 'learning_rate': 1.690041568769203e-05, 'epoch': 0.87}
{'loss': 0.8068, 'learning_rate': 1.689770468100488e-05, 'epoch': 0.87}
{'loss': 0.7083, 'learning_rate': 1.689499367431773e-05, 'epoch': 0.87}
{'loss': 1.1572, 'learning_rate': 1.689228266763058e-05, 'epoch': 0.87}
{'loss': 1.0501, 'learning_rate': 1.6889571660943433e-05, 'epoch': 0.87}
{'loss': 0.7177, 'learning_rate': 1.688686065425628e-05, 'epoch': 0.87}
{'loss': 0.9744, 'learning_rate': 1.6884149647569133e-05, 'epoch': 0.87}

 44%|████▎     | 4839/11066 [17:43<23:01,  4.51it/s]
 44%|████▎     | 4840/11066 [17:44<23:02,  4.50it/s]
                                                    

 44%|████▎     | 4840/11066 [17:44<23:02,  4.50it/s]
 44%|████▎     | 4841/11066 [17:44<23:01,  4.51it/s]
                                                    

 44%|████▎     | 4841/11066 [17:44<23:01,  4.51it/s]
 44%|████▍     | 4842/11066 [17:44<23:02,  4.50it/s]
                                                    

 44%|████▍     | 4842/11066 [17:44<23:02,  4.50it/s]
 44%|████▍     | 4843/11066 [17:44<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4843/11066 [17:44<23:01,  4.50it/s]
 44%|████▍     | 4844/11066 [17:45<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4844/11066 [17:45<23:01,  4.50it/s]
 44%|████▍     | 4845/11066 [17:45<23:00,  4.51it/s]
                                                    

 44%|████▍     | 4845/11066 [17:45<23:00,  4.51it/s]
 44%|████▍     | 4846/11066 [17:45<23:00,  4.50it/s]
                                                    

 44%|████▍     | 4846/11066 [17:45<23:00,  4.50it/s]
 44%|████▍     | 4847/11066 [17:45<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4847/11066 [17:45<23:01,  4.50it/s]
 44%|████▍     | 4848/11066 [17:45<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4848/11066 [17:45<23:01,  4.50it/s]
 44%|████▍     | 4849/11066 [17:46<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4849/11066 [17:46<23:01,  4.50it/s]
 44%|████▍     | 4850/11066 [17:46<23:14,  4.46it/s]
                                                    

 44%|████▍     | 4850/11066 [17:46<23:14,  4.46it/s]
 44%|████▍     | 4851/11066 [17:46<23:17,  4.45it/s]
                                                    

 44%|████▍     | 4851/11066 [17:46<23:17,  4.45it/s]
 44%|████▍     | 4852/11066 [17:46<23:01,  4.50it/s]
                                                    

 44%|████▍     | 4852/11066 [17:46<23:01,  4.50it/s]
 44%|████▍     | 4853/11066 [17:47<23:05,  4.48it/s]
                                                    

 44%|████▍     | 4853/11066 [17:47<23:05,  4.48it/s]
 44%|████▍     | 4854/11066 [17:47<23:06,  4.48it/s]
                                                    

 44%|████▍     | 4854/11066 [17:47<23:06,  4.48it/s]
 44%|████▍     | 4855/11066 [17:47<22:46,  4.55it/s]
                                                    

 44%|████▍     | 4855/11066 [17:47<22:46,  4.55it/s]
 44%|████▍     | 4856/11066 [17:47<22:40,  4.56it/s]
                                                    

 44%|████▍     | 4856/11066 [17:47<22:40,  4.56it/s]
 44%|████▍     | 4857/11066 [17:47<22:22,  4.63it/s]
                                                    

 44%|████▍     | 4857/11066 [17:47<22:22,  4.63it/s]
 44%|████▍     | 4858/11066 [17:48<22:22,  4.62it/s]
                                                    

 44%|████▍     | 4858/11066 [17:48<22:22,  4.62it/s]
 44%|████▍     | 4859/11066 [17:48<22:13,  4.66it/s]
                                                    

 44%|████▍     | 4859/11066 [17:48<22:13,  4.66it/s]
 44%|████▍     | 4860/11066 [17:48<22:11,  4.66it/s]
                                                    

 44%|████▍     | 4860/11066 [17:48<22:11,  4.66it/s]
 44%|████▍     | 4861/11066 [17:48<22:07,  4.67it/s]
                                                    

 44%|████▍     | 4861/11066 [17:48<22:07,  4.67it/s]
 44%|████▍     | 4862/11066 [17:48<22:04,  4.68it/s]
                                                    

 44%|████▍     | 4862/11066 [17:48<22:04,  4.68it/s]
 44%|████▍     | 4863/11066 [17:49<22:22,  4.62it/s]
                                                    

 44%|████▍     | 4863/11066 [17:49<22:22,  4.62it/s]
 44%|████▍     | 4864/11066 [17:49<22:19,  4.63it/s]
                                                    

 44%|████▍     | 4864/11066 [17:49<22:19,  4.63it/s]
 44%|████▍     | 4865/11066 [17:49<22:13,  4.65it/s]
                                                    

 44%|████▍     | 4865/11066 [17:49<22:13,  4.65it/s]
 44%|████▍     | 4866/11066 [17:49<22:08,  4.67it/s]
                                                    

 44%|████▍     | 4866/11066 [17:49<22:08,  4.67it/s]
 44%|████▍     | 4867/11066 [17:50<22:24,  4.61it/s]
                                                    

 44%|████▍     | 4867/11066 [17:50<22:24,  4.61it/s]
 44%|████▍     | 4868/11066 [17:50<22:32,  4.58it/s]
                                                    

 44%|████▍     | 4868/11066 [17:50<22:32,  4.58it/s]
 44%|████▍     | 4869/11066 [17:50<22:40,  4.56it/s]
                                                    

 44%|████▍     | 4869/11066 [17:50<22:40,  4.56it/s]
 44%|████▍     | 4870/11066 [17:50<22:47,  4.53it/s]
                                                    

 44%|████▍     | 4870/11066 [17:50<22:47,  4.53it/s]
 44%|████▍     | 4871/11066 [17:50<22:52,  4.52it/s]
                                                    

 44%|████▍     | 4871/11066 [17:50<22:52,  4.52it/s]
 44%|████▍     | 4872/11066 [17:51<22:55,  4.50it/s]
                                                    

 44%|████▍     | 4872/11066 [17:51<22:55,  4.50it/s]
 44%|████▍     | 4873/11066 [17:51<22:55,  4.50it/s]
                                                    

 44%|████▍     | 4873/11066 [17:51<22:55,  4.50it/s]
 44%|████▍     | 4874/11066 [17:51<22:57,  4.50it/s]
                                                    

 44%|████▍     | 4874/11066 [17:51<22:57,  4.50it/s]
 44%|████▍     | 4875/11066 [17:51<22:58,  4.49it/s]
                                                    

 44%|████▍     | 4875/11066 [17:51<22:58,  4.49it/s]
 44%|████▍     | 4876/11066 [17:52<22:57,  4.49it/s]
                                                    

 44%|████▍     | 4876/11066 [17:52<22:57,  4.49it/s]
 44%|████▍     | 4877/11066 [17:52<22:57,  4.49it/s]
                                                    

 44%|████▍     | 4877/11066 [17:52<22:57,  4.49it/s]
 44%|████▍     | 4878/11066 [17:52<22:54,  4.50it/s]
                                                    

 44%|████▍     | 4878/11066 [17:52<22:54,  4.50it/s]
 44%|████▍     | 4879/11066 [17:52<22:58,  4.49it/s]
                                                    

 44%|████▍     | 4879/11066 [17:52<22:58,  4.49it/s]
 44%|████▍     | 4880/11066 [17:52<22:58,  4.49it/s]
                                                    

 44%|████▍     | 4880/11066 [17:52<22:58,  4.49it/s]
 44%|████▍     | 4881/11066 [17:53<22:58,  4.49it/s]
                                                    

 44%|████▍     | 4881/11066 [17:53<22:58,  4.49it/s]
 44%|████▍     | 4882/11066 [17:53<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4882/11066 [17:53<22:56,  4.49it/s]
 44%|████▍     | 4883/11066 [17:53<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4883/11066 [17:53<22:56,  4.49it/s]
 44%|████▍     | 4884/11066 [17:53<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4884/11066 [17:53<22:56,  4.49it/s]
 44%|████▍     | 4885/11066 [17:54<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4885/11066 [17:54<22:56,  4.49it/s]
 44%|████▍     | 4886/11066 [17:54<22:55,  4.49it/s]
                                                    

 44%|████▍     | 4886/11066 [17:54<22:55,  4.49it/s]
 44%|████▍     | 4887/11066 [17:54<22:55,  4.49it/s]
                                                    

 44%|████▍     | 4887/11066 [17:54<22:55,  4.49it/s]
 44%|████▍     | 4888/11066 [17:54<22:55,  4.49it/s]
                                                    

 44%|████▍     | 4888/11066 [17:54<22:55,  4.49it/s]
 44%|████▍     | 4889/11066 [17:54<22:55,  4.49it/s]
                                                    

 44%|████▍     | 4889/11066 [17:54<22:55,  4.49it/s]
 44%|████▍     | 4890/11066 [17:55<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4890/11066 [17:55<22:56,  4.49it/s]
 44%|████▍     | 4891/11066 [17:55<22:56,  4.48it/s]
                                                    

 44%|████▍     | 4891/11066 [17:55<22:56,  4.48it/s]
 44%|████▍     | 4892/11066 [17:55<22:56,  4.49it/s]
                                                    

 44%|████▍     | 4892/11066 [17:55<22:56,  4.49it/s]
 44%|████▍     | 4893/11066 [17:55<22:54,  4.49it/s]
                                                    

 44%|████▍     | 4893/11066 [17:55<22:54,  4.49it/s]
 44%|████▍     | 4894/11066 [17:56<22:52,  4.50it/s]
                                                    

 44%|████▍     | 4894/11066 [17:56<22:52,  4.50it/s]
 44%|████▍     | 4895/11066 [17:56<22:52,  4.50it/s]
                                                    

 44%|████▍     | 4895/11066 [17:56<22:52,  4.50it/s]
 44%|████▍     | 4896/11066 [17:56<22:52,  4.50it/s]
                                                    

 44%|████▍     | 4896/11066 [17:56<22:52,  4.50it/s]
 44%|████▍     | 4897/11066 [17:56<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4897/11066 [17:56<22:51,  4.50it/s]
 44%|████▍     | 4898/11066 [17:56<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4898/11066 [17:56<22:51,  4.50it/s]
 44%|████▍     | 4899/11066 [17:57<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4899/11066 [17:57<22:51,  4.50it/s]
 44%|████▍     | 4900/11066 [17:57<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4900/11066 [17:57<22:51,  4.50it/s]
 44%|████▍     | 4901/11066 [17:57<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4901/11066 [17:57<22:51,  4.50it/s]
 44%|████▍     | 4902/11066 [17:57<22:51,  4.50it/s]
                                                    

 44%|████▍     | 4902/11066 [17:57<22:51,  4.50it/s]
 44%|████▍     | 4903/11066 [17:58<22:31,  4.56it/s]
                                                    

 44%|████▍     | 4903/11066 [17:58<22:31,  4.56it/s]
 44%|████▍     | 4904/11066 [17:58<22:27,  4.57it/s]
                                                    

 44%|████▍     | 4904/11066 [17:58<22:27,  4.57it/s]
 44%|████▍     | 4905/11066 [17:58<22:25,  4.58it/s]
                                                    

 44%|████▍     | 4905/11066 [17:58<22:25,  4.58it/s]
 44%|████▍     | 4906/11066 [17:58<22:25,  4.58it/s]
                                                    

 44%|████▍     | 4906/11066 [17:58<22:25,  4.58it/s]
 44%|████▍     | 4907/11066 [17:58<22:11,  4.63it/s]
                                                    

 44%|████▍     | 4907/11066 [17:58<22:11,  4.63it/s]
 44%|████▍     | 4908/11066 [17:59<22:24,  4.58it/s]
                                                    

 44%|████▍     | 4908/11066 [17:59<22:24,  4.58it/s]
 44%|████▍     | 4909/11066 [17:59<22:17,  4.60it/s]
                                                    

 44%|████▍     | 4909/11066 [17:59<22:17,  4.60it/s]
 44%|████▍     | 4910/11066 [17:59<22:20,  4.59it/s]
                                                    

 44%|████▍     | 4910/11066 [17:59<22:20,  4.59it/s]
 44%|████▍     | 4911/11066 [17:59<22:03,  4.65it/s]
                                                    

 44%|████▍     | 4911/11066 [17:59<22:03,  4.65it/s]
 44%|████▍     | 4912/11066 [17:59<22:15,  4.61it/s]
                                                    

 44%|████▍     | 4912/11066 [17:59<22:15,  4.61it/s]
 44%|████▍     | 4913/11066 [18:00<22:06,  4.64it/s]
                                                    

 44%|████▍     | 4913/11066 [18:00<22:06,  4.64it/s]
 44%|████▍     | 4914/11066 [18:00<22:08,  4.63it/s]
                                                    

 44%|████▍     | 4914/11066 [18:00<22:08,  4.63it/s]
 44%|████▍     | 4915/11066 [18:00<22:03,  4.65it/s]
                                                    

 44%|████▍     | 4915/11066 [18:00<22:03,  4.65it/s]
 44%|████▍     | 4916/11066 [18:00<22:21,  4.58it/s]
                                                    

 44%|████▍     | 4916/11066 [18:00<22:21,  4.58it/s]
 44%|████▍     | 4917/11066 [18:01<22:32,  4.55it/s]
                                                    

 44%|████▍     | 4917/11066 [18:01<22:32,  4.55it/s]
 44%|████▍     | 4918/11066 [18:01<22:26,  4.57it/s]
                                                    

 44%|████▍     | 4918/11066 [18:01<22:26,  4.57it/s]
 44%|████▍     | 4919/11066 [18:01<22:23,  4.58it/s]
                                                    

 44%|████▍     | 4919/11066 [18:01<22:23,  4.58it/s]
 44%|████▍     | 4920/11066 [18:01<22:34,  4.54it/s]
                                                    

 44%|████▍     | 4920/11066 [18:01<22:34,  4.54it/s]
 44%|████▍     | 4921/11066 [18:01<22:19,  4.59it/s]
                                                    

 44%|████▍     | 4921/11066 [18:01<22:19,  4.59it/s]
 44%|████▍     | 4922/11066 [18:02<22:09,  4.62it/s]
                                                    

 44%|████▍     | 4922/11066 [18:02<22:09,  4.62it/s]
 44%|████▍     | 4923/11066 [18:02<22:02,  4.64it/s]
                                                    

 44%|████▍     | 4923/11066 [18:02<22:02,  4.64it/s]
 44%|████▍     | 4924/11066 [18:02<21:55,  4.67it/s]
                                                    

 44%|████▍     | 4924/11066 [18:02<21:55,  4.67it/s]
 45%|████▍     | 4925/11066 [18:02<22:00,  4.65it/s]
                                                    

 45%|████▍     | 4925/11066 [18:02<22:00,  4.65it/s]
 45%|████▍     | 4926/11066 [18:03<21:58,  4.66it/s]
                                                    

 45%|████▍     | 4926/11066 [18:03<21:58,  4.66it/s]
 45%|████▍     | 4927/11066 [18:03<22:15,  4.60it/s]
                                                    

 45%|████▍     | 4927/11066 [18:03<22:15,  4.60it/s]
 45%|████▍     | 4928/11066 [18:03<22:05,  4.63it/s]
                                                    

 45%|████▍     | 4928/11066 [18:03<22:05,  4.63it/s]
 45%|████▍     | 4929/11066 [18:03<21:58,  4.65it/s]
                                                    

 45%|████▍     | 4929/11066 [18:03<21:58,  4.65it/s]
 45%|████▍     | 4930/11066 [18:03<21:53,  4.67it/s]
                                                    

 45%|████▍     | 4930/11066 [18:03<21:53,  4.67it/s]
 45%|████▍     | 4931/11066 [18:04<21:59,  4.65it/s]
                                                    

 45%|████▍     | 4931/11066 [18:04<21:59,  4.65it/s]
 45%|████▍     | 4932/11066 [18:04<21:47,  4.69it/s]
                                                    

 45%|████▍     | 4932/11066 [18:04<21:47,  4.69it/s]
 45%|████▍     | 4933/11066 [18:04<21:47,  4.69it/s]
                                                    

 45%|████▍     | 4933/11066 [18:04<21:47,  4.69it/s]
 45%|████▍     | 4934/11066 [18:04<21:48,  4.69it/s]
                                                    

 45%|████▍     | 4934/11066 [18:04<21:48,  4.69it/s]
 45%|████▍     | 4935/11066 [18:04<21:46,  4.69it/s]
                                                    

 45%|████▍     | 4935/11066 [18:04<21:46,  4.69it/s]
 45%|████▍     | 4936/11066 [18:05<21:58,  4.65it/s]
                                                    

 45%|████▍     | 4936/11066 [18:05<21:58,  4.65it/s]
 45%|████▍     | 4937/11066 [18:05<22:04,  4.63it/s]
                                                    

 45%|████▍     | 4937/11066 [18:05<22:04,  4.63it/s]
 45%|████▍     | 4938/11066 [18:05<21:59,  4.64it/s]
                                                    

 45%|████▍     | 4938/11066 [18:05<21:59,  4.64it/s]
 45%|████▍     | 4939/11066 [18:05<22:33,  4.53it/s]
                                                    

 45%|████▍     | 4939/11066 [18:05<22:33,  4.53it/s]
 45%|████▍     | 4940/11066 [18:06<22:46,  4.48it/s]
                                                    

 45%|████▍     | 4940/11066 [18:06<22:46,  4.48it/s]
 45%|████▍     | 4941/11066 [18:06<22:42,  4.50it/s]
                                                    

 45%|████▍     | 4941/11066 [18:06<22:42,  4.50it/s]
 45%|████▍     | 4942/11066 [18:06<22:42,  4.49it/s]
                                                    

 45%|████▍     | 4942/11066 [18:06<22:42,  4.49it/s]
 45%|████▍     | 4943/11066 [18:06<22:24,  4.56it/s]
                                                    

 45%|████▍     | 4943/11066 [18:06<22:24,  4.56it/s]
 45%|████▍     | 4944/11066 [18:06<22:10,  4.60it/s]
                                                    

 45%|████▍     | 4944/11066 [18:06<22:10,  4.60it/s]
 45%|████▍     | 4945/11066 [18:07<22:41,  4.50it/s]
                                                    

 45%|████▍     | 4945/11066 [18:07<22:41,  4.50it/s]
 45%|████▍     | 4946/11066 [18:07<22:57,  4.44it/s]
                                                    

 45%|████▍     | 4946/11066 [18:07<22:57,  4.44it/s]
 45%|████▍     | 4947/11066 [18:07<22:55,  4.45it/s]
                                                    

 45%|████▍     | 4947/11066 [18:07<22:55,  4.45it/s]
 45%|████▍     | 4948/11066 [18:07<22:53,  4.45it/s]
                                                    

 45%|████▍     | 4948/11066 [18:07<22:53,  4.45it/s]
 45%|████▍     | 4949/11066 [18:08<22:32,  4.52it/s]
                                                    

 45%|████▍     | 4949/11066 [18:08<22:32,  4.52it/s]
 45%|████▍     | 4950/11066 [18:08<22:09,  4.60it/s]
                                                    

 45%|████▍     | 4950/11066 [18:08<22:09,  4.60it/s]
 45%|████▍     | 4951/11066 [18:08<22:01,  4.63it/s]
                                                    

 45%|████▍     | 4951/11066 [18:08<22:01,  4.63it/s]
 45%|████▍     | 4952/11066 [18:08<21:52,  4.66it/s]
                                                    
{'loss': 1.1837, 'learning_rate': 1.688143864088198e-05, 'epoch': 0.87}
{'loss': 0.7404, 'learning_rate': 1.687872763419483e-05, 'epoch': 0.87}
{'loss': 1.4238, 'learning_rate': 1.6876016627507682e-05, 'epoch': 0.87}
{'loss': 0.6617, 'learning_rate': 1.687330562082053e-05, 'epoch': 0.88}
{'loss': 0.6831, 'learning_rate': 1.6870594614133382e-05, 'epoch': 0.88}
{'loss': 1.6539, 'learning_rate': 1.6867883607446234e-05, 'epoch': 0.88}
{'loss': 0.7519, 'learning_rate': 1.6865172600759083e-05, 'epoch': 0.88}
{'loss': 1.1228, 'learning_rate': 1.6862461594071934e-05, 'epoch': 0.88}
{'loss': 1.448, 'learning_rate': 1.6859750587384783e-05, 'epoch': 0.88}
{'loss': 0.9032, 'learning_rate': 1.685703958069763e-05, 'epoch': 0.88}
{'loss': 0.9694, 'learning_rate': 1.6854328574010483e-05, 'epoch': 0.88}
{'loss': 1.6121, 'learning_rate': 1.685161756732333e-05, 'epoch': 0.88}
{'loss': 1.4552, 'learning_rate': 1.6848906560636183e-05, 'epoch': 0.88}
{'loss': 0.4529, 'learning_rate': 1.6846195553949035e-05, 'epoch': 0.88}
{'loss': 1.1369, 'learning_rate': 1.6843484547261884e-05, 'epoch': 0.88}
{'loss': 0.8789, 'learning_rate': 1.6840773540574735e-05, 'epoch': 0.88}
{'loss': 1.2186, 'learning_rate': 1.6838062533887584e-05, 'epoch': 0.88}
{'loss': 0.8443, 'learning_rate': 1.6835351527200432e-05, 'epoch': 0.88}
{'loss': 0.9262, 'learning_rate': 1.6832640520513284e-05, 'epoch': 0.88}
{'loss': 1.1893, 'learning_rate': 1.6829929513826136e-05, 'epoch': 0.88}
{'loss': 1.7251, 'learning_rate': 1.6827218507138984e-05, 'epoch': 0.88}
{'loss': 0.8216, 'learning_rate': 1.6824507500451836e-05, 'epoch': 0.88}
{'loss': 1.2642, 'learning_rate': 1.6821796493764685e-05, 'epoch': 0.88}
{'loss': 1.8864, 'learning_rate': 1.6819085487077537e-05, 'epoch': 0.88}
{'loss': 1.183, 'learning_rate': 1.6816374480390385e-05, 'epoch': 0.88}
{'loss': 0.8349, 'learning_rate': 1.6813663473703233e-05, 'epoch': 0.88}
{'loss': 1.3434, 'learning_rate': 1.6810952467016085e-05, 'epoch': 0.88}
{'loss': 1.0468, 'learning_rate': 1.6808241460328937e-05, 'epoch': 0.88}
{'loss': 0.8324, 'learning_rate': 1.6805530453641786e-05, 'epoch': 0.88}
{'loss': 0.8893, 'learning_rate': 1.6802819446954637e-05, 'epoch': 0.88}
{'loss': 0.792, 'learning_rate': 1.680010844026749e-05, 'epoch': 0.88}
{'loss': 1.5437, 'learning_rate': 1.6797397433580338e-05, 'epoch': 0.88}
{'loss': 0.9923, 'learning_rate': 1.6794686426893186e-05, 'epoch': 0.88}
{'loss': 1.0018, 'learning_rate': 1.6791975420206035e-05, 'epoch': 0.88}
{'loss': 0.8635, 'learning_rate': 1.6789264413518886e-05, 'epoch': 0.88}
{'loss': 0.7745, 'learning_rate': 1.6786553406831738e-05, 'epoch': 0.88}
{'loss': 0.7958, 'learning_rate': 1.6783842400144587e-05, 'epoch': 0.88}
{'loss': 1.5573, 'learning_rate': 1.678113139345744e-05, 'epoch': 0.88}
{'loss': 1.0298, 'learning_rate': 1.677842038677029e-05, 'epoch': 0.88}
{'loss': 0.5684, 'learning_rate': 1.677570938008314e-05, 'epoch': 0.88}
{'loss': 0.655, 'learning_rate': 1.6772998373395987e-05, 'epoch': 0.88}
{'loss': 1.2193, 'learning_rate': 1.677028736670884e-05, 'epoch': 0.88}
{'loss': 1.072, 'learning_rate': 1.6767576360021687e-05, 'epoch': 0.88}
{'loss': 0.956, 'learning_rate': 1.676486535333454e-05, 'epoch': 0.88}
{'loss': 0.6732, 'learning_rate': 1.6762154346647388e-05, 'epoch': 0.88}
{'loss': 0.6357, 'learning_rate': 1.675944333996024e-05, 'epoch': 0.88}
{'loss': 0.6086, 'learning_rate': 1.675673233327309e-05, 'epoch': 0.88}
{'loss': 1.7686, 'learning_rate': 1.675402132658594e-05, 'epoch': 0.88}
{'loss': 1.3086, 'learning_rate': 1.6751310319898788e-05, 'epoch': 0.88}
{'loss': 1.0996, 'learning_rate': 1.674859931321164e-05, 'epoch': 0.88}
{'loss': 0.7122, 'learning_rate': 1.674588830652449e-05, 'epoch': 0.88}
{'loss': 0.5803, 'learning_rate': 1.674317729983734e-05, 'epoch': 0.88}
{'loss': 0.8058, 'learning_rate': 1.6740466293150192e-05, 'epoch': 0.88}
{'loss': 1.0548, 'learning_rate': 1.673775528646304e-05, 'epoch': 0.88}
{'loss': 1.0645, 'learning_rate': 1.6735044279775892e-05, 'epoch': 0.88}
{'loss': 1.301, 'learning_rate': 1.6732333273088737e-05, 'epoch': 0.88}
{'loss': 1.3286, 'learning_rate': 1.672962226640159e-05, 'epoch': 0.88}
{'loss': 0.4104, 'learning_rate': 1.672691125971444e-05, 'epoch': 0.88}
{'loss': 1.0109, 'learning_rate': 1.672420025302729e-05, 'epoch': 0.89}
{'loss': 0.8175, 'learning_rate': 1.672148924634014e-05, 'epoch': 0.89}
{'loss': 1.7588, 'learning_rate': 1.6718778239652993e-05, 'epoch': 0.89}
{'loss': 1.1818, 'learning_rate': 1.671606723296584e-05, 'epoch': 0.89}
{'loss': 1.2349, 'learning_rate': 1.6713356226278693e-05, 'epoch': 0.89}
{'loss': 1.3404, 'learning_rate': 1.6710645219591542e-05, 'epoch': 0.89}
{'loss': 2.1308, 'learning_rate': 1.670793421290439e-05, 'epoch': 0.89}
{'loss': 1.1734, 'learning_rate': 1.6705223206217242e-05, 'epoch': 0.89}
{'loss': 1.0889, 'learning_rate': 1.670251219953009e-05, 'epoch': 0.89}
{'loss': 1.2443, 'learning_rate': 1.6699801192842942e-05, 'epoch': 0.89}
{'loss': 0.7884, 'learning_rate': 1.6697090186155794e-05, 'epoch': 0.89}
{'loss': 1.0721, 'learning_rate': 1.6694379179468643e-05, 'epoch': 0.89}
{'loss': 1.0752, 'learning_rate': 1.6691668172781495e-05, 'epoch': 0.89}
{'loss': 1.5995, 'learning_rate': 1.6688957166094343e-05, 'epoch': 0.89}
{'loss': 0.7656, 'learning_rate': 1.668624615940719e-05, 'epoch': 0.89}
{'loss': 1.2299, 'learning_rate': 1.6683535152720043e-05, 'epoch': 0.89}
{'loss': 1.0593, 'learning_rate': 1.6680824146032895e-05, 'epoch': 0.89}
{'loss': 0.9947, 'learning_rate': 1.6678113139345744e-05, 'epoch': 0.89}
{'loss': 1.0913, 'learning_rate': 1.6675402132658595e-05, 'epoch': 0.89}
{'loss': 0.7264, 'learning_rate': 1.6672691125971444e-05, 'epoch': 0.89}
{'loss': 0.5847, 'learning_rate': 1.6669980119284296e-05, 'epoch': 0.89}
{'loss': 1.0365, 'learning_rate': 1.6667269112597144e-05, 'epoch': 0.89}
{'loss': 0.8294, 'learning_rate': 1.6664558105909993e-05, 'epoch': 0.89}
{'loss': 1.7234, 'learning_rate': 1.6661847099222844e-05, 'epoch': 0.89}
{'loss': 1.7913, 'learning_rate': 1.6659136092535696e-05, 'epoch': 0.89}
{'loss': 1.1199, 'learning_rate': 1.6656425085848545e-05, 'epoch': 0.89}
{'loss': 1.2265, 'learning_rate': 1.6653714079161396e-05, 'epoch': 0.89}
{'loss': 1.6522, 'learning_rate': 1.6651003072474248e-05, 'epoch': 0.89}
{'loss': 1.6103, 'learning_rate': 1.6648292065787097e-05, 'epoch': 0.89}
{'loss': 0.956, 'learning_rate': 1.6645581059099945e-05, 'epoch': 0.89}
{'loss': 1.449, 'learning_rate': 1.6642870052412794e-05, 'epoch': 0.89}
{'loss': 0.8971, 'learning_rate': 1.6640159045725645e-05, 'epoch': 0.89}
{'loss': 0.9813, 'learning_rate': 1.6637448039038497e-05, 'epoch': 0.89}
{'loss': 1.2775, 'learning_rate': 1.6634737032351346e-05, 'epoch': 0.89}
{'loss': 1.0043, 'learning_rate': 1.6632026025664198e-05, 'epoch': 0.89}
{'loss': 0.9735, 'learning_rate': 1.662931501897705e-05, 'epoch': 0.89}
{'loss': 0.6799, 'learning_rate': 1.6626604012289898e-05, 'epoch': 0.89}
{'loss': 0.8231, 'learning_rate': 1.6623893005602746e-05, 'epoch': 0.89}
{'loss': 1.2358, 'learning_rate': 1.6621181998915598e-05, 'epoch': 0.89}
{'loss': 1.1393, 'learning_rate': 1.6618470992228447e-05, 'epoch': 0.89}
{'loss': 0.7146, 'learning_rate': 1.66157599855413e-05, 'epoch': 0.89}
{'loss': 1.1669, 'learning_rate': 1.6613048978854147e-05, 'epoch': 0.89}
{'loss': 1.9243, 'learning_rate': 1.6610337972167e-05, 'epoch': 0.89}
{'loss': 0.6006, 'learning_rate': 1.660762696547985e-05, 'epoch': 0.89}
{'loss': 1.1236, 'learning_rate': 1.66049159587927e-05, 'epoch': 0.89}
{'loss': 0.8888, 'learning_rate': 1.6602204952105547e-05, 'epoch': 0.89}
{'loss': 1.1098, 'learning_rate': 1.65994939454184e-05, 'epoch': 0.89}
{'loss': 1.25, 'learning_rate': 1.6596782938731248e-05, 'epoch': 0.89}
{'loss': 0.6377, 'learning_rate': 1.65940719320441e-05, 'epoch': 0.89}
{'loss': 1.1992, 'learning_rate': 1.659136092535695e-05, 'epoch': 0.89}
{'loss': 1.8272, 'learning_rate': 1.65886499186698e-05, 'epoch': 0.89}
{'loss': 1.3303, 'learning_rate': 1.658593891198265e-05, 'epoch': 0.89}
{'loss': 0.8509, 'learning_rate': 1.65832279052955e-05, 'epoch': 0.89}
{'loss': 0.6771, 'learning_rate': 1.658051689860835e-05, 'epoch': 0.89}
{'loss': 1.1429, 'learning_rate': 1.65778058919212e-05, 'epoch': 0.89}

 45%|████▍     | 4952/11066 [18:08<21:52,  4.66it/s]
 45%|████▍     | 4953/11066 [18:08<21:57,  4.64it/s]
                                                    

 45%|████▍     | 4953/11066 [18:08<21:57,  4.64it/s]
 45%|████▍     | 4954/11066 [18:09<22:10,  4.59it/s]
                                                    

 45%|████▍     | 4954/11066 [18:09<22:10,  4.59it/s]
 45%|████▍     | 4955/11066 [18:09<22:01,  4.62it/s]
                                                    

 45%|████▍     | 4955/11066 [18:09<22:01,  4.62it/s]
 45%|████▍     | 4956/11066 [18:09<21:56,  4.64it/s]
                                                    

 45%|████▍     | 4956/11066 [18:09<21:56,  4.64it/s]
 45%|████▍     | 4957/11066 [18:09<21:52,  4.65it/s]
                                                    

 45%|████▍     | 4957/11066 [18:09<21:52,  4.65it/s]
 45%|████▍     | 4958/11066 [18:09<21:47,  4.67it/s]
                                                    

 45%|████▍     | 4958/11066 [18:09<21:47,  4.67it/s]
 45%|████▍     | 4959/11066 [18:10<22:08,  4.60it/s]
                                                    

 45%|████▍     | 4959/11066 [18:10<22:08,  4.60it/s]
 45%|████▍     | 4960/11066 [18:10<21:51,  4.66it/s]
                                                    

 45%|████▍     | 4960/11066 [18:10<21:51,  4.66it/s]
 45%|████▍     | 4961/11066 [18:10<21:49,  4.66it/s]
                                                    

 45%|████▍     | 4961/11066 [18:10<21:49,  4.66it/s]
 45%|████▍     | 4962/11066 [18:10<21:56,  4.64it/s]
                                                    

 45%|████▍     | 4962/11066 [18:10<21:56,  4.64it/s]
 45%|████▍     | 4963/11066 [18:11<21:51,  4.65it/s]
                                                    

 45%|████▍     | 4963/11066 [18:11<21:51,  4.65it/s]
 45%|████▍     | 4964/11066 [18:11<22:07,  4.60it/s]
                                                    

 45%|████▍     | 4964/11066 [18:11<22:07,  4.60it/s]
 45%|████▍     | 4965/11066 [18:11<21:59,  4.63it/s]
                                                    

 45%|████▍     | 4965/11066 [18:11<21:59,  4.63it/s]
 45%|████▍     | 4966/11066 [18:11<21:51,  4.65it/s]
                                                    

 45%|████▍     | 4966/11066 [18:11<21:51,  4.65it/s]
 45%|████▍     | 4967/11066 [18:11<21:45,  4.67it/s]
                                                    

 45%|████▍     | 4967/11066 [18:11<21:45,  4.67it/s]
 45%|████▍     | 4968/11066 [18:12<21:41,  4.69it/s]
                                                    

 45%|████▍     | 4968/11066 [18:12<21:41,  4.69it/s]
 45%|████▍     | 4969/11066 [18:12<21:38,  4.70it/s]
                                                    

 45%|████▍     | 4969/11066 [18:12<21:38,  4.70it/s]
 45%|████▍     | 4970/11066 [18:12<21:35,  4.70it/s]
                                                    

 45%|████▍     | 4970/11066 [18:12<21:35,  4.70it/s]
 45%|████▍     | 4971/11066 [18:12<21:35,  4.70it/s]
                                                    

 45%|████▍     | 4971/11066 [18:12<21:35,  4.70it/s]
 45%|████▍     | 4972/11066 [18:12<21:44,  4.67it/s]
                                                    

 45%|████▍     | 4972/11066 [18:12<21:44,  4.67it/s]
 45%|████▍     | 4973/11066 [18:13<21:43,  4.67it/s]
                                                    

 45%|████▍     | 4973/11066 [18:13<21:43,  4.67it/s]
 45%|████▍     | 4974/11066 [18:13<21:38,  4.69it/s]
                                                    

 45%|████▍     | 4974/11066 [18:13<21:38,  4.69it/s]
 45%|████▍     | 4975/11066 [18:13<21:33,  4.71it/s]
                                                    

 45%|████▍     | 4975/11066 [18:13<21:33,  4.71it/s]
 45%|████▍     | 4976/11066 [18:13<21:27,  4.73it/s]
                                                    

 45%|████▍     | 4976/11066 [18:13<21:27,  4.73it/s]
 45%|████▍     | 4977/11066 [18:14<21:50,  4.65it/s]
                                                    

 45%|████▍     | 4977/11066 [18:14<21:50,  4.65it/s]
 45%|████▍     | 4978/11066 [18:14<21:40,  4.68it/s]
                                                    

 45%|████▍     | 4978/11066 [18:14<21:40,  4.68it/s]
 45%|████▍     | 4979/11066 [18:14<21:38,  4.69it/s]
                                                    

 45%|████▍     | 4979/11066 [18:14<21:38,  4.69it/s]
 45%|████▌     | 4980/11066 [18:14<21:44,  4.66it/s]
                                                    

 45%|████▌     | 4980/11066 [18:14<21:44,  4.66it/s]
 45%|████▌     | 4981/11066 [18:14<21:33,  4.70it/s]
                                                    

 45%|████▌     | 4981/11066 [18:14<21:33,  4.70it/s]
 45%|████▌     | 4982/11066 [18:15<21:53,  4.63it/s]
                                                    

 45%|████▌     | 4982/11066 [18:15<21:53,  4.63it/s]
 45%|████▌     | 4983/11066 [18:15<21:56,  4.62it/s]
                                                    

 45%|████▌     | 4983/11066 [18:15<21:56,  4.62it/s]
 45%|████▌     | 4984/11066 [18:15<21:45,  4.66it/s]
                                                    

 45%|████▌     | 4984/11066 [18:15<21:45,  4.66it/s]
 45%|████▌     | 4985/11066 [18:15<21:43,  4.66it/s]
                                                    

 45%|████▌     | 4985/11066 [18:15<21:43,  4.66it/s]
 45%|████▌     | 4986/11066 [18:15<21:37,  4.69it/s]
                                                    

 45%|████▌     | 4986/11066 [18:15<21:37,  4.69it/s]
 45%|████▌     | 4987/11066 [18:16<21:57,  4.62it/s]
                                                    

 45%|████▌     | 4987/11066 [18:16<21:57,  4.62it/s]
 45%|████▌     | 4988/11066 [18:16<22:09,  4.57it/s]
                                                    

 45%|████▌     | 4988/11066 [18:16<22:09,  4.57it/s]
 45%|████▌     | 4989/11066 [18:16<21:59,  4.61it/s]
                                                    

 45%|████▌     | 4989/11066 [18:16<21:59,  4.61it/s]
 45%|████▌     | 4990/11066 [18:16<21:52,  4.63it/s]
                                                    

 45%|████▌     | 4990/11066 [18:16<21:52,  4.63it/s]
 45%|████▌     | 4991/11066 [18:17<22:05,  4.58it/s]
                                                    

 45%|████▌     | 4991/11066 [18:17<22:05,  4.58it/s]
 45%|████▌     | 4992/11066 [18:17<21:54,  4.62it/s]
                                                    

 45%|████▌     | 4992/11066 [18:17<21:54,  4.62it/s]
 45%|████▌     | 4993/11066 [18:17<21:45,  4.65it/s]
                                                    

 45%|████▌     | 4993/11066 [18:17<21:45,  4.65it/s]
 45%|████▌     | 4994/11066 [18:17<21:41,  4.67it/s]
                                                    

 45%|████▌     | 4994/11066 [18:17<21:41,  4.67it/s]
 45%|████▌     | 4995/11066 [18:17<21:37,  4.68it/s]
                                                    

 45%|████▌     | 4995/11066 [18:17<21:37,  4.68it/s]
 45%|████▌     | 4996/11066 [18:18<21:33,  4.69it/s]
                                                    

 45%|████▌     | 4996/11066 [18:18<21:33,  4.69it/s]
 45%|████▌     | 4997/11066 [18:18<21:31,  4.70it/s]
                                                    

 45%|████▌     | 4997/11066 [18:18<21:31,  4.70it/s]
 45%|████▌     | 4998/11066 [18:18<21:30,  4.70it/s]
                                                    

 45%|████▌     | 4998/11066 [18:18<21:30,  4.70it/s]
 45%|████▌     | 4999/11066 [18:18<21:38,  4.67it/s]
                                                    

 45%|████▌     | 4999/11066 [18:18<21:38,  4.67it/s]
 45%|████▌     | 5000/11066 [18:18<21:31,  4.70it/s]
                                                    

 45%|████▌     | 5000/11066 [18:18<21:31,  4.70it/s]
 45%|████▌     | 5001/11066 [18:19<21:49,  4.63it/s]
                                                    

 45%|████▌     | 5001/11066 [18:19<21:49,  4.63it/s]
 45%|████▌     | 5002/11066 [18:19<21:46,  4.64it/s]
                                                    

 45%|████▌     | 5002/11066 [18:19<21:46,  4.64it/s]
 45%|████▌     | 5003/11066 [18:19<21:39,  4.66it/s]
                                                    

 45%|████▌     | 5003/11066 [18:19<21:39,  4.66it/s]
 45%|████▌     | 5004/11066 [18:19<22:04,  4.58it/s]
                                                    

 45%|████▌     | 5004/11066 [18:19<22:04,  4.58it/s]
 45%|████▌     | 5005/11066 [18:20<22:16,  4.53it/s]
                                                    

 45%|████▌     | 5005/11066 [18:20<22:16,  4.53it/s]
 45%|████▌     | 5006/11066 [18:20<22:34,  4.47it/s]
                                                    

 45%|████▌     | 5006/11066 [18:20<22:34,  4.47it/s]
 45%|████▌     | 5007/11066 [18:20<22:45,  4.44it/s]
                                                    

 45%|████▌     | 5007/11066 [18:20<22:45,  4.44it/s]
 45%|████▌     | 5008/11066 [18:20<23:00,  4.39it/s]
                                                    

 45%|████▌     | 5008/11066 [18:20<23:00,  4.39it/s]
 45%|████▌     | 5009/11066 [18:21<23:02,  4.38it/s]
                                                    

 45%|████▌     | 5009/11066 [18:21<23:02,  4.38it/s]
 45%|████▌     | 5010/11066 [18:21<22:49,  4.42it/s]
                                                    

 45%|████▌     | 5010/11066 [18:21<22:49,  4.42it/s]
 45%|████▌     | 5011/11066 [18:21<22:50,  4.42it/s]
                                                    

 45%|████▌     | 5011/11066 [18:21<22:50,  4.42it/s]
 45%|████▌     | 5012/11066 [18:21<22:43,  4.44it/s]
                                                    

 45%|████▌     | 5012/11066 [18:21<22:43,  4.44it/s]
 45%|████▌     | 5013/11066 [18:21<22:38,  4.46it/s]
                                                    

 45%|████▌     | 5013/11066 [18:21<22:38,  4.46it/s]
 45%|████▌     | 5014/11066 [18:22<22:35,  4.46it/s]
                                                    

 45%|████▌     | 5014/11066 [18:22<22:35,  4.46it/s]
 45%|████▌     | 5015/11066 [18:22<22:31,  4.48it/s]
                                                    

 45%|████▌     | 5015/11066 [18:22<22:31,  4.48it/s]
 45%|████▌     | 5016/11066 [18:22<22:28,  4.49it/s]
                                                    

 45%|████▌     | 5016/11066 [18:22<22:28,  4.49it/s]
 45%|████▌     | 5017/11066 [18:22<22:28,  4.49it/s]
                                                    

 45%|████▌     | 5017/11066 [18:22<22:28,  4.49it/s]
 45%|████▌     | 5018/11066 [18:23<22:31,  4.47it/s]
                                                    

 45%|████▌     | 5018/11066 [18:23<22:31,  4.47it/s]
 45%|████▌     | 5019/11066 [18:23<22:30,  4.48it/s]
                                                    

 45%|████▌     | 5019/11066 [18:23<22:30,  4.48it/s]
 45%|████▌     | 5020/11066 [18:23<22:34,  4.46it/s]
                                                    

 45%|████▌     | 5020/11066 [18:23<22:34,  4.46it/s]
 45%|████▌     | 5021/11066 [18:23<22:38,  4.45it/s]
                                                    

 45%|████▌     | 5021/11066 [18:23<22:38,  4.45it/s]
 45%|████▌     | 5022/11066 [18:23<22:35,  4.46it/s]
                                                    

 45%|████▌     | 5022/11066 [18:23<22:35,  4.46it/s]
 45%|████▌     | 5023/11066 [18:24<22:49,  4.41it/s]
                                                    

 45%|████▌     | 5023/11066 [18:24<22:49,  4.41it/s]
 45%|████▌     | 5024/11066 [18:24<22:24,  4.49it/s]
                                                    

 45%|████▌     | 5024/11066 [18:24<22:24,  4.49it/s]
 45%|████▌     | 5025/11066 [18:24<22:08,  4.55it/s]
                                                    

 45%|████▌     | 5025/11066 [18:24<22:08,  4.55it/s]
 45%|████▌     | 5026/11066 [18:24<21:54,  4.60it/s]
                                                    

 45%|████▌     | 5026/11066 [18:24<21:54,  4.60it/s]
 45%|████▌     | 5027/11066 [18:25<21:51,  4.60it/s]
                                                    

 45%|████▌     | 5027/11066 [18:25<21:51,  4.60it/s]
 45%|████▌     | 5028/11066 [18:25<21:54,  4.59it/s]
                                                    

 45%|████▌     | 5028/11066 [18:25<21:54,  4.59it/s]
 45%|████▌     | 5029/11066 [18:25<21:43,  4.63it/s]
                                                    

 45%|████▌     | 5029/11066 [18:25<21:43,  4.63it/s]
 45%|████▌     | 5030/11066 [18:25<21:40,  4.64it/s]
                                                    

 45%|████▌     | 5030/11066 [18:25<21:40,  4.64it/s]
 45%|████▌     | 5031/11066 [18:25<21:35,  4.66it/s]
                                                    

 45%|████▌     | 5031/11066 [18:25<21:35,  4.66it/s]
 45%|████▌     | 5032/11066 [18:26<21:52,  4.60it/s]
                                                    

 45%|████▌     | 5032/11066 [18:26<21:52,  4.60it/s]
 45%|████▌     | 5033/11066 [18:26<22:05,  4.55it/s]
                                                    

 45%|████▌     | 5033/11066 [18:26<22:05,  4.55it/s]
 45%|████▌     | 5034/11066 [18:26<22:11,  4.53it/s]
                                                    

 45%|████▌     | 5034/11066 [18:26<22:11,  4.53it/s]
 45%|████▌     | 5035/11066 [18:26<22:13,  4.52it/s]
                                                    

 45%|████▌     | 5035/11066 [18:26<22:13,  4.52it/s]
 46%|████▌     | 5036/11066 [18:26<21:56,  4.58it/s]
                                                    

 46%|████▌     | 5036/11066 [18:26<21:56,  4.58it/s]
 46%|████▌     | 5037/11066 [18:27<22:03,  4.55it/s]
                                                    

 46%|████▌     | 5037/11066 [18:27<22:03,  4.55it/s]
 46%|████▌     | 5038/11066 [18:27<22:10,  4.53it/s]
                                                    

 46%|████▌     | 5038/11066 [18:27<22:10,  4.53it/s]
 46%|████▌     | 5039/11066 [18:27<21:56,  4.58it/s]
                                                    

 46%|████▌     | 5039/11066 [18:27<21:56,  4.58it/s]
 46%|████▌     | 5040/11066 [18:27<21:44,  4.62it/s]
                                                    

 46%|████▌     | 5040/11066 [18:27<21:44,  4.62it/s]
 46%|████▌     | 5041/11066 [18:28<21:44,  4.62it/s]
                                                    

 46%|████▌     | 5041/11066 [18:28<21:44,  4.62it/s]
 46%|████▌     | 5042/11066 [18:28<22:10,  4.53it/s]
                                                    

 46%|████▌     | 5042/11066 [18:28<22:10,  4.53it/s]
 46%|████▌     | 5043/11066 [18:28<22:21,  4.49it/s]
                                                    

 46%|████▌     | 5043/11066 [18:28<22:21,  4.49it/s]
 46%|████▌     | 5044/11066 [18:28<22:24,  4.48it/s]
                                                    

 46%|████▌     | 5044/11066 [18:28<22:24,  4.48it/s]
 46%|████▌     | 5045/11066 [18:28<22:27,  4.47it/s]
                                                    

 46%|████▌     | 5045/11066 [18:28<22:27,  4.47it/s]
 46%|████▌     | 5046/11066 [18:29<22:32,  4.45it/s]
                                                    

 46%|████▌     | 5046/11066 [18:29<22:32,  4.45it/s]
 46%|████▌     | 5047/11066 [18:29<22:38,  4.43it/s]
                                                    

 46%|████▌     | 5047/11066 [18:29<22:38,  4.43it/s]
 46%|████▌     | 5048/11066 [18:29<22:07,  4.53it/s]
                                                    

 46%|████▌     | 5048/11066 [18:29<22:07,  4.53it/s]
 46%|████▌     | 5049/11066 [18:29<21:55,  4.57it/s]
                                                    

 46%|████▌     | 5049/11066 [18:29<21:55,  4.57it/s]
 46%|████▌     | 5050/11066 [18:30<21:53,  4.58it/s]
                                                    

 46%|████▌     | 5050/11066 [18:30<21:53,  4.58it/s]
 46%|████▌     | 5051/11066 [18:30<22:02,  4.55it/s]
                                                    

 46%|████▌     | 5051/11066 [18:30<22:02,  4.55it/s]
 46%|████▌     | 5052/11066 [18:30<21:58,  4.56it/s]
                                                    

 46%|████▌     | 5052/11066 [18:30<21:58,  4.56it/s]
 46%|████▌     | 5053/11066 [18:30<21:52,  4.58it/s]
                                                    

 46%|████▌     | 5053/11066 [18:30<21:52,  4.58it/s]
 46%|████▌     | 5054/11066 [18:30<21:43,  4.61it/s]
                                                    

 46%|████▌     | 5054/11066 [18:30<21:43,  4.61it/s]
 46%|████▌     | 5055/11066 [18:31<21:55,  4.57it/s]
                                                    

 46%|████▌     | 5055/11066 [18:31<21:55,  4.57it/s]
 46%|████▌     | 5056/11066 [18:31<21:51,  4.58it/s]
                                                    

 46%|████▌     | 5056/11066 [18:31<21:51,  4.58it/s]
 46%|████▌     | 5057/11066 [18:31<21:35,  4.64it/s]
                                                    

 46%|████▌     | 5057/11066 [18:31<21:35,  4.64it/s]
 46%|████▌     | 5058/11066 [18:31<21:31,  4.65it/s]
                                                    

 46%|████▌     | 5058/11066 [18:31<21:31,  4.65it/s]
 46%|████▌     | 5059/11066 [18:32<21:47,  4.59it/s]
                                                    

 46%|████▌     | 5059/11066 [18:32<21:47,  4.59it/s]
 46%|████▌     | 5060/11066 [18:32<22:02,  4.54it/s]
                                                    

 46%|████▌     | 5060/11066 [18:32<22:02,  4.54it/s]
 46%|████▌     | 5061/11066 [18:32<22:17,  4.49it/s]
                                                    

 46%|████▌     | 5061/11066 [18:32<22:17,  4.49it/s]
 46%|████▌     | 5062/11066 [18:32<22:11,  4.51it/s]
                                                    

 46%|████▌     | 5062/11066 [18:32<22:11,  4.51it/s]
 46%|████▌     | 5063/11066 [18:32<22:05,  4.53it/s]
                                                    

 46%|████▌     | 5063/11066 [18:32<22:05,  4.53it/s]
 46%|████▌     | 5064/11066 [18:33<22:08,  4.52it/s]
                                                    

 46%|████▌     | 5064/11066 [18:33<22:08,  4.52it/s]
 46%|████▌     | 5065/11066 [18:33<22:03,  4.54it/s]
                                                    
{'loss': 1.0372, 'learning_rate': 1.657509488523405e-05, 'epoch': 0.89}
{'loss': 0.9179, 'learning_rate': 1.65723838785469e-05, 'epoch': 0.9}
{'loss': 1.2971, 'learning_rate': 1.6569672871859752e-05, 'epoch': 0.9}
{'loss': 0.9167, 'learning_rate': 1.65669618651726e-05, 'epoch': 0.9}
{'loss': 1.9013, 'learning_rate': 1.6564250858485453e-05, 'epoch': 0.9}
{'loss': 0.7445, 'learning_rate': 1.6561539851798304e-05, 'epoch': 0.9}
{'loss': 0.8801, 'learning_rate': 1.655882884511115e-05, 'epoch': 0.9}
{'loss': 0.8752, 'learning_rate': 1.6556117838424e-05, 'epoch': 0.9}
{'loss': 1.3146, 'learning_rate': 1.6553406831736853e-05, 'epoch': 0.9}
{'loss': 1.8209, 'learning_rate': 1.65506958250497e-05, 'epoch': 0.9}
{'loss': 0.7834, 'learning_rate': 1.6547984818362553e-05, 'epoch': 0.9}
{'loss': 0.7302, 'learning_rate': 1.6545273811675402e-05, 'epoch': 0.9}
{'loss': 1.3716, 'learning_rate': 1.6542562804988254e-05, 'epoch': 0.9}
{'loss': 1.6315, 'learning_rate': 1.6539851798301105e-05, 'epoch': 0.9}
{'loss': 0.9814, 'learning_rate': 1.653714079161395e-05, 'epoch': 0.9}
{'loss': 1.6803, 'learning_rate': 1.6534429784926802e-05, 'epoch': 0.9}
{'loss': 0.7457, 'learning_rate': 1.6531718778239654e-05, 'epoch': 0.9}
{'loss': 0.9625, 'learning_rate': 1.6529007771552503e-05, 'epoch': 0.9}
{'loss': 0.5657, 'learning_rate': 1.6526296764865354e-05, 'epoch': 0.9}
{'loss': 1.4864, 'learning_rate': 1.6523585758178206e-05, 'epoch': 0.9}
{'loss': 0.7145, 'learning_rate': 1.6520874751491055e-05, 'epoch': 0.9}
{'loss': 1.0613, 'learning_rate': 1.6518163744803907e-05, 'epoch': 0.9}
{'loss': 0.8687, 'learning_rate': 1.651545273811675e-05, 'epoch': 0.9}
{'loss': 0.5594, 'learning_rate': 1.6512741731429603e-05, 'epoch': 0.9}
{'loss': 1.3705, 'learning_rate': 1.6510030724742455e-05, 'epoch': 0.9}
{'loss': 0.9064, 'learning_rate': 1.6507319718055304e-05, 'epoch': 0.9}
{'loss': 0.6735, 'learning_rate': 1.6504608711368156e-05, 'epoch': 0.9}
{'loss': 0.9884, 'learning_rate': 1.6501897704681007e-05, 'epoch': 0.9}
{'loss': 0.7746, 'learning_rate': 1.6499186697993856e-05, 'epoch': 0.9}
{'loss': 0.7133, 'learning_rate': 1.6496475691306708e-05, 'epoch': 0.9}
{'loss': 1.3132, 'learning_rate': 1.6493764684619556e-05, 'epoch': 0.9}
{'loss': 1.2309, 'learning_rate': 1.6491053677932405e-05, 'epoch': 0.9}
{'loss': 1.8962, 'learning_rate': 1.6488342671245256e-05, 'epoch': 0.9}
{'loss': 0.7989, 'learning_rate': 1.6485631664558105e-05, 'epoch': 0.9}
{'loss': 0.5087, 'learning_rate': 1.6482920657870957e-05, 'epoch': 0.9}
{'loss': 1.439, 'learning_rate': 1.648020965118381e-05, 'epoch': 0.9}
{'loss': 1.0163, 'learning_rate': 1.6477498644496657e-05, 'epoch': 0.9}
{'loss': 0.9161, 'learning_rate': 1.647478763780951e-05, 'epoch': 0.9}
{'loss': 1.2906, 'learning_rate': 1.6472076631122357e-05, 'epoch': 0.9}
{'loss': 0.6974, 'learning_rate': 1.6469365624435206e-05, 'epoch': 0.9}
{'loss': 0.694, 'learning_rate': 1.6466654617748057e-05, 'epoch': 0.9}
{'loss': 0.9936, 'learning_rate': 1.646394361106091e-05, 'epoch': 0.9}
{'loss': 0.714, 'learning_rate': 1.6461232604373758e-05, 'epoch': 0.9}
{'loss': 1.102, 'learning_rate': 1.645852159768661e-05, 'epoch': 0.9}
{'loss': 1.1824, 'learning_rate': 1.6455810590999458e-05, 'epoch': 0.9}
{'loss': 0.6751, 'learning_rate': 1.645309958431231e-05, 'epoch': 0.9}
{'loss': 1.1895, 'learning_rate': 1.6450388577625158e-05, 'epoch': 0.9}
{'loss': 0.8975, 'learning_rate': 1.6447677570938007e-05, 'epoch': 0.9}
{'loss': 0.9645, 'learning_rate': 1.644496656425086e-05, 'epoch': 0.9}
{'loss': 0.8344, 'learning_rate': 1.644225555756371e-05, 'epoch': 0.9}
{'loss': 0.7746, 'learning_rate': 1.643954455087656e-05, 'epoch': 0.9}
{'loss': 0.5767, 'learning_rate': 1.643683354418941e-05, 'epoch': 0.9}
{'loss': 0.8043, 'learning_rate': 1.6434122537502262e-05, 'epoch': 0.9}
{'loss': 1.6544, 'learning_rate': 1.643141153081511e-05, 'epoch': 0.9}
{'loss': 0.981, 'learning_rate': 1.642870052412796e-05, 'epoch': 0.9}
{'loss': 0.8566, 'learning_rate': 1.6425989517440808e-05, 'epoch': 0.9}
{'loss': 1.5994, 'learning_rate': 1.642327851075366e-05, 'epoch': 0.91}
{'loss': 0.8646, 'learning_rate': 1.642056750406651e-05, 'epoch': 0.91}
{'loss': 0.7152, 'learning_rate': 1.641785649737936e-05, 'epoch': 0.91}
{'loss': 1.4722, 'learning_rate': 1.641514549069221e-05, 'epoch': 0.91}
{'loss': 1.016, 'learning_rate': 1.6412434484005063e-05, 'epoch': 0.91}
{'loss': 0.8141, 'learning_rate': 1.6409723477317912e-05, 'epoch': 0.91}
{'loss': 0.4782, 'learning_rate': 1.640701247063076e-05, 'epoch': 0.91}
{'loss': 0.9168, 'learning_rate': 1.6404301463943612e-05, 'epoch': 0.91}
{'loss': 0.7802, 'learning_rate': 1.640159045725646e-05, 'epoch': 0.91}
{'loss': 1.4356, 'learning_rate': 1.6398879450569312e-05, 'epoch': 0.91}
{'loss': 1.0088, 'learning_rate': 1.639616844388216e-05, 'epoch': 0.91}
{'loss': 0.7062, 'learning_rate': 1.6393457437195013e-05, 'epoch': 0.91}
{'loss': 1.3257, 'learning_rate': 1.6390746430507865e-05, 'epoch': 0.91}
{'loss': 0.5383, 'learning_rate': 1.638803542382071e-05, 'epoch': 0.91}
{'loss': 1.2583, 'learning_rate': 1.638532441713356e-05, 'epoch': 0.91}
{'loss': 0.9119, 'learning_rate': 1.6382613410446413e-05, 'epoch': 0.91}
{'loss': 1.3315, 'learning_rate': 1.6379902403759262e-05, 'epoch': 0.91}
{'loss': 1.0579, 'learning_rate': 1.6377191397072114e-05, 'epoch': 0.91}
{'loss': 0.9688, 'learning_rate': 1.6374480390384965e-05, 'epoch': 0.91}
{'loss': 1.3893, 'learning_rate': 1.6371769383697814e-05, 'epoch': 0.91}
{'loss': 1.5397, 'learning_rate': 1.6369058377010666e-05, 'epoch': 0.91}
{'loss': 1.2042, 'learning_rate': 1.636634737032351e-05, 'epoch': 0.91}
{'loss': 1.382, 'learning_rate': 1.6363636363636363e-05, 'epoch': 0.91}
{'loss': 1.0245, 'learning_rate': 1.6360925356949214e-05, 'epoch': 0.91}
{'loss': 0.729, 'learning_rate': 1.6358214350262063e-05, 'epoch': 0.91}
{'loss': 1.3579, 'learning_rate': 1.6355503343574915e-05, 'epoch': 0.91}
{'loss': 1.5212, 'learning_rate': 1.6352792336887766e-05, 'epoch': 0.91}
{'loss': 1.0578, 'learning_rate': 1.6350081330200615e-05, 'epoch': 0.91}
{'loss': 0.9893, 'learning_rate': 1.6347370323513467e-05, 'epoch': 0.91}
{'loss': 1.279, 'learning_rate': 1.6344659316826315e-05, 'epoch': 0.91}
{'loss': 1.0578, 'learning_rate': 1.6341948310139164e-05, 'epoch': 0.91}
{'loss': 0.5792, 'learning_rate': 1.6339237303452015e-05, 'epoch': 0.91}
{'loss': 0.4096, 'learning_rate': 1.6336526296764864e-05, 'epoch': 0.91}
{'loss': 1.0492, 'learning_rate': 1.6333815290077716e-05, 'epoch': 0.91}
{'loss': 1.1527, 'learning_rate': 1.6331104283390568e-05, 'epoch': 0.91}
{'loss': 1.4784, 'learning_rate': 1.6328393276703416e-05, 'epoch': 0.91}
{'loss': 1.103, 'learning_rate': 1.6325682270016268e-05, 'epoch': 0.91}
{'loss': 0.946, 'learning_rate': 1.6322971263329116e-05, 'epoch': 0.91}
{'loss': 1.3014, 'learning_rate': 1.6320260256641965e-05, 'epoch': 0.91}
{'loss': 1.0123, 'learning_rate': 1.6317549249954816e-05, 'epoch': 0.91}
{'loss': 0.5164, 'learning_rate': 1.631483824326767e-05, 'epoch': 0.91}
{'loss': 1.5717, 'learning_rate': 1.6312127236580517e-05, 'epoch': 0.91}
{'loss': 1.4067, 'learning_rate': 1.630941622989337e-05, 'epoch': 0.91}
{'loss': 0.8694, 'learning_rate': 1.6306705223206217e-05, 'epoch': 0.91}
{'loss': 1.0442, 'learning_rate': 1.630399421651907e-05, 'epoch': 0.91}
{'loss': 1.8876, 'learning_rate': 1.6301283209831917e-05, 'epoch': 0.91}
{'loss': 1.8832, 'learning_rate': 1.6298572203144766e-05, 'epoch': 0.91}
{'loss': 1.0942, 'learning_rate': 1.6295861196457618e-05, 'epoch': 0.91}
{'loss': 1.4258, 'learning_rate': 1.629315018977047e-05, 'epoch': 0.91}
{'loss': 0.5786, 'learning_rate': 1.6290439183083318e-05, 'epoch': 0.91}
{'loss': 1.4255, 'learning_rate': 1.628772817639617e-05, 'epoch': 0.91}
{'loss': 1.1229, 'learning_rate': 1.628501716970902e-05, 'epoch': 0.91}
{'loss': 0.515, 'learning_rate': 1.628230616302187e-05, 'epoch': 0.91}
{'loss': 1.2637, 'learning_rate': 1.627959515633472e-05, 'epoch': 0.91}
{'loss': 0.9214, 'learning_rate': 1.6276884149647567e-05, 'epoch': 0.91}
{'loss': 0.9832, 'learning_rate': 1.627417314296042e-05, 'epoch': 0.92}
{'loss': 1.4539, 'learning_rate': 1.627146213627327e-05, 'epoch': 0.92}

 46%|████▌     | 5065/11066 [18:33<22:03,  4.54it/s]
 46%|████▌     | 5066/11066 [18:33<21:59,  4.55it/s]
                                                    

 46%|████▌     | 5066/11066 [18:33<21:59,  4.55it/s]
 46%|████▌     | 5067/11066 [18:33<21:52,  4.57it/s]
                                                    

 46%|████▌     | 5067/11066 [18:33<21:52,  4.57it/s]
 46%|████▌     | 5068/11066 [18:34<21:58,  4.55it/s]
                                                    

 46%|████▌     | 5068/11066 [18:34<21:58,  4.55it/s]
 46%|████▌     | 5069/11066 [18:34<22:06,  4.52it/s]
                                                    

 46%|████▌     | 5069/11066 [18:34<22:06,  4.52it/s]
 46%|████▌     | 5070/11066 [18:34<22:09,  4.51it/s]
                                                    

 46%|████▌     | 5070/11066 [18:34<22:09,  4.51it/s]
 46%|████▌     | 5071/11066 [18:34<22:01,  4.54it/s]
                                                    

 46%|████▌     | 5071/11066 [18:34<22:01,  4.54it/s]
 46%|████▌     | 5072/11066 [18:34<21:48,  4.58it/s]
                                                    

 46%|████▌     | 5072/11066 [18:34<21:48,  4.58it/s]
 46%|████▌     | 5073/11066 [18:35<22:02,  4.53it/s]
                                                    

 46%|████▌     | 5073/11066 [18:35<22:02,  4.53it/s]
 46%|████▌     | 5074/11066 [18:35<22:08,  4.51it/s]
                                                    

 46%|████▌     | 5074/11066 [18:35<22:08,  4.51it/s]
 46%|████▌     | 5075/11066 [18:35<22:09,  4.51it/s]
                                                    

 46%|████▌     | 5075/11066 [18:35<22:09,  4.51it/s]
 46%|████▌     | 5076/11066 [18:35<22:12,  4.50it/s]
                                                    

 46%|████▌     | 5076/11066 [18:35<22:12,  4.50it/s]
 46%|████▌     | 5077/11066 [18:36<22:00,  4.54it/s]
                                                    

 46%|████▌     | 5077/11066 [18:36<22:00,  4.54it/s]
 46%|████▌     | 5078/11066 [18:36<22:04,  4.52it/s]
                                                    

 46%|████▌     | 5078/11066 [18:36<22:04,  4.52it/s]
 46%|████▌     | 5079/11066 [18:36<22:07,  4.51it/s]
                                                    

 46%|████▌     | 5079/11066 [18:36<22:07,  4.51it/s]
 46%|████▌     | 5080/11066 [18:36<22:01,  4.53it/s]
                                                    

 46%|████▌     | 5080/11066 [18:36<22:01,  4.53it/s]
 46%|████▌     | 5081/11066 [18:36<21:48,  4.58it/s]
                                                    

 46%|████▌     | 5081/11066 [18:36<21:48,  4.58it/s]
 46%|████▌     | 5082/11066 [18:37<22:00,  4.53it/s]
                                                    

 46%|████▌     | 5082/11066 [18:37<22:00,  4.53it/s]
 46%|████▌     | 5083/11066 [18:37<22:06,  4.51it/s]
                                                    

 46%|████▌     | 5083/11066 [18:37<22:06,  4.51it/s]
 46%|████▌     | 5084/11066 [18:37<22:07,  4.50it/s]
                                                    

 46%|████▌     | 5084/11066 [18:37<22:07,  4.50it/s]
 46%|████▌     | 5085/11066 [18:37<21:59,  4.53it/s]
                                                    

 46%|████▌     | 5085/11066 [18:37<21:59,  4.53it/s]
 46%|████▌     | 5086/11066 [18:37<22:02,  4.52it/s]
                                                    

 46%|████▌     | 5086/11066 [18:37<22:02,  4.52it/s]
 46%|████▌     | 5087/11066 [18:38<21:44,  4.58it/s]
                                                    

 46%|████▌     | 5087/11066 [18:38<21:44,  4.58it/s]
 46%|████▌     | 5088/11066 [18:38<21:58,  4.53it/s]
                                                    

 46%|████▌     | 5088/11066 [18:38<21:58,  4.53it/s]
 46%|████▌     | 5089/11066 [18:38<22:04,  4.51it/s]
                                                    

 46%|████▌     | 5089/11066 [18:38<22:04,  4.51it/s]
 46%|████▌     | 5090/11066 [18:38<21:55,  4.54it/s]
                                                    

 46%|████▌     | 5090/11066 [18:38<21:55,  4.54it/s]
 46%|████▌     | 5091/11066 [18:39<21:53,  4.55it/s]
                                                    

 46%|████▌     | 5091/11066 [18:39<21:53,  4.55it/s]
 46%|████▌     | 5092/11066 [18:39<21:57,  4.53it/s]
                                                    

 46%|████▌     | 5092/11066 [18:39<21:57,  4.53it/s]
 46%|████▌     | 5093/11066 [18:39<21:41,  4.59it/s]
                                                    

 46%|████▌     | 5093/11066 [18:39<21:41,  4.59it/s]
 46%|████▌     | 5094/11066 [18:39<21:49,  4.56it/s]
                                                    

 46%|████▌     | 5094/11066 [18:39<21:49,  4.56it/s]
 46%|████▌     | 5095/11066 [18:39<21:36,  4.61it/s]
                                                    

 46%|████▌     | 5095/11066 [18:39<21:36,  4.61it/s]
 46%|████▌     | 5096/11066 [18:40<21:44,  4.57it/s]
                                                    

 46%|████▌     | 5096/11066 [18:40<21:44,  4.57it/s]
 46%|████▌     | 5097/11066 [18:40<21:32,  4.62it/s]
                                                    

 46%|████▌     | 5097/11066 [18:40<21:32,  4.62it/s]
 46%|████▌     | 5098/11066 [18:40<21:32,  4.62it/s]
                                                    

 46%|████▌     | 5098/11066 [18:40<21:32,  4.62it/s]
 46%|████▌     | 5099/11066 [18:40<21:45,  4.57it/s]
                                                    

 46%|████▌     | 5099/11066 [18:40<21:45,  4.57it/s]
 46%|████▌     | 5100/11066 [18:41<21:35,  4.61it/s]
                                                    

 46%|████▌     | 5100/11066 [18:41<21:35,  4.61it/s]
 46%|████▌     | 5101/11066 [18:41<21:37,  4.60it/s]
                                                    

 46%|████▌     | 5101/11066 [18:41<21:37,  4.60it/s]
 46%|████▌     | 5102/11066 [18:41<21:49,  4.55it/s]
                                                    

 46%|████▌     | 5102/11066 [18:41<21:49,  4.55it/s]
 46%|████▌     | 5103/11066 [18:41<21:59,  4.52it/s]
                                                    

 46%|████▌     | 5103/11066 [18:41<21:59,  4.52it/s]
 46%|████▌     | 5104/11066 [18:41<21:53,  4.54it/s]
                                                    

 46%|████▌     | 5104/11066 [18:41<21:53,  4.54it/s]
 46%|████▌     | 5105/11066 [18:42<21:35,  4.60it/s]
                                                    

 46%|████▌     | 5105/11066 [18:42<21:35,  4.60it/s]
 46%|████▌     | 5106/11066 [18:42<21:25,  4.64it/s]
                                                    

 46%|████▌     | 5106/11066 [18:42<21:25,  4.64it/s]
 46%|████▌     | 5107/11066 [18:42<21:12,  4.68it/s]
                                                    

 46%|████▌     | 5107/11066 [18:42<21:12,  4.68it/s]
 46%|████▌     | 5108/11066 [18:42<21:30,  4.62it/s]
                                                    

 46%|████▌     | 5108/11066 [18:42<21:30,  4.62it/s]
 46%|████▌     | 5109/11066 [18:43<21:40,  4.58it/s]
                                                    

 46%|████▌     | 5109/11066 [18:43<21:40,  4.58it/s]
 46%|████▌     | 5110/11066 [18:43<21:48,  4.55it/s]
                                                    

 46%|████▌     | 5110/11066 [18:43<21:48,  4.55it/s]
 46%|████▌     | 5111/11066 [18:43<21:35,  4.60it/s]
                                                    

 46%|████▌     | 5111/11066 [18:43<21:35,  4.60it/s]
 46%|████▌     | 5112/11066 [18:43<21:27,  4.63it/s]
                                                    

 46%|████▌     | 5112/11066 [18:43<21:27,  4.63it/s]
 46%|████▌     | 5113/11066 [18:43<21:18,  4.65it/s]
                                                    

 46%|████▌     | 5113/11066 [18:43<21:18,  4.65it/s]
 46%|████▌     | 5114/11066 [18:44<21:20,  4.65it/s]
                                                    

 46%|████▌     | 5114/11066 [18:44<21:20,  4.65it/s]
 46%|████▌     | 5115/11066 [18:44<21:12,  4.68it/s]
                                                    

 46%|████▌     | 5115/11066 [18:44<21:12,  4.68it/s]
 46%|████▌     | 5116/11066 [18:44<21:32,  4.60it/s]
                                                    

 46%|████▌     | 5116/11066 [18:44<21:32,  4.60it/s]
 46%|████▌     | 5117/11066 [18:44<21:25,  4.63it/s]
                                                    

 46%|████▌     | 5117/11066 [18:44<21:25,  4.63it/s]
 46%|████▌     | 5118/11066 [18:44<21:18,  4.65it/s]
                                                    

 46%|████▌     | 5118/11066 [18:44<21:18,  4.65it/s]
 46%|████▋     | 5119/11066 [18:45<21:34,  4.59it/s]
                                                    

 46%|████▋     | 5119/11066 [18:45<21:34,  4.59it/s]
 46%|████▋     | 5120/11066 [18:45<21:26,  4.62it/s]
                                                    

 46%|████▋     | 5120/11066 [18:45<21:26,  4.62it/s]
 46%|████▋     | 5121/11066 [18:45<21:19,  4.65it/s]
                                                    

 46%|████▋     | 5121/11066 [18:45<21:19,  4.65it/s]
 46%|████▋     | 5122/11066 [18:45<21:32,  4.60it/s]
                                                    

 46%|████▋     | 5122/11066 [18:45<21:32,  4.60it/s]
 46%|████▋     | 5123/11066 [18:46<21:22,  4.63it/s]
                                                    

 46%|████▋     | 5123/11066 [18:46<21:22,  4.63it/s]
 46%|████▋     | 5124/11066 [18:46<21:33,  4.59it/s]
                                                    

 46%|████▋     | 5124/11066 [18:46<21:33,  4.59it/s]
 46%|████▋     | 5125/11066 [18:46<21:23,  4.63it/s]
                                                    

 46%|████▋     | 5125/11066 [18:46<21:23,  4.63it/s]
 46%|████▋     | 5126/11066 [18:46<21:16,  4.65it/s]
                                                    

 46%|████▋     | 5126/11066 [18:46<21:16,  4.65it/s]
 46%|████▋     | 5127/11066 [18:46<21:11,  4.67it/s]
                                                    

 46%|████▋     | 5127/11066 [18:46<21:11,  4.67it/s]
 46%|████▋     | 5128/11066 [18:47<21:14,  4.66it/s]
                                                    

 46%|████▋     | 5128/11066 [18:47<21:14,  4.66it/s]
 46%|████▋     | 5129/11066 [18:47<21:23,  4.63it/s]
                                                    

 46%|████▋     | 5129/11066 [18:47<21:23,  4.63it/s]
 46%|████▋     | 5130/11066 [18:47<21:34,  4.58it/s]
                                                    

 46%|████▋     | 5130/11066 [18:47<21:34,  4.58it/s]
 46%|████▋     | 5131/11066 [18:47<21:18,  4.64it/s]
                                                    

 46%|████▋     | 5131/11066 [18:47<21:18,  4.64it/s]
 46%|████▋     | 5132/11066 [18:47<21:15,  4.65it/s]
                                                    

 46%|████▋     | 5132/11066 [18:47<21:15,  4.65it/s]
 46%|████▋     | 5133/11066 [18:48<21:10,  4.67it/s]
                                                    

 46%|████▋     | 5133/11066 [18:48<21:10,  4.67it/s]
 46%|████▋     | 5134/11066 [18:48<21:06,  4.68it/s]
                                                    

 46%|████▋     | 5134/11066 [18:48<21:06,  4.68it/s]
 46%|████▋     | 5135/11066 [18:48<21:04,  4.69it/s]
                                                    

 46%|████▋     | 5135/11066 [18:48<21:04,  4.69it/s]
 46%|████▋     | 5136/11066 [18:48<21:02,  4.70it/s]
                                                    

 46%|████▋     | 5136/11066 [18:48<21:02,  4.70it/s]
 46%|████▋     | 5137/11066 [18:49<21:18,  4.64it/s]
                                                    

 46%|████▋     | 5137/11066 [18:49<21:18,  4.64it/s]
 46%|████▋     | 5138/11066 [18:49<21:20,  4.63it/s]
                                                    

 46%|████▋     | 5138/11066 [18:49<21:20,  4.63it/s]
 46%|████▋     | 5139/11066 [18:49<21:11,  4.66it/s]
                                                    

 46%|████▋     | 5139/11066 [18:49<21:11,  4.66it/s]
 46%|████▋     | 5140/11066 [18:49<21:01,  4.70it/s]
                                                    

 46%|████▋     | 5140/11066 [18:49<21:01,  4.70it/s]
 46%|████▋     | 5141/11066 [18:49<20:55,  4.72it/s]
                                                    

 46%|████▋     | 5141/11066 [18:49<20:55,  4.72it/s]
 46%|████▋     | 5142/11066 [18:50<20:57,  4.71it/s]
                                                    

 46%|████▋     | 5142/11066 [18:50<20:57,  4.71it/s]
 46%|████▋     | 5143/11066 [18:50<20:55,  4.72it/s]
                                                    

 46%|████▋     | 5143/11066 [18:50<20:55,  4.72it/s]
 46%|████▋     | 5144/11066 [18:50<21:15,  4.64it/s]
                                                    

 46%|████▋     | 5144/11066 [18:50<21:15,  4.64it/s]
 46%|████▋     | 5145/11066 [18:50<21:28,  4.60it/s]
                                                    

 46%|████▋     | 5145/11066 [18:50<21:28,  4.60it/s]
 47%|████▋     | 5146/11066 [18:50<21:35,  4.57it/s]
                                                    

 47%|████▋     | 5146/11066 [18:50<21:35,  4.57it/s]
 47%|████▋     | 5147/11066 [18:51<21:41,  4.55it/s]
                                                    

 47%|████▋     | 5147/11066 [18:51<21:41,  4.55it/s]
 47%|████▋     | 5148/11066 [18:51<21:27,  4.60it/s]
                                                    

 47%|████▋     | 5148/11066 [18:51<21:27,  4.60it/s]
 47%|████▋     | 5149/11066 [18:51<21:18,  4.63it/s]
                                                    

 47%|████▋     | 5149/11066 [18:51<21:18,  4.63it/s]
 47%|████▋     | 5150/11066 [18:51<21:11,  4.65it/s]
                                                    

 47%|████▋     | 5150/11066 [18:51<21:11,  4.65it/s]
 47%|████▋     | 5151/11066 [18:52<21:05,  4.67it/s]
                                                    

 47%|████▋     | 5151/11066 [18:52<21:05,  4.67it/s]
 47%|████▋     | 5152/11066 [18:52<21:02,  4.69it/s]
                                                    

 47%|████▋     | 5152/11066 [18:52<21:02,  4.69it/s]
 47%|████▋     | 5153/11066 [18:52<20:59,  4.70it/s]
                                                    

 47%|████▋     | 5153/11066 [18:52<20:59,  4.70it/s]
 47%|████▋     | 5154/11066 [18:52<20:58,  4.70it/s]
                                                    

 47%|████▋     | 5154/11066 [18:52<20:58,  4.70it/s]
 47%|████▋     | 5155/11066 [18:52<20:56,  4.70it/s]
                                                    

 47%|████▋     | 5155/11066 [18:52<20:56,  4.70it/s]
 47%|████▋     | 5156/11066 [18:53<20:54,  4.71it/s]
                                                    

 47%|████▋     | 5156/11066 [18:53<20:54,  4.71it/s]
 47%|████▋     | 5157/11066 [18:53<21:03,  4.68it/s]
                                                    

 47%|████▋     | 5157/11066 [18:53<21:03,  4.68it/s]
 47%|████▋     | 5158/11066 [18:53<21:08,  4.66it/s]
                                                    

 47%|████▋     | 5158/11066 [18:53<21:08,  4.66it/s]
 47%|████▋     | 5159/11066 [18:53<21:24,  4.60it/s]
                                                    

 47%|████▋     | 5159/11066 [18:53<21:24,  4.60it/s]
 47%|████▋     | 5160/11066 [18:53<21:33,  4.57it/s]
                                                    

 47%|████▋     | 5160/11066 [18:53<21:33,  4.57it/s]
 47%|████▋     | 5161/11066 [18:54<21:21,  4.61it/s]
                                                    

 47%|████▋     | 5161/11066 [18:54<21:21,  4.61it/s]
 47%|████▋     | 5162/11066 [18:54<21:11,  4.64it/s]
                                                    

 47%|████▋     | 5162/11066 [18:54<21:11,  4.64it/s]
 47%|████▋     | 5163/11066 [18:54<21:05,  4.66it/s]
                                                    

 47%|████▋     | 5163/11066 [18:54<21:05,  4.66it/s]
 47%|████▋     | 5164/11066 [18:54<21:00,  4.68it/s]
                                                    

 47%|████▋     | 5164/11066 [18:54<21:00,  4.68it/s]
 47%|████▋     | 5165/11066 [18:55<20:58,  4.69it/s]
                                                    

 47%|████▋     | 5165/11066 [18:55<20:58,  4.69it/s]
 47%|████▋     | 5166/11066 [18:55<21:13,  4.63it/s]
                                                    

 47%|████▋     | 5166/11066 [18:55<21:13,  4.63it/s]
 47%|████▋     | 5167/11066 [18:55<21:13,  4.63it/s]
                                                    

 47%|████▋     | 5167/11066 [18:55<21:13,  4.63it/s]
 47%|████▋     | 5168/11066 [18:55<21:03,  4.67it/s]
                                                    

 47%|████▋     | 5168/11066 [18:55<21:03,  4.67it/s]
 47%|████▋     | 5169/11066 [18:55<21:08,  4.65it/s]
                                                    

 47%|████▋     | 5169/11066 [18:55<21:08,  4.65it/s]
 47%|████▋     | 5170/11066 [18:56<21:04,  4.66it/s]
                                                    

 47%|████▋     | 5170/11066 [18:56<21:04,  4.66it/s]
 47%|████▋     | 5171/11066 [18:56<21:00,  4.68it/s]
                                                    

 47%|████▋     | 5171/11066 [18:56<21:00,  4.68it/s]
 47%|████▋     | 5172/11066 [18:56<20:59,  4.68it/s]
                                                    

 47%|████▋     | 5172/11066 [18:56<20:59,  4.68it/s]
 47%|████▋     | 5173/11066 [18:56<20:56,  4.69it/s]
                                                    

 47%|████▋     | 5173/11066 [18:56<20:56,  4.69it/s]
 47%|████▋     | 5174/11066 [18:56<21:01,  4.67it/s]
                                                    

 47%|████▋     | 5174/11066 [18:56<21:01,  4.67it/s]
 47%|████▋     | 5175/11066 [18:57<21:20,  4.60it/s]
                                                    

 47%|████▋     | 5175/11066 [18:57<21:20,  4.60it/s]
 47%|████▋     | 5176/11066 [18:57<21:12,  4.63it/s]
                                                    

 47%|████▋     | 5176/11066 [18:57<21:12,  4.63it/s]
 47%|████▋     | 5177/11066 [18:57<21:06,  4.65it/s]
                                                    
{'loss': 1.4174, 'learning_rate': 1.626875112958612e-05, 'epoch': 0.92}
{'loss': 0.8352, 'learning_rate': 1.626604012289897e-05, 'epoch': 0.92}
{'loss': 1.2933, 'learning_rate': 1.6263329116211823e-05, 'epoch': 0.92}
{'loss': 0.8276, 'learning_rate': 1.626061810952467e-05, 'epoch': 0.92}
{'loss': 1.0929, 'learning_rate': 1.625790710283752e-05, 'epoch': 0.92}
{'loss': 1.559, 'learning_rate': 1.625519609615037e-05, 'epoch': 0.92}
{'loss': 1.2441, 'learning_rate': 1.625248508946322e-05, 'epoch': 0.92}
{'loss': 0.6635, 'learning_rate': 1.624977408277607e-05, 'epoch': 0.92}
{'loss': 1.0901, 'learning_rate': 1.624706307608892e-05, 'epoch': 0.92}
{'loss': 1.4035, 'learning_rate': 1.6244352069401772e-05, 'epoch': 0.92}
{'loss': 1.0948, 'learning_rate': 1.6241641062714624e-05, 'epoch': 0.92}
{'loss': 1.6721, 'learning_rate': 1.6238930056027472e-05, 'epoch': 0.92}
{'loss': 1.4091, 'learning_rate': 1.623621904934032e-05, 'epoch': 0.92}
{'loss': 1.1267, 'learning_rate': 1.6233508042653172e-05, 'epoch': 0.92}
{'loss': 0.6203, 'learning_rate': 1.623079703596602e-05, 'epoch': 0.92}
{'loss': 1.1724, 'learning_rate': 1.6228086029278873e-05, 'epoch': 0.92}
{'loss': 1.0458, 'learning_rate': 1.6225375022591724e-05, 'epoch': 0.92}
{'loss': 1.0854, 'learning_rate': 1.6222664015904573e-05, 'epoch': 0.92}
{'loss': 1.5141, 'learning_rate': 1.6219953009217425e-05, 'epoch': 0.92}
{'loss': 1.0637, 'learning_rate': 1.6217242002530273e-05, 'epoch': 0.92}
{'loss': 0.6852, 'learning_rate': 1.621453099584312e-05, 'epoch': 0.92}
{'loss': 1.3279, 'learning_rate': 1.6211819989155973e-05, 'epoch': 0.92}
{'loss': 1.0476, 'learning_rate': 1.6209108982468822e-05, 'epoch': 0.92}
{'loss': 1.3343, 'learning_rate': 1.6206397975781674e-05, 'epoch': 0.92}
{'loss': 0.848, 'learning_rate': 1.6203686969094526e-05, 'epoch': 0.92}
{'loss': 1.0707, 'learning_rate': 1.6200975962407374e-05, 'epoch': 0.92}
{'loss': 1.6098, 'learning_rate': 1.6198264955720226e-05, 'epoch': 0.92}
{'loss': 1.2567, 'learning_rate': 1.6195553949033078e-05, 'epoch': 0.92}
{'loss': 0.7811, 'learning_rate': 1.6192842942345923e-05, 'epoch': 0.92}
{'loss': 0.3659, 'learning_rate': 1.6190131935658774e-05, 'epoch': 0.92}
{'loss': 0.9641, 'learning_rate': 1.6187420928971623e-05, 'epoch': 0.92}
{'loss': 0.6798, 'learning_rate': 1.6184709922284475e-05, 'epoch': 0.92}
{'loss': 1.1859, 'learning_rate': 1.6181998915597327e-05, 'epoch': 0.92}
{'loss': 1.0985, 'learning_rate': 1.6179287908910175e-05, 'epoch': 0.92}
{'loss': 1.4012, 'learning_rate': 1.6176576902223027e-05, 'epoch': 0.92}
{'loss': 1.0076, 'learning_rate': 1.617386589553588e-05, 'epoch': 0.92}
{'loss': 1.6947, 'learning_rate': 1.6171154888848724e-05, 'epoch': 0.92}
{'loss': 0.5921, 'learning_rate': 1.6168443882161576e-05, 'epoch': 0.92}
{'loss': 0.5874, 'learning_rate': 1.6165732875474427e-05, 'epoch': 0.92}
{'loss': 0.7131, 'learning_rate': 1.6163021868787276e-05, 'epoch': 0.92}
{'loss': 0.6165, 'learning_rate': 1.6160310862100128e-05, 'epoch': 0.92}
{'loss': 0.7594, 'learning_rate': 1.6157599855412976e-05, 'epoch': 0.92}
{'loss': 0.516, 'learning_rate': 1.6154888848725828e-05, 'epoch': 0.92}
{'loss': 1.2701, 'learning_rate': 1.615217784203868e-05, 'epoch': 0.92}
{'loss': 0.7541, 'learning_rate': 1.6149466835351525e-05, 'epoch': 0.92}
{'loss': 1.1418, 'learning_rate': 1.6146755828664377e-05, 'epoch': 0.92}
{'loss': 2.3949, 'learning_rate': 1.614404482197723e-05, 'epoch': 0.92}
{'loss': 1.1317, 'learning_rate': 1.6141333815290077e-05, 'epoch': 0.92}
{'loss': 1.0987, 'learning_rate': 1.613862280860293e-05, 'epoch': 0.92}
{'loss': 1.2393, 'learning_rate': 1.613591180191578e-05, 'epoch': 0.92}
{'loss': 1.2883, 'learning_rate': 1.613320079522863e-05, 'epoch': 0.92}
{'loss': 1.0248, 'learning_rate': 1.613048978854148e-05, 'epoch': 0.92}
{'loss': 0.4514, 'learning_rate': 1.612777878185433e-05, 'epoch': 0.92}
{'loss': 0.7938, 'learning_rate': 1.6125067775167178e-05, 'epoch': 0.92}
{'loss': 1.0703, 'learning_rate': 1.612235676848003e-05, 'epoch': 0.93}
{'loss': 1.34, 'learning_rate': 1.6119645761792878e-05, 'epoch': 0.93}
{'loss': 0.9139, 'learning_rate': 1.611693475510573e-05, 'epoch': 0.93}
{'loss': 0.6142, 'learning_rate': 1.611422374841858e-05, 'epoch': 0.93}
{'loss': 0.7845, 'learning_rate': 1.611151274173143e-05, 'epoch': 0.93}
{'loss': 0.5285, 'learning_rate': 1.6108801735044282e-05, 'epoch': 0.93}
{'loss': 1.0733, 'learning_rate': 1.610609072835713e-05, 'epoch': 0.93}
{'loss': 1.4742, 'learning_rate': 1.610337972166998e-05, 'epoch': 0.93}
{'loss': 0.8093, 'learning_rate': 1.610066871498283e-05, 'epoch': 0.93}
{'loss': 0.9224, 'learning_rate': 1.6097957708295682e-05, 'epoch': 0.93}
{'loss': 1.3502, 'learning_rate': 1.609524670160853e-05, 'epoch': 0.93}
{'loss': 1.2521, 'learning_rate': 1.6092535694921383e-05, 'epoch': 0.93}
{'loss': 1.2548, 'learning_rate': 1.608982468823423e-05, 'epoch': 0.93}
{'loss': 1.1075, 'learning_rate': 1.6087113681547083e-05, 'epoch': 0.93}
{'loss': 1.1076, 'learning_rate': 1.608440267485993e-05, 'epoch': 0.93}
{'loss': 1.2556, 'learning_rate': 1.608169166817278e-05, 'epoch': 0.93}
{'loss': 1.0867, 'learning_rate': 1.607898066148563e-05, 'epoch': 0.93}
{'loss': 1.4116, 'learning_rate': 1.6076269654798484e-05, 'epoch': 0.93}
{'loss': 0.589, 'learning_rate': 1.6073558648111332e-05, 'epoch': 0.93}
{'loss': 0.8783, 'learning_rate': 1.6070847641424184e-05, 'epoch': 0.93}
{'loss': 0.6979, 'learning_rate': 1.6068136634737036e-05, 'epoch': 0.93}
{'loss': 1.5155, 'learning_rate': 1.6065425628049884e-05, 'epoch': 0.93}
{'loss': 1.4528, 'learning_rate': 1.6062714621362732e-05, 'epoch': 0.93}
{'loss': 1.8536, 'learning_rate': 1.606000361467558e-05, 'epoch': 0.93}
{'loss': 0.6027, 'learning_rate': 1.6057292607988433e-05, 'epoch': 0.93}
{'loss': 1.295, 'learning_rate': 1.6054581601301285e-05, 'epoch': 0.93}
{'loss': 0.5293, 'learning_rate': 1.6051870594614133e-05, 'epoch': 0.93}
{'loss': 0.6493, 'learning_rate': 1.6049159587926985e-05, 'epoch': 0.93}
{'loss': 1.3251, 'learning_rate': 1.6046448581239837e-05, 'epoch': 0.93}
{'loss': 1.3884, 'learning_rate': 1.6043737574552682e-05, 'epoch': 0.93}
{'loss': 1.2661, 'learning_rate': 1.6041026567865534e-05, 'epoch': 0.93}
{'loss': 1.082, 'learning_rate': 1.6038315561178385e-05, 'epoch': 0.93}
{'loss': 1.6191, 'learning_rate': 1.6035604554491234e-05, 'epoch': 0.93}
{'loss': 1.2637, 'learning_rate': 1.6032893547804086e-05, 'epoch': 0.93}
{'loss': 0.678, 'learning_rate': 1.6030182541116934e-05, 'epoch': 0.93}
{'loss': 1.0601, 'learning_rate': 1.6027471534429786e-05, 'epoch': 0.93}
{'loss': 1.2245, 'learning_rate': 1.6024760527742638e-05, 'epoch': 0.93}
{'loss': 2.2108, 'learning_rate': 1.6022049521055483e-05, 'epoch': 0.93}
{'loss': 1.008, 'learning_rate': 1.6019338514368335e-05, 'epoch': 0.93}
{'loss': 0.7527, 'learning_rate': 1.6016627507681186e-05, 'epoch': 0.93}
{'loss': 1.4168, 'learning_rate': 1.6013916500994035e-05, 'epoch': 0.93}
{'loss': 1.2546, 'learning_rate': 1.6011205494306887e-05, 'epoch': 0.93}
{'loss': 0.9305, 'learning_rate': 1.600849448761974e-05, 'epoch': 0.93}
{'loss': 1.1232, 'learning_rate': 1.6005783480932587e-05, 'epoch': 0.93}
{'loss': 0.8626, 'learning_rate': 1.600307247424544e-05, 'epoch': 0.93}
{'loss': 0.843, 'learning_rate': 1.6000361467558284e-05, 'epoch': 0.93}
{'loss': 0.5371, 'learning_rate': 1.5997650460871136e-05, 'epoch': 0.93}
{'loss': 1.3516, 'learning_rate': 1.5994939454183988e-05, 'epoch': 0.93}
{'loss': 1.3652, 'learning_rate': 1.5992228447496836e-05, 'epoch': 0.93}
{'loss': 1.1057, 'learning_rate': 1.5989517440809688e-05, 'epoch': 0.93}
{'loss': 0.5487, 'learning_rate': 1.598680643412254e-05, 'epoch': 0.93}
{'loss': 1.0788, 'learning_rate': 1.5984095427435388e-05, 'epoch': 0.93}
{'loss': 0.3918, 'learning_rate': 1.598138442074824e-05, 'epoch': 0.93}
{'loss': 0.9202, 'learning_rate': 1.597867341406109e-05, 'epoch': 0.93}
{'loss': 0.6084, 'learning_rate': 1.5975962407373937e-05, 'epoch': 0.93}
{'loss': 0.7975, 'learning_rate': 1.597325140068679e-05, 'epoch': 0.94}
{'loss': 0.7279, 'learning_rate': 1.5970540393999637e-05, 'epoch': 0.94}
{'loss': 1.3108, 'learning_rate': 1.596782938731249e-05, 'epoch': 0.94}

 47%|████▋     | 5177/11066 [18:57<21:06,  4.65it/s]
 47%|████▋     | 5178/11066 [18:57<21:01,  4.67it/s]
                                                    

 47%|████▋     | 5178/11066 [18:57<21:01,  4.67it/s]
 47%|████▋     | 5179/11066 [18:58<20:57,  4.68it/s]
                                                    

 47%|████▋     | 5179/11066 [18:58<20:57,  4.68it/s]
 47%|████▋     | 5180/11066 [18:58<20:55,  4.69it/s]
                                                    

 47%|████▋     | 5180/11066 [18:58<20:55,  4.69it/s]
 47%|████▋     | 5181/11066 [18:58<20:53,  4.70it/s]
                                                    

 47%|████▋     | 5181/11066 [18:58<20:53,  4.70it/s]
 47%|████▋     | 5182/11066 [18:58<20:50,  4.70it/s]
                                                    

 47%|████▋     | 5182/11066 [18:58<20:50,  4.70it/s]
 47%|████▋     | 5183/11066 [18:58<20:50,  4.71it/s]
                                                    

 47%|████▋     | 5183/11066 [18:58<20:50,  4.71it/s]
 47%|████▋     | 5184/11066 [18:59<20:58,  4.68it/s]
                                                    

 47%|████▋     | 5184/11066 [18:59<20:58,  4.68it/s]
 47%|████▋     | 5185/11066 [18:59<20:58,  4.67it/s]
                                                    

 47%|████▋     | 5185/11066 [18:59<20:58,  4.67it/s]
 47%|████▋     | 5186/11066 [18:59<20:51,  4.70it/s]
                                                    

 47%|████▋     | 5186/11066 [18:59<20:51,  4.70it/s]
 47%|████▋     | 5187/11066 [18:59<21:15,  4.61it/s]
                                                    

 47%|████▋     | 5187/11066 [18:59<21:15,  4.61it/s]
 47%|████▋     | 5188/11066 [18:59<21:22,  4.58it/s]
                                                    

 47%|████▋     | 5188/11066 [18:59<21:22,  4.58it/s]
 47%|████▋     | 5189/11066 [19:00<21:34,  4.54it/s]
                                                    

 47%|████▋     | 5189/11066 [19:00<21:34,  4.54it/s]
 47%|████▋     | 5190/11066 [19:00<21:20,  4.59it/s]
                                                    

 47%|████▋     | 5190/11066 [19:00<21:20,  4.59it/s]
 47%|████▋     | 5191/11066 [19:00<21:17,  4.60it/s]
                                                    

 47%|████▋     | 5191/11066 [19:00<21:17,  4.60it/s]
 47%|████▋     | 5192/11066 [19:00<21:11,  4.62it/s]
                                                    

 47%|████▋     | 5192/11066 [19:00<21:11,  4.62it/s]
 47%|████▋     | 5193/11066 [19:01<21:24,  4.57it/s]
                                                    

 47%|████▋     | 5193/11066 [19:01<21:24,  4.57it/s]
 47%|████▋     | 5194/11066 [19:01<21:22,  4.58it/s]
                                                    

 47%|████▋     | 5194/11066 [19:01<21:22,  4.58it/s]
 47%|████▋     | 5195/11066 [19:01<21:05,  4.64it/s]
                                                    

 47%|████▋     | 5195/11066 [19:01<21:05,  4.64it/s]
 47%|████▋     | 5196/11066 [19:01<21:18,  4.59it/s]
                                                    

 47%|████▋     | 5196/11066 [19:01<21:18,  4.59it/s]
 47%|████▋     | 5197/11066 [19:01<21:27,  4.56it/s]
                                                    

 47%|████▋     | 5197/11066 [19:01<21:27,  4.56it/s]
 47%|████▋     | 5198/11066 [19:02<21:35,  4.53it/s]
                                                    

 47%|████▋     | 5198/11066 [19:02<21:35,  4.53it/s]
 47%|████▋     | 5199/11066 [19:02<21:29,  4.55it/s]
                                                    

 47%|████▋     | 5199/11066 [19:02<21:29,  4.55it/s]
 47%|████▋     | 5200/11066 [19:02<21:35,  4.53it/s]
                                                    

 47%|████▋     | 5200/11066 [19:02<21:35,  4.53it/s]
 47%|████▋     | 5201/11066 [19:02<21:36,  4.52it/s]
                                                    

 47%|████▋     | 5201/11066 [19:02<21:36,  4.52it/s]
 47%|████▋     | 5202/11066 [19:03<21:37,  4.52it/s]
                                                    

 47%|████▋     | 5202/11066 [19:03<21:37,  4.52it/s]
 47%|████▋     | 5203/11066 [19:03<21:38,  4.51it/s]
                                                    

 47%|████▋     | 5203/11066 [19:03<21:38,  4.51it/s]
 47%|████▋     | 5204/11066 [19:03<21:29,  4.55it/s]
                                                    

 47%|████▋     | 5204/11066 [19:03<21:29,  4.55it/s]
 47%|████▋     | 5205/11066 [19:03<21:28,  4.55it/s]
                                                    

 47%|████▋     | 5205/11066 [19:03<21:28,  4.55it/s]
 47%|████▋     | 5206/11066 [19:03<21:31,  4.54it/s]
                                                    

 47%|████▋     | 5206/11066 [19:03<21:31,  4.54it/s]
 47%|████▋     | 5207/11066 [19:04<21:33,  4.53it/s]
                                                    

 47%|████▋     | 5207/11066 [19:04<21:33,  4.53it/s]
 47%|████▋     | 5208/11066 [19:04<21:35,  4.52it/s]
                                                    

 47%|████▋     | 5208/11066 [19:04<21:35,  4.52it/s]
 47%|████▋     | 5209/11066 [19:04<21:26,  4.55it/s]
                                                    

 47%|████▋     | 5209/11066 [19:04<21:26,  4.55it/s]
 47%|████▋     | 5210/11066 [19:04<21:33,  4.53it/s]
                                                    

 47%|████▋     | 5210/11066 [19:04<21:33,  4.53it/s]
 47%|████▋     | 5211/11066 [19:05<21:39,  4.51it/s]
                                                    

 47%|████▋     | 5211/11066 [19:05<21:39,  4.51it/s]
 47%|████▋     | 5212/11066 [19:05<21:44,  4.49it/s]
                                                    

 47%|████▋     | 5212/11066 [19:05<21:44,  4.49it/s]
 47%|████▋     | 5213/11066 [19:05<21:42,  4.49it/s]
                                                    

 47%|████▋     | 5213/11066 [19:05<21:42,  4.49it/s]
 47%|████▋     | 5214/11066 [19:05<21:28,  4.54it/s]
                                                    

 47%|████▋     | 5214/11066 [19:05<21:28,  4.54it/s]
 47%|████▋     | 5215/11066 [19:05<21:34,  4.52it/s]
                                                    

 47%|████▋     | 5215/11066 [19:05<21:34,  4.52it/s]
 47%|████▋     | 5216/11066 [19:06<21:42,  4.49it/s]
                                                    

 47%|████▋     | 5216/11066 [19:06<21:42,  4.49it/s]
 47%|████▋     | 5217/11066 [19:06<21:43,  4.49it/s]
                                                    

 47%|████▋     | 5217/11066 [19:06<21:43,  4.49it/s]
 47%|████▋     | 5218/11066 [19:06<21:41,  4.49it/s]
                                                    

 47%|████▋     | 5218/11066 [19:06<21:41,  4.49it/s]
 47%|████▋     | 5219/11066 [19:06<21:41,  4.49it/s]
                                                    

 47%|████▋     | 5219/11066 [19:06<21:41,  4.49it/s]
 47%|████▋     | 5220/11066 [19:07<21:40,  4.49it/s]
                                                    

 47%|████▋     | 5220/11066 [19:07<21:40,  4.49it/s]
 47%|████▋     | 5221/11066 [19:07<21:40,  4.49it/s]
                                                    

 47%|████▋     | 5221/11066 [19:07<21:40,  4.49it/s]
 47%|████▋     | 5222/11066 [19:07<21:40,  4.49it/s]
                                                    

 47%|████▋     | 5222/11066 [19:07<21:40,  4.49it/s]
 47%|████▋     | 5223/11066 [19:07<21:38,  4.50it/s]
                                                    

 47%|████▋     | 5223/11066 [19:07<21:38,  4.50it/s]
 47%|████▋     | 5224/11066 [19:07<21:38,  4.50it/s]
                                                    

 47%|████▋     | 5224/11066 [19:07<21:38,  4.50it/s]
 47%|████▋     | 5225/11066 [19:08<21:37,  4.50it/s]
                                                    

 47%|████▋     | 5225/11066 [19:08<21:37,  4.50it/s]
 47%|████▋     | 5226/11066 [19:08<21:36,  4.51it/s]
                                                    

 47%|████▋     | 5226/11066 [19:08<21:36,  4.51it/s]
 47%|████▋     | 5227/11066 [19:08<21:27,  4.54it/s]
                                                    

 47%|████▋     | 5227/11066 [19:08<21:27,  4.54it/s]
 47%|████▋     | 5228/11066 [19:08<21:37,  4.50it/s]
                                                    

 47%|████▋     | 5228/11066 [19:08<21:37,  4.50it/s]
 47%|████▋     | 5229/11066 [19:09<21:40,  4.49it/s]
                                                    

 47%|████▋     | 5229/11066 [19:09<21:40,  4.49it/s]
 47%|████▋     | 5230/11066 [19:09<21:40,  4.49it/s]
                                                    

 47%|████▋     | 5230/11066 [19:09<21:40,  4.49it/s]
 47%|████▋     | 5231/11066 [19:09<21:27,  4.53it/s]
                                                    

 47%|████▋     | 5231/11066 [19:09<21:27,  4.53it/s]
 47%|████▋     | 5232/11066 [19:09<21:29,  4.52it/s]
                                                    

 47%|████▋     | 5232/11066 [19:09<21:29,  4.52it/s]
 47%|████▋     | 5233/11066 [19:09<21:37,  4.50it/s]
                                                    

 47%|████▋     | 5233/11066 [19:09<21:37,  4.50it/s]
 47%|████▋     | 5234/11066 [19:10<21:38,  4.49it/s]
                                                    

 47%|████▋     | 5234/11066 [19:10<21:38,  4.49it/s]
 47%|████▋     | 5235/11066 [19:10<21:37,  4.49it/s]
                                                    

 47%|████▋     | 5235/11066 [19:10<21:37,  4.49it/s]
 47%|████▋     | 5236/11066 [19:10<21:58,  4.42it/s]
                                                    

 47%|████▋     | 5236/11066 [19:10<21:58,  4.42it/s]
 47%|████▋     | 5237/11066 [19:10<22:22,  4.34it/s]
                                                    

 47%|████▋     | 5237/11066 [19:10<22:22,  4.34it/s]
 47%|████▋     | 5238/11066 [19:11<22:15,  4.37it/s]
                                                    

 47%|████▋     | 5238/11066 [19:11<22:15,  4.37it/s]
 47%|████▋     | 5239/11066 [19:11<22:07,  4.39it/s]
                                                    

 47%|████▋     | 5239/11066 [19:11<22:07,  4.39it/s]
 47%|████▋     | 5240/11066 [19:11<21:58,  4.42it/s]
                                                    

 47%|████▋     | 5240/11066 [19:11<21:58,  4.42it/s]
 47%|████▋     | 5241/11066 [19:11<21:55,  4.43it/s]
                                                    

 47%|████▋     | 5241/11066 [19:11<21:55,  4.43it/s]
 47%|████▋     | 5242/11066 [19:11<21:54,  4.43it/s]
                                                    

 47%|████▋     | 5242/11066 [19:11<21:54,  4.43it/s]
 47%|████▋     | 5243/11066 [19:12<21:56,  4.42it/s]
                                                    

 47%|████▋     | 5243/11066 [19:12<21:56,  4.42it/s]
 47%|████▋     | 5244/11066 [19:12<21:53,  4.43it/s]
                                                    

 47%|████▋     | 5244/11066 [19:12<21:53,  4.43it/s]
 47%|████▋     | 5245/11066 [19:12<21:49,  4.45it/s]
                                                    

 47%|████▋     | 5245/11066 [19:12<21:49,  4.45it/s]
 47%|████▋     | 5246/11066 [19:12<21:48,  4.45it/s]
                                                    

 47%|████▋     | 5246/11066 [19:12<21:48,  4.45it/s]
 47%|████▋     | 5247/11066 [19:13<22:14,  4.36it/s]
                                                    

 47%|████▋     | 5247/11066 [19:13<22:14,  4.36it/s]
 47%|████▋     | 5248/11066 [19:13<22:09,  4.38it/s]
                                                    

 47%|████▋     | 5248/11066 [19:13<22:09,  4.38it/s]
 47%|████▋     | 5249/11066 [19:13<21:58,  4.41it/s]
                                                    

 47%|████▋     | 5249/11066 [19:13<21:58,  4.41it/s]
 47%|████▋     | 5250/11066 [19:13<21:52,  4.43it/s]
                                                    

 47%|████▋     | 5250/11066 [19:13<21:52,  4.43it/s]
 47%|████▋     | 5251/11066 [19:14<21:46,  4.45it/s]
                                                    

 47%|████▋     | 5251/11066 [19:14<21:46,  4.45it/s]
 47%|████▋     | 5252/11066 [19:14<21:42,  4.46it/s]
                                                    

 47%|████▋     | 5252/11066 [19:14<21:42,  4.46it/s]
 47%|████▋     | 5253/11066 [19:14<21:38,  4.48it/s]
                                                    

 47%|████▋     | 5253/11066 [19:14<21:38,  4.48it/s]
 47%|████▋     | 5254/11066 [19:14<21:36,  4.48it/s]
                                                    

 47%|████▋     | 5254/11066 [19:14<21:36,  4.48it/s]
 47%|████▋     | 5255/11066 [19:14<21:35,  4.48it/s]
                                                    

 47%|████▋     | 5255/11066 [19:14<21:35,  4.48it/s]
 47%|████▋     | 5256/11066 [19:15<21:34,  4.49it/s]
                                                    

 47%|████▋     | 5256/11066 [19:15<21:34,  4.49it/s]
 48%|████▊     | 5257/11066 [19:15<21:22,  4.53it/s]
                                                    

 48%|████▊     | 5257/11066 [19:15<21:22,  4.53it/s]
 48%|████▊     | 5258/11066 [19:15<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5258/11066 [19:15<21:29,  4.50it/s]
 48%|████▊     | 5259/11066 [19:15<21:31,  4.50it/s]
                                                    

 48%|████▊     | 5259/11066 [19:15<21:31,  4.50it/s]
 48%|████▊     | 5260/11066 [19:16<21:32,  4.49it/s]
                                                    

 48%|████▊     | 5260/11066 [19:16<21:32,  4.49it/s]
 48%|████▊     | 5261/11066 [19:16<21:31,  4.50it/s]
                                                    

 48%|████▊     | 5261/11066 [19:16<21:31,  4.50it/s]
 48%|████▊     | 5262/11066 [19:16<21:30,  4.50it/s]
                                                    

 48%|████▊     | 5262/11066 [19:16<21:30,  4.50it/s]
 48%|████▊     | 5263/11066 [19:16<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5263/11066 [19:16<21:29,  4.50it/s]
 48%|████▊     | 5264/11066 [19:16<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5264/11066 [19:16<21:29,  4.50it/s]
 48%|████▊     | 5265/11066 [19:17<21:27,  4.50it/s]
                                                    

 48%|████▊     | 5265/11066 [19:17<21:27,  4.50it/s]
 48%|████▊     | 5266/11066 [19:17<21:28,  4.50it/s]
                                                    

 48%|████▊     | 5266/11066 [19:17<21:28,  4.50it/s]
 48%|████▊     | 5267/11066 [19:17<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5267/11066 [19:17<21:29,  4.50it/s]
 48%|████▊     | 5268/11066 [19:17<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5268/11066 [19:17<21:29,  4.50it/s]
 48%|████▊     | 5269/11066 [19:18<21:29,  4.50it/s]
                                                    

 48%|████▊     | 5269/11066 [19:18<21:29,  4.50it/s]
 48%|████▊     | 5270/11066 [19:18<21:28,  4.50it/s]
                                                    

 48%|████▊     | 5270/11066 [19:18<21:28,  4.50it/s]
 48%|████▊     | 5271/11066 [19:18<21:27,  4.50it/s]
                                                    

 48%|████▊     | 5271/11066 [19:18<21:27,  4.50it/s]
 48%|████▊     | 5272/11066 [19:18<21:28,  4.50it/s]
                                                    

 48%|████▊     | 5272/11066 [19:18<21:28,  4.50it/s]
 48%|████▊     | 5273/11066 [19:18<21:28,  4.50it/s]
                                                    

 48%|████▊     | 5273/11066 [19:18<21:28,  4.50it/s]
 48%|████▊     | 5274/11066 [19:19<21:27,  4.50it/s]
                                                    

 48%|████▊     | 5274/11066 [19:19<21:27,  4.50it/s]
 48%|████▊     | 5275/11066 [19:19<21:27,  4.50it/s]
                                                    

 48%|████▊     | 5275/11066 [19:19<21:27,  4.50it/s]
 48%|████▊     | 5276/11066 [19:19<21:26,  4.50it/s]
                                                    

 48%|████▊     | 5276/11066 [19:19<21:26,  4.50it/s]
 48%|████▊     | 5277/11066 [19:19<21:26,  4.50it/s]
                                                    

 48%|████▊     | 5277/11066 [19:19<21:26,  4.50it/s]
 48%|████▊     | 5278/11066 [19:20<21:25,  4.50it/s]
                                                    

 48%|████▊     | 5278/11066 [19:20<21:25,  4.50it/s]
 48%|████▊     | 5279/11066 [19:20<21:26,  4.50it/s]
                                                    

 48%|████▊     | 5279/11066 [19:20<21:26,  4.50it/s]
 48%|████▊     | 5280/11066 [19:20<21:15,  4.54it/s]
                                                    

 48%|████▊     | 5280/11066 [19:20<21:15,  4.54it/s]
 48%|████▊     | 5281/11066 [19:20<21:23,  4.51it/s]
                                                    

 48%|████▊     | 5281/11066 [19:20<21:23,  4.51it/s]
 48%|████▊     | 5282/11066 [19:20<21:28,  4.49it/s]
                                                    

 48%|████▊     | 5282/11066 [19:20<21:28,  4.49it/s]
 48%|████▊     | 5283/11066 [19:21<21:30,  4.48it/s]
                                                    

 48%|████▊     | 5283/11066 [19:21<21:30,  4.48it/s]
 48%|████▊     | 5284/11066 [19:21<21:34,  4.47it/s]
                                                    

 48%|████▊     | 5284/11066 [19:21<21:34,  4.47it/s]
 48%|████▊     | 5285/11066 [19:21<21:35,  4.46it/s]
                                                    

 48%|████▊     | 5285/11066 [19:21<21:35,  4.46it/s]
 48%|████▊     | 5286/11066 [19:21<21:33,  4.47it/s]
                                                    

 48%|████▊     | 5286/11066 [19:21<21:33,  4.47it/s]
 48%|████▊     | 5287/11066 [19:22<21:31,  4.47it/s]
                                                    

 48%|████▊     | 5287/11066 [19:22<21:31,  4.47it/s]
 48%|████▊     | 5288/11066 [19:22<21:28,  4.48it/s]
                                                    

 48%|████▊     | 5288/11066 [19:22<21:28,  4.48it/s]
 48%|████▊     | 5289/11066 [19:22<21:26,  4.49it/s]
                                                    

 48%|████▊     | 5289/11066 [19:22<21:26,  4.49it/s]
 48%|████▊     | 5290/11066 [19:22<21:25,  4.49it/s]
                                                    
{'loss': 0.9894, 'learning_rate': 1.596511838062534e-05, 'epoch': 0.94}
{'loss': 0.8208, 'learning_rate': 1.596240737393819e-05, 'epoch': 0.94}
{'loss': 1.0175, 'learning_rate': 1.595969636725104e-05, 'epoch': 0.94}
{'loss': 0.8803, 'learning_rate': 1.595698536056389e-05, 'epoch': 0.94}
{'loss': 0.7571, 'learning_rate': 1.5954274353876738e-05, 'epoch': 0.94}
{'loss': 1.0003, 'learning_rate': 1.595156334718959e-05, 'epoch': 0.94}
{'loss': 1.3807, 'learning_rate': 1.594885234050244e-05, 'epoch': 0.94}
{'loss': 1.1672, 'learning_rate': 1.594614133381529e-05, 'epoch': 0.94}
{'loss': 0.8342, 'learning_rate': 1.5943430327128142e-05, 'epoch': 0.94}
{'loss': 1.871, 'learning_rate': 1.594071932044099e-05, 'epoch': 0.94}
{'loss': 0.7603, 'learning_rate': 1.5938008313753842e-05, 'epoch': 0.94}
{'loss': 1.0958, 'learning_rate': 1.593529730706669e-05, 'epoch': 0.94}
{'loss': 1.0077, 'learning_rate': 1.593258630037954e-05, 'epoch': 0.94}
{'loss': 0.6608, 'learning_rate': 1.592987529369239e-05, 'epoch': 0.94}
{'loss': 0.8082, 'learning_rate': 1.5927164287005243e-05, 'epoch': 0.94}
{'loss': 1.5015, 'learning_rate': 1.592445328031809e-05, 'epoch': 0.94}
{'loss': 0.993, 'learning_rate': 1.5921742273630943e-05, 'epoch': 0.94}
{'loss': 0.955, 'learning_rate': 1.5919031266943795e-05, 'epoch': 0.94}
{'loss': 1.0259, 'learning_rate': 1.5916320260256643e-05, 'epoch': 0.94}
{'loss': 0.8913, 'learning_rate': 1.591360925356949e-05, 'epoch': 0.94}
{'loss': 1.2243, 'learning_rate': 1.591089824688234e-05, 'epoch': 0.94}
{'loss': 0.6481, 'learning_rate': 1.5908187240195192e-05, 'epoch': 0.94}
{'loss': 0.861, 'learning_rate': 1.5905476233508044e-05, 'epoch': 0.94}
{'loss': 1.3674, 'learning_rate': 1.5902765226820892e-05, 'epoch': 0.94}
{'loss': 0.834, 'learning_rate': 1.5900054220133744e-05, 'epoch': 0.94}
{'loss': 1.2469, 'learning_rate': 1.5897343213446596e-05, 'epoch': 0.94}
{'loss': 1.5884, 'learning_rate': 1.5894632206759444e-05, 'epoch': 0.94}
{'loss': 1.1917, 'learning_rate': 1.5891921200072293e-05, 'epoch': 0.94}
{'loss': 1.4111, 'learning_rate': 1.5889210193385144e-05, 'epoch': 0.94}
{'loss': 1.1558, 'learning_rate': 1.5886499186697993e-05, 'epoch': 0.94}
{'loss': 0.9956, 'learning_rate': 1.5883788180010845e-05, 'epoch': 0.94}
{'loss': 0.8855, 'learning_rate': 1.5881077173323693e-05, 'epoch': 0.94}
{'loss': 1.1025, 'learning_rate': 1.5878366166636545e-05, 'epoch': 0.94}
{'loss': 0.7603, 'learning_rate': 1.5875655159949397e-05, 'epoch': 0.94}
{'loss': 1.1254, 'learning_rate': 1.5872944153262245e-05, 'epoch': 0.94}
{'loss': 0.4683, 'learning_rate': 1.5870233146575094e-05, 'epoch': 0.94}
{'loss': 0.5453, 'learning_rate': 1.5867522139887946e-05, 'epoch': 0.94}
{'loss': 0.8735, 'learning_rate': 1.5864811133200794e-05, 'epoch': 0.94}
{'loss': 1.1454, 'learning_rate': 1.5862100126513646e-05, 'epoch': 0.94}
{'loss': 0.8239, 'learning_rate': 1.5859389119826498e-05, 'epoch': 0.94}
{'loss': 0.8279, 'learning_rate': 1.5856678113139346e-05, 'epoch': 0.94}
{'loss': 1.2636, 'learning_rate': 1.5853967106452198e-05, 'epoch': 0.94}
{'loss': 0.662, 'learning_rate': 1.5851256099765046e-05, 'epoch': 0.94}
{'loss': 0.9017, 'learning_rate': 1.5848545093077895e-05, 'epoch': 0.94}
{'loss': 0.682, 'learning_rate': 1.5845834086390747e-05, 'epoch': 0.94}
{'loss': 0.8926, 'learning_rate': 1.5843123079703595e-05, 'epoch': 0.94}
{'loss': 0.9322, 'learning_rate': 1.5840412073016447e-05, 'epoch': 0.94}
{'loss': 0.8888, 'learning_rate': 1.58377010663293e-05, 'epoch': 0.94}
{'loss': 1.0141, 'learning_rate': 1.5834990059642147e-05, 'epoch': 0.94}
{'loss': 1.6533, 'learning_rate': 1.5832279052955e-05, 'epoch': 0.94}
{'loss': 1.4176, 'learning_rate': 1.582956804626785e-05, 'epoch': 0.94}
{'loss': 1.4934, 'learning_rate': 1.5826857039580696e-05, 'epoch': 0.94}
{'loss': 1.3431, 'learning_rate': 1.5824146032893548e-05, 'epoch': 0.95}
{'loss': 1.3557, 'learning_rate': 1.5821435026206396e-05, 'epoch': 0.95}
{'loss': 1.0059, 'learning_rate': 1.5818724019519248e-05, 'epoch': 0.95}
{'loss': 0.9429, 'learning_rate': 1.58160130128321e-05, 'epoch': 0.95}
{'loss': 0.5794, 'learning_rate': 1.5813302006144948e-05, 'epoch': 0.95}
{'loss': 1.4431, 'learning_rate': 1.58105909994578e-05, 'epoch': 0.95}
{'loss': 1.45, 'learning_rate': 1.5807879992770652e-05, 'epoch': 0.95}
{'loss': 0.6255, 'learning_rate': 1.5805168986083497e-05, 'epoch': 0.95}
{'loss': 1.3879, 'learning_rate': 1.580245797939635e-05, 'epoch': 0.95}
{'loss': 1.1289, 'learning_rate': 1.57997469727092e-05, 'epoch': 0.95}
{'loss': 0.7663, 'learning_rate': 1.579703596602205e-05, 'epoch': 0.95}
{'loss': 1.2135, 'learning_rate': 1.57943249593349e-05, 'epoch': 0.95}
{'loss': 0.6009, 'learning_rate': 1.579161395264775e-05, 'epoch': 0.95}
{'loss': 0.6908, 'learning_rate': 1.57889029459606e-05, 'epoch': 0.95}
{'loss': 0.8083, 'learning_rate': 1.5786191939273453e-05, 'epoch': 0.95}
{'loss': 0.9709, 'learning_rate': 1.5783480932586298e-05, 'epoch': 0.95}
{'loss': 1.0638, 'learning_rate': 1.578076992589915e-05, 'epoch': 0.95}
{'loss': 0.5968, 'learning_rate': 1.5778058919212e-05, 'epoch': 0.95}
{'loss': 1.1618, 'learning_rate': 1.577534791252485e-05, 'epoch': 0.95}
{'loss': 0.8083, 'learning_rate': 1.5772636905837702e-05, 'epoch': 0.95}
{'loss': 1.008, 'learning_rate': 1.5769925899150554e-05, 'epoch': 0.95}
{'loss': 1.0994, 'learning_rate': 1.5767214892463402e-05, 'epoch': 0.95}
{'loss': 1.0966, 'learning_rate': 1.5764503885776254e-05, 'epoch': 0.95}
{'loss': 1.9729, 'learning_rate': 1.5761792879089102e-05, 'epoch': 0.95}
{'loss': 1.145, 'learning_rate': 1.575908187240195e-05, 'epoch': 0.95}
{'loss': 1.1135, 'learning_rate': 1.5756370865714803e-05, 'epoch': 0.95}
{'loss': 0.7284, 'learning_rate': 1.575365985902765e-05, 'epoch': 0.95}
{'loss': 0.6484, 'learning_rate': 1.5750948852340503e-05, 'epoch': 0.95}
{'loss': 0.7728, 'learning_rate': 1.5748237845653355e-05, 'epoch': 0.95}
{'loss': 1.3438, 'learning_rate': 1.5745526838966203e-05, 'epoch': 0.95}
{'loss': 0.643, 'learning_rate': 1.5742815832279055e-05, 'epoch': 0.95}
{'loss': 0.6385, 'learning_rate': 1.5740104825591904e-05, 'epoch': 0.95}
{'loss': 0.9823, 'learning_rate': 1.5737393818904752e-05, 'epoch': 0.95}
{'loss': 0.9718, 'learning_rate': 1.5734682812217604e-05, 'epoch': 0.95}
{'loss': 1.5641, 'learning_rate': 1.5731971805530456e-05, 'epoch': 0.95}
{'loss': 1.2556, 'learning_rate': 1.5729260798843304e-05, 'epoch': 0.95}
{'loss': 1.664, 'learning_rate': 1.5726549792156156e-05, 'epoch': 0.95}
{'loss': 0.774, 'learning_rate': 1.5723838785469004e-05, 'epoch': 0.95}
{'loss': 0.9493, 'learning_rate': 1.5721127778781856e-05, 'epoch': 0.95}
{'loss': 0.699, 'learning_rate': 1.5718416772094705e-05, 'epoch': 0.95}
{'loss': 1.0463, 'learning_rate': 1.5715705765407553e-05, 'epoch': 0.95}
{'loss': 1.5507, 'learning_rate': 1.5712994758720405e-05, 'epoch': 0.95}
{'loss': 1.4393, 'learning_rate': 1.5710283752033257e-05, 'epoch': 0.95}
{'loss': 1.4551, 'learning_rate': 1.5707572745346105e-05, 'epoch': 0.95}
{'loss': 0.7697, 'learning_rate': 1.5704861738658957e-05, 'epoch': 0.95}
{'loss': 0.7313, 'learning_rate': 1.570215073197181e-05, 'epoch': 0.95}
{'loss': 1.7024, 'learning_rate': 1.5699439725284657e-05, 'epoch': 0.95}
{'loss': 0.7787, 'learning_rate': 1.5696728718597506e-05, 'epoch': 0.95}
{'loss': 0.7197, 'learning_rate': 1.5694017711910354e-05, 'epoch': 0.95}
{'loss': 1.4819, 'learning_rate': 1.5691306705223206e-05, 'epoch': 0.95}
{'loss': 1.0557, 'learning_rate': 1.5688595698536058e-05, 'epoch': 0.95}
{'loss': 1.2803, 'learning_rate': 1.5685884691848906e-05, 'epoch': 0.95}
{'loss': 1.2151, 'learning_rate': 1.5683173685161758e-05, 'epoch': 0.95}
{'loss': 0.5734, 'learning_rate': 1.568046267847461e-05, 'epoch': 0.95}
{'loss': 0.7704, 'learning_rate': 1.5677751671787455e-05, 'epoch': 0.95}
{'loss': 1.0279, 'learning_rate': 1.5675040665100307e-05, 'epoch': 0.95}
{'loss': 0.7368, 'learning_rate': 1.567232965841316e-05, 'epoch': 0.96}
{'loss': 0.9594, 'learning_rate': 1.5669618651726007e-05, 'epoch': 0.96}
{'loss': 1.3171, 'learning_rate': 1.566690764503886e-05, 'epoch': 0.96}
{'loss': 1.0, 'learning_rate': 1.5664196638351707e-05, 'epoch': 0.96}
{'loss': 1.0762, 'learning_rate': 1.566148563166456e-05, 'epoch': 0.96}

 48%|████▊     | 5290/11066 [19:22<21:25,  4.49it/s]
 48%|████▊     | 5291/11066 [19:22<21:24,  4.50it/s]
                                                    

 48%|████▊     | 5291/11066 [19:22<21:24,  4.50it/s]
 48%|████▊     | 5292/11066 [19:23<21:23,  4.50it/s]
                                                    

 48%|████▊     | 5292/11066 [19:23<21:23,  4.50it/s]
 48%|████▊     | 5293/11066 [19:23<21:24,  4.50it/s]
                                                    

 48%|████▊     | 5293/11066 [19:23<21:24,  4.50it/s]
 48%|████▊     | 5294/11066 [19:23<21:06,  4.56it/s]
                                                    

 48%|████▊     | 5294/11066 [19:23<21:06,  4.56it/s]
 48%|████▊     | 5295/11066 [19:23<21:12,  4.54it/s]
                                                    

 48%|████▊     | 5295/11066 [19:23<21:12,  4.54it/s]
 48%|████▊     | 5296/11066 [19:24<21:22,  4.50it/s]
                                                    

 48%|████▊     | 5296/11066 [19:24<21:22,  4.50it/s]
 48%|████▊     | 5297/11066 [19:24<21:40,  4.44it/s]
                                                    

 48%|████▊     | 5297/11066 [19:24<21:40,  4.44it/s]
 48%|████▊     | 5298/11066 [19:24<21:37,  4.45it/s]
                                                    

 48%|████▊     | 5298/11066 [19:24<21:37,  4.45it/s]
 48%|████▊     | 5299/11066 [19:24<21:32,  4.46it/s]
                                                    

 48%|████▊     | 5299/11066 [19:24<21:32,  4.46it/s]
 48%|████▊     | 5300/11066 [19:24<21:29,  4.47it/s]
                                                    

 48%|████▊     | 5300/11066 [19:24<21:29,  4.47it/s]
 48%|████▊     | 5301/11066 [19:25<21:29,  4.47it/s]
                                                    

 48%|████▊     | 5301/11066 [19:25<21:29,  4.47it/s]
 48%|████▊     | 5302/11066 [19:25<21:24,  4.49it/s]
                                                    

 48%|████▊     | 5302/11066 [19:25<21:24,  4.49it/s]
 48%|████▊     | 5303/11066 [19:25<21:22,  4.49it/s]
                                                    

 48%|████▊     | 5303/11066 [19:25<21:22,  4.49it/s]
 48%|████▊     | 5304/11066 [19:25<21:20,  4.50it/s]
                                                    

 48%|████▊     | 5304/11066 [19:25<21:20,  4.50it/s]
 48%|████▊     | 5305/11066 [19:26<21:19,  4.50it/s]
                                                    

 48%|████▊     | 5305/11066 [19:26<21:19,  4.50it/s]
 48%|████▊     | 5306/11066 [19:26<21:20,  4.50it/s]
                                                    

 48%|████▊     | 5306/11066 [19:26<21:20,  4.50it/s]
 48%|████▊     | 5307/11066 [19:26<21:19,  4.50it/s]
                                                    

 48%|████▊     | 5307/11066 [19:26<21:19,  4.50it/s]
 48%|████▊     | 5308/11066 [19:26<21:08,  4.54it/s]
                                                    

 48%|████▊     | 5308/11066 [19:26<21:08,  4.54it/s]
 48%|████▊     | 5309/11066 [19:26<21:16,  4.51it/s]
                                                    

 48%|████▊     | 5309/11066 [19:26<21:16,  4.51it/s]
 48%|████▊     | 5310/11066 [19:27<21:21,  4.49it/s]
                                                    

 48%|████▊     | 5310/11066 [19:27<21:21,  4.49it/s]
 48%|████▊     | 5311/11066 [19:27<21:21,  4.49it/s]
                                                    

 48%|████▊     | 5311/11066 [19:27<21:21,  4.49it/s]
 48%|████▊     | 5312/11066 [19:27<21:19,  4.50it/s]
                                                    

 48%|████▊     | 5312/11066 [19:27<21:19,  4.50it/s]
 48%|████▊     | 5313/11066 [19:27<21:19,  4.50it/s]
                                                    

 48%|████▊     | 5313/11066 [19:27<21:19,  4.50it/s]
 48%|████▊     | 5314/11066 [19:28<21:17,  4.50it/s]
                                                    

 48%|████▊     | 5314/11066 [19:28<21:17,  4.50it/s]
 48%|████▊     | 5315/11066 [19:28<21:17,  4.50it/s]
                                                    

 48%|████▊     | 5315/11066 [19:28<21:17,  4.50it/s]
 48%|████▊     | 5316/11066 [19:28<21:19,  4.50it/s]
                                                    

 48%|████▊     | 5316/11066 [19:28<21:19,  4.50it/s]
 48%|████▊     | 5317/11066 [19:28<21:07,  4.53it/s]
                                                    

 48%|████▊     | 5317/11066 [19:28<21:07,  4.53it/s]
 48%|████▊     | 5318/11066 [19:28<21:14,  4.51it/s]
                                                    

 48%|████▊     | 5318/11066 [19:28<21:14,  4.51it/s]
 48%|████▊     | 5319/11066 [19:29<21:17,  4.50it/s]
                                                    

 48%|████▊     | 5319/11066 [19:29<21:17,  4.50it/s]
 48%|████▊     | 5320/11066 [19:29<21:18,  4.49it/s]
                                                    

 48%|████▊     | 5320/11066 [19:29<21:18,  4.49it/s]
 48%|████▊     | 5321/11066 [19:29<21:16,  4.50it/s]
                                                    

 48%|████▊     | 5321/11066 [19:29<21:16,  4.50it/s]
 48%|████▊     | 5322/11066 [19:29<21:16,  4.50it/s]
                                                    

 48%|████▊     | 5322/11066 [19:29<21:16,  4.50it/s]
 48%|████▊     | 5323/11066 [19:30<21:17,  4.50it/s]
                                                    

 48%|████▊     | 5323/11066 [19:30<21:17,  4.50it/s]
 48%|████▊     | 5324/11066 [19:30<21:18,  4.49it/s]
                                                    

 48%|████▊     | 5324/11066 [19:30<21:18,  4.49it/s]
 48%|████▊     | 5325/11066 [19:30<21:09,  4.52it/s]
                                                    

 48%|████▊     | 5325/11066 [19:30<21:09,  4.52it/s]
 48%|████▊     | 5326/11066 [19:30<21:02,  4.55it/s]
                                                    

 48%|████▊     | 5326/11066 [19:30<21:02,  4.55it/s]
 48%|████▊     | 5327/11066 [19:30<21:09,  4.52it/s]
                                                    

 48%|████▊     | 5327/11066 [19:30<21:09,  4.52it/s]
 48%|████▊     | 5328/11066 [19:31<21:16,  4.49it/s]
                                                    

 48%|████▊     | 5328/11066 [19:31<21:16,  4.49it/s]
 48%|████▊     | 5329/11066 [19:31<21:18,  4.49it/s]
                                                    

 48%|████▊     | 5329/11066 [19:31<21:18,  4.49it/s]
 48%|████▊     | 5330/11066 [19:31<21:06,  4.53it/s]
                                                    

 48%|████▊     | 5330/11066 [19:31<21:06,  4.53it/s]
 48%|████▊     | 5331/11066 [19:31<20:49,  4.59it/s]
                                                    

 48%|████▊     | 5331/11066 [19:31<20:49,  4.59it/s]
 48%|████▊     | 5332/11066 [19:32<21:01,  4.54it/s]
                                                    

 48%|████▊     | 5332/11066 [19:32<21:01,  4.54it/s]
 48%|████▊     | 5333/11066 [19:32<21:09,  4.52it/s]
                                                    

 48%|████▊     | 5333/11066 [19:32<21:09,  4.52it/s]
 48%|████▊     | 5334/11066 [19:32<21:11,  4.51it/s]
                                                    

 48%|████▊     | 5334/11066 [19:32<21:11,  4.51it/s]
 48%|████▊     | 5335/11066 [19:32<21:02,  4.54it/s]
                                                    

 48%|████▊     | 5335/11066 [19:32<21:02,  4.54it/s]
 48%|████▊     | 5336/11066 [19:32<21:08,  4.52it/s]
                                                    

 48%|████▊     | 5336/11066 [19:32<21:08,  4.52it/s]
 48%|████▊     | 5337/11066 [19:33<20:56,  4.56it/s]
                                                    

 48%|████▊     | 5337/11066 [19:33<20:56,  4.56it/s]
 48%|████▊     | 5338/11066 [19:33<21:04,  4.53it/s]
                                                    

 48%|████▊     | 5338/11066 [19:33<21:04,  4.53it/s]
 48%|████▊     | 5339/11066 [19:33<21:02,  4.54it/s]
                                                    

 48%|████▊     | 5339/11066 [19:33<21:02,  4.54it/s]
 48%|████▊     | 5340/11066 [19:33<21:08,  4.51it/s]
                                                    

 48%|████▊     | 5340/11066 [19:33<21:08,  4.51it/s]
 48%|████▊     | 5341/11066 [19:34<21:10,  4.50it/s]
                                                    

 48%|████▊     | 5341/11066 [19:34<21:10,  4.50it/s]
 48%|████▊     | 5342/11066 [19:34<21:11,  4.50it/s]
                                                    

 48%|████▊     | 5342/11066 [19:34<21:11,  4.50it/s]
 48%|████▊     | 5343/11066 [19:34<21:10,  4.51it/s]
                                                    

 48%|████▊     | 5343/11066 [19:34<21:10,  4.51it/s]
 48%|████▊     | 5344/11066 [19:34<21:10,  4.50it/s]
                                                    

 48%|████▊     | 5344/11066 [19:34<21:10,  4.50it/s]
 48%|████▊     | 5345/11066 [19:34<21:00,  4.54it/s]
                                                    

 48%|████▊     | 5345/11066 [19:34<21:00,  4.54it/s]
 48%|████▊     | 5346/11066 [19:35<20:59,  4.54it/s]
                                                    

 48%|████▊     | 5346/11066 [19:35<20:59,  4.54it/s]
 48%|████▊     | 5347/11066 [19:35<21:00,  4.54it/s]
                                                    

 48%|████▊     | 5347/11066 [19:35<21:00,  4.54it/s]
 48%|████▊     | 5348/11066 [19:35<21:02,  4.53it/s]
                                                    

 48%|████▊     | 5348/11066 [19:35<21:02,  4.53it/s]
 48%|████▊     | 5349/11066 [19:35<21:04,  4.52it/s]
                                                    

 48%|████▊     | 5349/11066 [19:35<21:04,  4.52it/s]
 48%|████▊     | 5350/11066 [19:36<21:06,  4.51it/s]
                                                    

 48%|████▊     | 5350/11066 [19:36<21:06,  4.51it/s]
 48%|████▊     | 5351/11066 [19:36<21:30,  4.43it/s]
                                                    

 48%|████▊     | 5351/11066 [19:36<21:30,  4.43it/s]
 48%|████▊     | 5352/11066 [19:36<21:23,  4.45it/s]
                                                    

 48%|████▊     | 5352/11066 [19:36<21:23,  4.45it/s]
 48%|████▊     | 5353/11066 [19:36<21:21,  4.46it/s]
                                                    

 48%|████▊     | 5353/11066 [19:36<21:21,  4.46it/s]
 48%|████▊     | 5354/11066 [19:36<21:02,  4.52it/s]
                                                    

 48%|████▊     | 5354/11066 [19:36<21:02,  4.52it/s]
 48%|████▊     | 5355/11066 [19:37<21:07,  4.51it/s]
                                                    

 48%|████▊     | 5355/11066 [19:37<21:07,  4.51it/s]
 48%|████▊     | 5356/11066 [19:37<21:06,  4.51it/s]
                                                    

 48%|████▊     | 5356/11066 [19:37<21:06,  4.51it/s]
 48%|████▊     | 5357/11066 [19:37<20:56,  4.54it/s]
                                                    

 48%|████▊     | 5357/11066 [19:37<20:56,  4.54it/s]
 48%|████▊     | 5358/11066 [19:37<20:50,  4.56it/s]
                                                    

 48%|████▊     | 5358/11066 [19:37<20:50,  4.56it/s]
 48%|████▊     | 5359/11066 [19:38<21:01,  4.53it/s]
                                                    

 48%|████▊     | 5359/11066 [19:38<21:01,  4.53it/s]
 48%|████▊     | 5360/11066 [19:38<21:05,  4.51it/s]
                                                    

 48%|████▊     | 5360/11066 [19:38<21:05,  4.51it/s]
 48%|████▊     | 5361/11066 [19:38<20:56,  4.54it/s]
                                                    

 48%|████▊     | 5361/11066 [19:38<20:56,  4.54it/s]
 48%|████▊     | 5362/11066 [19:38<20:51,  4.56it/s]
                                                    

 48%|████▊     | 5362/11066 [19:38<20:51,  4.56it/s]
 48%|████▊     | 5363/11066 [19:38<20:47,  4.57it/s]
                                                    

 48%|████▊     | 5363/11066 [19:38<20:47,  4.57it/s]
 48%|████▊     | 5364/11066 [19:39<20:58,  4.53it/s]
                                                    

 48%|████▊     | 5364/11066 [19:39<20:58,  4.53it/s]
 48%|████▊     | 5365/11066 [19:39<21:05,  4.51it/s]
                                                    

 48%|████▊     | 5365/11066 [19:39<21:05,  4.51it/s]
 48%|████▊     | 5366/11066 [19:39<21:07,  4.50it/s]
                                                    

 48%|████▊     | 5366/11066 [19:39<21:07,  4.50it/s]
 48%|████▊     | 5367/11066 [19:39<21:06,  4.50it/s]
                                                    

 48%|████▊     | 5367/11066 [19:39<21:06,  4.50it/s]
 49%|████▊     | 5368/11066 [19:39<21:06,  4.50it/s]
                                                    

 49%|████▊     | 5368/11066 [19:39<21:06,  4.50it/s]
 49%|████▊     | 5369/11066 [19:40<21:05,  4.50it/s]
                                                    

 49%|████▊     | 5369/11066 [19:40<21:05,  4.50it/s]
 49%|████▊     | 5370/11066 [19:40<20:58,  4.53it/s]
                                                    

 49%|████▊     | 5370/11066 [19:40<20:58,  4.53it/s]
 49%|████▊     | 5371/11066 [19:40<21:01,  4.52it/s]
                                                    

 49%|████▊     | 5371/11066 [19:40<21:01,  4.52it/s]
 49%|████▊     | 5372/11066 [19:40<21:05,  4.50it/s]
                                                    

 49%|████▊     | 5372/11066 [19:40<21:05,  4.50it/s]
 49%|████▊     | 5373/11066 [19:41<21:07,  4.49it/s]
                                                    

 49%|████▊     | 5373/11066 [19:41<21:07,  4.49it/s]
 49%|████▊     | 5374/11066 [19:41<21:07,  4.49it/s]
                                                    

 49%|████▊     | 5374/11066 [19:41<21:07,  4.49it/s]
 49%|████▊     | 5375/11066 [19:41<20:55,  4.53it/s]
                                                    

 49%|████▊     | 5375/11066 [19:41<20:55,  4.53it/s]
 49%|████▊     | 5376/11066 [19:41<20:53,  4.54it/s]
                                                    

 49%|████▊     | 5376/11066 [19:41<20:53,  4.54it/s]
 49%|████▊     | 5377/11066 [19:41<20:54,  4.54it/s]
                                                    

 49%|████▊     | 5377/11066 [19:41<20:54,  4.54it/s]
 49%|████▊     | 5378/11066 [19:42<20:57,  4.52it/s]
                                                    

 49%|████▊     | 5378/11066 [19:42<20:57,  4.52it/s]
 49%|████▊     | 5379/11066 [19:42<20:59,  4.51it/s]
                                                    

 49%|████▊     | 5379/11066 [19:42<20:59,  4.51it/s]
 49%|████▊     | 5380/11066 [19:42<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5380/11066 [19:42<21:00,  4.51it/s]
 49%|████▊     | 5381/11066 [19:42<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5381/11066 [19:42<21:00,  4.51it/s]
 49%|████▊     | 5382/11066 [19:43<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5382/11066 [19:43<21:00,  4.51it/s]
 49%|████▊     | 5383/11066 [19:43<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5383/11066 [19:43<21:00,  4.51it/s]
 49%|████▊     | 5384/11066 [19:43<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5384/11066 [19:43<21:00,  4.51it/s]
 49%|████▊     | 5385/11066 [19:43<21:01,  4.50it/s]
                                                    

 49%|████▊     | 5385/11066 [19:43<21:01,  4.50it/s]
 49%|████▊     | 5386/11066 [19:43<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5386/11066 [19:43<21:00,  4.51it/s]
 49%|████▊     | 5387/11066 [19:44<21:00,  4.51it/s]
                                                    

 49%|████▊     | 5387/11066 [19:44<21:00,  4.51it/s]
 49%|████▊     | 5388/11066 [19:44<21:00,  4.50it/s]
                                                    

 49%|████▊     | 5388/11066 [19:44<21:00,  4.50it/s]
 49%|████▊     | 5389/11066 [19:44<20:59,  4.51it/s]
                                                    

 49%|████▊     | 5389/11066 [19:44<20:59,  4.51it/s]
 49%|████▊     | 5390/11066 [19:44<20:59,  4.51it/s]
                                                    

 49%|████▊     | 5390/11066 [19:44<20:59,  4.51it/s]
 49%|████▊     | 5391/11066 [19:45<20:58,  4.51it/s]
                                                    

 49%|████▊     | 5391/11066 [19:45<20:58,  4.51it/s]
 49%|████▊     | 5392/11066 [19:45<20:34,  4.59it/s]
                                                    

 49%|████▊     | 5392/11066 [19:45<20:34,  4.59it/s]
 49%|████▊     | 5393/11066 [19:45<20:37,  4.58it/s]
                                                    

 49%|████▊     | 5393/11066 [19:45<20:37,  4.58it/s]
 49%|████▊     | 5394/11066 [19:45<20:47,  4.55it/s]
                                                    

 49%|████▊     | 5394/11066 [19:45<20:47,  4.55it/s]
 49%|████▉     | 5395/11066 [19:45<20:57,  4.51it/s]
                                                    

 49%|████▉     | 5395/11066 [19:45<20:57,  4.51it/s]
 49%|████▉     | 5396/11066 [19:46<21:00,  4.50it/s]
                                                    

 49%|████▉     | 5396/11066 [19:46<21:00,  4.50it/s]
 49%|████▉     | 5397/11066 [19:46<21:01,  4.49it/s]
                                                    

 49%|████▉     | 5397/11066 [19:46<21:01,  4.49it/s]
 49%|████▉     | 5398/11066 [19:46<20:59,  4.50it/s]
                                                    

 49%|████▉     | 5398/11066 [19:46<20:59,  4.50it/s]
 49%|████▉     | 5399/11066 [19:46<20:59,  4.50it/s]
                                                    

 49%|████▉     | 5399/11066 [19:46<20:59,  4.50it/s]
 49%|████▉     | 5400/11066 [19:47<20:58,  4.50it/s]
                                                    

 49%|████▉     | 5400/11066 [19:47<20:58,  4.50it/s]
 49%|████▉     | 5401/11066 [19:47<20:58,  4.50it/s]
                                                    

 49%|████▉     | 5401/11066 [19:47<20:58,  4.50it/s]
 49%|████▉     | 5402/11066 [19:47<20:49,  4.53it/s]
                                                    
{'loss': 1.7014, 'learning_rate': 1.565877462497741e-05, 'epoch': 0.96}
{'loss': 1.0496, 'learning_rate': 1.5656063618290256e-05, 'epoch': 0.96}
{'loss': 0.9807, 'learning_rate': 1.5653352611603108e-05, 'epoch': 0.96}
{'loss': 1.4817, 'learning_rate': 1.565064160491596e-05, 'epoch': 0.96}
{'loss': 0.6919, 'learning_rate': 1.5647930598228808e-05, 'epoch': 0.96}
{'loss': 1.7316, 'learning_rate': 1.564521959154166e-05, 'epoch': 0.96}
{'loss': 1.4623, 'learning_rate': 1.5642508584854512e-05, 'epoch': 0.96}
{'loss': 0.8061, 'learning_rate': 1.563979757816736e-05, 'epoch': 0.96}
{'loss': 1.277, 'learning_rate': 1.5637086571480212e-05, 'epoch': 0.96}
{'loss': 0.6344, 'learning_rate': 1.5634375564793057e-05, 'epoch': 0.96}
{'loss': 1.0242, 'learning_rate': 1.563166455810591e-05, 'epoch': 0.96}
{'loss': 1.6488, 'learning_rate': 1.562895355141876e-05, 'epoch': 0.96}
{'loss': 0.6259, 'learning_rate': 1.562624254473161e-05, 'epoch': 0.96}
{'loss': 1.5117, 'learning_rate': 1.562353153804446e-05, 'epoch': 0.96}
{'loss': 1.708, 'learning_rate': 1.5620820531357313e-05, 'epoch': 0.96}
{'loss': 0.6163, 'learning_rate': 1.561810952467016e-05, 'epoch': 0.96}
{'loss': 0.6516, 'learning_rate': 1.5615398517983013e-05, 'epoch': 0.96}
{'loss': 0.5647, 'learning_rate': 1.561268751129586e-05, 'epoch': 0.96}
{'loss': 1.1277, 'learning_rate': 1.560997650460871e-05, 'epoch': 0.96}
{'loss': 1.3995, 'learning_rate': 1.5607265497921562e-05, 'epoch': 0.96}
{'loss': 0.7204, 'learning_rate': 1.560455449123441e-05, 'epoch': 0.96}
{'loss': 0.9041, 'learning_rate': 1.5601843484547262e-05, 'epoch': 0.96}
{'loss': 1.0791, 'learning_rate': 1.5599132477860114e-05, 'epoch': 0.96}
{'loss': 0.6667, 'learning_rate': 1.5596421471172962e-05, 'epoch': 0.96}
{'loss': 1.2845, 'learning_rate': 1.5593710464485814e-05, 'epoch': 0.96}
{'loss': 0.8687, 'learning_rate': 1.5590999457798663e-05, 'epoch': 0.96}
{'loss': 0.8094, 'learning_rate': 1.558828845111151e-05, 'epoch': 0.96}
{'loss': 0.7386, 'learning_rate': 1.5585577444424363e-05, 'epoch': 0.96}
{'loss': 0.6185, 'learning_rate': 1.5582866437737215e-05, 'epoch': 0.96}
{'loss': 0.92, 'learning_rate': 1.5580155431050063e-05, 'epoch': 0.96}
{'loss': 1.412, 'learning_rate': 1.5577444424362915e-05, 'epoch': 0.96}
{'loss': 0.6173, 'learning_rate': 1.5574733417675763e-05, 'epoch': 0.96}
{'loss': 0.593, 'learning_rate': 1.5572022410988615e-05, 'epoch': 0.96}
{'loss': 0.6673, 'learning_rate': 1.5569311404301464e-05, 'epoch': 0.96}
{'loss': 1.0351, 'learning_rate': 1.5566600397614312e-05, 'epoch': 0.96}
{'loss': 1.5973, 'learning_rate': 1.5563889390927164e-05, 'epoch': 0.96}
{'loss': 1.0423, 'learning_rate': 1.5561178384240016e-05, 'epoch': 0.96}
{'loss': 0.4582, 'learning_rate': 1.5558467377552864e-05, 'epoch': 0.96}
{'loss': 1.0236, 'learning_rate': 1.5555756370865716e-05, 'epoch': 0.96}
{'loss': 1.0174, 'learning_rate': 1.5553045364178568e-05, 'epoch': 0.96}
{'loss': 0.9554, 'learning_rate': 1.5550334357491416e-05, 'epoch': 0.96}
{'loss': 1.1962, 'learning_rate': 1.5547623350804265e-05, 'epoch': 0.96}
{'loss': 0.8394, 'learning_rate': 1.5544912344117113e-05, 'epoch': 0.96}
{'loss': 1.0186, 'learning_rate': 1.5542201337429965e-05, 'epoch': 0.96}
{'loss': 0.7298, 'learning_rate': 1.5539490330742817e-05, 'epoch': 0.96}
{'loss': 0.9612, 'learning_rate': 1.5536779324055665e-05, 'epoch': 0.96}
{'loss': 0.6788, 'learning_rate': 1.5534068317368517e-05, 'epoch': 0.96}
{'loss': 1.0405, 'learning_rate': 1.553135731068137e-05, 'epoch': 0.96}
{'loss': 1.1887, 'learning_rate': 1.5528646303994217e-05, 'epoch': 0.96}
{'loss': 1.4203, 'learning_rate': 1.5525935297307066e-05, 'epoch': 0.96}
{'loss': 1.46, 'learning_rate': 1.5523224290619918e-05, 'epoch': 0.97}
{'loss': 0.7211, 'learning_rate': 1.5520513283932766e-05, 'epoch': 0.97}
{'loss': 1.9449, 'learning_rate': 1.5517802277245618e-05, 'epoch': 0.97}
{'loss': 1.0376, 'learning_rate': 1.5515091270558466e-05, 'epoch': 0.97}
{'loss': 0.7292, 'learning_rate': 1.5512380263871318e-05, 'epoch': 0.97}
{'loss': 0.8157, 'learning_rate': 1.550966925718417e-05, 'epoch': 0.97}
{'loss': 0.5302, 'learning_rate': 1.550695825049702e-05, 'epoch': 0.97}
{'loss': 0.4047, 'learning_rate': 1.5504247243809867e-05, 'epoch': 0.97}
{'loss': 1.1466, 'learning_rate': 1.550153623712272e-05, 'epoch': 0.97}
{'loss': 1.1015, 'learning_rate': 1.5498825230435567e-05, 'epoch': 0.97}
{'loss': 1.0982, 'learning_rate': 1.549611422374842e-05, 'epoch': 0.97}
{'loss': 0.4668, 'learning_rate': 1.549340321706127e-05, 'epoch': 0.97}
{'loss': 1.2088, 'learning_rate': 1.549069221037412e-05, 'epoch': 0.97}
{'loss': 0.8883, 'learning_rate': 1.548798120368697e-05, 'epoch': 0.97}
{'loss': 0.7752, 'learning_rate': 1.548527019699982e-05, 'epoch': 0.97}
{'loss': 0.5851, 'learning_rate': 1.5482559190312668e-05, 'epoch': 0.97}
{'loss': 0.8657, 'learning_rate': 1.547984818362552e-05, 'epoch': 0.97}
{'loss': 0.9864, 'learning_rate': 1.5477137176938368e-05, 'epoch': 0.97}
{'loss': 1.3521, 'learning_rate': 1.547442617025122e-05, 'epoch': 0.97}
{'loss': 1.0191, 'learning_rate': 1.5471715163564072e-05, 'epoch': 0.97}
{'loss': 2.7395, 'learning_rate': 1.546900415687692e-05, 'epoch': 0.97}
{'loss': 0.8937, 'learning_rate': 1.5466293150189772e-05, 'epoch': 0.97}
{'loss': 0.5669, 'learning_rate': 1.5463582143502624e-05, 'epoch': 0.97}
{'loss': 1.2129, 'learning_rate': 1.546087113681547e-05, 'epoch': 0.97}
{'loss': 1.0425, 'learning_rate': 1.545816013012832e-05, 'epoch': 0.97}
{'loss': 0.8021, 'learning_rate': 1.545544912344117e-05, 'epoch': 0.97}
{'loss': 0.6912, 'learning_rate': 1.545273811675402e-05, 'epoch': 0.97}
{'loss': 0.4094, 'learning_rate': 1.5450027110066873e-05, 'epoch': 0.97}
{'loss': 2.218, 'learning_rate': 1.544731610337972e-05, 'epoch': 0.97}
{'loss': 1.079, 'learning_rate': 1.5444605096692573e-05, 'epoch': 0.97}
{'loss': 1.1251, 'learning_rate': 1.5441894090005425e-05, 'epoch': 0.97}
{'loss': 0.4502, 'learning_rate': 1.543918308331827e-05, 'epoch': 0.97}
{'loss': 0.8557, 'learning_rate': 1.5436472076631122e-05, 'epoch': 0.97}
{'loss': 0.471, 'learning_rate': 1.5433761069943974e-05, 'epoch': 0.97}
{'loss': 0.6695, 'learning_rate': 1.5431050063256822e-05, 'epoch': 0.97}
{'loss': 1.0676, 'learning_rate': 1.5428339056569674e-05, 'epoch': 0.97}
{'loss': 0.4958, 'learning_rate': 1.5425628049882523e-05, 'epoch': 0.97}
{'loss': 0.7117, 'learning_rate': 1.5422917043195374e-05, 'epoch': 0.97}
{'loss': 0.9823, 'learning_rate': 1.5420206036508226e-05, 'epoch': 0.97}
{'loss': 0.8855, 'learning_rate': 1.541749502982107e-05, 'epoch': 0.97}
{'loss': 0.9955, 'learning_rate': 1.5414784023133923e-05, 'epoch': 0.97}
{'loss': 1.1487, 'learning_rate': 1.5412073016446775e-05, 'epoch': 0.97}
{'loss': 1.26, 'learning_rate': 1.5409362009759623e-05, 'epoch': 0.97}
{'loss': 1.321, 'learning_rate': 1.5406651003072475e-05, 'epoch': 0.97}
{'loss': 1.6027, 'learning_rate': 1.5403939996385327e-05, 'epoch': 0.97}
{'loss': 1.0719, 'learning_rate': 1.5401228989698175e-05, 'epoch': 0.97}
{'loss': 0.885, 'learning_rate': 1.5398517983011027e-05, 'epoch': 0.97}
{'loss': 0.9898, 'learning_rate': 1.5395806976323876e-05, 'epoch': 0.97}
{'loss': 1.4872, 'learning_rate': 1.5393095969636724e-05, 'epoch': 0.97}
{'loss': 0.8129, 'learning_rate': 1.5390384962949576e-05, 'epoch': 0.97}
{'loss': 0.9075, 'learning_rate': 1.5387673956262424e-05, 'epoch': 0.97}
{'loss': 0.8017, 'learning_rate': 1.5384962949575276e-05, 'epoch': 0.97}
{'loss': 0.9366, 'learning_rate': 1.5382251942888128e-05, 'epoch': 0.97}
{'loss': 0.775, 'learning_rate': 1.5379540936200976e-05, 'epoch': 0.97}
{'loss': 1.0466, 'learning_rate': 1.537682992951383e-05, 'epoch': 0.97}
{'loss': 0.8573, 'learning_rate': 1.5374118922826677e-05, 'epoch': 0.98}
{'loss': 1.2464, 'learning_rate': 1.5371407916139525e-05, 'epoch': 0.98}
{'loss': 1.4308, 'learning_rate': 1.5368696909452377e-05, 'epoch': 0.98}
{'loss': 0.7171, 'learning_rate': 1.536598590276523e-05, 'epoch': 0.98}
{'loss': 0.5372, 'learning_rate': 1.5363274896078077e-05, 'epoch': 0.98}
{'loss': 1.8043, 'learning_rate': 1.536056388939093e-05, 'epoch': 0.98}
{'loss': 1.1253, 'learning_rate': 1.5357852882703778e-05, 'epoch': 0.98}

 49%|████▉     | 5402/11066 [19:47<20:49,  4.53it/s]
 49%|████▉     | 5403/11066 [19:47<20:57,  4.50it/s]
                                                    

 49%|████▉     | 5403/11066 [19:47<20:57,  4.50it/s]
 49%|████▉     | 5404/11066 [19:47<21:00,  4.49it/s]
                                                    

 49%|████▉     | 5404/11066 [19:47<21:00,  4.49it/s]
 49%|████▉     | 5405/11066 [19:48<20:59,  4.49it/s]
                                                    

 49%|████▉     | 5405/11066 [19:48<20:59,  4.49it/s]
 49%|████▉     | 5406/11066 [19:48<21:01,  4.49it/s]
                                                    

 49%|████▉     | 5406/11066 [19:48<21:01,  4.49it/s]
 49%|████▉     | 5407/11066 [19:48<21:03,  4.48it/s]
                                                    

 49%|████▉     | 5407/11066 [19:48<21:03,  4.48it/s]
 49%|████▉     | 5408/11066 [19:48<21:08,  4.46it/s]
                                                    

 49%|████▉     | 5408/11066 [19:48<21:08,  4.46it/s]
 49%|████▉     | 5409/11066 [19:49<21:08,  4.46it/s]
                                                    

 49%|████▉     | 5409/11066 [19:49<21:08,  4.46it/s]
 49%|████▉     | 5410/11066 [19:49<21:05,  4.47it/s]
                                                    

 49%|████▉     | 5410/11066 [19:49<21:05,  4.47it/s]
 49%|████▉     | 5411/11066 [19:49<21:02,  4.48it/s]
                                                    

 49%|████▉     | 5411/11066 [19:49<21:02,  4.48it/s]
 49%|████▉     | 5412/11066 [19:49<20:59,  4.49it/s]
                                                    

 49%|████▉     | 5412/11066 [19:49<20:59,  4.49it/s]
 49%|████▉     | 5413/11066 [19:49<20:58,  4.49it/s]
                                                    

 49%|████▉     | 5413/11066 [19:49<20:58,  4.49it/s]
 49%|████▉     | 5414/11066 [19:50<20:56,  4.50it/s]
                                                    

 49%|████▉     | 5414/11066 [19:50<20:56,  4.50it/s]
 49%|████▉     | 5415/11066 [19:50<20:56,  4.50it/s]
                                                    

 49%|████▉     | 5415/11066 [19:50<20:56,  4.50it/s]
 49%|████▉     | 5416/11066 [19:50<20:46,  4.53it/s]
                                                    

 49%|████▉     | 5416/11066 [19:50<20:46,  4.53it/s]
 49%|████▉     | 5417/11066 [19:50<20:53,  4.51it/s]
                                                    

 49%|████▉     | 5417/11066 [19:50<20:53,  4.51it/s]
 49%|████▉     | 5418/11066 [19:51<20:46,  4.53it/s]
                                                    

 49%|████▉     | 5418/11066 [19:51<20:46,  4.53it/s]
 49%|████▉     | 5419/11066 [19:51<20:51,  4.51it/s]
                                                    

 49%|████▉     | 5419/11066 [19:51<20:51,  4.51it/s]
 49%|████▉     | 5420/11066 [19:51<20:58,  4.49it/s]
                                                    

 49%|████▉     | 5420/11066 [19:51<20:58,  4.49it/s]
 49%|████▉     | 5421/11066 [19:51<20:58,  4.49it/s]
                                                    

 49%|████▉     | 5421/11066 [19:51<20:58,  4.49it/s]
 49%|████▉     | 5422/11066 [19:51<20:56,  4.49it/s]
                                                    

 49%|████▉     | 5422/11066 [19:51<20:56,  4.49it/s]
 49%|████▉     | 5423/11066 [19:52<20:56,  4.49it/s]
                                                    

 49%|████▉     | 5423/11066 [19:52<20:56,  4.49it/s]
 49%|████▉     | 5424/11066 [19:52<20:56,  4.49it/s]
                                                    

 49%|████▉     | 5424/11066 [19:52<20:56,  4.49it/s]
 49%|████▉     | 5425/11066 [19:52<20:46,  4.53it/s]
                                                    

 49%|████▉     | 5425/11066 [19:52<20:46,  4.53it/s]
 49%|████▉     | 5426/11066 [19:52<20:29,  4.59it/s]
                                                    

 49%|████▉     | 5426/11066 [19:52<20:29,  4.59it/s]
 49%|████▉     | 5427/11066 [19:53<20:42,  4.54it/s]
                                                    

 49%|████▉     | 5427/11066 [19:53<20:42,  4.54it/s]
 49%|████▉     | 5428/11066 [19:53<20:47,  4.52it/s]
                                                    

 49%|████▉     | 5428/11066 [19:53<20:47,  4.52it/s]
 49%|████▉     | 5429/11066 [19:53<20:38,  4.55it/s]
                                                    

 49%|████▉     | 5429/11066 [19:53<20:38,  4.55it/s]
 49%|████▉     | 5430/11066 [19:53<20:39,  4.55it/s]
                                                    

 49%|████▉     | 5430/11066 [19:53<20:39,  4.55it/s]
 49%|████▉     | 5431/11066 [19:53<20:50,  4.51it/s]
                                                    

 49%|████▉     | 5431/11066 [19:53<20:50,  4.51it/s]
 49%|████▉     | 5432/11066 [19:54<20:52,  4.50it/s]
                                                    

 49%|████▉     | 5432/11066 [19:54<20:52,  4.50it/s]
 49%|████▉     | 5433/11066 [19:54<20:53,  4.49it/s]
                                                    

 49%|████▉     | 5433/11066 [19:54<20:53,  4.49it/s]
 49%|████▉     | 5434/11066 [19:54<20:43,  4.53it/s]
                                                    

 49%|████▉     | 5434/11066 [19:54<20:43,  4.53it/s]
 49%|████▉     | 5435/11066 [19:54<20:36,  4.55it/s]
                                                    

 49%|████▉     | 5435/11066 [19:54<20:36,  4.55it/s]
 49%|████▉     | 5436/11066 [19:55<20:39,  4.54it/s]
                                                    

 49%|████▉     | 5436/11066 [19:55<20:39,  4.54it/s]
 49%|████▉     | 5437/11066 [19:55<20:42,  4.53it/s]
                                                    

 49%|████▉     | 5437/11066 [19:55<20:42,  4.53it/s]
 49%|████▉     | 5438/11066 [19:55<20:44,  4.52it/s]
                                                    

 49%|████▉     | 5438/11066 [19:55<20:44,  4.52it/s]
 49%|████▉     | 5439/11066 [19:55<20:30,  4.57it/s]
                                                    

 49%|████▉     | 5439/11066 [19:55<20:30,  4.57it/s]
 49%|████▉     | 5440/11066 [19:55<20:35,  4.55it/s]
                                                    

 49%|████▉     | 5440/11066 [19:55<20:35,  4.55it/s]
 49%|████▉     | 5441/11066 [19:56<20:39,  4.54it/s]
                                                    

 49%|████▉     | 5441/11066 [19:56<20:39,  4.54it/s]
 49%|████▉     | 5442/11066 [19:56<20:42,  4.53it/s]
                                                    

 49%|████▉     | 5442/11066 [19:56<20:42,  4.53it/s]
 49%|████▉     | 5443/11066 [19:56<20:34,  4.56it/s]
                                                    

 49%|████▉     | 5443/11066 [19:56<20:34,  4.56it/s]
 49%|████▉     | 5444/11066 [19:56<20:26,  4.58it/s]
                                                    

 49%|████▉     | 5444/11066 [19:56<20:26,  4.58it/s]
 49%|████▉     | 5445/11066 [19:57<20:35,  4.55it/s]
                                                    

 49%|████▉     | 5445/11066 [19:57<20:35,  4.55it/s]
 49%|████▉     | 5446/11066 [19:57<20:39,  4.53it/s]
                                                    

 49%|████▉     | 5446/11066 [19:57<20:39,  4.53it/s]
 49%|████▉     | 5447/11066 [19:57<20:42,  4.52it/s]
                                                    

 49%|████▉     | 5447/11066 [19:57<20:42,  4.52it/s]
 49%|████▉     | 5448/11066 [19:57<20:47,  4.50it/s]
                                                    

 49%|████▉     | 5448/11066 [19:57<20:47,  4.50it/s]
 49%|████▉     | 5449/11066 [19:57<20:55,  4.47it/s]
                                                    

 49%|████▉     | 5449/11066 [19:57<20:55,  4.47it/s]
 49%|████▉     | 5450/11066 [19:58<20:56,  4.47it/s]
                                                    

 49%|████▉     | 5450/11066 [19:58<20:56,  4.47it/s]
 49%|████▉     | 5451/11066 [19:58<21:06,  4.43it/s]
                                                    

 49%|████▉     | 5451/11066 [19:58<21:06,  4.43it/s]
 49%|████▉     | 5452/11066 [19:58<21:09,  4.42it/s]
                                                    

 49%|████▉     | 5452/11066 [19:58<21:09,  4.42it/s]
 49%|████▉     | 5453/11066 [19:58<20:47,  4.50it/s]
                                                    

 49%|████▉     | 5453/11066 [19:58<20:47,  4.50it/s]
 49%|████▉     | 5454/11066 [19:59<20:58,  4.46it/s]
                                                    

 49%|████▉     | 5454/11066 [19:59<20:58,  4.46it/s]
 49%|████▉     | 5455/11066 [19:59<21:15,  4.40it/s]
                                                    

 49%|████▉     | 5455/11066 [19:59<21:15,  4.40it/s]
 49%|████▉     | 5456/11066 [19:59<21:14,  4.40it/s]
                                                    

 49%|████▉     | 5456/11066 [19:59<21:14,  4.40it/s]
 49%|████▉     | 5457/11066 [19:59<21:31,  4.34it/s]
                                                    

 49%|████▉     | 5457/11066 [19:59<21:31,  4.34it/s]
 49%|████▉     | 5458/11066 [19:59<21:30,  4.35it/s]
                                                    

 49%|████▉     | 5458/11066 [19:59<21:30,  4.35it/s]
 49%|████▉     | 5459/11066 [20:00<21:23,  4.37it/s]
                                                    

 49%|████▉     | 5459/11066 [20:00<21:23,  4.37it/s]
 49%|████▉     | 5460/11066 [20:00<21:25,  4.36it/s]
                                                    

 49%|████▉     | 5460/11066 [20:00<21:25,  4.36it/s]
 49%|████▉     | 5461/11066 [20:00<21:32,  4.34it/s]
                                                    

 49%|████▉     | 5461/11066 [20:00<21:32,  4.34it/s]
 49%|████▉     | 5462/11066 [20:00<21:29,  4.35it/s]
                                                    

 49%|████▉     | 5462/11066 [20:00<21:29,  4.35it/s]
 49%|████▉     | 5463/11066 [20:01<21:22,  4.37it/s]
                                                    

 49%|████▉     | 5463/11066 [20:01<21:22,  4.37it/s]
 49%|████▉     | 5464/11066 [20:01<21:16,  4.39it/s]
                                                    

 49%|████▉     | 5464/11066 [20:01<21:16,  4.39it/s]
 49%|████▉     | 5465/11066 [20:01<21:24,  4.36it/s]
                                                    

 49%|████▉     | 5465/11066 [20:01<21:24,  4.36it/s]
 49%|████▉     | 5466/11066 [20:01<21:17,  4.38it/s]
                                                    

 49%|████▉     | 5466/11066 [20:01<21:17,  4.38it/s]
 49%|████▉     | 5467/11066 [20:02<21:08,  4.41it/s]
                                                    

 49%|████▉     | 5467/11066 [20:02<21:08,  4.41it/s]
 49%|████▉     | 5468/11066 [20:02<21:02,  4.43it/s]
                                                    

 49%|████▉     | 5468/11066 [20:02<21:02,  4.43it/s]
 49%|████▉     | 5469/11066 [20:02<20:57,  4.45it/s]
                                                    

 49%|████▉     | 5469/11066 [20:02<20:57,  4.45it/s]
 49%|████▉     | 5470/11066 [20:02<20:32,  4.54it/s]
                                                    

 49%|████▉     | 5470/11066 [20:02<20:32,  4.54it/s]
 49%|████▉     | 5471/11066 [20:02<20:29,  4.55it/s]
                                                    

 49%|████▉     | 5471/11066 [20:02<20:29,  4.55it/s]
 49%|████▉     | 5472/11066 [20:03<20:07,  4.63it/s]
                                                    

 49%|████▉     | 5472/11066 [20:03<20:07,  4.63it/s]
 49%|████▉     | 5473/11066 [20:03<20:21,  4.58it/s]
                                                    

 49%|████▉     | 5473/11066 [20:03<20:21,  4.58it/s]
 49%|████▉     | 5474/11066 [20:03<20:33,  4.53it/s]
                                                    

 49%|████▉     | 5474/11066 [20:03<20:33,  4.53it/s]
 49%|████▉     | 5475/11066 [20:03<20:44,  4.49it/s]
                                                    

 49%|████▉     | 5475/11066 [20:03<20:44,  4.49it/s]
 49%|████▉     | 5476/11066 [20:04<20:45,  4.49it/s]
                                                    

 49%|████▉     | 5476/11066 [20:04<20:45,  4.49it/s]
 49%|████▉     | 5477/11066 [20:04<20:44,  4.49it/s]
                                                    

 49%|████▉     | 5477/11066 [20:04<20:44,  4.49it/s]
 50%|████▉     | 5478/11066 [20:04<20:44,  4.49it/s]
                                                    

 50%|████▉     | 5478/11066 [20:04<20:44,  4.49it/s]
 50%|████▉     | 5479/11066 [20:04<20:42,  4.50it/s]
                                                    

 50%|████▉     | 5479/11066 [20:04<20:42,  4.50it/s]
 50%|████▉     | 5480/11066 [20:04<20:41,  4.50it/s]
                                                    

 50%|████▉     | 5480/11066 [20:04<20:41,  4.50it/s]
 50%|████▉     | 5481/11066 [20:05<20:41,  4.50it/s]
                                                    

 50%|████▉     | 5481/11066 [20:05<20:41,  4.50it/s]
 50%|████▉     | 5482/11066 [20:05<20:41,  4.50it/s]
                                                    

 50%|████▉     | 5482/11066 [20:05<20:41,  4.50it/s]
 50%|████▉     | 5483/11066 [20:05<20:31,  4.53it/s]
                                                    

 50%|████▉     | 5483/11066 [20:05<20:31,  4.53it/s]
 50%|████▉     | 5484/11066 [20:05<20:12,  4.60it/s]
                                                    

 50%|████▉     | 5484/11066 [20:05<20:12,  4.60it/s]
 50%|████▉     | 5485/11066 [20:06<20:49,  4.47it/s]
                                                    

 50%|████▉     | 5485/11066 [20:06<20:49,  4.47it/s]
 50%|████▉     | 5486/11066 [20:06<20:51,  4.46it/s]
                                                    

 50%|████▉     | 5486/11066 [20:06<20:51,  4.46it/s]
 50%|████▉     | 5487/11066 [20:06<21:07,  4.40it/s]
                                                    

 50%|████▉     | 5487/11066 [20:06<21:07,  4.40it/s]
 50%|████▉     | 5488/11066 [20:06<21:01,  4.42it/s]
                                                    

 50%|████▉     | 5488/11066 [20:06<21:01,  4.42it/s]
 50%|████▉     | 5489/11066 [20:06<20:48,  4.47it/s]
                                                    

 50%|████▉     | 5489/11066 [20:06<20:48,  4.47it/s]
 50%|████▉     | 5490/11066 [20:07<20:46,  4.47it/s]
                                                    

 50%|████▉     | 5490/11066 [20:07<20:46,  4.47it/s]
 50%|████▉     | 5491/11066 [20:07<20:48,  4.46it/s]
                                                    

 50%|████▉     | 5491/11066 [20:07<20:48,  4.46it/s]
 50%|████▉     | 5492/11066 [20:07<20:39,  4.50it/s]
                                                    

 50%|████▉     | 5492/11066 [20:07<20:39,  4.50it/s]
 50%|████▉     | 5493/11066 [20:07<20:31,  4.52it/s]
                                                    

 50%|████▉     | 5493/11066 [20:07<20:31,  4.52it/s]
 50%|████▉     | 5494/11066 [20:08<20:35,  4.51it/s]
                                                    

 50%|████▉     | 5494/11066 [20:08<20:35,  4.51it/s]
 50%|████▉     | 5495/11066 [20:08<20:36,  4.50it/s]
                                                    

 50%|████▉     | 5495/11066 [20:08<20:36,  4.50it/s]
 50%|████▉     | 5496/11066 [20:08<20:27,  4.54it/s]
                                                    

 50%|████▉     | 5496/11066 [20:08<20:27,  4.54it/s]
 50%|████▉     | 5497/11066 [20:08<20:17,  4.57it/s]
                                                    

 50%|████▉     | 5497/11066 [20:08<20:17,  4.57it/s]
 50%|████▉     | 5498/11066 [20:08<20:15,  4.58it/s]
                                                    

 50%|████▉     | 5498/11066 [20:08<20:15,  4.58it/s]
 50%|████▉     | 5499/11066 [20:09<20:23,  4.55it/s]
                                                    

 50%|████▉     | 5499/11066 [20:09<20:23,  4.55it/s]
 50%|████▉     | 5500/11066 [20:09<20:29,  4.53it/s]
                                                    

 50%|████▉     | 5500/11066 [20:09<20:29,  4.53it/s]
 50%|████▉     | 5501/11066 [20:09<20:26,  4.54it/s]
                                                    

 50%|████▉     | 5501/11066 [20:09<20:26,  4.54it/s]
 50%|████▉     | 5502/11066 [20:09<20:31,  4.52it/s]
                                                    

 50%|████▉     | 5502/11066 [20:09<20:31,  4.52it/s]
 50%|████▉     | 5503/11066 [20:10<20:39,  4.49it/s]
                                                    

 50%|████▉     | 5503/11066 [20:10<20:39,  4.49it/s]
 50%|████▉     | 5504/11066 [20:10<20:41,  4.48it/s]
                                                    

 50%|████▉     | 5504/11066 [20:10<20:41,  4.48it/s]
 50%|████▉     | 5505/11066 [20:10<20:40,  4.48it/s]
                                                    

 50%|████▉     | 5505/11066 [20:10<20:40,  4.48it/s]
 50%|████▉     | 5506/11066 [20:10<20:39,  4.49it/s]
                                                    

 50%|████▉     | 5506/11066 [20:10<20:39,  4.49it/s]
 50%|████▉     | 5507/11066 [20:10<20:38,  4.49it/s]
                                                    

 50%|████▉     | 5507/11066 [20:10<20:38,  4.49it/s]
 50%|████▉     | 5508/11066 [20:11<20:37,  4.49it/s]
                                                    

 50%|████▉     | 5508/11066 [20:11<20:37,  4.49it/s]
 50%|████▉     | 5509/11066 [20:11<20:36,  4.49it/s]
                                                    

 50%|████▉     | 5509/11066 [20:11<20:36,  4.49it/s]
 50%|████▉     | 5510/11066 [20:11<20:35,  4.50it/s]
                                                    

 50%|████▉     | 5510/11066 [20:11<20:35,  4.50it/s]
 50%|████▉     | 5511/11066 [20:11<20:34,  4.50it/s]
                                                    

 50%|████▉     | 5511/11066 [20:11<20:34,  4.50it/s]
 50%|████▉     | 5512/11066 [20:12<20:35,  4.49it/s]
                                                    

 50%|████▉     | 5512/11066 [20:12<20:35,  4.49it/s]
 50%|████▉     | 5513/11066 [20:12<20:35,  4.49it/s]
                                                    

 50%|████▉     | 5513/11066 [20:12<20:35,  4.49it/s]
 50%|████▉     | 5514/11066 [20:12<20:34,  4.50it/s]
                                                    
{'loss': 0.6049, 'learning_rate': 1.535514187601663e-05, 'epoch': 0.98}
{'loss': 1.4478, 'learning_rate': 1.5352430869329478e-05, 'epoch': 0.98}
{'loss': 0.533, 'learning_rate': 1.5349719862642326e-05, 'epoch': 0.98}
{'loss': 1.0407, 'learning_rate': 1.5347008855955178e-05, 'epoch': 0.98}
{'loss': 0.9305, 'learning_rate': 1.534429784926803e-05, 'epoch': 0.98}
{'loss': 1.0803, 'learning_rate': 1.534158684258088e-05, 'epoch': 0.98}
{'loss': 1.1562, 'learning_rate': 1.533887583589373e-05, 'epoch': 0.98}
{'loss': 1.1156, 'learning_rate': 1.5336164829206582e-05, 'epoch': 0.98}
{'loss': 1.5203, 'learning_rate': 1.5333453822519427e-05, 'epoch': 0.98}
{'loss': 1.5108, 'learning_rate': 1.533074281583228e-05, 'epoch': 0.98}
{'loss': 1.0622, 'learning_rate': 1.5328031809145127e-05, 'epoch': 0.98}
{'loss': 1.1097, 'learning_rate': 1.532532080245798e-05, 'epoch': 0.98}
{'loss': 0.5671, 'learning_rate': 1.532260979577083e-05, 'epoch': 0.98}
{'loss': 0.7148, 'learning_rate': 1.531989878908368e-05, 'epoch': 0.98}
{'loss': 0.7708, 'learning_rate': 1.531718778239653e-05, 'epoch': 0.98}
{'loss': 1.1256, 'learning_rate': 1.5314476775709383e-05, 'epoch': 0.98}
{'loss': 1.6284, 'learning_rate': 1.5311765769022228e-05, 'epoch': 0.98}
{'loss': 0.876, 'learning_rate': 1.530905476233508e-05, 'epoch': 0.98}
{'loss': 0.8988, 'learning_rate': 1.5306343755647932e-05, 'epoch': 0.98}
{'loss': 0.7363, 'learning_rate': 1.530363274896078e-05, 'epoch': 0.98}
{'loss': 0.5934, 'learning_rate': 1.5300921742273632e-05, 'epoch': 0.98}
{'loss': 0.7768, 'learning_rate': 1.529821073558648e-05, 'epoch': 0.98}
{'loss': 1.8234, 'learning_rate': 1.5295499728899332e-05, 'epoch': 0.98}
{'loss': 0.9062, 'learning_rate': 1.5292788722212184e-05, 'epoch': 0.98}
{'loss': 0.8457, 'learning_rate': 1.529007771552503e-05, 'epoch': 0.98}
{'loss': 0.6737, 'learning_rate': 1.528736670883788e-05, 'epoch': 0.98}
{'loss': 1.9399, 'learning_rate': 1.5284655702150733e-05, 'epoch': 0.98}
{'loss': 0.4403, 'learning_rate': 1.528194469546358e-05, 'epoch': 0.98}
{'loss': 1.6649, 'learning_rate': 1.5279233688776433e-05, 'epoch': 0.98}
{'loss': 1.3973, 'learning_rate': 1.5276522682089285e-05, 'epoch': 0.98}
{'loss': 2.2588, 'learning_rate': 1.5273811675402133e-05, 'epoch': 0.98}
{'loss': 1.1527, 'learning_rate': 1.5271100668714985e-05, 'epoch': 0.98}
{'loss': 0.6989, 'learning_rate': 1.526838966202783e-05, 'epoch': 0.98}
{'loss': 1.8136, 'learning_rate': 1.5265678655340682e-05, 'epoch': 0.98}
{'loss': 1.8599, 'learning_rate': 1.5262967648653534e-05, 'epoch': 0.98}
{'loss': 1.0017, 'learning_rate': 1.5260256641966382e-05, 'epoch': 0.98}
{'loss': 1.0155, 'learning_rate': 1.5257545635279234e-05, 'epoch': 0.98}
{'loss': 0.8558, 'learning_rate': 1.5254834628592084e-05, 'epoch': 0.98}
{'loss': 1.1033, 'learning_rate': 1.5252123621904936e-05, 'epoch': 0.98}
{'loss': 0.5001, 'learning_rate': 1.5249412615217786e-05, 'epoch': 0.98}
{'loss': 0.9721, 'learning_rate': 1.5246701608530633e-05, 'epoch': 0.98}
{'loss': 0.6246, 'learning_rate': 1.5243990601843483e-05, 'epoch': 0.98}
{'loss': 0.8891, 'learning_rate': 1.5241279595156335e-05, 'epoch': 0.98}
{'loss': 1.2004, 'learning_rate': 1.5238568588469185e-05, 'epoch': 0.98}
{'loss': 0.5398, 'learning_rate': 1.5235857581782035e-05, 'epoch': 0.98}
{'loss': 0.7947, 'learning_rate': 1.5233146575094885e-05, 'epoch': 0.98}
{'loss': 1.2791, 'learning_rate': 1.5230435568407737e-05, 'epoch': 0.98}
{'loss': 1.4077, 'learning_rate': 1.5227724561720587e-05, 'epoch': 0.98}
{'loss': 0.6004, 'learning_rate': 1.5225013555033434e-05, 'epoch': 0.98}
{'loss': 0.9329, 'learning_rate': 1.5222302548346286e-05, 'epoch': 0.99}
{'loss': 1.0459, 'learning_rate': 1.5219591541659136e-05, 'epoch': 0.99}
{'loss': 0.7665, 'learning_rate': 1.5216880534971986e-05, 'epoch': 0.99}
{'loss': 1.1639, 'learning_rate': 1.5214169528284836e-05, 'epoch': 0.99}
{'loss': 1.2977, 'learning_rate': 1.5211458521597688e-05, 'epoch': 0.99}
{'loss': 1.0295, 'learning_rate': 1.5208747514910538e-05, 'epoch': 0.99}
{'loss': 1.9028, 'learning_rate': 1.5206036508223388e-05, 'epoch': 0.99}
{'loss': 0.9741, 'learning_rate': 1.5203325501536235e-05, 'epoch': 0.99}
{'loss': 0.8317, 'learning_rate': 1.5200614494849087e-05, 'epoch': 0.99}
{'loss': 1.0806, 'learning_rate': 1.5197903488161937e-05, 'epoch': 0.99}
{'loss': 0.9996, 'learning_rate': 1.5195192481474787e-05, 'epoch': 0.99}
{'loss': 0.6801, 'learning_rate': 1.5192481474787639e-05, 'epoch': 0.99}
{'loss': 0.8916, 'learning_rate': 1.518977046810049e-05, 'epoch': 0.99}
{'loss': 0.6978, 'learning_rate': 1.518705946141334e-05, 'epoch': 0.99}
{'loss': 1.0579, 'learning_rate': 1.518434845472619e-05, 'epoch': 0.99}
{'loss': 1.2561, 'learning_rate': 1.5181637448039038e-05, 'epoch': 0.99}
{'loss': 0.8293, 'learning_rate': 1.5178926441351888e-05, 'epoch': 0.99}
{'loss': 1.2578, 'learning_rate': 1.5176215434664738e-05, 'epoch': 0.99}
{'loss': 1.601, 'learning_rate': 1.5173504427977588e-05, 'epoch': 0.99}
{'loss': 1.1146, 'learning_rate': 1.517079342129044e-05, 'epoch': 0.99}
{'loss': 1.0887, 'learning_rate': 1.516808241460329e-05, 'epoch': 0.99}
{'loss': 0.7432, 'learning_rate': 1.516537140791614e-05, 'epoch': 0.99}
{'loss': 0.8498, 'learning_rate': 1.5162660401228992e-05, 'epoch': 0.99}
{'loss': 0.6755, 'learning_rate': 1.5159949394541839e-05, 'epoch': 0.99}
{'loss': 0.8192, 'learning_rate': 1.515723838785469e-05, 'epoch': 0.99}
{'loss': 0.9048, 'learning_rate': 1.515452738116754e-05, 'epoch': 0.99}
{'loss': 0.9831, 'learning_rate': 1.5151816374480391e-05, 'epoch': 0.99}
{'loss': 0.7021, 'learning_rate': 1.5149105367793241e-05, 'epoch': 0.99}
{'loss': 0.625, 'learning_rate': 1.5146394361106091e-05, 'epoch': 0.99}
{'loss': 0.758, 'learning_rate': 1.5143683354418942e-05, 'epoch': 0.99}
{'loss': 0.6891, 'learning_rate': 1.5140972347731793e-05, 'epoch': 0.99}
{'loss': 1.2584, 'learning_rate': 1.513826134104464e-05, 'epoch': 0.99}
{'loss': 0.7613, 'learning_rate': 1.513555033435749e-05, 'epoch': 0.99}
{'loss': 1.3557, 'learning_rate': 1.5132839327670342e-05, 'epoch': 0.99}
{'loss': 1.1059, 'learning_rate': 1.5130128320983192e-05, 'epoch': 0.99}
{'loss': 1.1114, 'learning_rate': 1.5127417314296042e-05, 'epoch': 0.99}
{'loss': 1.1719, 'learning_rate': 1.5124706307608893e-05, 'epoch': 0.99}
{'loss': 0.9474, 'learning_rate': 1.5121995300921744e-05, 'epoch': 0.99}
{'loss': 1.5497, 'learning_rate': 1.5119284294234594e-05, 'epoch': 0.99}
{'loss': 1.2741, 'learning_rate': 1.5116573287547441e-05, 'epoch': 0.99}
{'loss': 0.9976, 'learning_rate': 1.5113862280860293e-05, 'epoch': 0.99}
{'loss': 0.6589, 'learning_rate': 1.5111151274173143e-05, 'epoch': 0.99}
{'loss': 0.5756, 'learning_rate': 1.5108440267485993e-05, 'epoch': 0.99}
{'loss': 1.1783, 'learning_rate': 1.5105729260798843e-05, 'epoch': 0.99}
{'loss': 0.7142, 'learning_rate': 1.5103018254111695e-05, 'epoch': 0.99}
{'loss': 1.3783, 'learning_rate': 1.5100307247424545e-05, 'epoch': 0.99}
{'loss': 0.805, 'learning_rate': 1.5097596240737396e-05, 'epoch': 0.99}
{'loss': 1.2242, 'learning_rate': 1.5094885234050242e-05, 'epoch': 0.99}
{'loss': 1.2519, 'learning_rate': 1.5092174227363094e-05, 'epoch': 0.99}
{'loss': 1.1809, 'learning_rate': 1.5089463220675944e-05, 'epoch': 0.99}
{'loss': 1.1696, 'learning_rate': 1.5086752213988794e-05, 'epoch': 0.99}
{'loss': 1.3307, 'learning_rate': 1.5084041207301646e-05, 'epoch': 0.99}
{'loss': 1.555, 'learning_rate': 1.5081330200614496e-05, 'epoch': 0.99}
{'loss': 1.0898, 'learning_rate': 1.5078619193927346e-05, 'epoch': 0.99}
{'loss': 1.5367, 'learning_rate': 1.5075908187240197e-05, 'epoch': 0.99}
{'loss': 0.9625, 'learning_rate': 1.5073197180553045e-05, 'epoch': 1.0}
{'loss': 0.9752, 'learning_rate': 1.5070486173865895e-05, 'epoch': 1.0}
{'loss': 1.1187, 'learning_rate': 1.5067775167178745e-05, 'epoch': 1.0}
{'loss': 1.2868, 'learning_rate': 1.5065064160491595e-05, 'epoch': 1.0}
{'loss': 1.4928, 'learning_rate': 1.5062353153804447e-05, 'epoch': 1.0}
{'loss': 1.0847, 'learning_rate': 1.5059642147117297e-05, 'epoch': 1.0}
{'loss': 0.489, 'learning_rate': 1.5056931140430148e-05, 'epoch': 1.0}
{'loss': 1.0393, 'learning_rate': 1.5054220133743e-05, 'epoch': 1.0}

 50%|████▉     | 5514/11066 [20:12<20:34,  4.50it/s]
 50%|████▉     | 5515/11066 [20:12<20:25,  4.53it/s]
                                                    

 50%|████▉     | 5515/11066 [20:12<20:25,  4.53it/s]
 50%|████▉     | 5516/11066 [20:12<20:36,  4.49it/s]
                                                    

 50%|████▉     | 5516/11066 [20:12<20:36,  4.49it/s]
 50%|████▉     | 5517/11066 [20:13<20:50,  4.44it/s]
                                                    

 50%|████▉     | 5517/11066 [20:13<20:50,  4.44it/s]
 50%|████▉     | 5518/11066 [20:13<20:48,  4.44it/s]
                                                    

 50%|████▉     | 5518/11066 [20:13<20:48,  4.44it/s]
 50%|████▉     | 5519/11066 [20:13<20:34,  4.49it/s]
                                                    

 50%|████▉     | 5519/11066 [20:13<20:34,  4.49it/s]
 50%|████▉     | 5520/11066 [20:13<20:31,  4.50it/s]
                                                    

 50%|████▉     | 5520/11066 [20:13<20:31,  4.50it/s]
 50%|████▉     | 5521/11066 [20:14<20:38,  4.48it/s]
                                                    

 50%|████▉     | 5521/11066 [20:14<20:38,  4.48it/s]
 50%|████▉     | 5522/11066 [20:14<20:37,  4.48it/s]
                                                    

 50%|████▉     | 5522/11066 [20:14<20:37,  4.48it/s]
 50%|████▉     | 5523/11066 [20:14<20:36,  4.48it/s]
                                                    

 50%|████▉     | 5523/11066 [20:14<20:36,  4.48it/s]
 50%|████▉     | 5524/11066 [20:14<20:35,  4.49it/s]
                                                    

 50%|████▉     | 5524/11066 [20:14<20:35,  4.49it/s]
 50%|████▉     | 5525/11066 [20:14<20:33,  4.49it/s]
                                                    

 50%|████▉     | 5525/11066 [20:14<20:33,  4.49it/s]
 50%|████▉     | 5526/11066 [20:15<20:32,  4.49it/s]
                                                    

 50%|████▉     | 5526/11066 [20:15<20:32,  4.49it/s]
 50%|████▉     | 5527/11066 [20:15<20:32,  4.50it/s]
                                                    

 50%|████▉     | 5527/11066 [20:15<20:32,  4.50it/s]
 50%|████▉     | 5528/11066 [20:15<20:22,  4.53it/s]
                                                    

 50%|████▉     | 5528/11066 [20:15<20:22,  4.53it/s]
 50%|████▉     | 5529/11066 [20:15<20:28,  4.51it/s]
                                                    

 50%|████▉     | 5529/11066 [20:15<20:28,  4.51it/s]
 50%|████▉     | 5530/11066 [20:16<20:32,  4.49it/s]
                                                    

 50%|████▉     | 5530/11066 [20:16<20:32,  4.49it/s]
 50%|████▉     | 5531/11066 [20:16<20:32,  4.49it/s]
                                                    

 50%|████▉     | 5531/11066 [20:16<20:32,  4.49it/s]
 50%|████▉     | 5532/11066 [20:16<20:32,  4.49it/s]
                                                    

 50%|████▉     | 5532/11066 [20:16<20:32,  4.49it/s]
 50%|█████     | 5533/11066 [20:16<19:22,  4.76it/s]
                                                    

 50%|█████     | 5533/11066 [20:16<19:22,  4.76it/s]
 50%|█████     | 5534/11066 [20:16<19:50,  4.65it/s]
                                                    

 50%|█████     | 5534/11066 [20:16<19:50,  4.65it/s]
 50%|█████     | 5535/11066 [20:17<20:07,  4.58it/s]
                                                    

 50%|█████     | 5535/11066 [20:17<20:07,  4.58it/s]
 50%|█████     | 5536/11066 [20:17<20:16,  4.54it/s]
                                                    

 50%|█████     | 5536/11066 [20:17<20:16,  4.54it/s]
 50%|█████     | 5537/11066 [20:17<20:20,  4.53it/s]
                                                    

 50%|█████     | 5537/11066 [20:17<20:20,  4.53it/s]
 50%|█████     | 5538/11066 [20:17<20:22,  4.52it/s]
                                                    

 50%|█████     | 5538/11066 [20:17<20:22,  4.52it/s]
 50%|█████     | 5539/11066 [20:18<20:32,  4.49it/s]
                                                    

 50%|█████     | 5539/11066 [20:18<20:32,  4.49it/s]
 50%|█████     | 5540/11066 [20:18<20:35,  4.47it/s]
                                                    

 50%|█████     | 5540/11066 [20:18<20:35,  4.47it/s]
 50%|█████     | 5541/11066 [20:18<20:33,  4.48it/s]
                                                    

 50%|█████     | 5541/11066 [20:18<20:33,  4.48it/s]
 50%|█████     | 5542/11066 [20:18<20:22,  4.52it/s]
                                                    

 50%|█████     | 5542/11066 [20:18<20:22,  4.52it/s]
 50%|█████     | 5543/11066 [20:18<20:21,  4.52it/s]
                                                    

 50%|█████     | 5543/11066 [20:18<20:21,  4.52it/s]
 50%|█████     | 5544/11066 [20:19<20:48,  4.42it/s]
                                                    

 50%|█████     | 5544/11066 [20:19<20:48,  4.42it/s]
 50%|█████     | 5545/11066 [20:19<20:44,  4.44it/s]
                                                    

 50%|█████     | 5545/11066 [20:19<20:44,  4.44it/s]
 50%|█████     | 5546/11066 [20:19<20:28,  4.49it/s]
                                                    

 50%|█████     | 5546/11066 [20:19<20:28,  4.49it/s]
 50%|█████     | 5547/11066 [20:19<20:16,  4.54it/s]
                                                    

 50%|█████     | 5547/11066 [20:19<20:16,  4.54it/s]
 50%|█████     | 5548/11066 [20:20<20:22,  4.51it/s]
                                                    

 50%|█████     | 5548/11066 [20:20<20:22,  4.51it/s]
 50%|█████     | 5549/11066 [20:20<20:23,  4.51it/s]
                                                    

 50%|█████     | 5549/11066 [20:20<20:23,  4.51it/s]
 50%|█████     | 5550/11066 [20:20<20:24,  4.51it/s]
                                                    

 50%|█████     | 5550/11066 [20:20<20:24,  4.51it/s]
 50%|█████     | 5551/11066 [20:20<20:17,  4.53it/s]
                                                    

 50%|█████     | 5551/11066 [20:20<20:17,  4.53it/s]
 50%|█████     | 5552/11066 [20:20<20:22,  4.51it/s]
                                                    

 50%|█████     | 5552/11066 [20:20<20:22,  4.51it/s]
 50%|█████     | 5553/11066 [20:21<20:58,  4.38it/s]
                                                    

 50%|█████     | 5553/11066 [20:21<20:58,  4.38it/s]
 50%|█████     | 5554/11066 [20:21<20:55,  4.39it/s]
                                                    

 50%|█████     | 5554/11066 [20:21<20:55,  4.39it/s]
 50%|█████     | 5555/11066 [20:21<20:42,  4.44it/s]
                                                    

 50%|█████     | 5555/11066 [20:21<20:42,  4.44it/s]
 50%|█████     | 5556/11066 [20:21<20:20,  4.52it/s]
                                                    

 50%|█████     | 5556/11066 [20:21<20:20,  4.52it/s]
 50%|█████     | 5557/11066 [20:22<20:21,  4.51it/s]
                                                    

 50%|█████     | 5557/11066 [20:22<20:21,  4.51it/s]
 50%|█████     | 5558/11066 [20:22<20:22,  4.50it/s]
                                                    

 50%|█████     | 5558/11066 [20:22<20:22,  4.50it/s]
 50%|█████     | 5559/11066 [20:22<20:22,  4.51it/s]
                                                    

 50%|█████     | 5559/11066 [20:22<20:22,  4.51it/s]
 50%|█████     | 5560/11066 [20:22<20:21,  4.51it/s]
                                                    

 50%|█████     | 5560/11066 [20:22<20:21,  4.51it/s]
 50%|█████     | 5561/11066 [20:22<20:14,  4.53it/s]
                                                    

 50%|█████     | 5561/11066 [20:22<20:14,  4.53it/s]
 50%|█████     | 5562/11066 [20:23<20:20,  4.51it/s]
                                                    

 50%|█████     | 5562/11066 [20:23<20:20,  4.51it/s]
 50%|█████     | 5563/11066 [20:23<20:21,  4.50it/s]
                                                    

 50%|█████     | 5563/11066 [20:23<20:21,  4.50it/s]
 50%|█████     | 5564/11066 [20:23<20:22,  4.50it/s]
                                                    

 50%|█████     | 5564/11066 [20:23<20:22,  4.50it/s]
 50%|█████     | 5565/11066 [20:23<20:20,  4.51it/s]
                                                    

 50%|█████     | 5565/11066 [20:23<20:20,  4.51it/s]
 50%|█████     | 5566/11066 [20:24<20:21,  4.50it/s]
                                                    

 50%|█████     | 5566/11066 [20:24<20:21,  4.50it/s]
 50%|█████     | 5567/11066 [20:24<20:21,  4.50it/s]
                                                    

 50%|█████     | 5567/11066 [20:24<20:21,  4.50it/s]
 50%|█████     | 5568/11066 [20:24<20:20,  4.50it/s]
                                                    

 50%|█████     | 5568/11066 [20:24<20:20,  4.50it/s]
 50%|█████     | 5569/11066 [20:24<20:21,  4.50it/s]
                                                    

 50%|█████     | 5569/11066 [20:24<20:21,  4.50it/s]
 50%|█████     | 5570/11066 [20:24<20:42,  4.42it/s]
                                                    

 50%|█████     | 5570/11066 [20:24<20:42,  4.42it/s]
 50%|█████     | 5571/11066 [20:25<20:49,  4.40it/s]
                                                    

 50%|█████     | 5571/11066 [20:25<20:49,  4.40it/s]
 50%|█████     | 5572/11066 [20:25<20:41,  4.42it/s]
                                                    

 50%|█████     | 5572/11066 [20:25<20:41,  4.42it/s]
 50%|█████     | 5573/11066 [20:25<20:34,  4.45it/s]
                                                    

 50%|█████     | 5573/11066 [20:25<20:34,  4.45it/s]
 50%|█████     | 5574/11066 [20:25<20:29,  4.47it/s]
                                                    

 50%|█████     | 5574/11066 [20:25<20:29,  4.47it/s]
 50%|█████     | 5575/11066 [20:26<20:26,  4.48it/s]
                                                    

 50%|█████     | 5575/11066 [20:26<20:26,  4.48it/s]
 50%|█████     | 5576/11066 [20:26<20:23,  4.49it/s]
                                                    

 50%|█████     | 5576/11066 [20:26<20:23,  4.49it/s]
 50%|█████     | 5577/11066 [20:26<20:22,  4.49it/s]
                                                    

 50%|█████     | 5577/11066 [20:26<20:22,  4.49it/s]
 50%|█████     | 5578/11066 [20:26<20:20,  4.50it/s]
                                                    

 50%|█████     | 5578/11066 [20:26<20:20,  4.50it/s]
 50%|█████     | 5579/11066 [20:26<20:19,  4.50it/s]
                                                    

 50%|█████     | 5579/11066 [20:26<20:19,  4.50it/s]
 50%|█████     | 5580/11066 [20:27<20:19,  4.50it/s]
                                                    

 50%|█████     | 5580/11066 [20:27<20:19,  4.50it/s]
 50%|█████     | 5581/11066 [20:27<20:18,  4.50it/s]
                                                    

 50%|█████     | 5581/11066 [20:27<20:18,  4.50it/s]
 50%|█████     | 5582/11066 [20:27<20:18,  4.50it/s]
                                                    

 50%|█████     | 5582/11066 [20:27<20:18,  4.50it/s]
 50%|█████     | 5583/11066 [20:27<20:17,  4.50it/s]
                                                    

 50%|█████     | 5583/11066 [20:27<20:17,  4.50it/s]
 50%|█████     | 5584/11066 [20:28<19:53,  4.59it/s]
                                                    

 50%|█████     | 5584/11066 [20:28<19:53,  4.59it/s]
 50%|█████     | 5585/11066 [20:28<20:06,  4.54it/s]
                                                    

 50%|█████     | 5585/11066 [20:28<20:06,  4.54it/s]
 50%|█████     | 5586/11066 [20:28<20:10,  4.53it/s]
                                                    

 50%|█████     | 5586/11066 [20:28<20:10,  4.53it/s]
 50%|█████     | 5587/11066 [20:28<20:12,  4.52it/s]
                                                    

 50%|█████     | 5587/11066 [20:28<20:12,  4.52it/s]
 50%|█████     | 5588/11066 [20:28<20:13,  4.51it/s]
                                                    

 50%|█████     | 5588/11066 [20:28<20:13,  4.51it/s]
 51%|█████     | 5589/11066 [20:29<20:13,  4.51it/s]
                                                    

 51%|█████     | 5589/11066 [20:29<20:13,  4.51it/s]
 51%|█████     | 5590/11066 [20:29<20:14,  4.51it/s]
                                                    

 51%|█████     | 5590/11066 [20:29<20:14,  4.51it/s]
 51%|█████     | 5591/11066 [20:29<20:14,  4.51it/s]
                                                    

 51%|█████     | 5591/11066 [20:29<20:14,  4.51it/s]
 51%|█████     | 5592/11066 [20:29<20:16,  4.50it/s]
                                                    

 51%|█████     | 5592/11066 [20:29<20:16,  4.50it/s]
 51%|█████     | 5593/11066 [20:30<20:16,  4.50it/s]
                                                    

 51%|█████     | 5593/11066 [20:30<20:16,  4.50it/s]
 51%|█████     | 5594/11066 [20:30<20:16,  4.50it/s]
                                                    

 51%|█████     | 5594/11066 [20:30<20:16,  4.50it/s]
 51%|█████     | 5595/11066 [20:30<20:15,  4.50it/s]
                                                    

 51%|█████     | 5595/11066 [20:30<20:15,  4.50it/s]
 51%|█████     | 5596/11066 [20:30<20:15,  4.50it/s]
                                                    

 51%|█████     | 5596/11066 [20:30<20:15,  4.50it/s]
 51%|█████     | 5597/11066 [20:30<20:15,  4.50it/s]
                                                    

 51%|█████     | 5597/11066 [20:30<20:15,  4.50it/s]
 51%|█████     | 5598/11066 [20:31<20:08,  4.52it/s]
                                                    

 51%|█████     | 5598/11066 [20:31<20:08,  4.52it/s]
 51%|█████     | 5599/11066 [20:31<20:15,  4.50it/s]
                                                    

 51%|█████     | 5599/11066 [20:31<20:15,  4.50it/s]
 51%|█████     | 5600/11066 [20:31<20:16,  4.49it/s]
                                                    

 51%|█████     | 5600/11066 [20:31<20:16,  4.49it/s]
 51%|█████     | 5601/11066 [20:31<20:16,  4.49it/s]
                                                    

 51%|█████     | 5601/11066 [20:31<20:16,  4.49it/s]
 51%|█████     | 5602/11066 [20:32<20:15,  4.50it/s]
                                                    

 51%|█████     | 5602/11066 [20:32<20:15,  4.50it/s]
 51%|█████     | 5603/11066 [20:32<20:13,  4.50it/s]
                                                    

 51%|█████     | 5603/11066 [20:32<20:13,  4.50it/s]
 51%|█████     | 5604/11066 [20:32<20:13,  4.50it/s]
                                                    

 51%|█████     | 5604/11066 [20:32<20:13,  4.50it/s]
 51%|█████     | 5605/11066 [20:32<20:13,  4.50it/s]
                                                    

 51%|█████     | 5605/11066 [20:32<20:13,  4.50it/s]
 51%|█████     | 5606/11066 [20:32<20:13,  4.50it/s]
                                                    

 51%|█████     | 5606/11066 [20:32<20:13,  4.50it/s]
 51%|█████     | 5607/11066 [20:33<20:12,  4.50it/s]
                                                    

 51%|█████     | 5607/11066 [20:33<20:12,  4.50it/s]
 51%|█████     | 5608/11066 [20:33<20:11,  4.50it/s]
                                                    

 51%|█████     | 5608/11066 [20:33<20:11,  4.50it/s]
 51%|█████     | 5609/11066 [20:33<20:12,  4.50it/s]
                                                    

 51%|█████     | 5609/11066 [20:33<20:12,  4.50it/s]
 51%|█████     | 5610/11066 [20:33<20:12,  4.50it/s]
                                                    

 51%|█████     | 5610/11066 [20:33<20:12,  4.50it/s]
 51%|█████     | 5611/11066 [20:34<20:12,  4.50it/s]
                                                    

 51%|█████     | 5611/11066 [20:34<20:12,  4.50it/s]
 51%|█████     | 5612/11066 [20:34<20:13,  4.49it/s]
                                                    

 51%|█████     | 5612/11066 [20:34<20:13,  4.49it/s]
 51%|█████     | 5613/11066 [20:34<20:13,  4.50it/s]
                                                    

 51%|█████     | 5613/11066 [20:34<20:13,  4.50it/s]
 51%|█████     | 5614/11066 [20:34<20:11,  4.50it/s]
                                                    

 51%|█████     | 5614/11066 [20:34<20:11,  4.50it/s]
 51%|█████     | 5615/11066 [20:34<20:11,  4.50it/s]
                                                    

 51%|█████     | 5615/11066 [20:34<20:11,  4.50it/s]
 51%|█████     | 5616/11066 [20:35<20:11,  4.50it/s]
                                                    

 51%|█████     | 5616/11066 [20:35<20:11,  4.50it/s]
 51%|█████     | 5617/11066 [20:35<20:11,  4.50it/s]
                                                    

 51%|█████     | 5617/11066 [20:35<20:11,  4.50it/s]
 51%|█████     | 5618/11066 [20:35<20:10,  4.50it/s]
                                                    

 51%|█████     | 5618/11066 [20:35<20:10,  4.50it/s]
 51%|█████     | 5619/11066 [20:35<19:56,  4.55it/s]
                                                    

 51%|█████     | 5619/11066 [20:35<19:56,  4.55it/s]
 51%|█████     | 5620/11066 [20:36<19:59,  4.54it/s]
                                                    

 51%|█████     | 5620/11066 [20:36<19:59,  4.54it/s]
 51%|█████     | 5621/11066 [20:36<20:01,  4.53it/s]
                                                    

 51%|█████     | 5621/11066 [20:36<20:01,  4.53it/s]
 51%|█████     | 5622/11066 [20:36<20:03,  4.52it/s]
                                                    

 51%|█████     | 5622/11066 [20:36<20:03,  4.52it/s]
 51%|█████     | 5623/11066 [20:36<19:55,  4.55it/s]
                                                    

 51%|█████     | 5623/11066 [20:36<19:55,  4.55it/s]
 51%|█████     | 5624/11066 [20:36<19:55,  4.55it/s]
                                                    

 51%|█████     | 5624/11066 [20:36<19:55,  4.55it/s]
 51%|█████     | 5625/11066 [20:37<19:58,  4.54it/s]
                                                    

 51%|█████     | 5625/11066 [20:37<19:58,  4.54it/s]
 51%|█████     | 5626/11066 [20:37<20:02,  4.53it/s]
                                                    

 51%|█████     | 5626/11066 [20:37<20:02,  4.53it/s]
 51%|█████     | 5627/11066 [20:37<20:02,  4.52it/s]
                                                    
{'loss': 0.6189, 'learning_rate': 1.5051509127055846e-05, 'epoch': 1.0}
{'loss': 0.4827, 'learning_rate': 1.5048798120368696e-05, 'epoch': 1.0}
{'loss': 1.3404, 'learning_rate': 1.5046087113681546e-05, 'epoch': 1.0}
{'loss': 1.2958, 'learning_rate': 1.5043376106994398e-05, 'epoch': 1.0}
{'loss': 1.3013, 'learning_rate': 1.5040665100307248e-05, 'epoch': 1.0}
{'loss': 0.6884, 'learning_rate': 1.5037954093620099e-05, 'epoch': 1.0}
{'loss': 1.1592, 'learning_rate': 1.5035243086932949e-05, 'epoch': 1.0}
{'loss': 0.8021, 'learning_rate': 1.50325320802458e-05, 'epoch': 1.0}
{'loss': 1.1366, 'learning_rate': 1.5029821073558647e-05, 'epoch': 1.0}
{'loss': 0.7576, 'learning_rate': 1.5027110066871497e-05, 'epoch': 1.0}
{'loss': 1.3876, 'learning_rate': 1.502439906018435e-05, 'epoch': 1.0}
{'loss': 0.6201, 'learning_rate': 1.50216880534972e-05, 'epoch': 1.0}
{'loss': 0.8799, 'learning_rate': 1.501897704681005e-05, 'epoch': 1.0}
{'loss': 1.0425, 'learning_rate': 1.50162660401229e-05, 'epoch': 1.0}
{'loss': 0.8548, 'learning_rate': 1.5013555033435751e-05, 'epoch': 1.0}
{'loss': 1.0247, 'learning_rate': 1.5010844026748602e-05, 'epoch': 1.0}
{'loss': 1.4346, 'learning_rate': 1.5008133020061448e-05, 'epoch': 1.0}
{'loss': 1.0356, 'learning_rate': 1.5005422013374298e-05, 'epoch': 1.0}
{'loss': 0.926, 'learning_rate': 1.500271100668715e-05, 'epoch': 1.0}
{'loss': 0.5837, 'learning_rate': 1.5e-05, 'epoch': 1.0}
{'loss': 0.5663, 'learning_rate': 1.499728899331285e-05, 'epoch': 1.0}
{'loss': 0.9003, 'learning_rate': 1.49945779866257e-05, 'epoch': 1.0}
{'loss': 0.4541, 'learning_rate': 1.499186697993855e-05, 'epoch': 1.0}
{'loss': 0.6022, 'learning_rate': 1.4989155973251401e-05, 'epoch': 1.0}
{'loss': 0.4398, 'learning_rate': 1.4986444966564251e-05, 'epoch': 1.0}
{'loss': 0.8599, 'learning_rate': 1.4983733959877101e-05, 'epoch': 1.0}
{'loss': 1.0225, 'learning_rate': 1.4981022953189951e-05, 'epoch': 1.0}
{'loss': 0.8979, 'learning_rate': 1.4978311946502801e-05, 'epoch': 1.0}
{'loss': 0.9195, 'learning_rate': 1.4975600939815652e-05, 'epoch': 1.0}
{'loss': 0.9469, 'learning_rate': 1.4972889933128502e-05, 'epoch': 1.0}
{'loss': 0.5126, 'learning_rate': 1.4970178926441352e-05, 'epoch': 1.0}
{'loss': 0.5765, 'learning_rate': 1.4967467919754202e-05, 'epoch': 1.0}
{'loss': 0.6599, 'learning_rate': 1.4964756913067054e-05, 'epoch': 1.0}
{'loss': 1.1221, 'learning_rate': 1.4962045906379902e-05, 'epoch': 1.0}
{'loss': 0.9048, 'learning_rate': 1.4959334899692752e-05, 'epoch': 1.0}
{'loss': 1.2028, 'learning_rate': 1.4956623893005603e-05, 'epoch': 1.0}
{'loss': 0.9839, 'learning_rate': 1.4953912886318454e-05, 'epoch': 1.0}
{'loss': 0.6324, 'learning_rate': 1.4951201879631303e-05, 'epoch': 1.0}
{'loss': 0.3832, 'learning_rate': 1.4948490872944153e-05, 'epoch': 1.0}
{'loss': 0.5698, 'learning_rate': 1.4945779866257003e-05, 'epoch': 1.0}
{'loss': 0.9444, 'learning_rate': 1.4943068859569855e-05, 'epoch': 1.0}
{'loss': 0.5652, 'learning_rate': 1.4940357852882703e-05, 'epoch': 1.0}
{'loss': 1.2299, 'learning_rate': 1.4937646846195553e-05, 'epoch': 1.0}
{'loss': 1.1567, 'learning_rate': 1.4934935839508405e-05, 'epoch': 1.0}
{'loss': 0.723, 'learning_rate': 1.4932224832821255e-05, 'epoch': 1.0}
{'loss': 0.3911, 'learning_rate': 1.4929513826134104e-05, 'epoch': 1.0}
{'loss': 0.7779, 'learning_rate': 1.4926802819446954e-05, 'epoch': 1.0}
{'loss': 0.7027, 'learning_rate': 1.4924091812759806e-05, 'epoch': 1.01}
{'loss': 0.7149, 'learning_rate': 1.4921380806072656e-05, 'epoch': 1.01}
{'loss': 0.6883, 'learning_rate': 1.4918669799385504e-05, 'epoch': 1.01}
{'loss': 0.617, 'learning_rate': 1.4915958792698355e-05, 'epoch': 1.01}
{'loss': 0.6131, 'learning_rate': 1.4913247786011206e-05, 'epoch': 1.01}
{'loss': 0.8333, 'learning_rate': 1.4910536779324057e-05, 'epoch': 1.01}
{'loss': 0.4004, 'learning_rate': 1.4907825772636905e-05, 'epoch': 1.01}
{'loss': 0.9322, 'learning_rate': 1.4905114765949757e-05, 'epoch': 1.01}
{'loss': 0.6913, 'learning_rate': 1.4902403759262607e-05, 'epoch': 1.01}
{'loss': 0.9208, 'learning_rate': 1.4899692752575457e-05, 'epoch': 1.01}
{'loss': 1.3039, 'learning_rate': 1.4896981745888305e-05, 'epoch': 1.01}
{'loss': 0.3245, 'learning_rate': 1.4894270739201157e-05, 'epoch': 1.01}
{'loss': 0.9616, 'learning_rate': 1.4891559732514007e-05, 'epoch': 1.01}
{'loss': 0.3705, 'learning_rate': 1.4888848725826858e-05, 'epoch': 1.01}
{'loss': 0.7389, 'learning_rate': 1.4886137719139708e-05, 'epoch': 1.01}
{'loss': 1.1486, 'learning_rate': 1.4883426712452558e-05, 'epoch': 1.01}
{'loss': 0.5826, 'learning_rate': 1.4880715705765408e-05, 'epoch': 1.01}
{'loss': 0.7287, 'learning_rate': 1.4878004699078258e-05, 'epoch': 1.01}
{'loss': 0.7756, 'learning_rate': 1.4875293692391108e-05, 'epoch': 1.01}
{'loss': 1.1944, 'learning_rate': 1.4872582685703958e-05, 'epoch': 1.01}
{'loss': 1.0138, 'learning_rate': 1.4869871679016809e-05, 'epoch': 1.01}
{'loss': 0.4776, 'learning_rate': 1.4867160672329659e-05, 'epoch': 1.01}
{'loss': 0.6291, 'learning_rate': 1.4864449665642509e-05, 'epoch': 1.01}
{'loss': 0.6152, 'learning_rate': 1.4861738658955359e-05, 'epoch': 1.01}
{'loss': 0.9985, 'learning_rate': 1.4859027652268209e-05, 'epoch': 1.01}
{'loss': 1.308, 'learning_rate': 1.4856316645581061e-05, 'epoch': 1.01}
{'loss': 1.4361, 'learning_rate': 1.485360563889391e-05, 'epoch': 1.01}
{'loss': 0.4825, 'learning_rate': 1.485089463220676e-05, 'epoch': 1.01}
{'loss': 1.4488, 'learning_rate': 1.484818362551961e-05, 'epoch': 1.01}
{'loss': 0.6456, 'learning_rate': 1.4845472618832461e-05, 'epoch': 1.01}
{'loss': 0.3343, 'learning_rate': 1.484276161214531e-05, 'epoch': 1.01}
{'loss': 0.5991, 'learning_rate': 1.484005060545816e-05, 'epoch': 1.01}
{'loss': 0.6022, 'learning_rate': 1.483733959877101e-05, 'epoch': 1.01}
{'loss': 0.8182, 'learning_rate': 1.4834628592083862e-05, 'epoch': 1.01}
{'loss': 0.8771, 'learning_rate': 1.483191758539671e-05, 'epoch': 1.01}
{'loss': 0.9489, 'learning_rate': 1.482920657870956e-05, 'epoch': 1.01}
{'loss': 0.6271, 'learning_rate': 1.4826495572022412e-05, 'epoch': 1.01}
{'loss': 0.9622, 'learning_rate': 1.4823784565335262e-05, 'epoch': 1.01}
{'loss': 0.4204, 'learning_rate': 1.4821073558648111e-05, 'epoch': 1.01}
{'loss': 0.6196, 'learning_rate': 1.4818362551960961e-05, 'epoch': 1.01}
{'loss': 0.5093, 'learning_rate': 1.4815651545273813e-05, 'epoch': 1.01}
{'loss': 0.6176, 'learning_rate': 1.4812940538586663e-05, 'epoch': 1.01}
{'loss': 0.312, 'learning_rate': 1.4810229531899511e-05, 'epoch': 1.01}
{'loss': 0.7161, 'learning_rate': 1.4807518525212362e-05, 'epoch': 1.01}
{'loss': 0.5342, 'learning_rate': 1.4804807518525213e-05, 'epoch': 1.01}
{'loss': 0.397, 'learning_rate': 1.4802096511838064e-05, 'epoch': 1.01}
{'loss': 1.6012, 'learning_rate': 1.4799385505150912e-05, 'epoch': 1.01}
{'loss': 0.6011, 'learning_rate': 1.4796674498463764e-05, 'epoch': 1.01}
{'loss': 0.4135, 'learning_rate': 1.4793963491776614e-05, 'epoch': 1.01}
{'loss': 1.0275, 'learning_rate': 1.4791252485089464e-05, 'epoch': 1.01}
{'loss': 1.3031, 'learning_rate': 1.4788541478402313e-05, 'epoch': 1.01}
{'loss': 0.8895, 'learning_rate': 1.4785830471715164e-05, 'epoch': 1.01}
{'loss': 0.4339, 'learning_rate': 1.4783119465028015e-05, 'epoch': 1.01}
{'loss': 1.2779, 'learning_rate': 1.4780408458340865e-05, 'epoch': 1.01}
{'loss': 0.7632, 'learning_rate': 1.4777697451653713e-05, 'epoch': 1.01}
{'loss': 1.0145, 'learning_rate': 1.4774986444966565e-05, 'epoch': 1.02}
{'loss': 0.6004, 'learning_rate': 1.4772275438279415e-05, 'epoch': 1.02}
{'loss': 0.9721, 'learning_rate': 1.4769564431592265e-05, 'epoch': 1.02}
{'loss': 0.8531, 'learning_rate': 1.4766853424905115e-05, 'epoch': 1.02}
{'loss': 1.1264, 'learning_rate': 1.4764142418217965e-05, 'epoch': 1.02}
{'loss': 1.2396, 'learning_rate': 1.4761431411530816e-05, 'epoch': 1.02}
{'loss': 0.6151, 'learning_rate': 1.4758720404843666e-05, 'epoch': 1.02}
{'loss': 0.3889, 'learning_rate': 1.4756009398156516e-05, 'epoch': 1.02}
{'loss': 0.4879, 'learning_rate': 1.4753298391469366e-05, 'epoch': 1.02}
{'loss': 0.9232, 'learning_rate': 1.4750587384782216e-05, 'epoch': 1.02}
{'loss': 0.7024, 'learning_rate': 1.4747876378095066e-05, 'epoch': 1.02}

 51%|█████     | 5627/11066 [20:37<20:02,  4.52it/s]
 51%|█████     | 5628/11066 [20:37<20:04,  4.52it/s]
                                                    

 51%|█████     | 5628/11066 [20:37<20:04,  4.52it/s]
 51%|█████     | 5629/11066 [20:38<20:04,  4.51it/s]
                                                    

 51%|█████     | 5629/11066 [20:38<20:04,  4.51it/s]
 51%|█████     | 5630/11066 [20:38<20:06,  4.51it/s]
                                                    

 51%|█████     | 5630/11066 [20:38<20:06,  4.51it/s]
 51%|█████     | 5631/11066 [20:38<20:06,  4.50it/s]
                                                    

 51%|█████     | 5631/11066 [20:38<20:06,  4.50it/s]
 51%|█████     | 5632/11066 [20:38<20:06,  4.50it/s]
                                                    

 51%|█████     | 5632/11066 [20:38<20:06,  4.50it/s]
 51%|█████     | 5633/11066 [20:38<19:56,  4.54it/s]
                                                    

 51%|█████     | 5633/11066 [20:38<19:56,  4.54it/s]
 51%|█████     | 5634/11066 [20:39<20:04,  4.51it/s]
                                                    

 51%|█████     | 5634/11066 [20:39<20:04,  4.51it/s]
 51%|█████     | 5635/11066 [20:39<20:08,  4.49it/s]
                                                    

 51%|█████     | 5635/11066 [20:39<20:08,  4.49it/s]
 51%|█████     | 5636/11066 [20:39<20:09,  4.49it/s]
                                                    

 51%|█████     | 5636/11066 [20:39<20:09,  4.49it/s]
 51%|█████     | 5637/11066 [20:39<19:59,  4.53it/s]
                                                    

 51%|█████     | 5637/11066 [20:39<19:59,  4.53it/s]
 51%|█████     | 5638/11066 [20:40<20:05,  4.50it/s]
                                                    

 51%|█████     | 5638/11066 [20:40<20:05,  4.50it/s]
 51%|█████     | 5639/11066 [20:40<20:07,  4.50it/s]
                                                    

 51%|█████     | 5639/11066 [20:40<20:07,  4.50it/s]
 51%|█████     | 5640/11066 [20:40<20:07,  4.49it/s]
                                                    

 51%|█████     | 5640/11066 [20:40<20:07,  4.49it/s]
 51%|█████     | 5641/11066 [20:40<20:07,  4.49it/s]
                                                    

 51%|█████     | 5641/11066 [20:40<20:07,  4.49it/s]
 51%|█████     | 5642/11066 [20:40<20:11,  4.48it/s]
                                                    

 51%|█████     | 5642/11066 [20:40<20:11,  4.48it/s]
 51%|█████     | 5643/11066 [20:41<19:56,  4.53it/s]
                                                    

 51%|█████     | 5643/11066 [20:41<19:56,  4.53it/s]
 51%|█████     | 5644/11066 [20:41<19:53,  4.54it/s]
                                                    

 51%|█████     | 5644/11066 [20:41<19:53,  4.54it/s]
 51%|█████     | 5645/11066 [20:41<19:42,  4.59it/s]
                                                    

 51%|█████     | 5645/11066 [20:41<19:42,  4.59it/s]
 51%|█████     | 5646/11066 [20:41<19:33,  4.62it/s]
                                                    

 51%|█████     | 5646/11066 [20:41<19:33,  4.62it/s]
 51%|█████     | 5647/11066 [20:41<19:27,  4.64it/s]
                                                    

 51%|█████     | 5647/11066 [20:41<19:27,  4.64it/s]
 51%|█████     | 5648/11066 [20:42<19:18,  4.68it/s]
                                                    

 51%|█████     | 5648/11066 [20:42<19:18,  4.68it/s]
 51%|█████     | 5649/11066 [20:42<19:09,  4.71it/s]
                                                    

 51%|█████     | 5649/11066 [20:42<19:09,  4.71it/s]
 51%|█████     | 5650/11066 [20:42<19:10,  4.71it/s]
                                                    

 51%|█████     | 5650/11066 [20:42<19:10,  4.71it/s]
 51%|█████     | 5651/11066 [20:42<19:18,  4.68it/s]
                                                    

 51%|█████     | 5651/11066 [20:42<19:18,  4.68it/s]
 51%|█████     | 5652/11066 [20:43<19:20,  4.66it/s]
                                                    

 51%|█████     | 5652/11066 [20:43<19:20,  4.66it/s]
 51%|█████     | 5653/11066 [20:43<19:35,  4.60it/s]
                                                    

 51%|█████     | 5653/11066 [20:43<19:35,  4.60it/s]
 51%|█████     | 5654/11066 [20:43<19:36,  4.60it/s]
                                                    

 51%|█████     | 5654/11066 [20:43<19:36,  4.60it/s]
 51%|█████     | 5655/11066 [20:43<19:25,  4.64it/s]
                                                    

 51%|█████     | 5655/11066 [20:43<19:25,  4.64it/s]
 51%|█████     | 5656/11066 [20:43<19:14,  4.69it/s]
                                                    

 51%|█████     | 5656/11066 [20:43<19:14,  4.69it/s]
 51%|█████     | 5657/11066 [20:44<19:21,  4.66it/s]
                                                    

 51%|█████     | 5657/11066 [20:44<19:21,  4.66it/s]
 51%|█████     | 5658/11066 [20:44<19:13,  4.69it/s]
                                                    

 51%|█████     | 5658/11066 [20:44<19:13,  4.69it/s]
 51%|█████     | 5659/11066 [20:44<19:05,  4.72it/s]
                                                    

 51%|█████     | 5659/11066 [20:44<19:05,  4.72it/s]
 51%|█████     | 5660/11066 [20:44<19:06,  4.71it/s]
                                                    

 51%|█████     | 5660/11066 [20:44<19:06,  4.71it/s]
 51%|█████     | 5661/11066 [20:44<19:15,  4.68it/s]
                                                    

 51%|█████     | 5661/11066 [20:44<19:15,  4.68it/s]
 51%|█████     | 5662/11066 [20:45<19:20,  4.66it/s]
                                                    

 51%|█████     | 5662/11066 [20:45<19:20,  4.66it/s]
 51%|█████     | 5663/11066 [20:45<19:32,  4.61it/s]
                                                    

 51%|█████     | 5663/11066 [20:45<19:32,  4.61it/s]
 51%|█████     | 5664/11066 [20:45<19:24,  4.64it/s]
                                                    

 51%|█████     | 5664/11066 [20:45<19:24,  4.64it/s]
 51%|█████     | 5665/11066 [20:45<19:34,  4.60it/s]
                                                    

 51%|█████     | 5665/11066 [20:45<19:34,  4.60it/s]
 51%|█████     | 5666/11066 [20:46<19:39,  4.58it/s]
                                                    

 51%|█████     | 5666/11066 [20:46<19:39,  4.58it/s]
 51%|█████     | 5667/11066 [20:46<19:59,  4.50it/s]
                                                    

 51%|█████     | 5667/11066 [20:46<19:59,  4.50it/s]
 51%|█████     | 5668/11066 [20:46<20:06,  4.47it/s]
                                                    

 51%|█████     | 5668/11066 [20:46<20:06,  4.47it/s]
 51%|█████     | 5669/11066 [20:46<20:05,  4.48it/s]
                                                    

 51%|█████     | 5669/11066 [20:46<20:05,  4.48it/s]
 51%|█████     | 5670/11066 [20:46<20:03,  4.48it/s]
                                                    

 51%|█████     | 5670/11066 [20:46<20:03,  4.48it/s]
 51%|█████     | 5671/11066 [20:47<20:02,  4.49it/s]
                                                    

 51%|█████     | 5671/11066 [20:47<20:02,  4.49it/s]
 51%|█████▏    | 5672/11066 [20:47<20:01,  4.49it/s]
                                                    

 51%|█████▏    | 5672/11066 [20:47<20:01,  4.49it/s]
 51%|█████▏    | 5673/11066 [20:47<20:16,  4.43it/s]
                                                    

 51%|█████▏    | 5673/11066 [20:47<20:16,  4.43it/s]
 51%|█████▏    | 5674/11066 [20:47<20:26,  4.40it/s]
                                                    

 51%|█████▏    | 5674/11066 [20:47<20:26,  4.40it/s]
 51%|█████▏    | 5675/11066 [20:48<20:33,  4.37it/s]
                                                    

 51%|█████▏    | 5675/11066 [20:48<20:33,  4.37it/s]
 51%|█████▏    | 5676/11066 [20:48<20:41,  4.34it/s]
                                                    

 51%|█████▏    | 5676/11066 [20:48<20:41,  4.34it/s]
 51%|█████▏    | 5677/11066 [20:48<20:33,  4.37it/s]
                                                    

 51%|█████▏    | 5677/11066 [20:48<20:33,  4.37it/s]
 51%|█████▏    | 5678/11066 [20:48<20:16,  4.43it/s]
                                                    

 51%|█████▏    | 5678/11066 [20:48<20:16,  4.43it/s]
 51%|█████▏    | 5679/11066 [20:48<20:13,  4.44it/s]
                                                    

 51%|█████▏    | 5679/11066 [20:49<20:13,  4.44it/s]
 51%|█████▏    | 5680/11066 [20:49<20:10,  4.45it/s]
                                                    

 51%|█████▏    | 5680/11066 [20:49<20:10,  4.45it/s]
 51%|█████▏    | 5681/11066 [20:49<20:07,  4.46it/s]
                                                    

 51%|█████▏    | 5681/11066 [20:49<20:07,  4.46it/s]
 51%|█████▏    | 5682/11066 [20:49<20:04,  4.47it/s]
                                                    

 51%|█████▏    | 5682/11066 [20:49<20:04,  4.47it/s]
 51%|█████▏    | 5683/11066 [20:49<20:01,  4.48it/s]
                                                    

 51%|█████▏    | 5683/11066 [20:49<20:01,  4.48it/s]
 51%|█████▏    | 5684/11066 [20:50<19:59,  4.49it/s]
                                                    

 51%|█████▏    | 5684/11066 [20:50<19:59,  4.49it/s]
 51%|█████▏    | 5685/11066 [20:50<19:59,  4.49it/s]
                                                    

 51%|█████▏    | 5685/11066 [20:50<19:59,  4.49it/s]
 51%|█████▏    | 5686/11066 [20:50<19:58,  4.49it/s]
                                                    

 51%|█████▏    | 5686/11066 [20:50<19:58,  4.49it/s]
 51%|█████▏    | 5687/11066 [20:50<19:57,  4.49it/s]
                                                    

 51%|█████▏    | 5687/11066 [20:50<19:57,  4.49it/s]
 51%|█████▏    | 5688/11066 [20:51<19:56,  4.50it/s]
                                                    

 51%|█████▏    | 5688/11066 [20:51<19:56,  4.50it/s]
 51%|█████▏    | 5689/11066 [20:51<19:54,  4.50it/s]
                                                    

 51%|█████▏    | 5689/11066 [20:51<19:54,  4.50it/s]
 51%|█████▏    | 5690/11066 [20:51<19:54,  4.50it/s]
                                                    

 51%|█████▏    | 5690/11066 [20:51<19:54,  4.50it/s]
 51%|█████▏    | 5691/11066 [20:51<19:37,  4.57it/s]
                                                    

 51%|█████▏    | 5691/11066 [20:51<19:37,  4.57it/s]
 51%|█████▏    | 5692/11066 [20:51<19:25,  4.61it/s]
                                                    

 51%|█████▏    | 5692/11066 [20:51<19:25,  4.61it/s]
 51%|█████▏    | 5693/11066 [20:52<19:34,  4.58it/s]
                                                    

 51%|█████▏    | 5693/11066 [20:52<19:34,  4.58it/s]
 51%|█████▏    | 5694/11066 [20:52<19:40,  4.55it/s]
                                                    

 51%|█████▏    | 5694/11066 [20:52<19:40,  4.55it/s]
 51%|█████▏    | 5695/11066 [20:52<19:47,  4.52it/s]
                                                    

 51%|█████▏    | 5695/11066 [20:52<19:47,  4.52it/s]
 51%|█████▏    | 5696/11066 [20:52<19:56,  4.49it/s]
                                                    

 51%|█████▏    | 5696/11066 [20:52<19:56,  4.49it/s]
 51%|█████▏    | 5697/11066 [20:52<20:00,  4.47it/s]
                                                    

 51%|█████▏    | 5697/11066 [20:52<20:00,  4.47it/s]
 51%|█████▏    | 5698/11066 [20:53<20:01,  4.47it/s]
                                                    

 51%|█████▏    | 5698/11066 [20:53<20:01,  4.47it/s]
 52%|█████▏    | 5699/11066 [20:53<20:02,  4.46it/s]
                                                    

 52%|█████▏    | 5699/11066 [20:53<20:02,  4.46it/s]
 52%|█████▏    | 5700/11066 [20:53<20:19,  4.40it/s]
                                                    

 52%|█████▏    | 5700/11066 [20:53<20:19,  4.40it/s]
 52%|█████▏    | 5701/11066 [20:53<20:15,  4.41it/s]
                                                    

 52%|█████▏    | 5701/11066 [20:53<20:15,  4.41it/s]
 52%|█████▏    | 5702/11066 [20:54<20:08,  4.44it/s]
                                                    

 52%|█████▏    | 5702/11066 [20:54<20:08,  4.44it/s]
 52%|█████▏    | 5703/11066 [20:54<20:04,  4.45it/s]
                                                    

 52%|█████▏    | 5703/11066 [20:54<20:04,  4.45it/s]
 52%|█████▏    | 5704/11066 [20:54<19:58,  4.47it/s]
                                                    

 52%|█████▏    | 5704/11066 [20:54<19:58,  4.47it/s]
 52%|█████▏    | 5705/11066 [20:54<20:04,  4.45it/s]
                                                    

 52%|█████▏    | 5705/11066 [20:54<20:04,  4.45it/s]
 52%|█████▏    | 5706/11066 [20:55<20:24,  4.38it/s]
                                                    

 52%|█████▏    | 5706/11066 [20:55<20:24,  4.38it/s]
 52%|█████▏    | 5707/11066 [20:55<20:28,  4.36it/s]
                                                    

 52%|█████▏    | 5707/11066 [20:55<20:28,  4.36it/s]
 52%|█████▏    | 5708/11066 [20:55<20:19,  4.39it/s]
                                                    

 52%|█████▏    | 5708/11066 [20:55<20:19,  4.39it/s]
 52%|█████▏    | 5709/11066 [20:55<19:55,  4.48it/s]
                                                    

 52%|█████▏    | 5709/11066 [20:55<19:55,  4.48it/s]
 52%|█████▏    | 5710/11066 [20:55<19:45,  4.52it/s]
                                                    

 52%|█████▏    | 5710/11066 [20:55<19:45,  4.52it/s]
 52%|█████▏    | 5711/11066 [20:56<19:27,  4.59it/s]
                                                    

 52%|█████▏    | 5711/11066 [20:56<19:27,  4.59it/s]
 52%|█████▏    | 5712/11066 [20:56<19:11,  4.65it/s]
                                                    

 52%|█████▏    | 5712/11066 [20:56<19:11,  4.65it/s]
 52%|█████▏    | 5713/11066 [20:56<19:08,  4.66it/s]
                                                    

 52%|█████▏    | 5713/11066 [20:56<19:08,  4.66it/s]
 52%|█████▏    | 5714/11066 [20:56<19:13,  4.64it/s]
                                                    

 52%|█████▏    | 5714/11066 [20:56<19:13,  4.64it/s]
 52%|█████▏    | 5715/11066 [20:56<19:27,  4.58it/s]
                                                    

 52%|█████▏    | 5715/11066 [20:56<19:27,  4.58it/s]
 52%|█████▏    | 5716/11066 [20:57<19:36,  4.55it/s]
                                                    

 52%|█████▏    | 5716/11066 [20:57<19:36,  4.55it/s]
 52%|█████▏    | 5717/11066 [20:57<19:41,  4.53it/s]
                                                    

 52%|█████▏    | 5717/11066 [20:57<19:41,  4.53it/s]
 52%|█████▏    | 5718/11066 [20:57<19:45,  4.51it/s]
                                                    

 52%|█████▏    | 5718/11066 [20:57<19:45,  4.51it/s]
 52%|█████▏    | 5719/11066 [20:57<19:48,  4.50it/s]
                                                    

 52%|█████▏    | 5719/11066 [20:57<19:48,  4.50it/s]
 52%|█████▏    | 5720/11066 [20:58<19:48,  4.50it/s]
                                                    

 52%|█████▏    | 5720/11066 [20:58<19:48,  4.50it/s]
 52%|█████▏    | 5721/11066 [20:58<19:49,  4.49it/s]
                                                    

 52%|█████▏    | 5721/11066 [20:58<19:49,  4.49it/s]
 52%|█████▏    | 5722/11066 [20:58<19:26,  4.58it/s]
                                                    

 52%|█████▏    | 5722/11066 [20:58<19:26,  4.58it/s]
 52%|█████▏    | 5723/11066 [20:58<19:38,  4.53it/s]
                                                    

 52%|█████▏    | 5723/11066 [20:58<19:38,  4.53it/s]
 52%|█████▏    | 5724/11066 [20:58<19:42,  4.52it/s]
                                                    

 52%|█████▏    | 5724/11066 [20:58<19:42,  4.52it/s]
 52%|█████▏    | 5725/11066 [20:59<19:43,  4.51it/s]
                                                    

 52%|█████▏    | 5725/11066 [20:59<19:43,  4.51it/s]
 52%|█████▏    | 5726/11066 [20:59<19:43,  4.51it/s]
                                                    

 52%|█████▏    | 5726/11066 [20:59<19:43,  4.51it/s]
 52%|█████▏    | 5727/11066 [20:59<19:28,  4.57it/s]
                                                    

 52%|█████▏    | 5727/11066 [20:59<19:28,  4.57it/s]
 52%|█████▏    | 5728/11066 [20:59<19:17,  4.61it/s]
                                                    

 52%|█████▏    | 5728/11066 [20:59<19:17,  4.61it/s]
 52%|█████▏    | 5729/11066 [21:00<19:18,  4.61it/s]
                                                    

 52%|█████▏    | 5729/11066 [21:00<19:18,  4.61it/s]
 52%|█████▏    | 5730/11066 [21:00<19:09,  4.64it/s]
                                                    

 52%|█████▏    | 5730/11066 [21:00<19:09,  4.64it/s]
 52%|█████▏    | 5731/11066 [21:00<19:20,  4.60it/s]
                                                    

 52%|█████▏    | 5731/11066 [21:00<19:20,  4.60it/s]
 52%|█████▏    | 5732/11066 [21:00<19:08,  4.64it/s]
                                                    

 52%|█████▏    | 5732/11066 [21:00<19:08,  4.64it/s]
 52%|█████▏    | 5733/11066 [21:00<19:13,  4.63it/s]
                                                    

 52%|█████▏    | 5733/11066 [21:00<19:13,  4.63it/s]
 52%|█████▏    | 5734/11066 [21:01<19:06,  4.65it/s]
                                                    

 52%|█████▏    | 5734/11066 [21:01<19:06,  4.65it/s]
 52%|█████▏    | 5735/11066 [21:01<19:02,  4.67it/s]
                                                    

 52%|█████▏    | 5735/11066 [21:01<19:02,  4.67it/s]
 52%|█████▏    | 5736/11066 [21:01<19:09,  4.64it/s]
                                                    

 52%|█████▏    | 5736/11066 [21:01<19:09,  4.64it/s]
 52%|█████▏    | 5737/11066 [21:01<19:01,  4.67it/s]
                                                    

 52%|█████▏    | 5737/11066 [21:01<19:01,  4.67it/s]
 52%|█████▏    | 5738/11066 [21:02<19:08,  4.64it/s]
                                                    

 52%|█████▏    | 5738/11066 [21:02<19:08,  4.64it/s]
 52%|█████▏    | 5739/11066 [21:02<19:03,  4.66it/s]
                                                    
{'loss': 1.251, 'learning_rate': 1.4745165371407916e-05, 'epoch': 1.02}
{'loss': 0.744, 'learning_rate': 1.4742454364720767e-05, 'epoch': 1.02}
{'loss': 0.5651, 'learning_rate': 1.4739743358033617e-05, 'epoch': 1.02}
{'loss': 0.8896, 'learning_rate': 1.4737032351346468e-05, 'epoch': 1.02}
{'loss': 0.5959, 'learning_rate': 1.4734321344659317e-05, 'epoch': 1.02}
{'loss': 1.5154, 'learning_rate': 1.4731610337972167e-05, 'epoch': 1.02}
{'loss': 0.4811, 'learning_rate': 1.4728899331285017e-05, 'epoch': 1.02}
{'loss': 1.0965, 'learning_rate': 1.4726188324597869e-05, 'epoch': 1.02}
{'loss': 0.8403, 'learning_rate': 1.4723477317910717e-05, 'epoch': 1.02}
{'loss': 0.7401, 'learning_rate': 1.4720766311223568e-05, 'epoch': 1.02}
{'loss': 0.4894, 'learning_rate': 1.4718055304536418e-05, 'epoch': 1.02}
{'loss': 0.5438, 'learning_rate': 1.471534429784927e-05, 'epoch': 1.02}
{'loss': 0.8055, 'learning_rate': 1.4712633291162118e-05, 'epoch': 1.02}
{'loss': 0.7423, 'learning_rate': 1.4709922284474968e-05, 'epoch': 1.02}
{'loss': 0.8079, 'learning_rate': 1.470721127778782e-05, 'epoch': 1.02}
{'loss': 0.5526, 'learning_rate': 1.470450027110067e-05, 'epoch': 1.02}
{'loss': 0.6293, 'learning_rate': 1.4701789264413519e-05, 'epoch': 1.02}
{'loss': 0.8374, 'learning_rate': 1.4699078257726369e-05, 'epoch': 1.02}
{'loss': 0.6737, 'learning_rate': 1.469636725103922e-05, 'epoch': 1.02}
{'loss': 0.695, 'learning_rate': 1.469365624435207e-05, 'epoch': 1.02}
{'loss': 1.1417, 'learning_rate': 1.4690945237664919e-05, 'epoch': 1.02}
{'loss': 1.6744, 'learning_rate': 1.4688234230977771e-05, 'epoch': 1.02}
{'loss': 0.7383, 'learning_rate': 1.4685523224290621e-05, 'epoch': 1.02}
{'loss': 0.6321, 'learning_rate': 1.4682812217603471e-05, 'epoch': 1.02}
{'loss': 0.2684, 'learning_rate': 1.468010121091632e-05, 'epoch': 1.02}
{'loss': 0.485, 'learning_rate': 1.4677390204229171e-05, 'epoch': 1.02}
{'loss': 0.1926, 'learning_rate': 1.4674679197542022e-05, 'epoch': 1.02}
{'loss': 0.6469, 'learning_rate': 1.4671968190854872e-05, 'epoch': 1.02}
{'loss': 0.5135, 'learning_rate': 1.466925718416772e-05, 'epoch': 1.02}
{'loss': 0.936, 'learning_rate': 1.4666546177480572e-05, 'epoch': 1.02}
{'loss': 0.6915, 'learning_rate': 1.4663835170793422e-05, 'epoch': 1.02}
{'loss': 0.7359, 'learning_rate': 1.4661124164106272e-05, 'epoch': 1.02}
{'loss': 0.8522, 'learning_rate': 1.4658413157419122e-05, 'epoch': 1.02}
{'loss': 0.5363, 'learning_rate': 1.4655702150731973e-05, 'epoch': 1.02}
{'loss': 1.0846, 'learning_rate': 1.4652991144044823e-05, 'epoch': 1.02}
{'loss': 0.8446, 'learning_rate': 1.4650280137357671e-05, 'epoch': 1.02}
{'loss': 0.8633, 'learning_rate': 1.4647569130670523e-05, 'epoch': 1.02}
{'loss': 0.6174, 'learning_rate': 1.4644858123983373e-05, 'epoch': 1.02}
{'loss': 0.9205, 'learning_rate': 1.4642147117296223e-05, 'epoch': 1.02}
{'loss': 0.6606, 'learning_rate': 1.4639436110609072e-05, 'epoch': 1.02}
{'loss': 0.7247, 'learning_rate': 1.4636725103921923e-05, 'epoch': 1.02}
{'loss': 1.6146, 'learning_rate': 1.4634014097234774e-05, 'epoch': 1.02}
{'loss': 0.5345, 'learning_rate': 1.4631303090547624e-05, 'epoch': 1.02}
{'loss': 0.8331, 'learning_rate': 1.4628592083860474e-05, 'epoch': 1.02}
{'loss': 0.923, 'learning_rate': 1.4625881077173324e-05, 'epoch': 1.02}
{'loss': 0.8851, 'learning_rate': 1.4623170070486174e-05, 'epoch': 1.03}
{'loss': 0.9294, 'learning_rate': 1.4620459063799024e-05, 'epoch': 1.03}
{'loss': 0.6119, 'learning_rate': 1.4617748057111874e-05, 'epoch': 1.03}
{'loss': 1.1553, 'learning_rate': 1.4615037050424725e-05, 'epoch': 1.03}
{'loss': 0.6947, 'learning_rate': 1.4612326043737575e-05, 'epoch': 1.03}
{'loss': 1.3493, 'learning_rate': 1.4609615037050425e-05, 'epoch': 1.03}
{'loss': 0.6865, 'learning_rate': 1.4606904030363275e-05, 'epoch': 1.03}
{'loss': 0.7651, 'learning_rate': 1.4604193023676125e-05, 'epoch': 1.03}
{'loss': 0.5318, 'learning_rate': 1.4601482016988975e-05, 'epoch': 1.03}
{'loss': 0.5395, 'learning_rate': 1.4598771010301827e-05, 'epoch': 1.03}
{'loss': 0.7239, 'learning_rate': 1.4596060003614675e-05, 'epoch': 1.03}
{'loss': 1.0899, 'learning_rate': 1.4593348996927526e-05, 'epoch': 1.03}
{'loss': 1.1303, 'learning_rate': 1.4590637990240376e-05, 'epoch': 1.03}
{'loss': 1.0575, 'learning_rate': 1.4587926983553228e-05, 'epoch': 1.03}
{'loss': 0.6633, 'learning_rate': 1.4585215976866076e-05, 'epoch': 1.03}
{'loss': 0.2632, 'learning_rate': 1.4582504970178926e-05, 'epoch': 1.03}
{'loss': 0.641, 'learning_rate': 1.4579793963491776e-05, 'epoch': 1.03}
{'loss': 0.653, 'learning_rate': 1.4577082956804628e-05, 'epoch': 1.03}
{'loss': 0.5775, 'learning_rate': 1.4574371950117477e-05, 'epoch': 1.03}
{'loss': 0.8516, 'learning_rate': 1.4571660943430327e-05, 'epoch': 1.03}
{'loss': 0.8436, 'learning_rate': 1.4568949936743179e-05, 'epoch': 1.03}
{'loss': 0.9707, 'learning_rate': 1.4566238930056029e-05, 'epoch': 1.03}
{'loss': 0.3721, 'learning_rate': 1.4563527923368877e-05, 'epoch': 1.03}
{'loss': 0.4385, 'learning_rate': 1.4560816916681727e-05, 'epoch': 1.03}
{'loss': 0.5403, 'learning_rate': 1.4558105909994579e-05, 'epoch': 1.03}
{'loss': 0.3315, 'learning_rate': 1.455539490330743e-05, 'epoch': 1.03}
{'loss': 1.0782, 'learning_rate': 1.4552683896620278e-05, 'epoch': 1.03}
{'loss': 0.7411, 'learning_rate': 1.4549972889933128e-05, 'epoch': 1.03}
{'loss': 0.7978, 'learning_rate': 1.454726188324598e-05, 'epoch': 1.03}
{'loss': 0.6505, 'learning_rate': 1.454455087655883e-05, 'epoch': 1.03}
{'loss': 0.349, 'learning_rate': 1.4541839869871678e-05, 'epoch': 1.03}
{'loss': 0.4873, 'learning_rate': 1.453912886318453e-05, 'epoch': 1.03}
{'loss': 0.9697, 'learning_rate': 1.453641785649738e-05, 'epoch': 1.03}
{'loss': 1.4095, 'learning_rate': 1.453370684981023e-05, 'epoch': 1.03}
{'loss': 1.2429, 'learning_rate': 1.4530995843123079e-05, 'epoch': 1.03}
{'loss': 1.251, 'learning_rate': 1.452828483643593e-05, 'epoch': 1.03}
{'loss': 0.8815, 'learning_rate': 1.452557382974878e-05, 'epoch': 1.03}
{'loss': 0.6302, 'learning_rate': 1.452286282306163e-05, 'epoch': 1.03}
{'loss': 0.9274, 'learning_rate': 1.4520151816374481e-05, 'epoch': 1.03}
{'loss': 0.8147, 'learning_rate': 1.4517440809687331e-05, 'epoch': 1.03}
{'loss': 0.5193, 'learning_rate': 1.4514729803000181e-05, 'epoch': 1.03}
{'loss': 0.9526, 'learning_rate': 1.4512018796313031e-05, 'epoch': 1.03}
{'loss': 1.651, 'learning_rate': 1.4509307789625881e-05, 'epoch': 1.03}
{'loss': 0.563, 'learning_rate': 1.4506596782938732e-05, 'epoch': 1.03}
{'loss': 1.012, 'learning_rate': 1.4503885776251582e-05, 'epoch': 1.03}
{'loss': 0.6023, 'learning_rate': 1.4501174769564432e-05, 'epoch': 1.03}
{'loss': 1.0398, 'learning_rate': 1.4498463762877282e-05, 'epoch': 1.03}
{'loss': 0.9023, 'learning_rate': 1.4495752756190132e-05, 'epoch': 1.03}
{'loss': 0.3622, 'learning_rate': 1.4493041749502982e-05, 'epoch': 1.03}
{'loss': 0.5426, 'learning_rate': 1.4490330742815834e-05, 'epoch': 1.03}
{'loss': 0.6314, 'learning_rate': 1.4487619736128683e-05, 'epoch': 1.03}
{'loss': 0.3036, 'learning_rate': 1.4484908729441533e-05, 'epoch': 1.03}
{'loss': 0.3499, 'learning_rate': 1.4482197722754383e-05, 'epoch': 1.03}
{'loss': 0.9772, 'learning_rate': 1.4479486716067235e-05, 'epoch': 1.03}
{'loss': 0.4542, 'learning_rate': 1.4476775709380083e-05, 'epoch': 1.03}
{'loss': 0.6556, 'learning_rate': 1.4474064702692933e-05, 'epoch': 1.04}
{'loss': 0.5315, 'learning_rate': 1.4471353696005783e-05, 'epoch': 1.04}
{'loss': 0.5378, 'learning_rate': 1.4468642689318635e-05, 'epoch': 1.04}
{'loss': 0.8806, 'learning_rate': 1.4465931682631484e-05, 'epoch': 1.04}
{'loss': 0.5878, 'learning_rate': 1.4463220675944334e-05, 'epoch': 1.04}
{'loss': 0.824, 'learning_rate': 1.4460509669257186e-05, 'epoch': 1.04}
{'loss': 0.5159, 'learning_rate': 1.4457798662570036e-05, 'epoch': 1.04}
{'loss': 0.6551, 'learning_rate': 1.4455087655882884e-05, 'epoch': 1.04}
{'loss': 0.5943, 'learning_rate': 1.4452376649195734e-05, 'epoch': 1.04}
{'loss': 0.7423, 'learning_rate': 1.4449665642508586e-05, 'epoch': 1.04}
{'loss': 0.4333, 'learning_rate': 1.4446954635821436e-05, 'epoch': 1.04}
{'loss': 0.5298, 'learning_rate': 1.4444243629134285e-05, 'epoch': 1.04}

 52%|█████▏    | 5739/11066 [21:02<19:03,  4.66it/s]
 52%|█████▏    | 5740/11066 [21:02<19:00,  4.67it/s]
                                                    

 52%|█████▏    | 5740/11066 [21:02<19:00,  4.67it/s]
 52%|█████▏    | 5741/11066 [21:02<19:05,  4.65it/s]
                                                    

 52%|█████▏    | 5741/11066 [21:02<19:05,  4.65it/s]
 52%|█████▏    | 5742/11066 [21:02<18:55,  4.69it/s]
                                                    

 52%|█████▏    | 5742/11066 [21:02<18:55,  4.69it/s]
 52%|█████▏    | 5743/11066 [21:03<19:02,  4.66it/s]
                                                    

 52%|█████▏    | 5743/11066 [21:03<19:02,  4.66it/s]
 52%|█████▏    | 5744/11066 [21:03<19:18,  4.59it/s]
                                                    

 52%|█████▏    | 5744/11066 [21:03<19:18,  4.59it/s]
 52%|█████▏    | 5745/11066 [21:03<19:20,  4.59it/s]
                                                    

 52%|█████▏    | 5745/11066 [21:03<19:20,  4.59it/s]
 52%|█████▏    | 5746/11066 [21:03<19:05,  4.64it/s]
                                                    

 52%|█████▏    | 5746/11066 [21:03<19:05,  4.64it/s]
 52%|█████▏    | 5747/11066 [21:03<19:08,  4.63it/s]
                                                    

 52%|█████▏    | 5747/11066 [21:03<19:08,  4.63it/s]
 52%|█████▏    | 5748/11066 [21:04<18:59,  4.67it/s]
                                                    

 52%|█████▏    | 5748/11066 [21:04<18:59,  4.67it/s]
 52%|█████▏    | 5749/11066 [21:04<18:57,  4.67it/s]
                                                    

 52%|█████▏    | 5749/11066 [21:04<18:57,  4.67it/s]
 52%|█████▏    | 5750/11066 [21:04<18:54,  4.69it/s]
                                                    

 52%|█████▏    | 5750/11066 [21:04<18:54,  4.69it/s]
 52%|█████▏    | 5751/11066 [21:04<19:13,  4.61it/s]
                                                    

 52%|█████▏    | 5751/11066 [21:04<19:13,  4.61it/s]
 52%|█████▏    | 5752/11066 [21:05<19:13,  4.61it/s]
                                                    

 52%|█████▏    | 5752/11066 [21:05<19:13,  4.61it/s]
 52%|█████▏    | 5753/11066 [21:05<19:01,  4.65it/s]
                                                    

 52%|█████▏    | 5753/11066 [21:05<19:01,  4.65it/s]
 52%|█████▏    | 5754/11066 [21:05<19:15,  4.60it/s]
                                                    

 52%|█████▏    | 5754/11066 [21:05<19:15,  4.60it/s]
 52%|█████▏    | 5755/11066 [21:05<19:10,  4.62it/s]
                                                    

 52%|█████▏    | 5755/11066 [21:05<19:10,  4.62it/s]
 52%|█████▏    | 5756/11066 [21:05<19:03,  4.64it/s]
                                                    

 52%|█████▏    | 5756/11066 [21:05<19:03,  4.64it/s]
 52%|█████▏    | 5757/11066 [21:06<19:07,  4.63it/s]
                                                    

 52%|█████▏    | 5757/11066 [21:06<19:07,  4.63it/s]
 52%|█████▏    | 5758/11066 [21:06<18:55,  4.68it/s]
                                                    

 52%|█████▏    | 5758/11066 [21:06<18:55,  4.68it/s]
 52%|█████▏    | 5759/11066 [21:06<18:53,  4.68it/s]
                                                    

 52%|█████▏    | 5759/11066 [21:06<18:53,  4.68it/s]
 52%|█████▏    | 5760/11066 [21:06<18:50,  4.69it/s]
                                                    

 52%|█████▏    | 5760/11066 [21:06<18:50,  4.69it/s]
 52%|█████▏    | 5761/11066 [21:06<18:49,  4.70it/s]
                                                    

 52%|█████▏    | 5761/11066 [21:06<18:49,  4.70it/s]
 52%|█████▏    | 5762/11066 [21:07<18:55,  4.67it/s]
                                                    

 52%|█████▏    | 5762/11066 [21:07<18:55,  4.67it/s]
 52%|█████▏    | 5763/11066 [21:07<19:04,  4.63it/s]
                                                    

 52%|█████▏    | 5763/11066 [21:07<19:04,  4.63it/s]
 52%|█████▏    | 5764/11066 [21:07<19:13,  4.60it/s]
                                                    

 52%|█████▏    | 5764/11066 [21:07<19:13,  4.60it/s]
 52%|█████▏    | 5765/11066 [21:07<19:22,  4.56it/s]
                                                    

 52%|█████▏    | 5765/11066 [21:07<19:22,  4.56it/s]
 52%|█████▏    | 5766/11066 [21:08<19:13,  4.59it/s]
                                                    

 52%|█████▏    | 5766/11066 [21:08<19:13,  4.59it/s]
 52%|█████▏    | 5767/11066 [21:08<19:06,  4.62it/s]
                                                    

 52%|█████▏    | 5767/11066 [21:08<19:06,  4.62it/s]
 52%|█████▏    | 5768/11066 [21:08<19:03,  4.63it/s]
                                                    

 52%|█████▏    | 5768/11066 [21:08<19:03,  4.63it/s]
 52%|█████▏    | 5769/11066 [21:08<19:15,  4.58it/s]
                                                    

 52%|█████▏    | 5769/11066 [21:08<19:15,  4.58it/s]
 52%|█████▏    | 5770/11066 [21:08<19:14,  4.59it/s]
                                                    

 52%|█████▏    | 5770/11066 [21:08<19:14,  4.59it/s]
 52%|█████▏    | 5771/11066 [21:09<18:59,  4.65it/s]
                                                    

 52%|█████▏    | 5771/11066 [21:09<18:59,  4.65it/s]
 52%|█████▏    | 5772/11066 [21:09<18:56,  4.66it/s]
                                                    

 52%|█████▏    | 5772/11066 [21:09<18:56,  4.66it/s]
 52%|█████▏    | 5773/11066 [21:09<18:58,  4.65it/s]
                                                    

 52%|█████▏    | 5773/11066 [21:09<18:58,  4.65it/s]
 52%|█████▏    | 5774/11066 [21:09<18:49,  4.69it/s]
                                                    

 52%|█████▏    | 5774/11066 [21:09<18:49,  4.69it/s]
 52%|█████▏    | 5775/11066 [21:09<18:47,  4.69it/s]
                                                    

 52%|█████▏    | 5775/11066 [21:09<18:47,  4.69it/s]
 52%|█████▏    | 5776/11066 [21:10<18:45,  4.70it/s]
                                                    

 52%|█████▏    | 5776/11066 [21:10<18:45,  4.70it/s]
 52%|█████▏    | 5777/11066 [21:10<19:00,  4.64it/s]
                                                    

 52%|█████▏    | 5777/11066 [21:10<19:00,  4.64it/s]
 52%|█████▏    | 5778/11066 [21:10<19:04,  4.62it/s]
                                                    

 52%|█████▏    | 5778/11066 [21:10<19:04,  4.62it/s]
 52%|█████▏    | 5779/11066 [21:10<19:03,  4.62it/s]
                                                    

 52%|█████▏    | 5779/11066 [21:10<19:03,  4.62it/s]
 52%|█████▏    | 5780/11066 [21:11<19:05,  4.61it/s]
                                                    

 52%|█████▏    | 5780/11066 [21:11<19:05,  4.61it/s]
 52%|█████▏    | 5781/11066 [21:11<19:06,  4.61it/s]
                                                    

 52%|█████▏    | 5781/11066 [21:11<19:06,  4.61it/s]
 52%|█████▏    | 5782/11066 [21:11<19:06,  4.61it/s]
                                                    

 52%|█████▏    | 5782/11066 [21:11<19:06,  4.61it/s]
 52%|█████▏    | 5783/11066 [21:11<18:54,  4.66it/s]
                                                    

 52%|█████▏    | 5783/11066 [21:11<18:54,  4.66it/s]
 52%|█████▏    | 5784/11066 [21:11<18:50,  4.67it/s]
                                                    

 52%|█████▏    | 5784/11066 [21:11<18:50,  4.67it/s]
 52%|█████▏    | 5785/11066 [21:12<18:47,  4.68it/s]
                                                    

 52%|█████▏    | 5785/11066 [21:12<18:47,  4.68it/s]
 52%|█████▏    | 5786/11066 [21:12<18:44,  4.70it/s]
                                                    

 52%|█████▏    | 5786/11066 [21:12<18:44,  4.70it/s]
 52%|█████▏    | 5787/11066 [21:12<18:41,  4.71it/s]
                                                    

 52%|█████▏    | 5787/11066 [21:12<18:41,  4.71it/s]
 52%|█████▏    | 5788/11066 [21:12<18:48,  4.68it/s]
                                                    

 52%|█████▏    | 5788/11066 [21:12<18:48,  4.68it/s]
 52%|█████▏    | 5789/11066 [21:12<18:55,  4.65it/s]
                                                    

 52%|█████▏    | 5789/11066 [21:12<18:55,  4.65it/s]
 52%|█████▏    | 5790/11066 [21:13<19:06,  4.60it/s]
                                                    

 52%|█████▏    | 5790/11066 [21:13<19:06,  4.60it/s]
 52%|█████▏    | 5791/11066 [21:13<18:59,  4.63it/s]
                                                    

 52%|█████▏    | 5791/11066 [21:13<18:59,  4.63it/s]
 52%|█████▏    | 5792/11066 [21:13<19:00,  4.62it/s]
                                                    

 52%|█████▏    | 5792/11066 [21:13<19:00,  4.62it/s]
 52%|█████▏    | 5793/11066 [21:13<19:16,  4.56it/s]
                                                    

 52%|█████▏    | 5793/11066 [21:13<19:16,  4.56it/s]
 52%|█████▏    | 5794/11066 [21:14<19:12,  4.57it/s]
                                                    

 52%|█████▏    | 5794/11066 [21:14<19:12,  4.57it/s]
 52%|█████▏    | 5795/11066 [21:14<19:05,  4.60it/s]
                                                    

 52%|█████▏    | 5795/11066 [21:14<19:05,  4.60it/s]
 52%|█████▏    | 5796/11066 [21:14<18:55,  4.64it/s]
                                                    

 52%|█████▏    | 5796/11066 [21:14<18:55,  4.64it/s]
 52%|█████▏    | 5797/11066 [21:14<19:03,  4.61it/s]
                                                    

 52%|█████▏    | 5797/11066 [21:14<19:03,  4.61it/s]
 52%|█████▏    | 5798/11066 [21:14<18:58,  4.63it/s]
                                                    

 52%|█████▏    | 5798/11066 [21:14<18:58,  4.63it/s]
 52%|█████▏    | 5799/11066 [21:15<19:11,  4.57it/s]
                                                    

 52%|█████▏    | 5799/11066 [21:15<19:11,  4.57it/s]
 52%|█████▏    | 5800/11066 [21:15<19:18,  4.54it/s]
                                                    

 52%|█████▏    | 5800/11066 [21:15<19:18,  4.54it/s]
 52%|█████▏    | 5801/11066 [21:15<19:24,  4.52it/s]
                                                    

 52%|█████▏    | 5801/11066 [21:15<19:24,  4.52it/s]
 52%|█████▏    | 5802/11066 [21:15<19:17,  4.55it/s]
                                                    

 52%|█████▏    | 5802/11066 [21:15<19:17,  4.55it/s]
 52%|█████▏    | 5803/11066 [21:16<19:23,  4.52it/s]
                                                    

 52%|█████▏    | 5803/11066 [21:16<19:23,  4.52it/s]
 52%|█████▏    | 5804/11066 [21:16<19:07,  4.59it/s]
                                                    

 52%|█████▏    | 5804/11066 [21:16<19:07,  4.59it/s]
 52%|█████▏    | 5805/11066 [21:16<18:51,  4.65it/s]
                                                    

 52%|█████▏    | 5805/11066 [21:16<18:51,  4.65it/s]
 52%|█████▏    | 5806/11066 [21:16<18:49,  4.66it/s]
                                                    

 52%|█████▏    | 5806/11066 [21:16<18:49,  4.66it/s]
 52%|█████▏    | 5807/11066 [21:16<18:46,  4.67it/s]
                                                    

 52%|█████▏    | 5807/11066 [21:16<18:46,  4.67it/s]
 52%|█████▏    | 5808/11066 [21:17<18:50,  4.65it/s]
                                                    

 52%|█████▏    | 5808/11066 [21:17<18:50,  4.65it/s]
 52%|█████▏    | 5809/11066 [21:17<18:49,  4.66it/s]
                                                    

 52%|█████▏    | 5809/11066 [21:17<18:49,  4.66it/s]
 53%|█████▎    | 5810/11066 [21:17<19:02,  4.60it/s]
                                                    

 53%|█████▎    | 5810/11066 [21:17<19:02,  4.60it/s]
 53%|█████▎    | 5811/11066 [21:17<19:11,  4.56it/s]
                                                    

 53%|█████▎    | 5811/11066 [21:17<19:11,  4.56it/s]
 53%|█████▎    | 5812/11066 [21:18<19:16,  4.54it/s]
                                                    

 53%|█████▎    | 5812/11066 [21:18<19:16,  4.54it/s]
 53%|█████▎    | 5813/11066 [21:18<19:10,  4.57it/s]
                                                    

 53%|█████▎    | 5813/11066 [21:18<19:10,  4.57it/s]
 53%|█████▎    | 5814/11066 [21:18<19:01,  4.60it/s]
                                                    

 53%|█████▎    | 5814/11066 [21:18<19:01,  4.60it/s]
 53%|█████▎    | 5815/11066 [21:18<18:49,  4.65it/s]
                                                    

 53%|█████▎    | 5815/11066 [21:18<18:49,  4.65it/s]
 53%|█████▎    | 5816/11066 [21:18<18:50,  4.64it/s]
                                                    

 53%|█████▎    | 5816/11066 [21:18<18:50,  4.64it/s]
 53%|█████▎    | 5817/11066 [21:19<18:48,  4.65it/s]
                                                    

 53%|█████▎    | 5817/11066 [21:19<18:48,  4.65it/s]
 53%|█████▎    | 5818/11066 [21:19<19:03,  4.59it/s]
                                                    

 53%|█████▎    | 5818/11066 [21:19<19:03,  4.59it/s]
 53%|█████▎    | 5819/11066 [21:19<19:11,  4.55it/s]
                                                    

 53%|█████▎    | 5819/11066 [21:19<19:11,  4.55it/s]
 53%|█████▎    | 5820/11066 [21:19<19:10,  4.56it/s]
                                                    

 53%|█████▎    | 5820/11066 [21:19<19:10,  4.56it/s]
 53%|█████▎    | 5821/11066 [21:19<18:58,  4.61it/s]
                                                    

 53%|█████▎    | 5821/11066 [21:19<18:58,  4.61it/s]
 53%|█████▎    | 5822/11066 [21:20<19:12,  4.55it/s]
                                                    

 53%|█████▎    | 5822/11066 [21:20<19:12,  4.55it/s]
 53%|█████▎    | 5823/11066 [21:20<19:18,  4.53it/s]
                                                    

 53%|█████▎    | 5823/11066 [21:20<19:18,  4.53it/s]
 53%|█████▎    | 5824/11066 [21:20<19:05,  4.58it/s]
                                                    

 53%|█████▎    | 5824/11066 [21:20<19:05,  4.58it/s]
 53%|█████▎    | 5825/11066 [21:20<19:03,  4.59it/s]
                                                    

 53%|█████▎    | 5825/11066 [21:20<19:03,  4.59it/s]
 53%|█████▎    | 5826/11066 [21:21<19:14,  4.54it/s]
                                                    

 53%|█████▎    | 5826/11066 [21:21<19:14,  4.54it/s]
 53%|█████▎    | 5827/11066 [21:21<19:18,  4.52it/s]
                                                    

 53%|█████▎    | 5827/11066 [21:21<19:18,  4.52it/s]
 53%|█████▎    | 5828/11066 [21:21<19:20,  4.51it/s]
                                                    

 53%|█████▎    | 5828/11066 [21:21<19:20,  4.51it/s]
 53%|█████▎    | 5829/11066 [21:21<19:05,  4.57it/s]
                                                    

 53%|█████▎    | 5829/11066 [21:21<19:05,  4.57it/s]
 53%|█████▎    | 5830/11066 [21:21<19:02,  4.58it/s]
                                                    

 53%|█████▎    | 5830/11066 [21:21<19:02,  4.58it/s]
 53%|█████▎    | 5831/11066 [21:22<18:48,  4.64it/s]
                                                    

 53%|█████▎    | 5831/11066 [21:22<18:48,  4.64it/s]
 53%|█████▎    | 5832/11066 [21:22<18:37,  4.69it/s]
                                                    

 53%|█████▎    | 5832/11066 [21:22<18:37,  4.69it/s]
 53%|█████▎    | 5833/11066 [21:22<18:44,  4.65it/s]
                                                    

 53%|█████▎    | 5833/11066 [21:22<18:44,  4.65it/s]
 53%|█████▎    | 5834/11066 [21:22<18:38,  4.68it/s]
                                                    

 53%|█████▎    | 5834/11066 [21:22<18:38,  4.68it/s]
 53%|█████▎    | 5835/11066 [21:22<18:47,  4.64it/s]
                                                    

 53%|█████▎    | 5835/11066 [21:23<18:47,  4.64it/s]
 53%|█████▎    | 5836/11066 [21:23<18:58,  4.59it/s]
                                                    

 53%|█████▎    | 5836/11066 [21:23<18:58,  4.59it/s]
 53%|█████▎    | 5837/11066 [21:23<18:56,  4.60it/s]
                                                    

 53%|█████▎    | 5837/11066 [21:23<18:56,  4.60it/s]
 53%|█████▎    | 5838/11066 [21:23<18:57,  4.60it/s]
                                                    

 53%|█████▎    | 5838/11066 [21:23<18:57,  4.60it/s]
 53%|█████▎    | 5839/11066 [21:23<18:48,  4.63it/s]
                                                    

 53%|█████▎    | 5839/11066 [21:23<18:48,  4.63it/s]
 53%|█████▎    | 5840/11066 [21:24<18:51,  4.62it/s]
                                                    

 53%|█████▎    | 5840/11066 [21:24<18:51,  4.62it/s]
 53%|█████▎    | 5841/11066 [21:24<18:45,  4.64it/s]
                                                    

 53%|█████▎    | 5841/11066 [21:24<18:45,  4.64it/s]
 53%|█████▎    | 5842/11066 [21:24<18:41,  4.66it/s]
                                                    

 53%|█████▎    | 5842/11066 [21:24<18:41,  4.66it/s]
 53%|█████▎    | 5843/11066 [21:24<18:38,  4.67it/s]
                                                    

 53%|█████▎    | 5843/11066 [21:24<18:38,  4.67it/s]
 53%|█████▎    | 5844/11066 [21:24<18:38,  4.67it/s]
                                                    

 53%|█████▎    | 5844/11066 [21:24<18:38,  4.67it/s]
 53%|█████▎    | 5845/11066 [21:25<18:44,  4.64it/s]
                                                    

 53%|█████▎    | 5845/11066 [21:25<18:44,  4.64it/s]
 53%|█████▎    | 5846/11066 [21:25<18:39,  4.66it/s]
                                                    

 53%|█████▎    | 5846/11066 [21:25<18:39,  4.66it/s]
 53%|█████▎    | 5847/11066 [21:25<18:36,  4.67it/s]
                                                    

 53%|█████▎    | 5847/11066 [21:25<18:36,  4.67it/s]
 53%|█████▎    | 5848/11066 [21:25<18:34,  4.68it/s]
                                                    

 53%|█████▎    | 5848/11066 [21:25<18:34,  4.68it/s]
 53%|█████▎    | 5849/11066 [21:26<18:42,  4.65it/s]
                                                    

 53%|█████▎    | 5849/11066 [21:26<18:42,  4.65it/s]
 53%|█████▎    | 5850/11066 [21:26<18:44,  4.64it/s]
                                                    

 53%|█████▎    | 5850/11066 [21:26<18:44,  4.64it/s]
 53%|█████▎    | 5851/11066 [21:26<18:42,  4.65it/s]
                                                    
{'loss': 1.4624, 'learning_rate': 1.4441532622447135e-05, 'epoch': 1.04}
{'loss': 0.6598, 'learning_rate': 1.4438821615759987e-05, 'epoch': 1.04}
{'loss': 0.9028, 'learning_rate': 1.4436110609072837e-05, 'epoch': 1.04}
{'loss': 0.4932, 'learning_rate': 1.4433399602385685e-05, 'epoch': 1.04}
{'loss': 0.4483, 'learning_rate': 1.4430688595698537e-05, 'epoch': 1.04}
{'loss': 0.3577, 'learning_rate': 1.4427977589011387e-05, 'epoch': 1.04}
{'loss': 0.9098, 'learning_rate': 1.4425266582324237e-05, 'epoch': 1.04}
{'loss': 0.6337, 'learning_rate': 1.4422555575637086e-05, 'epoch': 1.04}
{'loss': 1.2091, 'learning_rate': 1.4419844568949938e-05, 'epoch': 1.04}
{'loss': 0.7867, 'learning_rate': 1.4417133562262788e-05, 'epoch': 1.04}
{'loss': 0.9405, 'learning_rate': 1.4414422555575638e-05, 'epoch': 1.04}
{'loss': 0.5504, 'learning_rate': 1.4411711548888486e-05, 'epoch': 1.04}
{'loss': 1.1522, 'learning_rate': 1.4409000542201338e-05, 'epoch': 1.04}
{'loss': 0.7034, 'learning_rate': 1.4406289535514188e-05, 'epoch': 1.04}
{'loss': 1.3517, 'learning_rate': 1.4403578528827038e-05, 'epoch': 1.04}
{'loss': 0.8245, 'learning_rate': 1.4400867522139889e-05, 'epoch': 1.04}
{'loss': 0.9378, 'learning_rate': 1.4398156515452739e-05, 'epoch': 1.04}
{'loss': 0.553, 'learning_rate': 1.4395445508765589e-05, 'epoch': 1.04}
{'loss': 0.3249, 'learning_rate': 1.4392734502078439e-05, 'epoch': 1.04}
{'loss': 0.9385, 'learning_rate': 1.4390023495391289e-05, 'epoch': 1.04}
{'loss': 0.8901, 'learning_rate': 1.438731248870414e-05, 'epoch': 1.04}
{'loss': 0.5505, 'learning_rate': 1.438460148201699e-05, 'epoch': 1.04}
{'loss': 0.5537, 'learning_rate': 1.438189047532984e-05, 'epoch': 1.04}
{'loss': 0.5389, 'learning_rate': 1.437917946864269e-05, 'epoch': 1.04}
{'loss': 1.0437, 'learning_rate': 1.437646846195554e-05, 'epoch': 1.04}
{'loss': 0.7571, 'learning_rate': 1.437375745526839e-05, 'epoch': 1.04}
{'loss': 0.2544, 'learning_rate': 1.4371046448581242e-05, 'epoch': 1.04}
{'loss': 1.3678, 'learning_rate': 1.436833544189409e-05, 'epoch': 1.04}
{'loss': 0.6217, 'learning_rate': 1.436562443520694e-05, 'epoch': 1.04}
{'loss': 0.563, 'learning_rate': 1.436291342851979e-05, 'epoch': 1.04}
{'loss': 0.6501, 'learning_rate': 1.4360202421832642e-05, 'epoch': 1.04}
{'loss': 0.6962, 'learning_rate': 1.435749141514549e-05, 'epoch': 1.04}
{'loss': 0.463, 'learning_rate': 1.435478040845834e-05, 'epoch': 1.04}
{'loss': 0.4408, 'learning_rate': 1.4352069401771191e-05, 'epoch': 1.04}
{'loss': 1.2917, 'learning_rate': 1.4349358395084043e-05, 'epoch': 1.04}
{'loss': 0.6168, 'learning_rate': 1.4346647388396891e-05, 'epoch': 1.04}
{'loss': 0.6093, 'learning_rate': 1.4343936381709741e-05, 'epoch': 1.04}
{'loss': 0.9205, 'learning_rate': 1.4341225375022593e-05, 'epoch': 1.04}
{'loss': 1.1308, 'learning_rate': 1.4338514368335443e-05, 'epoch': 1.04}
{'loss': 0.6457, 'learning_rate': 1.4335803361648292e-05, 'epoch': 1.04}
{'loss': 1.4777, 'learning_rate': 1.4333092354961142e-05, 'epoch': 1.04}
{'loss': 1.0482, 'learning_rate': 1.4330381348273994e-05, 'epoch': 1.04}
{'loss': 0.2784, 'learning_rate': 1.4327670341586844e-05, 'epoch': 1.04}
{'loss': 0.4392, 'learning_rate': 1.4324959334899692e-05, 'epoch': 1.05}
{'loss': 0.7412, 'learning_rate': 1.4322248328212542e-05, 'epoch': 1.05}
{'loss': 1.0361, 'learning_rate': 1.4319537321525394e-05, 'epoch': 1.05}
{'loss': 0.6282, 'learning_rate': 1.4316826314838244e-05, 'epoch': 1.05}
{'loss': 0.6589, 'learning_rate': 1.4314115308151093e-05, 'epoch': 1.05}
{'loss': 0.3509, 'learning_rate': 1.4311404301463945e-05, 'epoch': 1.05}
{'loss': 1.2844, 'learning_rate': 1.4308693294776795e-05, 'epoch': 1.05}
{'loss': 1.0125, 'learning_rate': 1.4305982288089645e-05, 'epoch': 1.05}
{'loss': 0.514, 'learning_rate': 1.4303271281402493e-05, 'epoch': 1.05}
{'loss': 0.3558, 'learning_rate': 1.4300560274715345e-05, 'epoch': 1.05}
{'loss': 0.8019, 'learning_rate': 1.4297849268028195e-05, 'epoch': 1.05}
{'loss': 1.8817, 'learning_rate': 1.4295138261341044e-05, 'epoch': 1.05}
{'loss': 0.81, 'learning_rate': 1.4292427254653896e-05, 'epoch': 1.05}
{'loss': 0.8137, 'learning_rate': 1.4289716247966746e-05, 'epoch': 1.05}
{'loss': 0.5107, 'learning_rate': 1.4287005241279596e-05, 'epoch': 1.05}
{'loss': 0.5051, 'learning_rate': 1.4284294234592444e-05, 'epoch': 1.05}
{'loss': 0.6331, 'learning_rate': 1.4281583227905296e-05, 'epoch': 1.05}
{'loss': 1.6405, 'learning_rate': 1.4278872221218146e-05, 'epoch': 1.05}
{'loss': 1.3661, 'learning_rate': 1.4276161214530996e-05, 'epoch': 1.05}
{'loss': 0.8658, 'learning_rate': 1.4273450207843845e-05, 'epoch': 1.05}
{'loss': 0.5994, 'learning_rate': 1.4270739201156697e-05, 'epoch': 1.05}
{'loss': 0.6257, 'learning_rate': 1.4268028194469547e-05, 'epoch': 1.05}
{'loss': 1.0357, 'learning_rate': 1.4265317187782397e-05, 'epoch': 1.05}
{'loss': 0.4254, 'learning_rate': 1.4262606181095247e-05, 'epoch': 1.05}
{'loss': 1.0541, 'learning_rate': 1.4259895174408097e-05, 'epoch': 1.05}
{'loss': 0.7983, 'learning_rate': 1.4257184167720947e-05, 'epoch': 1.05}
{'loss': 0.6099, 'learning_rate': 1.4254473161033797e-05, 'epoch': 1.05}
{'loss': 0.6707, 'learning_rate': 1.4251762154346648e-05, 'epoch': 1.05}
{'loss': 0.3487, 'learning_rate': 1.4249051147659498e-05, 'epoch': 1.05}
{'loss': 0.4183, 'learning_rate': 1.4246340140972348e-05, 'epoch': 1.05}
{'loss': 0.5595, 'learning_rate': 1.4243629134285198e-05, 'epoch': 1.05}
{'loss': 0.665, 'learning_rate': 1.4240918127598048e-05, 'epoch': 1.05}
{'loss': 0.6353, 'learning_rate': 1.4238207120910898e-05, 'epoch': 1.05}
{'loss': 0.7528, 'learning_rate': 1.4235496114223748e-05, 'epoch': 1.05}
{'loss': 0.7185, 'learning_rate': 1.42327851075366e-05, 'epoch': 1.05}
{'loss': 0.5758, 'learning_rate': 1.4230074100849449e-05, 'epoch': 1.05}
{'loss': 1.0978, 'learning_rate': 1.4227363094162299e-05, 'epoch': 1.05}
{'loss': 0.6903, 'learning_rate': 1.4224652087475149e-05, 'epoch': 1.05}
{'loss': 0.6113, 'learning_rate': 1.4221941080788e-05, 'epoch': 1.05}
{'loss': 0.9427, 'learning_rate': 1.421923007410085e-05, 'epoch': 1.05}
{'loss': 1.1351, 'learning_rate': 1.42165190674137e-05, 'epoch': 1.05}
{'loss': 1.2412, 'learning_rate': 1.421380806072655e-05, 'epoch': 1.05}
{'loss': 1.0727, 'learning_rate': 1.4211097054039401e-05, 'epoch': 1.05}
{'loss': 1.3172, 'learning_rate': 1.420838604735225e-05, 'epoch': 1.05}
{'loss': 1.2707, 'learning_rate': 1.42056750406651e-05, 'epoch': 1.05}
{'loss': 0.6921, 'learning_rate': 1.4202964033977952e-05, 'epoch': 1.05}
{'loss': 0.771, 'learning_rate': 1.4200253027290802e-05, 'epoch': 1.05}
{'loss': 0.777, 'learning_rate': 1.419754202060365e-05, 'epoch': 1.05}
{'loss': 0.8933, 'learning_rate': 1.41948310139165e-05, 'epoch': 1.05}
{'loss': 0.9732, 'learning_rate': 1.4192120007229352e-05, 'epoch': 1.05}
{'loss': 1.4409, 'learning_rate': 1.4189409000542202e-05, 'epoch': 1.05}
{'loss': 0.5356, 'learning_rate': 1.418669799385505e-05, 'epoch': 1.05}
{'loss': 0.7628, 'learning_rate': 1.4183986987167901e-05, 'epoch': 1.05}
{'loss': 0.4097, 'learning_rate': 1.4181275980480753e-05, 'epoch': 1.05}
{'loss': 0.5645, 'learning_rate': 1.4178564973793603e-05, 'epoch': 1.05}
{'loss': 1.6319, 'learning_rate': 1.4175853967106451e-05, 'epoch': 1.05}
{'loss': 0.4153, 'learning_rate': 1.4173142960419303e-05, 'epoch': 1.06}
{'loss': 0.3204, 'learning_rate': 1.4170431953732153e-05, 'epoch': 1.06}
{'loss': 1.0146, 'learning_rate': 1.4167720947045003e-05, 'epoch': 1.06}
{'loss': 0.4845, 'learning_rate': 1.4165009940357852e-05, 'epoch': 1.06}
{'loss': 0.8445, 'learning_rate': 1.4162298933670704e-05, 'epoch': 1.06}
{'loss': 0.9649, 'learning_rate': 1.4159587926983554e-05, 'epoch': 1.06}
{'loss': 0.6378, 'learning_rate': 1.4156876920296404e-05, 'epoch': 1.06}
{'loss': 0.7075, 'learning_rate': 1.4154165913609252e-05, 'epoch': 1.06}
{'loss': 1.0163, 'learning_rate': 1.4151454906922104e-05, 'epoch': 1.06}
{'loss': 0.9241, 'learning_rate': 1.4148743900234954e-05, 'epoch': 1.06}
{'loss': 0.5373, 'learning_rate': 1.4146032893547805e-05, 'epoch': 1.06}
{'loss': 0.3693, 'learning_rate': 1.4143321886860655e-05, 'epoch': 1.06}
{'loss': 0.6257, 'learning_rate': 1.4140610880173505e-05, 'epoch': 1.06}

 53%|█████▎    | 5851/11066 [21:26<18:42,  4.65it/s]
 53%|█████▎    | 5852/11066 [21:26<18:54,  4.60it/s]
                                                    

 53%|█████▎    | 5852/11066 [21:26<18:54,  4.60it/s]
 53%|█████▎    | 5853/11066 [21:26<18:55,  4.59it/s]
                                                    

 53%|█████▎    | 5853/11066 [21:26<18:55,  4.59it/s]
 53%|█████▎    | 5854/11066 [21:27<18:40,  4.65it/s]
                                                    

 53%|█████▎    | 5854/11066 [21:27<18:40,  4.65it/s]
 53%|█████▎    | 5855/11066 [21:27<18:55,  4.59it/s]
                                                    

 53%|█████▎    | 5855/11066 [21:27<18:55,  4.59it/s]
 53%|█████▎    | 5856/11066 [21:27<19:02,  4.56it/s]
                                                    

 53%|█████▎    | 5856/11066 [21:27<19:02,  4.56it/s]
 53%|█████▎    | 5857/11066 [21:27<18:57,  4.58it/s]
                                                    

 53%|█████▎    | 5857/11066 [21:27<18:57,  4.58it/s]
 53%|█████▎    | 5858/11066 [21:27<18:50,  4.61it/s]
                                                    

 53%|█████▎    | 5858/11066 [21:27<18:50,  4.61it/s]
 53%|█████▎    | 5859/11066 [21:28<18:41,  4.64it/s]
                                                    

 53%|█████▎    | 5859/11066 [21:28<18:41,  4.64it/s]
 53%|█████▎    | 5860/11066 [21:28<18:30,  4.69it/s]
                                                    

 53%|█████▎    | 5860/11066 [21:28<18:30,  4.69it/s]
 53%|█████▎    | 5861/11066 [21:28<18:31,  4.68it/s]
                                                    

 53%|█████▎    | 5861/11066 [21:28<18:31,  4.68it/s]
 53%|█████▎    | 5862/11066 [21:28<18:28,  4.69it/s]
                                                    

 53%|█████▎    | 5862/11066 [21:28<18:28,  4.69it/s]
 53%|█████▎    | 5863/11066 [21:29<18:43,  4.63it/s]
                                                    

 53%|█████▎    | 5863/11066 [21:29<18:43,  4.63it/s]
 53%|█████▎    | 5864/11066 [21:29<18:44,  4.63it/s]
                                                    

 53%|█████▎    | 5864/11066 [21:29<18:44,  4.63it/s]
 53%|█████▎    | 5865/11066 [21:29<18:41,  4.64it/s]
                                                    

 53%|█████▎    | 5865/11066 [21:29<18:41,  4.64it/s]
 53%|█████▎    | 5866/11066 [21:29<18:55,  4.58it/s]
                                                    

 53%|█████▎    | 5866/11066 [21:29<18:55,  4.58it/s]
 53%|█████▎    | 5867/11066 [21:29<19:03,  4.55it/s]
                                                    

 53%|█████▎    | 5867/11066 [21:29<19:03,  4.55it/s]
 53%|█████▎    | 5868/11066 [21:30<19:07,  4.53it/s]
                                                    

 53%|█████▎    | 5868/11066 [21:30<19:07,  4.53it/s]
 53%|█████▎    | 5869/11066 [21:30<19:11,  4.51it/s]
                                                    

 53%|█████▎    | 5869/11066 [21:30<19:11,  4.51it/s]
 53%|█████▎    | 5870/11066 [21:30<19:03,  4.55it/s]
                                                    

 53%|█████▎    | 5870/11066 [21:30<19:03,  4.55it/s]
 53%|█████▎    | 5871/11066 [21:30<19:09,  4.52it/s]
                                                    

 53%|█████▎    | 5871/11066 [21:30<19:09,  4.52it/s]
 53%|█████▎    | 5872/11066 [21:31<19:14,  4.50it/s]
                                                    

 53%|█████▎    | 5872/11066 [21:31<19:14,  4.50it/s]
 53%|█████▎    | 5873/11066 [21:31<19:17,  4.49it/s]
                                                    

 53%|█████▎    | 5873/11066 [21:31<19:17,  4.49it/s]
 53%|█████▎    | 5874/11066 [21:31<19:17,  4.49it/s]
                                                    

 53%|█████▎    | 5874/11066 [21:31<19:17,  4.49it/s]
 53%|█████▎    | 5875/11066 [21:31<19:16,  4.49it/s]
                                                    

 53%|█████▎    | 5875/11066 [21:31<19:16,  4.49it/s]
 53%|█████▎    | 5876/11066 [21:31<19:10,  4.51it/s]
                                                    

 53%|█████▎    | 5876/11066 [21:31<19:10,  4.51it/s]
 53%|█████▎    | 5877/11066 [21:32<19:16,  4.49it/s]
                                                    

 53%|█████▎    | 5877/11066 [21:32<19:16,  4.49it/s]
 53%|█████▎    | 5878/11066 [21:32<19:20,  4.47it/s]
                                                    

 53%|█████▎    | 5878/11066 [21:32<19:20,  4.47it/s]
 53%|█████▎    | 5879/11066 [21:32<19:32,  4.42it/s]
                                                    

 53%|█████▎    | 5879/11066 [21:32<19:32,  4.42it/s]
 53%|█████▎    | 5880/11066 [21:32<19:40,  4.39it/s]
                                                    

 53%|█████▎    | 5880/11066 [21:32<19:40,  4.39it/s]
 53%|█████▎    | 5881/11066 [21:33<19:34,  4.41it/s]
                                                    

 53%|█████▎    | 5881/11066 [21:33<19:34,  4.41it/s]
 53%|█████▎    | 5882/11066 [21:33<19:39,  4.39it/s]
                                                    

 53%|█████▎    | 5882/11066 [21:33<19:39,  4.39it/s]
 53%|█████▎    | 5883/11066 [21:33<19:43,  4.38it/s]
                                                    

 53%|█████▎    | 5883/11066 [21:33<19:43,  4.38it/s]
 53%|█████▎    | 5884/11066 [21:33<19:36,  4.40it/s]
                                                    

 53%|█████▎    | 5884/11066 [21:33<19:36,  4.40it/s]
 53%|█████▎    | 5885/11066 [21:33<19:32,  4.42it/s]
                                                    

 53%|█████▎    | 5885/11066 [21:33<19:32,  4.42it/s]
 53%|█████▎    | 5886/11066 [21:34<19:30,  4.43it/s]
                                                    

 53%|█████▎    | 5886/11066 [21:34<19:30,  4.43it/s]
 53%|█████▎    | 5887/11066 [21:34<19:40,  4.39it/s]
                                                    

 53%|█████▎    | 5887/11066 [21:34<19:40,  4.39it/s]
 53%|█████▎    | 5888/11066 [21:34<20:01,  4.31it/s]
                                                    

 53%|█████▎    | 5888/11066 [21:34<20:01,  4.31it/s]
 53%|█████▎    | 5889/11066 [21:34<20:00,  4.31it/s]
                                                    

 53%|█████▎    | 5889/11066 [21:34<20:00,  4.31it/s]
 53%|█████▎    | 5890/11066 [21:35<19:52,  4.34it/s]
                                                    

 53%|█████▎    | 5890/11066 [21:35<19:52,  4.34it/s]
 53%|█████▎    | 5891/11066 [21:35<19:40,  4.39it/s]
                                                    

 53%|█████▎    | 5891/11066 [21:35<19:40,  4.39it/s]
 53%|█████▎    | 5892/11066 [21:35<19:34,  4.41it/s]
                                                    

 53%|█████▎    | 5892/11066 [21:35<19:34,  4.41it/s]
 53%|█████▎    | 5893/11066 [21:35<19:19,  4.46it/s]
                                                    

 53%|█████▎    | 5893/11066 [21:35<19:19,  4.46it/s]
 53%|█████▎    | 5894/11066 [21:36<19:10,  4.49it/s]
                                                    

 53%|█████▎    | 5894/11066 [21:36<19:10,  4.49it/s]
 53%|█████▎    | 5895/11066 [21:36<19:10,  4.49it/s]
                                                    

 53%|█████▎    | 5895/11066 [21:36<19:10,  4.49it/s]
 53%|█████▎    | 5896/11066 [21:36<18:53,  4.56it/s]
                                                    

 53%|█████▎    | 5896/11066 [21:36<18:53,  4.56it/s]
 53%|█████▎    | 5897/11066 [21:36<18:49,  4.58it/s]
                                                    

 53%|█████▎    | 5897/11066 [21:36<18:49,  4.58it/s]
 53%|█████▎    | 5898/11066 [21:36<18:43,  4.60it/s]
                                                    

 53%|█████▎    | 5898/11066 [21:36<18:43,  4.60it/s]
 53%|█████▎    | 5899/11066 [21:37<18:52,  4.56it/s]
                                                    

 53%|█████▎    | 5899/11066 [21:37<18:52,  4.56it/s]
 53%|█████▎    | 5900/11066 [21:37<18:50,  4.57it/s]
                                                    

 53%|█████▎    | 5900/11066 [21:37<18:50,  4.57it/s]
 53%|█████▎    | 5901/11066 [21:37<18:43,  4.60it/s]
                                                    

 53%|█████▎    | 5901/11066 [21:37<18:43,  4.60it/s]
 53%|█████▎    | 5902/11066 [21:37<18:32,  4.64it/s]
                                                    

 53%|█████▎    | 5902/11066 [21:37<18:32,  4.64it/s]
 53%|█████▎    | 5903/11066 [21:37<18:23,  4.68it/s]
                                                    

 53%|█████▎    | 5903/11066 [21:37<18:23,  4.68it/s]
 53%|█████▎    | 5904/11066 [21:38<18:24,  4.67it/s]
                                                    

 53%|█████▎    | 5904/11066 [21:38<18:24,  4.67it/s]
 53%|█████▎    | 5905/11066 [21:38<18:24,  4.67it/s]
                                                    

 53%|█████▎    | 5905/11066 [21:38<18:24,  4.67it/s]
 53%|█████▎    | 5906/11066 [21:38<18:36,  4.62it/s]
                                                    

 53%|█████▎    | 5906/11066 [21:38<18:36,  4.62it/s]
 53%|█████▎    | 5907/11066 [21:38<18:37,  4.62it/s]
                                                    

 53%|█████▎    | 5907/11066 [21:38<18:37,  4.62it/s]
 53%|█████▎    | 5908/11066 [21:39<18:46,  4.58it/s]
                                                    

 53%|█████▎    | 5908/11066 [21:39<18:46,  4.58it/s]
 53%|█████▎    | 5909/11066 [21:39<18:54,  4.54it/s]
                                                    

 53%|█████▎    | 5909/11066 [21:39<18:54,  4.54it/s]
 53%|█████▎    | 5910/11066 [21:39<18:49,  4.56it/s]
                                                    

 53%|█████▎    | 5910/11066 [21:39<18:49,  4.56it/s]
 53%|█████▎    | 5911/11066 [21:39<18:41,  4.60it/s]
                                                    

 53%|█████▎    | 5911/11066 [21:39<18:41,  4.60it/s]
 53%|█████▎    | 5912/11066 [21:39<18:42,  4.59it/s]
                                                    

 53%|█████▎    | 5912/11066 [21:39<18:42,  4.59it/s]
 53%|█████▎    | 5913/11066 [21:40<18:32,  4.63it/s]
                                                    

 53%|█████▎    | 5913/11066 [21:40<18:32,  4.63it/s]
 53%|█████▎    | 5914/11066 [21:40<18:36,  4.61it/s]
                                                    

 53%|█████▎    | 5914/11066 [21:40<18:36,  4.61it/s]
 53%|█████▎    | 5915/11066 [21:40<18:37,  4.61it/s]
                                                    

 53%|█████▎    | 5915/11066 [21:40<18:37,  4.61it/s]
 53%|█████▎    | 5916/11066 [21:40<18:31,  4.63it/s]
                                                    

 53%|█████▎    | 5916/11066 [21:40<18:31,  4.63it/s]
 53%|█████▎    | 5917/11066 [21:40<18:34,  4.62it/s]
                                                    

 53%|█████▎    | 5917/11066 [21:40<18:34,  4.62it/s]
 53%|█████▎    | 5918/11066 [21:41<18:45,  4.57it/s]
                                                    

 53%|█████▎    | 5918/11066 [21:41<18:45,  4.57it/s]
 53%|█████▎    | 5919/11066 [21:41<18:42,  4.59it/s]
                                                    

 53%|█████▎    | 5919/11066 [21:41<18:42,  4.59it/s]
 53%|█████▎    | 5920/11066 [21:41<19:10,  4.47it/s]
                                                    

 53%|█████▎    | 5920/11066 [21:41<19:10,  4.47it/s]
 54%|█████▎    | 5921/11066 [21:41<19:09,  4.47it/s]
                                                    

 54%|█████▎    | 5921/11066 [21:41<19:09,  4.47it/s]
 54%|█████▎    | 5922/11066 [21:42<19:18,  4.44it/s]
                                                    

 54%|█████▎    | 5922/11066 [21:42<19:18,  4.44it/s]
 54%|█████▎    | 5923/11066 [21:42<19:30,  4.39it/s]
                                                    

 54%|█████▎    | 5923/11066 [21:42<19:30,  4.39it/s]
 54%|█████▎    | 5924/11066 [21:42<19:26,  4.41it/s]
                                                    

 54%|█████▎    | 5924/11066 [21:42<19:26,  4.41it/s]
 54%|█████▎    | 5925/11066 [21:42<19:27,  4.41it/s]
                                                    

 54%|█████▎    | 5925/11066 [21:42<19:27,  4.41it/s]
 54%|█████▎    | 5926/11066 [21:43<19:26,  4.41it/s]
                                                    

 54%|█████▎    | 5926/11066 [21:43<19:26,  4.41it/s]
 54%|█████▎    | 5927/11066 [21:43<19:22,  4.42it/s]
                                                    

 54%|█████▎    | 5927/11066 [21:43<19:22,  4.42it/s]
 54%|█████▎    | 5928/11066 [21:43<19:31,  4.38it/s]
                                                    

 54%|█████▎    | 5928/11066 [21:43<19:31,  4.38it/s]
 54%|█████▎    | 5929/11066 [21:43<19:15,  4.45it/s]
                                                    

 54%|█████▎    | 5929/11066 [21:43<19:15,  4.45it/s]
 54%|█████▎    | 5930/11066 [21:43<19:01,  4.50it/s]
                                                    

 54%|█████▎    | 5930/11066 [21:43<19:01,  4.50it/s]
 54%|█████▎    | 5931/11066 [21:44<18:48,  4.55it/s]
                                                    

 54%|█████▎    | 5931/11066 [21:44<18:48,  4.55it/s]
 54%|█████▎    | 5932/11066 [21:44<18:37,  4.59it/s]
                                                    

 54%|█████▎    | 5932/11066 [21:44<18:37,  4.59it/s]
 54%|█████▎    | 5933/11066 [21:44<18:36,  4.60it/s]
                                                    

 54%|█████▎    | 5933/11066 [21:44<18:36,  4.60it/s]
 54%|█████▎    | 5934/11066 [21:44<18:30,  4.62it/s]
                                                    

 54%|█████▎    | 5934/11066 [21:44<18:30,  4.62it/s]
 54%|█████▎    | 5935/11066 [21:45<18:40,  4.58it/s]
                                                    

 54%|█████▎    | 5935/11066 [21:45<18:40,  4.58it/s]
 54%|█████▎    | 5936/11066 [21:45<18:49,  4.54it/s]
                                                    

 54%|█████▎    | 5936/11066 [21:45<18:49,  4.54it/s]
 54%|█████▎    | 5937/11066 [21:45<18:52,  4.53it/s]
                                                    

 54%|█████▎    | 5937/11066 [21:45<18:52,  4.53it/s]
 54%|█████▎    | 5938/11066 [21:45<18:56,  4.51it/s]
                                                    

 54%|█████▎    | 5938/11066 [21:45<18:56,  4.51it/s]
 54%|█████▎    | 5939/11066 [21:45<18:50,  4.54it/s]
                                                    

 54%|█████▎    | 5939/11066 [21:45<18:50,  4.54it/s]
 54%|█████▎    | 5940/11066 [21:46<18:47,  4.55it/s]
                                                    

 54%|█████▎    | 5940/11066 [21:46<18:47,  4.55it/s]
 54%|█████▎    | 5941/11066 [21:46<18:41,  4.57it/s]
                                                    

 54%|█████▎    | 5941/11066 [21:46<18:41,  4.57it/s]
 54%|█████▎    | 5942/11066 [21:46<18:34,  4.60it/s]
                                                    

 54%|█████▎    | 5942/11066 [21:46<18:34,  4.60it/s]
 54%|█████▎    | 5943/11066 [21:46<18:34,  4.60it/s]
                                                    

 54%|█████▎    | 5943/11066 [21:46<18:34,  4.60it/s]
 54%|█████▎    | 5944/11066 [21:46<18:41,  4.57it/s]
                                                    

 54%|█████▎    | 5944/11066 [21:46<18:41,  4.57it/s]
 54%|█████▎    | 5945/11066 [21:47<18:38,  4.58it/s]
                                                    

 54%|█████▎    | 5945/11066 [21:47<18:38,  4.58it/s]
 54%|█████▎    | 5946/11066 [21:47<18:37,  4.58it/s]
                                                    

 54%|█████▎    | 5946/11066 [21:47<18:37,  4.58it/s]
 54%|█████▎    | 5947/11066 [21:47<18:45,  4.55it/s]
                                                    

 54%|█████▎    | 5947/11066 [21:47<18:45,  4.55it/s]
 54%|█████▍    | 5948/11066 [21:47<18:48,  4.53it/s]
                                                    

 54%|█████▍    | 5948/11066 [21:47<18:48,  4.53it/s]
 54%|█████▍    | 5949/11066 [21:48<18:44,  4.55it/s]
                                                    

 54%|█████▍    | 5949/11066 [21:48<18:44,  4.55it/s]
 54%|█████▍    | 5950/11066 [21:48<18:43,  4.56it/s]
                                                    

 54%|█████▍    | 5950/11066 [21:48<18:43,  4.56it/s]
 54%|█████▍    | 5951/11066 [21:48<18:37,  4.58it/s]
                                                    

 54%|█████▍    | 5951/11066 [21:48<18:37,  4.58it/s]
 54%|█████▍    | 5952/11066 [21:48<18:32,  4.60it/s]
                                                    

 54%|█████▍    | 5952/11066 [21:48<18:32,  4.60it/s]
 54%|█████▍    | 5953/11066 [21:48<18:41,  4.56it/s]
                                                    

 54%|█████▍    | 5953/11066 [21:48<18:41,  4.56it/s]
 54%|█████▍    | 5954/11066 [21:49<18:37,  4.57it/s]
                                                    

 54%|█████▍    | 5954/11066 [21:49<18:37,  4.57it/s]
 54%|█████▍    | 5955/11066 [21:49<18:39,  4.57it/s]
                                                    

 54%|█████▍    | 5955/11066 [21:49<18:39,  4.57it/s]
 54%|█████▍    | 5956/11066 [21:49<18:45,  4.54it/s]
                                                    

 54%|█████▍    | 5956/11066 [21:49<18:45,  4.54it/s]
 54%|█████▍    | 5957/11066 [21:49<18:51,  4.52it/s]
                                                    

 54%|█████▍    | 5957/11066 [21:49<18:51,  4.52it/s]
 54%|█████▍    | 5958/11066 [21:50<18:42,  4.55it/s]
                                                    

 54%|█████▍    | 5958/11066 [21:50<18:42,  4.55it/s]
 54%|█████▍    | 5959/11066 [21:50<18:50,  4.52it/s]
                                                    

 54%|█████▍    | 5959/11066 [21:50<18:50,  4.52it/s]
 54%|█████▍    | 5960/11066 [21:50<19:01,  4.47it/s]
                                                    

 54%|█████▍    | 5960/11066 [21:50<19:01,  4.47it/s]
 54%|█████▍    | 5961/11066 [21:50<19:03,  4.46it/s]
                                                    

 54%|█████▍    | 5961/11066 [21:50<19:03,  4.46it/s]
 54%|█████▍    | 5962/11066 [21:50<19:02,  4.47it/s]
                                                    

 54%|█████▍    | 5962/11066 [21:50<19:02,  4.47it/s]
 54%|█████▍    | 5963/11066 [21:51<19:00,  4.47it/s]
                                                    
{'loss': 1.7402, 'learning_rate': 1.4137899873486355e-05, 'epoch': 1.06}
{'loss': 0.6471, 'learning_rate': 1.4135188866799205e-05, 'epoch': 1.06}
{'loss': 0.6731, 'learning_rate': 1.4132477860112055e-05, 'epoch': 1.06}
{'loss': 0.2536, 'learning_rate': 1.4129766853424905e-05, 'epoch': 1.06}
{'loss': 0.5165, 'learning_rate': 1.4127055846737755e-05, 'epoch': 1.06}
{'loss': 0.944, 'learning_rate': 1.4124344840050606e-05, 'epoch': 1.06}
{'loss': 0.6208, 'learning_rate': 1.4121633833363456e-05, 'epoch': 1.06}
{'loss': 0.9141, 'learning_rate': 1.4118922826676306e-05, 'epoch': 1.06}
{'loss': 0.5705, 'learning_rate': 1.4116211819989156e-05, 'epoch': 1.06}
{'loss': 0.769, 'learning_rate': 1.4113500813302008e-05, 'epoch': 1.06}
{'loss': 0.9631, 'learning_rate': 1.4110789806614856e-05, 'epoch': 1.06}
{'loss': 0.8447, 'learning_rate': 1.4108078799927706e-05, 'epoch': 1.06}
{'loss': 0.7453, 'learning_rate': 1.4105367793240557e-05, 'epoch': 1.06}
{'loss': 0.8252, 'learning_rate': 1.4102656786553408e-05, 'epoch': 1.06}
{'loss': 0.5605, 'learning_rate': 1.4099945779866257e-05, 'epoch': 1.06}
{'loss': 1.1823, 'learning_rate': 1.4097234773179107e-05, 'epoch': 1.06}
{'loss': 0.9855, 'learning_rate': 1.4094523766491959e-05, 'epoch': 1.06}
{'loss': 0.7961, 'learning_rate': 1.4091812759804809e-05, 'epoch': 1.06}
{'loss': 1.0346, 'learning_rate': 1.4089101753117657e-05, 'epoch': 1.06}
{'loss': 0.3844, 'learning_rate': 1.4086390746430507e-05, 'epoch': 1.06}
{'loss': 0.7874, 'learning_rate': 1.408367973974336e-05, 'epoch': 1.06}
{'loss': 0.6795, 'learning_rate': 1.408096873305621e-05, 'epoch': 1.06}
{'loss': 1.0123, 'learning_rate': 1.4078257726369058e-05, 'epoch': 1.06}
{'loss': 0.8188, 'learning_rate': 1.4075546719681908e-05, 'epoch': 1.06}
{'loss': 1.1488, 'learning_rate': 1.407283571299476e-05, 'epoch': 1.06}
{'loss': 0.8594, 'learning_rate': 1.407012470630761e-05, 'epoch': 1.06}
{'loss': 1.2148, 'learning_rate': 1.4067413699620458e-05, 'epoch': 1.06}
{'loss': 1.2651, 'learning_rate': 1.406470269293331e-05, 'epoch': 1.06}
{'loss': 0.3839, 'learning_rate': 1.406199168624616e-05, 'epoch': 1.06}
{'loss': 0.9483, 'learning_rate': 1.405928067955901e-05, 'epoch': 1.06}
{'loss': 0.873, 'learning_rate': 1.4056569672871859e-05, 'epoch': 1.06}
{'loss': 1.1389, 'learning_rate': 1.405385866618471e-05, 'epoch': 1.06}
{'loss': 0.9083, 'learning_rate': 1.4051147659497561e-05, 'epoch': 1.06}
{'loss': 0.6906, 'learning_rate': 1.4048436652810411e-05, 'epoch': 1.06}
{'loss': 0.47, 'learning_rate': 1.404572564612326e-05, 'epoch': 1.06}
{'loss': 1.4145, 'learning_rate': 1.4043014639436111e-05, 'epoch': 1.06}
{'loss': 0.4298, 'learning_rate': 1.4040303632748961e-05, 'epoch': 1.06}
{'loss': 0.4465, 'learning_rate': 1.4037592626061812e-05, 'epoch': 1.06}
{'loss': 0.7088, 'learning_rate': 1.4034881619374662e-05, 'epoch': 1.06}
{'loss': 0.7924, 'learning_rate': 1.4032170612687512e-05, 'epoch': 1.06}
{'loss': 0.9601, 'learning_rate': 1.4029459606000362e-05, 'epoch': 1.06}
{'loss': 0.4331, 'learning_rate': 1.4026748599313212e-05, 'epoch': 1.06}
{'loss': 1.0758, 'learning_rate': 1.4024037592626062e-05, 'epoch': 1.07}
{'loss': 0.8251, 'learning_rate': 1.4021326585938912e-05, 'epoch': 1.07}
{'loss': 0.4596, 'learning_rate': 1.4018615579251763e-05, 'epoch': 1.07}
{'loss': 0.9647, 'learning_rate': 1.4015904572564613e-05, 'epoch': 1.07}
{'loss': 0.7133, 'learning_rate': 1.4013193565877463e-05, 'epoch': 1.07}
{'loss': 0.5316, 'learning_rate': 1.4010482559190313e-05, 'epoch': 1.07}
{'loss': 0.2294, 'learning_rate': 1.4007771552503163e-05, 'epoch': 1.07}
{'loss': 0.3849, 'learning_rate': 1.4005060545816015e-05, 'epoch': 1.07}
{'loss': 0.6596, 'learning_rate': 1.4002349539128863e-05, 'epoch': 1.07}
{'loss': 1.3988, 'learning_rate': 1.3999638532441713e-05, 'epoch': 1.07}
{'loss': 1.125, 'learning_rate': 1.3996927525754564e-05, 'epoch': 1.07}
{'loss': 0.6586, 'learning_rate': 1.3994216519067415e-05, 'epoch': 1.07}
{'loss': 0.8022, 'learning_rate': 1.3991505512380264e-05, 'epoch': 1.07}
{'loss': 0.7646, 'learning_rate': 1.3988794505693114e-05, 'epoch': 1.07}
{'loss': 1.4023, 'learning_rate': 1.3986083499005964e-05, 'epoch': 1.07}
{'loss': 0.7168, 'learning_rate': 1.3983372492318816e-05, 'epoch': 1.07}
{'loss': 1.1186, 'learning_rate': 1.3980661485631664e-05, 'epoch': 1.07}
{'loss': 0.976, 'learning_rate': 1.3977950478944515e-05, 'epoch': 1.07}
{'loss': 0.5543, 'learning_rate': 1.3975239472257366e-05, 'epoch': 1.07}
{'loss': 0.8459, 'learning_rate': 1.3972528465570217e-05, 'epoch': 1.07}
{'loss': 0.9324, 'learning_rate': 1.3969817458883065e-05, 'epoch': 1.07}
{'loss': 0.7864, 'learning_rate': 1.3967106452195915e-05, 'epoch': 1.07}
{'loss': 0.8522, 'learning_rate': 1.3964395445508767e-05, 'epoch': 1.07}
{'loss': 0.3541, 'learning_rate': 1.3961684438821617e-05, 'epoch': 1.07}
{'loss': 0.5696, 'learning_rate': 1.3958973432134465e-05, 'epoch': 1.07}
{'loss': 0.7721, 'learning_rate': 1.3956262425447316e-05, 'epoch': 1.07}
{'loss': 0.566, 'learning_rate': 1.3953551418760167e-05, 'epoch': 1.07}
{'loss': 0.4833, 'learning_rate': 1.3950840412073016e-05, 'epoch': 1.07}
{'loss': 1.631, 'learning_rate': 1.3948129405385866e-05, 'epoch': 1.07}
{'loss': 0.9078, 'learning_rate': 1.3945418398698718e-05, 'epoch': 1.07}
{'loss': 0.8633, 'learning_rate': 1.3942707392011568e-05, 'epoch': 1.07}
{'loss': 0.8362, 'learning_rate': 1.3939996385324416e-05, 'epoch': 1.07}
{'loss': 0.4952, 'learning_rate': 1.3937285378637267e-05, 'epoch': 1.07}
{'loss': 1.0697, 'learning_rate': 1.3934574371950118e-05, 'epoch': 1.07}
{'loss': 0.4137, 'learning_rate': 1.3931863365262969e-05, 'epoch': 1.07}
{'loss': 0.9626, 'learning_rate': 1.3929152358575817e-05, 'epoch': 1.07}
{'loss': 1.3431, 'learning_rate': 1.3926441351888669e-05, 'epoch': 1.07}
{'loss': 0.7368, 'learning_rate': 1.3923730345201519e-05, 'epoch': 1.07}
{'loss': 0.7624, 'learning_rate': 1.3921019338514369e-05, 'epoch': 1.07}
{'loss': 0.9743, 'learning_rate': 1.3918308331827218e-05, 'epoch': 1.07}
{'loss': 0.5314, 'learning_rate': 1.391559732514007e-05, 'epoch': 1.07}
{'loss': 0.6364, 'learning_rate': 1.391288631845292e-05, 'epoch': 1.07}
{'loss': 2.0612, 'learning_rate': 1.391017531176577e-05, 'epoch': 1.07}
{'loss': 0.4816, 'learning_rate': 1.3907464305078618e-05, 'epoch': 1.07}
{'loss': 0.5359, 'learning_rate': 1.390475329839147e-05, 'epoch': 1.07}
{'loss': 0.3881, 'learning_rate': 1.390204229170432e-05, 'epoch': 1.07}
{'loss': 0.6049, 'learning_rate': 1.389933128501717e-05, 'epoch': 1.07}
{'loss': 0.5488, 'learning_rate': 1.389662027833002e-05, 'epoch': 1.07}
{'loss': 0.6886, 'learning_rate': 1.389390927164287e-05, 'epoch': 1.07}
{'loss': 1.0777, 'learning_rate': 1.389119826495572e-05, 'epoch': 1.07}
{'loss': 1.042, 'learning_rate': 1.388848725826857e-05, 'epoch': 1.07}
{'loss': 0.635, 'learning_rate': 1.388577625158142e-05, 'epoch': 1.07}
{'loss': 0.5828, 'learning_rate': 1.3883065244894271e-05, 'epoch': 1.07}
{'loss': 0.6372, 'learning_rate': 1.3880354238207121e-05, 'epoch': 1.07}
{'loss': 0.8708, 'learning_rate': 1.3877643231519971e-05, 'epoch': 1.07}
{'loss': 0.7267, 'learning_rate': 1.3874932224832821e-05, 'epoch': 1.08}
{'loss': 0.961, 'learning_rate': 1.3872221218145671e-05, 'epoch': 1.08}
{'loss': 0.5725, 'learning_rate': 1.3869510211458522e-05, 'epoch': 1.08}
{'loss': 0.8499, 'learning_rate': 1.3866799204771373e-05, 'epoch': 1.08}
{'loss': 0.7066, 'learning_rate': 1.3864088198084222e-05, 'epoch': 1.08}
{'loss': 0.5437, 'learning_rate': 1.3861377191397072e-05, 'epoch': 1.08}
{'loss': 0.5363, 'learning_rate': 1.3858666184709922e-05, 'epoch': 1.08}
{'loss': 1.2216, 'learning_rate': 1.3855955178022774e-05, 'epoch': 1.08}
{'loss': 1.1036, 'learning_rate': 1.3853244171335622e-05, 'epoch': 1.08}
{'loss': 0.5927, 'learning_rate': 1.3850533164648473e-05, 'epoch': 1.08}
{'loss': 1.3341, 'learning_rate': 1.3847822157961323e-05, 'epoch': 1.08}
{'loss': 0.36, 'learning_rate': 1.3845111151274175e-05, 'epoch': 1.08}
{'loss': 0.4835, 'learning_rate': 1.3842400144587023e-05, 'epoch': 1.08}
{'loss': 0.299, 'learning_rate': 1.3839689137899873e-05, 'epoch': 1.08}
{'loss': 0.7922, 'learning_rate': 1.3836978131212725e-05, 'epoch': 1.08}

 54%|█████▍    | 5963/11066 [21:51<19:00,  4.47it/s]
 54%|█████▍    | 5964/11066 [21:51<18:58,  4.48it/s]
                                                    

 54%|█████▍    | 5964/11066 [21:51<18:58,  4.48it/s]
 54%|█████▍    | 5965/11066 [21:51<18:58,  4.48it/s]
                                                    

 54%|█████▍    | 5965/11066 [21:51<18:58,  4.48it/s]
 54%|█████▍    | 5966/11066 [21:51<18:57,  4.48it/s]
                                                    

 54%|█████▍    | 5966/11066 [21:51<18:57,  4.48it/s]
 54%|█████▍    | 5967/11066 [21:52<18:55,  4.49it/s]
                                                    

 54%|█████▍    | 5967/11066 [21:52<18:55,  4.49it/s]
 54%|█████▍    | 5968/11066 [21:52<18:46,  4.53it/s]
                                                    

 54%|█████▍    | 5968/11066 [21:52<18:46,  4.53it/s]
 54%|█████▍    | 5969/11066 [21:52<18:43,  4.54it/s]
                                                    

 54%|█████▍    | 5969/11066 [21:52<18:43,  4.54it/s]
 54%|█████▍    | 5970/11066 [21:52<18:35,  4.57it/s]
                                                    

 54%|█████▍    | 5970/11066 [21:52<18:35,  4.57it/s]
 54%|█████▍    | 5971/11066 [21:52<18:36,  4.56it/s]
                                                    

 54%|█████▍    | 5971/11066 [21:52<18:36,  4.56it/s]
 54%|█████▍    | 5972/11066 [21:53<18:47,  4.52it/s]
                                                    

 54%|█████▍    | 5972/11066 [21:53<18:47,  4.52it/s]
 54%|█████▍    | 5973/11066 [21:53<19:10,  4.43it/s]
                                                    

 54%|█████▍    | 5973/11066 [21:53<19:10,  4.43it/s]
 54%|█████▍    | 5974/11066 [21:53<19:13,  4.42it/s]
                                                    

 54%|█████▍    | 5974/11066 [21:53<19:13,  4.42it/s]
 54%|█████▍    | 5975/11066 [21:53<19:21,  4.38it/s]
                                                    

 54%|█████▍    | 5975/11066 [21:53<19:21,  4.38it/s]
 54%|█████▍    | 5976/11066 [21:54<19:19,  4.39it/s]
                                                    

 54%|█████▍    | 5976/11066 [21:54<19:19,  4.39it/s]
 54%|█████▍    | 5977/11066 [21:54<19:03,  4.45it/s]
                                                    

 54%|█████▍    | 5977/11066 [21:54<19:03,  4.45it/s]
 54%|█████▍    | 5978/11066 [21:54<19:03,  4.45it/s]
                                                    

 54%|█████▍    | 5978/11066 [21:54<19:03,  4.45it/s]
 54%|█████▍    | 5979/11066 [21:54<19:18,  4.39it/s]
                                                    

 54%|█████▍    | 5979/11066 [21:54<19:18,  4.39it/s]
 54%|█████▍    | 5980/11066 [21:54<19:15,  4.40it/s]
                                                    

 54%|█████▍    | 5980/11066 [21:54<19:15,  4.40it/s]
 54%|█████▍    | 5981/11066 [21:55<19:10,  4.42it/s]
                                                    

 54%|█████▍    | 5981/11066 [21:55<19:10,  4.42it/s]
 54%|█████▍    | 5982/11066 [21:55<19:14,  4.41it/s]
                                                    

 54%|█████▍    | 5982/11066 [21:55<19:14,  4.41it/s]
 54%|█████▍    | 5983/11066 [21:55<19:18,  4.39it/s]
                                                    

 54%|█████▍    | 5983/11066 [21:55<19:18,  4.39it/s]
 54%|█████▍    | 5984/11066 [21:55<19:12,  4.41it/s]
                                                    

 54%|█████▍    | 5984/11066 [21:55<19:12,  4.41it/s]
 54%|█████▍    | 5985/11066 [21:56<19:06,  4.43it/s]
                                                    

 54%|█████▍    | 5985/11066 [21:56<19:06,  4.43it/s]
 54%|█████▍    | 5986/11066 [21:56<19:02,  4.45it/s]
                                                    

 54%|█████▍    | 5986/11066 [21:56<19:02,  4.45it/s]
 54%|█████▍    | 5987/11066 [21:56<18:57,  4.46it/s]
                                                    

 54%|█████▍    | 5987/11066 [21:56<18:57,  4.46it/s]
 54%|█████▍    | 5988/11066 [21:56<18:55,  4.47it/s]
                                                    

 54%|█████▍    | 5988/11066 [21:56<18:55,  4.47it/s]
 54%|█████▍    | 5989/11066 [21:57<19:11,  4.41it/s]
                                                    

 54%|█████▍    | 5989/11066 [21:57<19:11,  4.41it/s]
 54%|█████▍    | 5990/11066 [21:57<19:22,  4.37it/s]
                                                    

 54%|█████▍    | 5990/11066 [21:57<19:22,  4.37it/s]
 54%|█████▍    | 5991/11066 [21:57<19:17,  4.38it/s]
                                                    

 54%|█████▍    | 5991/11066 [21:57<19:17,  4.38it/s]
 54%|█████▍    | 5992/11066 [21:57<19:11,  4.41it/s]
                                                    

 54%|█████▍    | 5992/11066 [21:57<19:11,  4.41it/s]
 54%|█████▍    | 5993/11066 [21:57<19:04,  4.43it/s]
                                                    

 54%|█████▍    | 5993/11066 [21:57<19:04,  4.43it/s]
 54%|█████▍    | 5994/11066 [21:58<18:59,  4.45it/s]
                                                    

 54%|█████▍    | 5994/11066 [21:58<18:59,  4.45it/s]
 54%|█████▍    | 5995/11066 [21:58<18:57,  4.46it/s]
                                                    

 54%|█████▍    | 5995/11066 [21:58<18:57,  4.46it/s]
 54%|█████▍    | 5996/11066 [21:58<18:54,  4.47it/s]
                                                    

 54%|█████▍    | 5996/11066 [21:58<18:54,  4.47it/s]
 54%|█████▍    | 5997/11066 [21:58<18:52,  4.48it/s]
                                                    

 54%|█████▍    | 5997/11066 [21:58<18:52,  4.48it/s]
 54%|█████▍    | 5998/11066 [21:59<18:50,  4.48it/s]
                                                    

 54%|█████▍    | 5998/11066 [21:59<18:50,  4.48it/s]
 54%|█████▍    | 5999/11066 [21:59<18:50,  4.48it/s]
                                                    

 54%|█████▍    | 5999/11066 [21:59<18:50,  4.48it/s]
 54%|█████▍    | 6000/11066 [21:59<18:50,  4.48it/s]
                                                    

 54%|█████▍    | 6000/11066 [21:59<18:50,  4.48it/s]
 54%|█████▍    | 6001/11066 [21:59<18:48,  4.49it/s]
                                                    

 54%|█████▍    | 6001/11066 [21:59<18:48,  4.49it/s]
 54%|█████▍    | 6002/11066 [21:59<18:46,  4.49it/s]
                                                    

 54%|█████▍    | 6002/11066 [21:59<18:46,  4.49it/s]
 54%|█████▍    | 6003/11066 [22:00<18:46,  4.49it/s]
                                                    

 54%|█████▍    | 6003/11066 [22:00<18:46,  4.49it/s]
 54%|█████▍    | 6004/11066 [22:00<18:46,  4.49it/s]
                                                    

 54%|█████▍    | 6004/11066 [22:00<18:46,  4.49it/s]
 54%|█████▍    | 6005/11066 [22:00<18:47,  4.49it/s]
                                                    

 54%|█████▍    | 6005/11066 [22:00<18:47,  4.49it/s]
 54%|█████▍    | 6006/11066 [22:00<18:55,  4.46it/s]
                                                    

 54%|█████▍    | 6006/11066 [22:00<18:55,  4.46it/s]
 54%|█████▍    | 6007/11066 [22:01<18:55,  4.45it/s]
                                                    

 54%|█████▍    | 6007/11066 [22:01<18:55,  4.45it/s]
 54%|█████▍    | 6008/11066 [22:01<18:44,  4.50it/s]
                                                    

 54%|█████▍    | 6008/11066 [22:01<18:44,  4.50it/s]
 54%|█████▍    | 6009/11066 [22:01<18:39,  4.52it/s]
                                                    

 54%|█████▍    | 6009/11066 [22:01<18:39,  4.52it/s]
 54%|█████▍    | 6010/11066 [22:01<18:40,  4.51it/s]
                                                    

 54%|█████▍    | 6010/11066 [22:01<18:40,  4.51it/s]
 54%|█████▍    | 6011/11066 [22:01<18:31,  4.55it/s]
                                                    

 54%|█████▍    | 6011/11066 [22:01<18:31,  4.55it/s]
 54%|█████▍    | 6012/11066 [22:02<18:21,  4.59it/s]
                                                    

 54%|█████▍    | 6012/11066 [22:02<18:21,  4.59it/s]
 54%|█████▍    | 6013/11066 [22:02<18:14,  4.62it/s]
                                                    

 54%|█████▍    | 6013/11066 [22:02<18:14,  4.62it/s]
 54%|█████▍    | 6014/11066 [22:02<18:14,  4.61it/s]
                                                    

 54%|█████▍    | 6014/11066 [22:02<18:14,  4.61it/s]
 54%|█████▍    | 6015/11066 [22:02<18:23,  4.58it/s]
                                                    

 54%|█████▍    | 6015/11066 [22:02<18:23,  4.58it/s]
 54%|█████▍    | 6016/11066 [22:03<18:27,  4.56it/s]
                                                    

 54%|█████▍    | 6016/11066 [22:03<18:27,  4.56it/s]
 54%|█████▍    | 6017/11066 [22:03<18:32,  4.54it/s]
                                                    

 54%|█████▍    | 6017/11066 [22:03<18:32,  4.54it/s]
 54%|█████▍    | 6018/11066 [22:03<18:20,  4.59it/s]
                                                    

 54%|█████▍    | 6018/11066 [22:03<18:20,  4.59it/s]
 54%|█████▍    | 6019/11066 [22:03<18:26,  4.56it/s]
                                                    

 54%|█████▍    | 6019/11066 [22:03<18:26,  4.56it/s]
 54%|█████▍    | 6020/11066 [22:03<18:22,  4.58it/s]
                                                    

 54%|█████▍    | 6020/11066 [22:03<18:22,  4.58it/s]
 54%|█████▍    | 6021/11066 [22:04<18:10,  4.63it/s]
                                                    

 54%|█████▍    | 6021/11066 [22:04<18:10,  4.63it/s]
 54%|█████▍    | 6022/11066 [22:04<17:58,  4.68it/s]
                                                    

 54%|█████▍    | 6022/11066 [22:04<17:58,  4.68it/s]
 54%|█████▍    | 6023/11066 [22:04<18:03,  4.65it/s]
                                                    

 54%|█████▍    | 6023/11066 [22:04<18:03,  4.65it/s]
 54%|█████▍    | 6024/11066 [22:04<18:00,  4.67it/s]
                                                    

 54%|█████▍    | 6024/11066 [22:04<18:00,  4.67it/s]
 54%|█████▍    | 6025/11066 [22:04<17:58,  4.67it/s]
                                                    

 54%|█████▍    | 6025/11066 [22:04<17:58,  4.67it/s]
 54%|█████▍    | 6026/11066 [22:05<17:56,  4.68it/s]
                                                    

 54%|█████▍    | 6026/11066 [22:05<17:56,  4.68it/s]
 54%|█████▍    | 6027/11066 [22:05<17:47,  4.72it/s]
                                                    

 54%|█████▍    | 6027/11066 [22:05<17:47,  4.72it/s]
 54%|█████▍    | 6028/11066 [22:05<18:07,  4.63it/s]
                                                    

 54%|█████▍    | 6028/11066 [22:05<18:07,  4.63it/s]
 54%|█████▍    | 6029/11066 [22:05<18:20,  4.58it/s]
                                                    

 54%|█████▍    | 6029/11066 [22:05<18:20,  4.58it/s]
 54%|█████▍    | 6030/11066 [22:06<18:33,  4.52it/s]
                                                    

 54%|█████▍    | 6030/11066 [22:06<18:33,  4.52it/s]
 55%|█████▍    | 6031/11066 [22:06<18:39,  4.50it/s]
                                                    

 55%|█████▍    | 6031/11066 [22:06<18:39,  4.50it/s]
 55%|█████▍    | 6032/11066 [22:06<18:42,  4.48it/s]
                                                    

 55%|█████▍    | 6032/11066 [22:06<18:42,  4.48it/s]
 55%|█████▍    | 6033/11066 [22:06<19:01,  4.41it/s]
                                                    

 55%|█████▍    | 6033/11066 [22:06<19:01,  4.41it/s]
 55%|█████▍    | 6034/11066 [22:06<19:03,  4.40it/s]
                                                    

 55%|█████▍    | 6034/11066 [22:06<19:03,  4.40it/s]
 55%|█████▍    | 6035/11066 [22:07<18:44,  4.47it/s]
                                                    

 55%|█████▍    | 6035/11066 [22:07<18:44,  4.47it/s]
 55%|█████▍    | 6036/11066 [22:07<18:28,  4.54it/s]
                                                    

 55%|█████▍    | 6036/11066 [22:07<18:28,  4.54it/s]
 55%|█████▍    | 6037/11066 [22:07<18:24,  4.55it/s]
                                                    

 55%|█████▍    | 6037/11066 [22:07<18:24,  4.55it/s]
 55%|█████▍    | 6038/11066 [22:07<18:07,  4.62it/s]
                                                    

 55%|█████▍    | 6038/11066 [22:07<18:07,  4.62it/s]
 55%|█████▍    | 6039/11066 [22:08<18:11,  4.61it/s]
                                                    

 55%|█████▍    | 6039/11066 [22:08<18:11,  4.61it/s]
 55%|█████▍    | 6040/11066 [22:08<18:03,  4.64it/s]
                                                    

 55%|█████▍    | 6040/11066 [22:08<18:03,  4.64it/s]
 55%|█████▍    | 6041/11066 [22:08<18:05,  4.63it/s]
                                                    

 55%|█████▍    | 6041/11066 [22:08<18:05,  4.63it/s]
 55%|█████▍    | 6042/11066 [22:08<18:07,  4.62it/s]
                                                    

 55%|█████▍    | 6042/11066 [22:08<18:07,  4.62it/s]
 55%|█████▍    | 6043/11066 [22:08<17:56,  4.67it/s]
                                                    

 55%|█████▍    | 6043/11066 [22:08<17:56,  4.67it/s]
 55%|█████▍    | 6044/11066 [22:09<17:59,  4.65it/s]
                                                    

 55%|█████▍    | 6044/11066 [22:09<17:59,  4.65it/s]
 55%|█████▍    | 6045/11066 [22:09<17:54,  4.67it/s]
                                                    

 55%|█████▍    | 6045/11066 [22:09<17:54,  4.67it/s]
 55%|█████▍    | 6046/11066 [22:09<17:50,  4.69it/s]
                                                    

 55%|█████▍    | 6046/11066 [22:09<17:50,  4.69it/s]
 55%|█████▍    | 6047/11066 [22:09<17:54,  4.67it/s]
                                                    

 55%|█████▍    | 6047/11066 [22:09<17:54,  4.67it/s]
 55%|█████▍    | 6048/11066 [22:09<17:53,  4.68it/s]
                                                    

 55%|█████▍    | 6048/11066 [22:09<17:53,  4.68it/s]
 55%|█████▍    | 6049/11066 [22:10<17:50,  4.69it/s]
                                                    

 55%|█████▍    | 6049/11066 [22:10<17:50,  4.69it/s]
 55%|█████▍    | 6050/11066 [22:10<17:47,  4.70it/s]
                                                    

 55%|█████▍    | 6050/11066 [22:10<17:47,  4.70it/s]
 55%|█████▍    | 6051/11066 [22:10<17:53,  4.67it/s]
                                                    

 55%|█████▍    | 6051/11066 [22:10<17:53,  4.67it/s]
 55%|█████▍    | 6052/11066 [22:10<17:47,  4.70it/s]
                                                    

 55%|█████▍    | 6052/11066 [22:10<17:47,  4.70it/s]
 55%|█████▍    | 6053/11066 [22:11<17:52,  4.68it/s]
                                                    

 55%|█████▍    | 6053/11066 [22:11<17:52,  4.68it/s]
 55%|█████▍    | 6054/11066 [22:11<18:00,  4.64it/s]
                                                    

 55%|█████▍    | 6054/11066 [22:11<18:00,  4.64it/s]
 55%|█████▍    | 6055/11066 [22:11<17:51,  4.68it/s]
                                                    

 55%|█████▍    | 6055/11066 [22:11<17:51,  4.68it/s]
 55%|█████▍    | 6056/11066 [22:11<18:06,  4.61it/s]
                                                    

 55%|█████▍    | 6056/11066 [22:11<18:06,  4.61it/s]
 55%|█████▍    | 6057/11066 [22:11<18:05,  4.61it/s]
                                                    

 55%|█████▍    | 6057/11066 [22:11<18:05,  4.61it/s]
 55%|█████▍    | 6058/11066 [22:12<18:16,  4.57it/s]
                                                    

 55%|█████▍    | 6058/11066 [22:12<18:16,  4.57it/s]
 55%|█████▍    | 6059/11066 [22:12<18:16,  4.57it/s]
                                                    

 55%|█████▍    | 6059/11066 [22:12<18:16,  4.57it/s]
 55%|█████▍    | 6060/11066 [22:12<18:10,  4.59it/s]
                                                    

 55%|█████▍    | 6060/11066 [22:12<18:10,  4.59it/s]
 55%|█████▍    | 6061/11066 [22:12<18:00,  4.63it/s]
                                                    

 55%|█████▍    | 6061/11066 [22:12<18:00,  4.63it/s]
 55%|█████▍    | 6062/11066 [22:12<17:56,  4.65it/s]
                                                    

 55%|█████▍    | 6062/11066 [22:12<17:56,  4.65it/s]
 55%|█████▍    | 6063/11066 [22:13<17:56,  4.65it/s]
                                                    

 55%|█████▍    | 6063/11066 [22:13<17:56,  4.65it/s]
 55%|█████▍    | 6064/11066 [22:13<18:09,  4.59it/s]
                                                    

 55%|█████▍    | 6064/11066 [22:13<18:09,  4.59it/s]
 55%|█████▍    | 6065/11066 [22:13<18:15,  4.56it/s]
                                                    

 55%|█████▍    | 6065/11066 [22:13<18:15,  4.56it/s]
 55%|█████▍    | 6066/11066 [22:13<18:05,  4.60it/s]
                                                    

 55%|█████▍    | 6066/11066 [22:13<18:05,  4.60it/s]
 55%|█████▍    | 6067/11066 [22:14<18:13,  4.57it/s]
                                                    

 55%|█████▍    | 6067/11066 [22:14<18:13,  4.57it/s]
 55%|█████▍    | 6068/11066 [22:14<18:10,  4.58it/s]
                                                    

 55%|█████▍    | 6068/11066 [22:14<18:10,  4.58it/s]
 55%|█████▍    | 6069/11066 [22:14<18:14,  4.57it/s]
                                                    

 55%|█████▍    | 6069/11066 [22:14<18:14,  4.57it/s]
 55%|█████▍    | 6070/11066 [22:14<18:21,  4.54it/s]
                                                    

 55%|█████▍    | 6070/11066 [22:14<18:21,  4.54it/s]
 55%|█████▍    | 6071/11066 [22:14<18:07,  4.59it/s]
                                                    

 55%|█████▍    | 6071/11066 [22:14<18:07,  4.59it/s]
 55%|█████▍    | 6072/11066 [22:15<18:08,  4.59it/s]
                                                    

 55%|█████▍    | 6072/11066 [22:15<18:08,  4.59it/s]
 55%|█████▍    | 6073/11066 [22:15<18:07,  4.59it/s]
                                                    

 55%|█████▍    | 6073/11066 [22:15<18:07,  4.59it/s]
 55%|█████▍    | 6074/11066 [22:15<18:07,  4.59it/s]
                                                    

 55%|█████▍    | 6074/11066 [22:15<18:07,  4.59it/s]
 55%|█████▍    | 6075/11066 [22:15<18:06,  4.59it/s]
                                                    
{'loss': 0.6063, 'learning_rate': 1.3834267124525575e-05, 'epoch': 1.08}
{'loss': 0.9014, 'learning_rate': 1.3831556117838423e-05, 'epoch': 1.08}
{'loss': 0.5459, 'learning_rate': 1.3828845111151274e-05, 'epoch': 1.08}
{'loss': 0.1886, 'learning_rate': 1.3826134104464125e-05, 'epoch': 1.08}
{'loss': 0.8285, 'learning_rate': 1.3823423097776976e-05, 'epoch': 1.08}
{'loss': 0.5889, 'learning_rate': 1.3820712091089824e-05, 'epoch': 1.08}
{'loss': 0.6608, 'learning_rate': 1.3818001084402674e-05, 'epoch': 1.08}
{'loss': 1.0414, 'learning_rate': 1.3815290077715526e-05, 'epoch': 1.08}
{'loss': 0.9816, 'learning_rate': 1.3812579071028376e-05, 'epoch': 1.08}
{'loss': 0.7627, 'learning_rate': 1.3809868064341225e-05, 'epoch': 1.08}
{'loss': 0.3823, 'learning_rate': 1.3807157057654076e-05, 'epoch': 1.08}
{'loss': 0.213, 'learning_rate': 1.3804446050966927e-05, 'epoch': 1.08}
{'loss': 0.9144, 'learning_rate': 1.3801735044279777e-05, 'epoch': 1.08}
{'loss': 1.1956, 'learning_rate': 1.3799024037592625e-05, 'epoch': 1.08}
{'loss': 0.4528, 'learning_rate': 1.3796313030905477e-05, 'epoch': 1.08}
{'loss': 1.2194, 'learning_rate': 1.3793602024218327e-05, 'epoch': 1.08}
{'loss': 0.7514, 'learning_rate': 1.3790891017531177e-05, 'epoch': 1.08}
{'loss': 0.3891, 'learning_rate': 1.3788180010844026e-05, 'epoch': 1.08}
{'loss': 0.7241, 'learning_rate': 1.3785469004156877e-05, 'epoch': 1.08}
{'loss': 0.3104, 'learning_rate': 1.3782757997469728e-05, 'epoch': 1.08}
{'loss': 0.7944, 'learning_rate': 1.3780046990782578e-05, 'epoch': 1.08}
{'loss': 0.7143, 'learning_rate': 1.3777335984095428e-05, 'epoch': 1.08}
{'loss': 1.0681, 'learning_rate': 1.3774624977408278e-05, 'epoch': 1.08}
{'loss': 0.7574, 'learning_rate': 1.3771913970721128e-05, 'epoch': 1.08}
{'loss': 0.7397, 'learning_rate': 1.3769202964033978e-05, 'epoch': 1.08}
{'loss': 1.4618, 'learning_rate': 1.3766491957346828e-05, 'epoch': 1.08}
{'loss': 0.4512, 'learning_rate': 1.3763780950659679e-05, 'epoch': 1.08}
{'loss': 0.8855, 'learning_rate': 1.3761069943972529e-05, 'epoch': 1.08}
{'loss': 0.8474, 'learning_rate': 1.3758358937285379e-05, 'epoch': 1.08}
{'loss': 0.4525, 'learning_rate': 1.3755647930598229e-05, 'epoch': 1.08}
{'loss': 0.4292, 'learning_rate': 1.3752936923911079e-05, 'epoch': 1.08}
{'loss': 1.7782, 'learning_rate': 1.375022591722393e-05, 'epoch': 1.08}
{'loss': 0.3203, 'learning_rate': 1.3747514910536781e-05, 'epoch': 1.08}
{'loss': 0.6068, 'learning_rate': 1.374480390384963e-05, 'epoch': 1.08}
{'loss': 0.9309, 'learning_rate': 1.374209289716248e-05, 'epoch': 1.08}
{'loss': 0.9432, 'learning_rate': 1.373938189047533e-05, 'epoch': 1.08}
{'loss': 0.8318, 'learning_rate': 1.3736670883788182e-05, 'epoch': 1.08}
{'loss': 1.006, 'learning_rate': 1.373395987710103e-05, 'epoch': 1.08}
{'loss': 0.8278, 'learning_rate': 1.373124887041388e-05, 'epoch': 1.08}
{'loss': 0.8997, 'learning_rate': 1.372853786372673e-05, 'epoch': 1.08}
{'loss': 0.872, 'learning_rate': 1.3725826857039582e-05, 'epoch': 1.08}
{'loss': 0.6971, 'learning_rate': 1.372311585035243e-05, 'epoch': 1.09}
{'loss': 0.2731, 'learning_rate': 1.372040484366528e-05, 'epoch': 1.09}
{'loss': 0.5502, 'learning_rate': 1.3717693836978133e-05, 'epoch': 1.09}
{'loss': 0.5804, 'learning_rate': 1.3714982830290983e-05, 'epoch': 1.09}
{'loss': 0.8271, 'learning_rate': 1.3712271823603831e-05, 'epoch': 1.09}
{'loss': 0.507, 'learning_rate': 1.3709560816916681e-05, 'epoch': 1.09}
{'loss': 0.5841, 'learning_rate': 1.3706849810229533e-05, 'epoch': 1.09}
{'loss': 0.6081, 'learning_rate': 1.3704138803542383e-05, 'epoch': 1.09}
{'loss': 0.6044, 'learning_rate': 1.3701427796855232e-05, 'epoch': 1.09}
{'loss': 1.3378, 'learning_rate': 1.3698716790168083e-05, 'epoch': 1.09}
{'loss': 0.7957, 'learning_rate': 1.3696005783480934e-05, 'epoch': 1.09}
{'loss': 0.5404, 'learning_rate': 1.3693294776793784e-05, 'epoch': 1.09}
{'loss': 0.3431, 'learning_rate': 1.3690583770106632e-05, 'epoch': 1.09}
{'loss': 0.3355, 'learning_rate': 1.3687872763419484e-05, 'epoch': 1.09}
{'loss': 0.5256, 'learning_rate': 1.3685161756732334e-05, 'epoch': 1.09}
{'loss': 0.9899, 'learning_rate': 1.3682450750045184e-05, 'epoch': 1.09}
{'loss': 0.7846, 'learning_rate': 1.3679739743358033e-05, 'epoch': 1.09}
{'loss': 0.389, 'learning_rate': 1.3677028736670885e-05, 'epoch': 1.09}
{'loss': 0.365, 'learning_rate': 1.3674317729983735e-05, 'epoch': 1.09}
{'loss': 0.6241, 'learning_rate': 1.3671606723296585e-05, 'epoch': 1.09}
{'loss': 1.0476, 'learning_rate': 1.3668895716609435e-05, 'epoch': 1.09}
{'loss': 0.5208, 'learning_rate': 1.3666184709922285e-05, 'epoch': 1.09}
{'loss': 0.7417, 'learning_rate': 1.3663473703235135e-05, 'epoch': 1.09}
{'loss': 1.0138, 'learning_rate': 1.3660762696547985e-05, 'epoch': 1.09}
{'loss': 0.7379, 'learning_rate': 1.3658051689860835e-05, 'epoch': 1.09}
{'loss': 0.3691, 'learning_rate': 1.3655340683173686e-05, 'epoch': 1.09}
{'loss': 1.104, 'learning_rate': 1.3652629676486536e-05, 'epoch': 1.09}
{'loss': 0.5152, 'learning_rate': 1.3649918669799386e-05, 'epoch': 1.09}
{'loss': 0.5506, 'learning_rate': 1.3647207663112236e-05, 'epoch': 1.09}
{'loss': 0.275, 'learning_rate': 1.3644496656425086e-05, 'epoch': 1.09}
{'loss': 0.6083, 'learning_rate': 1.3641785649737936e-05, 'epoch': 1.09}
{'loss': 0.9019, 'learning_rate': 1.3639074643050788e-05, 'epoch': 1.09}
{'loss': 0.5112, 'learning_rate': 1.3636363636363637e-05, 'epoch': 1.09}
{'loss': 1.2197, 'learning_rate': 1.3633652629676487e-05, 'epoch': 1.09}
{'loss': 0.3263, 'learning_rate': 1.3630941622989337e-05, 'epoch': 1.09}
{'loss': 0.6089, 'learning_rate': 1.3628230616302189e-05, 'epoch': 1.09}
{'loss': 0.6528, 'learning_rate': 1.3625519609615037e-05, 'epoch': 1.09}
{'loss': 0.6726, 'learning_rate': 1.3622808602927887e-05, 'epoch': 1.09}
{'loss': 0.2664, 'learning_rate': 1.3620097596240737e-05, 'epoch': 1.09}
{'loss': 0.8235, 'learning_rate': 1.361738658955359e-05, 'epoch': 1.09}
{'loss': 1.0574, 'learning_rate': 1.3614675582866438e-05, 'epoch': 1.09}
{'loss': 0.6102, 'learning_rate': 1.3611964576179288e-05, 'epoch': 1.09}
{'loss': 0.5476, 'learning_rate': 1.360925356949214e-05, 'epoch': 1.09}
{'loss': 0.7671, 'learning_rate': 1.360654256280499e-05, 'epoch': 1.09}
{'loss': 1.4105, 'learning_rate': 1.3603831556117838e-05, 'epoch': 1.09}
{'loss': 1.2462, 'learning_rate': 1.3601120549430688e-05, 'epoch': 1.09}
{'loss': 0.5274, 'learning_rate': 1.359840954274354e-05, 'epoch': 1.09}
{'loss': 1.1666, 'learning_rate': 1.3595698536056389e-05, 'epoch': 1.09}
{'loss': 0.8861, 'learning_rate': 1.3592987529369239e-05, 'epoch': 1.09}
{'loss': 0.875, 'learning_rate': 1.3590276522682089e-05, 'epoch': 1.09}
{'loss': 0.7631, 'learning_rate': 1.358756551599494e-05, 'epoch': 1.09}
{'loss': 1.0639, 'learning_rate': 1.3584854509307789e-05, 'epoch': 1.09}
{'loss': 0.5986, 'learning_rate': 1.358214350262064e-05, 'epoch': 1.09}
{'loss': 0.3236, 'learning_rate': 1.3579432495933491e-05, 'epoch': 1.09}
{'loss': 0.7314, 'learning_rate': 1.3576721489246341e-05, 'epoch': 1.09}
{'loss': 0.3029, 'learning_rate': 1.357401048255919e-05, 'epoch': 1.1}
{'loss': 0.9787, 'learning_rate': 1.357129947587204e-05, 'epoch': 1.1}
{'loss': 1.2568, 'learning_rate': 1.3568588469184892e-05, 'epoch': 1.1}
{'loss': 0.5095, 'learning_rate': 1.3565877462497742e-05, 'epoch': 1.1}
{'loss': 0.7301, 'learning_rate': 1.356316645581059e-05, 'epoch': 1.1}
{'loss': 1.3568, 'learning_rate': 1.356045544912344e-05, 'epoch': 1.1}
{'loss': 0.7776, 'learning_rate': 1.3557744442436292e-05, 'epoch': 1.1}
{'loss': 0.4777, 'learning_rate': 1.3555033435749142e-05, 'epoch': 1.1}
{'loss': 1.2122, 'learning_rate': 1.355232242906199e-05, 'epoch': 1.1}
{'loss': 0.6927, 'learning_rate': 1.3549611422374843e-05, 'epoch': 1.1}
{'loss': 0.7312, 'learning_rate': 1.3546900415687693e-05, 'epoch': 1.1}
{'loss': 0.8637, 'learning_rate': 1.3544189409000543e-05, 'epoch': 1.1}
{'loss': 0.5769, 'learning_rate': 1.3541478402313391e-05, 'epoch': 1.1}
{'loss': 0.6722, 'learning_rate': 1.3538767395626243e-05, 'epoch': 1.1}
{'loss': 1.2725, 'learning_rate': 1.3536056388939093e-05, 'epoch': 1.1}
{'loss': 1.1408, 'learning_rate': 1.3533345382251943e-05, 'epoch': 1.1}

 55%|█████▍    | 6075/11066 [22:15<18:06,  4.59it/s]
 55%|█████▍    | 6076/11066 [22:16<18:17,  4.55it/s]
                                                    

 55%|█████▍    | 6076/11066 [22:16<18:17,  4.55it/s]
 55%|█████▍    | 6077/11066 [22:16<18:14,  4.56it/s]
                                                    

 55%|█████▍    | 6077/11066 [22:16<18:14,  4.56it/s]
 55%|█████▍    | 6078/11066 [22:16<18:05,  4.60it/s]
                                                    

 55%|█████▍    | 6078/11066 [22:16<18:05,  4.60it/s]
 55%|█████▍    | 6079/11066 [22:16<18:37,  4.46it/s]
                                                    

 55%|█████▍    | 6079/11066 [22:16<18:37,  4.46it/s]
 55%|█████▍    | 6080/11066 [22:16<18:39,  4.45it/s]
                                                    

 55%|█████▍    | 6080/11066 [22:16<18:39,  4.45it/s]
 55%|█████▍    | 6081/11066 [22:17<18:23,  4.52it/s]
                                                    

 55%|█████▍    | 6081/11066 [22:17<18:23,  4.52it/s]
 55%|█████▍    | 6082/11066 [22:17<18:07,  4.58it/s]
                                                    

 55%|█████▍    | 6082/11066 [22:17<18:07,  4.58it/s]
 55%|█████▍    | 6083/11066 [22:17<18:07,  4.58it/s]
                                                    

 55%|█████▍    | 6083/11066 [22:17<18:07,  4.58it/s]
 55%|█████▍    | 6084/11066 [22:17<18:13,  4.55it/s]
                                                    

 55%|█████▍    | 6084/11066 [22:17<18:13,  4.55it/s]
 55%|█████▍    | 6085/11066 [22:18<18:10,  4.57it/s]
                                                    

 55%|█████▍    | 6085/11066 [22:18<18:10,  4.57it/s]
 55%|█████▍    | 6086/11066 [22:18<18:03,  4.60it/s]
                                                    

 55%|█████▍    | 6086/11066 [22:18<18:03,  4.60it/s]
 55%|█████▌    | 6087/11066 [22:18<18:03,  4.60it/s]
                                                    

 55%|█████▌    | 6087/11066 [22:18<18:03,  4.60it/s]
 55%|█████▌    | 6088/11066 [22:18<18:01,  4.60it/s]
                                                    

 55%|█████▌    | 6088/11066 [22:18<18:01,  4.60it/s]
 55%|█████▌    | 6089/11066 [22:18<17:51,  4.65it/s]
                                                    

 55%|█████▌    | 6089/11066 [22:18<17:51,  4.65it/s]
 55%|█████▌    | 6090/11066 [22:19<17:59,  4.61it/s]
                                                    

 55%|█████▌    | 6090/11066 [22:19<17:59,  4.61it/s]
 55%|█████▌    | 6091/11066 [22:19<18:07,  4.57it/s]
                                                    

 55%|█████▌    | 6091/11066 [22:19<18:07,  4.57it/s]
 55%|█████▌    | 6092/11066 [22:19<18:13,  4.55it/s]
                                                    

 55%|█████▌    | 6092/11066 [22:19<18:13,  4.55it/s]
 55%|█████▌    | 6093/11066 [22:19<18:07,  4.57it/s]
                                                    

 55%|█████▌    | 6093/11066 [22:19<18:07,  4.57it/s]
 55%|█████▌    | 6094/11066 [22:19<18:00,  4.60it/s]
                                                    

 55%|█████▌    | 6094/11066 [22:19<18:00,  4.60it/s]
 55%|█████▌    | 6095/11066 [22:20<18:01,  4.60it/s]
                                                    

 55%|█████▌    | 6095/11066 [22:20<18:01,  4.60it/s]
 55%|█████▌    | 6096/11066 [22:20<17:55,  4.62it/s]
                                                    

 55%|█████▌    | 6096/11066 [22:20<17:55,  4.62it/s]
 55%|█████▌    | 6097/11066 [22:20<18:07,  4.57it/s]
                                                    

 55%|█████▌    | 6097/11066 [22:20<18:07,  4.57it/s]
 55%|█████▌    | 6098/11066 [22:20<18:07,  4.57it/s]
                                                    

 55%|█████▌    | 6098/11066 [22:20<18:07,  4.57it/s]
 55%|█████▌    | 6099/11066 [22:21<18:15,  4.53it/s]
                                                    

 55%|█████▌    | 6099/11066 [22:21<18:15,  4.53it/s]
 55%|█████▌    | 6100/11066 [22:21<18:02,  4.59it/s]
                                                    

 55%|█████▌    | 6100/11066 [22:21<18:02,  4.59it/s]
 55%|█████▌    | 6101/11066 [22:21<17:51,  4.64it/s]
                                                    

 55%|█████▌    | 6101/11066 [22:21<17:51,  4.64it/s]
 55%|█████▌    | 6102/11066 [22:21<17:46,  4.65it/s]
                                                    

 55%|█████▌    | 6102/11066 [22:21<17:46,  4.65it/s]
 55%|█████▌    | 6103/11066 [22:21<17:37,  4.69it/s]
                                                    

 55%|█████▌    | 6103/11066 [22:21<17:37,  4.69it/s]
 55%|█████▌    | 6104/11066 [22:22<17:36,  4.70it/s]
                                                    

 55%|█████▌    | 6104/11066 [22:22<17:36,  4.70it/s]
 55%|█████▌    | 6105/11066 [22:22<17:29,  4.73it/s]
                                                    

 55%|█████▌    | 6105/11066 [22:22<17:29,  4.73it/s]
 55%|█████▌    | 6106/11066 [22:22<17:32,  4.71it/s]
                                                    

 55%|█████▌    | 6106/11066 [22:22<17:32,  4.71it/s]
 55%|█████▌    | 6107/11066 [22:22<17:32,  4.71it/s]
                                                    

 55%|█████▌    | 6107/11066 [22:22<17:32,  4.71it/s]
 55%|█████▌    | 6108/11066 [22:22<17:38,  4.68it/s]
                                                    

 55%|█████▌    | 6108/11066 [22:22<17:38,  4.68it/s]
 55%|█████▌    | 6109/11066 [22:23<17:46,  4.65it/s]
                                                    

 55%|█████▌    | 6109/11066 [22:23<17:46,  4.65it/s]
 55%|█████▌    | 6110/11066 [22:23<17:41,  4.67it/s]
                                                    

 55%|█████▌    | 6110/11066 [22:23<17:41,  4.67it/s]
 55%|█████▌    | 6111/11066 [22:23<17:46,  4.65it/s]
                                                    

 55%|█████▌    | 6111/11066 [22:23<17:46,  4.65it/s]
 55%|█████▌    | 6112/11066 [22:23<17:49,  4.63it/s]
                                                    

 55%|█████▌    | 6112/11066 [22:23<17:49,  4.63it/s]
 55%|█████▌    | 6113/11066 [22:24<17:50,  4.63it/s]
                                                    

 55%|█████▌    | 6113/11066 [22:24<17:50,  4.63it/s]
 55%|█████▌    | 6114/11066 [22:24<17:42,  4.66it/s]
                                                    

 55%|█████▌    | 6114/11066 [22:24<17:42,  4.66it/s]
 55%|█████▌    | 6115/11066 [22:24<17:39,  4.67it/s]
                                                    

 55%|█████▌    | 6115/11066 [22:24<17:39,  4.67it/s]
 55%|█████▌    | 6116/11066 [22:24<17:38,  4.68it/s]
                                                    

 55%|█████▌    | 6116/11066 [22:24<17:38,  4.68it/s]
 55%|█████▌    | 6117/11066 [22:24<17:40,  4.67it/s]
                                                    

 55%|█████▌    | 6117/11066 [22:24<17:40,  4.67it/s]
 55%|█████▌    | 6118/11066 [22:25<17:45,  4.65it/s]
                                                    

 55%|█████▌    | 6118/11066 [22:25<17:45,  4.65it/s]
 55%|█████▌    | 6119/11066 [22:25<17:43,  4.65it/s]
                                                    

 55%|█████▌    | 6119/11066 [22:25<17:43,  4.65it/s]
 55%|█████▌    | 6120/11066 [22:25<17:57,  4.59it/s]
                                                    

 55%|█████▌    | 6120/11066 [22:25<17:57,  4.59it/s]
 55%|█████▌    | 6121/11066 [22:25<17:57,  4.59it/s]
                                                    

 55%|█████▌    | 6121/11066 [22:25<17:57,  4.59it/s]
 55%|█████▌    | 6122/11066 [22:26<17:59,  4.58it/s]
                                                    

 55%|█████▌    | 6122/11066 [22:26<17:59,  4.58it/s]
 55%|█████▌    | 6123/11066 [22:26<18:04,  4.56it/s]
                                                    

 55%|█████▌    | 6123/11066 [22:26<18:04,  4.56it/s]
 55%|█████▌    | 6124/11066 [22:26<17:53,  4.60it/s]
                                                    

 55%|█████▌    | 6124/11066 [22:26<17:53,  4.60it/s]
 55%|█████▌    | 6125/11066 [22:26<17:54,  4.60it/s]
                                                    

 55%|█████▌    | 6125/11066 [22:26<17:54,  4.60it/s]
 55%|█████▌    | 6126/11066 [22:26<17:53,  4.60it/s]
                                                    

 55%|█████▌    | 6126/11066 [22:26<17:53,  4.60it/s]
 55%|█████▌    | 6127/11066 [22:27<18:00,  4.57it/s]
                                                    

 55%|█████▌    | 6127/11066 [22:27<18:00,  4.57it/s]
 55%|█████▌    | 6128/11066 [22:27<18:07,  4.54it/s]
                                                    

 55%|█████▌    | 6128/11066 [22:27<18:07,  4.54it/s]
 55%|█████▌    | 6129/11066 [22:27<18:04,  4.55it/s]
                                                    

 55%|█████▌    | 6129/11066 [22:27<18:04,  4.55it/s]
 55%|█████▌    | 6130/11066 [22:27<18:02,  4.56it/s]
                                                    

 55%|█████▌    | 6130/11066 [22:27<18:02,  4.56it/s]
 55%|█████▌    | 6131/11066 [22:27<17:58,  4.58it/s]
                                                    

 55%|█████▌    | 6131/11066 [22:27<17:58,  4.58it/s]
 55%|█████▌    | 6132/11066 [22:28<17:57,  4.58it/s]
                                                    

 55%|█████▌    | 6132/11066 [22:28<17:57,  4.58it/s]
 55%|█████▌    | 6133/11066 [22:28<17:50,  4.61it/s]
                                                    

 55%|█████▌    | 6133/11066 [22:28<17:50,  4.61it/s]
 55%|█████▌    | 6134/11066 [22:28<17:49,  4.61it/s]
                                                    

 55%|█████▌    | 6134/11066 [22:28<17:49,  4.61it/s]
 55%|█████▌    | 6135/11066 [22:28<17:49,  4.61it/s]
                                                    

 55%|█████▌    | 6135/11066 [22:28<17:49,  4.61it/s]
 55%|█████▌    | 6136/11066 [22:29<17:57,  4.58it/s]
                                                    

 55%|█████▌    | 6136/11066 [22:29<17:57,  4.58it/s]
 55%|█████▌    | 6137/11066 [22:29<17:54,  4.59it/s]
                                                    

 55%|█████▌    | 6137/11066 [22:29<17:54,  4.59it/s]
 55%|█████▌    | 6138/11066 [22:29<17:41,  4.64it/s]
                                                    

 55%|█████▌    | 6138/11066 [22:29<17:41,  4.64it/s]
 55%|█████▌    | 6139/11066 [22:29<17:53,  4.59it/s]
                                                    

 55%|█████▌    | 6139/11066 [22:29<17:53,  4.59it/s]
 55%|█████▌    | 6140/11066 [22:29<17:59,  4.56it/s]
                                                    

 55%|█████▌    | 6140/11066 [22:29<17:59,  4.56it/s]
 55%|█████▌    | 6141/11066 [22:30<18:03,  4.54it/s]
                                                    

 55%|█████▌    | 6141/11066 [22:30<18:03,  4.54it/s]
 56%|█████▌    | 6142/11066 [22:30<18:06,  4.53it/s]
                                                    

 56%|█████▌    | 6142/11066 [22:30<18:06,  4.53it/s]
 56%|█████▌    | 6143/11066 [22:30<18:10,  4.52it/s]
                                                    

 56%|█████▌    | 6143/11066 [22:30<18:10,  4.52it/s]
 56%|█████▌    | 6144/11066 [22:30<18:11,  4.51it/s]
                                                    

 56%|█████▌    | 6144/11066 [22:30<18:11,  4.51it/s]
 56%|█████▌    | 6145/11066 [22:31<18:12,  4.50it/s]
                                                    

 56%|█████▌    | 6145/11066 [22:31<18:12,  4.50it/s]
 56%|█████▌    | 6146/11066 [22:31<18:13,  4.50it/s]
                                                    

 56%|█████▌    | 6146/11066 [22:31<18:13,  4.50it/s]
 56%|█████▌    | 6147/11066 [22:31<18:13,  4.50it/s]
                                                    

 56%|█████▌    | 6147/11066 [22:31<18:13,  4.50it/s]
 56%|█████▌    | 6148/11066 [22:31<18:16,  4.49it/s]
                                                    

 56%|█████▌    | 6148/11066 [22:31<18:16,  4.49it/s]
 56%|█████▌    | 6149/11066 [22:31<18:16,  4.48it/s]
                                                    

 56%|█████▌    | 6149/11066 [22:31<18:16,  4.48it/s]
 56%|█████▌    | 6150/11066 [22:32<18:15,  4.49it/s]
                                                    

 56%|█████▌    | 6150/11066 [22:32<18:15,  4.49it/s]
 56%|█████▌    | 6151/11066 [22:32<18:06,  4.53it/s]
                                                    

 56%|█████▌    | 6151/11066 [22:32<18:06,  4.53it/s]
 56%|█████▌    | 6152/11066 [22:32<17:59,  4.55it/s]
                                                    

 56%|█████▌    | 6152/11066 [22:32<17:59,  4.55it/s]
 56%|█████▌    | 6153/11066 [22:32<18:06,  4.52it/s]
                                                    

 56%|█████▌    | 6153/11066 [22:32<18:06,  4.52it/s]
 56%|█████▌    | 6154/11066 [22:33<18:10,  4.51it/s]
                                                    

 56%|█████▌    | 6154/11066 [22:33<18:10,  4.51it/s]
 56%|█████▌    | 6155/11066 [22:33<17:56,  4.56it/s]
                                                    

 56%|█████▌    | 6155/11066 [22:33<17:56,  4.56it/s]
 56%|█████▌    | 6156/11066 [22:33<17:40,  4.63it/s]
                                                    

 56%|█████▌    | 6156/11066 [22:33<17:40,  4.63it/s]
 56%|█████▌    | 6157/11066 [22:33<17:43,  4.62it/s]
                                                    

 56%|█████▌    | 6157/11066 [22:33<17:43,  4.62it/s]
 56%|█████▌    | 6158/11066 [22:33<17:38,  4.64it/s]
                                                    

 56%|█████▌    | 6158/11066 [22:33<17:38,  4.64it/s]
 56%|█████▌    | 6159/11066 [22:34<17:30,  4.67it/s]
                                                    

 56%|█████▌    | 6159/11066 [22:34<17:30,  4.67it/s]
 56%|█████▌    | 6160/11066 [22:34<17:23,  4.70it/s]
                                                    

 56%|█████▌    | 6160/11066 [22:34<17:23,  4.70it/s]
 56%|█████▌    | 6161/11066 [22:34<17:23,  4.70it/s]
                                                    

 56%|█████▌    | 6161/11066 [22:34<17:23,  4.70it/s]
 56%|█████▌    | 6162/11066 [22:34<17:28,  4.68it/s]
                                                    

 56%|█████▌    | 6162/11066 [22:34<17:28,  4.68it/s]
 56%|█████▌    | 6163/11066 [22:34<17:27,  4.68it/s]
                                                    

 56%|█████▌    | 6163/11066 [22:34<17:27,  4.68it/s]
 56%|█████▌    | 6164/11066 [22:35<17:44,  4.60it/s]
                                                    

 56%|█████▌    | 6164/11066 [22:35<17:44,  4.60it/s]
 56%|█████▌    | 6165/11066 [22:35<17:53,  4.57it/s]
                                                    

 56%|█████▌    | 6165/11066 [22:35<17:53,  4.57it/s]
 56%|█████▌    | 6166/11066 [22:35<18:00,  4.54it/s]
                                                    

 56%|█████▌    | 6166/11066 [22:35<18:00,  4.54it/s]
 56%|█████▌    | 6167/11066 [22:35<18:04,  4.52it/s]
                                                    

 56%|█████▌    | 6167/11066 [22:35<18:04,  4.52it/s]
 56%|█████▌    | 6168/11066 [22:36<18:25,  4.43it/s]
                                                    

 56%|█████▌    | 6168/11066 [22:36<18:25,  4.43it/s]
 56%|█████▌    | 6169/11066 [22:36<18:29,  4.41it/s]
                                                    

 56%|█████▌    | 6169/11066 [22:36<18:29,  4.41it/s]
 56%|█████▌    | 6170/11066 [22:36<18:34,  4.39it/s]
                                                    

 56%|█████▌    | 6170/11066 [22:36<18:34,  4.39it/s]
 56%|█████▌    | 6171/11066 [22:36<18:35,  4.39it/s]
                                                    

 56%|█████▌    | 6171/11066 [22:36<18:35,  4.39it/s]
 56%|█████▌    | 6172/11066 [22:37<18:18,  4.46it/s]
                                                    

 56%|█████▌    | 6172/11066 [22:37<18:18,  4.46it/s]
 56%|█████▌    | 6173/11066 [22:37<17:57,  4.54it/s]
                                                    

 56%|█████▌    | 6173/11066 [22:37<17:57,  4.54it/s]
 56%|█████▌    | 6174/11066 [22:37<17:39,  4.62it/s]
                                                    

 56%|█████▌    | 6174/11066 [22:37<17:39,  4.62it/s]
 56%|█████▌    | 6175/11066 [22:37<17:42,  4.60it/s]
                                                    

 56%|█████▌    | 6175/11066 [22:37<17:42,  4.60it/s]
 56%|█████▌    | 6176/11066 [22:37<17:33,  4.64it/s]
                                                    

 56%|█████▌    | 6176/11066 [22:37<17:33,  4.64it/s]
 56%|█████▌    | 6177/11066 [22:38<17:26,  4.67it/s]
                                                    

 56%|█████▌    | 6177/11066 [22:38<17:26,  4.67it/s]
 56%|█████▌    | 6178/11066 [22:38<17:17,  4.71it/s]
                                                    

 56%|█████▌    | 6178/11066 [22:38<17:17,  4.71it/s]
 56%|█████▌    | 6179/11066 [22:38<17:18,  4.70it/s]
                                                    

 56%|█████▌    | 6179/11066 [22:38<17:18,  4.70it/s]
 56%|█████▌    | 6180/11066 [22:38<17:25,  4.67it/s]
                                                    

 56%|█████▌    | 6180/11066 [22:38<17:25,  4.67it/s]
 56%|█████▌    | 6181/11066 [22:38<17:20,  4.70it/s]
                                                    

 56%|█████▌    | 6181/11066 [22:38<17:20,  4.70it/s]
 56%|█████▌    | 6182/11066 [22:39<17:35,  4.63it/s]
                                                    

 56%|█████▌    | 6182/11066 [22:39<17:35,  4.63it/s]
 56%|█████▌    | 6183/11066 [22:39<17:32,  4.64it/s]
                                                    

 56%|█████▌    | 6183/11066 [22:39<17:32,  4.64it/s]
 56%|█████▌    | 6184/11066 [22:39<17:42,  4.60it/s]
                                                    

 56%|█████▌    | 6184/11066 [22:39<17:42,  4.60it/s]
 56%|█████▌    | 6185/11066 [22:39<17:34,  4.63it/s]
                                                    

 56%|█████▌    | 6185/11066 [22:39<17:34,  4.63it/s]
 56%|█████▌    | 6186/11066 [22:40<17:32,  4.64it/s]
                                                    

 56%|█████▌    | 6186/11066 [22:40<17:32,  4.64it/s]
 56%|█████▌    | 6187/11066 [22:40<17:34,  4.63it/s]
                                                    

 56%|█████▌    | 6187/11066 [22:40<17:34,  4.63it/s]
 56%|█████▌    | 6188/11066 [22:40<17:23,  4.67it/s]
                                                    
{'loss': 0.7475, 'learning_rate': 1.3530634375564793e-05, 'epoch': 1.1}
{'loss': 0.7868, 'learning_rate': 1.3527923368877644e-05, 'epoch': 1.1}
{'loss': 0.5833, 'learning_rate': 1.3525212362190494e-05, 'epoch': 1.1}
{'loss': 0.8061, 'learning_rate': 1.3522501355503344e-05, 'epoch': 1.1}
{'loss': 1.0358, 'learning_rate': 1.3519790348816194e-05, 'epoch': 1.1}
{'loss': 0.3987, 'learning_rate': 1.3517079342129044e-05, 'epoch': 1.1}
{'loss': 1.1641, 'learning_rate': 1.3514368335441894e-05, 'epoch': 1.1}
{'loss': 0.7834, 'learning_rate': 1.3511657328754744e-05, 'epoch': 1.1}
{'loss': 0.7323, 'learning_rate': 1.3508946322067595e-05, 'epoch': 1.1}
{'loss': 0.449, 'learning_rate': 1.3506235315380445e-05, 'epoch': 1.1}
{'loss': 0.5398, 'learning_rate': 1.3503524308693295e-05, 'epoch': 1.1}
{'loss': 0.7275, 'learning_rate': 1.3500813302006147e-05, 'epoch': 1.1}
{'loss': 0.6031, 'learning_rate': 1.3498102295318995e-05, 'epoch': 1.1}
{'loss': 0.5165, 'learning_rate': 1.3495391288631845e-05, 'epoch': 1.1}
{'loss': 0.5194, 'learning_rate': 1.3492680281944695e-05, 'epoch': 1.1}
{'loss': 1.018, 'learning_rate': 1.3489969275257547e-05, 'epoch': 1.1}
{'loss': 0.5559, 'learning_rate': 1.3487258268570396e-05, 'epoch': 1.1}
{'loss': 0.6703, 'learning_rate': 1.3484547261883246e-05, 'epoch': 1.1}
{'loss': 0.564, 'learning_rate': 1.3481836255196096e-05, 'epoch': 1.1}
{'loss': 0.6148, 'learning_rate': 1.3479125248508948e-05, 'epoch': 1.1}
{'loss': 0.3827, 'learning_rate': 1.3476414241821796e-05, 'epoch': 1.1}
{'loss': 0.6711, 'learning_rate': 1.3473703235134646e-05, 'epoch': 1.1}
{'loss': 1.246, 'learning_rate': 1.3470992228447498e-05, 'epoch': 1.1}
{'loss': 1.0122, 'learning_rate': 1.3468281221760348e-05, 'epoch': 1.1}
{'loss': 0.8021, 'learning_rate': 1.3465570215073197e-05, 'epoch': 1.1}
{'loss': 1.2986, 'learning_rate': 1.3462859208386047e-05, 'epoch': 1.1}
{'loss': 1.0375, 'learning_rate': 1.3460148201698899e-05, 'epoch': 1.1}
{'loss': 0.7123, 'learning_rate': 1.3457437195011749e-05, 'epoch': 1.1}
{'loss': 0.7062, 'learning_rate': 1.3454726188324597e-05, 'epoch': 1.1}
{'loss': 0.6073, 'learning_rate': 1.3452015181637447e-05, 'epoch': 1.1}
{'loss': 0.5038, 'learning_rate': 1.34493041749503e-05, 'epoch': 1.1}
{'loss': 0.4975, 'learning_rate': 1.344659316826315e-05, 'epoch': 1.1}
{'loss': 0.6583, 'learning_rate': 1.3443882161575998e-05, 'epoch': 1.1}
{'loss': 0.5616, 'learning_rate': 1.344117115488885e-05, 'epoch': 1.1}
{'loss': 0.4696, 'learning_rate': 1.34384601482017e-05, 'epoch': 1.1}
{'loss': 0.5032, 'learning_rate': 1.343574914151455e-05, 'epoch': 1.1}
{'loss': 0.5866, 'learning_rate': 1.3433038134827398e-05, 'epoch': 1.1}
{'loss': 0.8136, 'learning_rate': 1.343032712814025e-05, 'epoch': 1.1}
{'loss': 0.9989, 'learning_rate': 1.34276161214531e-05, 'epoch': 1.1}
{'loss': 0.5957, 'learning_rate': 1.342490511476595e-05, 'epoch': 1.11}
{'loss': 0.5001, 'learning_rate': 1.3422194108078799e-05, 'epoch': 1.11}
{'loss': 0.7725, 'learning_rate': 1.341948310139165e-05, 'epoch': 1.11}
{'loss': 0.4996, 'learning_rate': 1.34167720947045e-05, 'epoch': 1.11}
{'loss': 0.367, 'learning_rate': 1.3414061088017351e-05, 'epoch': 1.11}
{'loss': 0.5885, 'learning_rate': 1.3411350081330201e-05, 'epoch': 1.11}
{'loss': 1.3497, 'learning_rate': 1.3408639074643051e-05, 'epoch': 1.11}
{'loss': 0.6595, 'learning_rate': 1.3405928067955901e-05, 'epoch': 1.11}
{'loss': 0.7056, 'learning_rate': 1.3403217061268751e-05, 'epoch': 1.11}
{'loss': 0.518, 'learning_rate': 1.3400506054581602e-05, 'epoch': 1.11}
{'loss': 0.9093, 'learning_rate': 1.3397795047894452e-05, 'epoch': 1.11}
{'loss': 1.0142, 'learning_rate': 1.3395084041207302e-05, 'epoch': 1.11}
{'loss': 1.2031, 'learning_rate': 1.3392373034520152e-05, 'epoch': 1.11}
{'loss': 0.2102, 'learning_rate': 1.3389662027833002e-05, 'epoch': 1.11}
{'loss': 0.4649, 'learning_rate': 1.3386951021145852e-05, 'epoch': 1.11}
{'loss': 0.6684, 'learning_rate': 1.3384240014458702e-05, 'epoch': 1.11}
{'loss': 1.0927, 'learning_rate': 1.3381529007771554e-05, 'epoch': 1.11}
{'loss': 0.3045, 'learning_rate': 1.3378818001084403e-05, 'epoch': 1.11}
{'loss': 0.6557, 'learning_rate': 1.3376106994397253e-05, 'epoch': 1.11}
{'loss': 0.8452, 'learning_rate': 1.3373395987710103e-05, 'epoch': 1.11}
{'loss': 0.7044, 'learning_rate': 1.3370684981022955e-05, 'epoch': 1.11}
{'loss': 0.865, 'learning_rate': 1.3367973974335803e-05, 'epoch': 1.11}
{'loss': 0.8789, 'learning_rate': 1.3365262967648653e-05, 'epoch': 1.11}
{'loss': 0.6229, 'learning_rate': 1.3362551960961504e-05, 'epoch': 1.11}
{'loss': 0.5162, 'learning_rate': 1.3359840954274355e-05, 'epoch': 1.11}
{'loss': 1.3168, 'learning_rate': 1.3357129947587204e-05, 'epoch': 1.11}
{'loss': 0.528, 'learning_rate': 1.3354418940900054e-05, 'epoch': 1.11}
{'loss': 0.7332, 'learning_rate': 1.3351707934212906e-05, 'epoch': 1.11}
{'loss': 0.6342, 'learning_rate': 1.3348996927525756e-05, 'epoch': 1.11}
{'loss': 0.9201, 'learning_rate': 1.3346285920838604e-05, 'epoch': 1.11}
{'loss': 0.4709, 'learning_rate': 1.3343574914151454e-05, 'epoch': 1.11}
{'loss': 0.912, 'learning_rate': 1.3340863907464306e-05, 'epoch': 1.11}
{'loss': 1.1978, 'learning_rate': 1.3338152900777156e-05, 'epoch': 1.11}
{'loss': 0.6843, 'learning_rate': 1.3335441894090005e-05, 'epoch': 1.11}
{'loss': 0.8842, 'learning_rate': 1.3332730887402857e-05, 'epoch': 1.11}
{'loss': 0.5563, 'learning_rate': 1.3330019880715707e-05, 'epoch': 1.11}
{'loss': 0.6073, 'learning_rate': 1.3327308874028557e-05, 'epoch': 1.11}
{'loss': 0.9835, 'learning_rate': 1.3324597867341405e-05, 'epoch': 1.11}
{'loss': 0.3019, 'learning_rate': 1.3321886860654257e-05, 'epoch': 1.11}
{'loss': 0.5619, 'learning_rate': 1.3319175853967107e-05, 'epoch': 1.11}
{'loss': 0.4364, 'learning_rate': 1.3316464847279957e-05, 'epoch': 1.11}
{'loss': 0.4416, 'learning_rate': 1.3313753840592806e-05, 'epoch': 1.11}
{'loss': 0.7417, 'learning_rate': 1.3311042833905658e-05, 'epoch': 1.11}
{'loss': 0.7508, 'learning_rate': 1.3308331827218508e-05, 'epoch': 1.11}
{'loss': 0.8621, 'learning_rate': 1.3305620820531358e-05, 'epoch': 1.11}
{'loss': 1.6416, 'learning_rate': 1.3302909813844208e-05, 'epoch': 1.11}
{'loss': 0.8251, 'learning_rate': 1.3300198807157058e-05, 'epoch': 1.11}
{'loss': 0.5112, 'learning_rate': 1.3297487800469908e-05, 'epoch': 1.11}
{'loss': 1.049, 'learning_rate': 1.3294776793782759e-05, 'epoch': 1.11}
{'loss': 1.0598, 'learning_rate': 1.3292065787095609e-05, 'epoch': 1.11}
{'loss': 0.6682, 'learning_rate': 1.3289354780408459e-05, 'epoch': 1.11}
{'loss': 0.7128, 'learning_rate': 1.3286643773721309e-05, 'epoch': 1.11}
{'loss': 0.5696, 'learning_rate': 1.3283932767034159e-05, 'epoch': 1.11}
{'loss': 0.6331, 'learning_rate': 1.328122176034701e-05, 'epoch': 1.11}
{'loss': 0.9614, 'learning_rate': 1.327851075365986e-05, 'epoch': 1.11}
{'loss': 0.443, 'learning_rate': 1.327579974697271e-05, 'epoch': 1.11}
{'loss': 1.0588, 'learning_rate': 1.3273088740285561e-05, 'epoch': 1.12}
{'loss': 0.6571, 'learning_rate': 1.327037773359841e-05, 'epoch': 1.12}
{'loss': 0.9747, 'learning_rate': 1.326766672691126e-05, 'epoch': 1.12}
{'loss': 0.5156, 'learning_rate': 1.326495572022411e-05, 'epoch': 1.12}
{'loss': 0.7507, 'learning_rate': 1.3262244713536962e-05, 'epoch': 1.12}
{'loss': 0.7796, 'learning_rate': 1.325953370684981e-05, 'epoch': 1.12}
{'loss': 0.4679, 'learning_rate': 1.325682270016266e-05, 'epoch': 1.12}
{'loss': 0.5842, 'learning_rate': 1.325411169347551e-05, 'epoch': 1.12}
{'loss': 0.5943, 'learning_rate': 1.325140068678836e-05, 'epoch': 1.12}
{'loss': 0.6149, 'learning_rate': 1.324868968010121e-05, 'epoch': 1.12}
{'loss': 0.5097, 'learning_rate': 1.3245978673414061e-05, 'epoch': 1.12}
{'loss': 0.8437, 'learning_rate': 1.3243267666726913e-05, 'epoch': 1.12}
{'loss': 0.693, 'learning_rate': 1.3240556660039761e-05, 'epoch': 1.12}
{'loss': 0.3009, 'learning_rate': 1.3237845653352611e-05, 'epoch': 1.12}
{'loss': 0.3705, 'learning_rate': 1.3235134646665462e-05, 'epoch': 1.12}
{'loss': 0.8361, 'learning_rate': 1.3232423639978313e-05, 'epoch': 1.12}
{'loss': 0.6604, 'learning_rate': 1.3229712633291162e-05, 'epoch': 1.12}
{'loss': 0.9009, 'learning_rate': 1.3227001626604012e-05, 'epoch': 1.12}

 56%|█████▌    | 6188/11066 [22:40<17:23,  4.67it/s]
 56%|█████▌    | 6189/11066 [22:40<17:36,  4.61it/s]
                                                    

 56%|█████▌    | 6189/11066 [22:40<17:36,  4.61it/s]
 56%|█████▌    | 6190/11066 [22:40<17:29,  4.64it/s]
                                                    

 56%|█████▌    | 6190/11066 [22:40<17:29,  4.64it/s]
 56%|█████▌    | 6191/11066 [22:41<17:31,  4.64it/s]
                                                    

 56%|█████▌    | 6191/11066 [22:41<17:31,  4.64it/s]
 56%|█████▌    | 6192/11066 [22:41<17:21,  4.68it/s]
                                                    

 56%|█████▌    | 6192/11066 [22:41<17:21,  4.68it/s]
 56%|█████▌    | 6193/11066 [22:41<17:19,  4.69it/s]
                                                    

 56%|█████▌    | 6193/11066 [22:41<17:19,  4.69it/s]
 56%|█████▌    | 6194/11066 [22:41<17:24,  4.67it/s]
                                                    

 56%|█████▌    | 6194/11066 [22:41<17:24,  4.67it/s]
 56%|█████▌    | 6195/11066 [22:41<17:40,  4.59it/s]
                                                    

 56%|█████▌    | 6195/11066 [22:41<17:40,  4.59it/s]
 56%|█████▌    | 6196/11066 [22:42<17:39,  4.59it/s]
                                                    

 56%|█████▌    | 6196/11066 [22:42<17:39,  4.59it/s]
 56%|█████▌    | 6197/11066 [22:42<17:28,  4.65it/s]
                                                    

 56%|█████▌    | 6197/11066 [22:42<17:28,  4.65it/s]
 56%|█████▌    | 6198/11066 [22:42<17:30,  4.63it/s]
                                                    

 56%|█████▌    | 6198/11066 [22:42<17:30,  4.63it/s]
 56%|█████▌    | 6199/11066 [22:42<17:22,  4.67it/s]
                                                    

 56%|█████▌    | 6199/11066 [22:42<17:22,  4.67it/s]
 56%|█████▌    | 6200/11066 [22:43<17:16,  4.70it/s]
                                                    

 56%|█████▌    | 6200/11066 [22:43<17:16,  4.70it/s]
 56%|█████▌    | 6201/11066 [22:43<17:29,  4.64it/s]
                                                    

 56%|█████▌    | 6201/11066 [22:43<17:29,  4.64it/s]
 56%|█████▌    | 6202/11066 [22:43<17:24,  4.66it/s]
                                                    

 56%|█████▌    | 6202/11066 [22:43<17:24,  4.66it/s]
 56%|█████▌    | 6203/11066 [22:43<17:35,  4.61it/s]
                                                    

 56%|█████▌    | 6203/11066 [22:43<17:35,  4.61it/s]
 56%|█████▌    | 6204/11066 [22:43<17:27,  4.64it/s]
                                                    

 56%|█████▌    | 6204/11066 [22:43<17:27,  4.64it/s]
 56%|█████▌    | 6205/11066 [22:44<17:22,  4.66it/s]
                                                    

 56%|█████▌    | 6205/11066 [22:44<17:22,  4.66it/s]
 56%|█████▌    | 6206/11066 [22:44<17:26,  4.64it/s]
                                                    

 56%|█████▌    | 6206/11066 [22:44<17:26,  4.64it/s]
 56%|█████▌    | 6207/11066 [22:44<17:24,  4.65it/s]
                                                    

 56%|█████▌    | 6207/11066 [22:44<17:24,  4.65it/s]
 56%|█████▌    | 6208/11066 [22:44<17:20,  4.67it/s]
                                                    

 56%|█████▌    | 6208/11066 [22:44<17:20,  4.67it/s]
 56%|█████▌    | 6209/11066 [22:44<17:15,  4.69it/s]
                                                    

 56%|█████▌    | 6209/11066 [22:44<17:15,  4.69it/s]
 56%|█████▌    | 6210/11066 [22:45<17:16,  4.69it/s]
                                                    

 56%|█████▌    | 6210/11066 [22:45<17:16,  4.69it/s]
 56%|█████▌    | 6211/11066 [22:45<17:11,  4.71it/s]
                                                    

 56%|█████▌    | 6211/11066 [22:45<17:11,  4.71it/s]
 56%|█████▌    | 6212/11066 [22:45<17:19,  4.67it/s]
                                                    

 56%|█████▌    | 6212/11066 [22:45<17:19,  4.67it/s]
 56%|█████▌    | 6213/11066 [22:45<17:16,  4.68it/s]
                                                    

 56%|█████▌    | 6213/11066 [22:45<17:16,  4.68it/s]
 56%|█████▌    | 6214/11066 [22:46<17:21,  4.66it/s]
                                                    

 56%|█████▌    | 6214/11066 [22:46<17:21,  4.66it/s]
 56%|█████▌    | 6215/11066 [22:46<17:21,  4.66it/s]
                                                    

 56%|█████▌    | 6215/11066 [22:46<17:21,  4.66it/s]
 56%|█████▌    | 6216/11066 [22:46<17:18,  4.67it/s]
                                                    

 56%|█████▌    | 6216/11066 [22:46<17:18,  4.67it/s]
 56%|█████▌    | 6217/11066 [22:46<17:15,  4.68it/s]
                                                    

 56%|█████▌    | 6217/11066 [22:46<17:15,  4.68it/s]
 56%|█████▌    | 6218/11066 [22:46<17:30,  4.61it/s]
                                                    

 56%|█████▌    | 6218/11066 [22:46<17:30,  4.61it/s]
 56%|█████▌    | 6219/11066 [22:47<17:40,  4.57it/s]
                                                    

 56%|█████▌    | 6219/11066 [22:47<17:40,  4.57it/s]
 56%|█████▌    | 6220/11066 [22:47<17:44,  4.55it/s]
                                                    

 56%|█████▌    | 6220/11066 [22:47<17:44,  4.55it/s]
 56%|█████▌    | 6221/11066 [22:47<17:48,  4.53it/s]
                                                    

 56%|█████▌    | 6221/11066 [22:47<17:48,  4.53it/s]
 56%|█████▌    | 6222/11066 [22:47<17:51,  4.52it/s]
                                                    

 56%|█████▌    | 6222/11066 [22:47<17:51,  4.52it/s]
 56%|█████▌    | 6223/11066 [22:48<17:54,  4.51it/s]
                                                    

 56%|█████▌    | 6223/11066 [22:48<17:54,  4.51it/s]
 56%|█████▌    | 6224/11066 [22:48<17:54,  4.50it/s]
                                                    

 56%|█████▌    | 6224/11066 [22:48<17:54,  4.50it/s]
 56%|█████▋    | 6225/11066 [22:48<17:54,  4.51it/s]
                                                    

 56%|█████▋    | 6225/11066 [22:48<17:54,  4.51it/s]
 56%|█████▋    | 6226/11066 [22:48<17:54,  4.50it/s]
                                                    

 56%|█████▋    | 6226/11066 [22:48<17:54,  4.50it/s]
 56%|█████▋    | 6227/11066 [22:48<17:46,  4.54it/s]
                                                    

 56%|█████▋    | 6227/11066 [22:48<17:46,  4.54it/s]
 56%|█████▋    | 6228/11066 [22:49<17:35,  4.58it/s]
                                                    

 56%|█████▋    | 6228/11066 [22:49<17:35,  4.58it/s]
 56%|█████▋    | 6229/11066 [22:49<17:28,  4.62it/s]
                                                    

 56%|█████▋    | 6229/11066 [22:49<17:28,  4.62it/s]
 56%|█████▋    | 6230/11066 [22:49<17:19,  4.65it/s]
                                                    

 56%|█████▋    | 6230/11066 [22:49<17:19,  4.65it/s]
 56%|█████▋    | 6231/11066 [22:49<17:16,  4.66it/s]
                                                    

 56%|█████▋    | 6231/11066 [22:49<17:16,  4.66it/s]
 56%|█████▋    | 6232/11066 [22:49<17:09,  4.70it/s]
                                                    

 56%|█████▋    | 6232/11066 [22:49<17:09,  4.70it/s]
 56%|█████▋    | 6233/11066 [22:50<17:08,  4.70it/s]
                                                    

 56%|█████▋    | 6233/11066 [22:50<17:08,  4.70it/s]
 56%|█████▋    | 6234/11066 [22:50<17:13,  4.68it/s]
                                                    

 56%|█████▋    | 6234/11066 [22:50<17:13,  4.68it/s]
 56%|█████▋    | 6235/11066 [22:50<17:28,  4.61it/s]
                                                    

 56%|█████▋    | 6235/11066 [22:50<17:28,  4.61it/s]
 56%|█████▋    | 6236/11066 [22:50<17:22,  4.63it/s]
                                                    

 56%|█████▋    | 6236/11066 [22:50<17:22,  4.63it/s]
 56%|█████▋    | 6237/11066 [22:51<17:34,  4.58it/s]
                                                    

 56%|█████▋    | 6237/11066 [22:51<17:34,  4.58it/s]
 56%|█████▋    | 6238/11066 [22:51<17:41,  4.55it/s]
                                                    

 56%|█████▋    | 6238/11066 [22:51<17:41,  4.55it/s]
 56%|█████▋    | 6239/11066 [22:51<17:30,  4.59it/s]
                                                    

 56%|█████▋    | 6239/11066 [22:51<17:30,  4.59it/s]
 56%|█████▋    | 6240/11066 [22:51<17:28,  4.60it/s]
                                                    

 56%|█████▋    | 6240/11066 [22:51<17:28,  4.60it/s]
 56%|█████▋    | 6241/11066 [22:51<17:17,  4.65it/s]
                                                    

 56%|█████▋    | 6241/11066 [22:51<17:17,  4.65it/s]
 56%|█████▋    | 6242/11066 [22:52<17:13,  4.67it/s]
                                                    

 56%|█████▋    | 6242/11066 [22:52<17:13,  4.67it/s]
 56%|█████▋    | 6243/11066 [22:52<17:04,  4.71it/s]
                                                    

 56%|█████▋    | 6243/11066 [22:52<17:04,  4.71it/s]
 56%|█████▋    | 6244/11066 [22:52<17:05,  4.70it/s]
                                                    

 56%|█████▋    | 6244/11066 [22:52<17:05,  4.70it/s]
 56%|█████▋    | 6245/11066 [22:52<17:05,  4.70it/s]
                                                    

 56%|█████▋    | 6245/11066 [22:52<17:05,  4.70it/s]
 56%|█████▋    | 6246/11066 [22:52<17:04,  4.70it/s]
                                                    

 56%|█████▋    | 6246/11066 [22:52<17:04,  4.70it/s]
 56%|█████▋    | 6247/11066 [22:53<17:03,  4.71it/s]
                                                    

 56%|█████▋    | 6247/11066 [22:53<17:03,  4.71it/s]
 56%|█████▋    | 6248/11066 [22:53<17:02,  4.71it/s]
                                                    

 56%|█████▋    | 6248/11066 [22:53<17:02,  4.71it/s]
 56%|█████▋    | 6249/11066 [22:53<17:02,  4.71it/s]
                                                    

 56%|█████▋    | 6249/11066 [22:53<17:02,  4.71it/s]
 56%|█████▋    | 6250/11066 [22:53<17:09,  4.68it/s]
                                                    

 56%|█████▋    | 6250/11066 [22:53<17:09,  4.68it/s]
 56%|█████▋    | 6251/11066 [22:54<17:00,  4.72it/s]
                                                    

 56%|█████▋    | 6251/11066 [22:54<17:00,  4.72it/s]
 56%|█████▋    | 6252/11066 [22:54<17:19,  4.63it/s]
                                                    

 56%|█████▋    | 6252/11066 [22:54<17:19,  4.63it/s]
 57%|█████▋    | 6253/11066 [22:54<17:14,  4.65it/s]
                                                    

 57%|█████▋    | 6253/11066 [22:54<17:14,  4.65it/s]
 57%|█████▋    | 6254/11066 [22:54<17:10,  4.67it/s]
                                                    

 57%|█████▋    | 6254/11066 [22:54<17:10,  4.67it/s]
 57%|█████▋    | 6255/11066 [22:54<17:07,  4.68it/s]
                                                    

 57%|█████▋    | 6255/11066 [22:54<17:07,  4.68it/s]
 57%|█████▋    | 6256/11066 [22:55<17:04,  4.69it/s]
                                                    

 57%|█████▋    | 6256/11066 [22:55<17:04,  4.69it/s]
 57%|█████▋    | 6257/11066 [22:55<17:17,  4.63it/s]
                                                    

 57%|█████▋    | 6257/11066 [22:55<17:17,  4.63it/s]
 57%|█████▋    | 6258/11066 [22:55<17:13,  4.65it/s]
                                                    

 57%|█████▋    | 6258/11066 [22:55<17:13,  4.65it/s]
 57%|█████▋    | 6259/11066 [22:55<17:16,  4.64it/s]
                                                    

 57%|█████▋    | 6259/11066 [22:55<17:16,  4.64it/s]
 57%|█████▋    | 6260/11066 [22:55<17:07,  4.68it/s]
                                                    

 57%|█████▋    | 6260/11066 [22:55<17:07,  4.68it/s]
 57%|█████▋    | 6261/11066 [22:56<16:59,  4.71it/s]
                                                    

 57%|█████▋    | 6261/11066 [22:56<16:59,  4.71it/s]
 57%|█████▋    | 6262/11066 [22:56<17:01,  4.70it/s]
                                                    

 57%|█████▋    | 6262/11066 [22:56<17:01,  4.70it/s]
 57%|█████▋    | 6263/11066 [22:56<17:00,  4.71it/s]
                                                    

 57%|█████▋    | 6263/11066 [22:56<17:00,  4.71it/s]
 57%|█████▋    | 6264/11066 [22:56<16:59,  4.71it/s]
                                                    

 57%|█████▋    | 6264/11066 [22:56<16:59,  4.71it/s]
 57%|█████▋    | 6265/11066 [22:57<17:07,  4.67it/s]
                                                    

 57%|█████▋    | 6265/11066 [22:57<17:07,  4.67it/s]
 57%|█████▋    | 6266/11066 [22:57<17:15,  4.63it/s]
                                                    

 57%|█████▋    | 6266/11066 [22:57<17:15,  4.63it/s]
 57%|█████▋    | 6267/11066 [22:57<17:17,  4.63it/s]
                                                    

 57%|█████▋    | 6267/11066 [22:57<17:17,  4.63it/s]
 57%|█████▋    | 6268/11066 [22:57<17:26,  4.59it/s]
                                                    

 57%|█████▋    | 6268/11066 [22:57<17:26,  4.59it/s]
 57%|█████▋    | 6269/11066 [22:57<17:34,  4.55it/s]
                                                    

 57%|█████▋    | 6269/11066 [22:57<17:34,  4.55it/s]
 57%|█████▋    | 6270/11066 [22:58<17:32,  4.56it/s]
                                                    

 57%|█████▋    | 6270/11066 [22:58<17:32,  4.56it/s]
 57%|█████▋    | 6271/11066 [22:58<17:22,  4.60it/s]
                                                    

 57%|█████▋    | 6271/11066 [22:58<17:22,  4.60it/s]
 57%|█████▋    | 6272/11066 [22:58<17:15,  4.63it/s]
                                                    

 57%|█████▋    | 6272/11066 [22:58<17:15,  4.63it/s]
 57%|█████▋    | 6273/11066 [22:58<17:10,  4.65it/s]
                                                    

 57%|█████▋    | 6273/11066 [22:58<17:10,  4.65it/s]
 57%|█████▋    | 6274/11066 [22:58<17:14,  4.63it/s]
                                                    

 57%|█████▋    | 6274/11066 [22:58<17:14,  4.63it/s]
 57%|█████▋    | 6275/11066 [22:59<17:24,  4.59it/s]
                                                    

 57%|█████▋    | 6275/11066 [22:59<17:24,  4.59it/s]
 57%|█████▋    | 6276/11066 [22:59<17:22,  4.60it/s]
                                                    

 57%|█████▋    | 6276/11066 [22:59<17:22,  4.60it/s]
 57%|█████▋    | 6277/11066 [22:59<17:16,  4.62it/s]
                                                    

 57%|█████▋    | 6277/11066 [22:59<17:16,  4.62it/s]
 57%|█████▋    | 6278/11066 [22:59<17:28,  4.57it/s]
                                                    

 57%|█████▋    | 6278/11066 [22:59<17:28,  4.57it/s]
 57%|█████▋    | 6279/11066 [23:00<17:37,  4.52it/s]
                                                    

 57%|█████▋    | 6279/11066 [23:00<17:37,  4.52it/s]
 57%|█████▋    | 6280/11066 [23:00<17:41,  4.51it/s]
                                                    

 57%|█████▋    | 6280/11066 [23:00<17:41,  4.51it/s]
 57%|█████▋    | 6281/11066 [23:00<17:41,  4.51it/s]
                                                    

 57%|█████▋    | 6281/11066 [23:00<17:41,  4.51it/s]
 57%|█████▋    | 6282/11066 [23:00<17:58,  4.44it/s]
                                                    

 57%|█████▋    | 6282/11066 [23:00<17:58,  4.44it/s]
 57%|█████▋    | 6283/11066 [23:00<18:03,  4.41it/s]
                                                    

 57%|█████▋    | 6283/11066 [23:00<18:03,  4.41it/s]
 57%|█████▋    | 6284/11066 [23:01<17:59,  4.43it/s]
                                                    

 57%|█████▋    | 6284/11066 [23:01<17:59,  4.43it/s]
 57%|█████▋    | 6285/11066 [23:01<17:54,  4.45it/s]
                                                    

 57%|█████▋    | 6285/11066 [23:01<17:54,  4.45it/s]
 57%|█████▋    | 6286/11066 [23:01<17:55,  4.44it/s]
                                                    

 57%|█████▋    | 6286/11066 [23:01<17:55,  4.44it/s]
 57%|█████▋    | 6287/11066 [23:01<18:02,  4.42it/s]
                                                    

 57%|█████▋    | 6287/11066 [23:01<18:02,  4.42it/s]
 57%|█████▋    | 6288/11066 [23:02<17:59,  4.42it/s]
                                                    

 57%|█████▋    | 6288/11066 [23:02<17:59,  4.42it/s]
 57%|█████▋    | 6289/11066 [23:02<18:10,  4.38it/s]
                                                    

 57%|█████▋    | 6289/11066 [23:02<18:10,  4.38it/s]
 57%|█████▋    | 6290/11066 [23:02<18:06,  4.40it/s]
                                                    

 57%|█████▋    | 6290/11066 [23:02<18:06,  4.40it/s]
 57%|█████▋    | 6291/11066 [23:02<18:01,  4.42it/s]
                                                    

 57%|█████▋    | 6291/11066 [23:02<18:01,  4.42it/s]
 57%|█████▋    | 6292/11066 [23:03<17:56,  4.43it/s]
                                                    

 57%|█████▋    | 6292/11066 [23:03<17:56,  4.43it/s]
 57%|█████▋    | 6293/11066 [23:03<17:53,  4.45it/s]
                                                    

 57%|█████▋    | 6293/11066 [23:03<17:53,  4.45it/s]
 57%|█████▋    | 6294/11066 [23:03<17:41,  4.50it/s]
                                                    

 57%|█████▋    | 6294/11066 [23:03<17:41,  4.50it/s]
 57%|█████▋    | 6295/11066 [23:03<17:36,  4.52it/s]
                                                    

 57%|█████▋    | 6295/11066 [23:03<17:36,  4.52it/s]
 57%|█████▋    | 6296/11066 [23:03<17:37,  4.51it/s]
                                                    

 57%|█████▋    | 6296/11066 [23:03<17:37,  4.51it/s]
 57%|█████▋    | 6297/11066 [23:04<17:29,  4.54it/s]
                                                    

 57%|█████▋    | 6297/11066 [23:04<17:29,  4.54it/s]
 57%|█████▋    | 6298/11066 [23:04<17:20,  4.58it/s]
                                                    

 57%|█████▋    | 6298/11066 [23:04<17:20,  4.58it/s]
 57%|█████▋    | 6299/11066 [23:04<17:17,  4.59it/s]
                                                    

 57%|█████▋    | 6299/11066 [23:04<17:17,  4.59it/s]
 57%|█████▋    | 6300/11066 [23:04<17:15,  4.60it/s]
                                                    
{'loss': 1.1071, 'learning_rate': 1.3224290619916862e-05, 'epoch': 1.12}
{'loss': 0.9466, 'learning_rate': 1.3221579613229714e-05, 'epoch': 1.12}
{'loss': 0.5926, 'learning_rate': 1.3218868606542562e-05, 'epoch': 1.12}
{'loss': 0.4299, 'learning_rate': 1.3216157599855412e-05, 'epoch': 1.12}
{'loss': 0.6417, 'learning_rate': 1.3213446593168264e-05, 'epoch': 1.12}
{'loss': 1.1849, 'learning_rate': 1.3210735586481114e-05, 'epoch': 1.12}
{'loss': 0.8757, 'learning_rate': 1.3208024579793963e-05, 'epoch': 1.12}
{'loss': 0.64, 'learning_rate': 1.3205313573106813e-05, 'epoch': 1.12}
{'loss': 0.8668, 'learning_rate': 1.3202602566419665e-05, 'epoch': 1.12}
{'loss': 0.737, 'learning_rate': 1.3199891559732515e-05, 'epoch': 1.12}
{'loss': 0.9014, 'learning_rate': 1.3197180553045363e-05, 'epoch': 1.12}
{'loss': 0.8172, 'learning_rate': 1.3194469546358214e-05, 'epoch': 1.12}
{'loss': 0.5132, 'learning_rate': 1.3191758539671065e-05, 'epoch': 1.12}
{'loss': 0.8469, 'learning_rate': 1.3189047532983915e-05, 'epoch': 1.12}
{'loss': 0.4232, 'learning_rate': 1.3186336526296764e-05, 'epoch': 1.12}
{'loss': 0.9239, 'learning_rate': 1.3183625519609616e-05, 'epoch': 1.12}
{'loss': 0.89, 'learning_rate': 1.3180914512922466e-05, 'epoch': 1.12}
{'loss': 0.7265, 'learning_rate': 1.3178203506235316e-05, 'epoch': 1.12}
{'loss': 0.3803, 'learning_rate': 1.3175492499548164e-05, 'epoch': 1.12}
{'loss': 0.5901, 'learning_rate': 1.3172781492861016e-05, 'epoch': 1.12}
{'loss': 1.5071, 'learning_rate': 1.3170070486173866e-05, 'epoch': 1.12}
{'loss': 0.3956, 'learning_rate': 1.3167359479486717e-05, 'epoch': 1.12}
{'loss': 0.8102, 'learning_rate': 1.3164648472799567e-05, 'epoch': 1.12}
{'loss': 1.1202, 'learning_rate': 1.3161937466112417e-05, 'epoch': 1.12}
{'loss': 0.997, 'learning_rate': 1.3159226459425267e-05, 'epoch': 1.12}
{'loss': 0.48, 'learning_rate': 1.3156515452738117e-05, 'epoch': 1.12}
{'loss': 1.0016, 'learning_rate': 1.3153804446050967e-05, 'epoch': 1.12}
{'loss': 0.8513, 'learning_rate': 1.3151093439363817e-05, 'epoch': 1.12}
{'loss': 1.1349, 'learning_rate': 1.3148382432676668e-05, 'epoch': 1.12}
{'loss': 0.3783, 'learning_rate': 1.3145671425989518e-05, 'epoch': 1.12}
{'loss': 0.7984, 'learning_rate': 1.3142960419302368e-05, 'epoch': 1.12}
{'loss': 1.0478, 'learning_rate': 1.3140249412615218e-05, 'epoch': 1.12}
{'loss': 1.3222, 'learning_rate': 1.3137538405928068e-05, 'epoch': 1.12}
{'loss': 0.928, 'learning_rate': 1.313482739924092e-05, 'epoch': 1.12}
{'loss': 0.7064, 'learning_rate': 1.3132116392553768e-05, 'epoch': 1.12}
{'loss': 0.7003, 'learning_rate': 1.3129405385866618e-05, 'epoch': 1.12}
{'loss': 0.7898, 'learning_rate': 1.3126694379179469e-05, 'epoch': 1.12}
{'loss': 0.7026, 'learning_rate': 1.312398337249232e-05, 'epoch': 1.13}
{'loss': 0.3694, 'learning_rate': 1.3121272365805169e-05, 'epoch': 1.13}
{'loss': 0.8476, 'learning_rate': 1.3118561359118019e-05, 'epoch': 1.13}
{'loss': 0.3128, 'learning_rate': 1.3115850352430869e-05, 'epoch': 1.13}
{'loss': 1.4827, 'learning_rate': 1.3113139345743721e-05, 'epoch': 1.13}
{'loss': 1.1308, 'learning_rate': 1.311042833905657e-05, 'epoch': 1.13}
{'loss': 0.5603, 'learning_rate': 1.310771733236942e-05, 'epoch': 1.13}
{'loss': 1.3545, 'learning_rate': 1.3105006325682271e-05, 'epoch': 1.13}
{'loss': 0.6076, 'learning_rate': 1.3102295318995121e-05, 'epoch': 1.13}
{'loss': 0.7324, 'learning_rate': 1.309958431230797e-05, 'epoch': 1.13}
{'loss': 0.6979, 'learning_rate': 1.309687330562082e-05, 'epoch': 1.13}
{'loss': 0.8522, 'learning_rate': 1.3094162298933672e-05, 'epoch': 1.13}
{'loss': 1.0198, 'learning_rate': 1.3091451292246522e-05, 'epoch': 1.13}
{'loss': 0.6362, 'learning_rate': 1.308874028555937e-05, 'epoch': 1.13}
{'loss': 1.034, 'learning_rate': 1.308602927887222e-05, 'epoch': 1.13}
{'loss': 0.3182, 'learning_rate': 1.3083318272185072e-05, 'epoch': 1.13}
{'loss': 0.5005, 'learning_rate': 1.3080607265497923e-05, 'epoch': 1.13}
{'loss': 0.6326, 'learning_rate': 1.3077896258810771e-05, 'epoch': 1.13}
{'loss': 0.9357, 'learning_rate': 1.3075185252123623e-05, 'epoch': 1.13}
{'loss': 1.2534, 'learning_rate': 1.3072474245436473e-05, 'epoch': 1.13}
{'loss': 0.3894, 'learning_rate': 1.3069763238749323e-05, 'epoch': 1.13}
{'loss': 0.6693, 'learning_rate': 1.3067052232062172e-05, 'epoch': 1.13}
{'loss': 0.678, 'learning_rate': 1.3064341225375023e-05, 'epoch': 1.13}
{'loss': 0.8112, 'learning_rate': 1.3061630218687873e-05, 'epoch': 1.13}
{'loss': 0.5743, 'learning_rate': 1.3058919212000724e-05, 'epoch': 1.13}
{'loss': 1.0898, 'learning_rate': 1.3056208205313572e-05, 'epoch': 1.13}
{'loss': 1.0544, 'learning_rate': 1.3053497198626424e-05, 'epoch': 1.13}
{'loss': 0.706, 'learning_rate': 1.3050786191939274e-05, 'epoch': 1.13}
{'loss': 0.5533, 'learning_rate': 1.3048075185252124e-05, 'epoch': 1.13}
{'loss': 0.9592, 'learning_rate': 1.3045364178564974e-05, 'epoch': 1.13}
{'loss': 0.9352, 'learning_rate': 1.3042653171877824e-05, 'epoch': 1.13}
{'loss': 0.6091, 'learning_rate': 1.3039942165190675e-05, 'epoch': 1.13}
{'loss': 0.7162, 'learning_rate': 1.3037231158503525e-05, 'epoch': 1.13}
{'loss': 0.3892, 'learning_rate': 1.3034520151816375e-05, 'epoch': 1.13}
{'loss': 0.74, 'learning_rate': 1.3031809145129225e-05, 'epoch': 1.13}
{'loss': 0.8499, 'learning_rate': 1.3029098138442075e-05, 'epoch': 1.13}
{'loss': 0.7854, 'learning_rate': 1.3026387131754925e-05, 'epoch': 1.13}
{'loss': 0.9418, 'learning_rate': 1.3023676125067775e-05, 'epoch': 1.13}
{'loss': 0.6984, 'learning_rate': 1.3020965118380626e-05, 'epoch': 1.13}
{'loss': 0.9513, 'learning_rate': 1.3018254111693476e-05, 'epoch': 1.13}
{'loss': 0.796, 'learning_rate': 1.3015543105006327e-05, 'epoch': 1.13}
{'loss': 0.7072, 'learning_rate': 1.3012832098319176e-05, 'epoch': 1.13}
{'loss': 0.7162, 'learning_rate': 1.3010121091632026e-05, 'epoch': 1.13}
{'loss': 1.3401, 'learning_rate': 1.3007410084944876e-05, 'epoch': 1.13}
{'loss': 0.4969, 'learning_rate': 1.3004699078257728e-05, 'epoch': 1.13}
{'loss': 0.7597, 'learning_rate': 1.3001988071570576e-05, 'epoch': 1.13}
{'loss': 0.6423, 'learning_rate': 1.2999277064883427e-05, 'epoch': 1.13}
{'loss': 0.8652, 'learning_rate': 1.2996566058196277e-05, 'epoch': 1.13}
{'loss': 0.6046, 'learning_rate': 1.2993855051509129e-05, 'epoch': 1.13}
{'loss': 0.7569, 'learning_rate': 1.2991144044821977e-05, 'epoch': 1.13}
{'loss': 0.6642, 'learning_rate': 1.2988433038134827e-05, 'epoch': 1.13}
{'loss': 0.891, 'learning_rate': 1.2985722031447679e-05, 'epoch': 1.13}
{'loss': 1.1957, 'learning_rate': 1.2983011024760529e-05, 'epoch': 1.13}
{'loss': 1.2995, 'learning_rate': 1.2980300018073378e-05, 'epoch': 1.13}
{'loss': 0.5969, 'learning_rate': 1.2977589011386228e-05, 'epoch': 1.13}
{'loss': 1.0949, 'learning_rate': 1.297487800469908e-05, 'epoch': 1.14}
{'loss': 0.6796, 'learning_rate': 1.297216699801193e-05, 'epoch': 1.14}
{'loss': 0.7334, 'learning_rate': 1.2969455991324778e-05, 'epoch': 1.14}
{'loss': 0.6799, 'learning_rate': 1.2966744984637628e-05, 'epoch': 1.14}
{'loss': 0.4949, 'learning_rate': 1.296403397795048e-05, 'epoch': 1.14}
{'loss': 0.9708, 'learning_rate': 1.296132297126333e-05, 'epoch': 1.14}
{'loss': 1.0362, 'learning_rate': 1.2958611964576179e-05, 'epoch': 1.14}
{'loss': 0.7686, 'learning_rate': 1.295590095788903e-05, 'epoch': 1.14}
{'loss': 1.1834, 'learning_rate': 1.295318995120188e-05, 'epoch': 1.14}
{'loss': 0.8694, 'learning_rate': 1.295047894451473e-05, 'epoch': 1.14}
{'loss': 0.6905, 'learning_rate': 1.2947767937827579e-05, 'epoch': 1.14}
{'loss': 0.835, 'learning_rate': 1.2945056931140431e-05, 'epoch': 1.14}
{'loss': 0.4318, 'learning_rate': 1.2942345924453281e-05, 'epoch': 1.14}
{'loss': 0.4647, 'learning_rate': 1.2939634917766131e-05, 'epoch': 1.14}
{'loss': 0.5753, 'learning_rate': 1.2936923911078981e-05, 'epoch': 1.14}
{'loss': 0.7272, 'learning_rate': 1.2934212904391831e-05, 'epoch': 1.14}
{'loss': 1.1073, 'learning_rate': 1.2931501897704682e-05, 'epoch': 1.14}
{'loss': 0.6738, 'learning_rate': 1.2928790891017532e-05, 'epoch': 1.14}
{'loss': 0.6608, 'learning_rate': 1.2926079884330382e-05, 'epoch': 1.14}
{'loss': 0.7425, 'learning_rate': 1.2923368877643232e-05, 'epoch': 1.14}

 57%|█████▋    | 6300/11066 [23:04<17:15,  4.60it/s]
 57%|█████▋    | 6301/11066 [23:04<17:18,  4.59it/s]
                                                    

 57%|█████▋    | 6301/11066 [23:04<17:18,  4.59it/s]
 57%|█████▋    | 6302/11066 [23:05<17:15,  4.60it/s]
                                                    

 57%|█████▋    | 6302/11066 [23:05<17:15,  4.60it/s]
 57%|█████▋    | 6303/11066 [23:05<17:10,  4.62it/s]
                                                    

 57%|█████▋    | 6303/11066 [23:05<17:10,  4.62it/s]
 57%|█████▋    | 6304/11066 [23:05<17:17,  4.59it/s]
                                                    

 57%|█████▋    | 6304/11066 [23:05<17:17,  4.59it/s]
 57%|█████▋    | 6305/11066 [23:05<17:24,  4.56it/s]
                                                    

 57%|█████▋    | 6305/11066 [23:05<17:24,  4.56it/s]
 57%|█████▋    | 6306/11066 [23:06<17:33,  4.52it/s]
                                                    

 57%|█████▋    | 6306/11066 [23:06<17:33,  4.52it/s]
 57%|█████▋    | 6307/11066 [23:06<17:37,  4.50it/s]
                                                    

 57%|█████▋    | 6307/11066 [23:06<17:37,  4.50it/s]
 57%|█████▋    | 6308/11066 [23:06<17:37,  4.50it/s]
                                                    

 57%|█████▋    | 6308/11066 [23:06<17:37,  4.50it/s]
 57%|█████▋    | 6309/11066 [23:06<17:38,  4.49it/s]
                                                    

 57%|█████▋    | 6309/11066 [23:06<17:38,  4.49it/s]
 57%|█████▋    | 6310/11066 [23:06<17:40,  4.49it/s]
                                                    

 57%|█████▋    | 6310/11066 [23:06<17:40,  4.49it/s]
 57%|█████▋    | 6311/11066 [23:07<17:40,  4.48it/s]
                                                    

 57%|█████▋    | 6311/11066 [23:07<17:40,  4.48it/s]
 57%|█████▋    | 6312/11066 [23:07<17:34,  4.51it/s]
                                                    

 57%|█████▋    | 6312/11066 [23:07<17:34,  4.51it/s]
 57%|█████▋    | 6313/11066 [23:07<17:36,  4.50it/s]
                                                    

 57%|█████▋    | 6313/11066 [23:07<17:36,  4.50it/s]
 57%|█████▋    | 6314/11066 [23:07<17:36,  4.50it/s]
                                                    

 57%|█████▋    | 6314/11066 [23:07<17:36,  4.50it/s]
 57%|█████▋    | 6315/11066 [23:08<17:37,  4.49it/s]
                                                    

 57%|█████▋    | 6315/11066 [23:08<17:37,  4.49it/s]
 57%|█████▋    | 6316/11066 [23:08<17:36,  4.49it/s]
                                                    

 57%|█████▋    | 6316/11066 [23:08<17:36,  4.49it/s]
 57%|█████▋    | 6317/11066 [23:08<17:35,  4.50it/s]
                                                    

 57%|█████▋    | 6317/11066 [23:08<17:35,  4.50it/s]
 57%|█████▋    | 6318/11066 [23:08<17:35,  4.50it/s]
                                                    

 57%|█████▋    | 6318/11066 [23:08<17:35,  4.50it/s]
 57%|█████▋    | 6319/11066 [23:08<17:36,  4.49it/s]
                                                    

 57%|█████▋    | 6319/11066 [23:08<17:36,  4.49it/s]
 57%|█████▋    | 6320/11066 [23:09<17:18,  4.57it/s]
                                                    

 57%|█████▋    | 6320/11066 [23:09<17:18,  4.57it/s]
 57%|█████▋    | 6321/11066 [23:09<17:25,  4.54it/s]
                                                    

 57%|█████▋    | 6321/11066 [23:09<17:25,  4.54it/s]
 57%|█████▋    | 6322/11066 [23:09<17:22,  4.55it/s]
                                                    

 57%|█████▋    | 6322/11066 [23:09<17:22,  4.55it/s]
 57%|█████▋    | 6323/11066 [23:09<17:23,  4.54it/s]
                                                    

 57%|█████▋    | 6323/11066 [23:09<17:23,  4.54it/s]
 57%|█████▋    | 6324/11066 [23:10<17:21,  4.55it/s]
                                                    

 57%|█████▋    | 6324/11066 [23:10<17:21,  4.55it/s]
 57%|█████▋    | 6325/11066 [23:10<17:17,  4.57it/s]
                                                    

 57%|█████▋    | 6325/11066 [23:10<17:17,  4.57it/s]
 57%|█████▋    | 6326/11066 [23:10<17:09,  4.60it/s]
                                                    

 57%|█████▋    | 6326/11066 [23:10<17:09,  4.60it/s]
 57%|█████▋    | 6327/11066 [23:10<17:12,  4.59it/s]
                                                    

 57%|█████▋    | 6327/11066 [23:10<17:12,  4.59it/s]
 57%|█████▋    | 6328/11066 [23:10<17:09,  4.60it/s]
                                                    

 57%|█████▋    | 6328/11066 [23:10<17:09,  4.60it/s]
 57%|█████▋    | 6329/11066 [23:11<17:19,  4.56it/s]
                                                    

 57%|█████▋    | 6329/11066 [23:11<17:19,  4.56it/s]
 57%|█████▋    | 6330/11066 [23:11<17:17,  4.57it/s]
                                                    

 57%|█████▋    | 6330/11066 [23:11<17:17,  4.57it/s]
 57%|█████▋    | 6331/11066 [23:11<17:07,  4.61it/s]
                                                    

 57%|█████▋    | 6331/11066 [23:11<17:07,  4.61it/s]
 57%|█████▋    | 6332/11066 [23:11<17:14,  4.58it/s]
                                                    

 57%|█████▋    | 6332/11066 [23:11<17:14,  4.58it/s]
 57%|█████▋    | 6333/11066 [23:12<17:12,  4.58it/s]
                                                    

 57%|█████▋    | 6333/11066 [23:12<17:12,  4.58it/s]
 57%|█████▋    | 6334/11066 [23:12<17:21,  4.54it/s]
                                                    

 57%|█████▋    | 6334/11066 [23:12<17:21,  4.54it/s]
 57%|█████▋    | 6335/11066 [23:12<17:19,  4.55it/s]
                                                    

 57%|█████▋    | 6335/11066 [23:12<17:19,  4.55it/s]
 57%|█████▋    | 6336/11066 [23:12<17:07,  4.60it/s]
                                                    

 57%|█████▋    | 6336/11066 [23:12<17:07,  4.60it/s]
 57%|█████▋    | 6337/11066 [23:12<17:06,  4.61it/s]
                                                    

 57%|█████▋    | 6337/11066 [23:12<17:06,  4.61it/s]
 57%|█████▋    | 6338/11066 [23:13<17:17,  4.56it/s]
                                                    

 57%|█████▋    | 6338/11066 [23:13<17:17,  4.56it/s]
 57%|█████▋    | 6339/11066 [23:13<17:24,  4.53it/s]
                                                    

 57%|█████▋    | 6339/11066 [23:13<17:24,  4.53it/s]
 57%|█████▋    | 6340/11066 [23:13<17:11,  4.58it/s]
                                                    

 57%|█████▋    | 6340/11066 [23:13<17:11,  4.58it/s]
 57%|█████▋    | 6341/11066 [23:13<17:10,  4.59it/s]
                                                    

 57%|█████▋    | 6341/11066 [23:13<17:10,  4.59it/s]
 57%|█████▋    | 6342/11066 [23:13<17:01,  4.63it/s]
                                                    

 57%|█████▋    | 6342/11066 [23:13<17:01,  4.63it/s]
 57%|█████▋    | 6343/11066 [23:14<16:49,  4.68it/s]
                                                    

 57%|█████▋    | 6343/11066 [23:14<16:49,  4.68it/s]
 57%|█████▋    | 6344/11066 [23:14<16:55,  4.65it/s]
                                                    

 57%|█████▋    | 6344/11066 [23:14<16:55,  4.65it/s]
 57%|█████▋    | 6345/11066 [23:14<16:58,  4.64it/s]
                                                    

 57%|█████▋    | 6345/11066 [23:14<16:58,  4.64it/s]
 57%|█████▋    | 6346/11066 [23:14<16:52,  4.66it/s]
                                                    

 57%|█████▋    | 6346/11066 [23:14<16:52,  4.66it/s]
 57%|█████▋    | 6347/11066 [23:15<17:05,  4.60it/s]
                                                    

 57%|█████▋    | 6347/11066 [23:15<17:05,  4.60it/s]
 57%|█████▋    | 6348/11066 [23:15<17:16,  4.55it/s]
                                                    

 57%|█████▋    | 6348/11066 [23:15<17:16,  4.55it/s]
 57%|█████▋    | 6349/11066 [23:15<17:33,  4.48it/s]
                                                    

 57%|█████▋    | 6349/11066 [23:15<17:33,  4.48it/s]
 57%|█████▋    | 6350/11066 [23:15<17:44,  4.43it/s]
                                                    

 57%|█████▋    | 6350/11066 [23:15<17:44,  4.43it/s]
 57%|█████▋    | 6351/11066 [23:15<17:46,  4.42it/s]
                                                    

 57%|█████▋    | 6351/11066 [23:15<17:46,  4.42it/s]
 57%|█████▋    | 6352/11066 [23:16<17:37,  4.46it/s]
                                                    

 57%|█████▋    | 6352/11066 [23:16<17:37,  4.46it/s]
 57%|█████▋    | 6353/11066 [23:16<17:33,  4.47it/s]
                                                    

 57%|█████▋    | 6353/11066 [23:16<17:33,  4.47it/s]
 57%|█████▋    | 6354/11066 [23:16<17:31,  4.48it/s]
                                                    

 57%|█████▋    | 6354/11066 [23:16<17:31,  4.48it/s]
 57%|█████▋    | 6355/11066 [23:16<17:30,  4.49it/s]
                                                    

 57%|█████▋    | 6355/11066 [23:16<17:30,  4.49it/s]
 57%|█████▋    | 6356/11066 [23:17<17:29,  4.49it/s]
                                                    

 57%|█████▋    | 6356/11066 [23:17<17:29,  4.49it/s]
 57%|█████▋    | 6357/11066 [23:17<17:30,  4.48it/s]
                                                    

 57%|█████▋    | 6357/11066 [23:17<17:30,  4.48it/s]
 57%|█████▋    | 6358/11066 [23:17<17:29,  4.49it/s]
                                                    

 57%|█████▋    | 6358/11066 [23:17<17:29,  4.49it/s]
 57%|█████▋    | 6359/11066 [23:17<17:28,  4.49it/s]
                                                    

 57%|█████▋    | 6359/11066 [23:17<17:28,  4.49it/s]
 57%|█████▋    | 6360/11066 [23:17<17:29,  4.49it/s]
                                                    

 57%|█████▋    | 6360/11066 [23:17<17:29,  4.49it/s]
 57%|█████▋    | 6361/11066 [23:18<17:32,  4.47it/s]
                                                    

 57%|█████▋    | 6361/11066 [23:18<17:32,  4.47it/s]
 57%|█████▋    | 6362/11066 [23:18<17:34,  4.46it/s]
                                                    

 57%|█████▋    | 6362/11066 [23:18<17:34,  4.46it/s]
 58%|█████▊    | 6363/11066 [23:18<17:32,  4.47it/s]
                                                    

 58%|█████▊    | 6363/11066 [23:18<17:32,  4.47it/s]
 58%|█████▊    | 6364/11066 [23:18<17:21,  4.51it/s]
                                                    

 58%|█████▊    | 6364/11066 [23:18<17:21,  4.51it/s]
 58%|█████▊    | 6365/11066 [23:19<17:26,  4.49it/s]
                                                    

 58%|█████▊    | 6365/11066 [23:19<17:26,  4.49it/s]
 58%|█████▊    | 6366/11066 [23:19<17:27,  4.49it/s]
                                                    

 58%|█████▊    | 6366/11066 [23:19<17:27,  4.49it/s]
 58%|█████▊    | 6367/11066 [23:19<17:27,  4.49it/s]
                                                    

 58%|█████▊    | 6367/11066 [23:19<17:27,  4.49it/s]
 58%|█████▊    | 6368/11066 [23:19<17:25,  4.49it/s]
                                                    

 58%|█████▊    | 6368/11066 [23:19<17:25,  4.49it/s]
 58%|█████▊    | 6369/11066 [23:19<17:23,  4.50it/s]
                                                    

 58%|█████▊    | 6369/11066 [23:19<17:23,  4.50it/s]
 58%|█████▊    | 6370/11066 [23:20<17:23,  4.50it/s]
                                                    

 58%|█████▊    | 6370/11066 [23:20<17:23,  4.50it/s]
 58%|█████▊    | 6371/11066 [23:20<17:22,  4.50it/s]
                                                    

 58%|█████▊    | 6371/11066 [23:20<17:22,  4.50it/s]
 58%|█████▊    | 6372/11066 [23:20<17:22,  4.50it/s]
                                                    

 58%|█████▊    | 6372/11066 [23:20<17:22,  4.50it/s]
 58%|█████▊    | 6373/11066 [23:20<17:21,  4.51it/s]
                                                    

 58%|█████▊    | 6373/11066 [23:20<17:21,  4.51it/s]
 58%|█████▊    | 6374/11066 [23:21<17:21,  4.51it/s]
                                                    

 58%|█████▊    | 6374/11066 [23:21<17:21,  4.51it/s]
 58%|█████▊    | 6375/11066 [23:21<17:22,  4.50it/s]
                                                    

 58%|█████▊    | 6375/11066 [23:21<17:22,  4.50it/s]
 58%|█████▊    | 6376/11066 [23:21<17:25,  4.49it/s]
                                                    

 58%|█████▊    | 6376/11066 [23:21<17:25,  4.49it/s]
 58%|█████▊    | 6377/11066 [23:21<17:28,  4.47it/s]
                                                    

 58%|█████▊    | 6377/11066 [23:21<17:28,  4.47it/s]
 58%|█████▊    | 6378/11066 [23:22<17:31,  4.46it/s]
                                                    

 58%|█████▊    | 6378/11066 [23:22<17:31,  4.46it/s]
 58%|█████▊    | 6379/11066 [23:22<17:08,  4.56it/s]
                                                    

 58%|█████▊    | 6379/11066 [23:22<17:08,  4.56it/s]
 58%|█████▊    | 6380/11066 [23:22<17:18,  4.51it/s]
                                                    

 58%|█████▊    | 6380/11066 [23:22<17:18,  4.51it/s]
 58%|█████▊    | 6381/11066 [23:22<17:20,  4.50it/s]
                                                    

 58%|█████▊    | 6381/11066 [23:22<17:20,  4.50it/s]
 58%|█████▊    | 6382/11066 [23:22<17:24,  4.48it/s]
                                                    

 58%|█████▊    | 6382/11066 [23:22<17:24,  4.48it/s]
 58%|█████▊    | 6383/11066 [23:23<17:14,  4.53it/s]
                                                    

 58%|█████▊    | 6383/11066 [23:23<17:14,  4.53it/s]
 58%|█████▊    | 6384/11066 [23:23<17:15,  4.52it/s]
                                                    

 58%|█████▊    | 6384/11066 [23:23<17:15,  4.52it/s]
 58%|█████▊    | 6385/11066 [23:23<17:03,  4.57it/s]
                                                    

 58%|█████▊    | 6385/11066 [23:23<17:03,  4.57it/s]
 58%|█████▊    | 6386/11066 [23:23<17:11,  4.54it/s]
                                                    

 58%|█████▊    | 6386/11066 [23:23<17:11,  4.54it/s]
 58%|█████▊    | 6387/11066 [23:23<16:59,  4.59it/s]
                                                    

 58%|█████▊    | 6387/11066 [23:23<16:59,  4.59it/s]
 58%|█████▊    | 6388/11066 [23:24<16:52,  4.62it/s]
                                                    

 58%|█████▊    | 6388/11066 [23:24<16:52,  4.62it/s]
 58%|█████▊    | 6389/11066 [23:24<16:47,  4.64it/s]
                                                    

 58%|█████▊    | 6389/11066 [23:24<16:47,  4.64it/s]
 58%|█████▊    | 6390/11066 [23:24<16:57,  4.60it/s]
                                                    

 58%|█████▊    | 6390/11066 [23:24<16:57,  4.60it/s]
 58%|█████▊    | 6391/11066 [23:24<16:57,  4.59it/s]
                                                    

 58%|█████▊    | 6391/11066 [23:24<16:57,  4.59it/s]
 58%|█████▊    | 6392/11066 [23:25<17:07,  4.55it/s]
                                                    

 58%|█████▊    | 6392/11066 [23:25<17:07,  4.55it/s]
 58%|█████▊    | 6393/11066 [23:25<16:58,  4.59it/s]
                                                    

 58%|█████▊    | 6393/11066 [23:25<16:58,  4.59it/s]
 58%|█████▊    | 6394/11066 [23:25<17:04,  4.56it/s]
                                                    

 58%|█████▊    | 6394/11066 [23:25<17:04,  4.56it/s]
 58%|█████▊    | 6395/11066 [23:25<17:10,  4.53it/s]
                                                    

 58%|█████▊    | 6395/11066 [23:25<17:10,  4.53it/s]
 58%|█████▊    | 6396/11066 [23:25<17:12,  4.52it/s]
                                                    

 58%|█████▊    | 6396/11066 [23:25<17:12,  4.52it/s]
 58%|█████▊    | 6397/11066 [23:26<17:14,  4.52it/s]
                                                    

 58%|█████▊    | 6397/11066 [23:26<17:14,  4.52it/s]
 58%|█████▊    | 6398/11066 [23:26<17:15,  4.51it/s]
                                                    

 58%|█████▊    | 6398/11066 [23:26<17:15,  4.51it/s]
 58%|█████▊    | 6399/11066 [23:26<17:08,  4.54it/s]
                                                    

 58%|█████▊    | 6399/11066 [23:26<17:08,  4.54it/s]
 58%|█████▊    | 6400/11066 [23:26<17:01,  4.57it/s]
                                                    

 58%|█████▊    | 6400/11066 [23:26<17:01,  4.57it/s]
 58%|█████▊    | 6401/11066 [23:27<16:55,  4.59it/s]
                                                    

 58%|█████▊    | 6401/11066 [23:27<16:55,  4.59it/s]
 58%|█████▊    | 6402/11066 [23:27<17:04,  4.55it/s]
                                                    

 58%|█████▊    | 6402/11066 [23:27<17:04,  4.55it/s]
 58%|█████▊    | 6403/11066 [23:27<17:00,  4.57it/s]
                                                    

 58%|█████▊    | 6403/11066 [23:27<17:00,  4.57it/s]
 58%|█████▊    | 6404/11066 [23:27<17:11,  4.52it/s]
                                                    

 58%|█████▊    | 6404/11066 [23:27<17:11,  4.52it/s]
 58%|█████▊    | 6405/11066 [23:27<17:14,  4.51it/s]
                                                    

 58%|█████▊    | 6405/11066 [23:27<17:14,  4.51it/s]
 58%|█████▊    | 6406/11066 [23:28<17:15,  4.50it/s]
                                                    

 58%|█████▊    | 6406/11066 [23:28<17:15,  4.50it/s]
 58%|█████▊    | 6407/11066 [23:28<17:28,  4.45it/s]
                                                    

 58%|█████▊    | 6407/11066 [23:28<17:28,  4.45it/s]
 58%|█████▊    | 6408/11066 [23:28<17:24,  4.46it/s]
                                                    

 58%|█████▊    | 6408/11066 [23:28<17:24,  4.46it/s]
 58%|█████▊    | 6409/11066 [23:28<17:13,  4.51it/s]
                                                    

 58%|█████▊    | 6409/11066 [23:28<17:13,  4.51it/s]
 58%|█████▊    | 6410/11066 [23:29<17:10,  4.52it/s]
                                                    

 58%|█████▊    | 6410/11066 [23:29<17:10,  4.52it/s]
 58%|█████▊    | 6411/11066 [23:29<17:11,  4.51it/s]
                                                    

 58%|█████▊    | 6411/11066 [23:29<17:11,  4.51it/s]
 58%|█████▊    | 6412/11066 [23:29<16:58,  4.57it/s]
                                                    
{'loss': 1.1392, 'learning_rate': 1.2920657870956082e-05, 'epoch': 1.14}
{'loss': 0.8794, 'learning_rate': 1.2917946864268932e-05, 'epoch': 1.14}
{'loss': 0.8214, 'learning_rate': 1.2915235857581782e-05, 'epoch': 1.14}
{'loss': 1.2687, 'learning_rate': 1.2912524850894633e-05, 'epoch': 1.14}
{'loss': 0.3708, 'learning_rate': 1.2909813844207483e-05, 'epoch': 1.14}
{'loss': 0.6483, 'learning_rate': 1.2907102837520335e-05, 'epoch': 1.14}
{'loss': 1.102, 'learning_rate': 1.2904391830833183e-05, 'epoch': 1.14}
{'loss': 0.4869, 'learning_rate': 1.2901680824146033e-05, 'epoch': 1.14}
{'loss': 0.4796, 'learning_rate': 1.2898969817458883e-05, 'epoch': 1.14}
{'loss': 0.9457, 'learning_rate': 1.2896258810771733e-05, 'epoch': 1.14}
{'loss': 0.8779, 'learning_rate': 1.2893547804084584e-05, 'epoch': 1.14}
{'loss': 0.8772, 'learning_rate': 1.2890836797397434e-05, 'epoch': 1.14}
{'loss': 1.5246, 'learning_rate': 1.2888125790710284e-05, 'epoch': 1.14}
{'loss': 0.7619, 'learning_rate': 1.2885414784023134e-05, 'epoch': 1.14}
{'loss': 0.5698, 'learning_rate': 1.2882703777335984e-05, 'epoch': 1.14}
{'loss': 0.7231, 'learning_rate': 1.2879992770648834e-05, 'epoch': 1.14}
{'loss': 0.3488, 'learning_rate': 1.2877281763961686e-05, 'epoch': 1.14}
{'loss': 0.8592, 'learning_rate': 1.2874570757274534e-05, 'epoch': 1.14}
{'loss': 0.4722, 'learning_rate': 1.2871859750587385e-05, 'epoch': 1.14}
{'loss': 1.2459, 'learning_rate': 1.2869148743900235e-05, 'epoch': 1.14}
{'loss': 1.3073, 'learning_rate': 1.2866437737213087e-05, 'epoch': 1.14}
{'loss': 0.5651, 'learning_rate': 1.2863726730525935e-05, 'epoch': 1.14}
{'loss': 0.7705, 'learning_rate': 1.2861015723838785e-05, 'epoch': 1.14}
{'loss': 1.2908, 'learning_rate': 1.2858304717151635e-05, 'epoch': 1.14}
{'loss': 0.5805, 'learning_rate': 1.2855593710464487e-05, 'epoch': 1.14}
{'loss': 0.9386, 'learning_rate': 1.2852882703777336e-05, 'epoch': 1.14}
{'loss': 0.9373, 'learning_rate': 1.2850171697090186e-05, 'epoch': 1.14}
{'loss': 0.759, 'learning_rate': 1.2847460690403037e-05, 'epoch': 1.14}
{'loss': 0.7463, 'learning_rate': 1.2844749683715888e-05, 'epoch': 1.14}
{'loss': 0.9098, 'learning_rate': 1.2842038677028736e-05, 'epoch': 1.14}
{'loss': 0.5634, 'learning_rate': 1.2839327670341586e-05, 'epoch': 1.14}
{'loss': 0.9679, 'learning_rate': 1.2836616663654438e-05, 'epoch': 1.14}
{'loss': 0.7109, 'learning_rate': 1.2833905656967288e-05, 'epoch': 1.14}
{'loss': 0.6662, 'learning_rate': 1.2831194650280137e-05, 'epoch': 1.14}
{'loss': 1.0887, 'learning_rate': 1.2828483643592987e-05, 'epoch': 1.14}
{'loss': 0.8073, 'learning_rate': 1.2825772636905839e-05, 'epoch': 1.14}
{'loss': 0.9684, 'learning_rate': 1.2823061630218689e-05, 'epoch': 1.15}
{'loss': 1.3566, 'learning_rate': 1.2820350623531537e-05, 'epoch': 1.15}
{'loss': 0.3994, 'learning_rate': 1.2817639616844389e-05, 'epoch': 1.15}
{'loss': 0.6194, 'learning_rate': 1.2814928610157239e-05, 'epoch': 1.15}
{'loss': 0.2282, 'learning_rate': 1.281221760347009e-05, 'epoch': 1.15}
{'loss': 0.3164, 'learning_rate': 1.2809506596782938e-05, 'epoch': 1.15}
{'loss': 0.8155, 'learning_rate': 1.280679559009579e-05, 'epoch': 1.15}
{'loss': 0.8004, 'learning_rate': 1.280408458340864e-05, 'epoch': 1.15}
{'loss': 0.4303, 'learning_rate': 1.280137357672149e-05, 'epoch': 1.15}
{'loss': 0.4617, 'learning_rate': 1.2798662570034338e-05, 'epoch': 1.15}
{'loss': 0.413, 'learning_rate': 1.279595156334719e-05, 'epoch': 1.15}
{'loss': 0.7791, 'learning_rate': 1.279324055666004e-05, 'epoch': 1.15}
{'loss': 1.0579, 'learning_rate': 1.279052954997289e-05, 'epoch': 1.15}
{'loss': 0.7867, 'learning_rate': 1.278781854328574e-05, 'epoch': 1.15}
{'loss': 0.7576, 'learning_rate': 1.278510753659859e-05, 'epoch': 1.15}
{'loss': 0.5292, 'learning_rate': 1.278239652991144e-05, 'epoch': 1.15}
{'loss': 0.8325, 'learning_rate': 1.277968552322429e-05, 'epoch': 1.15}
{'loss': 0.4815, 'learning_rate': 1.2776974516537141e-05, 'epoch': 1.15}
{'loss': 0.8654, 'learning_rate': 1.2774263509849991e-05, 'epoch': 1.15}
{'loss': 0.3588, 'learning_rate': 1.2771552503162841e-05, 'epoch': 1.15}
{'loss': 1.1332, 'learning_rate': 1.2768841496475691e-05, 'epoch': 1.15}
{'loss': 1.0681, 'learning_rate': 1.2766130489788542e-05, 'epoch': 1.15}
{'loss': 0.7456, 'learning_rate': 1.2763419483101392e-05, 'epoch': 1.15}
{'loss': 1.0204, 'learning_rate': 1.2760708476414242e-05, 'epoch': 1.15}
{'loss': 0.7675, 'learning_rate': 1.2757997469727094e-05, 'epoch': 1.15}
{'loss': 0.9255, 'learning_rate': 1.2755286463039942e-05, 'epoch': 1.15}
{'loss': 0.2724, 'learning_rate': 1.2752575456352792e-05, 'epoch': 1.15}
{'loss': 0.7007, 'learning_rate': 1.2749864449665642e-05, 'epoch': 1.15}
{'loss': 0.3575, 'learning_rate': 1.2747153442978494e-05, 'epoch': 1.15}
{'loss': 0.3988, 'learning_rate': 1.2744442436291343e-05, 'epoch': 1.15}
{'loss': 0.566, 'learning_rate': 1.2741731429604193e-05, 'epoch': 1.15}
{'loss': 0.7877, 'learning_rate': 1.2739020422917045e-05, 'epoch': 1.15}
{'loss': 0.4182, 'learning_rate': 1.2736309416229895e-05, 'epoch': 1.15}
{'loss': 0.3386, 'learning_rate': 1.2733598409542743e-05, 'epoch': 1.15}
{'loss': 0.5951, 'learning_rate': 1.2730887402855593e-05, 'epoch': 1.15}
{'loss': 0.3599, 'learning_rate': 1.2728176396168445e-05, 'epoch': 1.15}
{'loss': 0.8627, 'learning_rate': 1.2725465389481295e-05, 'epoch': 1.15}
{'loss': 0.6682, 'learning_rate': 1.2722754382794144e-05, 'epoch': 1.15}
{'loss': 0.8527, 'learning_rate': 1.2720043376106994e-05, 'epoch': 1.15}
{'loss': 0.8002, 'learning_rate': 1.2717332369419846e-05, 'epoch': 1.15}
{'loss': 0.3303, 'learning_rate': 1.2714621362732696e-05, 'epoch': 1.15}
{'loss': 0.3699, 'learning_rate': 1.2711910356045544e-05, 'epoch': 1.15}
{'loss': 1.0323, 'learning_rate': 1.2709199349358396e-05, 'epoch': 1.15}
{'loss': 1.1121, 'learning_rate': 1.2706488342671246e-05, 'epoch': 1.15}
{'loss': 0.6671, 'learning_rate': 1.2703777335984096e-05, 'epoch': 1.15}
{'loss': 0.4811, 'learning_rate': 1.2701066329296945e-05, 'epoch': 1.15}
{'loss': 0.3926, 'learning_rate': 1.2698355322609797e-05, 'epoch': 1.15}
{'loss': 0.6474, 'learning_rate': 1.2695644315922647e-05, 'epoch': 1.15}
{'loss': 0.5972, 'learning_rate': 1.2692933309235497e-05, 'epoch': 1.15}
{'loss': 0.5509, 'learning_rate': 1.2690222302548345e-05, 'epoch': 1.15}
{'loss': 0.4739, 'learning_rate': 1.2687511295861197e-05, 'epoch': 1.15}
{'loss': 0.4934, 'learning_rate': 1.2684800289174047e-05, 'epoch': 1.15}
{'loss': 1.1021, 'learning_rate': 1.2682089282486897e-05, 'epoch': 1.15}
{'loss': 0.3672, 'learning_rate': 1.2679378275799748e-05, 'epoch': 1.15}
{'loss': 0.8824, 'learning_rate': 1.2676667269112598e-05, 'epoch': 1.15}
{'loss': 0.8742, 'learning_rate': 1.2673956262425448e-05, 'epoch': 1.16}
{'loss': 1.605, 'learning_rate': 1.2671245255738298e-05, 'epoch': 1.16}
{'loss': 0.8753, 'learning_rate': 1.2668534249051148e-05, 'epoch': 1.16}
{'loss': 0.6917, 'learning_rate': 1.2665823242363998e-05, 'epoch': 1.16}
{'loss': 0.5042, 'learning_rate': 1.2663112235676848e-05, 'epoch': 1.16}
{'loss': 0.6785, 'learning_rate': 1.2660401228989698e-05, 'epoch': 1.16}
{'loss': 0.7277, 'learning_rate': 1.2657690222302549e-05, 'epoch': 1.16}
{'loss': 0.7969, 'learning_rate': 1.2654979215615399e-05, 'epoch': 1.16}
{'loss': 1.2634, 'learning_rate': 1.2652268208928249e-05, 'epoch': 1.16}
{'loss': 1.1243, 'learning_rate': 1.26495572022411e-05, 'epoch': 1.16}
{'loss': 1.0245, 'learning_rate': 1.2646846195553949e-05, 'epoch': 1.16}
{'loss': 0.6678, 'learning_rate': 1.26441351888668e-05, 'epoch': 1.16}
{'loss': 0.8244, 'learning_rate': 1.264142418217965e-05, 'epoch': 1.16}
{'loss': 0.5072, 'learning_rate': 1.2638713175492501e-05, 'epoch': 1.16}
{'loss': 1.0529, 'learning_rate': 1.263600216880535e-05, 'epoch': 1.16}
{'loss': 0.885, 'learning_rate': 1.26332911621182e-05, 'epoch': 1.16}
{'loss': 0.9148, 'learning_rate': 1.263058015543105e-05, 'epoch': 1.16}
{'loss': 0.9444, 'learning_rate': 1.2627869148743902e-05, 'epoch': 1.16}
{'loss': 0.4614, 'learning_rate': 1.262515814205675e-05, 'epoch': 1.16}
{'loss': 1.3502, 'learning_rate': 1.26224471353696e-05, 'epoch': 1.16}
{'loss': 0.6912, 'learning_rate': 1.2619736128682452e-05, 'epoch': 1.16}

 58%|█████▊    | 6412/11066 [23:29<16:58,  4.57it/s]
 58%|█████▊    | 6413/11066 [23:29<16:50,  4.61it/s]
                                                    

 58%|█████▊    | 6413/11066 [23:29<16:50,  4.61it/s]
 58%|█████▊    | 6414/11066 [23:29<16:44,  4.63it/s]
                                                    

 58%|█████▊    | 6414/11066 [23:29<16:44,  4.63it/s]
 58%|█████▊    | 6415/11066 [23:30<16:40,  4.65it/s]
                                                    

 58%|█████▊    | 6415/11066 [23:30<16:40,  4.65it/s]
 58%|█████▊    | 6416/11066 [23:30<16:46,  4.62it/s]
                                                    

 58%|█████▊    | 6416/11066 [23:30<16:46,  4.62it/s]
 58%|█████▊    | 6417/11066 [23:30<16:49,  4.60it/s]
                                                    

 58%|█████▊    | 6417/11066 [23:30<16:49,  4.60it/s]
 58%|█████▊    | 6418/11066 [23:30<16:58,  4.56it/s]
                                                    

 58%|█████▊    | 6418/11066 [23:30<16:58,  4.56it/s]
 58%|█████▊    | 6419/11066 [23:30<16:55,  4.58it/s]
                                                    

 58%|█████▊    | 6419/11066 [23:30<16:55,  4.58it/s]
 58%|█████▊    | 6420/11066 [23:31<17:03,  4.54it/s]
                                                    

 58%|█████▊    | 6420/11066 [23:31<17:03,  4.54it/s]
 58%|█████▊    | 6421/11066 [23:31<16:54,  4.58it/s]
                                                    

 58%|█████▊    | 6421/11066 [23:31<16:54,  4.58it/s]
 58%|█████▊    | 6422/11066 [23:31<17:02,  4.54it/s]
                                                    

 58%|█████▊    | 6422/11066 [23:31<17:02,  4.54it/s]
 58%|█████▊    | 6423/11066 [23:31<17:07,  4.52it/s]
                                                    

 58%|█████▊    | 6423/11066 [23:31<17:07,  4.52it/s]
 58%|█████▊    | 6424/11066 [23:32<17:10,  4.50it/s]
                                                    

 58%|█████▊    | 6424/11066 [23:32<17:10,  4.50it/s]
 58%|█████▊    | 6425/11066 [23:32<17:12,  4.50it/s]
                                                    

 58%|█████▊    | 6425/11066 [23:32<17:12,  4.50it/s]
 58%|█████▊    | 6426/11066 [23:32<17:12,  4.49it/s]
                                                    

 58%|█████▊    | 6426/11066 [23:32<17:12,  4.49it/s]
 58%|█████▊    | 6427/11066 [23:32<17:12,  4.49it/s]
                                                    

 58%|█████▊    | 6427/11066 [23:32<17:12,  4.49it/s]
 58%|█████▊    | 6428/11066 [23:32<17:14,  4.49it/s]
                                                    

 58%|█████▊    | 6428/11066 [23:32<17:14,  4.49it/s]
 58%|█████▊    | 6429/11066 [23:33<17:14,  4.48it/s]
                                                    

 58%|█████▊    | 6429/11066 [23:33<17:14,  4.48it/s]
 58%|█████▊    | 6430/11066 [23:33<17:13,  4.49it/s]
                                                    

 58%|█████▊    | 6430/11066 [23:33<17:13,  4.49it/s]
 58%|█████▊    | 6431/11066 [23:33<17:15,  4.48it/s]
                                                    

 58%|█████▊    | 6431/11066 [23:33<17:15,  4.48it/s]
 58%|█████▊    | 6432/11066 [23:33<17:12,  4.49it/s]
                                                    

 58%|█████▊    | 6432/11066 [23:33<17:12,  4.49it/s]
 58%|█████▊    | 6433/11066 [23:34<17:12,  4.49it/s]
                                                    

 58%|█████▊    | 6433/11066 [23:34<17:12,  4.49it/s]
 58%|█████▊    | 6434/11066 [23:34<17:11,  4.49it/s]
                                                    

 58%|█████▊    | 6434/11066 [23:34<17:11,  4.49it/s]
 58%|█████▊    | 6435/11066 [23:34<17:10,  4.49it/s]
                                                    

 58%|█████▊    | 6435/11066 [23:34<17:10,  4.49it/s]
 58%|█████▊    | 6436/11066 [23:34<17:10,  4.49it/s]
                                                    

 58%|█████▊    | 6436/11066 [23:34<17:10,  4.49it/s]
 58%|█████▊    | 6437/11066 [23:35<17:11,  4.49it/s]
                                                    

 58%|█████▊    | 6437/11066 [23:35<17:11,  4.49it/s]
 58%|█████▊    | 6438/11066 [23:35<17:11,  4.48it/s]
                                                    

 58%|█████▊    | 6438/11066 [23:35<17:11,  4.48it/s]
 58%|█████▊    | 6439/11066 [23:35<16:56,  4.55it/s]
                                                    

 58%|█████▊    | 6439/11066 [23:35<16:56,  4.55it/s]
 58%|█████▊    | 6440/11066 [23:35<16:59,  4.54it/s]
                                                    

 58%|█████▊    | 6440/11066 [23:35<16:59,  4.54it/s]
 58%|█████▊    | 6441/11066 [23:35<16:53,  4.56it/s]
                                                    

 58%|█████▊    | 6441/11066 [23:35<16:53,  4.56it/s]
 58%|█████▊    | 6442/11066 [23:36<16:46,  4.59it/s]
                                                    

 58%|█████▊    | 6442/11066 [23:36<16:46,  4.59it/s]
 58%|█████▊    | 6443/11066 [23:36<16:36,  4.64it/s]
                                                    

 58%|█████▊    | 6443/11066 [23:36<16:36,  4.64it/s]
 58%|█████▊    | 6444/11066 [23:36<16:27,  4.68it/s]
                                                    

 58%|█████▊    | 6444/11066 [23:36<16:27,  4.68it/s]
 58%|█████▊    | 6445/11066 [23:36<16:27,  4.68it/s]
                                                    

 58%|█████▊    | 6445/11066 [23:36<16:27,  4.68it/s]
 58%|█████▊    | 6446/11066 [23:36<16:20,  4.71it/s]
                                                    

 58%|█████▊    | 6446/11066 [23:36<16:20,  4.71it/s]
 58%|█████▊    | 6447/11066 [23:37<16:22,  4.70it/s]
                                                    

 58%|█████▊    | 6447/11066 [23:37<16:22,  4.70it/s]
 58%|█████▊    | 6448/11066 [23:37<16:27,  4.68it/s]
                                                    

 58%|█████▊    | 6448/11066 [23:37<16:27,  4.68it/s]
 58%|█████▊    | 6449/11066 [23:37<16:21,  4.70it/s]
                                                    

 58%|█████▊    | 6449/11066 [23:37<16:21,  4.70it/s]
 58%|█████▊    | 6450/11066 [23:37<16:21,  4.70it/s]
                                                    

 58%|█████▊    | 6450/11066 [23:37<16:21,  4.70it/s]
 58%|█████▊    | 6451/11066 [23:37<16:19,  4.71it/s]
                                                    

 58%|█████▊    | 6451/11066 [23:37<16:19,  4.71it/s]
 58%|█████▊    | 6452/11066 [23:38<16:14,  4.74it/s]
                                                    

 58%|█████▊    | 6452/11066 [23:38<16:14,  4.74it/s]
 58%|█████▊    | 6453/11066 [23:38<16:17,  4.72it/s]
                                                    

 58%|█████▊    | 6453/11066 [23:38<16:17,  4.72it/s]
 58%|█████▊    | 6454/11066 [23:38<16:23,  4.69it/s]
                                                    

 58%|█████▊    | 6454/11066 [23:38<16:23,  4.69it/s]
 58%|█████▊    | 6455/11066 [23:38<16:24,  4.68it/s]
                                                    

 58%|█████▊    | 6455/11066 [23:38<16:24,  4.68it/s]
 58%|█████▊    | 6456/11066 [23:39<16:25,  4.68it/s]
                                                    

 58%|█████▊    | 6456/11066 [23:39<16:25,  4.68it/s]
 58%|█████▊    | 6457/11066 [23:39<17:09,  4.48it/s]
                                                    

 58%|█████▊    | 6457/11066 [23:39<17:09,  4.48it/s]
 58%|█████▊    | 6458/11066 [23:39<16:51,  4.55it/s]
                                                    

 58%|█████▊    | 6458/11066 [23:39<16:51,  4.55it/s]
 58%|█████▊    | 6459/11066 [23:39<16:59,  4.52it/s]
                                                    

 58%|█████▊    | 6459/11066 [23:39<16:59,  4.52it/s]
 58%|█████▊    | 6460/11066 [23:39<16:53,  4.54it/s]
                                                    

 58%|█████▊    | 6460/11066 [23:39<16:53,  4.54it/s]
 58%|█████▊    | 6461/11066 [23:40<16:44,  4.58it/s]
                                                    

 58%|█████▊    | 6461/11066 [23:40<16:44,  4.58it/s]
 58%|█████▊    | 6462/11066 [23:40<16:37,  4.62it/s]
                                                    

 58%|█████▊    | 6462/11066 [23:40<16:37,  4.62it/s]
 58%|█████▊    | 6463/11066 [23:40<16:31,  4.64it/s]
                                                    

 58%|█████▊    | 6463/11066 [23:40<16:31,  4.64it/s]
 58%|█████▊    | 6464/11066 [23:40<16:27,  4.66it/s]
                                                    

 58%|█████▊    | 6464/11066 [23:40<16:27,  4.66it/s]
 58%|█████▊    | 6465/11066 [23:41<16:31,  4.64it/s]
                                                    

 58%|█████▊    | 6465/11066 [23:41<16:31,  4.64it/s]
 58%|█████▊    | 6466/11066 [23:41<16:21,  4.69it/s]
                                                    

 58%|█████▊    | 6466/11066 [23:41<16:21,  4.69it/s]
 58%|█████▊    | 6467/11066 [23:41<16:21,  4.69it/s]
                                                    

 58%|█████▊    | 6467/11066 [23:41<16:21,  4.69it/s]
 58%|█████▊    | 6468/11066 [23:41<16:25,  4.66it/s]
                                                    

 58%|█████▊    | 6468/11066 [23:41<16:25,  4.66it/s]
 58%|█████▊    | 6469/11066 [23:41<16:23,  4.67it/s]
                                                    

 58%|█████▊    | 6469/11066 [23:41<16:23,  4.67it/s]
 58%|█████▊    | 6470/11066 [23:42<16:23,  4.67it/s]
                                                    

 58%|█████▊    | 6470/11066 [23:42<16:23,  4.67it/s]
 58%|█████▊    | 6471/11066 [23:42<16:19,  4.69it/s]
                                                    

 58%|█████▊    | 6471/11066 [23:42<16:19,  4.69it/s]
 58%|█████▊    | 6472/11066 [23:42<16:13,  4.72it/s]
                                                    

 58%|█████▊    | 6472/11066 [23:42<16:13,  4.72it/s]
 58%|█████▊    | 6473/11066 [23:42<16:15,  4.71it/s]
                                                    

 58%|█████▊    | 6473/11066 [23:42<16:15,  4.71it/s]
 59%|█████▊    | 6474/11066 [23:42<16:12,  4.72it/s]
                                                    

 59%|█████▊    | 6474/11066 [23:42<16:12,  4.72it/s]
 59%|█████▊    | 6475/11066 [23:43<16:13,  4.72it/s]
                                                    

 59%|█████▊    | 6475/11066 [23:43<16:13,  4.72it/s]
 59%|█████▊    | 6476/11066 [23:43<16:13,  4.72it/s]
                                                    

 59%|█████▊    | 6476/11066 [23:43<16:13,  4.72it/s]
 59%|█████▊    | 6477/11066 [23:43<16:12,  4.72it/s]
                                                    

 59%|█████▊    | 6477/11066 [23:43<16:12,  4.72it/s]
 59%|█████▊    | 6478/11066 [23:43<16:19,  4.69it/s]
                                                    

 59%|█████▊    | 6478/11066 [23:43<16:19,  4.69it/s]
 59%|█████▊    | 6479/11066 [23:44<16:19,  4.68it/s]
                                                    

 59%|█████▊    | 6479/11066 [23:44<16:19,  4.68it/s]
 59%|█████▊    | 6480/11066 [23:44<16:15,  4.70it/s]
                                                    

 59%|█████▊    | 6480/11066 [23:44<16:15,  4.70it/s]
 59%|█████▊    | 6481/11066 [23:44<16:13,  4.71it/s]
                                                    

 59%|█████▊    | 6481/11066 [23:44<16:13,  4.71it/s]
 59%|█████▊    | 6482/11066 [23:44<16:20,  4.67it/s]
                                                    

 59%|█████▊    | 6482/11066 [23:44<16:20,  4.67it/s]
 59%|█████▊    | 6483/11066 [23:44<16:32,  4.62it/s]
                                                    

 59%|█████▊    | 6483/11066 [23:44<16:32,  4.62it/s]
 59%|█████▊    | 6484/11066 [23:45<16:40,  4.58it/s]
                                                    

 59%|█████▊    | 6484/11066 [23:45<16:40,  4.58it/s]
 59%|█████▊    | 6485/11066 [23:45<16:45,  4.55it/s]
                                                    

 59%|█████▊    | 6485/11066 [23:45<16:45,  4.55it/s]
 59%|█████▊    | 6486/11066 [23:45<16:49,  4.54it/s]
                                                    

 59%|█████▊    | 6486/11066 [23:45<16:49,  4.54it/s]
 59%|█████▊    | 6487/11066 [23:45<16:53,  4.52it/s]
                                                    

 59%|█████▊    | 6487/11066 [23:45<16:53,  4.52it/s]
 59%|█████▊    | 6488/11066 [23:45<16:54,  4.51it/s]
                                                    

 59%|█████▊    | 6488/11066 [23:45<16:54,  4.51it/s]
 59%|█████▊    | 6489/11066 [23:46<16:54,  4.51it/s]
                                                    

 59%|█████▊    | 6489/11066 [23:46<16:54,  4.51it/s]
 59%|█████▊    | 6490/11066 [23:46<16:55,  4.51it/s]
                                                    

 59%|█████▊    | 6490/11066 [23:46<16:55,  4.51it/s]
 59%|█████▊    | 6491/11066 [23:46<16:56,  4.50it/s]
                                                    

 59%|█████▊    | 6491/11066 [23:46<16:56,  4.50it/s]
 59%|█████▊    | 6492/11066 [23:46<16:57,  4.50it/s]
                                                    

 59%|█████▊    | 6492/11066 [23:46<16:57,  4.50it/s]
 59%|█████▊    | 6493/11066 [23:47<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6493/11066 [23:47<16:57,  4.49it/s]
 59%|█████▊    | 6494/11066 [23:47<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6494/11066 [23:47<16:57,  4.49it/s]
 59%|█████▊    | 6495/11066 [23:47<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6495/11066 [23:47<16:57,  4.49it/s]
 59%|█████▊    | 6496/11066 [23:47<16:56,  4.49it/s]
                                                    

 59%|█████▊    | 6496/11066 [23:47<16:56,  4.49it/s]
 59%|█████▊    | 6497/11066 [23:47<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6497/11066 [23:47<16:57,  4.49it/s]
 59%|█████▊    | 6498/11066 [23:48<16:56,  4.49it/s]
                                                    

 59%|█████▊    | 6498/11066 [23:48<16:56,  4.49it/s]
 59%|█████▊    | 6499/11066 [23:48<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6499/11066 [23:48<16:57,  4.49it/s]
 59%|█████▊    | 6500/11066 [23:48<16:57,  4.49it/s]
                                                    

 59%|█████▊    | 6500/11066 [23:48<16:57,  4.49it/s]
 59%|█████▊    | 6501/11066 [23:48<16:58,  4.48it/s]
                                                    

 59%|█████▊    | 6501/11066 [23:48<16:58,  4.48it/s]
 59%|█████▉    | 6502/11066 [23:49<17:20,  4.39it/s]
                                                    

 59%|█████▉    | 6502/11066 [23:49<17:20,  4.39it/s]
 59%|█████▉    | 6503/11066 [23:49<17:16,  4.40it/s]
                                                    

 59%|█████▉    | 6503/11066 [23:49<17:16,  4.40it/s]
 59%|█████▉    | 6504/11066 [23:49<17:09,  4.43it/s]
                                                    

 59%|█████▉    | 6504/11066 [23:49<17:09,  4.43it/s]
 59%|█████▉    | 6505/11066 [23:49<17:05,  4.45it/s]
                                                    

 59%|█████▉    | 6505/11066 [23:49<17:05,  4.45it/s]
 59%|█████▉    | 6506/11066 [23:50<17:01,  4.46it/s]
                                                    

 59%|█████▉    | 6506/11066 [23:50<17:01,  4.46it/s]
 59%|█████▉    | 6507/11066 [23:50<16:56,  4.48it/s]
                                                    

 59%|█████▉    | 6507/11066 [23:50<16:56,  4.48it/s]
 59%|█████▉    | 6508/11066 [23:50<16:57,  4.48it/s]
                                                    

 59%|█████▉    | 6508/11066 [23:50<16:57,  4.48it/s]
 59%|█████▉    | 6509/11066 [23:50<16:57,  4.48it/s]
                                                    

 59%|█████▉    | 6509/11066 [23:50<16:57,  4.48it/s]
 59%|█████▉    | 6510/11066 [23:50<16:55,  4.48it/s]
                                                    

 59%|█████▉    | 6510/11066 [23:50<16:55,  4.48it/s]
 59%|█████▉    | 6511/11066 [23:51<16:54,  4.49it/s]
                                                    

 59%|█████▉    | 6511/11066 [23:51<16:54,  4.49it/s]
 59%|█████▉    | 6512/11066 [23:51<16:54,  4.49it/s]
                                                    

 59%|█████▉    | 6512/11066 [23:51<16:54,  4.49it/s]
 59%|█████▉    | 6513/11066 [23:51<16:54,  4.49it/s]
                                                    

 59%|█████▉    | 6513/11066 [23:51<16:54,  4.49it/s]
 59%|█████▉    | 6514/11066 [23:51<16:56,  4.48it/s]
                                                    

 59%|█████▉    | 6514/11066 [23:51<16:56,  4.48it/s]
 59%|█████▉    | 6515/11066 [23:52<17:10,  4.42it/s]
                                                    

 59%|█████▉    | 6515/11066 [23:52<17:10,  4.42it/s]
 59%|█████▉    | 6516/11066 [23:52<17:09,  4.42it/s]
                                                    

 59%|█████▉    | 6516/11066 [23:52<17:09,  4.42it/s]
 59%|█████▉    | 6517/11066 [23:52<17:06,  4.43it/s]
                                                    

 59%|█████▉    | 6517/11066 [23:52<17:06,  4.43it/s]
 59%|█████▉    | 6518/11066 [23:52<17:02,  4.45it/s]
                                                    

 59%|█████▉    | 6518/11066 [23:52<17:02,  4.45it/s]
 59%|█████▉    | 6519/11066 [23:52<16:59,  4.46it/s]
                                                    

 59%|█████▉    | 6519/11066 [23:52<16:59,  4.46it/s]
 59%|█████▉    | 6520/11066 [23:53<16:57,  4.47it/s]
                                                    

 59%|█████▉    | 6520/11066 [23:53<16:57,  4.47it/s]
 59%|█████▉    | 6521/11066 [23:53<16:55,  4.48it/s]
                                                    

 59%|█████▉    | 6521/11066 [23:53<16:55,  4.48it/s]
 59%|█████▉    | 6522/11066 [23:53<16:53,  4.48it/s]
                                                    

 59%|█████▉    | 6522/11066 [23:53<16:53,  4.48it/s]
 59%|█████▉    | 6523/11066 [23:53<16:51,  4.49it/s]
                                                    

 59%|█████▉    | 6523/11066 [23:53<16:51,  4.49it/s]
 59%|█████▉    | 6524/11066 [23:54<16:51,  4.49it/s]
                                                    
{'loss': 0.5585, 'learning_rate': 1.2617025121995302e-05, 'epoch': 1.16}
{'loss': 0.6058, 'learning_rate': 1.261431411530815e-05, 'epoch': 1.16}
{'loss': 1.058, 'learning_rate': 1.2611603108621001e-05, 'epoch': 1.16}
{'loss': 0.4257, 'learning_rate': 1.2608892101933853e-05, 'epoch': 1.16}
{'loss': 1.2023, 'learning_rate': 1.2606181095246703e-05, 'epoch': 1.16}
{'loss': 1.1217, 'learning_rate': 1.2603470088559551e-05, 'epoch': 1.16}
{'loss': 0.6235, 'learning_rate': 1.2600759081872401e-05, 'epoch': 1.16}
{'loss': 1.2784, 'learning_rate': 1.2598048075185253e-05, 'epoch': 1.16}
{'loss': 0.7181, 'learning_rate': 1.2595337068498103e-05, 'epoch': 1.16}
{'loss': 0.9669, 'learning_rate': 1.2592626061810952e-05, 'epoch': 1.16}
{'loss': 0.5905, 'learning_rate': 1.2589915055123804e-05, 'epoch': 1.16}
{'loss': 0.7687, 'learning_rate': 1.2587204048436654e-05, 'epoch': 1.16}
{'loss': 1.1354, 'learning_rate': 1.2584493041749504e-05, 'epoch': 1.16}
{'loss': 0.3847, 'learning_rate': 1.2581782035062352e-05, 'epoch': 1.16}
{'loss': 0.6026, 'learning_rate': 1.2579071028375204e-05, 'epoch': 1.16}
{'loss': 1.0003, 'learning_rate': 1.2576360021688054e-05, 'epoch': 1.16}
{'loss': 1.0054, 'learning_rate': 1.2573649015000904e-05, 'epoch': 1.16}
{'loss': 0.6941, 'learning_rate': 1.2570938008313755e-05, 'epoch': 1.16}
{'loss': 0.8265, 'learning_rate': 1.2568227001626605e-05, 'epoch': 1.16}
{'loss': 0.8575, 'learning_rate': 1.2565515994939455e-05, 'epoch': 1.16}
{'loss': 1.19, 'learning_rate': 1.2562804988252305e-05, 'epoch': 1.16}
{'loss': 0.6002, 'learning_rate': 1.2560093981565155e-05, 'epoch': 1.16}
{'loss': 0.7103, 'learning_rate': 1.2557382974878005e-05, 'epoch': 1.16}
{'loss': 0.7917, 'learning_rate': 1.2554671968190855e-05, 'epoch': 1.16}
{'loss': 1.3591, 'learning_rate': 1.2551960961503704e-05, 'epoch': 1.16}
{'loss': 0.6386, 'learning_rate': 1.2549249954816556e-05, 'epoch': 1.16}
{'loss': 0.9402, 'learning_rate': 1.2546538948129406e-05, 'epoch': 1.16}
{'loss': 0.8583, 'learning_rate': 1.2543827941442256e-05, 'epoch': 1.16}
{'loss': 0.4781, 'learning_rate': 1.2541116934755106e-05, 'epoch': 1.16}
{'loss': 0.3711, 'learning_rate': 1.2538405928067956e-05, 'epoch': 1.16}
{'loss': 0.6488, 'learning_rate': 1.2535694921380806e-05, 'epoch': 1.16}
{'loss': 1.5025, 'learning_rate': 1.2532983914693656e-05, 'epoch': 1.16}
{'loss': 0.4595, 'learning_rate': 1.2530272908006507e-05, 'epoch': 1.16}
{'loss': 0.6928, 'learning_rate': 1.2527561901319357e-05, 'epoch': 1.16}
{'loss': 0.6008, 'learning_rate': 1.2524850894632207e-05, 'epoch': 1.17}
{'loss': 0.3659, 'learning_rate': 1.2522139887945057e-05, 'epoch': 1.17}
{'loss': 0.5121, 'learning_rate': 1.2519428881257907e-05, 'epoch': 1.17}
{'loss': 0.887, 'learning_rate': 1.2516717874570757e-05, 'epoch': 1.17}
{'loss': 0.8846, 'learning_rate': 1.2514006867883607e-05, 'epoch': 1.17}
{'loss': 0.3213, 'learning_rate': 1.251129586119646e-05, 'epoch': 1.17}
{'loss': 0.7707, 'learning_rate': 1.2508584854509308e-05, 'epoch': 1.17}
{'loss': 0.5519, 'learning_rate': 1.2505873847822158e-05, 'epoch': 1.17}
{'loss': 0.3421, 'learning_rate': 1.2503162841135008e-05, 'epoch': 1.17}
{'loss': 0.4982, 'learning_rate': 1.250045183444786e-05, 'epoch': 1.17}
{'loss': 0.7351, 'learning_rate': 1.2497740827760708e-05, 'epoch': 1.17}
{'loss': 0.6069, 'learning_rate': 1.2495029821073558e-05, 'epoch': 1.17}
{'loss': 0.3631, 'learning_rate': 1.2492318814386408e-05, 'epoch': 1.17}
{'loss': 0.4433, 'learning_rate': 1.248960780769926e-05, 'epoch': 1.17}
{'loss': 0.7834, 'learning_rate': 1.2486896801012109e-05, 'epoch': 1.17}
{'loss': 0.408, 'learning_rate': 1.2484185794324959e-05, 'epoch': 1.17}
{'loss': 1.7454, 'learning_rate': 1.248147478763781e-05, 'epoch': 1.17}
{'loss': 0.7318, 'learning_rate': 1.247876378095066e-05, 'epoch': 1.17}
{'loss': 0.7207, 'learning_rate': 1.247605277426351e-05, 'epoch': 1.17}
{'loss': 0.7997, 'learning_rate': 1.247334176757636e-05, 'epoch': 1.17}
{'loss': 1.0833, 'learning_rate': 1.2470630760889211e-05, 'epoch': 1.17}
{'loss': 0.9509, 'learning_rate': 1.2467919754202061e-05, 'epoch': 1.17}
{'loss': 1.2502, 'learning_rate': 1.246520874751491e-05, 'epoch': 1.17}
{'loss': 0.889, 'learning_rate': 1.246249774082776e-05, 'epoch': 1.17}
{'loss': 0.9816, 'learning_rate': 1.2459786734140612e-05, 'epoch': 1.17}
{'loss': 0.714, 'learning_rate': 1.2457075727453462e-05, 'epoch': 1.17}
{'loss': 0.7084, 'learning_rate': 1.245436472076631e-05, 'epoch': 1.17}
{'loss': 1.0743, 'learning_rate': 1.2451653714079162e-05, 'epoch': 1.17}
{'loss': 0.8788, 'learning_rate': 1.2448942707392012e-05, 'epoch': 1.17}
{'loss': 1.7487, 'learning_rate': 1.2446231700704862e-05, 'epoch': 1.17}
{'loss': 0.9687, 'learning_rate': 1.2443520694017711e-05, 'epoch': 1.17}
{'loss': 0.3445, 'learning_rate': 1.2440809687330563e-05, 'epoch': 1.17}
{'loss': 0.7704, 'learning_rate': 1.2438098680643413e-05, 'epoch': 1.17}
{'loss': 0.6117, 'learning_rate': 1.2435387673956263e-05, 'epoch': 1.17}
{'loss': 0.8468, 'learning_rate': 1.2432676667269111e-05, 'epoch': 1.17}
{'loss': 0.5808, 'learning_rate': 1.2429965660581963e-05, 'epoch': 1.17}
{'loss': 0.6651, 'learning_rate': 1.2427254653894813e-05, 'epoch': 1.17}
{'loss': 0.6929, 'learning_rate': 1.2424543647207664e-05, 'epoch': 1.17}
{'loss': 1.379, 'learning_rate': 1.2421832640520514e-05, 'epoch': 1.17}
{'loss': 0.8245, 'learning_rate': 1.2419121633833364e-05, 'epoch': 1.17}
{'loss': 0.6173, 'learning_rate': 1.2416410627146214e-05, 'epoch': 1.17}
{'loss': 0.9656, 'learning_rate': 1.2413699620459064e-05, 'epoch': 1.17}
{'loss': 0.3949, 'learning_rate': 1.2410988613771914e-05, 'epoch': 1.17}
{'loss': 1.2557, 'learning_rate': 1.2408277607084764e-05, 'epoch': 1.17}
{'loss': 0.5234, 'learning_rate': 1.2405566600397614e-05, 'epoch': 1.17}
{'loss': 0.7472, 'learning_rate': 1.2402855593710465e-05, 'epoch': 1.17}
{'loss': 0.7477, 'learning_rate': 1.2400144587023315e-05, 'epoch': 1.17}
{'loss': 0.5979, 'learning_rate': 1.2397433580336165e-05, 'epoch': 1.17}
{'loss': 0.7197, 'learning_rate': 1.2394722573649015e-05, 'epoch': 1.17}
{'loss': 0.7786, 'learning_rate': 1.2392011566961867e-05, 'epoch': 1.17}
{'loss': 0.5717, 'learning_rate': 1.2389300560274715e-05, 'epoch': 1.17}
{'loss': 0.399, 'learning_rate': 1.2386589553587565e-05, 'epoch': 1.17}
{'loss': 0.9171, 'learning_rate': 1.2383878546900416e-05, 'epoch': 1.17}
{'loss': 0.2632, 'learning_rate': 1.2381167540213267e-05, 'epoch': 1.17}
{'loss': 0.8072, 'learning_rate': 1.2378456533526116e-05, 'epoch': 1.17}
{'loss': 0.6546, 'learning_rate': 1.2375745526838966e-05, 'epoch': 1.17}
{'loss': 0.3771, 'learning_rate': 1.2373034520151816e-05, 'epoch': 1.18}
{'loss': 0.4381, 'learning_rate': 1.2370323513464668e-05, 'epoch': 1.18}
{'loss': 0.6862, 'learning_rate': 1.2367612506777516e-05, 'epoch': 1.18}
{'loss': 0.4519, 'learning_rate': 1.2364901500090366e-05, 'epoch': 1.18}
{'loss': 0.5725, 'learning_rate': 1.2362190493403218e-05, 'epoch': 1.18}
{'loss': 0.2837, 'learning_rate': 1.2359479486716068e-05, 'epoch': 1.18}
{'loss': 0.5084, 'learning_rate': 1.2356768480028917e-05, 'epoch': 1.18}
{'loss': 1.1361, 'learning_rate': 1.2354057473341767e-05, 'epoch': 1.18}
{'loss': 0.3455, 'learning_rate': 1.2351346466654619e-05, 'epoch': 1.18}
{'loss': 0.853, 'learning_rate': 1.2348635459967469e-05, 'epoch': 1.18}
{'loss': 1.0885, 'learning_rate': 1.2345924453280317e-05, 'epoch': 1.18}
{'loss': 0.5123, 'learning_rate': 1.234321344659317e-05, 'epoch': 1.18}
{'loss': 0.1509, 'learning_rate': 1.234050243990602e-05, 'epoch': 1.18}
{'loss': 0.3887, 'learning_rate': 1.233779143321887e-05, 'epoch': 1.18}
{'loss': 0.5246, 'learning_rate': 1.2335080426531718e-05, 'epoch': 1.18}
{'loss': 0.8463, 'learning_rate': 1.233236941984457e-05, 'epoch': 1.18}
{'loss': 0.3708, 'learning_rate': 1.232965841315742e-05, 'epoch': 1.18}
{'loss': 1.5485, 'learning_rate': 1.232694740647027e-05, 'epoch': 1.18}
{'loss': 0.8813, 'learning_rate': 1.2324236399783118e-05, 'epoch': 1.18}
{'loss': 0.7185, 'learning_rate': 1.232152539309597e-05, 'epoch': 1.18}
{'loss': 1.0883, 'learning_rate': 1.231881438640882e-05, 'epoch': 1.18}
{'loss': 1.0791, 'learning_rate': 1.231610337972167e-05, 'epoch': 1.18}

 59%|█████▉    | 6524/11066 [23:54<16:51,  4.49it/s]
 59%|█████▉    | 6525/11066 [23:54<16:44,  4.52it/s]
                                                    

 59%|█████▉    | 6525/11066 [23:54<16:44,  4.52it/s]
 59%|█████▉    | 6526/11066 [23:54<16:49,  4.50it/s]
                                                    

 59%|█████▉    | 6526/11066 [23:54<16:49,  4.50it/s]
 59%|█████▉    | 6527/11066 [23:54<16:51,  4.49it/s]
                                                    

 59%|█████▉    | 6527/11066 [23:54<16:51,  4.49it/s]
 59%|█████▉    | 6528/11066 [23:54<16:53,  4.48it/s]
                                                    

 59%|█████▉    | 6528/11066 [23:54<16:53,  4.48it/s]
 59%|█████▉    | 6529/11066 [23:55<16:52,  4.48it/s]
                                                    

 59%|█████▉    | 6529/11066 [23:55<16:52,  4.48it/s]
 59%|█████▉    | 6530/11066 [23:55<16:50,  4.49it/s]
                                                    

 59%|█████▉    | 6530/11066 [23:55<16:50,  4.49it/s]
 59%|█████▉    | 6531/11066 [23:55<16:48,  4.50it/s]
                                                    

 59%|█████▉    | 6531/11066 [23:55<16:48,  4.50it/s]
 59%|█████▉    | 6532/11066 [23:55<16:47,  4.50it/s]
                                                    

 59%|█████▉    | 6532/11066 [23:55<16:47,  4.50it/s]
 59%|█████▉    | 6533/11066 [23:56<16:46,  4.50it/s]
                                                    

 59%|█████▉    | 6533/11066 [23:56<16:46,  4.50it/s]
 59%|█████▉    | 6534/11066 [23:56<16:39,  4.53it/s]
                                                    

 59%|█████▉    | 6534/11066 [23:56<16:39,  4.53it/s]
 59%|█████▉    | 6535/11066 [23:56<16:45,  4.51it/s]
                                                    

 59%|█████▉    | 6535/11066 [23:56<16:45,  4.51it/s]
 59%|█████▉    | 6536/11066 [23:56<16:48,  4.49it/s]
                                                    

 59%|█████▉    | 6536/11066 [23:56<16:48,  4.49it/s]
 59%|█████▉    | 6537/11066 [23:56<16:47,  4.49it/s]
                                                    

 59%|█████▉    | 6537/11066 [23:56<16:47,  4.49it/s]
 59%|█████▉    | 6538/11066 [23:57<16:48,  4.49it/s]
                                                    

 59%|█████▉    | 6538/11066 [23:57<16:48,  4.49it/s]
 59%|█████▉    | 6539/11066 [23:57<16:47,  4.49it/s]
                                                    

 59%|█████▉    | 6539/11066 [23:57<16:47,  4.49it/s]
 59%|█████▉    | 6540/11066 [23:57<16:47,  4.49it/s]
                                                    

 59%|█████▉    | 6540/11066 [23:57<16:47,  4.49it/s]
 59%|█████▉    | 6541/11066 [23:57<16:46,  4.50it/s]
                                                    

 59%|█████▉    | 6541/11066 [23:57<16:46,  4.50it/s]
 59%|█████▉    | 6542/11066 [23:58<16:46,  4.49it/s]
                                                    

 59%|█████▉    | 6542/11066 [23:58<16:46,  4.49it/s]
 59%|█████▉    | 6543/11066 [23:58<16:32,  4.56it/s]
                                                    

 59%|█████▉    | 6543/11066 [23:58<16:32,  4.56it/s]
 59%|█████▉    | 6544/11066 [23:58<16:35,  4.54it/s]
                                                    

 59%|█████▉    | 6544/11066 [23:58<16:35,  4.54it/s]
 59%|█████▉    | 6545/11066 [23:58<16:38,  4.53it/s]
                                                    

 59%|█████▉    | 6545/11066 [23:58<16:38,  4.53it/s]
 59%|█████▉    | 6546/11066 [23:58<16:26,  4.58it/s]
                                                    

 59%|█████▉    | 6546/11066 [23:58<16:26,  4.58it/s]
 59%|█████▉    | 6547/11066 [23:59<16:32,  4.55it/s]
                                                    

 59%|█████▉    | 6547/11066 [23:59<16:32,  4.55it/s]
 59%|█████▉    | 6548/11066 [23:59<16:36,  4.53it/s]
                                                    

 59%|█████▉    | 6548/11066 [23:59<16:36,  4.53it/s]
 59%|█████▉    | 6549/11066 [23:59<16:38,  4.52it/s]
                                                    

 59%|█████▉    | 6549/11066 [23:59<16:38,  4.52it/s]
 59%|█████▉    | 6550/11066 [23:59<16:40,  4.52it/s]
                                                    

 59%|█████▉    | 6550/11066 [23:59<16:40,  4.52it/s]
 59%|█████▉    | 6551/11066 [24:00<16:40,  4.51it/s]
                                                    

 59%|█████▉    | 6551/11066 [24:00<16:40,  4.51it/s]
 59%|█████▉    | 6552/11066 [24:00<16:40,  4.51it/s]
                                                    

 59%|█████▉    | 6552/11066 [24:00<16:40,  4.51it/s]
 59%|█████▉    | 6553/11066 [24:00<16:40,  4.51it/s]
                                                    

 59%|█████▉    | 6553/11066 [24:00<16:40,  4.51it/s]
 59%|█████▉    | 6554/11066 [24:00<16:41,  4.51it/s]
                                                    

 59%|█████▉    | 6554/11066 [24:00<16:41,  4.51it/s]
 59%|█████▉    | 6555/11066 [24:00<16:51,  4.46it/s]
                                                    

 59%|█████▉    | 6555/11066 [24:00<16:51,  4.46it/s]
 59%|█████▉    | 6556/11066 [24:01<16:30,  4.55it/s]
                                                    

 59%|█████▉    | 6556/11066 [24:01<16:30,  4.55it/s]
 59%|█████▉    | 6557/11066 [24:01<16:30,  4.55it/s]
                                                    

 59%|█████▉    | 6557/11066 [24:01<16:30,  4.55it/s]
 59%|█████▉    | 6558/11066 [24:01<16:21,  4.59it/s]
                                                    

 59%|█████▉    | 6558/11066 [24:01<16:21,  4.59it/s]
 59%|█████▉    | 6559/11066 [24:01<16:29,  4.55it/s]
                                                    

 59%|█████▉    | 6559/11066 [24:01<16:29,  4.55it/s]
 59%|█████▉    | 6560/11066 [24:02<16:27,  4.56it/s]
                                                    

 59%|█████▉    | 6560/11066 [24:02<16:27,  4.56it/s]
 59%|█████▉    | 6561/11066 [24:02<16:32,  4.54it/s]
                                                    

 59%|█████▉    | 6561/11066 [24:02<16:32,  4.54it/s]
 59%|█████▉    | 6562/11066 [24:02<16:26,  4.57it/s]
                                                    

 59%|█████▉    | 6562/11066 [24:02<16:26,  4.57it/s]
 59%|█████▉    | 6563/11066 [24:02<16:27,  4.56it/s]
                                                    

 59%|█████▉    | 6563/11066 [24:02<16:27,  4.56it/s]
 59%|█████▉    | 6564/11066 [24:02<16:20,  4.59it/s]
                                                    

 59%|█████▉    | 6564/11066 [24:02<16:20,  4.59it/s]
 59%|█████▉    | 6565/11066 [24:03<16:20,  4.59it/s]
                                                    

 59%|█████▉    | 6565/11066 [24:03<16:20,  4.59it/s]
 59%|█████▉    | 6566/11066 [24:03<16:28,  4.55it/s]
                                                    

 59%|█████▉    | 6566/11066 [24:03<16:28,  4.55it/s]
 59%|█████▉    | 6567/11066 [24:03<16:24,  4.57it/s]
                                                    

 59%|█████▉    | 6567/11066 [24:03<16:24,  4.57it/s]
 59%|█████▉    | 6568/11066 [24:03<16:17,  4.60it/s]
                                                    

 59%|█████▉    | 6568/11066 [24:03<16:17,  4.60it/s]
 59%|█████▉    | 6569/11066 [24:03<16:22,  4.58it/s]
                                                    

 59%|█████▉    | 6569/11066 [24:03<16:22,  4.58it/s]
 59%|█████▉    | 6570/11066 [24:04<16:21,  4.58it/s]
                                                    

 59%|█████▉    | 6570/11066 [24:04<16:21,  4.58it/s]
 59%|█████▉    | 6571/11066 [24:04<16:19,  4.59it/s]
                                                    

 59%|█████▉    | 6571/11066 [24:04<16:19,  4.59it/s]
 59%|█████▉    | 6572/11066 [24:04<16:13,  4.62it/s]
                                                    

 59%|█████▉    | 6572/11066 [24:04<16:13,  4.62it/s]
 59%|█████▉    | 6573/11066 [24:04<16:16,  4.60it/s]
                                                    

 59%|█████▉    | 6573/11066 [24:04<16:16,  4.60it/s]
 59%|█████▉    | 6574/11066 [24:05<16:17,  4.60it/s]
                                                    

 59%|█████▉    | 6574/11066 [24:05<16:17,  4.60it/s]
 59%|█████▉    | 6575/11066 [24:05<16:11,  4.62it/s]
                                                    

 59%|█████▉    | 6575/11066 [24:05<16:11,  4.62it/s]
 59%|█████▉    | 6576/11066 [24:05<16:05,  4.65it/s]
                                                    

 59%|█████▉    | 6576/11066 [24:05<16:05,  4.65it/s]
 59%|█████▉    | 6577/11066 [24:05<16:07,  4.64it/s]
                                                    

 59%|█████▉    | 6577/11066 [24:05<16:07,  4.64it/s]
 59%|█████▉    | 6578/11066 [24:05<16:04,  4.66it/s]
                                                    

 59%|█████▉    | 6578/11066 [24:05<16:04,  4.66it/s]
 59%|█████▉    | 6579/11066 [24:06<16:12,  4.62it/s]
                                                    

 59%|█████▉    | 6579/11066 [24:06<16:12,  4.62it/s]
 59%|█████▉    | 6580/11066 [24:06<16:01,  4.66it/s]
                                                    

 59%|█████▉    | 6580/11066 [24:06<16:01,  4.66it/s]
 59%|█████▉    | 6581/11066 [24:06<15:54,  4.70it/s]
                                                    

 59%|█████▉    | 6581/11066 [24:06<15:54,  4.70it/s]
 59%|█████▉    | 6582/11066 [24:06<15:55,  4.69it/s]
                                                    

 59%|█████▉    | 6582/11066 [24:06<15:55,  4.69it/s]
 59%|█████▉    | 6583/11066 [24:06<16:08,  4.63it/s]
                                                    

 59%|█████▉    | 6583/11066 [24:06<16:08,  4.63it/s]
 59%|█████▉    | 6584/11066 [24:07<16:18,  4.58it/s]
                                                    

 59%|█████▉    | 6584/11066 [24:07<16:18,  4.58it/s]
 60%|█████▉    | 6585/11066 [24:07<16:15,  4.59it/s]
                                                    

 60%|█████▉    | 6585/11066 [24:07<16:15,  4.59it/s]
 60%|█████▉    | 6586/11066 [24:07<16:05,  4.64it/s]
                                                    

 60%|█████▉    | 6586/11066 [24:07<16:05,  4.64it/s]
 60%|█████▉    | 6587/11066 [24:07<16:02,  4.65it/s]
                                                    

 60%|█████▉    | 6587/11066 [24:07<16:02,  4.65it/s]
 60%|█████▉    | 6588/11066 [24:08<15:59,  4.67it/s]
                                                    

 60%|█████▉    | 6588/11066 [24:08<15:59,  4.67it/s]
 60%|█████▉    | 6589/11066 [24:08<16:05,  4.64it/s]
                                                    

 60%|█████▉    | 6589/11066 [24:08<16:05,  4.64it/s]
 60%|█████▉    | 6590/11066 [24:08<15:59,  4.66it/s]
                                                    

 60%|█████▉    | 6590/11066 [24:08<15:59,  4.66it/s]
 60%|█████▉    | 6591/11066 [24:08<16:09,  4.62it/s]
                                                    

 60%|█████▉    | 6591/11066 [24:08<16:09,  4.62it/s]
 60%|█████▉    | 6592/11066 [24:08<16:03,  4.64it/s]
                                                    

 60%|█████▉    | 6592/11066 [24:08<16:03,  4.64it/s]
 60%|█████▉    | 6593/11066 [24:09<15:59,  4.66it/s]
                                                    

 60%|█████▉    | 6593/11066 [24:09<15:59,  4.66it/s]
 60%|█████▉    | 6594/11066 [24:09<15:56,  4.68it/s]
                                                    

 60%|█████▉    | 6594/11066 [24:09<15:56,  4.68it/s]
 60%|█████▉    | 6595/11066 [24:09<15:53,  4.69it/s]
                                                    

 60%|█████▉    | 6595/11066 [24:09<15:53,  4.69it/s]
 60%|█████▉    | 6596/11066 [24:09<15:51,  4.70it/s]
                                                    

 60%|█████▉    | 6596/11066 [24:09<15:51,  4.70it/s]
 60%|█████▉    | 6597/11066 [24:09<16:05,  4.63it/s]
                                                    

 60%|█████▉    | 6597/11066 [24:09<16:05,  4.63it/s]
 60%|█████▉    | 6598/11066 [24:10<16:06,  4.62it/s]
                                                    

 60%|█████▉    | 6598/11066 [24:10<16:06,  4.62it/s]
 60%|█████▉    | 6599/11066 [24:10<16:08,  4.61it/s]
                                                    

 60%|█████▉    | 6599/11066 [24:10<16:08,  4.61it/s]
 60%|█████▉    | 6600/11066 [24:10<16:08,  4.61it/s]
                                                    

 60%|█████▉    | 6600/11066 [24:10<16:08,  4.61it/s]
 60%|█████▉    | 6601/11066 [24:10<16:10,  4.60it/s]
                                                    

 60%|█████▉    | 6601/11066 [24:10<16:10,  4.60it/s]
 60%|█████▉    | 6602/11066 [24:11<16:12,  4.59it/s]
                                                    

 60%|█████▉    | 6602/11066 [24:11<16:12,  4.59it/s]
 60%|█████▉    | 6603/11066 [24:11<16:18,  4.56it/s]
                                                    

 60%|█████▉    | 6603/11066 [24:11<16:18,  4.56it/s]
 60%|█████▉    | 6604/11066 [24:11<16:09,  4.60it/s]
                                                    

 60%|█████▉    | 6604/11066 [24:11<16:09,  4.60it/s]
 60%|█████▉    | 6605/11066 [24:11<16:17,  4.57it/s]
                                                    

 60%|█████▉    | 6605/11066 [24:11<16:17,  4.57it/s]
 60%|█████▉    | 6606/11066 [24:11<16:09,  4.60it/s]
                                                    

 60%|█████▉    | 6606/11066 [24:11<16:09,  4.60it/s]
 60%|█████▉    | 6607/11066 [24:12<16:01,  4.64it/s]
                                                    

 60%|█████▉    | 6607/11066 [24:12<16:01,  4.64it/s]
 60%|█████▉    | 6608/11066 [24:12<15:57,  4.66it/s]
                                                    

 60%|█████▉    | 6608/11066 [24:12<15:57,  4.66it/s]
 60%|█████▉    | 6609/11066 [24:12<15:52,  4.68it/s]
                                                    

 60%|█████▉    | 6609/11066 [24:12<15:52,  4.68it/s]
 60%|█████▉    | 6610/11066 [24:12<15:50,  4.69it/s]
                                                    

 60%|█████▉    | 6610/11066 [24:12<15:50,  4.69it/s]
 60%|█████▉    | 6611/11066 [24:13<15:55,  4.66it/s]
                                                    

 60%|█████▉    | 6611/11066 [24:13<15:55,  4.66it/s]
 60%|█████▉    | 6612/11066 [24:13<15:57,  4.65it/s]
                                                    

 60%|█████▉    | 6612/11066 [24:13<15:57,  4.65it/s]
 60%|█████▉    | 6613/11066 [24:13<15:54,  4.67it/s]
                                                    

 60%|█████▉    | 6613/11066 [24:13<15:54,  4.67it/s]
 60%|█████▉    | 6614/11066 [24:13<16:06,  4.61it/s]
                                                    

 60%|█████▉    | 6614/11066 [24:13<16:06,  4.61it/s]
 60%|█████▉    | 6615/11066 [24:13<16:05,  4.61it/s]
                                                    

 60%|█████▉    | 6615/11066 [24:13<16:05,  4.61it/s]
 60%|█████▉    | 6616/11066 [24:14<15:55,  4.66it/s]
                                                    

 60%|█████▉    | 6616/11066 [24:14<15:55,  4.66it/s]
 60%|█████▉    | 6617/11066 [24:14<15:46,  4.70it/s]
                                                    

 60%|█████▉    | 6617/11066 [24:14<15:46,  4.70it/s]
 60%|█████▉    | 6618/11066 [24:14<15:48,  4.69it/s]
                                                    

 60%|█████▉    | 6618/11066 [24:14<15:48,  4.69it/s]
 60%|█████▉    | 6619/11066 [24:14<15:52,  4.67it/s]
                                                    

 60%|█████▉    | 6619/11066 [24:14<15:52,  4.67it/s]
 60%|█████▉    | 6620/11066 [24:14<15:46,  4.70it/s]
                                                    

 60%|█████▉    | 6620/11066 [24:14<15:46,  4.70it/s]
 60%|█████▉    | 6621/11066 [24:15<15:51,  4.67it/s]
                                                    

 60%|█████▉    | 6621/11066 [24:15<15:51,  4.67it/s]
 60%|█████▉    | 6622/11066 [24:15<15:53,  4.66it/s]
                                                    

 60%|█████▉    | 6622/11066 [24:15<15:53,  4.66it/s]
 60%|█████▉    | 6623/11066 [24:15<15:51,  4.67it/s]
                                                    

 60%|█████▉    | 6623/11066 [24:15<15:51,  4.67it/s]
 60%|█████▉    | 6624/11066 [24:15<16:02,  4.61it/s]
                                                    

 60%|█████▉    | 6624/11066 [24:15<16:02,  4.61it/s]
 60%|█████▉    | 6625/11066 [24:16<15:56,  4.64it/s]
                                                    

 60%|█████▉    | 6625/11066 [24:16<15:56,  4.64it/s]
 60%|█████▉    | 6626/11066 [24:16<15:53,  4.65it/s]
                                                    

 60%|█████▉    | 6626/11066 [24:16<15:53,  4.65it/s]
 60%|█████▉    | 6627/11066 [24:16<15:50,  4.67it/s]
                                                    

 60%|█████▉    | 6627/11066 [24:16<15:50,  4.67it/s]
 60%|█████▉    | 6628/11066 [24:16<15:47,  4.68it/s]
                                                    

 60%|█████▉    | 6628/11066 [24:16<15:47,  4.68it/s]
 60%|█████▉    | 6629/11066 [24:16<15:45,  4.69it/s]
                                                    

 60%|█████▉    | 6629/11066 [24:16<15:45,  4.69it/s]
 60%|█████▉    | 6630/11066 [24:17<15:58,  4.63it/s]
                                                    

 60%|█████▉    | 6630/11066 [24:17<15:58,  4.63it/s]
 60%|█████▉    | 6631/11066 [24:17<16:07,  4.58it/s]
                                                    

 60%|█████▉    | 6631/11066 [24:17<16:07,  4.58it/s]
 60%|█████▉    | 6632/11066 [24:17<16:13,  4.55it/s]
                                                    

 60%|█████▉    | 6632/11066 [24:17<16:13,  4.55it/s]
 60%|█████▉    | 6633/11066 [24:17<16:19,  4.53it/s]
                                                    

 60%|█████▉    | 6633/11066 [24:17<16:19,  4.53it/s]
 60%|█████▉    | 6634/11066 [24:17<16:13,  4.55it/s]
                                                    

 60%|█████▉    | 6634/11066 [24:17<16:13,  4.55it/s]
 60%|█████▉    | 6635/11066 [24:18<15:58,  4.62it/s]
                                                    

 60%|█████▉    | 6635/11066 [24:18<15:58,  4.62it/s]
 60%|█████▉    | 6636/11066 [24:18<15:59,  4.62it/s]
                                                    
{'loss': 0.5397, 'learning_rate': 1.231339237303452e-05, 'epoch': 1.18}
{'loss': 0.237, 'learning_rate': 1.2310681366347371e-05, 'epoch': 1.18}
{'loss': 1.1271, 'learning_rate': 1.2307970359660221e-05, 'epoch': 1.18}
{'loss': 0.3513, 'learning_rate': 1.2305259352973071e-05, 'epoch': 1.18}
{'loss': 1.3603, 'learning_rate': 1.2302548346285921e-05, 'epoch': 1.18}
{'loss': 0.7032, 'learning_rate': 1.2299837339598771e-05, 'epoch': 1.18}
{'loss': 0.8888, 'learning_rate': 1.2297126332911622e-05, 'epoch': 1.18}
{'loss': 0.3433, 'learning_rate': 1.2294415326224472e-05, 'epoch': 1.18}
{'loss': 0.615, 'learning_rate': 1.2291704319537322e-05, 'epoch': 1.18}
{'loss': 0.4064, 'learning_rate': 1.2288993312850172e-05, 'epoch': 1.18}
{'loss': 0.694, 'learning_rate': 1.2286282306163022e-05, 'epoch': 1.18}
{'loss': 0.4127, 'learning_rate': 1.2283571299475874e-05, 'epoch': 1.18}
{'loss': 1.0799, 'learning_rate': 1.2280860292788722e-05, 'epoch': 1.18}
{'loss': 0.5359, 'learning_rate': 1.2278149286101572e-05, 'epoch': 1.18}
{'loss': 0.6206, 'learning_rate': 1.2275438279414423e-05, 'epoch': 1.18}
{'loss': 0.9596, 'learning_rate': 1.2272727272727274e-05, 'epoch': 1.18}
{'loss': 0.6268, 'learning_rate': 1.2270016266040123e-05, 'epoch': 1.18}
{'loss': 0.6175, 'learning_rate': 1.2267305259352973e-05, 'epoch': 1.18}
{'loss': 0.6118, 'learning_rate': 1.2264594252665823e-05, 'epoch': 1.18}
{'loss': 0.6777, 'learning_rate': 1.2261883245978675e-05, 'epoch': 1.18}
{'loss': 0.6634, 'learning_rate': 1.2259172239291523e-05, 'epoch': 1.18}
{'loss': 0.7132, 'learning_rate': 1.2256461232604374e-05, 'epoch': 1.18}
{'loss': 1.5854, 'learning_rate': 1.2253750225917225e-05, 'epoch': 1.18}
{'loss': 0.903, 'learning_rate': 1.2251039219230075e-05, 'epoch': 1.18}
{'loss': 0.7507, 'learning_rate': 1.2248328212542924e-05, 'epoch': 1.18}
{'loss': 0.4926, 'learning_rate': 1.2245617205855774e-05, 'epoch': 1.18}
{'loss': 0.3488, 'learning_rate': 1.2242906199168626e-05, 'epoch': 1.18}
{'loss': 0.7626, 'learning_rate': 1.2240195192481476e-05, 'epoch': 1.18}
{'loss': 0.8279, 'learning_rate': 1.2237484185794324e-05, 'epoch': 1.18}
{'loss': 0.6161, 'learning_rate': 1.2234773179107175e-05, 'epoch': 1.18}
{'loss': 0.5911, 'learning_rate': 1.2232062172420026e-05, 'epoch': 1.18}
{'loss': 0.922, 'learning_rate': 1.2229351165732877e-05, 'epoch': 1.18}
{'loss': 0.597, 'learning_rate': 1.2226640159045725e-05, 'epoch': 1.18}
{'loss': 0.7614, 'learning_rate': 1.2223929152358577e-05, 'epoch': 1.19}
{'loss': 1.1001, 'learning_rate': 1.2221218145671427e-05, 'epoch': 1.19}
{'loss': 0.7458, 'learning_rate': 1.2218507138984277e-05, 'epoch': 1.19}
{'loss': 1.6541, 'learning_rate': 1.2215796132297126e-05, 'epoch': 1.19}
{'loss': 0.7054, 'learning_rate': 1.2213085125609977e-05, 'epoch': 1.19}
{'loss': 0.5629, 'learning_rate': 1.2210374118922828e-05, 'epoch': 1.19}
{'loss': 0.4375, 'learning_rate': 1.2207663112235676e-05, 'epoch': 1.19}
{'loss': 1.1596, 'learning_rate': 1.2204952105548526e-05, 'epoch': 1.19}
{'loss': 0.5133, 'learning_rate': 1.2202241098861378e-05, 'epoch': 1.19}
{'loss': 0.9913, 'learning_rate': 1.2199530092174228e-05, 'epoch': 1.19}
{'loss': 0.4922, 'learning_rate': 1.2196819085487076e-05, 'epoch': 1.19}
{'loss': 0.5061, 'learning_rate': 1.2194108078799928e-05, 'epoch': 1.19}
{'loss': 1.0862, 'learning_rate': 1.2191397072112778e-05, 'epoch': 1.19}
{'loss': 1.0112, 'learning_rate': 1.2188686065425629e-05, 'epoch': 1.19}
{'loss': 0.3718, 'learning_rate': 1.2185975058738477e-05, 'epoch': 1.19}
{'loss': 0.6588, 'learning_rate': 1.2183264052051329e-05, 'epoch': 1.19}
{'loss': 1.1649, 'learning_rate': 1.2180553045364179e-05, 'epoch': 1.19}
{'loss': 0.7089, 'learning_rate': 1.2177842038677029e-05, 'epoch': 1.19}
{'loss': 1.0986, 'learning_rate': 1.217513103198988e-05, 'epoch': 1.19}
{'loss': 0.7297, 'learning_rate': 1.217242002530273e-05, 'epoch': 1.19}
{'loss': 0.7003, 'learning_rate': 1.216970901861558e-05, 'epoch': 1.19}
{'loss': 0.7548, 'learning_rate': 1.216699801192843e-05, 'epoch': 1.19}
{'loss': 1.2692, 'learning_rate': 1.216428700524128e-05, 'epoch': 1.19}
{'loss': 0.3116, 'learning_rate': 1.216157599855413e-05, 'epoch': 1.19}
{'loss': 0.4447, 'learning_rate': 1.215886499186698e-05, 'epoch': 1.19}
{'loss': 0.7836, 'learning_rate': 1.215615398517983e-05, 'epoch': 1.19}
{'loss': 0.5022, 'learning_rate': 1.215344297849268e-05, 'epoch': 1.19}
{'loss': 0.7238, 'learning_rate': 1.215073197180553e-05, 'epoch': 1.19}
{'loss': 0.4024, 'learning_rate': 1.214802096511838e-05, 'epoch': 1.19}
{'loss': 0.8071, 'learning_rate': 1.2145309958431232e-05, 'epoch': 1.19}
{'loss': 0.8077, 'learning_rate': 1.2142598951744081e-05, 'epoch': 1.19}
{'loss': 0.6015, 'learning_rate': 1.2139887945056931e-05, 'epoch': 1.19}
{'loss': 0.5271, 'learning_rate': 1.2137176938369781e-05, 'epoch': 1.19}
{'loss': 0.3076, 'learning_rate': 1.2134465931682633e-05, 'epoch': 1.19}
{'loss': 0.525, 'learning_rate': 1.2131754924995481e-05, 'epoch': 1.19}
{'loss': 0.7324, 'learning_rate': 1.2129043918308332e-05, 'epoch': 1.19}
{'loss': 0.7709, 'learning_rate': 1.2126332911621182e-05, 'epoch': 1.19}
{'loss': 0.7182, 'learning_rate': 1.2123621904934034e-05, 'epoch': 1.19}
{'loss': 0.5859, 'learning_rate': 1.2120910898246882e-05, 'epoch': 1.19}
{'loss': 0.7984, 'learning_rate': 1.2118199891559732e-05, 'epoch': 1.19}
{'loss': 0.8507, 'learning_rate': 1.2115488884872584e-05, 'epoch': 1.19}
{'loss': 1.3842, 'learning_rate': 1.2112777878185434e-05, 'epoch': 1.19}
{'loss': 0.5764, 'learning_rate': 1.2110066871498282e-05, 'epoch': 1.19}
{'loss': 0.4751, 'learning_rate': 1.2107355864811133e-05, 'epoch': 1.19}
{'loss': 1.0302, 'learning_rate': 1.2104644858123984e-05, 'epoch': 1.19}
{'loss': 0.6489, 'learning_rate': 1.2101933851436835e-05, 'epoch': 1.19}
{'loss': 0.7988, 'learning_rate': 1.2099222844749683e-05, 'epoch': 1.19}
{'loss': 0.8447, 'learning_rate': 1.2096511838062533e-05, 'epoch': 1.19}
{'loss': 0.8654, 'learning_rate': 1.2093800831375385e-05, 'epoch': 1.19}
{'loss': 0.9138, 'learning_rate': 1.2091089824688235e-05, 'epoch': 1.19}
{'loss': 0.7611, 'learning_rate': 1.2088378818001084e-05, 'epoch': 1.19}
{'loss': 0.6682, 'learning_rate': 1.2085667811313935e-05, 'epoch': 1.19}
{'loss': 0.1835, 'learning_rate': 1.2082956804626786e-05, 'epoch': 1.19}
{'loss': 0.7497, 'learning_rate': 1.2080245797939636e-05, 'epoch': 1.19}
{'loss': 0.6658, 'learning_rate': 1.2077534791252484e-05, 'epoch': 1.19}
{'loss': 0.4575, 'learning_rate': 1.2074823784565336e-05, 'epoch': 1.2}
{'loss': 0.6721, 'learning_rate': 1.2072112777878186e-05, 'epoch': 1.2}
{'loss': 0.5622, 'learning_rate': 1.2069401771191036e-05, 'epoch': 1.2}
{'loss': 0.5794, 'learning_rate': 1.2066690764503885e-05, 'epoch': 1.2}
{'loss': 1.1448, 'learning_rate': 1.2063979757816736e-05, 'epoch': 1.2}
{'loss': 0.891, 'learning_rate': 1.2061268751129587e-05, 'epoch': 1.2}
{'loss': 1.1077, 'learning_rate': 1.2058557744442437e-05, 'epoch': 1.2}
{'loss': 0.6911, 'learning_rate': 1.2055846737755287e-05, 'epoch': 1.2}
{'loss': 0.3951, 'learning_rate': 1.2053135731068137e-05, 'epoch': 1.2}
{'loss': 0.5944, 'learning_rate': 1.2050424724380987e-05, 'epoch': 1.2}
{'loss': 0.5774, 'learning_rate': 1.2047713717693837e-05, 'epoch': 1.2}
{'loss': 0.8888, 'learning_rate': 1.2045002711006687e-05, 'epoch': 1.2}
{'loss': 0.6002, 'learning_rate': 1.2042291704319538e-05, 'epoch': 1.2}
{'loss': 0.6224, 'learning_rate': 1.2039580697632388e-05, 'epoch': 1.2}
{'loss': 0.9889, 'learning_rate': 1.2036869690945238e-05, 'epoch': 1.2}
{'loss': 0.8903, 'learning_rate': 1.2034158684258088e-05, 'epoch': 1.2}
{'loss': 0.8149, 'learning_rate': 1.2031447677570938e-05, 'epoch': 1.2}
{'loss': 0.7644, 'learning_rate': 1.2028736670883788e-05, 'epoch': 1.2}
{'loss': 0.4954, 'learning_rate': 1.202602566419664e-05, 'epoch': 1.2}
{'loss': 0.7142, 'learning_rate': 1.2023314657509488e-05, 'epoch': 1.2}
{'loss': 1.5383, 'learning_rate': 1.2020603650822339e-05, 'epoch': 1.2}
{'loss': 0.6527, 'learning_rate': 1.2017892644135189e-05, 'epoch': 1.2}
{'loss': 0.7238, 'learning_rate': 1.201518163744804e-05, 'epoch': 1.2}
{'loss': 0.2843, 'learning_rate': 1.2012470630760889e-05, 'epoch': 1.2}

 60%|█████▉    | 6636/11066 [24:18<15:59,  4.62it/s]
 60%|█████▉    | 6637/11066 [24:18<15:52,  4.65it/s]
                                                    

 60%|█████▉    | 6637/11066 [24:18<15:52,  4.65it/s]
 60%|█████▉    | 6638/11066 [24:18<15:45,  4.68it/s]
                                                    

 60%|█████▉    | 6638/11066 [24:18<15:45,  4.68it/s]
 60%|█████▉    | 6639/11066 [24:19<15:48,  4.67it/s]
                                                    

 60%|█████▉    | 6639/11066 [24:19<15:48,  4.67it/s]
 60%|██████    | 6640/11066 [24:19<16:03,  4.59it/s]
                                                    

 60%|██████    | 6640/11066 [24:19<16:03,  4.59it/s]
 60%|██████    | 6641/11066 [24:19<16:03,  4.59it/s]
                                                    

 60%|██████    | 6641/11066 [24:19<16:03,  4.59it/s]
 60%|██████    | 6642/11066 [24:19<15:53,  4.64it/s]
                                                    

 60%|██████    | 6642/11066 [24:19<15:53,  4.64it/s]
 60%|██████    | 6643/11066 [24:19<15:51,  4.65it/s]
                                                    

 60%|██████    | 6643/11066 [24:19<15:51,  4.65it/s]
 60%|██████    | 6644/11066 [24:20<15:44,  4.68it/s]
                                                    

 60%|██████    | 6644/11066 [24:20<15:44,  4.68it/s]
 60%|██████    | 6645/11066 [24:20<15:37,  4.72it/s]
                                                    

 60%|██████    | 6645/11066 [24:20<15:37,  4.72it/s]
 60%|██████    | 6646/11066 [24:20<15:38,  4.71it/s]
                                                    

 60%|██████    | 6646/11066 [24:20<15:38,  4.71it/s]
 60%|██████    | 6647/11066 [24:20<15:51,  4.64it/s]
                                                    

 60%|██████    | 6647/11066 [24:20<15:51,  4.64it/s]
 60%|██████    | 6648/11066 [24:20<15:48,  4.66it/s]
                                                    

 60%|██████    | 6648/11066 [24:20<15:48,  4.66it/s]
 60%|██████    | 6649/11066 [24:21<15:58,  4.61it/s]
                                                    

 60%|██████    | 6649/11066 [24:21<15:58,  4.61it/s]
 60%|██████    | 6650/11066 [24:21<15:58,  4.61it/s]
                                                    

 60%|██████    | 6650/11066 [24:21<15:58,  4.61it/s]
 60%|██████    | 6651/11066 [24:21<15:54,  4.63it/s]
                                                    

 60%|██████    | 6651/11066 [24:21<15:54,  4.63it/s]
 60%|██████    | 6652/11066 [24:21<16:00,  4.59it/s]
                                                    

 60%|██████    | 6652/11066 [24:21<16:00,  4.59it/s]
 60%|██████    | 6653/11066 [24:22<15:58,  4.60it/s]
                                                    

 60%|██████    | 6653/11066 [24:22<15:58,  4.60it/s]
 60%|██████    | 6654/11066 [24:22<15:54,  4.62it/s]
                                                    

 60%|██████    | 6654/11066 [24:22<15:54,  4.62it/s]
 60%|██████    | 6655/11066 [24:22<15:55,  4.62it/s]
                                                    

 60%|██████    | 6655/11066 [24:22<15:55,  4.62it/s]
 60%|██████    | 6656/11066 [24:22<15:54,  4.62it/s]
                                                    

 60%|██████    | 6656/11066 [24:22<15:54,  4.62it/s]
 60%|██████    | 6657/11066 [24:22<16:02,  4.58it/s]
                                                    

 60%|██████    | 6657/11066 [24:22<16:02,  4.58it/s]
 60%|██████    | 6658/11066 [24:23<16:00,  4.59it/s]
                                                    

 60%|██████    | 6658/11066 [24:23<16:00,  4.59it/s]
 60%|██████    | 6659/11066 [24:23<15:54,  4.62it/s]
                                                    

 60%|██████    | 6659/11066 [24:23<15:54,  4.62it/s]
 60%|██████    | 6660/11066 [24:23<15:52,  4.63it/s]
                                                    

 60%|██████    | 6660/11066 [24:23<15:52,  4.63it/s]
 60%|██████    | 6661/11066 [24:23<16:01,  4.58it/s]
                                                    

 60%|██████    | 6661/11066 [24:23<16:01,  4.58it/s]
 60%|██████    | 6662/11066 [24:24<16:00,  4.59it/s]
                                                    

 60%|██████    | 6662/11066 [24:24<16:00,  4.59it/s]
 60%|██████    | 6663/11066 [24:24<16:02,  4.58it/s]
                                                    

 60%|██████    | 6663/11066 [24:24<16:02,  4.58it/s]
 60%|██████    | 6664/11066 [24:24<15:58,  4.59it/s]
                                                    

 60%|██████    | 6664/11066 [24:24<15:58,  4.59it/s]
 60%|██████    | 6665/11066 [24:24<15:48,  4.64it/s]
                                                    

 60%|██████    | 6665/11066 [24:24<15:48,  4.64it/s]
 60%|██████    | 6666/11066 [24:24<15:38,  4.69it/s]
                                                    

 60%|██████    | 6666/11066 [24:24<15:38,  4.69it/s]
 60%|██████    | 6667/11066 [24:25<15:39,  4.68it/s]
                                                    

 60%|██████    | 6667/11066 [24:25<15:39,  4.68it/s]
 60%|██████    | 6668/11066 [24:25<15:44,  4.66it/s]
                                                    

 60%|██████    | 6668/11066 [24:25<15:44,  4.66it/s]
 60%|██████    | 6669/11066 [24:25<15:46,  4.64it/s]
                                                    

 60%|██████    | 6669/11066 [24:25<15:46,  4.64it/s]
 60%|██████    | 6670/11066 [24:25<15:56,  4.60it/s]
                                                    

 60%|██████    | 6670/11066 [24:25<15:56,  4.60it/s]
 60%|██████    | 6671/11066 [24:25<15:57,  4.59it/s]
                                                    

 60%|██████    | 6671/11066 [24:25<15:57,  4.59it/s]
 60%|██████    | 6672/11066 [24:26<15:56,  4.59it/s]
                                                    

 60%|██████    | 6672/11066 [24:26<15:56,  4.59it/s]
 60%|██████    | 6673/11066 [24:26<15:48,  4.63it/s]
                                                    

 60%|██████    | 6673/11066 [24:26<15:48,  4.63it/s]
 60%|██████    | 6674/11066 [24:26<15:42,  4.66it/s]
                                                    

 60%|██████    | 6674/11066 [24:26<15:42,  4.66it/s]
 60%|██████    | 6675/11066 [24:26<15:39,  4.67it/s]
                                                    

 60%|██████    | 6675/11066 [24:26<15:39,  4.67it/s]
 60%|██████    | 6676/11066 [24:27<15:37,  4.68it/s]
                                                    

 60%|██████    | 6676/11066 [24:27<15:37,  4.68it/s]
 60%|██████    | 6677/11066 [24:27<15:49,  4.62it/s]
                                                    

 60%|██████    | 6677/11066 [24:27<15:49,  4.62it/s]
 60%|██████    | 6678/11066 [24:27<15:43,  4.65it/s]
                                                    

 60%|██████    | 6678/11066 [24:27<15:43,  4.65it/s]
 60%|██████    | 6679/11066 [24:27<15:39,  4.67it/s]
                                                    

 60%|██████    | 6679/11066 [24:27<15:39,  4.67it/s]
 60%|██████    | 6680/11066 [24:27<15:42,  4.66it/s]
                                                    

 60%|██████    | 6680/11066 [24:27<15:42,  4.66it/s]
 60%|██████    | 6681/11066 [24:28<15:53,  4.60it/s]
                                                    

 60%|██████    | 6681/11066 [24:28<15:53,  4.60it/s]
 60%|██████    | 6682/11066 [24:28<15:43,  4.64it/s]
                                                    

 60%|██████    | 6682/11066 [24:28<15:43,  4.64it/s]
 60%|██████    | 6683/11066 [24:28<15:44,  4.64it/s]
                                                    

 60%|██████    | 6683/11066 [24:28<15:44,  4.64it/s]
 60%|██████    | 6684/11066 [24:28<15:39,  4.66it/s]
                                                    

 60%|██████    | 6684/11066 [24:28<15:39,  4.66it/s]
 60%|██████    | 6685/11066 [24:28<15:37,  4.67it/s]
                                                    

 60%|██████    | 6685/11066 [24:28<15:37,  4.67it/s]
 60%|██████    | 6686/11066 [24:29<15:36,  4.68it/s]
                                                    

 60%|██████    | 6686/11066 [24:29<15:36,  4.68it/s]
 60%|██████    | 6687/11066 [24:29<15:41,  4.65it/s]
                                                    

 60%|██████    | 6687/11066 [24:29<15:41,  4.65it/s]
 60%|██████    | 6688/11066 [24:29<15:39,  4.66it/s]
                                                    

 60%|██████    | 6688/11066 [24:29<15:39,  4.66it/s]
 60%|██████    | 6689/11066 [24:29<15:40,  4.65it/s]
                                                    

 60%|██████    | 6689/11066 [24:29<15:40,  4.65it/s]
 60%|██████    | 6690/11066 [24:30<15:50,  4.60it/s]
                                                    

 60%|██████    | 6690/11066 [24:30<15:50,  4.60it/s]
 60%|██████    | 6691/11066 [24:30<15:57,  4.57it/s]
                                                    

 60%|██████    | 6691/11066 [24:30<15:57,  4.57it/s]
 60%|██████    | 6692/11066 [24:30<15:54,  4.58it/s]
                                                    

 60%|██████    | 6692/11066 [24:30<15:54,  4.58it/s]
 60%|██████    | 6693/11066 [24:30<16:00,  4.55it/s]
                                                    

 60%|██████    | 6693/11066 [24:30<16:00,  4.55it/s]
 60%|██████    | 6694/11066 [24:30<16:08,  4.52it/s]
                                                    

 60%|██████    | 6694/11066 [24:30<16:08,  4.52it/s]
 61%|██████    | 6695/11066 [24:31<16:26,  4.43it/s]
                                                    

 61%|██████    | 6695/11066 [24:31<16:26,  4.43it/s]
 61%|██████    | 6696/11066 [24:31<16:15,  4.48it/s]
                                                    

 61%|██████    | 6696/11066 [24:31<16:15,  4.48it/s]
 61%|██████    | 6697/11066 [24:31<16:17,  4.47it/s]
                                                    

 61%|██████    | 6697/11066 [24:31<16:17,  4.47it/s]
 61%|██████    | 6698/11066 [24:31<16:18,  4.47it/s]
                                                    

 61%|██████    | 6698/11066 [24:31<16:18,  4.47it/s]
 61%|██████    | 6699/11066 [24:32<16:09,  4.51it/s]
                                                    

 61%|██████    | 6699/11066 [24:32<16:09,  4.51it/s]
 61%|██████    | 6700/11066 [24:32<15:52,  4.58it/s]
                                                    

 61%|██████    | 6700/11066 [24:32<15:52,  4.58it/s]
 61%|██████    | 6701/11066 [24:32<15:50,  4.59it/s]
                                                    

 61%|██████    | 6701/11066 [24:32<15:50,  4.59it/s]
 61%|██████    | 6702/11066 [24:32<15:47,  4.61it/s]
                                                    

 61%|██████    | 6702/11066 [24:32<15:47,  4.61it/s]
 61%|██████    | 6703/11066 [24:32<16:12,  4.49it/s]
                                                    

 61%|██████    | 6703/11066 [24:32<16:12,  4.49it/s]
 61%|██████    | 6704/11066 [24:33<16:21,  4.44it/s]
                                                    

 61%|██████    | 6704/11066 [24:33<16:21,  4.44it/s]
 61%|██████    | 6705/11066 [24:33<16:11,  4.49it/s]
                                                    

 61%|██████    | 6705/11066 [24:33<16:11,  4.49it/s]
 61%|██████    | 6706/11066 [24:33<15:53,  4.57it/s]
                                                    

 61%|██████    | 6706/11066 [24:33<15:53,  4.57it/s]
 61%|██████    | 6707/11066 [24:33<15:46,  4.61it/s]
                                                    

 61%|██████    | 6707/11066 [24:33<15:46,  4.61it/s]
 61%|██████    | 6708/11066 [24:34<15:39,  4.64it/s]
                                                    

 61%|██████    | 6708/11066 [24:34<15:39,  4.64it/s]
 61%|██████    | 6709/11066 [24:34<15:49,  4.59it/s]
                                                    

 61%|██████    | 6709/11066 [24:34<15:49,  4.59it/s]
 61%|██████    | 6710/11066 [24:34<15:44,  4.61it/s]
                                                    

 61%|██████    | 6710/11066 [24:34<15:44,  4.61it/s]
 61%|██████    | 6711/11066 [24:34<15:38,  4.64it/s]
                                                    

 61%|██████    | 6711/11066 [24:34<15:38,  4.64it/s]
 61%|██████    | 6712/11066 [24:34<15:34,  4.66it/s]
                                                    

 61%|██████    | 6712/11066 [24:34<15:34,  4.66it/s]
 61%|██████    | 6713/11066 [24:35<15:31,  4.67it/s]
                                                    

 61%|██████    | 6713/11066 [24:35<15:31,  4.67it/s]
 61%|██████    | 6714/11066 [24:35<15:41,  4.62it/s]
                                                    

 61%|██████    | 6714/11066 [24:35<15:41,  4.62it/s]
 61%|██████    | 6715/11066 [24:35<15:41,  4.62it/s]
                                                    

 61%|██████    | 6715/11066 [24:35<15:41,  4.62it/s]
 61%|██████    | 6716/11066 [24:35<15:51,  4.57it/s]
                                                    

 61%|██████    | 6716/11066 [24:35<15:51,  4.57it/s]
 61%|██████    | 6717/11066 [24:35<15:59,  4.53it/s]
                                                    

 61%|██████    | 6717/11066 [24:36<15:59,  4.53it/s]
 61%|██████    | 6718/11066 [24:36<16:01,  4.52it/s]
                                                    

 61%|██████    | 6718/11066 [24:36<16:01,  4.52it/s]
 61%|██████    | 6719/11066 [24:36<15:56,  4.55it/s]
                                                    

 61%|██████    | 6719/11066 [24:36<15:56,  4.55it/s]
 61%|██████    | 6720/11066 [24:36<15:48,  4.58it/s]
                                                    

 61%|██████    | 6720/11066 [24:36<15:48,  4.58it/s]
 61%|██████    | 6721/11066 [24:36<15:46,  4.59it/s]
                                                    

 61%|██████    | 6721/11066 [24:36<15:46,  4.59it/s]
 61%|██████    | 6722/11066 [24:37<15:54,  4.55it/s]
                                                    

 61%|██████    | 6722/11066 [24:37<15:54,  4.55it/s]
 61%|██████    | 6723/11066 [24:37<15:57,  4.54it/s]
                                                    

 61%|██████    | 6723/11066 [24:37<15:57,  4.54it/s]
 61%|██████    | 6724/11066 [24:37<16:01,  4.52it/s]
                                                    

 61%|██████    | 6724/11066 [24:37<16:01,  4.52it/s]
 61%|██████    | 6725/11066 [24:37<16:02,  4.51it/s]
                                                    

 61%|██████    | 6725/11066 [24:37<16:02,  4.51it/s]
 61%|██████    | 6726/11066 [24:37<16:03,  4.50it/s]
                                                    

 61%|██████    | 6726/11066 [24:37<16:03,  4.50it/s]
 61%|██████    | 6727/11066 [24:38<15:56,  4.54it/s]
                                                    

 61%|██████    | 6727/11066 [24:38<15:56,  4.54it/s]
 61%|██████    | 6728/11066 [24:38<15:47,  4.58it/s]
                                                    

 61%|██████    | 6728/11066 [24:38<15:47,  4.58it/s]
 61%|██████    | 6729/11066 [24:38<15:40,  4.61it/s]
                                                    

 61%|██████    | 6729/11066 [24:38<15:40,  4.61it/s]
 61%|██████    | 6730/11066 [24:38<15:33,  4.64it/s]
                                                    

 61%|██████    | 6730/11066 [24:38<15:33,  4.64it/s]
 61%|██████    | 6731/11066 [24:39<15:45,  4.58it/s]
                                                    

 61%|██████    | 6731/11066 [24:39<15:45,  4.58it/s]
 61%|██████    | 6732/11066 [24:39<15:53,  4.54it/s]
                                                    

 61%|██████    | 6732/11066 [24:39<15:53,  4.54it/s]
 61%|██████    | 6733/11066 [24:39<15:57,  4.53it/s]
                                                    

 61%|██████    | 6733/11066 [24:39<15:57,  4.53it/s]
 61%|██████    | 6734/11066 [24:39<15:55,  4.53it/s]
                                                    

 61%|██████    | 6734/11066 [24:39<15:55,  4.53it/s]
 61%|██████    | 6735/11066 [24:39<16:00,  4.51it/s]
                                                    

 61%|██████    | 6735/11066 [24:39<16:00,  4.51it/s]
 61%|██████    | 6736/11066 [24:40<15:55,  4.53it/s]
                                                    

 61%|██████    | 6736/11066 [24:40<15:55,  4.53it/s]
 61%|██████    | 6737/11066 [24:40<15:50,  4.56it/s]
                                                    

 61%|██████    | 6737/11066 [24:40<15:50,  4.56it/s]
 61%|██████    | 6738/11066 [24:40<15:54,  4.53it/s]
                                                    

 61%|██████    | 6738/11066 [24:40<15:54,  4.53it/s]
 61%|██████    | 6739/11066 [24:40<15:57,  4.52it/s]
                                                    

 61%|██████    | 6739/11066 [24:40<15:57,  4.52it/s]
 61%|██████    | 6740/11066 [24:41<15:59,  4.51it/s]
                                                    

 61%|██████    | 6740/11066 [24:41<15:59,  4.51it/s]
 61%|██████    | 6741/11066 [24:41<15:51,  4.54it/s]
                                                    

 61%|██████    | 6741/11066 [24:41<15:51,  4.54it/s]
 61%|██████    | 6742/11066 [24:41<15:43,  4.58it/s]
                                                    

 61%|██████    | 6742/11066 [24:41<15:43,  4.58it/s]
 61%|██████    | 6743/11066 [24:41<15:35,  4.62it/s]
                                                    

 61%|██████    | 6743/11066 [24:41<15:35,  4.62it/s]
 61%|██████    | 6744/11066 [24:41<15:35,  4.62it/s]
                                                    

 61%|██████    | 6744/11066 [24:41<15:35,  4.62it/s]
 61%|██████    | 6745/11066 [24:42<15:29,  4.65it/s]
                                                    

 61%|██████    | 6745/11066 [24:42<15:29,  4.65it/s]
 61%|██████    | 6746/11066 [24:42<15:27,  4.66it/s]
                                                    

 61%|██████    | 6746/11066 [24:42<15:27,  4.66it/s]
 61%|██████    | 6747/11066 [24:42<15:24,  4.67it/s]
                                                    

 61%|██████    | 6747/11066 [24:42<15:24,  4.67it/s]
 61%|██████    | 6748/11066 [24:42<15:21,  4.68it/s]
                                                    

 61%|██████    | 6748/11066 [24:42<15:21,  4.68it/s]
 61%|██████    | 6749/11066 [24:42<15:20,  4.69it/s]
                                                    
{'loss': 0.4686, 'learning_rate': 1.2009759624073739e-05, 'epoch': 1.2}
{'loss': 0.4224, 'learning_rate': 1.200704861738659e-05, 'epoch': 1.2}
{'loss': 0.6891, 'learning_rate': 1.2004337610699441e-05, 'epoch': 1.2}
{'loss': 0.9522, 'learning_rate': 1.200162660401229e-05, 'epoch': 1.2}
{'loss': 0.726, 'learning_rate': 1.199891559732514e-05, 'epoch': 1.2}
{'loss': 0.8303, 'learning_rate': 1.1996204590637992e-05, 'epoch': 1.2}
{'loss': 1.0954, 'learning_rate': 1.1993493583950842e-05, 'epoch': 1.2}
{'loss': 0.9115, 'learning_rate': 1.199078257726369e-05, 'epoch': 1.2}
{'loss': 0.6196, 'learning_rate': 1.198807157057654e-05, 'epoch': 1.2}
{'loss': 0.8324, 'learning_rate': 1.1985360563889392e-05, 'epoch': 1.2}
{'loss': 0.9563, 'learning_rate': 1.1982649557202242e-05, 'epoch': 1.2}
{'loss': 0.7134, 'learning_rate': 1.197993855051509e-05, 'epoch': 1.2}
{'loss': 0.1742, 'learning_rate': 1.1977227543827942e-05, 'epoch': 1.2}
{'loss': 0.6277, 'learning_rate': 1.1974516537140793e-05, 'epoch': 1.2}
{'loss': 0.9776, 'learning_rate': 1.1971805530453643e-05, 'epoch': 1.2}
{'loss': 0.6442, 'learning_rate': 1.1969094523766491e-05, 'epoch': 1.2}
{'loss': 0.7641, 'learning_rate': 1.1966383517079343e-05, 'epoch': 1.2}
{'loss': 0.8408, 'learning_rate': 1.1963672510392193e-05, 'epoch': 1.2}
{'loss': 0.7479, 'learning_rate': 1.1960961503705043e-05, 'epoch': 1.2}
{'loss': 0.7017, 'learning_rate': 1.1958250497017892e-05, 'epoch': 1.2}
{'loss': 0.605, 'learning_rate': 1.1955539490330744e-05, 'epoch': 1.2}
{'loss': 0.6104, 'learning_rate': 1.1952828483643594e-05, 'epoch': 1.2}
{'loss': 0.8632, 'learning_rate': 1.1950117476956444e-05, 'epoch': 1.2}
{'loss': 0.9794, 'learning_rate': 1.1947406470269294e-05, 'epoch': 1.2}
{'loss': 0.799, 'learning_rate': 1.1944695463582144e-05, 'epoch': 1.2}
{'loss': 0.8647, 'learning_rate': 1.1941984456894994e-05, 'epoch': 1.2}
{'loss': 1.048, 'learning_rate': 1.1939273450207844e-05, 'epoch': 1.2}
{'loss': 0.7605, 'learning_rate': 1.1936562443520694e-05, 'epoch': 1.2}
{'loss': 0.874, 'learning_rate': 1.1933851436833545e-05, 'epoch': 1.2}
{'loss': 0.9914, 'learning_rate': 1.1931140430146395e-05, 'epoch': 1.2}
{'loss': 0.347, 'learning_rate': 1.1928429423459245e-05, 'epoch': 1.2}
{'loss': 0.7608, 'learning_rate': 1.1925718416772095e-05, 'epoch': 1.2}
{'loss': 0.9772, 'learning_rate': 1.1923007410084945e-05, 'epoch': 1.21}
{'loss': 1.116, 'learning_rate': 1.1920296403397795e-05, 'epoch': 1.21}
{'loss': 0.7087, 'learning_rate': 1.1917585396710647e-05, 'epoch': 1.21}
{'loss': 0.3347, 'learning_rate': 1.1914874390023496e-05, 'epoch': 1.21}
{'loss': 0.7175, 'learning_rate': 1.1912163383336346e-05, 'epoch': 1.21}
{'loss': 0.8057, 'learning_rate': 1.1909452376649196e-05, 'epoch': 1.21}
{'loss': 0.892, 'learning_rate': 1.1906741369962048e-05, 'epoch': 1.21}
{'loss': 1.088, 'learning_rate': 1.1904030363274896e-05, 'epoch': 1.21}
{'loss': 1.1839, 'learning_rate': 1.1901319356587746e-05, 'epoch': 1.21}
{'loss': 0.6793, 'learning_rate': 1.1898608349900596e-05, 'epoch': 1.21}
{'loss': 1.0384, 'learning_rate': 1.1895897343213448e-05, 'epoch': 1.21}
{'loss': 0.4471, 'learning_rate': 1.1893186336526297e-05, 'epoch': 1.21}
{'loss': 0.8522, 'learning_rate': 1.1890475329839147e-05, 'epoch': 1.21}
{'loss': 0.7664, 'learning_rate': 1.1887764323151999e-05, 'epoch': 1.21}
{'loss': 0.5078, 'learning_rate': 1.1885053316464849e-05, 'epoch': 1.21}
{'loss': 0.4592, 'learning_rate': 1.1882342309777697e-05, 'epoch': 1.21}
{'loss': 0.6838, 'learning_rate': 1.1879631303090547e-05, 'epoch': 1.21}
{'loss': 0.5781, 'learning_rate': 1.1876920296403399e-05, 'epoch': 1.21}
{'loss': 0.565, 'learning_rate': 1.187420928971625e-05, 'epoch': 1.21}
{'loss': 0.2057, 'learning_rate': 1.1871498283029098e-05, 'epoch': 1.21}
{'loss': 0.9536, 'learning_rate': 1.1868787276341948e-05, 'epoch': 1.21}
{'loss': 0.8723, 'learning_rate': 1.18660762696548e-05, 'epoch': 1.21}
{'loss': 1.5269, 'learning_rate': 1.186336526296765e-05, 'epoch': 1.21}
{'loss': 0.8074, 'learning_rate': 1.1860654256280498e-05, 'epoch': 1.21}
{'loss': 1.4261, 'learning_rate': 1.185794324959335e-05, 'epoch': 1.21}
{'loss': 0.3773, 'learning_rate': 1.18552322429062e-05, 'epoch': 1.21}
{'loss': 0.4411, 'learning_rate': 1.1852521236219049e-05, 'epoch': 1.21}
{'loss': 0.6681, 'learning_rate': 1.1849810229531899e-05, 'epoch': 1.21}
{'loss': 0.6053, 'learning_rate': 1.184709922284475e-05, 'epoch': 1.21}
{'loss': 0.4049, 'learning_rate': 1.18443882161576e-05, 'epoch': 1.21}
{'loss': 0.4753, 'learning_rate': 1.184167720947045e-05, 'epoch': 1.21}
{'loss': 0.7444, 'learning_rate': 1.18389662027833e-05, 'epoch': 1.21}
{'loss': 0.9939, 'learning_rate': 1.1836255196096151e-05, 'epoch': 1.21}
{'loss': 0.7566, 'learning_rate': 1.1833544189409001e-05, 'epoch': 1.21}
{'loss': 0.9627, 'learning_rate': 1.183083318272185e-05, 'epoch': 1.21}
{'loss': 0.471, 'learning_rate': 1.1828122176034702e-05, 'epoch': 1.21}
{'loss': 1.1481, 'learning_rate': 1.1825411169347552e-05, 'epoch': 1.21}
{'loss': 0.8515, 'learning_rate': 1.1822700162660402e-05, 'epoch': 1.21}
{'loss': 0.916, 'learning_rate': 1.181998915597325e-05, 'epoch': 1.21}
{'loss': 0.3349, 'learning_rate': 1.1817278149286102e-05, 'epoch': 1.21}
{'loss': 0.719, 'learning_rate': 1.1814567142598952e-05, 'epoch': 1.21}
{'loss': 0.4969, 'learning_rate': 1.1811856135911802e-05, 'epoch': 1.21}
{'loss': 1.8959, 'learning_rate': 1.180914512922465e-05, 'epoch': 1.21}
{'loss': 0.7535, 'learning_rate': 1.1806434122537503e-05, 'epoch': 1.21}
{'loss': 0.8415, 'learning_rate': 1.1803723115850353e-05, 'epoch': 1.21}
{'loss': 0.316, 'learning_rate': 1.1801012109163203e-05, 'epoch': 1.21}
{'loss': 0.2819, 'learning_rate': 1.1798301102476053e-05, 'epoch': 1.21}
{'loss': 0.4256, 'learning_rate': 1.1795590095788903e-05, 'epoch': 1.21}
{'loss': 0.4168, 'learning_rate': 1.1792879089101753e-05, 'epoch': 1.21}
{'loss': 0.5197, 'learning_rate': 1.1790168082414603e-05, 'epoch': 1.21}
{'loss': 0.9711, 'learning_rate': 1.1787457075727454e-05, 'epoch': 1.21}
{'loss': 0.5571, 'learning_rate': 1.1784746069040304e-05, 'epoch': 1.21}
{'loss': 0.4059, 'learning_rate': 1.1782035062353154e-05, 'epoch': 1.21}
{'loss': 0.561, 'learning_rate': 1.1779324055666004e-05, 'epoch': 1.21}
{'loss': 0.7873, 'learning_rate': 1.1776613048978854e-05, 'epoch': 1.21}
{'loss': 0.888, 'learning_rate': 1.1773902042291704e-05, 'epoch': 1.22}
{'loss': 0.8873, 'learning_rate': 1.1771191035604554e-05, 'epoch': 1.22}
{'loss': 0.7664, 'learning_rate': 1.1768480028917406e-05, 'epoch': 1.22}
{'loss': 0.4909, 'learning_rate': 1.1765769022230255e-05, 'epoch': 1.22}
{'loss': 0.3441, 'learning_rate': 1.1763058015543105e-05, 'epoch': 1.22}
{'loss': 0.8432, 'learning_rate': 1.1760347008855955e-05, 'epoch': 1.22}
{'loss': 0.6074, 'learning_rate': 1.1757636002168807e-05, 'epoch': 1.22}
{'loss': 0.7976, 'learning_rate': 1.1754924995481655e-05, 'epoch': 1.22}
{'loss': 0.4777, 'learning_rate': 1.1752213988794505e-05, 'epoch': 1.22}
{'loss': 0.5164, 'learning_rate': 1.1749502982107357e-05, 'epoch': 1.22}
{'loss': 0.8684, 'learning_rate': 1.1746791975420207e-05, 'epoch': 1.22}
{'loss': 0.4811, 'learning_rate': 1.1744080968733056e-05, 'epoch': 1.22}
{'loss': 0.8935, 'learning_rate': 1.1741369962045906e-05, 'epoch': 1.22}
{'loss': 0.2007, 'learning_rate': 1.1738658955358758e-05, 'epoch': 1.22}
{'loss': 1.2846, 'learning_rate': 1.1735947948671608e-05, 'epoch': 1.22}
{'loss': 0.5166, 'learning_rate': 1.1733236941984456e-05, 'epoch': 1.22}
{'loss': 0.3892, 'learning_rate': 1.1730525935297306e-05, 'epoch': 1.22}
{'loss': 0.6265, 'learning_rate': 1.1727814928610158e-05, 'epoch': 1.22}
{'loss': 0.9424, 'learning_rate': 1.1725103921923008e-05, 'epoch': 1.22}
{'loss': 0.572, 'learning_rate': 1.1722392915235857e-05, 'epoch': 1.22}
{'loss': 0.6178, 'learning_rate': 1.1719681908548709e-05, 'epoch': 1.22}
{'loss': 1.0315, 'learning_rate': 1.1716970901861559e-05, 'epoch': 1.22}
{'loss': 0.8011, 'learning_rate': 1.1714259895174409e-05, 'epoch': 1.22}
{'loss': 0.9047, 'learning_rate': 1.1711548888487257e-05, 'epoch': 1.22}
{'loss': 0.581, 'learning_rate': 1.1708837881800109e-05, 'epoch': 1.22}
{'loss': 0.7391, 'learning_rate': 1.170612687511296e-05, 'epoch': 1.22}

 61%|██████    | 6749/11066 [24:42<15:20,  4.69it/s]
 61%|██████    | 6750/11066 [24:43<15:33,  4.62it/s]
                                                    

 61%|██████    | 6750/11066 [24:43<15:33,  4.62it/s]
 61%|██████    | 6751/11066 [24:43<15:28,  4.65it/s]
                                                    

 61%|██████    | 6751/11066 [24:43<15:28,  4.65it/s]
 61%|██████    | 6752/11066 [24:43<15:39,  4.59it/s]
                                                    

 61%|██████    | 6752/11066 [24:43<15:39,  4.59it/s]
 61%|██████    | 6753/11066 [24:43<15:44,  4.56it/s]
                                                    

 61%|██████    | 6753/11066 [24:43<15:44,  4.56it/s]
 61%|██████    | 6754/11066 [24:44<15:48,  4.55it/s]
                                                    

 61%|██████    | 6754/11066 [24:44<15:48,  4.55it/s]
 61%|██████    | 6755/11066 [24:44<15:44,  4.57it/s]
                                                    

 61%|██████    | 6755/11066 [24:44<15:44,  4.57it/s]
 61%|██████    | 6756/11066 [24:44<15:38,  4.59it/s]
                                                    

 61%|██████    | 6756/11066 [24:44<15:38,  4.59it/s]
 61%|██████    | 6757/11066 [24:44<15:46,  4.55it/s]
                                                    

 61%|██████    | 6757/11066 [24:44<15:46,  4.55it/s]
 61%|██████    | 6758/11066 [24:44<15:37,  4.59it/s]
                                                    

 61%|██████    | 6758/11066 [24:44<15:37,  4.59it/s]
 61%|██████    | 6759/11066 [24:45<15:37,  4.59it/s]
                                                    

 61%|██████    | 6759/11066 [24:45<15:37,  4.59it/s]
 61%|██████    | 6760/11066 [24:45<15:39,  4.58it/s]
                                                    

 61%|██████    | 6760/11066 [24:45<15:39,  4.58it/s]
 61%|██████    | 6761/11066 [24:45<15:36,  4.60it/s]
                                                    

 61%|██████    | 6761/11066 [24:45<15:36,  4.60it/s]
 61%|██████    | 6762/11066 [24:45<15:45,  4.55it/s]
                                                    

 61%|██████    | 6762/11066 [24:45<15:45,  4.55it/s]
 61%|██████    | 6763/11066 [24:46<15:36,  4.59it/s]
                                                    

 61%|██████    | 6763/11066 [24:46<15:36,  4.59it/s]
 61%|██████    | 6764/11066 [24:46<15:44,  4.56it/s]
                                                    

 61%|██████    | 6764/11066 [24:46<15:44,  4.56it/s]
 61%|██████    | 6765/11066 [24:46<15:35,  4.60it/s]
                                                    

 61%|██████    | 6765/11066 [24:46<15:35,  4.60it/s]
 61%|██████    | 6766/11066 [24:46<15:46,  4.54it/s]
                                                    

 61%|██████    | 6766/11066 [24:46<15:46,  4.54it/s]
 61%|██████    | 6767/11066 [24:46<16:05,  4.45it/s]
                                                    

 61%|██████    | 6767/11066 [24:46<16:05,  4.45it/s]
 61%|██████    | 6768/11066 [24:47<16:08,  4.44it/s]
                                                    

 61%|██████    | 6768/11066 [24:47<16:08,  4.44it/s]
 61%|██████    | 6769/11066 [24:47<16:06,  4.44it/s]
                                                    

 61%|██████    | 6769/11066 [24:47<16:06,  4.44it/s]
 61%|██████    | 6770/11066 [24:47<16:04,  4.45it/s]
                                                    

 61%|██████    | 6770/11066 [24:47<16:04,  4.45it/s]
 61%|██████    | 6771/11066 [24:47<16:02,  4.46it/s]
                                                    

 61%|██████    | 6771/11066 [24:47<16:02,  4.46it/s]
 61%|██████    | 6772/11066 [24:48<15:57,  4.49it/s]
                                                    

 61%|██████    | 6772/11066 [24:48<15:57,  4.49it/s]
 61%|██████    | 6773/11066 [24:48<15:58,  4.48it/s]
                                                    

 61%|██████    | 6773/11066 [24:48<15:58,  4.48it/s]
 61%|██████    | 6774/11066 [24:48<15:58,  4.48it/s]
                                                    

 61%|██████    | 6774/11066 [24:48<15:58,  4.48it/s]
 61%|██████    | 6775/11066 [24:48<15:50,  4.52it/s]
                                                    

 61%|██████    | 6775/11066 [24:48<15:50,  4.52it/s]
 61%|██████    | 6776/11066 [24:48<15:46,  4.53it/s]
                                                    

 61%|██████    | 6776/11066 [24:48<15:46,  4.53it/s]
 61%|██████    | 6777/11066 [24:49<15:47,  4.53it/s]
                                                    

 61%|██████    | 6777/11066 [24:49<15:47,  4.53it/s]
 61%|██████▏   | 6778/11066 [24:49<15:49,  4.52it/s]
                                                    

 61%|██████▏   | 6778/11066 [24:49<15:49,  4.52it/s]
 61%|██████▏   | 6779/11066 [24:49<15:51,  4.51it/s]
                                                    

 61%|██████▏   | 6779/11066 [24:49<15:51,  4.51it/s]
 61%|██████▏   | 6780/11066 [24:49<15:52,  4.50it/s]
                                                    

 61%|██████▏   | 6780/11066 [24:49<15:52,  4.50it/s]
 61%|██████▏   | 6781/11066 [24:50<15:41,  4.55it/s]
                                                    

 61%|██████▏   | 6781/11066 [24:50<15:41,  4.55it/s]
 61%|██████▏   | 6782/11066 [24:50<15:49,  4.51it/s]
                                                    

 61%|██████▏   | 6782/11066 [24:50<15:49,  4.51it/s]
 61%|██████▏   | 6783/11066 [24:50<15:51,  4.50it/s]
                                                    

 61%|██████▏   | 6783/11066 [24:50<15:51,  4.50it/s]
 61%|██████▏   | 6784/11066 [24:50<15:45,  4.53it/s]
                                                    

 61%|██████▏   | 6784/11066 [24:50<15:45,  4.53it/s]
 61%|██████▏   | 6785/11066 [24:50<15:51,  4.50it/s]
                                                    

 61%|██████▏   | 6785/11066 [24:50<15:51,  4.50it/s]
 61%|██████▏   | 6786/11066 [24:51<15:53,  4.49it/s]
                                                    

 61%|██████▏   | 6786/11066 [24:51<15:53,  4.49it/s]
 61%|██████▏   | 6787/11066 [24:51<15:54,  4.48it/s]
                                                    

 61%|██████▏   | 6787/11066 [24:51<15:54,  4.48it/s]
 61%|██████▏   | 6788/11066 [24:51<15:53,  4.49it/s]
                                                    

 61%|██████▏   | 6788/11066 [24:51<15:53,  4.49it/s]
 61%|██████▏   | 6789/11066 [24:51<15:52,  4.49it/s]
                                                    

 61%|██████▏   | 6789/11066 [24:51<15:52,  4.49it/s]
 61%|██████▏   | 6790/11066 [24:52<15:53,  4.49it/s]
                                                    

 61%|██████▏   | 6790/11066 [24:52<15:53,  4.49it/s]
 61%|██████▏   | 6791/11066 [24:52<15:53,  4.49it/s]
                                                    

 61%|██████▏   | 6791/11066 [24:52<15:53,  4.49it/s]
 61%|██████▏   | 6792/11066 [24:52<15:51,  4.49it/s]
                                                    

 61%|██████▏   | 6792/11066 [24:52<15:51,  4.49it/s]
 61%|██████▏   | 6793/11066 [24:52<15:51,  4.49it/s]
                                                    

 61%|██████▏   | 6793/11066 [24:52<15:51,  4.49it/s]
 61%|██████▏   | 6794/11066 [24:52<15:51,  4.49it/s]
                                                    

 61%|██████▏   | 6794/11066 [24:52<15:51,  4.49it/s]
 61%|██████▏   | 6795/11066 [24:53<15:50,  4.49it/s]
                                                    

 61%|██████▏   | 6795/11066 [24:53<15:50,  4.49it/s]
 61%|██████▏   | 6796/11066 [24:53<15:48,  4.50it/s]
                                                    

 61%|██████▏   | 6796/11066 [24:53<15:48,  4.50it/s]
 61%|██████▏   | 6797/11066 [24:53<15:47,  4.50it/s]
                                                    

 61%|██████▏   | 6797/11066 [24:53<15:47,  4.50it/s]
 61%|██████▏   | 6798/11066 [24:53<15:47,  4.51it/s]
                                                    

 61%|██████▏   | 6798/11066 [24:53<15:47,  4.51it/s]
 61%|██████▏   | 6799/11066 [24:54<15:46,  4.51it/s]
                                                    

 61%|██████▏   | 6799/11066 [24:54<15:46,  4.51it/s]
 61%|██████▏   | 6800/11066 [24:54<15:39,  4.54it/s]
                                                    

 61%|██████▏   | 6800/11066 [24:54<15:39,  4.54it/s]
 61%|██████▏   | 6801/11066 [24:54<15:45,  4.51it/s]
                                                    

 61%|██████▏   | 6801/11066 [24:54<15:45,  4.51it/s]
 61%|██████▏   | 6802/11066 [24:54<15:47,  4.50it/s]
                                                    

 61%|██████▏   | 6802/11066 [24:54<15:47,  4.50it/s]
 61%|██████▏   | 6803/11066 [24:54<15:34,  4.56it/s]
                                                    

 61%|██████▏   | 6803/11066 [24:54<15:34,  4.56it/s]
 61%|██████▏   | 6804/11066 [24:55<15:37,  4.54it/s]
                                                    

 61%|██████▏   | 6804/11066 [24:55<15:37,  4.54it/s]
 61%|██████▏   | 6805/11066 [24:55<15:40,  4.53it/s]
                                                    

 61%|██████▏   | 6805/11066 [24:55<15:40,  4.53it/s]
 62%|██████▏   | 6806/11066 [24:55<15:35,  4.55it/s]
                                                    

 62%|██████▏   | 6806/11066 [24:55<15:35,  4.55it/s]
 62%|██████▏   | 6807/11066 [24:55<15:44,  4.51it/s]
                                                    

 62%|██████▏   | 6807/11066 [24:55<15:44,  4.51it/s]
 62%|██████▏   | 6808/11066 [24:56<15:45,  4.50it/s]
                                                    

 62%|██████▏   | 6808/11066 [24:56<15:45,  4.50it/s]
 62%|██████▏   | 6809/11066 [24:56<15:38,  4.54it/s]
                                                    

 62%|██████▏   | 6809/11066 [24:56<15:38,  4.54it/s]
 62%|██████▏   | 6810/11066 [24:56<15:44,  4.51it/s]
                                                    

 62%|██████▏   | 6810/11066 [24:56<15:44,  4.51it/s]
 62%|██████▏   | 6811/11066 [24:56<15:46,  4.50it/s]
                                                    

 62%|██████▏   | 6811/11066 [24:56<15:46,  4.50it/s]
 62%|██████▏   | 6812/11066 [24:56<15:39,  4.53it/s]
                                                    

 62%|██████▏   | 6812/11066 [24:56<15:39,  4.53it/s]
 62%|██████▏   | 6813/11066 [24:57<15:44,  4.50it/s]
                                                    

 62%|██████▏   | 6813/11066 [24:57<15:44,  4.50it/s]
 62%|██████▏   | 6814/11066 [24:57<15:45,  4.50it/s]
                                                    

 62%|██████▏   | 6814/11066 [24:57<15:45,  4.50it/s]
 62%|██████▏   | 6815/11066 [24:57<15:45,  4.50it/s]
                                                    

 62%|██████▏   | 6815/11066 [24:57<15:45,  4.50it/s]
 62%|██████▏   | 6816/11066 [24:57<15:45,  4.50it/s]
                                                    

 62%|██████▏   | 6816/11066 [24:57<15:45,  4.50it/s]
 62%|██████▏   | 6817/11066 [24:58<15:44,  4.50it/s]
                                                    

 62%|██████▏   | 6817/11066 [24:58<15:44,  4.50it/s]
 62%|██████▏   | 6818/11066 [24:58<15:31,  4.56it/s]
                                                    

 62%|██████▏   | 6818/11066 [24:58<15:31,  4.56it/s]
 62%|██████▏   | 6819/11066 [24:58<15:34,  4.54it/s]
                                                    

 62%|██████▏   | 6819/11066 [24:58<15:34,  4.54it/s]
 62%|██████▏   | 6820/11066 [24:58<15:38,  4.52it/s]
                                                    

 62%|██████▏   | 6820/11066 [24:58<15:38,  4.52it/s]
 62%|██████▏   | 6821/11066 [24:58<15:40,  4.51it/s]
                                                    

 62%|██████▏   | 6821/11066 [24:58<15:40,  4.51it/s]
 62%|██████▏   | 6822/11066 [24:59<15:43,  4.50it/s]
                                                    

 62%|██████▏   | 6822/11066 [24:59<15:43,  4.50it/s]
 62%|██████▏   | 6823/11066 [24:59<15:42,  4.50it/s]
                                                    

 62%|██████▏   | 6823/11066 [24:59<15:42,  4.50it/s]
 62%|██████▏   | 6824/11066 [24:59<15:46,  4.48it/s]
                                                    

 62%|██████▏   | 6824/11066 [24:59<15:46,  4.48it/s]
 62%|██████▏   | 6825/11066 [24:59<15:39,  4.51it/s]
                                                    

 62%|██████▏   | 6825/11066 [24:59<15:39,  4.51it/s]
 62%|██████▏   | 6826/11066 [25:00<15:35,  4.53it/s]
                                                    

 62%|██████▏   | 6826/11066 [25:00<15:35,  4.53it/s]
 62%|██████▏   | 6827/11066 [25:00<15:32,  4.55it/s]
                                                    

 62%|██████▏   | 6827/11066 [25:00<15:32,  4.55it/s]
 62%|██████▏   | 6828/11066 [25:00<15:29,  4.56it/s]
                                                    

 62%|██████▏   | 6828/11066 [25:00<15:29,  4.56it/s]
 62%|██████▏   | 6829/11066 [25:00<15:31,  4.55it/s]
                                                    

 62%|██████▏   | 6829/11066 [25:00<15:31,  4.55it/s]
 62%|██████▏   | 6830/11066 [25:00<15:27,  4.57it/s]
                                                    

 62%|██████▏   | 6830/11066 [25:00<15:27,  4.57it/s]
 62%|██████▏   | 6831/11066 [25:01<15:34,  4.53it/s]
                                                    

 62%|██████▏   | 6831/11066 [25:01<15:34,  4.53it/s]
 62%|██████▏   | 6832/11066 [25:01<15:30,  4.55it/s]
                                                    

 62%|██████▏   | 6832/11066 [25:01<15:30,  4.55it/s]
 62%|██████▏   | 6833/11066 [25:01<15:30,  4.55it/s]
                                                    

 62%|██████▏   | 6833/11066 [25:01<15:30,  4.55it/s]
 62%|██████▏   | 6834/11066 [25:01<15:17,  4.61it/s]
                                                    

 62%|██████▏   | 6834/11066 [25:01<15:17,  4.61it/s]
 62%|██████▏   | 6835/11066 [25:01<15:13,  4.63it/s]
                                                    

 62%|██████▏   | 6835/11066 [25:01<15:13,  4.63it/s]
 62%|██████▏   | 6836/11066 [25:02<15:20,  4.60it/s]
                                                    

 62%|██████▏   | 6836/11066 [25:02<15:20,  4.60it/s]
 62%|██████▏   | 6837/11066 [25:02<15:25,  4.57it/s]
                                                    

 62%|██████▏   | 6837/11066 [25:02<15:25,  4.57it/s]
 62%|██████▏   | 6838/11066 [25:02<15:28,  4.55it/s]
                                                    

 62%|██████▏   | 6838/11066 [25:02<15:28,  4.55it/s]
 62%|██████▏   | 6839/11066 [25:02<15:34,  4.52it/s]
                                                    

 62%|██████▏   | 6839/11066 [25:02<15:34,  4.52it/s]
 62%|██████▏   | 6840/11066 [25:03<15:25,  4.57it/s]
                                                    

 62%|██████▏   | 6840/11066 [25:03<15:25,  4.57it/s]
 62%|██████▏   | 6841/11066 [25:03<15:34,  4.52it/s]
                                                    

 62%|██████▏   | 6841/11066 [25:03<15:34,  4.52it/s]
 62%|██████▏   | 6842/11066 [25:03<15:28,  4.55it/s]
                                                    

 62%|██████▏   | 6842/11066 [25:03<15:28,  4.55it/s]
 62%|██████▏   | 6843/11066 [25:03<15:35,  4.52it/s]
                                                    

 62%|██████▏   | 6843/11066 [25:03<15:35,  4.52it/s]
 62%|██████▏   | 6844/11066 [25:03<15:40,  4.49it/s]
                                                    

 62%|██████▏   | 6844/11066 [25:03<15:40,  4.49it/s]
 62%|██████▏   | 6845/11066 [25:04<15:27,  4.55it/s]
                                                    

 62%|██████▏   | 6845/11066 [25:04<15:27,  4.55it/s]
 62%|██████▏   | 6846/11066 [25:04<15:20,  4.58it/s]
                                                    

 62%|██████▏   | 6846/11066 [25:04<15:20,  4.58it/s]
 62%|██████▏   | 6847/11066 [25:04<15:07,  4.65it/s]
                                                    

 62%|██████▏   | 6847/11066 [25:04<15:07,  4.65it/s]
 62%|██████▏   | 6848/11066 [25:04<15:13,  4.62it/s]
                                                    

 62%|██████▏   | 6848/11066 [25:04<15:13,  4.62it/s]
 62%|██████▏   | 6849/11066 [25:05<15:15,  4.61it/s]
                                                    

 62%|██████▏   | 6849/11066 [25:05<15:15,  4.61it/s]
 62%|██████▏   | 6850/11066 [25:05<15:08,  4.64it/s]
                                                    

 62%|██████▏   | 6850/11066 [25:05<15:08,  4.64it/s]
 62%|██████▏   | 6851/11066 [25:05<15:00,  4.68it/s]
                                                    

 62%|██████▏   | 6851/11066 [25:05<15:00,  4.68it/s]
 62%|██████▏   | 6852/11066 [25:05<15:05,  4.65it/s]
                                                    

 62%|██████▏   | 6852/11066 [25:05<15:05,  4.65it/s]
 62%|██████▏   | 6853/11066 [25:05<15:16,  4.60it/s]
                                                    

 62%|██████▏   | 6853/11066 [25:05<15:16,  4.60it/s]
 62%|██████▏   | 6854/11066 [25:06<15:17,  4.59it/s]
                                                    

 62%|██████▏   | 6854/11066 [25:06<15:17,  4.59it/s]
 62%|██████▏   | 6855/11066 [25:06<15:10,  4.62it/s]
                                                    

 62%|██████▏   | 6855/11066 [25:06<15:10,  4.62it/s]
 62%|██████▏   | 6856/11066 [25:06<15:04,  4.66it/s]
                                                    

 62%|██████▏   | 6856/11066 [25:06<15:04,  4.66it/s]
 62%|██████▏   | 6857/11066 [25:06<15:00,  4.67it/s]
                                                    

 62%|██████▏   | 6857/11066 [25:06<15:00,  4.67it/s]
 62%|██████▏   | 6858/11066 [25:06<14:57,  4.69it/s]
                                                    

 62%|██████▏   | 6858/11066 [25:06<14:57,  4.69it/s]
 62%|██████▏   | 6859/11066 [25:07<15:08,  4.63it/s]
                                                    

 62%|██████▏   | 6859/11066 [25:07<15:08,  4.63it/s]
 62%|██████▏   | 6860/11066 [25:07<15:04,  4.65it/s]
                                                    

 62%|██████▏   | 6860/11066 [25:07<15:04,  4.65it/s]
 62%|██████▏   | 6861/11066 [25:07<15:00,  4.67it/s]
                                                    
{'loss': 0.3121, 'learning_rate': 1.170341586842581e-05, 'epoch': 1.22}
{'loss': 0.913, 'learning_rate': 1.1700704861738658e-05, 'epoch': 1.22}
{'loss': 0.4636, 'learning_rate': 1.169799385505151e-05, 'epoch': 1.22}
{'loss': 0.9814, 'learning_rate': 1.169528284836436e-05, 'epoch': 1.22}
{'loss': 0.4006, 'learning_rate': 1.169257184167721e-05, 'epoch': 1.22}
{'loss': 0.6563, 'learning_rate': 1.168986083499006e-05, 'epoch': 1.22}
{'loss': 0.3115, 'learning_rate': 1.168714982830291e-05, 'epoch': 1.22}
{'loss': 0.6904, 'learning_rate': 1.168443882161576e-05, 'epoch': 1.22}
{'loss': 0.4753, 'learning_rate': 1.168172781492861e-05, 'epoch': 1.22}
{'loss': 1.0419, 'learning_rate': 1.167901680824146e-05, 'epoch': 1.22}
{'loss': 0.453, 'learning_rate': 1.167630580155431e-05, 'epoch': 1.22}
{'loss': 0.4925, 'learning_rate': 1.1673594794867161e-05, 'epoch': 1.22}
{'loss': 0.6016, 'learning_rate': 1.1670883788180011e-05, 'epoch': 1.22}
{'loss': 0.9623, 'learning_rate': 1.1668172781492861e-05, 'epoch': 1.22}
{'loss': 0.5758, 'learning_rate': 1.1665461774805711e-05, 'epoch': 1.22}
{'loss': 0.6336, 'learning_rate': 1.1662750768118561e-05, 'epoch': 1.22}
{'loss': 0.7075, 'learning_rate': 1.1660039761431413e-05, 'epoch': 1.22}
{'loss': 0.8526, 'learning_rate': 1.1657328754744262e-05, 'epoch': 1.22}
{'loss': 1.1127, 'learning_rate': 1.1654617748057112e-05, 'epoch': 1.22}
{'loss': 0.5839, 'learning_rate': 1.1651906741369962e-05, 'epoch': 1.22}
{'loss': 0.4878, 'learning_rate': 1.1649195734682814e-05, 'epoch': 1.22}
{'loss': 0.6818, 'learning_rate': 1.1646484727995662e-05, 'epoch': 1.22}
{'loss': 0.3835, 'learning_rate': 1.1643773721308512e-05, 'epoch': 1.22}
{'loss': 1.0338, 'learning_rate': 1.1641062714621362e-05, 'epoch': 1.22}
{'loss': 1.1369, 'learning_rate': 1.1638351707934214e-05, 'epoch': 1.22}
{'loss': 1.2145, 'learning_rate': 1.1635640701247063e-05, 'epoch': 1.22}
{'loss': 0.8426, 'learning_rate': 1.1632929694559913e-05, 'epoch': 1.22}
{'loss': 0.4741, 'learning_rate': 1.1630218687872765e-05, 'epoch': 1.22}
{'loss': 0.8344, 'learning_rate': 1.1627507681185615e-05, 'epoch': 1.22}
{'loss': 0.8859, 'learning_rate': 1.1624796674498463e-05, 'epoch': 1.23}
{'loss': 1.0766, 'learning_rate': 1.1622085667811313e-05, 'epoch': 1.23}
{'loss': 0.4363, 'learning_rate': 1.1619374661124165e-05, 'epoch': 1.23}
{'loss': 0.9984, 'learning_rate': 1.1616663654437015e-05, 'epoch': 1.23}
{'loss': 0.3309, 'learning_rate': 1.1613952647749864e-05, 'epoch': 1.23}
{'loss': 0.9075, 'learning_rate': 1.1611241641062714e-05, 'epoch': 1.23}
{'loss': 1.0762, 'learning_rate': 1.1608530634375566e-05, 'epoch': 1.23}
{'loss': 0.6518, 'learning_rate': 1.1605819627688416e-05, 'epoch': 1.23}
{'loss': 0.8786, 'learning_rate': 1.1603108621001264e-05, 'epoch': 1.23}
{'loss': 1.5716, 'learning_rate': 1.1600397614314116e-05, 'epoch': 1.23}
{'loss': 0.6714, 'learning_rate': 1.1597686607626966e-05, 'epoch': 1.23}
{'loss': 0.8334, 'learning_rate': 1.1594975600939816e-05, 'epoch': 1.23}
{'loss': 0.6749, 'learning_rate': 1.1592264594252665e-05, 'epoch': 1.23}
{'loss': 0.3843, 'learning_rate': 1.1589553587565517e-05, 'epoch': 1.23}
{'loss': 1.4001, 'learning_rate': 1.1586842580878367e-05, 'epoch': 1.23}
{'loss': 0.694, 'learning_rate': 1.1584131574191217e-05, 'epoch': 1.23}
{'loss': 0.929, 'learning_rate': 1.1581420567504067e-05, 'epoch': 1.23}
{'loss': 1.4753, 'learning_rate': 1.1578709560816917e-05, 'epoch': 1.23}
{'loss': 0.6092, 'learning_rate': 1.1575998554129767e-05, 'epoch': 1.23}
{'loss': 0.2423, 'learning_rate': 1.1573287547442618e-05, 'epoch': 1.23}
{'loss': 0.3878, 'learning_rate': 1.1570576540755468e-05, 'epoch': 1.23}
{'loss': 0.6807, 'learning_rate': 1.1567865534068318e-05, 'epoch': 1.23}
{'loss': 0.9788, 'learning_rate': 1.1565154527381168e-05, 'epoch': 1.23}
{'loss': 0.7937, 'learning_rate': 1.1562443520694018e-05, 'epoch': 1.23}
{'loss': 0.6321, 'learning_rate': 1.1559732514006868e-05, 'epoch': 1.23}
{'loss': 0.5548, 'learning_rate': 1.1557021507319718e-05, 'epoch': 1.23}
{'loss': 0.9091, 'learning_rate': 1.1554310500632568e-05, 'epoch': 1.23}
{'loss': 1.6249, 'learning_rate': 1.155159949394542e-05, 'epoch': 1.23}
{'loss': 0.5825, 'learning_rate': 1.1548888487258269e-05, 'epoch': 1.23}
{'loss': 0.6571, 'learning_rate': 1.1546177480571119e-05, 'epoch': 1.23}
{'loss': 1.3844, 'learning_rate': 1.1543466473883969e-05, 'epoch': 1.23}
{'loss': 0.7596, 'learning_rate': 1.154075546719682e-05, 'epoch': 1.23}
{'loss': 1.3036, 'learning_rate': 1.153804446050967e-05, 'epoch': 1.23}
{'loss': 0.4896, 'learning_rate': 1.153533345382252e-05, 'epoch': 1.23}
{'loss': 0.4819, 'learning_rate': 1.153262244713537e-05, 'epoch': 1.23}
{'loss': 0.9002, 'learning_rate': 1.1529911440448221e-05, 'epoch': 1.23}
{'loss': 1.1818, 'learning_rate': 1.152720043376107e-05, 'epoch': 1.23}
{'loss': 0.9201, 'learning_rate': 1.152448942707392e-05, 'epoch': 1.23}
{'loss': 0.5027, 'learning_rate': 1.1521778420386772e-05, 'epoch': 1.23}
{'loss': 0.6419, 'learning_rate': 1.1519067413699622e-05, 'epoch': 1.23}
{'loss': 0.901, 'learning_rate': 1.151635640701247e-05, 'epoch': 1.23}
{'loss': 0.8599, 'learning_rate': 1.151364540032532e-05, 'epoch': 1.23}
{'loss': 0.8811, 'learning_rate': 1.1510934393638172e-05, 'epoch': 1.23}
{'loss': 1.1609, 'learning_rate': 1.150822338695102e-05, 'epoch': 1.23}
{'loss': 0.9348, 'learning_rate': 1.1505512380263871e-05, 'epoch': 1.23}
{'loss': 0.7219, 'learning_rate': 1.1502801373576721e-05, 'epoch': 1.23}
{'loss': 0.3646, 'learning_rate': 1.1500090366889573e-05, 'epoch': 1.23}
{'loss': 0.7937, 'learning_rate': 1.1497379360202421e-05, 'epoch': 1.23}
{'loss': 0.988, 'learning_rate': 1.1494668353515271e-05, 'epoch': 1.23}
{'loss': 0.5307, 'learning_rate': 1.1491957346828123e-05, 'epoch': 1.23}
{'loss': 0.4513, 'learning_rate': 1.1489246340140973e-05, 'epoch': 1.23}
{'loss': 0.2617, 'learning_rate': 1.1486535333453822e-05, 'epoch': 1.23}
{'loss': 0.7294, 'learning_rate': 1.1483824326766672e-05, 'epoch': 1.23}
{'loss': 0.9037, 'learning_rate': 1.1481113320079524e-05, 'epoch': 1.23}
{'loss': 0.4138, 'learning_rate': 1.1478402313392374e-05, 'epoch': 1.23}
{'loss': 1.1285, 'learning_rate': 1.1475691306705222e-05, 'epoch': 1.23}
{'loss': 0.5668, 'learning_rate': 1.1472980300018073e-05, 'epoch': 1.24}
{'loss': 1.2138, 'learning_rate': 1.1470269293330924e-05, 'epoch': 1.24}
{'loss': 1.5432, 'learning_rate': 1.1467558286643774e-05, 'epoch': 1.24}
{'loss': 0.8182, 'learning_rate': 1.1464847279956623e-05, 'epoch': 1.24}
{'loss': 1.3202, 'learning_rate': 1.1462136273269475e-05, 'epoch': 1.24}
{'loss': 0.2133, 'learning_rate': 1.1459425266582325e-05, 'epoch': 1.24}
{'loss': 0.8568, 'learning_rate': 1.1456714259895175e-05, 'epoch': 1.24}
{'loss': 0.6373, 'learning_rate': 1.1454003253208023e-05, 'epoch': 1.24}
{'loss': 1.0704, 'learning_rate': 1.1451292246520875e-05, 'epoch': 1.24}
{'loss': 0.7791, 'learning_rate': 1.1448581239833725e-05, 'epoch': 1.24}
{'loss': 0.299, 'learning_rate': 1.1445870233146576e-05, 'epoch': 1.24}
{'loss': 0.9682, 'learning_rate': 1.1443159226459424e-05, 'epoch': 1.24}
{'loss': 0.85, 'learning_rate': 1.1440448219772276e-05, 'epoch': 1.24}
{'loss': 0.558, 'learning_rate': 1.1437737213085126e-05, 'epoch': 1.24}
{'loss': 0.739, 'learning_rate': 1.1435026206397976e-05, 'epoch': 1.24}
{'loss': 0.6641, 'learning_rate': 1.1432315199710826e-05, 'epoch': 1.24}
{'loss': 0.9615, 'learning_rate': 1.1429604193023676e-05, 'epoch': 1.24}
{'loss': 0.923, 'learning_rate': 1.1426893186336526e-05, 'epoch': 1.24}
{'loss': 1.1064, 'learning_rate': 1.1424182179649377e-05, 'epoch': 1.24}
{'loss': 0.7199, 'learning_rate': 1.1421471172962227e-05, 'epoch': 1.24}
{'loss': 1.3492, 'learning_rate': 1.1418760166275077e-05, 'epoch': 1.24}
{'loss': 0.6984, 'learning_rate': 1.1416049159587927e-05, 'epoch': 1.24}
{'loss': 0.5894, 'learning_rate': 1.1413338152900777e-05, 'epoch': 1.24}
{'loss': 0.8874, 'learning_rate': 1.1410627146213627e-05, 'epoch': 1.24}
{'loss': 1.0943, 'learning_rate': 1.1407916139526477e-05, 'epoch': 1.24}
{'loss': 0.5359, 'learning_rate': 1.1405205132839328e-05, 'epoch': 1.24}
{'loss': 0.4131, 'learning_rate': 1.140249412615218e-05, 'epoch': 1.24}

 62%|██████▏   | 6861/11066 [25:07<15:00,  4.67it/s]
 62%|██████▏   | 6862/11066 [25:07<14:59,  4.67it/s]
                                                    

 62%|██████▏   | 6862/11066 [25:07<14:59,  4.67it/s]
 62%|██████▏   | 6863/11066 [25:08<15:03,  4.65it/s]
                                                    

 62%|██████▏   | 6863/11066 [25:08<15:03,  4.65it/s]
 62%|██████▏   | 6864/11066 [25:08<15:01,  4.66it/s]
                                                    

 62%|██████▏   | 6864/11066 [25:08<15:01,  4.66it/s]
 62%|██████▏   | 6865/11066 [25:08<14:58,  4.68it/s]
                                                    

 62%|██████▏   | 6865/11066 [25:08<14:58,  4.68it/s]
 62%|██████▏   | 6866/11066 [25:08<15:03,  4.65it/s]
                                                    

 62%|██████▏   | 6866/11066 [25:08<15:03,  4.65it/s]
 62%|██████▏   | 6867/11066 [25:08<14:55,  4.69it/s]
                                                    

 62%|██████▏   | 6867/11066 [25:08<14:55,  4.69it/s]
 62%|██████▏   | 6868/11066 [25:09<14:54,  4.70it/s]
                                                    

 62%|██████▏   | 6868/11066 [25:09<14:54,  4.70it/s]
 62%|██████▏   | 6869/11066 [25:09<14:52,  4.70it/s]
                                                    

 62%|██████▏   | 6869/11066 [25:09<14:52,  4.70it/s]
 62%|██████▏   | 6870/11066 [25:09<15:08,  4.62it/s]
                                                    

 62%|██████▏   | 6870/11066 [25:09<15:08,  4.62it/s]
 62%|██████▏   | 6871/11066 [25:09<15:01,  4.65it/s]
                                                    

 62%|██████▏   | 6871/11066 [25:09<15:01,  4.65it/s]
 62%|██████▏   | 6872/11066 [25:09<15:02,  4.65it/s]
                                                    

 62%|██████▏   | 6872/11066 [25:09<15:02,  4.65it/s]
 62%|██████▏   | 6873/11066 [25:10<14:56,  4.68it/s]
                                                    

 62%|██████▏   | 6873/11066 [25:10<14:56,  4.68it/s]
 62%|██████▏   | 6874/11066 [25:10<14:48,  4.72it/s]
                                                    

 62%|██████▏   | 6874/11066 [25:10<14:48,  4.72it/s]
 62%|██████▏   | 6875/11066 [25:10<14:49,  4.71it/s]
                                                    

 62%|██████▏   | 6875/11066 [25:10<14:49,  4.71it/s]
 62%|██████▏   | 6876/11066 [25:10<15:04,  4.63it/s]
                                                    

 62%|██████▏   | 6876/11066 [25:10<15:04,  4.63it/s]
 62%|██████▏   | 6877/11066 [25:11<15:08,  4.61it/s]
                                                    

 62%|██████▏   | 6877/11066 [25:11<15:08,  4.61it/s]
 62%|██████▏   | 6878/11066 [25:11<15:31,  4.50it/s]
                                                    

 62%|██████▏   | 6878/11066 [25:11<15:31,  4.50it/s]
 62%|██████▏   | 6879/11066 [25:11<15:35,  4.48it/s]
                                                    

 62%|██████▏   | 6879/11066 [25:11<15:35,  4.48it/s]
 62%|██████▏   | 6880/11066 [25:11<15:38,  4.46it/s]
                                                    

 62%|██████▏   | 6880/11066 [25:11<15:38,  4.46it/s]
 62%|██████▏   | 6881/11066 [25:11<15:51,  4.40it/s]
                                                    

 62%|██████▏   | 6881/11066 [25:11<15:51,  4.40it/s]
 62%|██████▏   | 6882/11066 [25:12<15:32,  4.49it/s]
                                                    

 62%|██████▏   | 6882/11066 [25:12<15:32,  4.49it/s]
 62%|██████▏   | 6883/11066 [25:12<15:19,  4.55it/s]
                                                    

 62%|██████▏   | 6883/11066 [25:12<15:19,  4.55it/s]
 62%|██████▏   | 6884/11066 [25:12<15:09,  4.60it/s]
                                                    

 62%|██████▏   | 6884/11066 [25:12<15:09,  4.60it/s]
 62%|██████▏   | 6885/11066 [25:12<15:02,  4.63it/s]
                                                    

 62%|██████▏   | 6885/11066 [25:12<15:02,  4.63it/s]
 62%|██████▏   | 6886/11066 [25:13<14:57,  4.66it/s]
                                                    

 62%|██████▏   | 6886/11066 [25:13<14:57,  4.66it/s]
 62%|██████▏   | 6887/11066 [25:13<14:54,  4.67it/s]
                                                    

 62%|██████▏   | 6887/11066 [25:13<14:54,  4.67it/s]
 62%|██████▏   | 6888/11066 [25:13<14:52,  4.68it/s]
                                                    

 62%|██████▏   | 6888/11066 [25:13<14:52,  4.68it/s]
 62%|██████▏   | 6889/11066 [25:13<14:50,  4.69it/s]
                                                    

 62%|██████▏   | 6889/11066 [25:13<14:50,  4.69it/s]
 62%|██████▏   | 6890/11066 [25:13<15:02,  4.62it/s]
                                                    

 62%|██████▏   | 6890/11066 [25:13<15:02,  4.62it/s]
 62%|██████▏   | 6891/11066 [25:14<14:58,  4.65it/s]
                                                    

 62%|██████▏   | 6891/11066 [25:14<14:58,  4.65it/s]
 62%|██████▏   | 6892/11066 [25:14<14:55,  4.66it/s]
                                                    

 62%|██████▏   | 6892/11066 [25:14<14:55,  4.66it/s]
 62%|██████▏   | 6893/11066 [25:14<14:55,  4.66it/s]
                                                    

 62%|██████▏   | 6893/11066 [25:14<14:55,  4.66it/s]
 62%|██████▏   | 6894/11066 [25:14<14:53,  4.67it/s]
                                                    

 62%|██████▏   | 6894/11066 [25:14<14:53,  4.67it/s]
 62%|██████▏   | 6895/11066 [25:14<14:49,  4.69it/s]
                                                    

 62%|██████▏   | 6895/11066 [25:14<14:49,  4.69it/s]
 62%|██████▏   | 6896/11066 [25:15<15:04,  4.61it/s]
                                                    

 62%|██████▏   | 6896/11066 [25:15<15:04,  4.61it/s]
 62%|██████▏   | 6897/11066 [25:15<15:05,  4.60it/s]
                                                    

 62%|██████▏   | 6897/11066 [25:15<15:05,  4.60it/s]
 62%|██████▏   | 6898/11066 [25:15<14:55,  4.65it/s]
                                                    

 62%|██████▏   | 6898/11066 [25:15<14:55,  4.65it/s]
 62%|██████▏   | 6899/11066 [25:15<15:04,  4.61it/s]
                                                    

 62%|██████▏   | 6899/11066 [25:15<15:04,  4.61it/s]
 62%|██████▏   | 6900/11066 [25:16<15:10,  4.57it/s]
                                                    

 62%|██████▏   | 6900/11066 [25:16<15:10,  4.57it/s]
 62%|██████▏   | 6901/11066 [25:16<15:15,  4.55it/s]
                                                    

 62%|██████▏   | 6901/11066 [25:16<15:15,  4.55it/s]
 62%|██████▏   | 6902/11066 [25:16<15:05,  4.60it/s]
                                                    

 62%|██████▏   | 6902/11066 [25:16<15:05,  4.60it/s]
 62%|██████▏   | 6903/11066 [25:16<14:59,  4.63it/s]
                                                    

 62%|██████▏   | 6903/11066 [25:16<14:59,  4.63it/s]
 62%|██████▏   | 6904/11066 [25:16<14:55,  4.65it/s]
                                                    

 62%|██████▏   | 6904/11066 [25:16<14:55,  4.65it/s]
 62%|██████▏   | 6905/11066 [25:17<14:48,  4.68it/s]
                                                    

 62%|██████▏   | 6905/11066 [25:17<14:48,  4.68it/s]
 62%|██████▏   | 6906/11066 [25:17<14:48,  4.68it/s]
                                                    

 62%|██████▏   | 6906/11066 [25:17<14:48,  4.68it/s]
 62%|██████▏   | 6907/11066 [25:17<14:45,  4.70it/s]
                                                    

 62%|██████▏   | 6907/11066 [25:17<14:45,  4.70it/s]
 62%|██████▏   | 6908/11066 [25:17<14:44,  4.70it/s]
                                                    

 62%|██████▏   | 6908/11066 [25:17<14:44,  4.70it/s]
 62%|██████▏   | 6909/11066 [25:18<14:56,  4.64it/s]
                                                    

 62%|██████▏   | 6909/11066 [25:18<14:56,  4.64it/s]
 62%|██████▏   | 6910/11066 [25:18<14:51,  4.66it/s]
                                                    

 62%|██████▏   | 6910/11066 [25:18<14:51,  4.66it/s]
 62%|██████▏   | 6911/11066 [25:18<14:48,  4.68it/s]
                                                    

 62%|██████▏   | 6911/11066 [25:18<14:48,  4.68it/s]
 62%|██████▏   | 6912/11066 [25:18<14:45,  4.69it/s]
                                                    

 62%|██████▏   | 6912/11066 [25:18<14:45,  4.69it/s]
 62%|██████▏   | 6913/11066 [25:18<14:44,  4.70it/s]
                                                    

 62%|██████▏   | 6913/11066 [25:18<14:44,  4.70it/s]
 62%|██████▏   | 6914/11066 [25:19<14:49,  4.67it/s]
                                                    

 62%|██████▏   | 6914/11066 [25:19<14:49,  4.67it/s]
 62%|██████▏   | 6915/11066 [25:19<14:54,  4.64it/s]
                                                    

 62%|██████▏   | 6915/11066 [25:19<14:54,  4.64it/s]
 62%|██████▏   | 6916/11066 [25:19<14:50,  4.66it/s]
                                                    

 62%|██████▏   | 6916/11066 [25:19<14:50,  4.66it/s]
 63%|██████▎   | 6917/11066 [25:19<15:06,  4.58it/s]
                                                    

 63%|██████▎   | 6917/11066 [25:19<15:06,  4.58it/s]
 63%|██████▎   | 6918/11066 [25:19<14:59,  4.61it/s]
                                                    

 63%|██████▎   | 6918/11066 [25:19<14:59,  4.61it/s]
 63%|██████▎   | 6919/11066 [25:20<15:13,  4.54it/s]
                                                    

 63%|██████▎   | 6919/11066 [25:20<15:13,  4.54it/s]
 63%|██████▎   | 6920/11066 [25:20<15:28,  4.46it/s]
                                                    

 63%|██████▎   | 6920/11066 [25:20<15:28,  4.46it/s]
 63%|██████▎   | 6921/11066 [25:20<15:32,  4.44it/s]
                                                    

 63%|██████▎   | 6921/11066 [25:20<15:32,  4.44it/s]
 63%|██████▎   | 6922/11066 [25:20<15:32,  4.44it/s]
                                                    

 63%|██████▎   | 6922/11066 [25:20<15:32,  4.44it/s]
 63%|██████▎   | 6923/11066 [25:21<15:31,  4.45it/s]
                                                    

 63%|██████▎   | 6923/11066 [25:21<15:31,  4.45it/s]
 63%|██████▎   | 6924/11066 [25:21<15:28,  4.46it/s]
                                                    

 63%|██████▎   | 6924/11066 [25:21<15:28,  4.46it/s]
 63%|██████▎   | 6925/11066 [25:21<15:25,  4.47it/s]
                                                    

 63%|██████▎   | 6925/11066 [25:21<15:25,  4.47it/s]
 63%|██████▎   | 6926/11066 [25:21<15:36,  4.42it/s]
                                                    

 63%|██████▎   | 6926/11066 [25:21<15:36,  4.42it/s]
 63%|██████▎   | 6927/11066 [25:21<15:30,  4.45it/s]
                                                    

 63%|██████▎   | 6927/11066 [25:21<15:30,  4.45it/s]
 63%|██████▎   | 6928/11066 [25:22<15:26,  4.46it/s]
                                                    

 63%|██████▎   | 6928/11066 [25:22<15:26,  4.46it/s]
 63%|██████▎   | 6929/11066 [25:22<15:23,  4.48it/s]
                                                    

 63%|██████▎   | 6929/11066 [25:22<15:23,  4.48it/s]
 63%|██████▎   | 6930/11066 [25:22<15:21,  4.49it/s]
                                                    

 63%|██████▎   | 6930/11066 [25:22<15:21,  4.49it/s]
 63%|██████▎   | 6931/11066 [25:22<15:20,  4.49it/s]
                                                    

 63%|██████▎   | 6931/11066 [25:22<15:20,  4.49it/s]
 63%|██████▎   | 6932/11066 [25:23<15:09,  4.54it/s]
                                                    

 63%|██████▎   | 6932/11066 [25:23<15:09,  4.54it/s]
 63%|██████▎   | 6933/11066 [25:23<15:11,  4.53it/s]
                                                    

 63%|██████▎   | 6933/11066 [25:23<15:11,  4.53it/s]
 63%|██████▎   | 6934/11066 [25:23<15:13,  4.52it/s]
                                                    

 63%|██████▎   | 6934/11066 [25:23<15:13,  4.52it/s]
 63%|██████▎   | 6935/11066 [25:23<15:13,  4.52it/s]
                                                    

 63%|██████▎   | 6935/11066 [25:23<15:13,  4.52it/s]
 63%|██████▎   | 6936/11066 [25:23<15:14,  4.52it/s]
                                                    

 63%|██████▎   | 6936/11066 [25:23<15:14,  4.52it/s]
 63%|██████▎   | 6937/11066 [25:24<15:15,  4.51it/s]
                                                    

 63%|██████▎   | 6937/11066 [25:24<15:15,  4.51it/s]
 63%|██████▎   | 6938/11066 [25:24<15:08,  4.55it/s]
                                                    

 63%|██████▎   | 6938/11066 [25:24<15:08,  4.55it/s]
 63%|██████▎   | 6939/11066 [25:24<15:13,  4.52it/s]
                                                    

 63%|██████▎   | 6939/11066 [25:24<15:13,  4.52it/s]
 63%|██████▎   | 6940/11066 [25:24<15:34,  4.42it/s]
                                                    

 63%|██████▎   | 6940/11066 [25:24<15:34,  4.42it/s]
 63%|██████▎   | 6941/11066 [25:25<15:33,  4.42it/s]
                                                    

 63%|██████▎   | 6941/11066 [25:25<15:33,  4.42it/s]
 63%|██████▎   | 6942/11066 [25:25<15:31,  4.43it/s]
                                                    

 63%|██████▎   | 6942/11066 [25:25<15:31,  4.43it/s]
 63%|██████▎   | 6943/11066 [25:25<15:26,  4.45it/s]
                                                    

 63%|██████▎   | 6943/11066 [25:25<15:26,  4.45it/s]
 63%|██████▎   | 6944/11066 [25:25<15:22,  4.47it/s]
                                                    

 63%|██████▎   | 6944/11066 [25:25<15:22,  4.47it/s]
 63%|██████▎   | 6945/11066 [25:25<15:20,  4.48it/s]
                                                    

 63%|██████▎   | 6945/11066 [25:25<15:20,  4.48it/s]
 63%|██████▎   | 6946/11066 [25:26<15:46,  4.35it/s]
                                                    

 63%|██████▎   | 6946/11066 [25:26<15:46,  4.35it/s]
 63%|██████▎   | 6947/11066 [25:26<15:44,  4.36it/s]
                                                    

 63%|██████▎   | 6947/11066 [25:26<15:44,  4.36it/s]
 63%|██████▎   | 6948/11066 [25:26<15:49,  4.34it/s]
                                                    

 63%|██████▎   | 6948/11066 [25:26<15:49,  4.34it/s]
 63%|██████▎   | 6949/11066 [25:26<15:39,  4.38it/s]
                                                    

 63%|██████▎   | 6949/11066 [25:26<15:39,  4.38it/s]
 63%|██████▎   | 6950/11066 [25:27<15:31,  4.42it/s]
                                                    

 63%|██████▎   | 6950/11066 [25:27<15:31,  4.42it/s]
 63%|██████▎   | 6951/11066 [25:27<15:26,  4.44it/s]
                                                    

 63%|██████▎   | 6951/11066 [25:27<15:26,  4.44it/s]
 63%|██████▎   | 6952/11066 [25:27<15:21,  4.47it/s]
                                                    

 63%|██████▎   | 6952/11066 [25:27<15:21,  4.47it/s]
 63%|██████▎   | 6953/11066 [25:27<15:18,  4.48it/s]
                                                    

 63%|██████▎   | 6953/11066 [25:27<15:18,  4.48it/s]
 63%|██████▎   | 6954/11066 [25:28<15:17,  4.48it/s]
                                                    

 63%|██████▎   | 6954/11066 [25:28<15:17,  4.48it/s]
 63%|██████▎   | 6955/11066 [25:28<15:16,  4.49it/s]
                                                    

 63%|██████▎   | 6955/11066 [25:28<15:16,  4.49it/s]
 63%|██████▎   | 6956/11066 [25:28<15:14,  4.49it/s]
                                                    

 63%|██████▎   | 6956/11066 [25:28<15:14,  4.49it/s]
 63%|██████▎   | 6957/11066 [25:28<15:14,  4.49it/s]
                                                    

 63%|██████▎   | 6957/11066 [25:28<15:14,  4.49it/s]
 63%|██████▎   | 6958/11066 [25:28<15:13,  4.50it/s]
                                                    

 63%|██████▎   | 6958/11066 [25:28<15:13,  4.50it/s]
 63%|██████▎   | 6959/11066 [25:29<15:12,  4.50it/s]
                                                    

 63%|██████▎   | 6959/11066 [25:29<15:12,  4.50it/s]
 63%|██████▎   | 6960/11066 [25:29<15:13,  4.50it/s]
                                                    

 63%|██████▎   | 6960/11066 [25:29<15:13,  4.50it/s]
 63%|██████▎   | 6961/11066 [25:29<15:04,  4.54it/s]
                                                    

 63%|██████▎   | 6961/11066 [25:29<15:04,  4.54it/s]
 63%|██████▎   | 6962/11066 [25:29<15:05,  4.53it/s]
                                                    

 63%|██████▎   | 6962/11066 [25:29<15:05,  4.53it/s]
 63%|██████▎   | 6963/11066 [25:30<15:14,  4.49it/s]
                                                    

 63%|██████▎   | 6963/11066 [25:30<15:14,  4.49it/s]
 63%|██████▎   | 6964/11066 [25:30<15:12,  4.49it/s]
                                                    

 63%|██████▎   | 6964/11066 [25:30<15:12,  4.49it/s]
 63%|██████▎   | 6965/11066 [25:30<15:01,  4.55it/s]
                                                    

 63%|██████▎   | 6965/11066 [25:30<15:01,  4.55it/s]
 63%|██████▎   | 6966/11066 [25:30<15:02,  4.54it/s]
                                                    

 63%|██████▎   | 6966/11066 [25:30<15:02,  4.54it/s]
 63%|██████▎   | 6967/11066 [25:30<15:05,  4.53it/s]
                                                    

 63%|██████▎   | 6967/11066 [25:30<15:05,  4.53it/s]
 63%|██████▎   | 6968/11066 [25:31<15:06,  4.52it/s]
                                                    

 63%|██████▎   | 6968/11066 [25:31<15:06,  4.52it/s]
 63%|██████▎   | 6969/11066 [25:31<15:02,  4.54it/s]
                                                    

 63%|██████▎   | 6969/11066 [25:31<15:02,  4.54it/s]
 63%|██████▎   | 6970/11066 [25:31<15:20,  4.45it/s]
                                                    

 63%|██████▎   | 6970/11066 [25:31<15:20,  4.45it/s]
 63%|██████▎   | 6971/11066 [25:31<15:17,  4.46it/s]
                                                    

 63%|██████▎   | 6971/11066 [25:31<15:17,  4.46it/s]
 63%|██████▎   | 6972/11066 [25:32<15:14,  4.48it/s]
                                                    

 63%|██████▎   | 6972/11066 [25:32<15:14,  4.48it/s]
 63%|██████▎   | 6973/11066 [25:32<15:15,  4.47it/s]
                                                    
{'loss': 1.1564, 'learning_rate': 1.1399783119465028e-05, 'epoch': 1.24}
{'loss': 0.9742, 'learning_rate': 1.1397072112777878e-05, 'epoch': 1.24}
{'loss': 0.6532, 'learning_rate': 1.1394361106090728e-05, 'epoch': 1.24}
{'loss': 1.0793, 'learning_rate': 1.139165009940358e-05, 'epoch': 1.24}
{'loss': 1.0352, 'learning_rate': 1.1388939092716428e-05, 'epoch': 1.24}
{'loss': 1.1557, 'learning_rate': 1.1386228086029278e-05, 'epoch': 1.24}
{'loss': 0.4315, 'learning_rate': 1.138351707934213e-05, 'epoch': 1.24}
{'loss': 0.962, 'learning_rate': 1.138080607265498e-05, 'epoch': 1.24}
{'loss': 0.7513, 'learning_rate': 1.1378095065967829e-05, 'epoch': 1.24}
{'loss': 0.8683, 'learning_rate': 1.1375384059280679e-05, 'epoch': 1.24}
{'loss': 0.442, 'learning_rate': 1.1372673052593531e-05, 'epoch': 1.24}
{'loss': 1.2248, 'learning_rate': 1.1369962045906381e-05, 'epoch': 1.24}
{'loss': 0.9796, 'learning_rate': 1.136725103921923e-05, 'epoch': 1.24}
{'loss': 0.6348, 'learning_rate': 1.136454003253208e-05, 'epoch': 1.24}
{'loss': 0.8473, 'learning_rate': 1.1361829025844931e-05, 'epoch': 1.24}
{'loss': 0.5202, 'learning_rate': 1.1359118019157782e-05, 'epoch': 1.24}
{'loss': 0.5747, 'learning_rate': 1.135640701247063e-05, 'epoch': 1.24}
{'loss': 0.7409, 'learning_rate': 1.1353696005783482e-05, 'epoch': 1.24}
{'loss': 0.9418, 'learning_rate': 1.1350984999096332e-05, 'epoch': 1.24}
{'loss': 0.6307, 'learning_rate': 1.1348273992409182e-05, 'epoch': 1.24}
{'loss': 0.3327, 'learning_rate': 1.134556298572203e-05, 'epoch': 1.24}
{'loss': 0.4767, 'learning_rate': 1.1342851979034882e-05, 'epoch': 1.24}
{'loss': 1.0905, 'learning_rate': 1.1340140972347732e-05, 'epoch': 1.24}
{'loss': 0.8052, 'learning_rate': 1.1337429965660583e-05, 'epoch': 1.24}
{'loss': 0.5208, 'learning_rate': 1.1334718958973431e-05, 'epoch': 1.24}
{'loss': 1.1702, 'learning_rate': 1.1332007952286283e-05, 'epoch': 1.24}
{'loss': 0.5225, 'learning_rate': 1.1329296945599133e-05, 'epoch': 1.24}
{'loss': 1.0993, 'learning_rate': 1.1326585938911983e-05, 'epoch': 1.24}
{'loss': 0.41, 'learning_rate': 1.1323874932224833e-05, 'epoch': 1.25}
{'loss': 0.632, 'learning_rate': 1.1321163925537683e-05, 'epoch': 1.25}
{'loss': 0.5734, 'learning_rate': 1.1318452918850534e-05, 'epoch': 1.25}
{'loss': 0.7813, 'learning_rate': 1.1315741912163384e-05, 'epoch': 1.25}
{'loss': 0.7105, 'learning_rate': 1.1313030905476234e-05, 'epoch': 1.25}
{'loss': 0.9137, 'learning_rate': 1.1310319898789084e-05, 'epoch': 1.25}
{'loss': 1.3251, 'learning_rate': 1.1307608892101934e-05, 'epoch': 1.25}
{'loss': 0.3388, 'learning_rate': 1.1304897885414784e-05, 'epoch': 1.25}
{'loss': 0.3183, 'learning_rate': 1.1302186878727634e-05, 'epoch': 1.25}
{'loss': 0.7065, 'learning_rate': 1.1299475872040484e-05, 'epoch': 1.25}
{'loss': 0.4162, 'learning_rate': 1.1296764865353335e-05, 'epoch': 1.25}
{'loss': 0.6559, 'learning_rate': 1.1294053858666186e-05, 'epoch': 1.25}
{'loss': 0.5197, 'learning_rate': 1.1291342851979035e-05, 'epoch': 1.25}
{'loss': 0.8723, 'learning_rate': 1.1288631845291885e-05, 'epoch': 1.25}
{'loss': 0.2543, 'learning_rate': 1.1285920838604735e-05, 'epoch': 1.25}
{'loss': 0.2812, 'learning_rate': 1.1283209831917587e-05, 'epoch': 1.25}
{'loss': 0.5815, 'learning_rate': 1.1280498825230435e-05, 'epoch': 1.25}
{'loss': 0.9922, 'learning_rate': 1.1277787818543286e-05, 'epoch': 1.25}
{'loss': 0.6065, 'learning_rate': 1.1275076811856136e-05, 'epoch': 1.25}
{'loss': 0.8615, 'learning_rate': 1.1272365805168988e-05, 'epoch': 1.25}
{'loss': 2.3779, 'learning_rate': 1.1269654798481836e-05, 'epoch': 1.25}
{'loss': 1.1846, 'learning_rate': 1.1266943791794686e-05, 'epoch': 1.25}
{'loss': 1.0128, 'learning_rate': 1.1264232785107538e-05, 'epoch': 1.25}
{'loss': 1.4916, 'learning_rate': 1.1261521778420388e-05, 'epoch': 1.25}
{'loss': 0.8098, 'learning_rate': 1.1258810771733237e-05, 'epoch': 1.25}
{'loss': 1.6556, 'learning_rate': 1.1256099765046087e-05, 'epoch': 1.25}
{'loss': 0.4126, 'learning_rate': 1.1253388758358938e-05, 'epoch': 1.25}
{'loss': 0.3735, 'learning_rate': 1.1250677751671789e-05, 'epoch': 1.25}
{'loss': 0.8498, 'learning_rate': 1.1247966744984637e-05, 'epoch': 1.25}
{'loss': 0.9097, 'learning_rate': 1.1245255738297487e-05, 'epoch': 1.25}
{'loss': 0.5394, 'learning_rate': 1.1242544731610339e-05, 'epoch': 1.25}
{'loss': 1.3781, 'learning_rate': 1.1239833724923189e-05, 'epoch': 1.25}
{'loss': 0.6467, 'learning_rate': 1.1237122718236038e-05, 'epoch': 1.25}
{'loss': 1.0262, 'learning_rate': 1.123441171154889e-05, 'epoch': 1.25}
{'loss': 0.8958, 'learning_rate': 1.123170070486174e-05, 'epoch': 1.25}
{'loss': 0.5348, 'learning_rate': 1.122898969817459e-05, 'epoch': 1.25}
{'loss': 0.4264, 'learning_rate': 1.1226278691487438e-05, 'epoch': 1.25}
{'loss': 0.7974, 'learning_rate': 1.122356768480029e-05, 'epoch': 1.25}
{'loss': 1.2929, 'learning_rate': 1.122085667811314e-05, 'epoch': 1.25}
{'loss': 1.274, 'learning_rate': 1.121814567142599e-05, 'epoch': 1.25}
{'loss': 0.4915, 'learning_rate': 1.1215434664738839e-05, 'epoch': 1.25}
{'loss': 1.0302, 'learning_rate': 1.121272365805169e-05, 'epoch': 1.25}
{'loss': 0.64, 'learning_rate': 1.121001265136454e-05, 'epoch': 1.25}
{'loss': 0.6552, 'learning_rate': 1.120730164467739e-05, 'epoch': 1.25}
{'loss': 1.0045, 'learning_rate': 1.1204590637990241e-05, 'epoch': 1.25}
{'loss': 0.4965, 'learning_rate': 1.1201879631303091e-05, 'epoch': 1.25}
{'loss': 0.5878, 'learning_rate': 1.1199168624615941e-05, 'epoch': 1.25}
{'loss': 1.0789, 'learning_rate': 1.1196457617928791e-05, 'epoch': 1.25}
{'loss': 0.4876, 'learning_rate': 1.1193746611241641e-05, 'epoch': 1.25}
{'loss': 1.4158, 'learning_rate': 1.1191035604554492e-05, 'epoch': 1.25}
{'loss': 1.0386, 'learning_rate': 1.1188324597867342e-05, 'epoch': 1.25}
{'loss': 0.3571, 'learning_rate': 1.1185613591180192e-05, 'epoch': 1.25}
{'loss': 1.2793, 'learning_rate': 1.1182902584493042e-05, 'epoch': 1.25}
{'loss': 0.6268, 'learning_rate': 1.1180191577805892e-05, 'epoch': 1.25}
{'loss': 1.1256, 'learning_rate': 1.1177480571118742e-05, 'epoch': 1.25}
{'loss': 0.5232, 'learning_rate': 1.1174769564431594e-05, 'epoch': 1.26}
{'loss': 0.7091, 'learning_rate': 1.1172058557744442e-05, 'epoch': 1.26}
{'loss': 0.842, 'learning_rate': 1.1169347551057293e-05, 'epoch': 1.26}
{'loss': 0.5706, 'learning_rate': 1.1166636544370143e-05, 'epoch': 1.26}
{'loss': 0.4592, 'learning_rate': 1.1163925537682995e-05, 'epoch': 1.26}
{'loss': 0.4989, 'learning_rate': 1.1161214530995843e-05, 'epoch': 1.26}
{'loss': 0.4811, 'learning_rate': 1.1158503524308693e-05, 'epoch': 1.26}
{'loss': 0.5002, 'learning_rate': 1.1155792517621545e-05, 'epoch': 1.26}
{'loss': 0.7966, 'learning_rate': 1.1153081510934393e-05, 'epoch': 1.26}
{'loss': 0.9187, 'learning_rate': 1.1150370504247244e-05, 'epoch': 1.26}
{'loss': 0.5668, 'learning_rate': 1.1147659497560094e-05, 'epoch': 1.26}
{'loss': 1.1276, 'learning_rate': 1.1144948490872946e-05, 'epoch': 1.26}
{'loss': 0.6042, 'learning_rate': 1.1142237484185794e-05, 'epoch': 1.26}
{'loss': 0.5531, 'learning_rate': 1.1139526477498644e-05, 'epoch': 1.26}
{'loss': 0.4058, 'learning_rate': 1.1136815470811494e-05, 'epoch': 1.26}
{'loss': 0.5792, 'learning_rate': 1.1134104464124346e-05, 'epoch': 1.26}
{'loss': 0.3526, 'learning_rate': 1.1131393457437195e-05, 'epoch': 1.26}
{'loss': 1.2807, 'learning_rate': 1.1128682450750045e-05, 'epoch': 1.26}
{'loss': 0.6256, 'learning_rate': 1.1125971444062896e-05, 'epoch': 1.26}
{'loss': 1.0049, 'learning_rate': 1.1123260437375747e-05, 'epoch': 1.26}
{'loss': 0.6497, 'learning_rate': 1.1120549430688595e-05, 'epoch': 1.26}
{'loss': 0.2009, 'learning_rate': 1.1117838424001445e-05, 'epoch': 1.26}
{'loss': 0.8671, 'learning_rate': 1.1115127417314297e-05, 'epoch': 1.26}
{'loss': 0.7391, 'learning_rate': 1.1112416410627147e-05, 'epoch': 1.26}
{'loss': 0.7062, 'learning_rate': 1.1109705403939996e-05, 'epoch': 1.26}
{'loss': 0.4605, 'learning_rate': 1.1106994397252846e-05, 'epoch': 1.26}
{'loss': 0.9617, 'learning_rate': 1.1104283390565698e-05, 'epoch': 1.26}
{'loss': 0.3355, 'learning_rate': 1.1101572383878548e-05, 'epoch': 1.26}
{'loss': 1.045, 'learning_rate': 1.1098861377191396e-05, 'epoch': 1.26}

 63%|██████▎   | 6973/11066 [25:32<15:15,  4.47it/s]
 63%|██████▎   | 6974/11066 [25:32<15:26,  4.41it/s]
                                                    

 63%|██████▎   | 6974/11066 [25:32<15:26,  4.41it/s]
 63%|██████▎   | 6975/11066 [25:32<15:20,  4.44it/s]
                                                    

 63%|██████▎   | 6975/11066 [25:32<15:20,  4.44it/s]
 63%|██████▎   | 6976/11066 [25:32<15:17,  4.46it/s]
                                                    

 63%|██████▎   | 6976/11066 [25:32<15:17,  4.46it/s]
 63%|██████▎   | 6977/11066 [25:33<15:15,  4.47it/s]
                                                    

 63%|██████▎   | 6977/11066 [25:33<15:15,  4.47it/s]
 63%|██████▎   | 6978/11066 [25:33<15:13,  4.48it/s]
                                                    

 63%|██████▎   | 6978/11066 [25:33<15:13,  4.48it/s]
 63%|██████▎   | 6979/11066 [25:33<15:12,  4.48it/s]
                                                    

 63%|██████▎   | 6979/11066 [25:33<15:12,  4.48it/s]
 63%|██████▎   | 6980/11066 [25:33<15:02,  4.53it/s]
                                                    

 63%|██████▎   | 6980/11066 [25:33<15:02,  4.53it/s]
 63%|██████▎   | 6981/11066 [25:34<15:03,  4.52it/s]
                                                    

 63%|██████▎   | 6981/11066 [25:34<15:03,  4.52it/s]
 63%|██████▎   | 6982/11066 [25:34<15:05,  4.51it/s]
                                                    

 63%|██████▎   | 6982/11066 [25:34<15:05,  4.51it/s]
 63%|██████▎   | 6983/11066 [25:34<15:05,  4.51it/s]
                                                    

 63%|██████▎   | 6983/11066 [25:34<15:05,  4.51it/s]
 63%|██████▎   | 6984/11066 [25:34<15:06,  4.50it/s]
                                                    

 63%|██████▎   | 6984/11066 [25:34<15:06,  4.50it/s]
 63%|██████▎   | 6985/11066 [25:34<15:07,  4.50it/s]
                                                    

 63%|██████▎   | 6985/11066 [25:34<15:07,  4.50it/s]
 63%|██████▎   | 6986/11066 [25:35<15:08,  4.49it/s]
                                                    

 63%|██████▎   | 6986/11066 [25:35<15:08,  4.49it/s]
 63%|██████▎   | 6987/11066 [25:35<15:08,  4.49it/s]
                                                    

 63%|██████▎   | 6987/11066 [25:35<15:08,  4.49it/s]
 63%|██████▎   | 6988/11066 [25:35<15:08,  4.49it/s]
                                                    

 63%|██████▎   | 6988/11066 [25:35<15:08,  4.49it/s]
 63%|██████▎   | 6989/11066 [25:35<15:08,  4.49it/s]
                                                    

 63%|██████▎   | 6989/11066 [25:35<15:08,  4.49it/s]
 63%|██████▎   | 6990/11066 [25:36<15:08,  4.49it/s]
                                                    

 63%|██████▎   | 6990/11066 [25:36<15:08,  4.49it/s]
 63%|██████▎   | 6991/11066 [25:36<15:07,  4.49it/s]
                                                    

 63%|██████▎   | 6991/11066 [25:36<15:07,  4.49it/s]
 63%|██████▎   | 6992/11066 [25:36<15:07,  4.49it/s]
                                                    

 63%|██████▎   | 6992/11066 [25:36<15:07,  4.49it/s]
 63%|██████▎   | 6993/11066 [25:36<15:06,  4.49it/s]
                                                    

 63%|██████▎   | 6993/11066 [25:36<15:06,  4.49it/s]
 63%|██████▎   | 6994/11066 [25:36<15:07,  4.49it/s]
                                                    

 63%|██████▎   | 6994/11066 [25:36<15:07,  4.49it/s]
 63%|██████▎   | 6995/11066 [25:37<15:07,  4.49it/s]
                                                    

 63%|██████▎   | 6995/11066 [25:37<15:07,  4.49it/s]
 63%|██████▎   | 6996/11066 [25:37<15:06,  4.49it/s]
                                                    

 63%|██████▎   | 6996/11066 [25:37<15:06,  4.49it/s]
 63%|██████▎   | 6997/11066 [25:37<15:06,  4.49it/s]
                                                    

 63%|██████▎   | 6997/11066 [25:37<15:06,  4.49it/s]
 63%|██████▎   | 6998/11066 [25:37<14:55,  4.54it/s]
                                                    

 63%|██████▎   | 6998/11066 [25:37<14:55,  4.54it/s]
 63%|██████▎   | 6999/11066 [25:38<14:57,  4.53it/s]
                                                    

 63%|██████▎   | 6999/11066 [25:38<14:57,  4.53it/s]
 63%|██████▎   | 7000/11066 [25:38<15:00,  4.52it/s]
                                                    

 63%|██████▎   | 7000/11066 [25:38<15:00,  4.52it/s]
 63%|██████▎   | 7001/11066 [25:38<15:00,  4.51it/s]
                                                    

 63%|██████▎   | 7001/11066 [25:38<15:00,  4.51it/s]
 63%|██████▎   | 7002/11066 [25:38<15:01,  4.51it/s]
                                                    

 63%|██████▎   | 7002/11066 [25:38<15:01,  4.51it/s]
 63%|██████▎   | 7003/11066 [25:38<15:01,  4.51it/s]
                                                    

 63%|██████▎   | 7003/11066 [25:38<15:01,  4.51it/s]
 63%|██████▎   | 7004/11066 [25:39<15:01,  4.50it/s]
                                                    

 63%|██████▎   | 7004/11066 [25:39<15:01,  4.50it/s]
 63%|██████▎   | 7005/11066 [25:39<15:03,  4.50it/s]
                                                    

 63%|██████▎   | 7005/11066 [25:39<15:03,  4.50it/s]
 63%|██████▎   | 7006/11066 [25:39<15:03,  4.49it/s]
                                                    

 63%|██████▎   | 7006/11066 [25:39<15:03,  4.49it/s]
 63%|██████▎   | 7007/11066 [25:39<14:52,  4.55it/s]
                                                    

 63%|██████▎   | 7007/11066 [25:39<14:52,  4.55it/s]
 63%|██████▎   | 7008/11066 [25:40<14:55,  4.53it/s]
                                                    

 63%|██████▎   | 7008/11066 [25:40<14:55,  4.53it/s]
 63%|██████▎   | 7009/11066 [25:40<14:57,  4.52it/s]
                                                    

 63%|██████▎   | 7009/11066 [25:40<14:57,  4.52it/s]
 63%|██████▎   | 7010/11066 [25:40<14:59,  4.51it/s]
                                                    

 63%|██████▎   | 7010/11066 [25:40<14:59,  4.51it/s]
 63%|██████▎   | 7011/11066 [25:40<15:00,  4.50it/s]
                                                    

 63%|██████▎   | 7011/11066 [25:40<15:00,  4.50it/s]
 63%|██████▎   | 7012/11066 [25:40<15:00,  4.50it/s]
                                                    

 63%|██████▎   | 7012/11066 [25:40<15:00,  4.50it/s]
 63%|██████▎   | 7013/11066 [25:41<15:01,  4.50it/s]
                                                    

 63%|██████▎   | 7013/11066 [25:41<15:01,  4.50it/s]
 63%|██████▎   | 7014/11066 [25:41<15:01,  4.50it/s]
                                                    

 63%|██████▎   | 7014/11066 [25:41<15:01,  4.50it/s]
 63%|██████▎   | 7015/11066 [25:41<15:00,  4.50it/s]
                                                    

 63%|██████▎   | 7015/11066 [25:41<15:00,  4.50it/s]
 63%|██████▎   | 7016/11066 [25:41<15:01,  4.49it/s]
                                                    

 63%|██████▎   | 7016/11066 [25:41<15:01,  4.49it/s]
 63%|██████▎   | 7017/11066 [25:42<15:02,  4.49it/s]
                                                    

 63%|██████▎   | 7017/11066 [25:42<15:02,  4.49it/s]
 63%|██████▎   | 7018/11066 [25:42<15:01,  4.49it/s]
                                                    

 63%|██████▎   | 7018/11066 [25:42<15:01,  4.49it/s]
 63%|██████▎   | 7019/11066 [25:42<15:02,  4.49it/s]
                                                    

 63%|██████▎   | 7019/11066 [25:42<15:02,  4.49it/s]
 63%|██████▎   | 7020/11066 [25:42<15:01,  4.49it/s]
                                                    

 63%|██████▎   | 7020/11066 [25:42<15:01,  4.49it/s]
 63%|██████▎   | 7021/11066 [25:42<15:01,  4.49it/s]
                                                    

 63%|██████▎   | 7021/11066 [25:42<15:01,  4.49it/s]
 63%|██████▎   | 7022/11066 [25:43<15:01,  4.49it/s]
                                                    

 63%|██████▎   | 7022/11066 [25:43<15:01,  4.49it/s]
 63%|██████▎   | 7023/11066 [25:43<15:00,  4.49it/s]
                                                    

 63%|██████▎   | 7023/11066 [25:43<15:00,  4.49it/s]
 63%|██████▎   | 7024/11066 [25:43<15:00,  4.49it/s]
                                                    

 63%|██████▎   | 7024/11066 [25:43<15:00,  4.49it/s]
 63%|██████▎   | 7025/11066 [25:43<14:51,  4.53it/s]
                                                    

 63%|██████▎   | 7025/11066 [25:43<14:51,  4.53it/s]
 63%|██████▎   | 7026/11066 [25:44<14:54,  4.52it/s]
                                                    

 63%|██████▎   | 7026/11066 [25:44<14:54,  4.52it/s]
 64%|██████▎   | 7027/11066 [25:44<14:48,  4.55it/s]
                                                    

 64%|██████▎   | 7027/11066 [25:44<14:48,  4.55it/s]
 64%|██████▎   | 7028/11066 [25:44<14:53,  4.52it/s]
                                                    

 64%|██████▎   | 7028/11066 [25:44<14:53,  4.52it/s]
 64%|██████▎   | 7029/11066 [25:44<14:55,  4.51it/s]
                                                    

 64%|██████▎   | 7029/11066 [25:44<14:55,  4.51it/s]
 64%|██████▎   | 7030/11066 [25:44<14:56,  4.50it/s]
                                                    

 64%|██████▎   | 7030/11066 [25:44<14:56,  4.50it/s]
 64%|██████▎   | 7031/11066 [25:45<14:56,  4.50it/s]
                                                    

 64%|██████▎   | 7031/11066 [25:45<14:56,  4.50it/s]
 64%|██████▎   | 7032/11066 [25:45<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7032/11066 [25:45<14:57,  4.49it/s]
 64%|██████▎   | 7033/11066 [25:45<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7033/11066 [25:45<14:57,  4.49it/s]
 64%|██████▎   | 7034/11066 [25:45<14:54,  4.51it/s]
                                                    

 64%|██████▎   | 7034/11066 [25:45<14:54,  4.51it/s]
 64%|██████▎   | 7035/11066 [25:46<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7035/11066 [25:46<14:57,  4.49it/s]
 64%|██████▎   | 7036/11066 [25:46<14:55,  4.50it/s]
                                                    

 64%|██████▎   | 7036/11066 [25:46<14:55,  4.50it/s]
 64%|██████▎   | 7037/11066 [25:46<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7037/11066 [25:46<14:57,  4.49it/s]
 64%|██████▎   | 7038/11066 [25:46<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7038/11066 [25:46<14:57,  4.49it/s]
 64%|██████▎   | 7039/11066 [25:46<14:57,  4.49it/s]
                                                    

 64%|██████▎   | 7039/11066 [25:46<14:57,  4.49it/s]
 64%|██████▎   | 7040/11066 [25:47<14:56,  4.49it/s]
                                                    

 64%|██████▎   | 7040/11066 [25:47<14:56,  4.49it/s]
 64%|██████▎   | 7041/11066 [25:47<14:56,  4.49it/s]
                                                    

 64%|██████▎   | 7041/11066 [25:47<14:56,  4.49it/s]
 64%|██████▎   | 7042/11066 [25:47<14:57,  4.48it/s]
                                                    

 64%|██████▎   | 7042/11066 [25:47<14:57,  4.48it/s]
 64%|██████▎   | 7043/11066 [25:47<15:00,  4.47it/s]
                                                    

 64%|██████▎   | 7043/11066 [25:47<15:00,  4.47it/s]
 64%|██████▎   | 7044/11066 [25:48<15:01,  4.46it/s]
                                                    

 64%|██████▎   | 7044/11066 [25:48<15:01,  4.46it/s]
 64%|██████▎   | 7045/11066 [25:48<15:00,  4.46it/s]
                                                    

 64%|██████▎   | 7045/11066 [25:48<15:00,  4.46it/s]
 64%|██████▎   | 7046/11066 [25:48<14:58,  4.47it/s]
                                                    

 64%|██████▎   | 7046/11066 [25:48<14:58,  4.47it/s]
 64%|██████▎   | 7047/11066 [25:48<14:57,  4.48it/s]
                                                    

 64%|██████▎   | 7047/11066 [25:48<14:57,  4.48it/s]
 64%|██████▎   | 7048/11066 [25:48<14:55,  4.48it/s]
                                                    

 64%|██████▎   | 7048/11066 [25:48<14:55,  4.48it/s]
 64%|██████▎   | 7049/11066 [25:49<14:54,  4.49it/s]
                                                    

 64%|██████▎   | 7049/11066 [25:49<14:54,  4.49it/s]
 64%|██████▎   | 7050/11066 [25:49<14:54,  4.49it/s]
                                                    

 64%|██████▎   | 7050/11066 [25:49<14:54,  4.49it/s]
 64%|██████▎   | 7051/11066 [25:49<14:53,  4.49it/s]
                                                    

 64%|██████▎   | 7051/11066 [25:49<14:53,  4.49it/s]
 64%|██████▎   | 7052/11066 [25:49<14:50,  4.51it/s]
                                                    

 64%|██████▎   | 7052/11066 [25:49<14:50,  4.51it/s]
 64%|██████▎   | 7053/11066 [25:50<14:53,  4.49it/s]
                                                    

 64%|██████▎   | 7053/11066 [25:50<14:53,  4.49it/s]
 64%|██████▎   | 7054/11066 [25:50<14:55,  4.48it/s]
                                                    

 64%|██████▎   | 7054/11066 [25:50<14:55,  4.48it/s]
 64%|██████▍   | 7055/11066 [25:50<14:54,  4.49it/s]
                                                    

 64%|██████▍   | 7055/11066 [25:50<14:54,  4.49it/s]
 64%|██████▍   | 7056/11066 [25:50<14:46,  4.52it/s]
                                                    

 64%|██████▍   | 7056/11066 [25:50<14:46,  4.52it/s]
 64%|██████▍   | 7057/11066 [25:50<14:50,  4.50it/s]
                                                    

 64%|██████▍   | 7057/11066 [25:50<14:50,  4.50it/s]
 64%|██████▍   | 7058/11066 [25:51<14:45,  4.53it/s]
                                                    

 64%|██████▍   | 7058/11066 [25:51<14:45,  4.53it/s]
 64%|██████▍   | 7059/11066 [25:51<14:33,  4.59it/s]
                                                    

 64%|██████▍   | 7059/11066 [25:51<14:33,  4.59it/s]
 64%|██████▍   | 7060/11066 [25:51<14:26,  4.62it/s]
                                                    

 64%|██████▍   | 7060/11066 [25:51<14:26,  4.62it/s]
 64%|██████▍   | 7061/11066 [25:51<14:17,  4.67it/s]
                                                    

 64%|██████▍   | 7061/11066 [25:51<14:17,  4.67it/s]
 64%|██████▍   | 7062/11066 [25:52<14:22,  4.64it/s]
                                                    

 64%|██████▍   | 7062/11066 [25:52<14:22,  4.64it/s]
 64%|██████▍   | 7063/11066 [25:52<14:18,  4.66it/s]
                                                    

 64%|██████▍   | 7063/11066 [25:52<14:18,  4.66it/s]
 64%|██████▍   | 7064/11066 [25:52<14:14,  4.68it/s]
                                                    

 64%|██████▍   | 7064/11066 [25:52<14:14,  4.68it/s]
 64%|██████▍   | 7065/11066 [25:52<14:10,  4.70it/s]
                                                    

 64%|██████▍   | 7065/11066 [25:52<14:10,  4.70it/s]
 64%|██████▍   | 7066/11066 [25:52<14:05,  4.73it/s]
                                                    

 64%|██████▍   | 7066/11066 [25:52<14:05,  4.73it/s]
 64%|██████▍   | 7067/11066 [25:53<14:21,  4.64it/s]
                                                    

 64%|██████▍   | 7067/11066 [25:53<14:21,  4.64it/s]
 64%|██████▍   | 7068/11066 [25:53<14:24,  4.62it/s]
                                                    

 64%|██████▍   | 7068/11066 [25:53<14:24,  4.62it/s]
 64%|██████▍   | 7069/11066 [25:53<14:35,  4.57it/s]
                                                    

 64%|██████▍   | 7069/11066 [25:53<14:35,  4.57it/s]
 64%|██████▍   | 7070/11066 [25:53<14:28,  4.60it/s]
                                                    

 64%|██████▍   | 7070/11066 [25:53<14:28,  4.60it/s]
 64%|██████▍   | 7071/11066 [25:53<14:20,  4.64it/s]
                                                    

 64%|██████▍   | 7071/11066 [25:53<14:20,  4.64it/s]
 64%|██████▍   | 7072/11066 [25:54<14:19,  4.65it/s]
                                                    

 64%|██████▍   | 7072/11066 [25:54<14:19,  4.65it/s]
 64%|██████▍   | 7073/11066 [25:54<14:17,  4.66it/s]
                                                    

 64%|██████▍   | 7073/11066 [25:54<14:17,  4.66it/s]
 64%|██████▍   | 7074/11066 [25:54<14:14,  4.67it/s]
                                                    

 64%|██████▍   | 7074/11066 [25:54<14:14,  4.67it/s]
 64%|██████▍   | 7075/11066 [25:54<14:12,  4.68it/s]
                                                    

 64%|██████▍   | 7075/11066 [25:54<14:12,  4.68it/s]
 64%|██████▍   | 7076/11066 [25:55<14:11,  4.69it/s]
                                                    

 64%|██████▍   | 7076/11066 [25:55<14:11,  4.69it/s]
 64%|██████▍   | 7077/11066 [25:55<14:23,  4.62it/s]
                                                    

 64%|██████▍   | 7077/11066 [25:55<14:23,  4.62it/s]
 64%|██████▍   | 7078/11066 [25:55<14:18,  4.65it/s]
                                                    

 64%|██████▍   | 7078/11066 [25:55<14:18,  4.65it/s]
 64%|██████▍   | 7079/11066 [25:55<14:13,  4.67it/s]
                                                    

 64%|██████▍   | 7079/11066 [25:55<14:13,  4.67it/s]
 64%|██████▍   | 7080/11066 [25:55<14:17,  4.65it/s]
                                                    

 64%|██████▍   | 7080/11066 [25:55<14:17,  4.65it/s]
 64%|██████▍   | 7081/11066 [25:56<14:21,  4.63it/s]
                                                    

 64%|██████▍   | 7081/11066 [25:56<14:21,  4.63it/s]
 64%|██████▍   | 7082/11066 [25:56<14:21,  4.62it/s]
                                                    

 64%|██████▍   | 7082/11066 [25:56<14:21,  4.62it/s]
 64%|██████▍   | 7083/11066 [25:56<14:32,  4.56it/s]
                                                    

 64%|██████▍   | 7083/11066 [25:56<14:32,  4.56it/s]
 64%|██████▍   | 7084/11066 [25:56<14:38,  4.53it/s]
                                                    

 64%|██████▍   | 7084/11066 [25:56<14:38,  4.53it/s]
 64%|██████▍   | 7085/11066 [25:56<14:33,  4.56it/s]
                                                    
{'loss': 0.5992, 'learning_rate': 1.1096150370504248e-05, 'epoch': 1.26}
{'loss': 0.9269, 'learning_rate': 1.1093439363817098e-05, 'epoch': 1.26}
{'loss': 0.654, 'learning_rate': 1.1090728357129948e-05, 'epoch': 1.26}
{'loss': 0.9317, 'learning_rate': 1.1088017350442797e-05, 'epoch': 1.26}
{'loss': 0.4813, 'learning_rate': 1.1085306343755648e-05, 'epoch': 1.26}
{'loss': 0.6321, 'learning_rate': 1.1082595337068499e-05, 'epoch': 1.26}
{'loss': 0.3644, 'learning_rate': 1.1079884330381349e-05, 'epoch': 1.26}
{'loss': 0.9885, 'learning_rate': 1.1077173323694197e-05, 'epoch': 1.26}
{'loss': 1.282, 'learning_rate': 1.1074462317007049e-05, 'epoch': 1.26}
{'loss': 0.9609, 'learning_rate': 1.10717513103199e-05, 'epoch': 1.26}
{'loss': 0.8972, 'learning_rate': 1.106904030363275e-05, 'epoch': 1.26}
{'loss': 0.6032, 'learning_rate': 1.10663292969456e-05, 'epoch': 1.26}
{'loss': 0.636, 'learning_rate': 1.106361829025845e-05, 'epoch': 1.26}
{'loss': 0.6255, 'learning_rate': 1.10609072835713e-05, 'epoch': 1.26}
{'loss': 0.4946, 'learning_rate': 1.105819627688415e-05, 'epoch': 1.26}
{'loss': 0.2652, 'learning_rate': 1.1055485270197e-05, 'epoch': 1.26}
{'loss': 0.6025, 'learning_rate': 1.105277426350985e-05, 'epoch': 1.26}
{'loss': 0.7848, 'learning_rate': 1.10500632568227e-05, 'epoch': 1.26}
{'loss': 0.6187, 'learning_rate': 1.104735225013555e-05, 'epoch': 1.26}
{'loss': 0.9246, 'learning_rate': 1.10446412434484e-05, 'epoch': 1.26}
{'loss': 0.4462, 'learning_rate': 1.104193023676125e-05, 'epoch': 1.26}
{'loss': 0.3091, 'learning_rate': 1.10392192300741e-05, 'epoch': 1.26}
{'loss': 0.5771, 'learning_rate': 1.1036508223386953e-05, 'epoch': 1.26}
{'loss': 0.6854, 'learning_rate': 1.1033797216699801e-05, 'epoch': 1.26}
{'loss': 1.0573, 'learning_rate': 1.1031086210012651e-05, 'epoch': 1.26}
{'loss': 0.6211, 'learning_rate': 1.1028375203325501e-05, 'epoch': 1.26}
{'loss': 0.7094, 'learning_rate': 1.1025664196638353e-05, 'epoch': 1.26}
{'loss': 0.5543, 'learning_rate': 1.1022953189951202e-05, 'epoch': 1.27}
{'loss': 0.8649, 'learning_rate': 1.1020242183264052e-05, 'epoch': 1.27}
{'loss': 0.5473, 'learning_rate': 1.1017531176576902e-05, 'epoch': 1.27}
{'loss': 0.6957, 'learning_rate': 1.1014820169889754e-05, 'epoch': 1.27}
{'loss': 0.5622, 'learning_rate': 1.1012109163202602e-05, 'epoch': 1.27}
{'loss': 1.0004, 'learning_rate': 1.1009398156515452e-05, 'epoch': 1.27}
{'loss': 0.9419, 'learning_rate': 1.1006687149828304e-05, 'epoch': 1.27}
{'loss': 0.8258, 'learning_rate': 1.1003976143141154e-05, 'epoch': 1.27}
{'loss': 0.7511, 'learning_rate': 1.1001265136454003e-05, 'epoch': 1.27}
{'loss': 0.5556, 'learning_rate': 1.0998554129766853e-05, 'epoch': 1.27}
{'loss': 0.6924, 'learning_rate': 1.0995843123079705e-05, 'epoch': 1.27}
{'loss': 1.0198, 'learning_rate': 1.0993132116392555e-05, 'epoch': 1.27}
{'loss': 1.2882, 'learning_rate': 1.0990421109705403e-05, 'epoch': 1.27}
{'loss': 0.6564, 'learning_rate': 1.0987710103018255e-05, 'epoch': 1.27}
{'loss': 0.7301, 'learning_rate': 1.0984999096331105e-05, 'epoch': 1.27}
{'loss': 0.5352, 'learning_rate': 1.0982288089643955e-05, 'epoch': 1.27}
{'loss': 1.3387, 'learning_rate': 1.0979577082956804e-05, 'epoch': 1.27}
{'loss': 0.6634, 'learning_rate': 1.0976866076269656e-05, 'epoch': 1.27}
{'loss': 0.7781, 'learning_rate': 1.0974155069582506e-05, 'epoch': 1.27}
{'loss': 0.4235, 'learning_rate': 1.0971444062895356e-05, 'epoch': 1.27}
{'loss': 0.4303, 'learning_rate': 1.0968733056208204e-05, 'epoch': 1.27}
{'loss': 0.5759, 'learning_rate': 1.0966022049521056e-05, 'epoch': 1.27}
{'loss': 1.3737, 'learning_rate': 1.0963311042833906e-05, 'epoch': 1.27}
{'loss': 1.1332, 'learning_rate': 1.0960600036146756e-05, 'epoch': 1.27}
{'loss': 0.7133, 'learning_rate': 1.0957889029459606e-05, 'epoch': 1.27}
{'loss': 0.5309, 'learning_rate': 1.0955178022772457e-05, 'epoch': 1.27}
{'loss': 1.0056, 'learning_rate': 1.0952467016085307e-05, 'epoch': 1.27}
{'loss': 0.4239, 'learning_rate': 1.0949756009398157e-05, 'epoch': 1.27}
{'loss': 0.6574, 'learning_rate': 1.0947045002711007e-05, 'epoch': 1.27}
{'loss': 0.6253, 'learning_rate': 1.0944333996023857e-05, 'epoch': 1.27}
{'loss': 0.8318, 'learning_rate': 1.0941622989336707e-05, 'epoch': 1.27}
{'loss': 1.311, 'learning_rate': 1.0938911982649557e-05, 'epoch': 1.27}
{'loss': 0.9185, 'learning_rate': 1.0936200975962408e-05, 'epoch': 1.27}
{'loss': 1.021, 'learning_rate': 1.0933489969275258e-05, 'epoch': 1.27}
{'loss': 0.2973, 'learning_rate': 1.0930778962588108e-05, 'epoch': 1.27}
{'loss': 0.5277, 'learning_rate': 1.092806795590096e-05, 'epoch': 1.27}
{'loss': 0.9622, 'learning_rate': 1.0925356949213808e-05, 'epoch': 1.27}
{'loss': 1.233, 'learning_rate': 1.0922645942526658e-05, 'epoch': 1.27}
{'loss': 0.3025, 'learning_rate': 1.0919934935839508e-05, 'epoch': 1.27}
{'loss': 1.1745, 'learning_rate': 1.091722392915236e-05, 'epoch': 1.27}
{'loss': 1.3969, 'learning_rate': 1.0914512922465209e-05, 'epoch': 1.27}
{'loss': 0.5934, 'learning_rate': 1.0911801915778059e-05, 'epoch': 1.27}
{'loss': 0.9006, 'learning_rate': 1.0909090909090909e-05, 'epoch': 1.27}
{'loss': 0.9446, 'learning_rate': 1.090637990240376e-05, 'epoch': 1.27}
{'loss': 1.112, 'learning_rate': 1.090366889571661e-05, 'epoch': 1.27}
{'loss': 0.9792, 'learning_rate': 1.090095788902946e-05, 'epoch': 1.27}
{'loss': 0.7942, 'learning_rate': 1.0898246882342311e-05, 'epoch': 1.27}
{'loss': 0.8267, 'learning_rate': 1.0895535875655161e-05, 'epoch': 1.27}
{'loss': 0.6433, 'learning_rate': 1.089282486896801e-05, 'epoch': 1.27}
{'loss': 0.634, 'learning_rate': 1.089011386228086e-05, 'epoch': 1.27}
{'loss': 1.6257, 'learning_rate': 1.0887402855593712e-05, 'epoch': 1.27}
{'loss': 0.1894, 'learning_rate': 1.0884691848906562e-05, 'epoch': 1.27}
{'loss': 0.386, 'learning_rate': 1.088198084221941e-05, 'epoch': 1.27}
{'loss': 0.5396, 'learning_rate': 1.087926983553226e-05, 'epoch': 1.27}
{'loss': 0.8079, 'learning_rate': 1.0876558828845112e-05, 'epoch': 1.27}
{'loss': 0.5782, 'learning_rate': 1.0873847822157962e-05, 'epoch': 1.28}
{'loss': 0.5505, 'learning_rate': 1.087113681547081e-05, 'epoch': 1.28}
{'loss': 0.6073, 'learning_rate': 1.0868425808783663e-05, 'epoch': 1.28}
{'loss': 1.1413, 'learning_rate': 1.0865714802096513e-05, 'epoch': 1.28}
{'loss': 0.6535, 'learning_rate': 1.0863003795409363e-05, 'epoch': 1.28}
{'loss': 0.6832, 'learning_rate': 1.0860292788722211e-05, 'epoch': 1.28}
{'loss': 1.1889, 'learning_rate': 1.0857581782035063e-05, 'epoch': 1.28}
{'loss': 0.9343, 'learning_rate': 1.0854870775347913e-05, 'epoch': 1.28}
{'loss': 1.3548, 'learning_rate': 1.0852159768660763e-05, 'epoch': 1.28}
{'loss': 0.4971, 'learning_rate': 1.0849448761973612e-05, 'epoch': 1.28}
{'loss': 0.3967, 'learning_rate': 1.0846737755286464e-05, 'epoch': 1.28}
{'loss': 0.936, 'learning_rate': 1.0844026748599314e-05, 'epoch': 1.28}
{'loss': 0.6097, 'learning_rate': 1.0841315741912164e-05, 'epoch': 1.28}
{'loss': 0.6898, 'learning_rate': 1.0838604735225014e-05, 'epoch': 1.28}
{'loss': 0.8378, 'learning_rate': 1.0835893728537864e-05, 'epoch': 1.28}
{'loss': 1.0784, 'learning_rate': 1.0833182721850714e-05, 'epoch': 1.28}
{'loss': 0.7271, 'learning_rate': 1.0830471715163564e-05, 'epoch': 1.28}
{'loss': 0.9828, 'learning_rate': 1.0827760708476415e-05, 'epoch': 1.28}
{'loss': 1.2882, 'learning_rate': 1.0825049701789265e-05, 'epoch': 1.28}
{'loss': 0.6431, 'learning_rate': 1.0822338695102115e-05, 'epoch': 1.28}
{'loss': 0.2794, 'learning_rate': 1.0819627688414965e-05, 'epoch': 1.28}
{'loss': 0.6779, 'learning_rate': 1.0816916681727815e-05, 'epoch': 1.28}
{'loss': 0.7869, 'learning_rate': 1.0814205675040665e-05, 'epoch': 1.28}
{'loss': 0.7716, 'learning_rate': 1.0811494668353515e-05, 'epoch': 1.28}
{'loss': 0.738, 'learning_rate': 1.0808783661666366e-05, 'epoch': 1.28}
{'loss': 1.0807, 'learning_rate': 1.0806072654979216e-05, 'epoch': 1.28}
{'loss': 0.7477, 'learning_rate': 1.0803361648292066e-05, 'epoch': 1.28}
{'loss': 0.3269, 'learning_rate': 1.0800650641604916e-05, 'epoch': 1.28}
{'loss': 0.8454, 'learning_rate': 1.0797939634917766e-05, 'epoch': 1.28}
{'loss': 0.8828, 'learning_rate': 1.0795228628230616e-05, 'epoch': 1.28}

 64%|██████▍   | 7085/11066 [25:56<14:33,  4.56it/s]
 64%|██████▍   | 7086/11066 [25:57<14:28,  4.58it/s]
                                                    

 64%|██████▍   | 7086/11066 [25:57<14:28,  4.58it/s]
 64%|██████▍   | 7087/11066 [25:57<14:21,  4.62it/s]
                                                    

 64%|██████▍   | 7087/11066 [25:57<14:21,  4.62it/s]
 64%|██████▍   | 7088/11066 [25:57<14:16,  4.65it/s]
                                                    

 64%|██████▍   | 7088/11066 [25:57<14:16,  4.65it/s]
 64%|██████▍   | 7089/11066 [25:57<14:13,  4.66it/s]
                                                    

 64%|██████▍   | 7089/11066 [25:57<14:13,  4.66it/s]
 64%|██████▍   | 7090/11066 [25:58<14:22,  4.61it/s]
                                                    

 64%|██████▍   | 7090/11066 [25:58<14:22,  4.61it/s]
 64%|██████▍   | 7091/11066 [25:58<14:17,  4.64it/s]
                                                    

 64%|██████▍   | 7091/11066 [25:58<14:17,  4.64it/s]
 64%|██████▍   | 7092/11066 [25:58<14:13,  4.66it/s]
                                                    

 64%|██████▍   | 7092/11066 [25:58<14:13,  4.66it/s]
 64%|██████▍   | 7093/11066 [25:58<14:09,  4.68it/s]
                                                    

 64%|██████▍   | 7093/11066 [25:58<14:09,  4.68it/s]
 64%|██████▍   | 7094/11066 [25:58<14:12,  4.66it/s]
                                                    

 64%|██████▍   | 7094/11066 [25:58<14:12,  4.66it/s]
 64%|██████▍   | 7095/11066 [25:59<14:11,  4.66it/s]
                                                    

 64%|██████▍   | 7095/11066 [25:59<14:11,  4.66it/s]
 64%|██████▍   | 7096/11066 [25:59<14:22,  4.60it/s]
                                                    

 64%|██████▍   | 7096/11066 [25:59<14:22,  4.60it/s]
 64%|██████▍   | 7097/11066 [25:59<14:30,  4.56it/s]
                                                    

 64%|██████▍   | 7097/11066 [25:59<14:30,  4.56it/s]
 64%|██████▍   | 7098/11066 [25:59<14:22,  4.60it/s]
                                                    

 64%|██████▍   | 7098/11066 [25:59<14:22,  4.60it/s]
 64%|██████▍   | 7099/11066 [25:59<14:17,  4.63it/s]
                                                    

 64%|██████▍   | 7099/11066 [25:59<14:17,  4.63it/s]
 64%|██████▍   | 7100/11066 [26:00<14:11,  4.66it/s]
                                                    

 64%|██████▍   | 7100/11066 [26:00<14:11,  4.66it/s]
 64%|██████▍   | 7101/11066 [26:00<14:08,  4.68it/s]
                                                    

 64%|██████▍   | 7101/11066 [26:00<14:08,  4.68it/s]
 64%|██████▍   | 7102/11066 [26:00<14:06,  4.68it/s]
                                                    

 64%|██████▍   | 7102/11066 [26:00<14:06,  4.68it/s]
 64%|██████▍   | 7103/11066 [26:00<14:25,  4.58it/s]
                                                    

 64%|██████▍   | 7103/11066 [26:00<14:25,  4.58it/s]
 64%|██████▍   | 7104/11066 [26:01<14:24,  4.58it/s]
                                                    

 64%|██████▍   | 7104/11066 [26:01<14:24,  4.58it/s]
 64%|██████▍   | 7105/11066 [26:01<14:12,  4.65it/s]
                                                    

 64%|██████▍   | 7105/11066 [26:01<14:12,  4.65it/s]
 64%|██████▍   | 7106/11066 [26:01<14:22,  4.59it/s]
                                                    

 64%|██████▍   | 7106/11066 [26:01<14:22,  4.59it/s]
 64%|██████▍   | 7107/11066 [26:01<14:15,  4.63it/s]
                                                    

 64%|██████▍   | 7107/11066 [26:01<14:15,  4.63it/s]
 64%|██████▍   | 7108/11066 [26:01<14:10,  4.66it/s]
                                                    

 64%|██████▍   | 7108/11066 [26:01<14:10,  4.66it/s]
 64%|██████▍   | 7109/11066 [26:02<14:11,  4.65it/s]
                                                    

 64%|██████▍   | 7109/11066 [26:02<14:11,  4.65it/s]
 64%|██████▍   | 7110/11066 [26:02<14:03,  4.69it/s]
                                                    

 64%|██████▍   | 7110/11066 [26:02<14:03,  4.69it/s]
 64%|██████▍   | 7111/11066 [26:02<14:16,  4.62it/s]
                                                    

 64%|██████▍   | 7111/11066 [26:02<14:16,  4.62it/s]
 64%|██████▍   | 7112/11066 [26:02<14:15,  4.62it/s]
                                                    

 64%|██████▍   | 7112/11066 [26:02<14:15,  4.62it/s]
 64%|██████▍   | 7113/11066 [26:03<14:17,  4.61it/s]
                                                    

 64%|██████▍   | 7113/11066 [26:03<14:17,  4.61it/s]
 64%|██████▍   | 7114/11066 [26:03<14:24,  4.57it/s]
                                                    

 64%|██████▍   | 7114/11066 [26:03<14:24,  4.57it/s]
 64%|██████▍   | 7115/11066 [26:03<14:24,  4.57it/s]
                                                    

 64%|██████▍   | 7115/11066 [26:03<14:24,  4.57it/s]
 64%|██████▍   | 7116/11066 [26:03<14:22,  4.58it/s]
                                                    

 64%|██████▍   | 7116/11066 [26:03<14:22,  4.58it/s]
 64%|██████▍   | 7117/11066 [26:03<14:10,  4.64it/s]
                                                    

 64%|██████▍   | 7117/11066 [26:03<14:10,  4.64it/s]
 64%|██████▍   | 7118/11066 [26:04<14:18,  4.60it/s]
                                                    

 64%|██████▍   | 7118/11066 [26:04<14:18,  4.60it/s]
 64%|██████▍   | 7119/11066 [26:04<14:12,  4.63it/s]
                                                    

 64%|██████▍   | 7119/11066 [26:04<14:12,  4.63it/s]
 64%|██████▍   | 7120/11066 [26:04<14:12,  4.63it/s]
                                                    

 64%|██████▍   | 7120/11066 [26:04<14:12,  4.63it/s]
 64%|██████▍   | 7121/11066 [26:04<14:08,  4.65it/s]
                                                    

 64%|██████▍   | 7121/11066 [26:04<14:08,  4.65it/s]
 64%|██████▍   | 7122/11066 [26:04<14:08,  4.65it/s]
                                                    

 64%|██████▍   | 7122/11066 [26:04<14:08,  4.65it/s]
 64%|██████▍   | 7123/11066 [26:05<14:05,  4.67it/s]
                                                    

 64%|██████▍   | 7123/11066 [26:05<14:05,  4.67it/s]
 64%|██████▍   | 7124/11066 [26:05<14:15,  4.61it/s]
                                                    

 64%|██████▍   | 7124/11066 [26:05<14:15,  4.61it/s]
 64%|██████▍   | 7125/11066 [26:05<14:16,  4.60it/s]
                                                    

 64%|██████▍   | 7125/11066 [26:05<14:16,  4.60it/s]
 64%|██████▍   | 7126/11066 [26:05<14:14,  4.61it/s]
                                                    

 64%|██████▍   | 7126/11066 [26:05<14:14,  4.61it/s]
 64%|██████▍   | 7127/11066 [26:06<14:35,  4.50it/s]
                                                    

 64%|██████▍   | 7127/11066 [26:06<14:35,  4.50it/s]
 64%|██████▍   | 7128/11066 [26:06<14:28,  4.53it/s]
                                                    

 64%|██████▍   | 7128/11066 [26:06<14:28,  4.53it/s]
 64%|██████▍   | 7129/11066 [26:06<14:21,  4.57it/s]
                                                    

 64%|██████▍   | 7129/11066 [26:06<14:21,  4.57it/s]
 64%|██████▍   | 7130/11066 [26:06<14:12,  4.62it/s]
                                                    

 64%|██████▍   | 7130/11066 [26:06<14:12,  4.62it/s]
 64%|██████▍   | 7131/11066 [26:06<14:07,  4.64it/s]
                                                    

 64%|██████▍   | 7131/11066 [26:06<14:07,  4.64it/s]
 64%|██████▍   | 7132/11066 [26:07<14:15,  4.60it/s]
                                                    

 64%|██████▍   | 7132/11066 [26:07<14:15,  4.60it/s]
 64%|██████▍   | 7133/11066 [26:07<14:11,  4.62it/s]
                                                    

 64%|██████▍   | 7133/11066 [26:07<14:11,  4.62it/s]
 64%|██████▍   | 7134/11066 [26:07<14:06,  4.64it/s]
                                                    

 64%|██████▍   | 7134/11066 [26:07<14:06,  4.64it/s]
 64%|██████▍   | 7135/11066 [26:07<14:16,  4.59it/s]
                                                    

 64%|██████▍   | 7135/11066 [26:07<14:16,  4.59it/s]
 64%|██████▍   | 7136/11066 [26:08<14:22,  4.56it/s]
                                                    

 64%|██████▍   | 7136/11066 [26:08<14:22,  4.56it/s]
 64%|██████▍   | 7137/11066 [26:08<14:14,  4.60it/s]
                                                    

 64%|██████▍   | 7137/11066 [26:08<14:14,  4.60it/s]
 65%|██████▍   | 7138/11066 [26:08<14:07,  4.64it/s]
                                                    

 65%|██████▍   | 7138/11066 [26:08<14:07,  4.64it/s]
 65%|██████▍   | 7139/11066 [26:08<14:03,  4.66it/s]
                                                    

 65%|██████▍   | 7139/11066 [26:08<14:03,  4.66it/s]
 65%|██████▍   | 7140/11066 [26:08<14:06,  4.64it/s]
                                                    

 65%|██████▍   | 7140/11066 [26:08<14:06,  4.64it/s]
 65%|██████▍   | 7141/11066 [26:09<14:10,  4.62it/s]
                                                    

 65%|██████▍   | 7141/11066 [26:09<14:10,  4.62it/s]
 65%|██████▍   | 7142/11066 [26:09<14:05,  4.64it/s]
                                                    

 65%|██████▍   | 7142/11066 [26:09<14:05,  4.64it/s]
 65%|██████▍   | 7143/11066 [26:09<13:57,  4.68it/s]
                                                    

 65%|██████▍   | 7143/11066 [26:09<13:57,  4.68it/s]
 65%|██████▍   | 7144/11066 [26:09<13:56,  4.69it/s]
                                                    

 65%|██████▍   | 7144/11066 [26:09<13:56,  4.69it/s]
 65%|██████▍   | 7145/11066 [26:09<13:54,  4.70it/s]
                                                    

 65%|██████▍   | 7145/11066 [26:09<13:54,  4.70it/s]
 65%|██████▍   | 7146/11066 [26:10<14:05,  4.64it/s]
                                                    

 65%|██████▍   | 7146/11066 [26:10<14:05,  4.64it/s]
 65%|██████▍   | 7147/11066 [26:10<14:08,  4.62it/s]
                                                    

 65%|██████▍   | 7147/11066 [26:10<14:08,  4.62it/s]
 65%|██████▍   | 7148/11066 [26:10<14:09,  4.61it/s]
                                                    

 65%|██████▍   | 7148/11066 [26:10<14:09,  4.61it/s]
 65%|██████▍   | 7149/11066 [26:10<14:04,  4.64it/s]
                                                    

 65%|██████▍   | 7149/11066 [26:10<14:04,  4.64it/s]
 65%|██████▍   | 7150/11066 [26:11<14:05,  4.63it/s]
                                                    

 65%|██████▍   | 7150/11066 [26:11<14:05,  4.63it/s]
 65%|██████▍   | 7151/11066 [26:11<14:15,  4.58it/s]
                                                    

 65%|██████▍   | 7151/11066 [26:11<14:15,  4.58it/s]
 65%|██████▍   | 7152/11066 [26:11<14:09,  4.61it/s]
                                                    

 65%|██████▍   | 7152/11066 [26:11<14:09,  4.61it/s]
 65%|██████▍   | 7153/11066 [26:11<14:18,  4.56it/s]
                                                    

 65%|██████▍   | 7153/11066 [26:11<14:18,  4.56it/s]
 65%|██████▍   | 7154/11066 [26:11<14:22,  4.54it/s]
                                                    

 65%|██████▍   | 7154/11066 [26:11<14:22,  4.54it/s]
 65%|██████▍   | 7155/11066 [26:12<14:24,  4.52it/s]
                                                    

 65%|██████▍   | 7155/11066 [26:12<14:24,  4.52it/s]
 65%|██████▍   | 7156/11066 [26:12<14:13,  4.58it/s]
                                                    

 65%|██████▍   | 7156/11066 [26:12<14:13,  4.58it/s]
 65%|██████▍   | 7157/11066 [26:12<14:05,  4.62it/s]
                                                    

 65%|██████▍   | 7157/11066 [26:12<14:05,  4.62it/s]
 65%|██████▍   | 7158/11066 [26:12<14:00,  4.65it/s]
                                                    

 65%|██████▍   | 7158/11066 [26:12<14:00,  4.65it/s]
 65%|██████▍   | 7159/11066 [26:12<13:56,  4.67it/s]
                                                    

 65%|██████▍   | 7159/11066 [26:12<13:56,  4.67it/s]
 65%|██████▍   | 7160/11066 [26:13<13:54,  4.68it/s]
                                                    

 65%|██████▍   | 7160/11066 [26:13<13:54,  4.68it/s]
 65%|██████▍   | 7161/11066 [26:13<13:52,  4.69it/s]
                                                    

 65%|██████▍   | 7161/11066 [26:13<13:52,  4.69it/s]
 65%|██████▍   | 7162/11066 [26:13<13:50,  4.70it/s]
                                                    

 65%|██████▍   | 7162/11066 [26:13<13:50,  4.70it/s]
 65%|██████▍   | 7163/11066 [26:13<13:55,  4.67it/s]
                                                    

 65%|██████▍   | 7163/11066 [26:13<13:55,  4.67it/s]
 65%|██████▍   | 7164/11066 [26:14<13:54,  4.67it/s]
                                                    

 65%|██████▍   | 7164/11066 [26:14<13:54,  4.67it/s]
 65%|██████▍   | 7165/11066 [26:14<13:58,  4.65it/s]
                                                    

 65%|██████▍   | 7165/11066 [26:14<13:58,  4.65it/s]
 65%|██████▍   | 7166/11066 [26:14<14:05,  4.61it/s]
                                                    

 65%|██████▍   | 7166/11066 [26:14<14:05,  4.61it/s]
 65%|██████▍   | 7167/11066 [26:14<14:12,  4.57it/s]
                                                    

 65%|██████▍   | 7167/11066 [26:14<14:12,  4.57it/s]
 65%|██████▍   | 7168/11066 [26:14<14:17,  4.55it/s]
                                                    

 65%|██████▍   | 7168/11066 [26:14<14:17,  4.55it/s]
 65%|██████▍   | 7169/11066 [26:15<14:19,  4.53it/s]
                                                    

 65%|██████▍   | 7169/11066 [26:15<14:19,  4.53it/s]
 65%|██████▍   | 7170/11066 [26:15<14:14,  4.56it/s]
                                                    

 65%|██████▍   | 7170/11066 [26:15<14:14,  4.56it/s]
 65%|██████▍   | 7171/11066 [26:15<14:02,  4.62it/s]
                                                    

 65%|██████▍   | 7171/11066 [26:15<14:02,  4.62it/s]
 65%|██████▍   | 7172/11066 [26:15<13:58,  4.64it/s]
                                                    

 65%|██████▍   | 7172/11066 [26:15<13:58,  4.64it/s]
 65%|██████▍   | 7173/11066 [26:16<14:07,  4.60it/s]
                                                    

 65%|██████▍   | 7173/11066 [26:16<14:07,  4.60it/s]
 65%|██████▍   | 7174/11066 [26:16<14:05,  4.60it/s]
                                                    

 65%|██████▍   | 7174/11066 [26:16<14:05,  4.60it/s]
 65%|██████▍   | 7175/11066 [26:16<14:01,  4.63it/s]
                                                    

 65%|██████▍   | 7175/11066 [26:16<14:01,  4.63it/s]
 65%|██████▍   | 7176/11066 [26:16<13:59,  4.63it/s]
                                                    

 65%|██████▍   | 7176/11066 [26:16<13:59,  4.63it/s]
 65%|██████▍   | 7177/11066 [26:16<14:01,  4.62it/s]
                                                    

 65%|██████▍   | 7177/11066 [26:16<14:01,  4.62it/s]
 65%|██████▍   | 7178/11066 [26:17<13:58,  4.64it/s]
                                                    

 65%|██████▍   | 7178/11066 [26:17<13:58,  4.64it/s]
 65%|██████▍   | 7179/11066 [26:17<13:58,  4.63it/s]
                                                    

 65%|██████▍   | 7179/11066 [26:17<13:58,  4.63it/s]
 65%|██████▍   | 7180/11066 [26:17<14:00,  4.62it/s]
                                                    

 65%|██████▍   | 7180/11066 [26:17<14:00,  4.62it/s]
 65%|██████▍   | 7181/11066 [26:17<14:03,  4.61it/s]
                                                    

 65%|██████▍   | 7181/11066 [26:17<14:03,  4.61it/s]
 65%|██████▍   | 7182/11066 [26:17<14:08,  4.58it/s]
                                                    

 65%|██████▍   | 7182/11066 [26:17<14:08,  4.58it/s]
 65%|██████▍   | 7183/11066 [26:18<14:13,  4.55it/s]
                                                    

 65%|██████▍   | 7183/11066 [26:18<14:13,  4.55it/s]
 65%|██████▍   | 7184/11066 [26:18<14:15,  4.54it/s]
                                                    

 65%|██████▍   | 7184/11066 [26:18<14:15,  4.54it/s]
 65%|██████▍   | 7185/11066 [26:18<14:17,  4.53it/s]
                                                    

 65%|██████▍   | 7185/11066 [26:18<14:17,  4.53it/s]
 65%|██████▍   | 7186/11066 [26:18<14:13,  4.55it/s]
                                                    

 65%|██████▍   | 7186/11066 [26:18<14:13,  4.55it/s]
 65%|██████▍   | 7187/11066 [26:19<13:59,  4.62it/s]
                                                    

 65%|██████▍   | 7187/11066 [26:19<13:59,  4.62it/s]
 65%|██████▍   | 7188/11066 [26:19<14:09,  4.57it/s]
                                                    

 65%|██████▍   | 7188/11066 [26:19<14:09,  4.57it/s]
 65%|██████▍   | 7189/11066 [26:19<13:56,  4.64it/s]
                                                    

 65%|██████▍   | 7189/11066 [26:19<13:56,  4.64it/s]
 65%|██████▍   | 7190/11066 [26:19<13:58,  4.62it/s]
                                                    

 65%|██████▍   | 7190/11066 [26:19<13:58,  4.62it/s]
 65%|██████▍   | 7191/11066 [26:19<13:50,  4.67it/s]
                                                    

 65%|██████▍   | 7191/11066 [26:19<13:50,  4.67it/s]
 65%|██████▍   | 7192/11066 [26:20<13:58,  4.62it/s]
                                                    

 65%|██████▍   | 7192/11066 [26:20<13:58,  4.62it/s]
 65%|██████▌   | 7193/11066 [26:20<14:04,  4.59it/s]
                                                    

 65%|██████▌   | 7193/11066 [26:20<14:04,  4.59it/s]
 65%|██████▌   | 7194/11066 [26:20<13:57,  4.63it/s]
                                                    

 65%|██████▌   | 7194/11066 [26:20<13:57,  4.63it/s]
 65%|██████▌   | 7195/11066 [26:20<14:06,  4.57it/s]
                                                    

 65%|██████▌   | 7195/11066 [26:20<14:06,  4.57it/s]
 65%|██████▌   | 7196/11066 [26:21<14:11,  4.55it/s]
                                                    

 65%|██████▌   | 7196/11066 [26:21<14:11,  4.55it/s]
 65%|██████▌   | 7197/11066 [26:21<14:08,  4.56it/s]
                                                    

 65%|██████▌   | 7197/11066 [26:21<14:08,  4.56it/s]
 65%|██████▌   | 7198/11066 [26:21<14:04,  4.58it/s]
                                                    
{'loss': 0.7937, 'learning_rate': 1.0792517621543466e-05, 'epoch': 1.28}
{'loss': 0.8288, 'learning_rate': 1.0789806614856318e-05, 'epoch': 1.28}
{'loss': 1.0285, 'learning_rate': 1.0787095608169167e-05, 'epoch': 1.28}
{'loss': 0.9279, 'learning_rate': 1.0784384601482017e-05, 'epoch': 1.28}
{'loss': 0.5269, 'learning_rate': 1.0781673594794867e-05, 'epoch': 1.28}
{'loss': 0.5685, 'learning_rate': 1.0778962588107719e-05, 'epoch': 1.28}
{'loss': 0.7239, 'learning_rate': 1.0776251581420567e-05, 'epoch': 1.28}
{'loss': 0.8828, 'learning_rate': 1.0773540574733417e-05, 'epoch': 1.28}
{'loss': 0.4329, 'learning_rate': 1.0770829568046267e-05, 'epoch': 1.28}
{'loss': 0.7346, 'learning_rate': 1.076811856135912e-05, 'epoch': 1.28}
{'loss': 0.6491, 'learning_rate': 1.0765407554671968e-05, 'epoch': 1.28}
{'loss': 0.5734, 'learning_rate': 1.0762696547984818e-05, 'epoch': 1.28}
{'loss': 0.8371, 'learning_rate': 1.075998554129767e-05, 'epoch': 1.28}
{'loss': 1.6556, 'learning_rate': 1.075727453461052e-05, 'epoch': 1.28}
{'loss': 1.1206, 'learning_rate': 1.0754563527923368e-05, 'epoch': 1.28}
{'loss': 0.6181, 'learning_rate': 1.0751852521236218e-05, 'epoch': 1.28}
{'loss': 0.9211, 'learning_rate': 1.074914151454907e-05, 'epoch': 1.28}
{'loss': 0.621, 'learning_rate': 1.074643050786192e-05, 'epoch': 1.28}
{'loss': 0.6225, 'learning_rate': 1.0743719501174769e-05, 'epoch': 1.28}
{'loss': 0.5728, 'learning_rate': 1.0741008494487619e-05, 'epoch': 1.28}
{'loss': 0.4669, 'learning_rate': 1.073829748780047e-05, 'epoch': 1.28}
{'loss': 0.4916, 'learning_rate': 1.0735586481113321e-05, 'epoch': 1.28}
{'loss': 0.6737, 'learning_rate': 1.073287547442617e-05, 'epoch': 1.28}
{'loss': 0.8336, 'learning_rate': 1.0730164467739021e-05, 'epoch': 1.28}
{'loss': 0.521, 'learning_rate': 1.0727453461051871e-05, 'epoch': 1.28}
{'loss': 0.4678, 'learning_rate': 1.0724742454364721e-05, 'epoch': 1.29}
{'loss': 0.6854, 'learning_rate': 1.072203144767757e-05, 'epoch': 1.29}
{'loss': 0.4818, 'learning_rate': 1.0719320440990422e-05, 'epoch': 1.29}
{'loss': 0.7278, 'learning_rate': 1.0716609434303272e-05, 'epoch': 1.29}
{'loss': 0.4774, 'learning_rate': 1.0713898427616122e-05, 'epoch': 1.29}
{'loss': 0.6599, 'learning_rate': 1.071118742092897e-05, 'epoch': 1.29}
{'loss': 0.9295, 'learning_rate': 1.0708476414241822e-05, 'epoch': 1.29}
{'loss': 0.4477, 'learning_rate': 1.0705765407554672e-05, 'epoch': 1.29}
{'loss': 0.6161, 'learning_rate': 1.0703054400867522e-05, 'epoch': 1.29}
{'loss': 1.0749, 'learning_rate': 1.0700343394180373e-05, 'epoch': 1.29}
{'loss': 0.5939, 'learning_rate': 1.0697632387493223e-05, 'epoch': 1.29}
{'loss': 0.9207, 'learning_rate': 1.0694921380806073e-05, 'epoch': 1.29}
{'loss': 0.5064, 'learning_rate': 1.0692210374118923e-05, 'epoch': 1.29}
{'loss': 0.5255, 'learning_rate': 1.0689499367431773e-05, 'epoch': 1.29}
{'loss': 1.2325, 'learning_rate': 1.0686788360744623e-05, 'epoch': 1.29}
{'loss': 1.1526, 'learning_rate': 1.0684077354057473e-05, 'epoch': 1.29}
{'loss': 0.6871, 'learning_rate': 1.0681366347370324e-05, 'epoch': 1.29}
{'loss': 0.3412, 'learning_rate': 1.0678655340683174e-05, 'epoch': 1.29}
{'loss': 1.4971, 'learning_rate': 1.0675944333996024e-05, 'epoch': 1.29}
{'loss': 0.5714, 'learning_rate': 1.0673233327308874e-05, 'epoch': 1.29}
{'loss': 0.9512, 'learning_rate': 1.0670522320621726e-05, 'epoch': 1.29}
{'loss': 1.2546, 'learning_rate': 1.0667811313934574e-05, 'epoch': 1.29}
{'loss': 0.6855, 'learning_rate': 1.0665100307247424e-05, 'epoch': 1.29}
{'loss': 0.6911, 'learning_rate': 1.0662389300560275e-05, 'epoch': 1.29}
{'loss': 0.2957, 'learning_rate': 1.0659678293873126e-05, 'epoch': 1.29}
{'loss': 0.7959, 'learning_rate': 1.0656967287185975e-05, 'epoch': 1.29}
{'loss': 0.5716, 'learning_rate': 1.0654256280498825e-05, 'epoch': 1.29}
{'loss': 0.6212, 'learning_rate': 1.0651545273811675e-05, 'epoch': 1.29}
{'loss': 0.7058, 'learning_rate': 1.0648834267124527e-05, 'epoch': 1.29}
{'loss': 1.1381, 'learning_rate': 1.0646123260437375e-05, 'epoch': 1.29}
{'loss': 0.9161, 'learning_rate': 1.0643412253750225e-05, 'epoch': 1.29}
{'loss': 0.7285, 'learning_rate': 1.0640701247063077e-05, 'epoch': 1.29}
{'loss': 0.8909, 'learning_rate': 1.0637990240375927e-05, 'epoch': 1.29}
{'loss': 0.7889, 'learning_rate': 1.0635279233688776e-05, 'epoch': 1.29}
{'loss': 1.3969, 'learning_rate': 1.0632568227001626e-05, 'epoch': 1.29}
{'loss': 0.4555, 'learning_rate': 1.0629857220314478e-05, 'epoch': 1.29}
{'loss': 0.8253, 'learning_rate': 1.0627146213627328e-05, 'epoch': 1.29}
{'loss': 0.8738, 'learning_rate': 1.0624435206940176e-05, 'epoch': 1.29}
{'loss': 0.4559, 'learning_rate': 1.0621724200253027e-05, 'epoch': 1.29}
{'loss': 0.6937, 'learning_rate': 1.0619013193565878e-05, 'epoch': 1.29}
{'loss': 0.7368, 'learning_rate': 1.0616302186878728e-05, 'epoch': 1.29}
{'loss': 0.3157, 'learning_rate': 1.0613591180191577e-05, 'epoch': 1.29}
{'loss': 1.023, 'learning_rate': 1.0610880173504429e-05, 'epoch': 1.29}
{'loss': 0.7385, 'learning_rate': 1.0608169166817279e-05, 'epoch': 1.29}
{'loss': 0.731, 'learning_rate': 1.0605458160130129e-05, 'epoch': 1.29}
{'loss': 0.9162, 'learning_rate': 1.0602747153442977e-05, 'epoch': 1.29}
{'loss': 0.4214, 'learning_rate': 1.060003614675583e-05, 'epoch': 1.29}
{'loss': 0.7421, 'learning_rate': 1.059732514006868e-05, 'epoch': 1.29}
{'loss': 1.092, 'learning_rate': 1.059461413338153e-05, 'epoch': 1.29}
{'loss': 0.9875, 'learning_rate': 1.059190312669438e-05, 'epoch': 1.29}
{'loss': 0.9953, 'learning_rate': 1.058919212000723e-05, 'epoch': 1.29}
{'loss': 0.7342, 'learning_rate': 1.058648111332008e-05, 'epoch': 1.29}
{'loss': 0.727, 'learning_rate': 1.058377010663293e-05, 'epoch': 1.29}
{'loss': 0.787, 'learning_rate': 1.058105909994578e-05, 'epoch': 1.29}
{'loss': 0.7953, 'learning_rate': 1.057834809325863e-05, 'epoch': 1.29}
{'loss': 0.5149, 'learning_rate': 1.057563708657148e-05, 'epoch': 1.29}
{'loss': 0.7082, 'learning_rate': 1.057292607988433e-05, 'epoch': 1.3}
{'loss': 0.6657, 'learning_rate': 1.057021507319718e-05, 'epoch': 1.3}
{'loss': 0.4633, 'learning_rate': 1.0567504066510031e-05, 'epoch': 1.3}
{'loss': 0.426, 'learning_rate': 1.0564793059822881e-05, 'epoch': 1.3}
{'loss': 1.5247, 'learning_rate': 1.0562082053135733e-05, 'epoch': 1.3}
{'loss': 0.2347, 'learning_rate': 1.0559371046448581e-05, 'epoch': 1.3}
{'loss': 0.6417, 'learning_rate': 1.0556660039761431e-05, 'epoch': 1.3}
{'loss': 0.4872, 'learning_rate': 1.0553949033074282e-05, 'epoch': 1.3}
{'loss': 0.8514, 'learning_rate': 1.0551238026387133e-05, 'epoch': 1.3}
{'loss': 0.8878, 'learning_rate': 1.0548527019699982e-05, 'epoch': 1.3}
{'loss': 0.8238, 'learning_rate': 1.0545816013012832e-05, 'epoch': 1.3}
{'loss': 0.7042, 'learning_rate': 1.0543105006325682e-05, 'epoch': 1.3}
{'loss': 0.8976, 'learning_rate': 1.0540393999638534e-05, 'epoch': 1.3}
{'loss': 0.5031, 'learning_rate': 1.0537682992951382e-05, 'epoch': 1.3}
{'loss': 0.6858, 'learning_rate': 1.0534971986264233e-05, 'epoch': 1.3}
{'loss': 0.764, 'learning_rate': 1.0532260979577084e-05, 'epoch': 1.3}
{'loss': 0.6781, 'learning_rate': 1.0529549972889934e-05, 'epoch': 1.3}
{'loss': 1.0712, 'learning_rate': 1.0526838966202783e-05, 'epoch': 1.3}
{'loss': 1.2349, 'learning_rate': 1.0524127959515633e-05, 'epoch': 1.3}
{'loss': 0.41, 'learning_rate': 1.0521416952828485e-05, 'epoch': 1.3}
{'loss': 0.4693, 'learning_rate': 1.0518705946141335e-05, 'epoch': 1.3}
{'loss': 0.7404, 'learning_rate': 1.0515994939454183e-05, 'epoch': 1.3}
{'loss': 0.5827, 'learning_rate': 1.0513283932767034e-05, 'epoch': 1.3}
{'loss': 0.561, 'learning_rate': 1.0510572926079885e-05, 'epoch': 1.3}
{'loss': 0.6129, 'learning_rate': 1.0507861919392736e-05, 'epoch': 1.3}
{'loss': 0.3873, 'learning_rate': 1.0505150912705584e-05, 'epoch': 1.3}
{'loss': 0.6434, 'learning_rate': 1.0502439906018436e-05, 'epoch': 1.3}
{'loss': 0.3498, 'learning_rate': 1.0499728899331286e-05, 'epoch': 1.3}
{'loss': 1.4526, 'learning_rate': 1.0497017892644136e-05, 'epoch': 1.3}
{'loss': 0.4942, 'learning_rate': 1.0494306885956985e-05, 'epoch': 1.3}
{'loss': 0.7435, 'learning_rate': 1.0491595879269836e-05, 'epoch': 1.3}
{'loss': 0.4472, 'learning_rate': 1.0488884872582686e-05, 'epoch': 1.3}

 65%|██████▌   | 7198/11066 [26:21<14:04,  4.58it/s]
 65%|██████▌   | 7199/11066 [26:21<14:01,  4.59it/s]
                                                    

 65%|██████▌   | 7199/11066 [26:21<14:01,  4.59it/s]
 65%|██████▌   | 7200/11066 [26:21<13:56,  4.62it/s]
                                                    

 65%|██████▌   | 7200/11066 [26:21<13:56,  4.62it/s]
 65%|██████▌   | 7201/11066 [26:22<13:53,  4.64it/s]
                                                    

 65%|██████▌   | 7201/11066 [26:22<13:53,  4.64it/s]
 65%|██████▌   | 7202/11066 [26:22<13:50,  4.65it/s]
                                                    

 65%|██████▌   | 7202/11066 [26:22<13:50,  4.65it/s]
 65%|██████▌   | 7203/11066 [26:22<13:48,  4.67it/s]
                                                    

 65%|██████▌   | 7203/11066 [26:22<13:48,  4.67it/s]
 65%|██████▌   | 7204/11066 [26:22<13:45,  4.68it/s]
                                                    

 65%|██████▌   | 7204/11066 [26:22<13:45,  4.68it/s]
 65%|██████▌   | 7205/11066 [26:22<13:42,  4.69it/s]
                                                    

 65%|██████▌   | 7205/11066 [26:22<13:42,  4.69it/s]
 65%|██████▌   | 7206/11066 [26:23<13:41,  4.70it/s]
                                                    

 65%|██████▌   | 7206/11066 [26:23<13:41,  4.70it/s]
 65%|██████▌   | 7207/11066 [26:23<13:40,  4.71it/s]
                                                    

 65%|██████▌   | 7207/11066 [26:23<13:40,  4.71it/s]
 65%|██████▌   | 7208/11066 [26:23<13:38,  4.71it/s]
                                                    

 65%|██████▌   | 7208/11066 [26:23<13:38,  4.71it/s]
 65%|██████▌   | 7209/11066 [26:23<13:45,  4.67it/s]
                                                    

 65%|██████▌   | 7209/11066 [26:23<13:45,  4.67it/s]
 65%|██████▌   | 7210/11066 [26:24<13:48,  4.66it/s]
                                                    

 65%|██████▌   | 7210/11066 [26:24<13:48,  4.66it/s]
 65%|██████▌   | 7211/11066 [26:24<13:51,  4.64it/s]
                                                    

 65%|██████▌   | 7211/11066 [26:24<13:51,  4.64it/s]
 65%|██████▌   | 7212/11066 [26:24<13:46,  4.66it/s]
                                                    

 65%|██████▌   | 7212/11066 [26:24<13:46,  4.66it/s]
 65%|██████▌   | 7213/11066 [26:24<13:39,  4.70it/s]
                                                    

 65%|██████▌   | 7213/11066 [26:24<13:39,  4.70it/s]
 65%|██████▌   | 7214/11066 [26:24<13:39,  4.70it/s]
                                                    

 65%|██████▌   | 7214/11066 [26:24<13:39,  4.70it/s]
 65%|██████▌   | 7215/11066 [26:25<13:35,  4.73it/s]
                                                    

 65%|██████▌   | 7215/11066 [26:25<13:35,  4.73it/s]
 65%|██████▌   | 7216/11066 [26:25<13:35,  4.72it/s]
                                                    

 65%|██████▌   | 7216/11066 [26:25<13:35,  4.72it/s]
 65%|██████▌   | 7217/11066 [26:25<13:36,  4.71it/s]
                                                    

 65%|██████▌   | 7217/11066 [26:25<13:36,  4.71it/s]
 65%|██████▌   | 7218/11066 [26:25<13:47,  4.65it/s]
                                                    

 65%|██████▌   | 7218/11066 [26:25<13:47,  4.65it/s]
 65%|██████▌   | 7219/11066 [26:25<13:56,  4.60it/s]
                                                    

 65%|██████▌   | 7219/11066 [26:25<13:56,  4.60it/s]
 65%|██████▌   | 7220/11066 [26:26<14:02,  4.56it/s]
                                                    

 65%|██████▌   | 7220/11066 [26:26<14:02,  4.56it/s]
 65%|██████▌   | 7221/11066 [26:26<13:54,  4.61it/s]
                                                    

 65%|██████▌   | 7221/11066 [26:26<13:54,  4.61it/s]
 65%|██████▌   | 7222/11066 [26:26<13:48,  4.64it/s]
                                                    

 65%|██████▌   | 7222/11066 [26:26<13:48,  4.64it/s]
 65%|██████▌   | 7223/11066 [26:26<13:41,  4.68it/s]
                                                    

 65%|██████▌   | 7223/11066 [26:26<13:41,  4.68it/s]
 65%|██████▌   | 7224/11066 [26:27<13:53,  4.61it/s]
                                                    

 65%|██████▌   | 7224/11066 [26:27<13:53,  4.61it/s]
 65%|██████▌   | 7225/11066 [26:27<14:15,  4.49it/s]
                                                    

 65%|██████▌   | 7225/11066 [26:27<14:15,  4.49it/s]
 65%|██████▌   | 7226/11066 [26:27<14:10,  4.52it/s]
                                                    

 65%|██████▌   | 7226/11066 [26:27<14:10,  4.52it/s]
 65%|██████▌   | 7227/11066 [26:27<14:13,  4.50it/s]
                                                    

 65%|██████▌   | 7227/11066 [26:27<14:13,  4.50it/s]
 65%|██████▌   | 7228/11066 [26:27<14:21,  4.46it/s]
                                                    

 65%|██████▌   | 7228/11066 [26:27<14:21,  4.46it/s]
 65%|██████▌   | 7229/11066 [26:28<14:29,  4.41it/s]
                                                    

 65%|██████▌   | 7229/11066 [26:28<14:29,  4.41it/s]
 65%|██████▌   | 7230/11066 [26:28<14:25,  4.43it/s]
                                                    

 65%|██████▌   | 7230/11066 [26:28<14:25,  4.43it/s]
 65%|██████▌   | 7231/11066 [26:28<14:23,  4.44it/s]
                                                    

 65%|██████▌   | 7231/11066 [26:28<14:23,  4.44it/s]
 65%|██████▌   | 7232/11066 [26:28<14:21,  4.45it/s]
                                                    

 65%|██████▌   | 7232/11066 [26:28<14:21,  4.45it/s]
 65%|██████▌   | 7233/11066 [26:29<14:18,  4.47it/s]
                                                    

 65%|██████▌   | 7233/11066 [26:29<14:18,  4.47it/s]
 65%|██████▌   | 7234/11066 [26:29<14:16,  4.48it/s]
                                                    

 65%|██████▌   | 7234/11066 [26:29<14:16,  4.48it/s]
 65%|██████▌   | 7235/11066 [26:29<14:15,  4.48it/s]
                                                    

 65%|██████▌   | 7235/11066 [26:29<14:15,  4.48it/s]
 65%|██████▌   | 7236/11066 [26:29<14:14,  4.48it/s]
                                                    

 65%|██████▌   | 7236/11066 [26:29<14:14,  4.48it/s]
 65%|██████▌   | 7237/11066 [26:29<14:07,  4.52it/s]
                                                    

 65%|██████▌   | 7237/11066 [26:29<14:07,  4.52it/s]
 65%|██████▌   | 7238/11066 [26:30<14:11,  4.50it/s]
                                                    

 65%|██████▌   | 7238/11066 [26:30<14:11,  4.50it/s]
 65%|██████▌   | 7239/11066 [26:30<14:12,  4.49it/s]
                                                    

 65%|██████▌   | 7239/11066 [26:30<14:12,  4.49it/s]
 65%|██████▌   | 7240/11066 [26:30<14:12,  4.49it/s]
                                                    

 65%|██████▌   | 7240/11066 [26:30<14:12,  4.49it/s]
 65%|██████▌   | 7241/11066 [26:30<14:11,  4.49it/s]
                                                    

 65%|██████▌   | 7241/11066 [26:30<14:11,  4.49it/s]
 65%|██████▌   | 7242/11066 [26:31<14:20,  4.45it/s]
                                                    

 65%|██████▌   | 7242/11066 [26:31<14:20,  4.45it/s]
 65%|██████▌   | 7243/11066 [26:31<14:19,  4.45it/s]
                                                    

 65%|██████▌   | 7243/11066 [26:31<14:19,  4.45it/s]
 65%|██████▌   | 7244/11066 [26:31<14:10,  4.50it/s]
                                                    

 65%|██████▌   | 7244/11066 [26:31<14:10,  4.50it/s]
 65%|██████▌   | 7245/11066 [26:31<14:06,  4.51it/s]
                                                    

 65%|██████▌   | 7245/11066 [26:31<14:06,  4.51it/s]
 65%|██████▌   | 7246/11066 [26:31<14:06,  4.51it/s]
                                                    

 65%|██████▌   | 7246/11066 [26:31<14:06,  4.51it/s]
 65%|██████▌   | 7247/11066 [26:32<13:59,  4.55it/s]
                                                    

 65%|██████▌   | 7247/11066 [26:32<13:59,  4.55it/s]
 65%|██████▌   | 7248/11066 [26:32<13:53,  4.58it/s]
                                                    

 65%|██████▌   | 7248/11066 [26:32<13:53,  4.58it/s]
 66%|██████▌   | 7249/11066 [26:32<13:52,  4.59it/s]
                                                    

 66%|██████▌   | 7249/11066 [26:32<13:52,  4.59it/s]
 66%|██████▌   | 7250/11066 [26:32<13:58,  4.55it/s]
                                                    

 66%|██████▌   | 7250/11066 [26:32<13:58,  4.55it/s]
 66%|██████▌   | 7251/11066 [26:33<14:06,  4.51it/s]
                                                    

 66%|██████▌   | 7251/11066 [26:33<14:06,  4.51it/s]
 66%|██████▌   | 7252/11066 [26:33<14:08,  4.50it/s]
                                                    

 66%|██████▌   | 7252/11066 [26:33<14:08,  4.50it/s]
 66%|██████▌   | 7253/11066 [26:33<14:08,  4.50it/s]
                                                    

 66%|██████▌   | 7253/11066 [26:33<14:08,  4.50it/s]
 66%|██████▌   | 7254/11066 [26:33<14:06,  4.50it/s]
                                                    

 66%|██████▌   | 7254/11066 [26:33<14:06,  4.50it/s]
 66%|██████▌   | 7255/11066 [26:33<14:06,  4.50it/s]
                                                    

 66%|██████▌   | 7255/11066 [26:33<14:06,  4.50it/s]
 66%|██████▌   | 7256/11066 [26:34<14:07,  4.50it/s]
                                                    

 66%|██████▌   | 7256/11066 [26:34<14:07,  4.50it/s]
 66%|██████▌   | 7257/11066 [26:34<14:09,  4.49it/s]
                                                    

 66%|██████▌   | 7257/11066 [26:34<14:09,  4.49it/s]
 66%|██████▌   | 7258/11066 [26:34<14:08,  4.49it/s]
                                                    

 66%|██████▌   | 7258/11066 [26:34<14:08,  4.49it/s]
 66%|██████▌   | 7259/11066 [26:34<14:11,  4.47it/s]
                                                    

 66%|██████▌   | 7259/11066 [26:34<14:11,  4.47it/s]
 66%|██████▌   | 7260/11066 [26:35<14:10,  4.47it/s]
                                                    

 66%|██████▌   | 7260/11066 [26:35<14:10,  4.47it/s]
 66%|██████▌   | 7261/11066 [26:35<14:09,  4.48it/s]
                                                    

 66%|██████▌   | 7261/11066 [26:35<14:09,  4.48it/s]
 66%|██████▌   | 7262/11066 [26:35<14:01,  4.52it/s]
                                                    

 66%|██████▌   | 7262/11066 [26:35<14:01,  4.52it/s]
 66%|██████▌   | 7263/11066 [26:35<14:00,  4.53it/s]
                                                    

 66%|██████▌   | 7263/11066 [26:35<14:00,  4.53it/s]
 66%|██████▌   | 7264/11066 [26:35<13:49,  4.58it/s]
                                                    

 66%|██████▌   | 7264/11066 [26:35<13:49,  4.58it/s]
 66%|██████▌   | 7265/11066 [26:36<13:45,  4.60it/s]
                                                    

 66%|██████▌   | 7265/11066 [26:36<13:45,  4.60it/s]
 66%|██████▌   | 7266/11066 [26:36<13:52,  4.57it/s]
                                                    

 66%|██████▌   | 7266/11066 [26:36<13:52,  4.57it/s]
 66%|██████▌   | 7267/11066 [26:36<13:50,  4.57it/s]
                                                    

 66%|██████▌   | 7267/11066 [26:36<13:50,  4.57it/s]
 66%|██████▌   | 7268/11066 [26:36<13:57,  4.54it/s]
                                                    

 66%|██████▌   | 7268/11066 [26:36<13:57,  4.54it/s]
 66%|██████▌   | 7269/11066 [26:37<13:54,  4.55it/s]
                                                    

 66%|██████▌   | 7269/11066 [26:37<13:54,  4.55it/s]
 66%|██████▌   | 7270/11066 [26:37<13:46,  4.59it/s]
                                                    

 66%|██████▌   | 7270/11066 [26:37<13:46,  4.59it/s]
 66%|██████▌   | 7271/11066 [26:37<13:45,  4.60it/s]
                                                    

 66%|██████▌   | 7271/11066 [26:37<13:45,  4.60it/s]
 66%|██████▌   | 7272/11066 [26:37<13:52,  4.56it/s]
                                                    

 66%|██████▌   | 7272/11066 [26:37<13:52,  4.56it/s]
 66%|██████▌   | 7273/11066 [26:37<13:55,  4.54it/s]
                                                    

 66%|██████▌   | 7273/11066 [26:37<13:55,  4.54it/s]
 66%|██████▌   | 7274/11066 [26:38<13:51,  4.56it/s]
                                                    

 66%|██████▌   | 7274/11066 [26:38<13:51,  4.56it/s]
 66%|██████▌   | 7275/11066 [26:38<13:45,  4.59it/s]
                                                    

 66%|██████▌   | 7275/11066 [26:38<13:45,  4.59it/s]
 66%|██████▌   | 7276/11066 [26:38<13:51,  4.56it/s]
                                                    

 66%|██████▌   | 7276/11066 [26:38<13:51,  4.56it/s]
 66%|██████▌   | 7277/11066 [26:38<13:55,  4.54it/s]
                                                    

 66%|██████▌   | 7277/11066 [26:38<13:55,  4.54it/s]
 66%|██████▌   | 7278/11066 [26:39<13:58,  4.52it/s]
                                                    

 66%|██████▌   | 7278/11066 [26:39<13:58,  4.52it/s]
 66%|██████▌   | 7279/11066 [26:39<13:59,  4.51it/s]
                                                    

 66%|██████▌   | 7279/11066 [26:39<13:59,  4.51it/s]
 66%|██████▌   | 7280/11066 [26:39<13:59,  4.51it/s]
                                                    

 66%|██████▌   | 7280/11066 [26:39<13:59,  4.51it/s]
 66%|██████▌   | 7281/11066 [26:39<13:59,  4.51it/s]
                                                    

 66%|██████▌   | 7281/11066 [26:39<13:59,  4.51it/s]
 66%|██████▌   | 7282/11066 [26:39<13:59,  4.51it/s]
                                                    

 66%|██████▌   | 7282/11066 [26:39<13:59,  4.51it/s]
 66%|██████▌   | 7283/11066 [26:40<14:00,  4.50it/s]
                                                    

 66%|██████▌   | 7283/11066 [26:40<14:00,  4.50it/s]
 66%|██████▌   | 7284/11066 [26:40<13:59,  4.50it/s]
                                                    

 66%|██████▌   | 7284/11066 [26:40<13:59,  4.50it/s]
 66%|██████▌   | 7285/11066 [26:40<13:59,  4.50it/s]
                                                    

 66%|██████▌   | 7285/11066 [26:40<13:59,  4.50it/s]
 66%|██████▌   | 7286/11066 [26:40<13:55,  4.53it/s]
                                                    

 66%|██████▌   | 7286/11066 [26:40<13:55,  4.53it/s]
 66%|██████▌   | 7287/11066 [26:41<13:59,  4.50it/s]
                                                    

 66%|██████▌   | 7287/11066 [26:41<13:59,  4.50it/s]
 66%|██████▌   | 7288/11066 [26:41<13:54,  4.53it/s]
                                                    

 66%|██████▌   | 7288/11066 [26:41<13:54,  4.53it/s]
 66%|██████▌   | 7289/11066 [26:41<13:54,  4.53it/s]
                                                    

 66%|██████▌   | 7289/11066 [26:41<13:54,  4.53it/s]
 66%|██████▌   | 7290/11066 [26:41<14:00,  4.49it/s]
                                                    

 66%|██████▌   | 7290/11066 [26:41<14:00,  4.49it/s]
 66%|██████▌   | 7291/11066 [26:41<13:55,  4.52it/s]
                                                    

 66%|██████▌   | 7291/11066 [26:41<13:55,  4.52it/s]
 66%|██████▌   | 7292/11066 [26:42<14:00,  4.49it/s]
                                                    

 66%|██████▌   | 7292/11066 [26:42<14:00,  4.49it/s]
 66%|██████▌   | 7293/11066 [26:42<13:54,  4.52it/s]
                                                    

 66%|██████▌   | 7293/11066 [26:42<13:54,  4.52it/s]
 66%|██████▌   | 7294/11066 [26:42<13:58,  4.50it/s]
                                                    

 66%|██████▌   | 7294/11066 [26:42<13:58,  4.50it/s]
 66%|██████▌   | 7295/11066 [26:42<13:52,  4.53it/s]
                                                    

 66%|██████▌   | 7295/11066 [26:42<13:52,  4.53it/s]
 66%|██████▌   | 7296/11066 [26:42<13:50,  4.54it/s]
                                                    

 66%|██████▌   | 7296/11066 [26:42<13:50,  4.54it/s]
 66%|██████▌   | 7297/11066 [26:43<13:51,  4.53it/s]
                                                    

 66%|██████▌   | 7297/11066 [26:43<13:51,  4.53it/s]
 66%|██████▌   | 7298/11066 [26:43<13:41,  4.59it/s]
                                                    

 66%|██████▌   | 7298/11066 [26:43<13:41,  4.59it/s]
 66%|██████▌   | 7299/11066 [26:43<13:45,  4.56it/s]
                                                    

 66%|██████▌   | 7299/11066 [26:43<13:45,  4.56it/s]
 66%|██████▌   | 7300/11066 [26:43<13:36,  4.61it/s]
                                                    

 66%|██████▌   | 7300/11066 [26:43<13:36,  4.61it/s]
 66%|██████▌   | 7301/11066 [26:44<13:36,  4.61it/s]
                                                    

 66%|██████▌   | 7301/11066 [26:44<13:36,  4.61it/s]
 66%|██████▌   | 7302/11066 [26:44<13:34,  4.62it/s]
                                                    

 66%|██████▌   | 7302/11066 [26:44<13:34,  4.62it/s]
 66%|██████▌   | 7303/11066 [26:44<13:35,  4.61it/s]
                                                    

 66%|██████▌   | 7303/11066 [26:44<13:35,  4.61it/s]
 66%|██████▌   | 7304/11066 [26:44<13:27,  4.66it/s]
                                                    

 66%|██████▌   | 7304/11066 [26:44<13:27,  4.66it/s]
 66%|██████▌   | 7305/11066 [26:44<13:22,  4.69it/s]
                                                    

 66%|██████▌   | 7305/11066 [26:44<13:22,  4.69it/s]
 66%|██████▌   | 7306/11066 [26:45<13:35,  4.61it/s]
                                                    

 66%|██████▌   | 7306/11066 [26:45<13:35,  4.61it/s]
 66%|██████▌   | 7307/11066 [26:45<13:52,  4.52it/s]
                                                    

 66%|██████▌   | 7307/11066 [26:45<13:52,  4.52it/s]
 66%|██████▌   | 7308/11066 [26:45<14:02,  4.46it/s]
                                                    

 66%|██████▌   | 7308/11066 [26:45<14:02,  4.46it/s]
 66%|██████▌   | 7309/11066 [26:45<13:59,  4.47it/s]
                                                    

 66%|██████▌   | 7309/11066 [26:45<13:59,  4.47it/s]
 66%|██████▌   | 7310/11066 [26:46<14:05,  4.44it/s]
                                                    

 66%|██████▌   | 7310/11066 [26:46<14:05,  4.44it/s]
 66%|██████▌   | 7311/11066 [26:46<14:06,  4.44it/s]
                                                    
{'loss': 0.7496, 'learning_rate': 1.0486173865895537e-05, 'epoch': 1.3}
{'loss': 0.5203, 'learning_rate': 1.0483462859208385e-05, 'epoch': 1.3}
{'loss': 0.668, 'learning_rate': 1.0480751852521237e-05, 'epoch': 1.3}
{'loss': 0.7517, 'learning_rate': 1.0478040845834087e-05, 'epoch': 1.3}
{'loss': 0.4458, 'learning_rate': 1.0475329839146937e-05, 'epoch': 1.3}
{'loss': 0.9633, 'learning_rate': 1.0472618832459787e-05, 'epoch': 1.3}
{'loss': 0.9121, 'learning_rate': 1.0469907825772637e-05, 'epoch': 1.3}
{'loss': 0.3104, 'learning_rate': 1.0467196819085488e-05, 'epoch': 1.3}
{'loss': 0.422, 'learning_rate': 1.0464485812398336e-05, 'epoch': 1.3}
{'loss': 0.9605, 'learning_rate': 1.0461774805711188e-05, 'epoch': 1.3}
{'loss': 0.5814, 'learning_rate': 1.0459063799024038e-05, 'epoch': 1.3}
{'loss': 0.4729, 'learning_rate': 1.0456352792336888e-05, 'epoch': 1.3}
{'loss': 0.902, 'learning_rate': 1.0453641785649737e-05, 'epoch': 1.3}
{'loss': 0.975, 'learning_rate': 1.0450930778962588e-05, 'epoch': 1.3}
{'loss': 0.535, 'learning_rate': 1.0448219772275439e-05, 'epoch': 1.3}
{'loss': 1.2676, 'learning_rate': 1.0445508765588289e-05, 'epoch': 1.3}
{'loss': 0.3711, 'learning_rate': 1.0442797758901139e-05, 'epoch': 1.3}
{'loss': 1.6249, 'learning_rate': 1.0440086752213989e-05, 'epoch': 1.3}
{'loss': 0.4161, 'learning_rate': 1.0437375745526839e-05, 'epoch': 1.3}
{'loss': 1.4169, 'learning_rate': 1.043466473883969e-05, 'epoch': 1.3}
{'loss': 1.2506, 'learning_rate': 1.043195373215254e-05, 'epoch': 1.3}
{'loss': 0.5756, 'learning_rate': 1.042924272546539e-05, 'epoch': 1.3}
{'loss': 1.0062, 'learning_rate': 1.042653171877824e-05, 'epoch': 1.3}
{'loss': 1.1382, 'learning_rate': 1.042382071209109e-05, 'epoch': 1.31}
{'loss': 0.8369, 'learning_rate': 1.042110970540394e-05, 'epoch': 1.31}
{'loss': 0.7244, 'learning_rate': 1.041839869871679e-05, 'epoch': 1.31}
{'loss': 1.3378, 'learning_rate': 1.041568769202964e-05, 'epoch': 1.31}
{'loss': 0.7405, 'learning_rate': 1.0412976685342492e-05, 'epoch': 1.31}
{'loss': 0.7756, 'learning_rate': 1.041026567865534e-05, 'epoch': 1.31}
{'loss': 0.8793, 'learning_rate': 1.040755467196819e-05, 'epoch': 1.31}
{'loss': 0.8128, 'learning_rate': 1.040484366528104e-05, 'epoch': 1.31}
{'loss': 0.6797, 'learning_rate': 1.0402132658593892e-05, 'epoch': 1.31}
{'loss': 0.6518, 'learning_rate': 1.0399421651906741e-05, 'epoch': 1.31}
{'loss': 1.3884, 'learning_rate': 1.0396710645219591e-05, 'epoch': 1.31}
{'loss': 0.6175, 'learning_rate': 1.0393999638532443e-05, 'epoch': 1.31}
{'loss': 0.4584, 'learning_rate': 1.0391288631845293e-05, 'epoch': 1.31}
{'loss': 0.8309, 'learning_rate': 1.0388577625158141e-05, 'epoch': 1.31}
{'loss': 0.6802, 'learning_rate': 1.0385866618470992e-05, 'epoch': 1.31}
{'loss': 1.3064, 'learning_rate': 1.0383155611783843e-05, 'epoch': 1.31}
{'loss': 0.6262, 'learning_rate': 1.0380444605096694e-05, 'epoch': 1.31}
{'loss': 0.5949, 'learning_rate': 1.0377733598409542e-05, 'epoch': 1.31}
{'loss': 0.715, 'learning_rate': 1.0375022591722392e-05, 'epoch': 1.31}
{'loss': 1.1859, 'learning_rate': 1.0372311585035244e-05, 'epoch': 1.31}
{'loss': 1.1094, 'learning_rate': 1.0369600578348094e-05, 'epoch': 1.31}
{'loss': 0.8369, 'learning_rate': 1.0366889571660943e-05, 'epoch': 1.31}
{'loss': 0.3584, 'learning_rate': 1.0364178564973794e-05, 'epoch': 1.31}
{'loss': 0.7603, 'learning_rate': 1.0361467558286644e-05, 'epoch': 1.31}
{'loss': 0.4338, 'learning_rate': 1.0358756551599495e-05, 'epoch': 1.31}
{'loss': 1.4111, 'learning_rate': 1.0356045544912343e-05, 'epoch': 1.31}
{'loss': 0.9076, 'learning_rate': 1.0353334538225195e-05, 'epoch': 1.31}
{'loss': 0.4934, 'learning_rate': 1.0350623531538045e-05, 'epoch': 1.31}
{'loss': 0.5025, 'learning_rate': 1.0347912524850895e-05, 'epoch': 1.31}
{'loss': 0.489, 'learning_rate': 1.0345201518163744e-05, 'epoch': 1.31}
{'loss': 0.4028, 'learning_rate': 1.0342490511476595e-05, 'epoch': 1.31}
{'loss': 0.7569, 'learning_rate': 1.0339779504789446e-05, 'epoch': 1.31}
{'loss': 0.5704, 'learning_rate': 1.0337068498102296e-05, 'epoch': 1.31}
{'loss': 0.7647, 'learning_rate': 1.0334357491415146e-05, 'epoch': 1.31}
{'loss': 0.4931, 'learning_rate': 1.0331646484727996e-05, 'epoch': 1.31}
{'loss': 0.3332, 'learning_rate': 1.0328935478040846e-05, 'epoch': 1.31}
{'loss': 0.7672, 'learning_rate': 1.0326224471353696e-05, 'epoch': 1.31}
{'loss': 0.916, 'learning_rate': 1.0323513464666546e-05, 'epoch': 1.31}
{'loss': 0.5823, 'learning_rate': 1.0320802457979397e-05, 'epoch': 1.31}
{'loss': 0.654, 'learning_rate': 1.0318091451292247e-05, 'epoch': 1.31}
{'loss': 0.2991, 'learning_rate': 1.0315380444605097e-05, 'epoch': 1.31}
{'loss': 0.6088, 'learning_rate': 1.0312669437917947e-05, 'epoch': 1.31}
{'loss': 0.3768, 'learning_rate': 1.0309958431230797e-05, 'epoch': 1.31}
{'loss': 0.2819, 'learning_rate': 1.0307247424543647e-05, 'epoch': 1.31}
{'loss': 1.3167, 'learning_rate': 1.0304536417856499e-05, 'epoch': 1.31}
{'loss': 0.4969, 'learning_rate': 1.0301825411169347e-05, 'epoch': 1.31}
{'loss': 1.289, 'learning_rate': 1.0299114404482198e-05, 'epoch': 1.31}
{'loss': 1.3074, 'learning_rate': 1.0296403397795048e-05, 'epoch': 1.31}
{'loss': 1.2198, 'learning_rate': 1.02936923911079e-05, 'epoch': 1.31}
{'loss': 0.4957, 'learning_rate': 1.0290981384420748e-05, 'epoch': 1.31}
{'loss': 0.9931, 'learning_rate': 1.0288270377733598e-05, 'epoch': 1.31}
{'loss': 0.6172, 'learning_rate': 1.0285559371046448e-05, 'epoch': 1.31}
{'loss': 0.4901, 'learning_rate': 1.02828483643593e-05, 'epoch': 1.31}
{'loss': 0.4769, 'learning_rate': 1.0280137357672149e-05, 'epoch': 1.31}
{'loss': 1.1693, 'learning_rate': 1.0277426350984999e-05, 'epoch': 1.31}
{'loss': 0.6612, 'learning_rate': 1.027471534429785e-05, 'epoch': 1.32}
{'loss': 0.7568, 'learning_rate': 1.02720043376107e-05, 'epoch': 1.32}
{'loss': 0.4356, 'learning_rate': 1.0269293330923549e-05, 'epoch': 1.32}
{'loss': 0.8485, 'learning_rate': 1.02665823242364e-05, 'epoch': 1.32}
{'loss': 0.7524, 'learning_rate': 1.0263871317549251e-05, 'epoch': 1.32}
{'loss': 0.6768, 'learning_rate': 1.0261160310862101e-05, 'epoch': 1.32}
{'loss': 0.6888, 'learning_rate': 1.025844930417495e-05, 'epoch': 1.32}
{'loss': 0.8601, 'learning_rate': 1.02557382974878e-05, 'epoch': 1.32}
{'loss': 0.403, 'learning_rate': 1.0253027290800652e-05, 'epoch': 1.32}
{'loss': 0.7395, 'learning_rate': 1.0250316284113502e-05, 'epoch': 1.32}
{'loss': 1.0422, 'learning_rate': 1.024760527742635e-05, 'epoch': 1.32}
{'loss': 0.3811, 'learning_rate': 1.0244894270739202e-05, 'epoch': 1.32}
{'loss': 1.5316, 'learning_rate': 1.0242183264052052e-05, 'epoch': 1.32}
{'loss': 0.7933, 'learning_rate': 1.0239472257364902e-05, 'epoch': 1.32}
{'loss': 0.3903, 'learning_rate': 1.023676125067775e-05, 'epoch': 1.32}
{'loss': 0.8577, 'learning_rate': 1.0234050243990603e-05, 'epoch': 1.32}
{'loss': 0.3097, 'learning_rate': 1.0231339237303453e-05, 'epoch': 1.32}
{'loss': 0.8924, 'learning_rate': 1.0228628230616303e-05, 'epoch': 1.32}
{'loss': 1.1151, 'learning_rate': 1.0225917223929153e-05, 'epoch': 1.32}
{'loss': 0.893, 'learning_rate': 1.0223206217242003e-05, 'epoch': 1.32}
{'loss': 0.9173, 'learning_rate': 1.0220495210554853e-05, 'epoch': 1.32}
{'loss': 0.9617, 'learning_rate': 1.0217784203867703e-05, 'epoch': 1.32}
{'loss': 1.1645, 'learning_rate': 1.0215073197180553e-05, 'epoch': 1.32}
{'loss': 0.6054, 'learning_rate': 1.0212362190493404e-05, 'epoch': 1.32}
{'loss': 0.6049, 'learning_rate': 1.0209651183806254e-05, 'epoch': 1.32}
{'loss': 0.8186, 'learning_rate': 1.0206940177119104e-05, 'epoch': 1.32}
{'loss': 0.7171, 'learning_rate': 1.0204229170431954e-05, 'epoch': 1.32}
{'loss': 0.997, 'learning_rate': 1.0201518163744804e-05, 'epoch': 1.32}
{'loss': 0.5754, 'learning_rate': 1.0198807157057654e-05, 'epoch': 1.32}
{'loss': 0.6729, 'learning_rate': 1.0196096150370506e-05, 'epoch': 1.32}
{'loss': 0.6995, 'learning_rate': 1.0193385143683355e-05, 'epoch': 1.32}
{'loss': 0.4577, 'learning_rate': 1.0190674136996205e-05, 'epoch': 1.32}
{'loss': 0.569, 'learning_rate': 1.0187963130309055e-05, 'epoch': 1.32}
{'loss': 0.7172, 'learning_rate': 1.0185252123621907e-05, 'epoch': 1.32}
{'loss': 0.5611, 'learning_rate': 1.0182541116934755e-05, 'epoch': 1.32}

 66%|██████▌   | 7311/11066 [26:46<14:06,  4.44it/s]
 66%|██████▌   | 7312/11066 [26:46<14:02,  4.46it/s]
                                                    

 66%|██████▌   | 7312/11066 [26:46<14:02,  4.46it/s]
 66%|██████▌   | 7313/11066 [26:46<14:07,  4.43it/s]
                                                    

 66%|██████▌   | 7313/11066 [26:46<14:07,  4.43it/s]
 66%|██████▌   | 7314/11066 [26:46<14:06,  4.43it/s]
                                                    

 66%|██████▌   | 7314/11066 [26:46<14:06,  4.43it/s]
 66%|██████▌   | 7315/11066 [26:47<14:14,  4.39it/s]
                                                    

 66%|██████▌   | 7315/11066 [26:47<14:14,  4.39it/s]
 66%|██████▌   | 7316/11066 [26:47<14:09,  4.42it/s]
                                                    

 66%|██████▌   | 7316/11066 [26:47<14:09,  4.42it/s]
 66%|██████▌   | 7317/11066 [26:47<14:04,  4.44it/s]
                                                    

 66%|██████▌   | 7317/11066 [26:47<14:04,  4.44it/s]
 66%|██████▌   | 7318/11066 [26:47<14:02,  4.45it/s]
                                                    

 66%|██████▌   | 7318/11066 [26:47<14:02,  4.45it/s]
 66%|██████▌   | 7319/11066 [26:48<14:00,  4.46it/s]
                                                    

 66%|██████▌   | 7319/11066 [26:48<14:00,  4.46it/s]
 66%|██████▌   | 7320/11066 [26:48<13:47,  4.53it/s]
                                                    

 66%|██████▌   | 7320/11066 [26:48<13:47,  4.53it/s]
 66%|██████▌   | 7321/11066 [26:48<13:37,  4.58it/s]
                                                    

 66%|██████▌   | 7321/11066 [26:48<13:37,  4.58it/s]
 66%|██████▌   | 7322/11066 [26:48<13:30,  4.62it/s]
                                                    

 66%|██████▌   | 7322/11066 [26:48<13:30,  4.62it/s]
 66%|██████▌   | 7323/11066 [26:48<13:24,  4.65it/s]
                                                    

 66%|██████▌   | 7323/11066 [26:48<13:24,  4.65it/s]
 66%|██████▌   | 7324/11066 [26:49<13:32,  4.61it/s]
                                                    

 66%|██████▌   | 7324/11066 [26:49<13:32,  4.61it/s]
 66%|██████▌   | 7325/11066 [26:49<13:38,  4.57it/s]
                                                    

 66%|██████▌   | 7325/11066 [26:49<13:38,  4.57it/s]
 66%|██████▌   | 7326/11066 [26:49<13:43,  4.54it/s]
                                                    

 66%|██████▌   | 7326/11066 [26:49<13:43,  4.54it/s]
 66%|██████▌   | 7327/11066 [26:49<13:46,  4.53it/s]
                                                    

 66%|██████▌   | 7327/11066 [26:49<13:46,  4.53it/s]
 66%|██████▌   | 7328/11066 [26:50<13:47,  4.52it/s]
                                                    

 66%|██████▌   | 7328/11066 [26:50<13:47,  4.52it/s]
 66%|██████▌   | 7329/11066 [26:50<13:37,  4.57it/s]
                                                    

 66%|██████▌   | 7329/11066 [26:50<13:37,  4.57it/s]
 66%|██████▌   | 7330/11066 [26:50<13:30,  4.61it/s]
                                                    

 66%|██████▌   | 7330/11066 [26:50<13:30,  4.61it/s]
 66%|██████▌   | 7331/11066 [26:50<13:29,  4.61it/s]
                                                    

 66%|██████▌   | 7331/11066 [26:50<13:29,  4.61it/s]
 66%|██████▋   | 7332/11066 [26:50<13:25,  4.63it/s]
                                                    

 66%|██████▋   | 7332/11066 [26:50<13:25,  4.63it/s]
 66%|██████▋   | 7333/11066 [26:51<13:36,  4.57it/s]
                                                    

 66%|██████▋   | 7333/11066 [26:51<13:36,  4.57it/s]
 66%|██████▋   | 7334/11066 [26:51<13:35,  4.57it/s]
                                                    

 66%|██████▋   | 7334/11066 [26:51<13:35,  4.57it/s]
 66%|██████▋   | 7335/11066 [26:51<13:43,  4.53it/s]
                                                    

 66%|██████▋   | 7335/11066 [26:51<13:43,  4.53it/s]
 66%|██████▋   | 7336/11066 [26:51<13:47,  4.51it/s]
                                                    

 66%|██████▋   | 7336/11066 [26:51<13:47,  4.51it/s]
 66%|██████▋   | 7337/11066 [26:52<13:42,  4.53it/s]
                                                    

 66%|██████▋   | 7337/11066 [26:52<13:42,  4.53it/s]
 66%|██████▋   | 7338/11066 [26:52<13:33,  4.58it/s]
                                                    

 66%|██████▋   | 7338/11066 [26:52<13:33,  4.58it/s]
 66%|██████▋   | 7339/11066 [26:52<13:27,  4.62it/s]
                                                    

 66%|██████▋   | 7339/11066 [26:52<13:27,  4.62it/s]
 66%|██████▋   | 7340/11066 [26:52<13:19,  4.66it/s]
                                                    

 66%|██████▋   | 7340/11066 [26:52<13:19,  4.66it/s]
 66%|██████▋   | 7341/11066 [26:52<13:13,  4.69it/s]
                                                    

 66%|██████▋   | 7341/11066 [26:52<13:13,  4.69it/s]
 66%|██████▋   | 7342/11066 [26:53<13:18,  4.66it/s]
                                                    

 66%|██████▋   | 7342/11066 [26:53<13:18,  4.66it/s]
 66%|██████▋   | 7343/11066 [26:53<13:14,  4.68it/s]
                                                    

 66%|██████▋   | 7343/11066 [26:53<13:14,  4.68it/s]
 66%|██████▋   | 7344/11066 [26:53<13:14,  4.69it/s]
                                                    

 66%|██████▋   | 7344/11066 [26:53<13:14,  4.69it/s]
 66%|██████▋   | 7345/11066 [26:53<13:15,  4.68it/s]
                                                    

 66%|██████▋   | 7345/11066 [26:53<13:15,  4.68it/s]
 66%|██████▋   | 7346/11066 [26:53<13:19,  4.65it/s]
                                                    

 66%|██████▋   | 7346/11066 [26:53<13:19,  4.65it/s]
 66%|██████▋   | 7347/11066 [26:54<13:22,  4.63it/s]
                                                    

 66%|██████▋   | 7347/11066 [26:54<13:22,  4.63it/s]
 66%|██████▋   | 7348/11066 [26:54<13:19,  4.65it/s]
                                                    

 66%|██████▋   | 7348/11066 [26:54<13:19,  4.65it/s]
 66%|██████▋   | 7349/11066 [26:54<13:17,  4.66it/s]
                                                    

 66%|██████▋   | 7349/11066 [26:54<13:17,  4.66it/s]
 66%|██████▋   | 7350/11066 [26:54<13:14,  4.68it/s]
                                                    

 66%|██████▋   | 7350/11066 [26:54<13:14,  4.68it/s]
 66%|██████▋   | 7351/11066 [26:55<13:12,  4.69it/s]
                                                    

 66%|██████▋   | 7351/11066 [26:55<13:12,  4.69it/s]
 66%|██████▋   | 7352/11066 [26:55<13:21,  4.63it/s]
                                                    

 66%|██████▋   | 7352/11066 [26:55<13:21,  4.63it/s]
 66%|██████▋   | 7353/11066 [26:55<13:17,  4.65it/s]
                                                    

 66%|██████▋   | 7353/11066 [26:55<13:17,  4.65it/s]
 66%|██████▋   | 7354/11066 [26:55<13:14,  4.67it/s]
                                                    

 66%|██████▋   | 7354/11066 [26:55<13:14,  4.67it/s]
 66%|██████▋   | 7355/11066 [26:55<13:13,  4.68it/s]
                                                    

 66%|██████▋   | 7355/11066 [26:55<13:13,  4.68it/s]
 66%|██████▋   | 7356/11066 [26:56<13:16,  4.66it/s]
                                                    

 66%|██████▋   | 7356/11066 [26:56<13:16,  4.66it/s]
 66%|██████▋   | 7357/11066 [26:56<13:11,  4.68it/s]
                                                    

 66%|██████▋   | 7357/11066 [26:56<13:11,  4.68it/s]
 66%|██████▋   | 7358/11066 [26:56<13:06,  4.71it/s]
                                                    

 66%|██████▋   | 7358/11066 [26:56<13:06,  4.71it/s]
 67%|██████▋   | 7359/11066 [26:56<13:11,  4.68it/s]
                                                    

 67%|██████▋   | 7359/11066 [26:56<13:11,  4.68it/s]
 67%|██████▋   | 7360/11066 [26:56<13:07,  4.71it/s]
                                                    

 67%|██████▋   | 7360/11066 [26:56<13:07,  4.71it/s]
 67%|██████▋   | 7361/11066 [26:57<13:19,  4.64it/s]
                                                    

 67%|██████▋   | 7361/11066 [26:57<13:19,  4.64it/s]
 67%|██████▋   | 7362/11066 [26:57<13:28,  4.58it/s]
                                                    

 67%|██████▋   | 7362/11066 [26:57<13:28,  4.58it/s]
 67%|██████▋   | 7363/11066 [26:57<13:36,  4.53it/s]
                                                    

 67%|██████▋   | 7363/11066 [26:57<13:36,  4.53it/s]
 67%|██████▋   | 7364/11066 [26:57<13:39,  4.52it/s]
                                                    

 67%|██████▋   | 7364/11066 [26:57<13:39,  4.52it/s]
 67%|██████▋   | 7365/11066 [26:58<13:40,  4.51it/s]
                                                    

 67%|██████▋   | 7365/11066 [26:58<13:40,  4.51it/s]
 67%|██████▋   | 7366/11066 [26:58<13:42,  4.50it/s]
                                                    

 67%|██████▋   | 7366/11066 [26:58<13:42,  4.50it/s]
 67%|██████▋   | 7367/11066 [26:58<13:46,  4.47it/s]
                                                    

 67%|██████▋   | 7367/11066 [26:58<13:46,  4.47it/s]
 67%|██████▋   | 7368/11066 [26:58<13:54,  4.43it/s]
                                                    

 67%|██████▋   | 7368/11066 [26:58<13:54,  4.43it/s]
 67%|██████▋   | 7369/11066 [26:58<13:52,  4.44it/s]
                                                    

 67%|██████▋   | 7369/11066 [26:58<13:52,  4.44it/s]
 67%|██████▋   | 7370/11066 [26:59<13:55,  4.43it/s]
                                                    

 67%|██████▋   | 7370/11066 [26:59<13:55,  4.43it/s]
 67%|██████▋   | 7371/11066 [26:59<13:52,  4.44it/s]
                                                    

 67%|██████▋   | 7371/11066 [26:59<13:52,  4.44it/s]
 67%|██████▋   | 7372/11066 [26:59<13:51,  4.44it/s]
                                                    

 67%|██████▋   | 7372/11066 [26:59<13:51,  4.44it/s]
 67%|██████▋   | 7373/11066 [26:59<13:56,  4.42it/s]
                                                    

 67%|██████▋   | 7373/11066 [26:59<13:56,  4.42it/s]
 67%|██████▋   | 7374/11066 [27:00<13:52,  4.44it/s]
                                                    

 67%|██████▋   | 7374/11066 [27:00<13:52,  4.44it/s]
 67%|██████▋   | 7375/11066 [27:00<13:49,  4.45it/s]
                                                    

 67%|██████▋   | 7375/11066 [27:00<13:49,  4.45it/s]
 67%|██████▋   | 7376/11066 [27:00<13:33,  4.54it/s]
                                                    

 67%|██████▋   | 7376/11066 [27:00<13:33,  4.54it/s]
 67%|██████▋   | 7377/11066 [27:00<13:29,  4.56it/s]
                                                    

 67%|██████▋   | 7377/11066 [27:00<13:29,  4.56it/s]
 67%|██████▋   | 7378/11066 [27:00<13:38,  4.51it/s]
                                                    

 67%|██████▋   | 7378/11066 [27:00<13:38,  4.51it/s]
 67%|██████▋   | 7379/11066 [27:01<13:34,  4.53it/s]
                                                    

 67%|██████▋   | 7379/11066 [27:01<13:34,  4.53it/s]
 67%|██████▋   | 7380/11066 [27:01<13:20,  4.60it/s]
                                                    

 67%|██████▋   | 7380/11066 [27:01<13:20,  4.60it/s]
 67%|██████▋   | 7381/11066 [27:01<13:16,  4.63it/s]
                                                    

 67%|██████▋   | 7381/11066 [27:01<13:16,  4.63it/s]
 67%|██████▋   | 7382/11066 [27:01<13:12,  4.65it/s]
                                                    

 67%|██████▋   | 7382/11066 [27:01<13:12,  4.65it/s]
 67%|██████▋   | 7383/11066 [27:02<13:08,  4.67it/s]
                                                    

 67%|██████▋   | 7383/11066 [27:02<13:08,  4.67it/s]
 67%|██████▋   | 7384/11066 [27:02<13:17,  4.61it/s]
                                                    

 67%|██████▋   | 7384/11066 [27:02<13:17,  4.61it/s]
 67%|██████▋   | 7385/11066 [27:02<13:12,  4.65it/s]
                                                    

 67%|██████▋   | 7385/11066 [27:02<13:12,  4.65it/s]
 67%|██████▋   | 7386/11066 [27:02<13:13,  4.64it/s]
                                                    

 67%|██████▋   | 7386/11066 [27:02<13:13,  4.64it/s]
 67%|██████▋   | 7387/11066 [27:02<13:06,  4.67it/s]
                                                    

 67%|██████▋   | 7387/11066 [27:02<13:06,  4.67it/s]
 67%|██████▋   | 7388/11066 [27:03<13:05,  4.68it/s]
                                                    

 67%|██████▋   | 7388/11066 [27:03<13:05,  4.68it/s]
 67%|██████▋   | 7389/11066 [27:03<13:17,  4.61it/s]
                                                    

 67%|██████▋   | 7389/11066 [27:03<13:17,  4.61it/s]
 67%|██████▋   | 7390/11066 [27:03<13:40,  4.48it/s]
                                                    

 67%|██████▋   | 7390/11066 [27:03<13:40,  4.48it/s]
 67%|██████▋   | 7391/11066 [27:03<13:40,  4.48it/s]
                                                    

 67%|██████▋   | 7391/11066 [27:03<13:40,  4.48it/s]
 67%|██████▋   | 7392/11066 [27:04<13:55,  4.40it/s]
                                                    

 67%|██████▋   | 7392/11066 [27:04<13:55,  4.40it/s]
 67%|██████▋   | 7393/11066 [27:04<13:51,  4.42it/s]
                                                    

 67%|██████▋   | 7393/11066 [27:04<13:51,  4.42it/s]
 67%|██████▋   | 7394/11066 [27:04<13:48,  4.43it/s]
                                                    

 67%|██████▋   | 7394/11066 [27:04<13:48,  4.43it/s]
 67%|██████▋   | 7395/11066 [27:04<13:45,  4.45it/s]
                                                    

 67%|██████▋   | 7395/11066 [27:04<13:45,  4.45it/s]
 67%|██████▋   | 7396/11066 [27:04<13:42,  4.46it/s]
                                                    

 67%|██████▋   | 7396/11066 [27:04<13:42,  4.46it/s]
 67%|██████▋   | 7397/11066 [27:05<13:39,  4.48it/s]
                                                    

 67%|██████▋   | 7397/11066 [27:05<13:39,  4.48it/s]
 67%|██████▋   | 7398/11066 [27:05<13:38,  4.48it/s]
                                                    

 67%|██████▋   | 7398/11066 [27:05<13:38,  4.48it/s]
 67%|██████▋   | 7399/11066 [27:05<13:38,  4.48it/s]
                                                    

 67%|██████▋   | 7399/11066 [27:05<13:38,  4.48it/s]
 67%|██████▋   | 7400/11066 [27:05<13:37,  4.48it/s]
                                                    

 67%|██████▋   | 7400/11066 [27:05<13:37,  4.48it/s]
 67%|██████▋   | 7401/11066 [27:06<13:37,  4.48it/s]
                                                    

 67%|██████▋   | 7401/11066 [27:06<13:37,  4.48it/s]
 67%|██████▋   | 7402/11066 [27:06<13:38,  4.48it/s]
                                                    

 67%|██████▋   | 7402/11066 [27:06<13:38,  4.48it/s]
 67%|██████▋   | 7403/11066 [27:06<13:31,  4.52it/s]
                                                    

 67%|██████▋   | 7403/11066 [27:06<13:31,  4.52it/s]
 67%|██████▋   | 7404/11066 [27:06<13:19,  4.58it/s]
                                                    

 67%|██████▋   | 7404/11066 [27:06<13:19,  4.58it/s]
 67%|██████▋   | 7405/11066 [27:06<13:12,  4.62it/s]
                                                    

 67%|██████▋   | 7405/11066 [27:06<13:12,  4.62it/s]
 67%|██████▋   | 7406/11066 [27:07<13:06,  4.65it/s]
                                                    

 67%|██████▋   | 7406/11066 [27:07<13:06,  4.65it/s]
 67%|██████▋   | 7407/11066 [27:07<13:08,  4.64it/s]
                                                    

 67%|██████▋   | 7407/11066 [27:07<13:08,  4.64it/s]
 67%|██████▋   | 7408/11066 [27:07<13:04,  4.66it/s]
                                                    

 67%|██████▋   | 7408/11066 [27:07<13:04,  4.66it/s]
 67%|██████▋   | 7409/11066 [27:07<13:28,  4.53it/s]
                                                    

 67%|██████▋   | 7409/11066 [27:07<13:28,  4.53it/s]
 67%|██████▋   | 7410/11066 [27:08<13:41,  4.45it/s]
                                                    

 67%|██████▋   | 7410/11066 [27:08<13:41,  4.45it/s]
 67%|██████▋   | 7411/11066 [27:08<13:34,  4.49it/s]
                                                    

 67%|██████▋   | 7411/11066 [27:08<13:34,  4.49it/s]
 67%|██████▋   | 7412/11066 [27:08<13:34,  4.49it/s]
                                                    

 67%|██████▋   | 7412/11066 [27:08<13:34,  4.49it/s]
 67%|██████▋   | 7413/11066 [27:08<13:34,  4.49it/s]
                                                    

 67%|██████▋   | 7413/11066 [27:08<13:34,  4.49it/s]
 67%|██████▋   | 7414/11066 [27:08<13:33,  4.49it/s]
                                                    

 67%|██████▋   | 7414/11066 [27:08<13:33,  4.49it/s]
 67%|██████▋   | 7415/11066 [27:09<13:33,  4.49it/s]
                                                    

 67%|██████▋   | 7415/11066 [27:09<13:33,  4.49it/s]
 67%|██████▋   | 7416/11066 [27:09<13:33,  4.49it/s]
                                                    

 67%|██████▋   | 7416/11066 [27:09<13:33,  4.49it/s]
 67%|██████▋   | 7417/11066 [27:09<13:32,  4.49it/s]
                                                    

 67%|██████▋   | 7417/11066 [27:09<13:32,  4.49it/s]
 67%|██████▋   | 7418/11066 [27:09<13:32,  4.49it/s]
                                                    

 67%|██████▋   | 7418/11066 [27:09<13:32,  4.49it/s]
 67%|██████▋   | 7419/11066 [27:10<13:32,  4.49it/s]
                                                    

 67%|██████▋   | 7419/11066 [27:10<13:32,  4.49it/s]
 67%|██████▋   | 7420/11066 [27:10<13:32,  4.49it/s]
                                                    

 67%|██████▋   | 7420/11066 [27:10<13:32,  4.49it/s]
 67%|██████▋   | 7421/11066 [27:10<13:32,  4.49it/s]
                                                    

 67%|██████▋   | 7421/11066 [27:10<13:32,  4.49it/s]
 67%|██████▋   | 7422/11066 [27:10<13:31,  4.49it/s]
                                                    

 67%|██████▋   | 7422/11066 [27:10<13:31,  4.49it/s]
 67%|██████▋   | 7423/11066 [27:10<13:31,  4.49it/s]
                                                    

 67%|██████▋   | 7423/11066 [27:10<13:31,  4.49it/s]
 67%|██████▋   | 7424/11066 [27:11<13:31,  4.49it/s]
                                                    
{'loss': 0.8308, 'learning_rate': 1.0179830110247605e-05, 'epoch': 1.32}
{'loss': 0.9325, 'learning_rate': 1.0177119103560455e-05, 'epoch': 1.32}
{'loss': 0.8739, 'learning_rate': 1.0174408096873307e-05, 'epoch': 1.32}
{'loss': 0.5199, 'learning_rate': 1.0171697090186156e-05, 'epoch': 1.32}
{'loss': 0.8739, 'learning_rate': 1.0168986083499006e-05, 'epoch': 1.32}
{'loss': 0.8731, 'learning_rate': 1.0166275076811858e-05, 'epoch': 1.32}
{'loss': 0.7899, 'learning_rate': 1.0163564070124708e-05, 'epoch': 1.32}
{'loss': 0.4418, 'learning_rate': 1.0160853063437556e-05, 'epoch': 1.32}
{'loss': 1.1247, 'learning_rate': 1.0158142056750406e-05, 'epoch': 1.32}
{'loss': 0.8157, 'learning_rate': 1.0155431050063258e-05, 'epoch': 1.32}
{'loss': 0.7374, 'learning_rate': 1.0152720043376108e-05, 'epoch': 1.32}
{'loss': 0.5971, 'learning_rate': 1.0150009036688957e-05, 'epoch': 1.32}
{'loss': 0.421, 'learning_rate': 1.0147298030001807e-05, 'epoch': 1.32}
{'loss': 1.0179, 'learning_rate': 1.0144587023314659e-05, 'epoch': 1.32}
{'loss': 0.2138, 'learning_rate': 1.0141876016627509e-05, 'epoch': 1.32}
{'loss': 0.596, 'learning_rate': 1.0139165009940357e-05, 'epoch': 1.32}
{'loss': 0.521, 'learning_rate': 1.0136454003253209e-05, 'epoch': 1.32}
{'loss': 0.8187, 'learning_rate': 1.013374299656606e-05, 'epoch': 1.32}
{'loss': 1.1435, 'learning_rate': 1.013103198987891e-05, 'epoch': 1.32}
{'loss': 0.5564, 'learning_rate': 1.0128320983191758e-05, 'epoch': 1.32}
{'loss': 0.9373, 'learning_rate': 1.012560997650461e-05, 'epoch': 1.32}
{'loss': 0.5774, 'learning_rate': 1.012289896981746e-05, 'epoch': 1.33}
{'loss': 1.6148, 'learning_rate': 1.012018796313031e-05, 'epoch': 1.33}
{'loss': 1.063, 'learning_rate': 1.0117476956443158e-05, 'epoch': 1.33}
{'loss': 0.5739, 'learning_rate': 1.011476594975601e-05, 'epoch': 1.33}
{'loss': 0.6914, 'learning_rate': 1.011205494306886e-05, 'epoch': 1.33}
{'loss': 1.2101, 'learning_rate': 1.0109343936381709e-05, 'epoch': 1.33}
{'loss': 0.8411, 'learning_rate': 1.010663292969456e-05, 'epoch': 1.33}
{'loss': 0.474, 'learning_rate': 1.010392192300741e-05, 'epoch': 1.33}
{'loss': 0.9923, 'learning_rate': 1.010121091632026e-05, 'epoch': 1.33}
{'loss': 0.5416, 'learning_rate': 1.009849990963311e-05, 'epoch': 1.33}
{'loss': 1.1217, 'learning_rate': 1.0095788902945961e-05, 'epoch': 1.33}
{'loss': 1.1523, 'learning_rate': 1.0093077896258811e-05, 'epoch': 1.33}
{'loss': 0.2338, 'learning_rate': 1.0090366889571661e-05, 'epoch': 1.33}
{'loss': 0.822, 'learning_rate': 1.008765588288451e-05, 'epoch': 1.33}
{'loss': 0.6711, 'learning_rate': 1.0084944876197362e-05, 'epoch': 1.33}
{'loss': 1.211, 'learning_rate': 1.0082233869510212e-05, 'epoch': 1.33}
{'loss': 1.115, 'learning_rate': 1.0079522862823062e-05, 'epoch': 1.33}
{'loss': 0.636, 'learning_rate': 1.0076811856135912e-05, 'epoch': 1.33}
{'loss': 0.5756, 'learning_rate': 1.0074100849448762e-05, 'epoch': 1.33}
{'loss': 0.5914, 'learning_rate': 1.0071389842761612e-05, 'epoch': 1.33}
{'loss': 0.9724, 'learning_rate': 1.0068678836074462e-05, 'epoch': 1.33}
{'loss': 1.0997, 'learning_rate': 1.0065967829387313e-05, 'epoch': 1.33}
{'loss': 0.6568, 'learning_rate': 1.0063256822700163e-05, 'epoch': 1.33}
{'loss': 0.8923, 'learning_rate': 1.0060545816013013e-05, 'epoch': 1.33}
{'loss': 0.9068, 'learning_rate': 1.0057834809325863e-05, 'epoch': 1.33}
{'loss': 0.735, 'learning_rate': 1.0055123802638713e-05, 'epoch': 1.33}
{'loss': 0.9011, 'learning_rate': 1.0052412795951563e-05, 'epoch': 1.33}
{'loss': 0.7454, 'learning_rate': 1.0049701789264413e-05, 'epoch': 1.33}
{'loss': 0.9642, 'learning_rate': 1.0046990782577265e-05, 'epoch': 1.33}
{'loss': 1.0498, 'learning_rate': 1.0044279775890114e-05, 'epoch': 1.33}
{'loss': 0.9302, 'learning_rate': 1.0041568769202964e-05, 'epoch': 1.33}
{'loss': 0.8513, 'learning_rate': 1.0038857762515814e-05, 'epoch': 1.33}
{'loss': 1.8154, 'learning_rate': 1.0036146755828666e-05, 'epoch': 1.33}
{'loss': 0.6327, 'learning_rate': 1.0033435749141514e-05, 'epoch': 1.33}
{'loss': 0.4356, 'learning_rate': 1.0030724742454364e-05, 'epoch': 1.33}
{'loss': 0.6875, 'learning_rate': 1.0028013735767216e-05, 'epoch': 1.33}
{'loss': 0.747, 'learning_rate': 1.0025302729080066e-05, 'epoch': 1.33}
{'loss': 0.6727, 'learning_rate': 1.0022591722392915e-05, 'epoch': 1.33}
{'loss': 0.7854, 'learning_rate': 1.0019880715705765e-05, 'epoch': 1.33}
{'loss': 0.5905, 'learning_rate': 1.0017169709018617e-05, 'epoch': 1.33}
{'loss': 0.4973, 'learning_rate': 1.0014458702331467e-05, 'epoch': 1.33}
{'loss': 0.7463, 'learning_rate': 1.0011747695644315e-05, 'epoch': 1.33}
{'loss': 0.5761, 'learning_rate': 1.0009036688957165e-05, 'epoch': 1.33}
{'loss': 0.2975, 'learning_rate': 1.0006325682270017e-05, 'epoch': 1.33}
{'loss': 0.4248, 'learning_rate': 1.0003614675582867e-05, 'epoch': 1.33}
{'loss': 0.6652, 'learning_rate': 1.0000903668895716e-05, 'epoch': 1.33}
{'loss': 0.7463, 'learning_rate': 9.998192662208568e-06, 'epoch': 1.33}
{'loss': 1.0752, 'learning_rate': 9.995481655521418e-06, 'epoch': 1.33}
{'loss': 1.4347, 'learning_rate': 9.992770648834268e-06, 'epoch': 1.33}
{'loss': 0.7374, 'learning_rate': 9.990059642147116e-06, 'epoch': 1.33}
{'loss': 0.8555, 'learning_rate': 9.987348635459968e-06, 'epoch': 1.33}
{'loss': 0.8902, 'learning_rate': 9.984637628772818e-06, 'epoch': 1.33}
{'loss': 0.4673, 'learning_rate': 9.981926622085668e-06, 'epoch': 1.33}
{'loss': 0.7997, 'learning_rate': 9.979215615398517e-06, 'epoch': 1.33}
{'loss': 0.2471, 'learning_rate': 9.976504608711369e-06, 'epoch': 1.33}
{'loss': 0.4077, 'learning_rate': 9.973793602024219e-06, 'epoch': 1.34}
{'loss': 0.6114, 'learning_rate': 9.971082595337069e-06, 'epoch': 1.34}
{'loss': 0.7286, 'learning_rate': 9.968371588649919e-06, 'epoch': 1.34}
{'loss': 0.4368, 'learning_rate': 9.96566058196277e-06, 'epoch': 1.34}
{'loss': 0.8838, 'learning_rate': 9.96294957527562e-06, 'epoch': 1.34}
{'loss': 0.4206, 'learning_rate': 9.96023856858847e-06, 'epoch': 1.34}
{'loss': 0.5621, 'learning_rate': 9.95752756190132e-06, 'epoch': 1.34}
{'loss': 0.5712, 'learning_rate': 9.95481655521417e-06, 'epoch': 1.34}
{'loss': 0.2881, 'learning_rate': 9.95210554852702e-06, 'epoch': 1.34}
{'loss': 0.8783, 'learning_rate': 9.94939454183987e-06, 'epoch': 1.34}
{'loss': 0.9139, 'learning_rate': 9.94668353515272e-06, 'epoch': 1.34}
{'loss': 0.8623, 'learning_rate': 9.94397252846557e-06, 'epoch': 1.34}
{'loss': 0.478, 'learning_rate': 9.94126152177842e-06, 'epoch': 1.34}
{'loss': 1.453, 'learning_rate': 9.938550515091272e-06, 'epoch': 1.34}
{'loss': 0.458, 'learning_rate': 9.93583950840412e-06, 'epoch': 1.34}
{'loss': 1.082, 'learning_rate': 9.93312850171697e-06, 'epoch': 1.34}
{'loss': 0.739, 'learning_rate': 9.930417495029821e-06, 'epoch': 1.34}
{'loss': 0.3713, 'learning_rate': 9.927706488342673e-06, 'epoch': 1.34}
{'loss': 0.4289, 'learning_rate': 9.924995481655521e-06, 'epoch': 1.34}
{'loss': 0.5732, 'learning_rate': 9.922284474968371e-06, 'epoch': 1.34}
{'loss': 0.5232, 'learning_rate': 9.919573468281221e-06, 'epoch': 1.34}
{'loss': 0.4859, 'learning_rate': 9.916862461594073e-06, 'epoch': 1.34}
{'loss': 1.0036, 'learning_rate': 9.914151454906922e-06, 'epoch': 1.34}
{'loss': 0.4063, 'learning_rate': 9.911440448219772e-06, 'epoch': 1.34}
{'loss': 1.1261, 'learning_rate': 9.908729441532624e-06, 'epoch': 1.34}
{'loss': 0.7025, 'learning_rate': 9.906018434845474e-06, 'epoch': 1.34}
{'loss': 0.9827, 'learning_rate': 9.903307428158322e-06, 'epoch': 1.34}
{'loss': 0.6172, 'learning_rate': 9.900596421471172e-06, 'epoch': 1.34}
{'loss': 0.5881, 'learning_rate': 9.897885414784024e-06, 'epoch': 1.34}
{'loss': 0.5181, 'learning_rate': 9.895174408096874e-06, 'epoch': 1.34}
{'loss': 0.3689, 'learning_rate': 9.892463401409723e-06, 'epoch': 1.34}
{'loss': 1.5051, 'learning_rate': 9.889752394722573e-06, 'epoch': 1.34}
{'loss': 0.6273, 'learning_rate': 9.887041388035425e-06, 'epoch': 1.34}
{'loss': 0.9165, 'learning_rate': 9.884330381348275e-06, 'epoch': 1.34}
{'loss': 0.4755, 'learning_rate': 9.881619374661123e-06, 'epoch': 1.34}
{'loss': 0.4918, 'learning_rate': 9.878908367973975e-06, 'epoch': 1.34}
{'loss': 1.0813, 'learning_rate': 9.876197361286825e-06, 'epoch': 1.34}

 67%|██████▋   | 7424/11066 [27:11<13:31,  4.49it/s]
 67%|██████▋   | 7425/11066 [27:11<13:31,  4.49it/s]
                                                    

 67%|██████▋   | 7425/11066 [27:11<13:31,  4.49it/s]
 67%|██████▋   | 7426/11066 [27:11<13:30,  4.49it/s]
                                                    

 67%|██████▋   | 7426/11066 [27:11<13:30,  4.49it/s]
 67%|██████▋   | 7427/11066 [27:11<13:30,  4.49it/s]
                                                    

 67%|██████▋   | 7427/11066 [27:11<13:30,  4.49it/s]
 67%|██████▋   | 7428/11066 [27:12<13:30,  4.49it/s]
                                                    

 67%|██████▋   | 7428/11066 [27:12<13:30,  4.49it/s]
 67%|██████▋   | 7429/11066 [27:12<13:30,  4.49it/s]
                                                    

 67%|██████▋   | 7429/11066 [27:12<13:30,  4.49it/s]
 67%|██████▋   | 7430/11066 [27:12<13:30,  4.49it/s]
                                                    

 67%|██████▋   | 7430/11066 [27:12<13:30,  4.49it/s]
 67%|██████▋   | 7431/11066 [27:12<13:18,  4.55it/s]
                                                    

 67%|██████▋   | 7431/11066 [27:12<13:18,  4.55it/s]
 67%|██████▋   | 7432/11066 [27:12<13:09,  4.60it/s]
                                                    

 67%|██████▋   | 7432/11066 [27:12<13:09,  4.60it/s]
 67%|██████▋   | 7433/11066 [27:13<13:11,  4.59it/s]
                                                    

 67%|██████▋   | 7433/11066 [27:13<13:11,  4.59it/s]
 67%|██████▋   | 7434/11066 [27:13<13:05,  4.62it/s]
                                                    

 67%|██████▋   | 7434/11066 [27:13<13:05,  4.62it/s]
 67%|██████▋   | 7435/11066 [27:13<13:07,  4.61it/s]
                                                    

 67%|██████▋   | 7435/11066 [27:13<13:07,  4.61it/s]
 67%|██████▋   | 7436/11066 [27:13<12:59,  4.66it/s]
                                                    

 67%|██████▋   | 7436/11066 [27:13<12:59,  4.66it/s]
 67%|██████▋   | 7437/11066 [27:13<12:57,  4.67it/s]
                                                    

 67%|██████▋   | 7437/11066 [27:13<12:57,  4.67it/s]
 67%|██████▋   | 7438/11066 [27:14<12:59,  4.65it/s]
                                                    

 67%|██████▋   | 7438/11066 [27:14<12:59,  4.65it/s]
 67%|██████▋   | 7439/11066 [27:14<12:52,  4.69it/s]
                                                    

 67%|██████▋   | 7439/11066 [27:14<12:52,  4.69it/s]
 67%|██████▋   | 7440/11066 [27:14<12:53,  4.69it/s]
                                                    

 67%|██████▋   | 7440/11066 [27:14<12:53,  4.69it/s]
 67%|██████▋   | 7441/11066 [27:14<12:52,  4.69it/s]
                                                    

 67%|██████▋   | 7441/11066 [27:14<12:52,  4.69it/s]
 67%|██████▋   | 7442/11066 [27:15<12:50,  4.70it/s]
                                                    

 67%|██████▋   | 7442/11066 [27:15<12:50,  4.70it/s]
 67%|██████▋   | 7443/11066 [27:15<13:02,  4.63it/s]
                                                    

 67%|██████▋   | 7443/11066 [27:15<13:02,  4.63it/s]
 67%|██████▋   | 7444/11066 [27:15<12:58,  4.65it/s]
                                                    

 67%|██████▋   | 7444/11066 [27:15<12:58,  4.65it/s]
 67%|██████▋   | 7445/11066 [27:15<12:56,  4.67it/s]
                                                    

 67%|██████▋   | 7445/11066 [27:15<12:56,  4.67it/s]
 67%|██████▋   | 7446/11066 [27:15<12:53,  4.68it/s]
                                                    

 67%|██████▋   | 7446/11066 [27:15<12:53,  4.68it/s]
 67%|██████▋   | 7447/11066 [27:16<13:03,  4.62it/s]
                                                    

 67%|██████▋   | 7447/11066 [27:16<13:03,  4.62it/s]
 67%|██████▋   | 7448/11066 [27:16<13:03,  4.62it/s]
                                                    

 67%|██████▋   | 7448/11066 [27:16<13:03,  4.62it/s]
 67%|██████▋   | 7449/11066 [27:16<12:56,  4.66it/s]
                                                    

 67%|██████▋   | 7449/11066 [27:16<12:56,  4.66it/s]
 67%|██████▋   | 7450/11066 [27:16<12:50,  4.69it/s]
                                                    

 67%|██████▋   | 7450/11066 [27:16<12:50,  4.69it/s]
 67%|██████▋   | 7451/11066 [27:16<12:54,  4.67it/s]
                                                    

 67%|██████▋   | 7451/11066 [27:16<12:54,  4.67it/s]
 67%|██████▋   | 7452/11066 [27:17<12:49,  4.70it/s]
                                                    

 67%|██████▋   | 7452/11066 [27:17<12:49,  4.70it/s]
 67%|██████▋   | 7453/11066 [27:17<12:59,  4.64it/s]
                                                    

 67%|██████▋   | 7453/11066 [27:17<12:59,  4.64it/s]
 67%|██████▋   | 7454/11066 [27:17<13:05,  4.60it/s]
                                                    

 67%|██████▋   | 7454/11066 [27:17<13:05,  4.60it/s]
 67%|██████▋   | 7455/11066 [27:17<13:09,  4.57it/s]
                                                    

 67%|██████▋   | 7455/11066 [27:17<13:09,  4.57it/s]
 67%|██████▋   | 7456/11066 [27:18<13:07,  4.58it/s]
                                                    

 67%|██████▋   | 7456/11066 [27:18<13:07,  4.58it/s]
 67%|██████▋   | 7457/11066 [27:18<13:14,  4.54it/s]
                                                    

 67%|██████▋   | 7457/11066 [27:18<13:14,  4.54it/s]
 67%|██████▋   | 7458/11066 [27:18<13:19,  4.51it/s]
                                                    

 67%|██████▋   | 7458/11066 [27:18<13:19,  4.51it/s]
 67%|██████▋   | 7459/11066 [27:18<13:21,  4.50it/s]
                                                    

 67%|██████▋   | 7459/11066 [27:18<13:21,  4.50it/s]
 67%|██████▋   | 7460/11066 [27:18<13:10,  4.56it/s]
                                                    

 67%|██████▋   | 7460/11066 [27:18<13:10,  4.56it/s]
 67%|██████▋   | 7461/11066 [27:19<13:02,  4.61it/s]
                                                    

 67%|██████▋   | 7461/11066 [27:19<13:02,  4.61it/s]
 67%|██████▋   | 7462/11066 [27:19<12:57,  4.63it/s]
                                                    

 67%|██████▋   | 7462/11066 [27:19<12:57,  4.63it/s]
 67%|██████▋   | 7463/11066 [27:19<12:53,  4.66it/s]
                                                    

 67%|██████▋   | 7463/11066 [27:19<12:53,  4.66it/s]
 67%|██████▋   | 7464/11066 [27:19<12:50,  4.68it/s]
                                                    

 67%|██████▋   | 7464/11066 [27:19<12:50,  4.68it/s]
 67%|██████▋   | 7465/11066 [27:19<12:48,  4.69it/s]
                                                    

 67%|██████▋   | 7465/11066 [27:19<12:48,  4.69it/s]
 67%|██████▋   | 7466/11066 [27:20<12:52,  4.66it/s]
                                                    

 67%|██████▋   | 7466/11066 [27:20<12:52,  4.66it/s]
 67%|██████▋   | 7467/11066 [27:20<12:46,  4.70it/s]
                                                    

 67%|██████▋   | 7467/11066 [27:20<12:46,  4.70it/s]
 67%|██████▋   | 7468/11066 [27:20<12:51,  4.67it/s]
                                                    

 67%|██████▋   | 7468/11066 [27:20<12:51,  4.67it/s]
 67%|██████▋   | 7469/11066 [27:20<12:45,  4.70it/s]
                                                    

 67%|██████▋   | 7469/11066 [27:20<12:45,  4.70it/s]
 68%|██████▊   | 7470/11066 [27:21<12:45,  4.70it/s]
                                                    

 68%|██████▊   | 7470/11066 [27:21<12:45,  4.70it/s]
 68%|██████▊   | 7471/11066 [27:21<12:54,  4.64it/s]
                                                    

 68%|██████▊   | 7471/11066 [27:21<12:54,  4.64it/s]
 68%|██████▊   | 7472/11066 [27:21<12:52,  4.65it/s]
                                                    

 68%|██████▊   | 7472/11066 [27:21<12:52,  4.65it/s]
 68%|██████▊   | 7473/11066 [27:21<13:01,  4.60it/s]
                                                    

 68%|██████▊   | 7473/11066 [27:21<13:01,  4.60it/s]
 68%|██████▊   | 7474/11066 [27:21<13:00,  4.60it/s]
                                                    

 68%|██████▊   | 7474/11066 [27:21<13:00,  4.60it/s]
 68%|██████▊   | 7475/11066 [27:22<13:06,  4.57it/s]
                                                    

 68%|██████▊   | 7475/11066 [27:22<13:06,  4.57it/s]
 68%|██████▊   | 7476/11066 [27:22<12:58,  4.61it/s]
                                                    

 68%|██████▊   | 7476/11066 [27:22<12:58,  4.61it/s]
 68%|██████▊   | 7477/11066 [27:22<13:04,  4.57it/s]
                                                    

 68%|██████▊   | 7477/11066 [27:22<13:04,  4.57it/s]
 68%|██████▊   | 7478/11066 [27:22<13:09,  4.55it/s]
                                                    

 68%|██████▊   | 7478/11066 [27:22<13:09,  4.55it/s]
 68%|██████▊   | 7479/11066 [27:23<13:05,  4.57it/s]
                                                    

 68%|██████▊   | 7479/11066 [27:23<13:05,  4.57it/s]
 68%|██████▊   | 7480/11066 [27:23<13:10,  4.54it/s]
                                                    

 68%|██████▊   | 7480/11066 [27:23<13:10,  4.54it/s]
 68%|██████▊   | 7481/11066 [27:23<13:00,  4.59it/s]
                                                    

 68%|██████▊   | 7481/11066 [27:23<13:00,  4.59it/s]
 68%|██████▊   | 7482/11066 [27:23<13:06,  4.56it/s]
                                                    

 68%|██████▊   | 7482/11066 [27:23<13:06,  4.56it/s]
 68%|██████▊   | 7483/11066 [27:23<12:57,  4.61it/s]
                                                    

 68%|██████▊   | 7483/11066 [27:23<12:57,  4.61it/s]
 68%|██████▊   | 7484/11066 [27:24<12:47,  4.67it/s]
                                                    

 68%|██████▊   | 7484/11066 [27:24<12:47,  4.67it/s]
 68%|██████▊   | 7485/11066 [27:24<12:50,  4.65it/s]
                                                    

 68%|██████▊   | 7485/11066 [27:24<12:50,  4.65it/s]
 68%|██████▊   | 7486/11066 [27:24<12:45,  4.68it/s]
                                                    

 68%|██████▊   | 7486/11066 [27:24<12:45,  4.68it/s]
 68%|██████▊   | 7487/11066 [27:24<12:41,  4.70it/s]
                                                    

 68%|██████▊   | 7487/11066 [27:24<12:41,  4.70it/s]
 68%|██████▊   | 7488/11066 [27:24<12:42,  4.69it/s]
                                                    

 68%|██████▊   | 7488/11066 [27:24<12:42,  4.69it/s]
 68%|██████▊   | 7489/11066 [27:25<12:46,  4.67it/s]
                                                    

 68%|██████▊   | 7489/11066 [27:25<12:46,  4.67it/s]
 68%|██████▊   | 7490/11066 [27:25<12:44,  4.67it/s]
                                                    

 68%|██████▊   | 7490/11066 [27:25<12:44,  4.67it/s]
 68%|██████▊   | 7491/11066 [27:25<12:43,  4.68it/s]
                                                    

 68%|██████▊   | 7491/11066 [27:25<12:43,  4.68it/s]
 68%|██████▊   | 7492/11066 [27:25<12:42,  4.69it/s]
                                                    

 68%|██████▊   | 7492/11066 [27:25<12:42,  4.69it/s]
 68%|██████▊   | 7493/11066 [27:26<12:52,  4.63it/s]
                                                    

 68%|██████▊   | 7493/11066 [27:26<12:52,  4.63it/s]
 68%|██████▊   | 7494/11066 [27:26<12:53,  4.62it/s]
                                                    

 68%|██████▊   | 7494/11066 [27:26<12:53,  4.62it/s]
 68%|██████▊   | 7495/11066 [27:26<12:45,  4.66it/s]
                                                    

 68%|██████▊   | 7495/11066 [27:26<12:45,  4.66it/s]
 68%|██████▊   | 7496/11066 [27:26<12:42,  4.68it/s]
                                                    

 68%|██████▊   | 7496/11066 [27:26<12:42,  4.68it/s]
 68%|██████▊   | 7497/11066 [27:26<12:37,  4.71it/s]
                                                    

 68%|██████▊   | 7497/11066 [27:26<12:37,  4.71it/s]
 68%|██████▊   | 7498/11066 [27:27<12:37,  4.71it/s]
                                                    

 68%|██████▊   | 7498/11066 [27:27<12:37,  4.71it/s]
 68%|██████▊   | 7499/11066 [27:27<12:47,  4.65it/s]
                                                    

 68%|██████▊   | 7499/11066 [27:27<12:47,  4.65it/s]
 68%|██████▊   | 7500/11066 [27:27<12:45,  4.66it/s]
                                                    

 68%|██████▊   | 7500/11066 [27:27<12:45,  4.66it/s]
 68%|██████▊   | 7501/11066 [27:27<12:48,  4.64it/s]
                                                    

 68%|██████▊   | 7501/11066 [27:27<12:48,  4.64it/s]
 68%|██████▊   | 7502/11066 [27:27<12:44,  4.66it/s]
                                                    

 68%|██████▊   | 7502/11066 [27:27<12:44,  4.66it/s]
 68%|██████▊   | 7503/11066 [27:28<12:54,  4.60it/s]
                                                    

 68%|██████▊   | 7503/11066 [27:28<12:54,  4.60it/s]
 68%|██████▊   | 7504/11066 [27:28<13:00,  4.56it/s]
                                                    

 68%|██████▊   | 7504/11066 [27:28<13:00,  4.56it/s]
 68%|██████▊   | 7505/11066 [27:28<13:05,  4.54it/s]
                                                    

 68%|██████▊   | 7505/11066 [27:28<13:05,  4.54it/s]
 68%|██████▊   | 7506/11066 [27:28<13:01,  4.56it/s]
                                                    

 68%|██████▊   | 7506/11066 [27:28<13:01,  4.56it/s]
 68%|██████▊   | 7507/11066 [27:29<13:00,  4.56it/s]
                                                    

 68%|██████▊   | 7507/11066 [27:29<13:00,  4.56it/s]
 68%|██████▊   | 7508/11066 [27:29<12:57,  4.58it/s]
                                                    

 68%|██████▊   | 7508/11066 [27:29<12:57,  4.58it/s]
 68%|██████▊   | 7509/11066 [27:29<12:50,  4.62it/s]
                                                    

 68%|██████▊   | 7509/11066 [27:29<12:50,  4.62it/s]
 68%|██████▊   | 7510/11066 [27:29<12:42,  4.67it/s]
                                                    

 68%|██████▊   | 7510/11066 [27:29<12:42,  4.67it/s]
 68%|██████▊   | 7511/11066 [27:29<12:41,  4.67it/s]
                                                    

 68%|██████▊   | 7511/11066 [27:29<12:41,  4.67it/s]
 68%|██████▊   | 7512/11066 [27:30<12:37,  4.69it/s]
                                                    

 68%|██████▊   | 7512/11066 [27:30<12:37,  4.69it/s]
 68%|██████▊   | 7513/11066 [27:30<12:41,  4.67it/s]
                                                    

 68%|██████▊   | 7513/11066 [27:30<12:41,  4.67it/s]
 68%|██████▊   | 7514/11066 [27:30<12:48,  4.62it/s]
                                                    

 68%|██████▊   | 7514/11066 [27:30<12:48,  4.62it/s]
 68%|██████▊   | 7515/11066 [27:30<12:58,  4.56it/s]
                                                    

 68%|██████▊   | 7515/11066 [27:30<12:58,  4.56it/s]
 68%|██████▊   | 7516/11066 [27:31<12:56,  4.57it/s]
                                                    

 68%|██████▊   | 7516/11066 [27:31<12:56,  4.57it/s]
 68%|██████▊   | 7517/11066 [27:31<13:01,  4.54it/s]
                                                    

 68%|██████▊   | 7517/11066 [27:31<13:01,  4.54it/s]
 68%|██████▊   | 7518/11066 [27:31<12:51,  4.60it/s]
                                                    

 68%|██████▊   | 7518/11066 [27:31<12:51,  4.60it/s]
 68%|██████▊   | 7519/11066 [27:31<13:04,  4.52it/s]
                                                    

 68%|██████▊   | 7519/11066 [27:31<13:04,  4.52it/s]
 68%|██████▊   | 7520/11066 [27:31<13:12,  4.47it/s]
                                                    

 68%|██████▊   | 7520/11066 [27:31<13:12,  4.47it/s]
 68%|██████▊   | 7521/11066 [27:32<13:21,  4.42it/s]
                                                    

 68%|██████▊   | 7521/11066 [27:32<13:21,  4.42it/s]
 68%|██████▊   | 7522/11066 [27:32<13:13,  4.47it/s]
                                                    

 68%|██████▊   | 7522/11066 [27:32<13:13,  4.47it/s]
 68%|██████▊   | 7523/11066 [27:32<12:58,  4.55it/s]
                                                    

 68%|██████▊   | 7523/11066 [27:32<12:58,  4.55it/s]
 68%|██████▊   | 7524/11066 [27:32<13:00,  4.54it/s]
                                                    

 68%|██████▊   | 7524/11066 [27:32<13:00,  4.54it/s]
 68%|██████▊   | 7525/11066 [27:33<13:02,  4.53it/s]
                                                    

 68%|██████▊   | 7525/11066 [27:33<13:02,  4.53it/s]
 68%|██████▊   | 7526/11066 [27:33<13:03,  4.52it/s]
                                                    

 68%|██████▊   | 7526/11066 [27:33<13:03,  4.52it/s]
 68%|██████▊   | 7527/11066 [27:33<13:03,  4.52it/s]
                                                    

 68%|██████▊   | 7527/11066 [27:33<13:03,  4.52it/s]
 68%|██████▊   | 7528/11066 [27:33<13:05,  4.50it/s]
                                                    

 68%|██████▊   | 7528/11066 [27:33<13:05,  4.50it/s]
 68%|██████▊   | 7529/11066 [27:33<13:05,  4.50it/s]
                                                    

 68%|██████▊   | 7529/11066 [27:33<13:05,  4.50it/s]
 68%|██████▊   | 7530/11066 [27:34<13:04,  4.50it/s]
                                                    

 68%|██████▊   | 7530/11066 [27:34<13:04,  4.50it/s]
 68%|██████▊   | 7531/11066 [27:34<13:04,  4.51it/s]
                                                    

 68%|██████▊   | 7531/11066 [27:34<13:04,  4.51it/s]
 68%|██████▊   | 7532/11066 [27:34<13:02,  4.52it/s]
                                                    

 68%|██████▊   | 7532/11066 [27:34<13:02,  4.52it/s]
 68%|██████▊   | 7533/11066 [27:34<13:04,  4.51it/s]
                                                    

 68%|██████▊   | 7533/11066 [27:34<13:04,  4.51it/s]
 68%|██████▊   | 7534/11066 [27:35<13:04,  4.50it/s]
                                                    

 68%|██████▊   | 7534/11066 [27:35<13:04,  4.50it/s]
 68%|██████▊   | 7535/11066 [27:35<13:04,  4.50it/s]
                                                    

 68%|██████▊   | 7535/11066 [27:35<13:04,  4.50it/s]
 68%|██████▊   | 7536/11066 [27:35<12:57,  4.54it/s]
                                                    

 68%|██████▊   | 7536/11066 [27:35<12:57,  4.54it/s]
 68%|██████▊   | 7537/11066 [27:35<13:02,  4.51it/s]
                                                    

 68%|██████▊   | 7537/11066 [27:35<13:02,  4.51it/s]
 68%|██████▊   | 7538/11066 [27:35<13:04,  4.50it/s]
                                                    
{'loss': 1.2054, 'learning_rate': 9.873486354599675e-06, 'epoch': 1.34}
{'loss': 0.8199, 'learning_rate': 9.870775347912524e-06, 'epoch': 1.34}
{'loss': 0.5002, 'learning_rate': 9.868064341225376e-06, 'epoch': 1.34}
{'loss': 0.6508, 'learning_rate': 9.865353334538226e-06, 'epoch': 1.34}
{'loss': 0.773, 'learning_rate': 9.862642327851076e-06, 'epoch': 1.34}
{'loss': 0.7562, 'learning_rate': 9.859931321163924e-06, 'epoch': 1.34}
{'loss': 1.0973, 'learning_rate': 9.857220314476776e-06, 'epoch': 1.34}
{'loss': 0.1034, 'learning_rate': 9.854509307789626e-06, 'epoch': 1.34}
{'loss': 0.4629, 'learning_rate': 9.851798301102477e-06, 'epoch': 1.34}
{'loss': 0.3854, 'learning_rate': 9.849087294415327e-06, 'epoch': 1.34}
{'loss': 1.4522, 'learning_rate': 9.846376287728177e-06, 'epoch': 1.34}
{'loss': 0.5309, 'learning_rate': 9.843665281041027e-06, 'epoch': 1.34}
{'loss': 0.6278, 'learning_rate': 9.840954274353877e-06, 'epoch': 1.34}
{'loss': 0.7585, 'learning_rate': 9.838243267666727e-06, 'epoch': 1.34}
{'loss': 0.604, 'learning_rate': 9.835532260979577e-06, 'epoch': 1.34}
{'loss': 0.8087, 'learning_rate': 9.832821254292427e-06, 'epoch': 1.34}
{'loss': 0.76, 'learning_rate': 9.830110247605278e-06, 'epoch': 1.34}
{'loss': 0.6892, 'learning_rate': 9.827399240918128e-06, 'epoch': 1.34}
{'loss': 0.7042, 'learning_rate': 9.824688234230978e-06, 'epoch': 1.35}
{'loss': 0.1889, 'learning_rate': 9.821977227543828e-06, 'epoch': 1.35}
{'loss': 0.4579, 'learning_rate': 9.81926622085668e-06, 'epoch': 1.35}
{'loss': 0.5406, 'learning_rate': 9.816555214169528e-06, 'epoch': 1.35}
{'loss': 1.4598, 'learning_rate': 9.813844207482378e-06, 'epoch': 1.35}
{'loss': 0.6361, 'learning_rate': 9.811133200795229e-06, 'epoch': 1.35}
{'loss': 0.4549, 'learning_rate': 9.80842219410808e-06, 'epoch': 1.35}
{'loss': 0.9091, 'learning_rate': 9.805711187420929e-06, 'epoch': 1.35}
{'loss': 0.9014, 'learning_rate': 9.803000180733779e-06, 'epoch': 1.35}
{'loss': 0.6989, 'learning_rate': 9.80028917404663e-06, 'epoch': 1.35}
{'loss': 0.6969, 'learning_rate': 9.797578167359481e-06, 'epoch': 1.35}
{'loss': 0.4463, 'learning_rate': 9.79486716067233e-06, 'epoch': 1.35}
{'loss': 0.7364, 'learning_rate': 9.79215615398518e-06, 'epoch': 1.35}
{'loss': 0.7181, 'learning_rate': 9.789445147298031e-06, 'epoch': 1.35}
{'loss': 0.4627, 'learning_rate': 9.786734140610881e-06, 'epoch': 1.35}
{'loss': 1.0914, 'learning_rate': 9.78402313392373e-06, 'epoch': 1.35}
{'loss': 0.9664, 'learning_rate': 9.78131212723658e-06, 'epoch': 1.35}
{'loss': 0.6553, 'learning_rate': 9.778601120549432e-06, 'epoch': 1.35}
{'loss': 0.291, 'learning_rate': 9.775890113862282e-06, 'epoch': 1.35}
{'loss': 0.2971, 'learning_rate': 9.77317910717513e-06, 'epoch': 1.35}
{'loss': 0.3771, 'learning_rate': 9.770468100487982e-06, 'epoch': 1.35}
{'loss': 0.7451, 'learning_rate': 9.767757093800832e-06, 'epoch': 1.35}
{'loss': 1.0545, 'learning_rate': 9.76504608711368e-06, 'epoch': 1.35}
{'loss': 0.353, 'learning_rate': 9.762335080426531e-06, 'epoch': 1.35}
{'loss': 0.4132, 'learning_rate': 9.759624073739383e-06, 'epoch': 1.35}
{'loss': 0.9501, 'learning_rate': 9.756913067052233e-06, 'epoch': 1.35}
{'loss': 0.5622, 'learning_rate': 9.754202060365081e-06, 'epoch': 1.35}
{'loss': 1.0204, 'learning_rate': 9.751491053677931e-06, 'epoch': 1.35}
{'loss': 0.6659, 'learning_rate': 9.748780046990783e-06, 'epoch': 1.35}
{'loss': 0.7444, 'learning_rate': 9.746069040303633e-06, 'epoch': 1.35}
{'loss': 0.5521, 'learning_rate': 9.743358033616482e-06, 'epoch': 1.35}
{'loss': 0.5753, 'learning_rate': 9.740647026929334e-06, 'epoch': 1.35}
{'loss': 1.2226, 'learning_rate': 9.737936020242184e-06, 'epoch': 1.35}
{'loss': 0.58, 'learning_rate': 9.735225013555034e-06, 'epoch': 1.35}
{'loss': 1.3297, 'learning_rate': 9.732514006867882e-06, 'epoch': 1.35}
{'loss': 0.2925, 'learning_rate': 9.729803000180734e-06, 'epoch': 1.35}
{'loss': 0.1994, 'learning_rate': 9.727091993493584e-06, 'epoch': 1.35}
{'loss': 1.1062, 'learning_rate': 9.724380986806435e-06, 'epoch': 1.35}
{'loss': 0.9868, 'learning_rate': 9.721669980119283e-06, 'epoch': 1.35}
{'loss': 0.4553, 'learning_rate': 9.718958973432135e-06, 'epoch': 1.35}
{'loss': 1.4773, 'learning_rate': 9.716247966744985e-06, 'epoch': 1.35}
{'loss': 1.219, 'learning_rate': 9.713536960057835e-06, 'epoch': 1.35}
{'loss': 1.2576, 'learning_rate': 9.710825953370685e-06, 'epoch': 1.35}
{'loss': 0.5212, 'learning_rate': 9.708114946683535e-06, 'epoch': 1.35}
{'loss': 0.4008, 'learning_rate': 9.705403939996385e-06, 'epoch': 1.35}
{'loss': 0.3816, 'learning_rate': 9.702692933309236e-06, 'epoch': 1.35}
{'loss': 0.4191, 'learning_rate': 9.699981926622086e-06, 'epoch': 1.35}
{'loss': 0.7299, 'learning_rate': 9.697270919934936e-06, 'epoch': 1.35}
{'loss': 0.3733, 'learning_rate': 9.694559913247786e-06, 'epoch': 1.35}
{'loss': 1.4099, 'learning_rate': 9.691848906560636e-06, 'epoch': 1.35}
{'loss': 0.9364, 'learning_rate': 9.689137899873486e-06, 'epoch': 1.35}
{'loss': 0.4753, 'learning_rate': 9.686426893186336e-06, 'epoch': 1.35}
{'loss': 0.9496, 'learning_rate': 9.683715886499187e-06, 'epoch': 1.35}
{'loss': 0.5614, 'learning_rate': 9.681004879812038e-06, 'epoch': 1.35}
{'loss': 0.5883, 'learning_rate': 9.678293873124887e-06, 'epoch': 1.35}
{'loss': 0.4759, 'learning_rate': 9.675582866437737e-06, 'epoch': 1.35}
{'loss': 0.6042, 'learning_rate': 9.672871859750587e-06, 'epoch': 1.36}
{'loss': 0.5148, 'learning_rate': 9.670160853063439e-06, 'epoch': 1.36}
{'loss': 0.8909, 'learning_rate': 9.667449846376287e-06, 'epoch': 1.36}
{'loss': 1.0063, 'learning_rate': 9.664738839689137e-06, 'epoch': 1.36}
{'loss': 0.7363, 'learning_rate': 9.662027833001988e-06, 'epoch': 1.36}
{'loss': 0.8027, 'learning_rate': 9.65931682631484e-06, 'epoch': 1.36}
{'loss': 1.073, 'learning_rate': 9.656605819627688e-06, 'epoch': 1.36}
{'loss': 0.8916, 'learning_rate': 9.653894812940538e-06, 'epoch': 1.36}
{'loss': 0.5188, 'learning_rate': 9.65118380625339e-06, 'epoch': 1.36}
{'loss': 0.7982, 'learning_rate': 9.64847279956624e-06, 'epoch': 1.36}
{'loss': 0.6558, 'learning_rate': 9.645761792879088e-06, 'epoch': 1.36}
{'loss': 0.272, 'learning_rate': 9.643050786191939e-06, 'epoch': 1.36}
{'loss': 0.9294, 'learning_rate': 9.64033977950479e-06, 'epoch': 1.36}
{'loss': 0.3927, 'learning_rate': 9.63762877281764e-06, 'epoch': 1.36}
{'loss': 0.6394, 'learning_rate': 9.634917766130489e-06, 'epoch': 1.36}
{'loss': 0.5851, 'learning_rate': 9.63220675944334e-06, 'epoch': 1.36}
{'loss': 0.4671, 'learning_rate': 9.629495752756191e-06, 'epoch': 1.36}
{'loss': 0.5094, 'learning_rate': 9.626784746069041e-06, 'epoch': 1.36}
{'loss': 0.7112, 'learning_rate': 9.62407373938189e-06, 'epoch': 1.36}
{'loss': 1.1395, 'learning_rate': 9.621362732694741e-06, 'epoch': 1.36}
{'loss': 0.5003, 'learning_rate': 9.618651726007591e-06, 'epoch': 1.36}
{'loss': 0.7251, 'learning_rate': 9.615940719320442e-06, 'epoch': 1.36}
{'loss': 0.609, 'learning_rate': 9.61322971263329e-06, 'epoch': 1.36}
{'loss': 0.7326, 'learning_rate': 9.610518705946142e-06, 'epoch': 1.36}
{'loss': 0.8627, 'learning_rate': 9.607807699258992e-06, 'epoch': 1.36}
{'loss': 0.951, 'learning_rate': 9.605096692571842e-06, 'epoch': 1.36}
{'loss': 0.7346, 'learning_rate': 9.602385685884692e-06, 'epoch': 1.36}
{'loss': 1.1065, 'learning_rate': 9.599674679197542e-06, 'epoch': 1.36}
{'loss': 1.5888, 'learning_rate': 9.596963672510393e-06, 'epoch': 1.36}
{'loss': 0.7644, 'learning_rate': 9.594252665823243e-06, 'epoch': 1.36}
{'loss': 0.45, 'learning_rate': 9.591541659136093e-06, 'epoch': 1.36}
{'loss': 0.984, 'learning_rate': 9.588830652448943e-06, 'epoch': 1.36}
{'loss': 0.7921, 'learning_rate': 9.586119645761793e-06, 'epoch': 1.36}
{'loss': 0.7304, 'learning_rate': 9.583408639074643e-06, 'epoch': 1.36}
{'loss': 0.7409, 'learning_rate': 9.580697632387493e-06, 'epoch': 1.36}
{'loss': 0.7294, 'learning_rate': 9.577986625700343e-06, 'epoch': 1.36}
{'loss': 0.7038, 'learning_rate': 9.575275619013194e-06, 'epoch': 1.36}
{'loss': 0.5271, 'learning_rate': 9.572564612326045e-06, 'epoch': 1.36}
{'loss': 0.7786, 'learning_rate': 9.569853605638894e-06, 'epoch': 1.36}
{'loss': 0.5628, 'learning_rate': 9.567142598951744e-06, 'epoch': 1.36}

 68%|██████▊   | 7538/11066 [27:35<13:04,  4.50it/s]
 68%|██████▊   | 7539/11066 [27:36<13:04,  4.50it/s]
                                                    

 68%|██████▊   | 7539/11066 [27:36<13:04,  4.50it/s]
 68%|██████▊   | 7540/11066 [27:36<13:03,  4.50it/s]
                                                    

 68%|██████▊   | 7540/11066 [27:36<13:03,  4.50it/s]
 68%|██████▊   | 7541/11066 [27:36<13:04,  4.50it/s]
                                                    

 68%|██████▊   | 7541/11066 [27:36<13:04,  4.50it/s]
 68%|██████▊   | 7542/11066 [27:36<13:04,  4.49it/s]
                                                    

 68%|██████▊   | 7542/11066 [27:36<13:04,  4.49it/s]
 68%|██████▊   | 7543/11066 [27:37<13:03,  4.50it/s]
                                                    

 68%|██████▊   | 7543/11066 [27:37<13:03,  4.50it/s]
 68%|██████▊   | 7544/11066 [27:37<13:02,  4.50it/s]
                                                    

 68%|██████▊   | 7544/11066 [27:37<13:02,  4.50it/s]
 68%|██████▊   | 7545/11066 [27:37<12:52,  4.56it/s]
                                                    

 68%|██████▊   | 7545/11066 [27:37<12:52,  4.56it/s]
 68%|██████▊   | 7546/11066 [27:37<12:44,  4.60it/s]
                                                    

 68%|██████▊   | 7546/11066 [27:37<12:44,  4.60it/s]
 68%|██████▊   | 7547/11066 [27:37<12:51,  4.56it/s]
                                                    

 68%|██████▊   | 7547/11066 [27:37<12:51,  4.56it/s]
 68%|██████▊   | 7548/11066 [27:38<12:56,  4.53it/s]
                                                    

 68%|██████▊   | 7548/11066 [27:38<12:56,  4.53it/s]
 68%|██████▊   | 7549/11066 [27:38<12:59,  4.51it/s]
                                                    

 68%|██████▊   | 7549/11066 [27:38<12:59,  4.51it/s]
 68%|██████▊   | 7550/11066 [27:38<12:53,  4.54it/s]
                                                    

 68%|██████▊   | 7550/11066 [27:38<12:53,  4.54it/s]
 68%|██████▊   | 7551/11066 [27:38<12:47,  4.58it/s]
                                                    

 68%|██████▊   | 7551/11066 [27:38<12:47,  4.58it/s]
 68%|██████▊   | 7552/11066 [27:38<12:52,  4.55it/s]
                                                    

 68%|██████▊   | 7552/11066 [27:38<12:52,  4.55it/s]
 68%|██████▊   | 7553/11066 [27:39<12:55,  4.53it/s]
                                                    

 68%|██████▊   | 7553/11066 [27:39<12:55,  4.53it/s]
 68%|██████▊   | 7554/11066 [27:39<12:50,  4.56it/s]
                                                    

 68%|██████▊   | 7554/11066 [27:39<12:50,  4.56it/s]
 68%|██████▊   | 7555/11066 [27:39<12:43,  4.60it/s]
                                                    

 68%|██████▊   | 7555/11066 [27:39<12:43,  4.60it/s]
 68%|██████▊   | 7556/11066 [27:39<12:51,  4.55it/s]
                                                    

 68%|██████▊   | 7556/11066 [27:39<12:51,  4.55it/s]
 68%|██████▊   | 7557/11066 [27:40<12:53,  4.53it/s]
                                                    

 68%|██████▊   | 7557/11066 [27:40<12:53,  4.53it/s]
 68%|██████▊   | 7558/11066 [27:40<12:55,  4.52it/s]
                                                    

 68%|██████▊   | 7558/11066 [27:40<12:55,  4.52it/s]
 68%|██████▊   | 7559/11066 [27:40<12:45,  4.58it/s]
                                                    

 68%|██████▊   | 7559/11066 [27:40<12:45,  4.58it/s]
 68%|██████▊   | 7560/11066 [27:40<12:38,  4.62it/s]
                                                    

 68%|██████▊   | 7560/11066 [27:40<12:38,  4.62it/s]
 68%|██████▊   | 7561/11066 [27:40<12:44,  4.58it/s]
                                                    

 68%|██████▊   | 7561/11066 [27:40<12:44,  4.58it/s]
 68%|██████▊   | 7562/11066 [27:41<13:00,  4.49it/s]
                                                    

 68%|██████▊   | 7562/11066 [27:41<13:00,  4.49it/s]
 68%|██████▊   | 7563/11066 [27:41<12:59,  4.50it/s]
                                                    

 68%|██████▊   | 7563/11066 [27:41<12:59,  4.50it/s]
 68%|██████▊   | 7564/11066 [27:41<12:47,  4.56it/s]
                                                    

 68%|██████▊   | 7564/11066 [27:41<12:47,  4.56it/s]
 68%|██████▊   | 7565/11066 [27:41<12:39,  4.61it/s]
                                                    

 68%|██████▊   | 7565/11066 [27:41<12:39,  4.61it/s]
 68%|██████▊   | 7566/11066 [27:42<12:38,  4.61it/s]
                                                    

 68%|██████▊   | 7566/11066 [27:42<12:38,  4.61it/s]
 68%|██████▊   | 7567/11066 [27:42<12:47,  4.56it/s]
                                                    

 68%|██████▊   | 7567/11066 [27:42<12:47,  4.56it/s]
 68%|██████▊   | 7568/11066 [27:42<12:40,  4.60it/s]
                                                    

 68%|██████▊   | 7568/11066 [27:42<12:40,  4.60it/s]
 68%|██████▊   | 7569/11066 [27:42<12:40,  4.60it/s]
                                                    

 68%|██████▊   | 7569/11066 [27:42<12:40,  4.60it/s]
 68%|██████▊   | 7570/11066 [27:42<12:49,  4.55it/s]
                                                    

 68%|██████▊   | 7570/11066 [27:42<12:49,  4.55it/s]
 68%|██████▊   | 7571/11066 [27:43<13:01,  4.47it/s]
                                                    

 68%|██████▊   | 7571/11066 [27:43<13:01,  4.47it/s]
 68%|██████▊   | 7572/11066 [27:43<13:00,  4.47it/s]
                                                    

 68%|██████▊   | 7572/11066 [27:43<13:00,  4.47it/s]
 68%|██████▊   | 7573/11066 [27:43<12:58,  4.48it/s]
                                                    

 68%|██████▊   | 7573/11066 [27:43<12:58,  4.48it/s]
 68%|██████▊   | 7574/11066 [27:43<12:58,  4.49it/s]
                                                    

 68%|██████▊   | 7574/11066 [27:43<12:58,  4.49it/s]
 68%|██████▊   | 7575/11066 [27:44<12:57,  4.49it/s]
                                                    

 68%|██████▊   | 7575/11066 [27:44<12:57,  4.49it/s]
 68%|██████▊   | 7576/11066 [27:44<12:57,  4.49it/s]
                                                    

 68%|██████▊   | 7576/11066 [27:44<12:57,  4.49it/s]
 68%|██████▊   | 7577/11066 [27:44<12:56,  4.49it/s]
                                                    

 68%|██████▊   | 7577/11066 [27:44<12:56,  4.49it/s]
 68%|██████▊   | 7578/11066 [27:44<12:55,  4.50it/s]
                                                    

 68%|██████▊   | 7578/11066 [27:44<12:55,  4.50it/s]
 68%|██████▊   | 7579/11066 [27:44<12:54,  4.50it/s]
                                                    

 68%|██████▊   | 7579/11066 [27:44<12:54,  4.50it/s]
 68%|██████▊   | 7580/11066 [27:45<12:53,  4.51it/s]
                                                    

 68%|██████▊   | 7580/11066 [27:45<12:53,  4.51it/s]
 69%|██████▊   | 7581/11066 [27:45<12:53,  4.51it/s]
                                                    

 69%|██████▊   | 7581/11066 [27:45<12:53,  4.51it/s]
 69%|██████▊   | 7582/11066 [27:45<12:54,  4.50it/s]
                                                    

 69%|██████▊   | 7582/11066 [27:45<12:54,  4.50it/s]
 69%|██████▊   | 7583/11066 [27:45<12:55,  4.49it/s]
                                                    

 69%|██████▊   | 7583/11066 [27:45<12:55,  4.49it/s]
 69%|██████▊   | 7584/11066 [27:46<13:01,  4.46it/s]
                                                    

 69%|██████▊   | 7584/11066 [27:46<13:01,  4.46it/s]
 69%|██████▊   | 7585/11066 [27:46<13:06,  4.43it/s]
                                                    

 69%|██████▊   | 7585/11066 [27:46<13:06,  4.43it/s]
 69%|██████▊   | 7586/11066 [27:46<13:05,  4.43it/s]
                                                    

 69%|██████▊   | 7586/11066 [27:46<13:05,  4.43it/s]
 69%|██████▊   | 7587/11066 [27:46<13:02,  4.45it/s]
                                                    

 69%|██████▊   | 7587/11066 [27:46<13:02,  4.45it/s]
 69%|██████▊   | 7588/11066 [27:46<12:59,  4.46it/s]
                                                    

 69%|██████▊   | 7588/11066 [27:46<12:59,  4.46it/s]
 69%|██████▊   | 7589/11066 [27:47<12:56,  4.48it/s]
                                                    

 69%|██████▊   | 7589/11066 [27:47<12:56,  4.48it/s]
 69%|██████▊   | 7590/11066 [27:47<12:55,  4.48it/s]
                                                    

 69%|██████▊   | 7590/11066 [27:47<12:55,  4.48it/s]
 69%|██████▊   | 7591/11066 [27:47<12:53,  4.49it/s]
                                                    

 69%|██████▊   | 7591/11066 [27:47<12:53,  4.49it/s]
 69%|██████▊   | 7592/11066 [27:47<12:53,  4.49it/s]
                                                    

 69%|██████▊   | 7592/11066 [27:47<12:53,  4.49it/s]
 69%|██████▊   | 7593/11066 [27:48<12:52,  4.50it/s]
                                                    

 69%|██████▊   | 7593/11066 [27:48<12:52,  4.50it/s]
 69%|██████▊   | 7594/11066 [27:48<12:52,  4.50it/s]
                                                    

 69%|██████▊   | 7594/11066 [27:48<12:52,  4.50it/s]
 69%|██████▊   | 7595/11066 [27:48<12:51,  4.50it/s]
                                                    

 69%|██████▊   | 7595/11066 [27:48<12:51,  4.50it/s]
 69%|██████▊   | 7596/11066 [27:48<12:38,  4.58it/s]
                                                    

 69%|██████▊   | 7596/11066 [27:48<12:38,  4.58it/s]
 69%|██████▊   | 7597/11066 [27:48<12:43,  4.54it/s]
                                                    

 69%|██████▊   | 7597/11066 [27:48<12:43,  4.54it/s]
 69%|██████▊   | 7598/11066 [27:49<12:45,  4.53it/s]
                                                    

 69%|██████▊   | 7598/11066 [27:49<12:45,  4.53it/s]
 69%|██████▊   | 7599/11066 [27:49<12:47,  4.52it/s]
                                                    

 69%|██████▊   | 7599/11066 [27:49<12:47,  4.52it/s]
 69%|██████▊   | 7600/11066 [27:49<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7600/11066 [27:49<12:47,  4.51it/s]
 69%|██████▊   | 7601/11066 [27:49<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7601/11066 [27:49<12:47,  4.51it/s]
 69%|██████▊   | 7602/11066 [27:50<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7602/11066 [27:50<12:47,  4.51it/s]
 69%|██████▊   | 7603/11066 [27:50<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7603/11066 [27:50<12:47,  4.51it/s]
 69%|██████▊   | 7604/11066 [27:50<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7604/11066 [27:50<12:47,  4.51it/s]
 69%|██████▊   | 7605/11066 [27:50<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7605/11066 [27:50<12:47,  4.51it/s]
 69%|██████▊   | 7606/11066 [27:50<12:48,  4.50it/s]
                                                    

 69%|██████▊   | 7606/11066 [27:50<12:48,  4.50it/s]
 69%|██████▊   | 7607/11066 [27:51<12:47,  4.51it/s]
                                                    

 69%|██████▊   | 7607/11066 [27:51<12:47,  4.51it/s]
 69%|██████▉   | 7608/11066 [27:51<12:47,  4.51it/s]
                                                    

 69%|██████▉   | 7608/11066 [27:51<12:47,  4.51it/s]
 69%|██████▉   | 7609/11066 [27:51<12:47,  4.50it/s]
                                                    

 69%|██████▉   | 7609/11066 [27:51<12:47,  4.50it/s]
 69%|██████▉   | 7610/11066 [27:51<12:42,  4.53it/s]
                                                    

 69%|██████▉   | 7610/11066 [27:51<12:42,  4.53it/s]
 69%|██████▉   | 7611/11066 [27:52<12:47,  4.50it/s]
                                                    

 69%|██████▉   | 7611/11066 [27:52<12:47,  4.50it/s]
 69%|██████▉   | 7612/11066 [27:52<12:48,  4.50it/s]
                                                    

 69%|██████▉   | 7612/11066 [27:52<12:48,  4.50it/s]
 69%|██████▉   | 7613/11066 [27:52<12:47,  4.50it/s]
                                                    

 69%|██████▉   | 7613/11066 [27:52<12:47,  4.50it/s]
 69%|██████▉   | 7614/11066 [27:52<12:47,  4.50it/s]
                                                    

 69%|██████▉   | 7614/11066 [27:52<12:47,  4.50it/s]
 69%|██████▉   | 7615/11066 [27:52<12:46,  4.50it/s]
                                                    

 69%|██████▉   | 7615/11066 [27:52<12:46,  4.50it/s]
 69%|██████▉   | 7616/11066 [27:53<12:46,  4.50it/s]
                                                    

 69%|██████▉   | 7616/11066 [27:53<12:46,  4.50it/s]
 69%|██████▉   | 7617/11066 [27:53<12:46,  4.50it/s]
                                                    

 69%|██████▉   | 7617/11066 [27:53<12:46,  4.50it/s]
 69%|██████▉   | 7618/11066 [27:53<12:45,  4.50it/s]
                                                    

 69%|██████▉   | 7618/11066 [27:53<12:45,  4.50it/s]
 69%|██████▉   | 7619/11066 [27:53<12:45,  4.50it/s]
                                                    

 69%|██████▉   | 7619/11066 [27:53<12:45,  4.50it/s]
 69%|██████▉   | 7620/11066 [27:54<12:45,  4.50it/s]
                                                    

 69%|██████▉   | 7620/11066 [27:54<12:45,  4.50it/s]
 69%|██████▉   | 7621/11066 [27:54<12:45,  4.50it/s]
                                                    

 69%|██████▉   | 7621/11066 [27:54<12:45,  4.50it/s]
 69%|██████▉   | 7622/11066 [27:54<12:44,  4.50it/s]
                                                    

 69%|██████▉   | 7622/11066 [27:54<12:44,  4.50it/s]
 69%|██████▉   | 7623/11066 [27:54<12:44,  4.50it/s]
                                                    

 69%|██████▉   | 7623/11066 [27:54<12:44,  4.50it/s]
 69%|██████▉   | 7624/11066 [27:54<12:45,  4.50it/s]
                                                    

 69%|██████▉   | 7624/11066 [27:54<12:45,  4.50it/s]
 69%|██████▉   | 7625/11066 [27:55<12:44,  4.50it/s]
                                                    

 69%|██████▉   | 7625/11066 [27:55<12:44,  4.50it/s]
 69%|██████▉   | 7626/11066 [27:55<12:43,  4.50it/s]
                                                    

 69%|██████▉   | 7626/11066 [27:55<12:43,  4.50it/s]
 69%|██████▉   | 7627/11066 [27:55<12:43,  4.50it/s]
                                                    

 69%|██████▉   | 7627/11066 [27:55<12:43,  4.50it/s]
 69%|██████▉   | 7628/11066 [27:55<12:42,  4.51it/s]
                                                    

 69%|██████▉   | 7628/11066 [27:55<12:42,  4.51it/s]
 69%|██████▉   | 7629/11066 [27:56<12:42,  4.50it/s]
                                                    

 69%|██████▉   | 7629/11066 [27:56<12:42,  4.50it/s]
 69%|██████▉   | 7630/11066 [27:56<12:42,  4.51it/s]
                                                    

 69%|██████▉   | 7630/11066 [27:56<12:42,  4.51it/s]
 69%|██████▉   | 7631/11066 [27:56<12:42,  4.51it/s]
                                                    

 69%|██████▉   | 7631/11066 [27:56<12:42,  4.51it/s]
 69%|██████▉   | 7632/11066 [27:56<12:42,  4.50it/s]
                                                    

 69%|██████▉   | 7632/11066 [27:56<12:42,  4.50it/s]
 69%|██████▉   | 7633/11066 [27:56<12:42,  4.50it/s]
                                                    

 69%|██████▉   | 7633/11066 [27:56<12:42,  4.50it/s]
 69%|██████▉   | 7634/11066 [27:57<12:41,  4.50it/s]
                                                    

 69%|██████▉   | 7634/11066 [27:57<12:41,  4.50it/s]
 69%|██████▉   | 7635/11066 [27:57<12:41,  4.50it/s]
                                                    

 69%|██████▉   | 7635/11066 [27:57<12:41,  4.50it/s]
 69%|██████▉   | 7636/11066 [27:57<12:42,  4.50it/s]
                                                    

 69%|██████▉   | 7636/11066 [27:57<12:42,  4.50it/s]
 69%|██████▉   | 7637/11066 [27:57<12:44,  4.49it/s]
                                                    

 69%|██████▉   | 7637/11066 [27:57<12:44,  4.49it/s]
 69%|██████▉   | 7638/11066 [27:58<12:47,  4.47it/s]
                                                    

 69%|██████▉   | 7638/11066 [27:58<12:47,  4.47it/s]
 69%|██████▉   | 7639/11066 [27:58<12:41,  4.50it/s]
                                                    

 69%|██████▉   | 7639/11066 [27:58<12:41,  4.50it/s]
 69%|██████▉   | 7640/11066 [27:58<12:27,  4.58it/s]
                                                    

 69%|██████▉   | 7640/11066 [27:58<12:27,  4.58it/s]
 69%|██████▉   | 7641/11066 [27:58<12:34,  4.54it/s]
                                                    

 69%|██████▉   | 7641/11066 [27:58<12:34,  4.54it/s]
 69%|██████▉   | 7642/11066 [27:58<12:40,  4.50it/s]
                                                    

 69%|██████▉   | 7642/11066 [27:58<12:40,  4.50it/s]
 69%|██████▉   | 7643/11066 [27:59<12:42,  4.49it/s]
                                                    

 69%|██████▉   | 7643/11066 [27:59<12:42,  4.49it/s]
 69%|██████▉   | 7644/11066 [27:59<12:42,  4.49it/s]
                                                    

 69%|██████▉   | 7644/11066 [27:59<12:42,  4.49it/s]
 69%|██████▉   | 7645/11066 [27:59<12:41,  4.49it/s]
                                                    

 69%|██████▉   | 7645/11066 [27:59<12:41,  4.49it/s]
 69%|██████▉   | 7646/11066 [27:59<12:40,  4.50it/s]
                                                    

 69%|██████▉   | 7646/11066 [27:59<12:40,  4.50it/s]
 69%|██████▉   | 7647/11066 [28:00<12:39,  4.50it/s]
                                                    

 69%|██████▉   | 7647/11066 [28:00<12:39,  4.50it/s]
 69%|██████▉   | 7648/11066 [28:00<12:38,  4.51it/s]
                                                    

 69%|██████▉   | 7648/11066 [28:00<12:38,  4.51it/s]
 69%|██████▉   | 7649/11066 [28:00<12:38,  4.51it/s]
                                                    

 69%|██████▉   | 7649/11066 [28:00<12:38,  4.51it/s]
 69%|██████▉   | 7650/11066 [28:00<12:38,  4.51it/s]
                                                    

 69%|██████▉   | 7650/11066 [28:00<12:38,  4.51it/s]
 69%|██████▉   | 7651/11066 [28:00<12:37,  4.51it/s]
                                                    

 69%|██████▉   | 7651/11066 [28:00<12:37,  4.51it/s]
 69%|██████▉   | 7652/11066 [28:01<12:40,  4.49it/s]
                                                    
{'loss': 0.9424, 'learning_rate': 9.564431592264594e-06, 'epoch': 1.36}
{'loss': 0.6744, 'learning_rate': 9.561720585577446e-06, 'epoch': 1.36}
{'loss': 0.802, 'learning_rate': 9.559009578890294e-06, 'epoch': 1.36}
{'loss': 0.2983, 'learning_rate': 9.556298572203145e-06, 'epoch': 1.36}
{'loss': 0.516, 'learning_rate': 9.553587565515995e-06, 'epoch': 1.36}
{'loss': 0.4636, 'learning_rate': 9.550876558828847e-06, 'epoch': 1.36}
{'loss': 0.8475, 'learning_rate': 9.548165552141695e-06, 'epoch': 1.36}
{'loss': 1.0413, 'learning_rate': 9.545454545454545e-06, 'epoch': 1.36}
{'loss': 0.9055, 'learning_rate': 9.542743538767397e-06, 'epoch': 1.36}
{'loss': 0.7543, 'learning_rate': 9.540032532080247e-06, 'epoch': 1.36}
{'loss': 0.9586, 'learning_rate': 9.537321525393095e-06, 'epoch': 1.36}
{'loss': 1.301, 'learning_rate': 9.534610518705946e-06, 'epoch': 1.36}
{'loss': 1.1415, 'learning_rate': 9.531899512018797e-06, 'epoch': 1.36}
{'loss': 0.7625, 'learning_rate': 9.529188505331648e-06, 'epoch': 1.36}
{'loss': 0.4903, 'learning_rate': 9.526477498644496e-06, 'epoch': 1.36}
{'loss': 0.9156, 'learning_rate': 9.523766491957346e-06, 'epoch': 1.37}
{'loss': 1.025, 'learning_rate': 9.521055485270198e-06, 'epoch': 1.37}
{'loss': 1.054, 'learning_rate': 9.518344478583048e-06, 'epoch': 1.37}
{'loss': 0.5766, 'learning_rate': 9.515633471895897e-06, 'epoch': 1.37}
{'loss': 0.5836, 'learning_rate': 9.512922465208748e-06, 'epoch': 1.37}
{'loss': 0.7723, 'learning_rate': 9.510211458521599e-06, 'epoch': 1.37}
{'loss': 0.892, 'learning_rate': 9.507500451834449e-06, 'epoch': 1.37}
{'loss': 0.5856, 'learning_rate': 9.504789445147297e-06, 'epoch': 1.37}
{'loss': 1.3629, 'learning_rate': 9.502078438460149e-06, 'epoch': 1.37}
{'loss': 0.7752, 'learning_rate': 9.499367431772999e-06, 'epoch': 1.37}
{'loss': 0.5183, 'learning_rate': 9.49665642508585e-06, 'epoch': 1.37}
{'loss': 1.2523, 'learning_rate': 9.493945418398698e-06, 'epoch': 1.37}
{'loss': 0.9689, 'learning_rate': 9.49123441171155e-06, 'epoch': 1.37}
{'loss': 1.1885, 'learning_rate': 9.4885234050244e-06, 'epoch': 1.37}
{'loss': 0.4217, 'learning_rate': 9.48581239833725e-06, 'epoch': 1.37}
{'loss': 0.7725, 'learning_rate': 9.4831013916501e-06, 'epoch': 1.37}
{'loss': 0.7745, 'learning_rate': 9.48039038496295e-06, 'epoch': 1.37}
{'loss': 1.0021, 'learning_rate': 9.4776793782758e-06, 'epoch': 1.37}
{'loss': 0.6021, 'learning_rate': 9.47496837158865e-06, 'epoch': 1.37}
{'loss': 1.2583, 'learning_rate': 9.4722573649015e-06, 'epoch': 1.37}
{'loss': 0.4528, 'learning_rate': 9.46954635821435e-06, 'epoch': 1.37}
{'loss': 0.7105, 'learning_rate': 9.4668353515272e-06, 'epoch': 1.37}
{'loss': 0.5873, 'learning_rate': 9.46412434484005e-06, 'epoch': 1.37}
{'loss': 1.2718, 'learning_rate': 9.461413338152901e-06, 'epoch': 1.37}
{'loss': 1.682, 'learning_rate': 9.458702331465751e-06, 'epoch': 1.37}
{'loss': 0.7744, 'learning_rate': 9.455991324778601e-06, 'epoch': 1.37}
{'loss': 0.7547, 'learning_rate': 9.453280318091453e-06, 'epoch': 1.37}
{'loss': 0.65, 'learning_rate': 9.450569311404301e-06, 'epoch': 1.37}
{'loss': 0.3903, 'learning_rate': 9.447858304717152e-06, 'epoch': 1.37}
{'loss': 0.95, 'learning_rate': 9.445147298030002e-06, 'epoch': 1.37}
{'loss': 1.0885, 'learning_rate': 9.442436291342854e-06, 'epoch': 1.37}
{'loss': 0.4694, 'learning_rate': 9.439725284655702e-06, 'epoch': 1.37}
{'loss': 0.8483, 'learning_rate': 9.437014277968552e-06, 'epoch': 1.37}
{'loss': 0.6125, 'learning_rate': 9.434303271281404e-06, 'epoch': 1.37}
{'loss': 1.1123, 'learning_rate': 9.431592264594254e-06, 'epoch': 1.37}
{'loss': 0.6633, 'learning_rate': 9.428881257907103e-06, 'epoch': 1.37}
{'loss': 0.9778, 'learning_rate': 9.426170251219953e-06, 'epoch': 1.37}
{'loss': 1.1371, 'learning_rate': 9.423459244532805e-06, 'epoch': 1.37}
{'loss': 0.8013, 'learning_rate': 9.420748237845655e-06, 'epoch': 1.37}
{'loss': 0.4071, 'learning_rate': 9.418037231158503e-06, 'epoch': 1.37}
{'loss': 0.6538, 'learning_rate': 9.415326224471353e-06, 'epoch': 1.37}
{'loss': 0.898, 'learning_rate': 9.412615217784205e-06, 'epoch': 1.37}
{'loss': 0.8677, 'learning_rate': 9.409904211097053e-06, 'epoch': 1.37}
{'loss': 0.9222, 'learning_rate': 9.407193204409904e-06, 'epoch': 1.37}
{'loss': 0.5672, 'learning_rate': 9.404482197722755e-06, 'epoch': 1.37}
{'loss': 0.3884, 'learning_rate': 9.401771191035606e-06, 'epoch': 1.37}
{'loss': 0.7195, 'learning_rate': 9.399060184348454e-06, 'epoch': 1.37}
{'loss': 0.6682, 'learning_rate': 9.396349177661304e-06, 'epoch': 1.37}
{'loss': 0.9906, 'learning_rate': 9.393638170974156e-06, 'epoch': 1.37}
{'loss': 0.4357, 'learning_rate': 9.390927164287006e-06, 'epoch': 1.37}
{'loss': 0.4259, 'learning_rate': 9.388216157599855e-06, 'epoch': 1.37}
{'loss': 0.3952, 'learning_rate': 9.385505150912705e-06, 'epoch': 1.37}
{'loss': 0.2353, 'learning_rate': 9.382794144225557e-06, 'epoch': 1.37}
{'loss': 1.4491, 'learning_rate': 9.380083137538407e-06, 'epoch': 1.37}
{'loss': 0.4996, 'learning_rate': 9.377372130851255e-06, 'epoch': 1.37}
{'loss': 1.1753, 'learning_rate': 9.374661124164107e-06, 'epoch': 1.38}
{'loss': 0.6262, 'learning_rate': 9.371950117476957e-06, 'epoch': 1.38}
{'loss': 0.9721, 'learning_rate': 9.369239110789807e-06, 'epoch': 1.38}
{'loss': 1.2643, 'learning_rate': 9.366528104102656e-06, 'epoch': 1.38}
{'loss': 0.4976, 'learning_rate': 9.363817097415507e-06, 'epoch': 1.38}
{'loss': 0.736, 'learning_rate': 9.361106090728358e-06, 'epoch': 1.38}
{'loss': 0.8335, 'learning_rate': 9.358395084041208e-06, 'epoch': 1.38}
{'loss': 0.8562, 'learning_rate': 9.355684077354056e-06, 'epoch': 1.38}
{'loss': 1.0362, 'learning_rate': 9.352973070666908e-06, 'epoch': 1.38}
{'loss': 0.8527, 'learning_rate': 9.350262063979758e-06, 'epoch': 1.38}
{'loss': 0.7404, 'learning_rate': 9.347551057292608e-06, 'epoch': 1.38}
{'loss': 0.8901, 'learning_rate': 9.344840050605458e-06, 'epoch': 1.38}
{'loss': 1.1493, 'learning_rate': 9.342129043918309e-06, 'epoch': 1.38}
{'loss': 0.4282, 'learning_rate': 9.339418037231159e-06, 'epoch': 1.38}
{'loss': 1.5558, 'learning_rate': 9.336707030544009e-06, 'epoch': 1.38}
{'loss': 0.9636, 'learning_rate': 9.333996023856859e-06, 'epoch': 1.38}
{'loss': 0.6224, 'learning_rate': 9.331285017169709e-06, 'epoch': 1.38}
{'loss': 0.5464, 'learning_rate': 9.32857401048256e-06, 'epoch': 1.38}
{'loss': 0.4813, 'learning_rate': 9.32586300379541e-06, 'epoch': 1.38}
{'loss': 0.9267, 'learning_rate': 9.32315199710826e-06, 'epoch': 1.38}
{'loss': 0.7691, 'learning_rate': 9.32044099042111e-06, 'epoch': 1.38}
{'loss': 0.6783, 'learning_rate': 9.31772998373396e-06, 'epoch': 1.38}
{'loss': 0.8425, 'learning_rate': 9.315018977046812e-06, 'epoch': 1.38}
{'loss': 0.7734, 'learning_rate': 9.31230797035966e-06, 'epoch': 1.38}
{'loss': 1.0502, 'learning_rate': 9.30959696367251e-06, 'epoch': 1.38}
{'loss': 0.6539, 'learning_rate': 9.30688595698536e-06, 'epoch': 1.38}
{'loss': 1.0851, 'learning_rate': 9.304174950298212e-06, 'epoch': 1.38}
{'loss': 0.7151, 'learning_rate': 9.30146394361106e-06, 'epoch': 1.38}
{'loss': 0.5287, 'learning_rate': 9.29875293692391e-06, 'epoch': 1.38}
{'loss': 0.6745, 'learning_rate': 9.29604193023676e-06, 'epoch': 1.38}
{'loss': 0.8131, 'learning_rate': 9.293330923549613e-06, 'epoch': 1.38}
{'loss': 0.6377, 'learning_rate': 9.290619916862461e-06, 'epoch': 1.38}
{'loss': 0.3432, 'learning_rate': 9.287908910175311e-06, 'epoch': 1.38}
{'loss': 0.5982, 'learning_rate': 9.285197903488163e-06, 'epoch': 1.38}
{'loss': 0.6758, 'learning_rate': 9.282486896801013e-06, 'epoch': 1.38}
{'loss': 0.8152, 'learning_rate': 9.279775890113862e-06, 'epoch': 1.38}
{'loss': 0.5692, 'learning_rate': 9.277064883426712e-06, 'epoch': 1.38}
{'loss': 1.3164, 'learning_rate': 9.274353876739564e-06, 'epoch': 1.38}
{'loss': 1.3846, 'learning_rate': 9.271642870052414e-06, 'epoch': 1.38}
{'loss': 0.422, 'learning_rate': 9.268931863365262e-06, 'epoch': 1.38}
{'loss': 0.693, 'learning_rate': 9.266220856678112e-06, 'epoch': 1.38}
{'loss': 0.6107, 'learning_rate': 9.263509849990964e-06, 'epoch': 1.38}
{'loss': 0.5498, 'learning_rate': 9.260798843303814e-06, 'epoch': 1.38}
{'loss': 0.6853, 'learning_rate': 9.258087836616663e-06, 'epoch': 1.38}

 69%|██████▉   | 7652/11066 [28:01<12:40,  4.49it/s]
 69%|██████▉   | 7653/11066 [28:01<12:43,  4.47it/s]
                                                    

 69%|██████▉   | 7653/11066 [28:01<12:43,  4.47it/s]
 69%|██████▉   | 7654/11066 [28:01<12:43,  4.47it/s]
                                                    

 69%|██████▉   | 7654/11066 [28:01<12:43,  4.47it/s]
 69%|██████▉   | 7655/11066 [28:01<12:42,  4.47it/s]
                                                    

 69%|██████▉   | 7655/11066 [28:01<12:42,  4.47it/s]
 69%|██████▉   | 7656/11066 [28:02<12:40,  4.48it/s]
                                                    

 69%|██████▉   | 7656/11066 [28:02<12:40,  4.48it/s]
 69%|██████▉   | 7657/11066 [28:02<12:40,  4.49it/s]
                                                    

 69%|██████▉   | 7657/11066 [28:02<12:40,  4.49it/s]
 69%|██████▉   | 7658/11066 [28:02<12:38,  4.49it/s]
                                                    

 69%|██████▉   | 7658/11066 [28:02<12:38,  4.49it/s]
 69%|██████▉   | 7659/11066 [28:02<12:37,  4.50it/s]
                                                    

 69%|██████▉   | 7659/11066 [28:02<12:37,  4.50it/s]
 69%|██████▉   | 7660/11066 [28:02<12:36,  4.50it/s]
                                                    

 69%|██████▉   | 7660/11066 [28:02<12:36,  4.50it/s]
 69%|██████▉   | 7661/11066 [28:03<12:35,  4.51it/s]
                                                    

 69%|██████▉   | 7661/11066 [28:03<12:35,  4.51it/s]
 69%|██████▉   | 7662/11066 [28:03<12:35,  4.51it/s]
                                                    

 69%|██████▉   | 7662/11066 [28:03<12:35,  4.51it/s]
 69%|██████▉   | 7663/11066 [28:03<12:35,  4.50it/s]
                                                    

 69%|██████▉   | 7663/11066 [28:03<12:35,  4.50it/s]
 69%|██████▉   | 7664/11066 [28:03<12:39,  4.48it/s]
                                                    

 69%|██████▉   | 7664/11066 [28:03<12:39,  4.48it/s]
 69%|██████▉   | 7665/11066 [28:04<12:42,  4.46it/s]
                                                    

 69%|██████▉   | 7665/11066 [28:04<12:42,  4.46it/s]
 69%|██████▉   | 7666/11066 [28:04<12:41,  4.47it/s]
                                                    

 69%|██████▉   | 7666/11066 [28:04<12:41,  4.47it/s]
 69%|██████▉   | 7667/11066 [28:04<12:44,  4.44it/s]
                                                    

 69%|██████▉   | 7667/11066 [28:04<12:44,  4.44it/s]
 69%|██████▉   | 7668/11066 [28:04<12:44,  4.44it/s]
                                                    

 69%|██████▉   | 7668/11066 [28:04<12:44,  4.44it/s]
 69%|██████▉   | 7669/11066 [28:04<12:42,  4.46it/s]
                                                    

 69%|██████▉   | 7669/11066 [28:04<12:42,  4.46it/s]
 69%|██████▉   | 7670/11066 [28:05<12:39,  4.47it/s]
                                                    

 69%|██████▉   | 7670/11066 [28:05<12:39,  4.47it/s]
 69%|██████▉   | 7671/11066 [28:05<12:38,  4.48it/s]
                                                    

 69%|██████▉   | 7671/11066 [28:05<12:38,  4.48it/s]
 69%|██████▉   | 7672/11066 [28:05<12:36,  4.48it/s]
                                                    

 69%|██████▉   | 7672/11066 [28:05<12:36,  4.48it/s]
 69%|██████▉   | 7673/11066 [28:05<12:35,  4.49it/s]
                                                    

 69%|██████▉   | 7673/11066 [28:05<12:35,  4.49it/s]
 69%|██████▉   | 7674/11066 [28:06<12:34,  4.50it/s]
                                                    

 69%|██████▉   | 7674/11066 [28:06<12:34,  4.50it/s]
 69%|██████▉   | 7675/11066 [28:06<12:32,  4.50it/s]
                                                    

 69%|██████▉   | 7675/11066 [28:06<12:32,  4.50it/s]
 69%|██████▉   | 7676/11066 [28:06<12:32,  4.50it/s]
                                                    

 69%|██████▉   | 7676/11066 [28:06<12:32,  4.50it/s]
 69%|██████▉   | 7677/11066 [28:06<12:32,  4.50it/s]
                                                    

 69%|██████▉   | 7677/11066 [28:06<12:32,  4.50it/s]
 69%|██████▉   | 7678/11066 [28:06<12:33,  4.50it/s]
                                                    

 69%|██████▉   | 7678/11066 [28:06<12:33,  4.50it/s]
 69%|██████▉   | 7679/11066 [28:07<12:33,  4.50it/s]
                                                    

 69%|██████▉   | 7679/11066 [28:07<12:33,  4.50it/s]
 69%|██████▉   | 7680/11066 [28:07<12:26,  4.53it/s]
                                                    

 69%|██████▉   | 7680/11066 [28:07<12:26,  4.53it/s]
 69%|██████▉   | 7681/11066 [28:07<12:30,  4.51it/s]
                                                    

 69%|██████▉   | 7681/11066 [28:07<12:30,  4.51it/s]
 69%|██████▉   | 7682/11066 [28:07<12:31,  4.50it/s]
                                                    

 69%|██████▉   | 7682/11066 [28:07<12:31,  4.50it/s]
 69%|██████▉   | 7683/11066 [28:08<12:31,  4.50it/s]
                                                    

 69%|██████▉   | 7683/11066 [28:08<12:31,  4.50it/s]
 69%|██████▉   | 7684/11066 [28:08<12:31,  4.50it/s]
                                                    

 69%|██████▉   | 7684/11066 [28:08<12:31,  4.50it/s]
 69%|██████▉   | 7685/11066 [28:08<12:30,  4.50it/s]
                                                    

 69%|██████▉   | 7685/11066 [28:08<12:30,  4.50it/s]
 69%|██████▉   | 7686/11066 [28:08<12:30,  4.50it/s]
                                                    

 69%|██████▉   | 7686/11066 [28:08<12:30,  4.50it/s]
 69%|██████▉   | 7687/11066 [28:08<12:30,  4.50it/s]
                                                    

 69%|██████▉   | 7687/11066 [28:08<12:30,  4.50it/s]
 69%|██████▉   | 7688/11066 [28:09<12:30,  4.50it/s]
                                                    

 69%|██████▉   | 7688/11066 [28:09<12:30,  4.50it/s]
 69%|██████▉   | 7689/11066 [28:09<12:30,  4.50it/s]
                                                    

 69%|██████▉   | 7689/11066 [28:09<12:30,  4.50it/s]
 69%|██████▉   | 7690/11066 [28:09<12:29,  4.50it/s]
                                                    

 69%|██████▉   | 7690/11066 [28:09<12:29,  4.50it/s]
 70%|██████▉   | 7691/11066 [28:09<12:29,  4.50it/s]
                                                    

 70%|██████▉   | 7691/11066 [28:09<12:29,  4.50it/s]
 70%|██████▉   | 7692/11066 [28:10<12:29,  4.50it/s]
                                                    

 70%|██████▉   | 7692/11066 [28:10<12:29,  4.50it/s]
 70%|██████▉   | 7693/11066 [28:10<12:29,  4.50it/s]
                                                    

 70%|██████▉   | 7693/11066 [28:10<12:29,  4.50it/s]
 70%|██████▉   | 7694/11066 [28:10<12:28,  4.50it/s]
                                                    

 70%|██████▉   | 7694/11066 [28:10<12:28,  4.50it/s]
 70%|██████▉   | 7695/11066 [28:10<12:27,  4.51it/s]
                                                    

 70%|██████▉   | 7695/11066 [28:10<12:27,  4.51it/s]
 70%|██████▉   | 7696/11066 [28:10<12:27,  4.51it/s]
                                                    

 70%|██████▉   | 7696/11066 [28:10<12:27,  4.51it/s]
 70%|██████▉   | 7697/11066 [28:11<12:27,  4.51it/s]
                                                    

 70%|██████▉   | 7697/11066 [28:11<12:27,  4.51it/s]
 70%|██████▉   | 7698/11066 [28:11<12:27,  4.51it/s]
                                                    

 70%|██████▉   | 7698/11066 [28:11<12:27,  4.51it/s]
 70%|██████▉   | 7699/11066 [28:11<12:27,  4.51it/s]
                                                    

 70%|██████▉   | 7699/11066 [28:11<12:27,  4.51it/s]
 70%|██████▉   | 7700/11066 [28:11<12:26,  4.51it/s]
                                                    

 70%|██████▉   | 7700/11066 [28:11<12:26,  4.51it/s]
 70%|██████▉   | 7701/11066 [28:12<12:26,  4.51it/s]
                                                    

 70%|██████▉   | 7701/11066 [28:12<12:26,  4.51it/s]
 70%|██████▉   | 7702/11066 [28:12<12:26,  4.51it/s]
                                                    

 70%|██████▉   | 7702/11066 [28:12<12:26,  4.51it/s]
 70%|██████▉   | 7703/11066 [28:12<12:26,  4.50it/s]
                                                    

 70%|██████▉   | 7703/11066 [28:12<12:26,  4.50it/s]
 70%|██████▉   | 7704/11066 [28:12<12:25,  4.51it/s]
                                                    

 70%|██████▉   | 7704/11066 [28:12<12:25,  4.51it/s]
 70%|██████▉   | 7705/11066 [28:12<12:25,  4.51it/s]
                                                    

 70%|██████▉   | 7705/11066 [28:12<12:25,  4.51it/s]
 70%|██████▉   | 7706/11066 [28:13<12:26,  4.50it/s]
                                                    

 70%|██████▉   | 7706/11066 [28:13<12:26,  4.50it/s]
 70%|██████▉   | 7707/11066 [28:13<12:25,  4.50it/s]
                                                    

 70%|██████▉   | 7707/11066 [28:13<12:25,  4.50it/s]
 70%|██████▉   | 7708/11066 [28:13<12:24,  4.51it/s]
                                                    

 70%|██████▉   | 7708/11066 [28:13<12:24,  4.51it/s]
 70%|██████▉   | 7709/11066 [28:13<12:24,  4.51it/s]
                                                    

 70%|██████▉   | 7709/11066 [28:13<12:24,  4.51it/s]
 70%|██████▉   | 7710/11066 [28:14<12:24,  4.51it/s]
                                                    

 70%|██████▉   | 7710/11066 [28:14<12:24,  4.51it/s]
 70%|██████▉   | 7711/11066 [28:14<12:24,  4.50it/s]
                                                    

 70%|██████▉   | 7711/11066 [28:14<12:24,  4.50it/s]
 70%|██████▉   | 7712/11066 [28:14<12:24,  4.51it/s]
                                                    

 70%|██████▉   | 7712/11066 [28:14<12:24,  4.51it/s]
 70%|██████▉   | 7713/11066 [28:14<12:23,  4.51it/s]
                                                    

 70%|██████▉   | 7713/11066 [28:14<12:23,  4.51it/s]
 70%|██████▉   | 7714/11066 [28:14<12:24,  4.51it/s]
                                                    

 70%|██████▉   | 7714/11066 [28:14<12:24,  4.51it/s]
 70%|██████▉   | 7715/11066 [28:15<12:23,  4.51it/s]
                                                    

 70%|██████▉   | 7715/11066 [28:15<12:23,  4.51it/s]
 70%|██████▉   | 7716/11066 [28:15<12:23,  4.51it/s]
                                                    

 70%|██████▉   | 7716/11066 [28:15<12:23,  4.51it/s]
 70%|██████▉   | 7717/11066 [28:15<12:23,  4.50it/s]
                                                    

 70%|██████▉   | 7717/11066 [28:15<12:23,  4.50it/s]
 70%|██████▉   | 7718/11066 [28:15<12:22,  4.51it/s]
                                                    

 70%|██████▉   | 7718/11066 [28:15<12:22,  4.51it/s]
 70%|██████▉   | 7719/11066 [28:16<12:23,  4.50it/s]
                                                    

 70%|██████▉   | 7719/11066 [28:16<12:23,  4.50it/s]
 70%|██████▉   | 7720/11066 [28:16<12:23,  4.50it/s]
                                                    

 70%|██████▉   | 7720/11066 [28:16<12:23,  4.50it/s]
 70%|██████▉   | 7721/11066 [28:16<12:22,  4.50it/s]
                                                    

 70%|██████▉   | 7721/11066 [28:16<12:22,  4.50it/s]
 70%|██████▉   | 7722/11066 [28:16<12:22,  4.50it/s]
                                                    

 70%|██████▉   | 7722/11066 [28:16<12:22,  4.50it/s]
 70%|██████▉   | 7723/11066 [28:16<12:23,  4.50it/s]
                                                    

 70%|██████▉   | 7723/11066 [28:16<12:23,  4.50it/s]
 70%|██████▉   | 7724/11066 [28:17<12:22,  4.50it/s]
                                                    

 70%|██████▉   | 7724/11066 [28:17<12:22,  4.50it/s]
 70%|██████▉   | 7725/11066 [28:17<12:22,  4.50it/s]
                                                    

 70%|██████▉   | 7725/11066 [28:17<12:22,  4.50it/s]
 70%|██████▉   | 7726/11066 [28:17<12:22,  4.50it/s]
                                                    

 70%|██████▉   | 7726/11066 [28:17<12:22,  4.50it/s]
 70%|██████▉   | 7727/11066 [28:17<12:21,  4.50it/s]
                                                    

 70%|██████▉   | 7727/11066 [28:17<12:21,  4.50it/s]
 70%|██████▉   | 7728/11066 [28:18<12:21,  4.50it/s]
                                                    

 70%|██████▉   | 7728/11066 [28:18<12:21,  4.50it/s]
 70%|██████▉   | 7729/11066 [28:18<12:20,  4.50it/s]
                                                    

 70%|██████▉   | 7729/11066 [28:18<12:20,  4.50it/s]
 70%|██████▉   | 7730/11066 [28:18<12:19,  4.51it/s]
                                                    

 70%|██████▉   | 7730/11066 [28:18<12:19,  4.51it/s]
 70%|██████▉   | 7731/11066 [28:18<12:20,  4.51it/s]
                                                    

 70%|██████▉   | 7731/11066 [28:18<12:20,  4.51it/s]
 70%|██████▉   | 7732/11066 [28:18<12:20,  4.50it/s]
                                                    

 70%|██████▉   | 7732/11066 [28:18<12:20,  4.50it/s]
 70%|██████▉   | 7733/11066 [28:19<12:20,  4.50it/s]
                                                    

 70%|██████▉   | 7733/11066 [28:19<12:20,  4.50it/s]
 70%|██████▉   | 7734/11066 [28:19<12:23,  4.48it/s]
                                                    

 70%|██████▉   | 7734/11066 [28:19<12:23,  4.48it/s]
 70%|██████▉   | 7735/11066 [28:19<12:25,  4.47it/s]
                                                    

 70%|██████▉   | 7735/11066 [28:19<12:25,  4.47it/s]
 70%|██████▉   | 7736/11066 [28:19<12:25,  4.47it/s]
                                                    

 70%|██████▉   | 7736/11066 [28:19<12:25,  4.47it/s]
 70%|██████▉   | 7737/11066 [28:20<12:24,  4.47it/s]
                                                    

 70%|██████▉   | 7737/11066 [28:20<12:24,  4.47it/s]
 70%|██████▉   | 7738/11066 [28:20<12:22,  4.48it/s]
                                                    

 70%|██████▉   | 7738/11066 [28:20<12:22,  4.48it/s]
 70%|██████▉   | 7739/11066 [28:20<12:21,  4.49it/s]
                                                    

 70%|██████▉   | 7739/11066 [28:20<12:21,  4.49it/s]
 70%|██████▉   | 7740/11066 [28:20<12:20,  4.49it/s]
                                                    

 70%|██████▉   | 7740/11066 [28:20<12:20,  4.49it/s]
 70%|██████▉   | 7741/11066 [28:20<12:19,  4.50it/s]
                                                    

 70%|██████▉   | 7741/11066 [28:20<12:19,  4.50it/s]
 70%|██████▉   | 7742/11066 [28:21<12:18,  4.50it/s]
                                                    

 70%|██████▉   | 7742/11066 [28:21<12:18,  4.50it/s]
 70%|██████▉   | 7743/11066 [28:21<12:17,  4.50it/s]
                                                    

 70%|██████▉   | 7743/11066 [28:21<12:17,  4.50it/s]
 70%|██████▉   | 7744/11066 [28:21<12:17,  4.51it/s]
                                                    

 70%|██████▉   | 7744/11066 [28:21<12:17,  4.51it/s]
 70%|██████▉   | 7745/11066 [28:21<12:17,  4.51it/s]
                                                    

 70%|██████▉   | 7745/11066 [28:21<12:17,  4.51it/s]
 70%|██████▉   | 7746/11066 [28:22<12:17,  4.50it/s]
                                                    

 70%|██████▉   | 7746/11066 [28:22<12:17,  4.50it/s]
 70%|███████   | 7747/11066 [28:22<12:18,  4.49it/s]
                                                    

 70%|███████   | 7747/11066 [28:22<12:18,  4.49it/s]
 70%|███████   | 7748/11066 [28:22<12:22,  4.47it/s]
                                                    

 70%|███████   | 7748/11066 [28:22<12:22,  4.47it/s]
 70%|███████   | 7749/11066 [28:22<12:22,  4.46it/s]
                                                    

 70%|███████   | 7749/11066 [28:22<12:22,  4.46it/s]
 70%|███████   | 7750/11066 [28:22<12:21,  4.47it/s]
                                                    

 70%|███████   | 7750/11066 [28:22<12:21,  4.47it/s]
 70%|███████   | 7751/11066 [28:23<12:19,  4.48it/s]
                                                    

 70%|███████   | 7751/11066 [28:23<12:19,  4.48it/s]
 70%|███████   | 7752/11066 [28:23<12:18,  4.49it/s]
                                                    

 70%|███████   | 7752/11066 [28:23<12:18,  4.49it/s]
 70%|███████   | 7753/11066 [28:23<12:16,  4.50it/s]
                                                    

 70%|███████   | 7753/11066 [28:23<12:16,  4.50it/s]
 70%|███████   | 7754/11066 [28:23<12:16,  4.50it/s]
                                                    

 70%|███████   | 7754/11066 [28:23<12:16,  4.50it/s]
 70%|███████   | 7755/11066 [28:24<12:15,  4.50it/s]
                                                    

 70%|███████   | 7755/11066 [28:24<12:15,  4.50it/s]
 70%|███████   | 7756/11066 [28:24<12:14,  4.50it/s]
                                                    

 70%|███████   | 7756/11066 [28:24<12:14,  4.50it/s]
 70%|███████   | 7757/11066 [28:24<12:14,  4.51it/s]
                                                    

 70%|███████   | 7757/11066 [28:24<12:14,  4.51it/s]
 70%|███████   | 7758/11066 [28:24<12:13,  4.51it/s]
                                                    

 70%|███████   | 7758/11066 [28:24<12:13,  4.51it/s]
 70%|███████   | 7759/11066 [28:24<12:13,  4.51it/s]
                                                    

 70%|███████   | 7759/11066 [28:24<12:13,  4.51it/s]
 70%|███████   | 7760/11066 [28:25<12:14,  4.50it/s]
                                                    

 70%|███████   | 7760/11066 [28:25<12:14,  4.50it/s]
 70%|███████   | 7761/11066 [28:25<12:14,  4.50it/s]
                                                    

 70%|███████   | 7761/11066 [28:25<12:14,  4.50it/s]
 70%|███████   | 7762/11066 [28:25<12:13,  4.50it/s]
                                                    

 70%|███████   | 7762/11066 [28:25<12:13,  4.50it/s]
 70%|███████   | 7763/11066 [28:25<12:13,  4.50it/s]
                                                    

 70%|███████   | 7763/11066 [28:25<12:13,  4.50it/s]
 70%|███████   | 7764/11066 [28:26<12:13,  4.50it/s]
                                                    

 70%|███████   | 7764/11066 [28:26<12:13,  4.50it/s]
 70%|███████   | 7765/11066 [28:26<12:12,  4.51it/s]
                                                    

 70%|███████   | 7765/11066 [28:26<12:12,  4.51it/s]
 70%|███████   | 7766/11066 [28:26<12:13,  4.50it/s]
                                                    
{'loss': 0.4098, 'learning_rate': 9.255376829929515e-06, 'epoch': 1.38}
{'loss': 0.5124, 'learning_rate': 9.252665823242365e-06, 'epoch': 1.38}
{'loss': 0.8236, 'learning_rate': 9.249954816555215e-06, 'epoch': 1.38}
{'loss': 0.4374, 'learning_rate': 9.247243809868063e-06, 'epoch': 1.38}
{'loss': 0.6336, 'learning_rate': 9.244532803180915e-06, 'epoch': 1.38}
{'loss': 1.0219, 'learning_rate': 9.241821796493765e-06, 'epoch': 1.38}
{'loss': 0.6245, 'learning_rate': 9.239110789806615e-06, 'epoch': 1.38}
{'loss': 0.5964, 'learning_rate': 9.236399783119465e-06, 'epoch': 1.38}
{'loss': 0.756, 'learning_rate': 9.233688776432316e-06, 'epoch': 1.38}
{'loss': 0.6138, 'learning_rate': 9.230977769745166e-06, 'epoch': 1.38}
{'loss': 0.9962, 'learning_rate': 9.228266763058016e-06, 'epoch': 1.38}
{'loss': 1.1396, 'learning_rate': 9.225555756370866e-06, 'epoch': 1.38}
{'loss': 0.2669, 'learning_rate': 9.222844749683716e-06, 'epoch': 1.39}
{'loss': 1.0401, 'learning_rate': 9.220133742996566e-06, 'epoch': 1.39}
{'loss': 0.5011, 'learning_rate': 9.217422736309416e-06, 'epoch': 1.39}
{'loss': 0.6607, 'learning_rate': 9.214711729622267e-06, 'epoch': 1.39}
{'loss': 0.8345, 'learning_rate': 9.212000722935117e-06, 'epoch': 1.39}
{'loss': 1.1276, 'learning_rate': 9.209289716247967e-06, 'epoch': 1.39}
{'loss': 0.4786, 'learning_rate': 9.206578709560819e-06, 'epoch': 1.39}
{'loss': 1.7071, 'learning_rate': 9.203867702873667e-06, 'epoch': 1.39}
{'loss': 1.0664, 'learning_rate': 9.201156696186517e-06, 'epoch': 1.39}
{'loss': 0.365, 'learning_rate': 9.198445689499367e-06, 'epoch': 1.39}
{'loss': 0.8267, 'learning_rate': 9.19573468281222e-06, 'epoch': 1.39}
{'loss': 0.8004, 'learning_rate': 9.193023676125068e-06, 'epoch': 1.39}
{'loss': 0.4534, 'learning_rate': 9.190312669437918e-06, 'epoch': 1.39}
{'loss': 0.538, 'learning_rate': 9.187601662750768e-06, 'epoch': 1.39}
{'loss': 1.1195, 'learning_rate': 9.18489065606362e-06, 'epoch': 1.39}
{'loss': 1.044, 'learning_rate': 9.182179649376468e-06, 'epoch': 1.39}
{'loss': 0.4678, 'learning_rate': 9.179468642689318e-06, 'epoch': 1.39}
{'loss': 0.5111, 'learning_rate': 9.17675763600217e-06, 'epoch': 1.39}
{'loss': 0.3776, 'learning_rate': 9.17404662931502e-06, 'epoch': 1.39}
{'loss': 1.3588, 'learning_rate': 9.171335622627869e-06, 'epoch': 1.39}
{'loss': 0.624, 'learning_rate': 9.168624615940719e-06, 'epoch': 1.39}
{'loss': 0.6591, 'learning_rate': 9.16591360925357e-06, 'epoch': 1.39}
{'loss': 1.5658, 'learning_rate': 9.16320260256642e-06, 'epoch': 1.39}
{'loss': 0.5702, 'learning_rate': 9.16049159587927e-06, 'epoch': 1.39}
{'loss': 0.7457, 'learning_rate': 9.15778058919212e-06, 'epoch': 1.39}
{'loss': 0.312, 'learning_rate': 9.155069582504971e-06, 'epoch': 1.39}
{'loss': 0.4547, 'learning_rate': 9.152358575817821e-06, 'epoch': 1.39}
{'loss': 0.5604, 'learning_rate': 9.14964756913067e-06, 'epoch': 1.39}
{'loss': 0.7341, 'learning_rate': 9.146936562443522e-06, 'epoch': 1.39}
{'loss': 0.8627, 'learning_rate': 9.144225555756372e-06, 'epoch': 1.39}
{'loss': 0.7394, 'learning_rate': 9.141514549069222e-06, 'epoch': 1.39}
{'loss': 0.577, 'learning_rate': 9.13880354238207e-06, 'epoch': 1.39}
{'loss': 0.5579, 'learning_rate': 9.136092535694922e-06, 'epoch': 1.39}
{'loss': 1.2796, 'learning_rate': 9.133381529007772e-06, 'epoch': 1.39}
{'loss': 0.5049, 'learning_rate': 9.130670522320622e-06, 'epoch': 1.39}
{'loss': 0.3448, 'learning_rate': 9.12795951563347e-06, 'epoch': 1.39}
{'loss': 0.5303, 'learning_rate': 9.125248508946323e-06, 'epoch': 1.39}
{'loss': 0.8504, 'learning_rate': 9.122537502259173e-06, 'epoch': 1.39}
{'loss': 0.8693, 'learning_rate': 9.119826495572023e-06, 'epoch': 1.39}
{'loss': 0.7966, 'learning_rate': 9.117115488884873e-06, 'epoch': 1.39}
{'loss': 0.7876, 'learning_rate': 9.114404482197723e-06, 'epoch': 1.39}
{'loss': 0.9455, 'learning_rate': 9.111693475510573e-06, 'epoch': 1.39}
{'loss': 0.46, 'learning_rate': 9.108982468823423e-06, 'epoch': 1.39}
{'loss': 1.2737, 'learning_rate': 9.106271462136274e-06, 'epoch': 1.39}
{'loss': 0.5929, 'learning_rate': 9.103560455449124e-06, 'epoch': 1.39}
{'loss': 0.9292, 'learning_rate': 9.100849448761974e-06, 'epoch': 1.39}
{'loss': 0.7327, 'learning_rate': 9.098138442074824e-06, 'epoch': 1.39}
{'loss': 0.3377, 'learning_rate': 9.095427435387674e-06, 'epoch': 1.39}
{'loss': 0.2392, 'learning_rate': 9.092716428700524e-06, 'epoch': 1.39}
{'loss': 1.267, 'learning_rate': 9.090005422013374e-06, 'epoch': 1.39}
{'loss': 0.9004, 'learning_rate': 9.087294415326226e-06, 'epoch': 1.39}
{'loss': 1.0837, 'learning_rate': 9.084583408639075e-06, 'epoch': 1.39}
{'loss': 0.6504, 'learning_rate': 9.081872401951925e-06, 'epoch': 1.39}
{'loss': 0.5802, 'learning_rate': 9.079161395264775e-06, 'epoch': 1.39}
{'loss': 0.8435, 'learning_rate': 9.076450388577627e-06, 'epoch': 1.39}
{'loss': 0.73, 'learning_rate': 9.073739381890475e-06, 'epoch': 1.4}
{'loss': 0.6607, 'learning_rate': 9.071028375203325e-06, 'epoch': 1.4}
{'loss': 0.3868, 'learning_rate': 9.068317368516175e-06, 'epoch': 1.4}
{'loss': 1.2318, 'learning_rate': 9.065606361829026e-06, 'epoch': 1.4}
{'loss': 0.4026, 'learning_rate': 9.062895355141876e-06, 'epoch': 1.4}
{'loss': 0.8977, 'learning_rate': 9.060184348454726e-06, 'epoch': 1.4}
{'loss': 1.2593, 'learning_rate': 9.057473341767578e-06, 'epoch': 1.4}
{'loss': 0.7869, 'learning_rate': 9.054762335080426e-06, 'epoch': 1.4}
{'loss': 0.5969, 'learning_rate': 9.052051328393276e-06, 'epoch': 1.4}
{'loss': 1.0934, 'learning_rate': 9.049340321706126e-06, 'epoch': 1.4}
{'loss': 0.7693, 'learning_rate': 9.046629315018978e-06, 'epoch': 1.4}
{'loss': 1.1636, 'learning_rate': 9.043918308331827e-06, 'epoch': 1.4}
{'loss': 0.6967, 'learning_rate': 9.041207301644677e-06, 'epoch': 1.4}
{'loss': 0.6274, 'learning_rate': 9.038496294957529e-06, 'epoch': 1.4}
{'loss': 0.6225, 'learning_rate': 9.035785288270379e-06, 'epoch': 1.4}
{'loss': 0.5823, 'learning_rate': 9.033074281583227e-06, 'epoch': 1.4}
{'loss': 0.4436, 'learning_rate': 9.030363274896077e-06, 'epoch': 1.4}
{'loss': 1.1646, 'learning_rate': 9.02765226820893e-06, 'epoch': 1.4}
{'loss': 0.5113, 'learning_rate': 9.02494126152178e-06, 'epoch': 1.4}
{'loss': 0.9221, 'learning_rate': 9.022230254834628e-06, 'epoch': 1.4}
{'loss': 1.4932, 'learning_rate': 9.019519248147478e-06, 'epoch': 1.4}
{'loss': 0.4017, 'learning_rate': 9.01680824146033e-06, 'epoch': 1.4}
{'loss': 0.7083, 'learning_rate': 9.01409723477318e-06, 'epoch': 1.4}
{'loss': 0.5244, 'learning_rate': 9.011386228086028e-06, 'epoch': 1.4}
{'loss': 0.5264, 'learning_rate': 9.00867522139888e-06, 'epoch': 1.4}
{'loss': 0.5224, 'learning_rate': 9.00596421471173e-06, 'epoch': 1.4}
{'loss': 0.5479, 'learning_rate': 9.00325320802458e-06, 'epoch': 1.4}
{'loss': 0.403, 'learning_rate': 9.000542201337429e-06, 'epoch': 1.4}
{'loss': 0.5372, 'learning_rate': 8.99783119465028e-06, 'epoch': 1.4}
{'loss': 0.5283, 'learning_rate': 8.99512018796313e-06, 'epoch': 1.4}
{'loss': 0.5517, 'learning_rate': 8.992409181275981e-06, 'epoch': 1.4}
{'loss': 0.4129, 'learning_rate': 8.98969817458883e-06, 'epoch': 1.4}
{'loss': 1.1471, 'learning_rate': 8.986987167901681e-06, 'epoch': 1.4}
{'loss': 0.6911, 'learning_rate': 8.984276161214531e-06, 'epoch': 1.4}
{'loss': 0.5543, 'learning_rate': 8.981565154527381e-06, 'epoch': 1.4}
{'loss': 0.9668, 'learning_rate': 8.978854147840232e-06, 'epoch': 1.4}
{'loss': 0.6657, 'learning_rate': 8.976143141153082e-06, 'epoch': 1.4}
{'loss': 0.4236, 'learning_rate': 8.973432134465932e-06, 'epoch': 1.4}
{'loss': 0.6293, 'learning_rate': 8.970721127778782e-06, 'epoch': 1.4}
{'loss': 0.8967, 'learning_rate': 8.968010121091632e-06, 'epoch': 1.4}
{'loss': 0.8678, 'learning_rate': 8.965299114404482e-06, 'epoch': 1.4}
{'loss': 0.3617, 'learning_rate': 8.962588107717332e-06, 'epoch': 1.4}
{'loss': 0.9478, 'learning_rate': 8.959877101030183e-06, 'epoch': 1.4}
{'loss': 0.876, 'learning_rate': 8.957166094343033e-06, 'epoch': 1.4}
{'loss': 1.255, 'learning_rate': 8.954455087655883e-06, 'epoch': 1.4}
{'loss': 0.3458, 'learning_rate': 8.951744080968733e-06, 'epoch': 1.4}
{'loss': 0.9163, 'learning_rate': 8.949033074281585e-06, 'epoch': 1.4}

 70%|███████   | 7766/11066 [28:26<12:13,  4.50it/s]
 70%|███████   | 7767/11066 [28:26<12:09,  4.52it/s]
                                                    

 70%|███████   | 7767/11066 [28:26<12:09,  4.52it/s]
 70%|███████   | 7768/11066 [28:26<12:10,  4.51it/s]
                                                    

 70%|███████   | 7768/11066 [28:26<12:10,  4.51it/s]
 70%|███████   | 7769/11066 [28:27<12:11,  4.50it/s]
                                                    

 70%|███████   | 7769/11066 [28:27<12:11,  4.50it/s]
 70%|███████   | 7770/11066 [28:27<12:11,  4.51it/s]
                                                    

 70%|███████   | 7770/11066 [28:27<12:11,  4.51it/s]
 70%|███████   | 7771/11066 [28:27<12:11,  4.51it/s]
                                                    

 70%|███████   | 7771/11066 [28:27<12:11,  4.51it/s]
 70%|███████   | 7772/11066 [28:27<12:11,  4.51it/s]
                                                    

 70%|███████   | 7772/11066 [28:27<12:11,  4.51it/s]
 70%|███████   | 7773/11066 [28:28<12:11,  4.50it/s]
                                                    

 70%|███████   | 7773/11066 [28:28<12:11,  4.50it/s]
 70%|███████   | 7774/11066 [28:28<12:11,  4.50it/s]
                                                    

 70%|███████   | 7774/11066 [28:28<12:11,  4.50it/s]
 70%|███████   | 7775/11066 [28:28<12:13,  4.49it/s]
                                                    

 70%|███████   | 7775/11066 [28:28<12:13,  4.49it/s]
 70%|███████   | 7776/11066 [28:28<12:15,  4.47it/s]
                                                    

 70%|███████   | 7776/11066 [28:28<12:15,  4.47it/s]
 70%|███████   | 7777/11066 [28:28<12:15,  4.47it/s]
                                                    

 70%|███████   | 7777/11066 [28:28<12:15,  4.47it/s]
 70%|███████   | 7778/11066 [28:29<12:14,  4.48it/s]
                                                    

 70%|███████   | 7778/11066 [28:29<12:14,  4.48it/s]
 70%|███████   | 7779/11066 [28:29<12:12,  4.49it/s]
                                                    

 70%|███████   | 7779/11066 [28:29<12:12,  4.49it/s]
 70%|███████   | 7780/11066 [28:29<12:11,  4.49it/s]
                                                    

 70%|███████   | 7780/11066 [28:29<12:11,  4.49it/s]
 70%|███████   | 7781/11066 [28:29<12:10,  4.50it/s]
                                                    

 70%|███████   | 7781/11066 [28:29<12:10,  4.50it/s]
 70%|███████   | 7782/11066 [28:30<12:09,  4.50it/s]
                                                    

 70%|███████   | 7782/11066 [28:30<12:09,  4.50it/s]
 70%|███████   | 7783/11066 [28:30<12:09,  4.50it/s]
                                                    

 70%|███████   | 7783/11066 [28:30<12:09,  4.50it/s]
 70%|███████   | 7784/11066 [28:30<12:09,  4.50it/s]
                                                    

 70%|███████   | 7784/11066 [28:30<12:09,  4.50it/s]
 70%|███████   | 7785/11066 [28:30<12:08,  4.51it/s]
                                                    

 70%|███████   | 7785/11066 [28:30<12:08,  4.51it/s]
 70%|███████   | 7786/11066 [28:30<12:08,  4.50it/s]
                                                    

 70%|███████   | 7786/11066 [28:30<12:08,  4.50it/s]
 70%|███████   | 7787/11066 [28:31<12:08,  4.50it/s]
                                                    

 70%|███████   | 7787/11066 [28:31<12:08,  4.50it/s]
 70%|███████   | 7788/11066 [28:31<12:25,  4.40it/s]
                                                    

 70%|███████   | 7788/11066 [28:31<12:25,  4.40it/s]
 70%|███████   | 7789/11066 [28:31<12:21,  4.42it/s]
                                                    

 70%|███████   | 7789/11066 [28:31<12:21,  4.42it/s]
 70%|███████   | 7790/11066 [28:31<12:18,  4.44it/s]
                                                    

 70%|███████   | 7790/11066 [28:31<12:18,  4.44it/s]
 70%|███████   | 7791/11066 [28:32<12:14,  4.46it/s]
                                                    

 70%|███████   | 7791/11066 [28:32<12:14,  4.46it/s]
 70%|███████   | 7792/11066 [28:32<12:11,  4.47it/s]
                                                    

 70%|███████   | 7792/11066 [28:32<12:11,  4.47it/s]
 70%|███████   | 7793/11066 [28:32<12:10,  4.48it/s]
                                                    

 70%|███████   | 7793/11066 [28:32<12:10,  4.48it/s]
 70%|███████   | 7794/11066 [28:32<12:08,  4.49it/s]
                                                    

 70%|███████   | 7794/11066 [28:32<12:08,  4.49it/s]
 70%|███████   | 7795/11066 [28:32<12:08,  4.49it/s]
                                                    

 70%|███████   | 7795/11066 [28:32<12:08,  4.49it/s]
 70%|███████   | 7796/11066 [28:33<12:08,  4.49it/s]
                                                    

 70%|███████   | 7796/11066 [28:33<12:08,  4.49it/s]
 70%|███████   | 7797/11066 [28:33<12:07,  4.49it/s]
                                                    

 70%|███████   | 7797/11066 [28:33<12:07,  4.49it/s]
 70%|███████   | 7798/11066 [28:33<12:06,  4.50it/s]
                                                    

 70%|███████   | 7798/11066 [28:33<12:06,  4.50it/s]
 70%|███████   | 7799/11066 [28:33<12:06,  4.50it/s]
                                                    

 70%|███████   | 7799/11066 [28:33<12:06,  4.50it/s]
 70%|███████   | 7800/11066 [28:34<12:06,  4.50it/s]
                                                    

 70%|███████   | 7800/11066 [28:34<12:06,  4.50it/s]
 70%|███████   | 7801/11066 [28:34<12:06,  4.49it/s]
                                                    

 70%|███████   | 7801/11066 [28:34<12:06,  4.49it/s]
 71%|███████   | 7802/11066 [28:34<12:08,  4.48it/s]
                                                    

 71%|███████   | 7802/11066 [28:34<12:08,  4.48it/s]
 71%|███████   | 7803/11066 [28:34<12:10,  4.47it/s]
                                                    

 71%|███████   | 7803/11066 [28:34<12:10,  4.47it/s]
 71%|███████   | 7804/11066 [28:34<12:10,  4.47it/s]
                                                    

 71%|███████   | 7804/11066 [28:34<12:10,  4.47it/s]
 71%|███████   | 7805/11066 [28:35<12:08,  4.48it/s]
                                                    

 71%|███████   | 7805/11066 [28:35<12:08,  4.48it/s]
 71%|███████   | 7806/11066 [28:35<12:01,  4.52it/s]
                                                    

 71%|███████   | 7806/11066 [28:35<12:01,  4.52it/s]
 71%|███████   | 7807/11066 [28:35<12:05,  4.49it/s]
                                                    

 71%|███████   | 7807/11066 [28:35<12:05,  4.49it/s]
 71%|███████   | 7808/11066 [28:35<12:05,  4.49it/s]
                                                    

 71%|███████   | 7808/11066 [28:35<12:05,  4.49it/s]
 71%|███████   | 7809/11066 [28:36<12:05,  4.49it/s]
                                                    

 71%|███████   | 7809/11066 [28:36<12:05,  4.49it/s]
 71%|███████   | 7810/11066 [28:36<11:56,  4.55it/s]
                                                    

 71%|███████   | 7810/11066 [28:36<11:56,  4.55it/s]
 71%|███████   | 7811/11066 [28:36<11:52,  4.57it/s]
                                                    

 71%|███████   | 7811/11066 [28:36<11:52,  4.57it/s]
 71%|███████   | 7812/11066 [28:36<11:48,  4.59it/s]
                                                    

 71%|███████   | 7812/11066 [28:36<11:48,  4.59it/s]
 71%|███████   | 7813/11066 [28:36<11:47,  4.60it/s]
                                                    

 71%|███████   | 7813/11066 [28:36<11:47,  4.60it/s]
 71%|███████   | 7814/11066 [28:37<12:00,  4.51it/s]
                                                    

 71%|███████   | 7814/11066 [28:37<12:00,  4.51it/s]
 71%|███████   | 7815/11066 [28:37<12:06,  4.48it/s]
                                                    

 71%|███████   | 7815/11066 [28:37<12:06,  4.48it/s]
 71%|███████   | 7816/11066 [28:37<12:05,  4.48it/s]
                                                    

 71%|███████   | 7816/11066 [28:37<12:05,  4.48it/s]
 71%|███████   | 7817/11066 [28:37<11:54,  4.55it/s]
                                                    

 71%|███████   | 7817/11066 [28:37<11:54,  4.55it/s]
 71%|███████   | 7818/11066 [28:38<11:51,  4.57it/s]
                                                    

 71%|███████   | 7818/11066 [28:38<11:51,  4.57it/s]
 71%|███████   | 7819/11066 [28:38<11:53,  4.55it/s]
                                                    

 71%|███████   | 7819/11066 [28:38<11:53,  4.55it/s]
 71%|███████   | 7820/11066 [28:38<11:52,  4.56it/s]
                                                    

 71%|███████   | 7820/11066 [28:38<11:52,  4.56it/s]
 71%|███████   | 7821/11066 [28:38<11:55,  4.53it/s]
                                                    

 71%|███████   | 7821/11066 [28:38<11:55,  4.53it/s]
 71%|███████   | 7822/11066 [28:38<11:46,  4.59it/s]
                                                    

 71%|███████   | 7822/11066 [28:38<11:46,  4.59it/s]
 71%|███████   | 7823/11066 [28:39<11:41,  4.62it/s]
                                                    

 71%|███████   | 7823/11066 [28:39<11:41,  4.62it/s]
 71%|███████   | 7824/11066 [28:39<11:50,  4.57it/s]
                                                    

 71%|███████   | 7824/11066 [28:39<11:50,  4.57it/s]
 71%|███████   | 7825/11066 [28:39<11:54,  4.54it/s]
                                                    

 71%|███████   | 7825/11066 [28:39<11:54,  4.54it/s]
 71%|███████   | 7826/11066 [28:39<11:51,  4.55it/s]
                                                    

 71%|███████   | 7826/11066 [28:39<11:51,  4.55it/s]
 71%|███████   | 7827/11066 [28:40<11:55,  4.53it/s]
                                                    

 71%|███████   | 7827/11066 [28:40<11:55,  4.53it/s]
 71%|███████   | 7828/11066 [28:40<11:59,  4.50it/s]
                                                    

 71%|███████   | 7828/11066 [28:40<11:59,  4.50it/s]
 71%|███████   | 7829/11066 [28:40<11:53,  4.53it/s]
                                                    

 71%|███████   | 7829/11066 [28:40<11:53,  4.53it/s]
 71%|███████   | 7830/11066 [28:40<11:58,  4.50it/s]
                                                    

 71%|███████   | 7830/11066 [28:40<11:58,  4.50it/s]
 71%|███████   | 7831/11066 [28:40<11:54,  4.53it/s]
                                                    

 71%|███████   | 7831/11066 [28:40<11:54,  4.53it/s]
 71%|███████   | 7832/11066 [28:41<11:58,  4.50it/s]
                                                    

 71%|███████   | 7832/11066 [28:41<11:58,  4.50it/s]
 71%|███████   | 7833/11066 [28:41<11:54,  4.53it/s]
                                                    

 71%|███████   | 7833/11066 [28:41<11:54,  4.53it/s]
 71%|███████   | 7834/11066 [28:41<11:51,  4.54it/s]
                                                    

 71%|███████   | 7834/11066 [28:41<11:51,  4.54it/s]
 71%|███████   | 7835/11066 [28:41<11:53,  4.53it/s]
                                                    

 71%|███████   | 7835/11066 [28:41<11:53,  4.53it/s]
 71%|███████   | 7836/11066 [28:42<11:54,  4.52it/s]
                                                    

 71%|███████   | 7836/11066 [28:42<11:54,  4.52it/s]
 71%|███████   | 7837/11066 [28:42<11:49,  4.55it/s]
                                                    

 71%|███████   | 7837/11066 [28:42<11:49,  4.55it/s]
 71%|███████   | 7838/11066 [28:42<11:44,  4.58it/s]
                                                    

 71%|███████   | 7838/11066 [28:42<11:44,  4.58it/s]
 71%|███████   | 7839/11066 [28:42<11:49,  4.55it/s]
                                                    

 71%|███████   | 7839/11066 [28:42<11:49,  4.55it/s]
 71%|███████   | 7840/11066 [28:42<11:45,  4.57it/s]
                                                    

 71%|███████   | 7840/11066 [28:42<11:45,  4.57it/s]
 71%|███████   | 7841/11066 [28:43<11:40,  4.60it/s]
                                                    

 71%|███████   | 7841/11066 [28:43<11:40,  4.60it/s]
 71%|███████   | 7842/11066 [28:43<11:49,  4.55it/s]
                                                    

 71%|███████   | 7842/11066 [28:43<11:49,  4.55it/s]
 71%|███████   | 7843/11066 [28:43<11:52,  4.52it/s]
                                                    

 71%|███████   | 7843/11066 [28:43<11:52,  4.52it/s]
 71%|███████   | 7844/11066 [28:43<11:53,  4.52it/s]
                                                    

 71%|███████   | 7844/11066 [28:43<11:53,  4.52it/s]
 71%|███████   | 7845/11066 [28:44<11:54,  4.51it/s]
                                                    

 71%|███████   | 7845/11066 [28:44<11:54,  4.51it/s]
 71%|███████   | 7846/11066 [28:44<11:56,  4.50it/s]
                                                    

 71%|███████   | 7846/11066 [28:44<11:56,  4.50it/s]
 71%|███████   | 7847/11066 [28:44<11:59,  4.47it/s]
                                                    

 71%|███████   | 7847/11066 [28:44<11:59,  4.47it/s]
 71%|███████   | 7848/11066 [28:44<11:59,  4.47it/s]
                                                    

 71%|███████   | 7848/11066 [28:44<11:59,  4.47it/s]
 71%|███████   | 7849/11066 [28:44<11:54,  4.50it/s]
                                                    

 71%|███████   | 7849/11066 [28:44<11:54,  4.50it/s]
 71%|███████   | 7850/11066 [28:45<11:56,  4.49it/s]
                                                    

 71%|███████   | 7850/11066 [28:45<11:56,  4.49it/s]
 71%|███████   | 7851/11066 [28:45<11:57,  4.48it/s]
                                                    

 71%|███████   | 7851/11066 [28:45<11:57,  4.48it/s]
 71%|███████   | 7852/11066 [28:45<11:55,  4.49it/s]
                                                    

 71%|███████   | 7852/11066 [28:45<11:55,  4.49it/s]
 71%|███████   | 7853/11066 [28:45<11:45,  4.55it/s]
                                                    

 71%|███████   | 7853/11066 [28:45<11:45,  4.55it/s]
 71%|███████   | 7854/11066 [28:46<11:47,  4.54it/s]
                                                    

 71%|███████   | 7854/11066 [28:46<11:47,  4.54it/s]
 71%|███████   | 7855/11066 [28:46<11:38,  4.59it/s]
                                                    

 71%|███████   | 7855/11066 [28:46<11:38,  4.59it/s]
 71%|███████   | 7856/11066 [28:46<11:46,  4.54it/s]
                                                    

 71%|███████   | 7856/11066 [28:46<11:46,  4.54it/s]
 71%|███████   | 7857/11066 [28:46<11:42,  4.57it/s]
                                                    

 71%|███████   | 7857/11066 [28:46<11:42,  4.57it/s]
 71%|███████   | 7858/11066 [28:46<11:46,  4.54it/s]
                                                    

 71%|███████   | 7858/11066 [28:46<11:46,  4.54it/s]
 71%|███████   | 7859/11066 [28:47<11:39,  4.59it/s]
                                                    

 71%|███████   | 7859/11066 [28:47<11:39,  4.59it/s]
 71%|███████   | 7860/11066 [28:47<11:47,  4.53it/s]
                                                    

 71%|███████   | 7860/11066 [28:47<11:47,  4.53it/s]
 71%|███████   | 7861/11066 [28:47<11:58,  4.46it/s]
                                                    

 71%|███████   | 7861/11066 [28:47<11:58,  4.46it/s]
 71%|███████   | 7862/11066 [28:47<11:56,  4.47it/s]
                                                    

 71%|███████   | 7862/11066 [28:47<11:56,  4.47it/s]
 71%|███████   | 7863/11066 [28:48<11:57,  4.46it/s]
                                                    

 71%|███████   | 7863/11066 [28:48<11:57,  4.46it/s]
 71%|███████   | 7864/11066 [28:48<11:57,  4.46it/s]
                                                    

 71%|███████   | 7864/11066 [28:48<11:57,  4.46it/s]
 71%|███████   | 7865/11066 [28:48<11:55,  4.48it/s]
                                                    

 71%|███████   | 7865/11066 [28:48<11:55,  4.48it/s]
 71%|███████   | 7866/11066 [28:48<11:44,  4.54it/s]
                                                    

 71%|███████   | 7866/11066 [28:48<11:44,  4.54it/s]
 71%|███████   | 7867/11066 [28:48<11:42,  4.56it/s]
                                                    

 71%|███████   | 7867/11066 [28:48<11:42,  4.56it/s]
 71%|███████   | 7868/11066 [28:49<11:46,  4.53it/s]
                                                    

 71%|███████   | 7868/11066 [28:49<11:46,  4.53it/s]
 71%|███████   | 7869/11066 [28:49<11:49,  4.51it/s]
                                                    

 71%|███████   | 7869/11066 [28:49<11:49,  4.51it/s]
 71%|███████   | 7870/11066 [28:49<11:49,  4.50it/s]
                                                    

 71%|███████   | 7870/11066 [28:49<11:49,  4.50it/s]
 71%|███████   | 7871/11066 [28:49<11:43,  4.54it/s]
                                                    

 71%|███████   | 7871/11066 [28:49<11:43,  4.54it/s]
 71%|███████   | 7872/11066 [28:50<11:48,  4.51it/s]
                                                    

 71%|███████   | 7872/11066 [28:50<11:48,  4.51it/s]
 71%|███████   | 7873/11066 [28:50<11:44,  4.53it/s]
                                                    

 71%|███████   | 7873/11066 [28:50<11:44,  4.53it/s]
 71%|███████   | 7874/11066 [28:50<11:38,  4.57it/s]
                                                    

 71%|███████   | 7874/11066 [28:50<11:38,  4.57it/s]
 71%|███████   | 7875/11066 [28:50<11:31,  4.61it/s]
                                                    

 71%|███████   | 7875/11066 [28:50<11:31,  4.61it/s]
 71%|███████   | 7876/11066 [28:50<11:38,  4.57it/s]
                                                    

 71%|███████   | 7876/11066 [28:50<11:38,  4.57it/s]
 71%|███████   | 7877/11066 [28:51<11:43,  4.54it/s]
                                                    

 71%|███████   | 7877/11066 [28:51<11:43,  4.54it/s]
 71%|███████   | 7878/11066 [28:51<11:55,  4.45it/s]
                                                    

 71%|███████   | 7878/11066 [28:51<11:55,  4.45it/s]
 71%|███████   | 7879/11066 [28:51<11:48,  4.50it/s]
                                                    

 71%|███████   | 7879/11066 [28:51<11:48,  4.50it/s]
 71%|███████   | 7880/11066 [28:51<11:50,  4.48it/s]
                                                    
{'loss': 1.0375, 'learning_rate': 8.946322067594433e-06, 'epoch': 1.4}
{'loss': 0.8946, 'learning_rate': 8.943611060907283e-06, 'epoch': 1.4}
{'loss': 0.8386, 'learning_rate': 8.940900054220133e-06, 'epoch': 1.4}
{'loss': 0.9836, 'learning_rate': 8.938189047532985e-06, 'epoch': 1.4}
{'loss': 0.4832, 'learning_rate': 8.935478040845834e-06, 'epoch': 1.4}
{'loss': 0.7125, 'learning_rate': 8.932767034158684e-06, 'epoch': 1.4}
{'loss': 1.3593, 'learning_rate': 8.930056027471534e-06, 'epoch': 1.4}
{'loss': 1.0481, 'learning_rate': 8.927345020784386e-06, 'epoch': 1.4}
{'loss': 1.456, 'learning_rate': 8.924634014097234e-06, 'epoch': 1.41}
{'loss': 0.9012, 'learning_rate': 8.921923007410084e-06, 'epoch': 1.41}
{'loss': 0.3924, 'learning_rate': 8.919212000722936e-06, 'epoch': 1.41}
{'loss': 0.7306, 'learning_rate': 8.916500994035786e-06, 'epoch': 1.41}
{'loss': 0.432, 'learning_rate': 8.913789987348635e-06, 'epoch': 1.41}
{'loss': 0.363, 'learning_rate': 8.911078980661485e-06, 'epoch': 1.41}
{'loss': 0.5297, 'learning_rate': 8.908367973974337e-06, 'epoch': 1.41}
{'loss': 0.8151, 'learning_rate': 8.905656967287187e-06, 'epoch': 1.41}
{'loss': 0.5638, 'learning_rate': 8.902945960600035e-06, 'epoch': 1.41}
{'loss': 1.2914, 'learning_rate': 8.900234953912886e-06, 'epoch': 1.41}
{'loss': 1.2291, 'learning_rate': 8.897523947225737e-06, 'epoch': 1.41}
{'loss': 0.8737, 'learning_rate': 8.894812940538587e-06, 'epoch': 1.41}
{'loss': 0.5395, 'learning_rate': 8.892101933851436e-06, 'epoch': 1.41}
{'loss': 0.954, 'learning_rate': 8.889390927164288e-06, 'epoch': 1.41}
{'loss': 0.562, 'learning_rate': 8.886679920477138e-06, 'epoch': 1.41}
{'loss': 0.6874, 'learning_rate': 8.883968913789988e-06, 'epoch': 1.41}
{'loss': 0.5032, 'learning_rate': 8.881257907102836e-06, 'epoch': 1.41}
{'loss': 1.0768, 'learning_rate': 8.878546900415688e-06, 'epoch': 1.41}
{'loss': 0.8397, 'learning_rate': 8.875835893728538e-06, 'epoch': 1.41}
{'loss': 1.0808, 'learning_rate': 8.873124887041389e-06, 'epoch': 1.41}
{'loss': 0.5349, 'learning_rate': 8.870413880354239e-06, 'epoch': 1.41}
{'loss': 1.1304, 'learning_rate': 8.867702873667089e-06, 'epoch': 1.41}
{'loss': 0.9149, 'learning_rate': 8.864991866979939e-06, 'epoch': 1.41}
{'loss': 0.7405, 'learning_rate': 8.862280860292789e-06, 'epoch': 1.41}
{'loss': 0.6289, 'learning_rate': 8.85956985360564e-06, 'epoch': 1.41}
{'loss': 0.9836, 'learning_rate': 8.85685884691849e-06, 'epoch': 1.41}
{'loss': 0.7687, 'learning_rate': 8.85414784023134e-06, 'epoch': 1.41}
{'loss': 0.8629, 'learning_rate': 8.85143683354419e-06, 'epoch': 1.41}
{'loss': 1.2765, 'learning_rate': 8.84872582685704e-06, 'epoch': 1.41}
{'loss': 0.7252, 'learning_rate': 8.84601482016989e-06, 'epoch': 1.41}
{'loss': 0.925, 'learning_rate': 8.84330381348274e-06, 'epoch': 1.41}
{'loss': 0.9136, 'learning_rate': 8.840592806795592e-06, 'epoch': 1.41}
{'loss': 0.7345, 'learning_rate': 8.83788180010844e-06, 'epoch': 1.41}
{'loss': 0.9217, 'learning_rate': 8.83517079342129e-06, 'epoch': 1.41}
{'loss': 0.828, 'learning_rate': 8.83245978673414e-06, 'epoch': 1.41}
{'loss': 0.9363, 'learning_rate': 8.829748780046992e-06, 'epoch': 1.41}
{'loss': 0.5302, 'learning_rate': 8.82703777335984e-06, 'epoch': 1.41}
{'loss': 0.7068, 'learning_rate': 8.824326766672691e-06, 'epoch': 1.41}
{'loss': 0.9144, 'learning_rate': 8.821615759985541e-06, 'epoch': 1.41}
{'loss': 0.6725, 'learning_rate': 8.818904753298393e-06, 'epoch': 1.41}
{'loss': 1.1948, 'learning_rate': 8.816193746611241e-06, 'epoch': 1.41}
{'loss': 0.67, 'learning_rate': 8.813482739924091e-06, 'epoch': 1.41}
{'loss': 1.1126, 'learning_rate': 8.810771733236943e-06, 'epoch': 1.41}
{'loss': 1.1886, 'learning_rate': 8.808060726549793e-06, 'epoch': 1.41}
{'loss': 0.4952, 'learning_rate': 8.805349719862642e-06, 'epoch': 1.41}
{'loss': 1.0208, 'learning_rate': 8.802638713175492e-06, 'epoch': 1.41}
{'loss': 0.2873, 'learning_rate': 8.799927706488344e-06, 'epoch': 1.41}
{'loss': 0.5679, 'learning_rate': 8.797216699801194e-06, 'epoch': 1.41}
{'loss': 0.5376, 'learning_rate': 8.794505693114042e-06, 'epoch': 1.41}
{'loss': 0.8961, 'learning_rate': 8.791794686426893e-06, 'epoch': 1.41}
{'loss': 0.5476, 'learning_rate': 8.789083679739744e-06, 'epoch': 1.41}
{'loss': 0.8635, 'learning_rate': 8.786372673052595e-06, 'epoch': 1.41}
{'loss': 0.7549, 'learning_rate': 8.783661666365443e-06, 'epoch': 1.41}
{'loss': 0.7098, 'learning_rate': 8.780950659678295e-06, 'epoch': 1.41}
{'loss': 0.7573, 'learning_rate': 8.778239652991145e-06, 'epoch': 1.41}
{'loss': 0.6885, 'learning_rate': 8.775528646303995e-06, 'epoch': 1.41}
{'loss': 0.4197, 'learning_rate': 8.772817639616844e-06, 'epoch': 1.42}
{'loss': 0.6567, 'learning_rate': 8.770106632929695e-06, 'epoch': 1.42}
{'loss': 1.0112, 'learning_rate': 8.767395626242545e-06, 'epoch': 1.42}
{'loss': 0.6069, 'learning_rate': 8.764684619555396e-06, 'epoch': 1.42}
{'loss': 1.1824, 'learning_rate': 8.761973612868244e-06, 'epoch': 1.42}
{'loss': 0.4564, 'learning_rate': 8.759262606181096e-06, 'epoch': 1.42}
{'loss': 0.8652, 'learning_rate': 8.756551599493946e-06, 'epoch': 1.42}
{'loss': 1.0299, 'learning_rate': 8.753840592806796e-06, 'epoch': 1.42}
{'loss': 0.9172, 'learning_rate': 8.751129586119646e-06, 'epoch': 1.42}
{'loss': 0.6413, 'learning_rate': 8.748418579432496e-06, 'epoch': 1.42}
{'loss': 0.6046, 'learning_rate': 8.745707572745347e-06, 'epoch': 1.42}
{'loss': 0.8188, 'learning_rate': 8.742996566058197e-06, 'epoch': 1.42}
{'loss': 0.989, 'learning_rate': 8.740285559371047e-06, 'epoch': 1.42}
{'loss': 0.5213, 'learning_rate': 8.737574552683897e-06, 'epoch': 1.42}
{'loss': 0.983, 'learning_rate': 8.734863545996747e-06, 'epoch': 1.42}
{'loss': 0.6833, 'learning_rate': 8.732152539309597e-06, 'epoch': 1.42}
{'loss': 0.9982, 'learning_rate': 8.729441532622447e-06, 'epoch': 1.42}
{'loss': 0.6018, 'learning_rate': 8.726730525935297e-06, 'epoch': 1.42}
{'loss': 0.5743, 'learning_rate': 8.724019519248148e-06, 'epoch': 1.42}
{'loss': 1.1385, 'learning_rate': 8.721308512561e-06, 'epoch': 1.42}
{'loss': 0.3802, 'learning_rate': 8.718597505873848e-06, 'epoch': 1.42}
{'loss': 0.78, 'learning_rate': 8.715886499186698e-06, 'epoch': 1.42}
{'loss': 0.5517, 'learning_rate': 8.713175492499548e-06, 'epoch': 1.42}
{'loss': 0.8821, 'learning_rate': 8.710464485812398e-06, 'epoch': 1.42}
{'loss': 0.867, 'learning_rate': 8.707753479125248e-06, 'epoch': 1.42}
{'loss': 0.6641, 'learning_rate': 8.705042472438099e-06, 'epoch': 1.42}
{'loss': 0.6496, 'learning_rate': 8.702331465750949e-06, 'epoch': 1.42}
{'loss': 0.494, 'learning_rate': 8.699620459063799e-06, 'epoch': 1.42}
{'loss': 0.3421, 'learning_rate': 8.696909452376649e-06, 'epoch': 1.42}
{'loss': 0.5273, 'learning_rate': 8.694198445689499e-06, 'epoch': 1.42}
{'loss': 0.512, 'learning_rate': 8.691487439002351e-06, 'epoch': 1.42}
{'loss': 0.8923, 'learning_rate': 8.6887764323152e-06, 'epoch': 1.42}
{'loss': 0.4999, 'learning_rate': 8.68606542562805e-06, 'epoch': 1.42}
{'loss': 0.5448, 'learning_rate': 8.6833544189409e-06, 'epoch': 1.42}
{'loss': 0.6772, 'learning_rate': 8.680643412253751e-06, 'epoch': 1.42}
{'loss': 0.8443, 'learning_rate': 8.6779324055666e-06, 'epoch': 1.42}
{'loss': 1.1802, 'learning_rate': 8.67522139887945e-06, 'epoch': 1.42}
{'loss': 1.0471, 'learning_rate': 8.6725103921923e-06, 'epoch': 1.42}
{'loss': 0.9145, 'learning_rate': 8.669799385505152e-06, 'epoch': 1.42}
{'loss': 0.4264, 'learning_rate': 8.667088378818e-06, 'epoch': 1.42}
{'loss': 0.7708, 'learning_rate': 8.66437737213085e-06, 'epoch': 1.42}
{'loss': 0.7625, 'learning_rate': 8.661666365443702e-06, 'epoch': 1.42}
{'loss': 0.6051, 'learning_rate': 8.658955358756553e-06, 'epoch': 1.42}
{'loss': 1.2892, 'learning_rate': 8.656244352069401e-06, 'epoch': 1.42}
{'loss': 0.717, 'learning_rate': 8.653533345382251e-06, 'epoch': 1.42}
{'loss': 0.6504, 'learning_rate': 8.650822338695103e-06, 'epoch': 1.42}
{'loss': 0.6169, 'learning_rate': 8.648111332007953e-06, 'epoch': 1.42}
{'loss': 0.7496, 'learning_rate': 8.645400325320802e-06, 'epoch': 1.42}
{'loss': 0.7396, 'learning_rate': 8.642689318633653e-06, 'epoch': 1.42}
{'loss': 1.1832, 'learning_rate': 8.639978311946503e-06, 'epoch': 1.42}

 71%|███████   | 7880/11066 [28:51<11:50,  4.48it/s]
 71%|███████   | 7881/11066 [28:51<11:50,  4.48it/s]
                                                    

 71%|███████   | 7881/11066 [28:51<11:50,  4.48it/s]
 71%|███████   | 7882/11066 [28:52<11:50,  4.48it/s]
                                                    

 71%|███████   | 7882/11066 [28:52<11:50,  4.48it/s]
 71%|███████   | 7883/11066 [28:52<11:55,  4.45it/s]
                                                    

 71%|███████   | 7883/11066 [28:52<11:55,  4.45it/s]
 71%|███████   | 7884/11066 [28:52<11:55,  4.45it/s]
                                                    

 71%|███████   | 7884/11066 [28:52<11:55,  4.45it/s]
 71%|███████▏  | 7885/11066 [28:52<11:53,  4.46it/s]
                                                    

 71%|███████▏  | 7885/11066 [28:52<11:53,  4.46it/s]
 71%|███████▏  | 7886/11066 [28:53<11:52,  4.47it/s]
                                                    

 71%|███████▏  | 7886/11066 [28:53<11:52,  4.47it/s]
 71%|███████▏  | 7887/11066 [28:53<11:51,  4.47it/s]
                                                    

 71%|███████▏  | 7887/11066 [28:53<11:51,  4.47it/s]
 71%|███████▏  | 7888/11066 [28:53<11:51,  4.47it/s]
                                                    

 71%|███████▏  | 7888/11066 [28:53<11:51,  4.47it/s]
 71%|███████▏  | 7889/11066 [28:53<11:50,  4.47it/s]
                                                    

 71%|███████▏  | 7889/11066 [28:53<11:50,  4.47it/s]
 71%|███████▏  | 7890/11066 [28:54<11:48,  4.48it/s]
                                                    

 71%|███████▏  | 7890/11066 [28:54<11:48,  4.48it/s]
 71%|███████▏  | 7891/11066 [28:54<11:47,  4.48it/s]
                                                    

 71%|███████▏  | 7891/11066 [28:54<11:47,  4.48it/s]
 71%|███████▏  | 7892/11066 [28:54<11:47,  4.48it/s]
                                                    

 71%|███████▏  | 7892/11066 [28:54<11:47,  4.48it/s]
 71%|███████▏  | 7893/11066 [28:54<11:46,  4.49it/s]
                                                    

 71%|███████▏  | 7893/11066 [28:54<11:46,  4.49it/s]
 71%|███████▏  | 7894/11066 [28:54<11:46,  4.49it/s]
                                                    

 71%|███████▏  | 7894/11066 [28:54<11:46,  4.49it/s]
 71%|███████▏  | 7895/11066 [28:55<11:46,  4.49it/s]
                                                    

 71%|███████▏  | 7895/11066 [28:55<11:46,  4.49it/s]
 71%|███████▏  | 7896/11066 [28:55<11:33,  4.57it/s]
                                                    

 71%|███████▏  | 7896/11066 [28:55<11:33,  4.57it/s]
 71%|███████▏  | 7897/11066 [28:55<11:34,  4.57it/s]
                                                    

 71%|███████▏  | 7897/11066 [28:55<11:34,  4.57it/s]
 71%|███████▏  | 7898/11066 [28:55<11:33,  4.57it/s]
                                                    

 71%|███████▏  | 7898/11066 [28:55<11:33,  4.57it/s]
 71%|███████▏  | 7899/11066 [28:55<11:37,  4.54it/s]
                                                    

 71%|███████▏  | 7899/11066 [28:55<11:37,  4.54it/s]
 71%|███████▏  | 7900/11066 [28:56<11:39,  4.52it/s]
                                                    

 71%|███████▏  | 7900/11066 [28:56<11:39,  4.52it/s]
 71%|███████▏  | 7901/11066 [28:56<11:41,  4.51it/s]
                                                    

 71%|███████▏  | 7901/11066 [28:56<11:41,  4.51it/s]
 71%|███████▏  | 7902/11066 [28:56<11:36,  4.54it/s]
                                                    

 71%|███████▏  | 7902/11066 [28:56<11:36,  4.54it/s]
 71%|███████▏  | 7903/11066 [28:56<11:30,  4.58it/s]
                                                    

 71%|███████▏  | 7903/11066 [28:56<11:30,  4.58it/s]
 71%|███████▏  | 7904/11066 [28:57<11:36,  4.54it/s]
                                                    

 71%|███████▏  | 7904/11066 [28:57<11:36,  4.54it/s]
 71%|███████▏  | 7905/11066 [28:57<11:34,  4.55it/s]
                                                    

 71%|███████▏  | 7905/11066 [28:57<11:34,  4.55it/s]
 71%|███████▏  | 7906/11066 [28:57<11:28,  4.59it/s]
                                                    

 71%|███████▏  | 7906/11066 [28:57<11:28,  4.59it/s]
 71%|███████▏  | 7907/11066 [28:57<11:34,  4.55it/s]
                                                    

 71%|███████▏  | 7907/11066 [28:57<11:34,  4.55it/s]
 71%|███████▏  | 7908/11066 [28:57<11:38,  4.52it/s]
                                                    

 71%|███████▏  | 7908/11066 [28:57<11:38,  4.52it/s]
 71%|███████▏  | 7909/11066 [28:58<11:35,  4.54it/s]
                                                    

 71%|███████▏  | 7909/11066 [28:58<11:35,  4.54it/s]
 71%|███████▏  | 7910/11066 [28:58<11:37,  4.53it/s]
                                                    

 71%|███████▏  | 7910/11066 [28:58<11:37,  4.53it/s]
 71%|███████▏  | 7911/11066 [28:58<11:40,  4.50it/s]
                                                    

 71%|███████▏  | 7911/11066 [28:58<11:40,  4.50it/s]
 71%|███████▏  | 7912/11066 [28:58<11:35,  4.53it/s]
                                                    

 71%|███████▏  | 7912/11066 [28:58<11:35,  4.53it/s]
 72%|███████▏  | 7913/11066 [28:59<11:39,  4.51it/s]
                                                    

 72%|███████▏  | 7913/11066 [28:59<11:39,  4.51it/s]
 72%|███████▏  | 7914/11066 [28:59<11:41,  4.49it/s]
                                                    

 72%|███████▏  | 7914/11066 [28:59<11:41,  4.49it/s]
 72%|███████▏  | 7915/11066 [28:59<11:33,  4.54it/s]
                                                    

 72%|███████▏  | 7915/11066 [28:59<11:33,  4.54it/s]
 72%|███████▏  | 7916/11066 [28:59<11:34,  4.53it/s]
                                                    

 72%|███████▏  | 7916/11066 [28:59<11:34,  4.53it/s]
 72%|███████▏  | 7917/11066 [28:59<11:35,  4.53it/s]
                                                    

 72%|███████▏  | 7917/11066 [28:59<11:35,  4.53it/s]
 72%|███████▏  | 7918/11066 [29:00<11:30,  4.56it/s]
                                                    

 72%|███████▏  | 7918/11066 [29:00<11:30,  4.56it/s]
 72%|███████▏  | 7919/11066 [29:00<11:31,  4.55it/s]
                                                    

 72%|███████▏  | 7919/11066 [29:00<11:31,  4.55it/s]
 72%|███████▏  | 7920/11066 [29:00<11:28,  4.57it/s]
                                                    

 72%|███████▏  | 7920/11066 [29:00<11:28,  4.57it/s]
 72%|███████▏  | 7921/11066 [29:00<11:32,  4.54it/s]
                                                    

 72%|███████▏  | 7921/11066 [29:00<11:32,  4.54it/s]
 72%|███████▏  | 7922/11066 [29:01<11:33,  4.53it/s]
                                                    

 72%|███████▏  | 7922/11066 [29:01<11:33,  4.53it/s]
 72%|███████▏  | 7923/11066 [29:01<11:35,  4.52it/s]
                                                    

 72%|███████▏  | 7923/11066 [29:01<11:35,  4.52it/s]
 72%|███████▏  | 7924/11066 [29:01<11:36,  4.51it/s]
                                                    

 72%|███████▏  | 7924/11066 [29:01<11:36,  4.51it/s]
 72%|███████▏  | 7925/11066 [29:01<11:38,  4.50it/s]
                                                    

 72%|███████▏  | 7925/11066 [29:01<11:38,  4.50it/s]
 72%|███████▏  | 7926/11066 [29:01<11:41,  4.47it/s]
                                                    

 72%|███████▏  | 7926/11066 [29:01<11:41,  4.47it/s]
 72%|███████▏  | 7927/11066 [29:02<11:41,  4.47it/s]
                                                    

 72%|███████▏  | 7927/11066 [29:02<11:41,  4.47it/s]
 72%|███████▏  | 7928/11066 [29:02<11:41,  4.47it/s]
                                                    

 72%|███████▏  | 7928/11066 [29:02<11:41,  4.47it/s]
 72%|███████▏  | 7929/11066 [29:02<11:40,  4.48it/s]
                                                    

 72%|███████▏  | 7929/11066 [29:02<11:40,  4.48it/s]
 72%|███████▏  | 7930/11066 [29:02<11:39,  4.49it/s]
                                                    

 72%|███████▏  | 7930/11066 [29:02<11:39,  4.49it/s]
 72%|███████▏  | 7931/11066 [29:03<11:37,  4.49it/s]
                                                    

 72%|███████▏  | 7931/11066 [29:03<11:37,  4.49it/s]
 72%|███████▏  | 7932/11066 [29:03<11:36,  4.50it/s]
                                                    

 72%|███████▏  | 7932/11066 [29:03<11:36,  4.50it/s]
 72%|███████▏  | 7933/11066 [29:03<11:36,  4.50it/s]
                                                    

 72%|███████▏  | 7933/11066 [29:03<11:36,  4.50it/s]
 72%|███████▏  | 7934/11066 [29:03<11:36,  4.50it/s]
                                                    

 72%|███████▏  | 7934/11066 [29:03<11:36,  4.50it/s]
 72%|███████▏  | 7935/11066 [29:03<11:35,  4.50it/s]
                                                    

 72%|███████▏  | 7935/11066 [29:03<11:35,  4.50it/s]
 72%|███████▏  | 7936/11066 [29:04<11:35,  4.50it/s]
                                                    

 72%|███████▏  | 7936/11066 [29:04<11:35,  4.50it/s]
 72%|███████▏  | 7937/11066 [29:04<11:27,  4.55it/s]
                                                    

 72%|███████▏  | 7937/11066 [29:04<11:27,  4.55it/s]
 72%|███████▏  | 7938/11066 [29:04<11:18,  4.61it/s]
                                                    

 72%|███████▏  | 7938/11066 [29:04<11:18,  4.61it/s]
 72%|███████▏  | 7939/11066 [29:04<11:15,  4.63it/s]
                                                    

 72%|███████▏  | 7939/11066 [29:04<11:15,  4.63it/s]
 72%|███████▏  | 7940/11066 [29:05<11:12,  4.65it/s]
                                                    

 72%|███████▏  | 7940/11066 [29:05<11:12,  4.65it/s]
 72%|███████▏  | 7941/11066 [29:05<11:06,  4.69it/s]
                                                    

 72%|███████▏  | 7941/11066 [29:05<11:06,  4.69it/s]
 72%|███████▏  | 7942/11066 [29:05<11:05,  4.69it/s]
                                                    

 72%|███████▏  | 7942/11066 [29:05<11:05,  4.69it/s]
 72%|███████▏  | 7943/11066 [29:05<11:13,  4.64it/s]
                                                    

 72%|███████▏  | 7943/11066 [29:05<11:13,  4.64it/s]
 72%|███████▏  | 7944/11066 [29:05<11:14,  4.63it/s]
                                                    

 72%|███████▏  | 7944/11066 [29:05<11:14,  4.63it/s]
 72%|███████▏  | 7945/11066 [29:06<11:07,  4.68it/s]
                                                    

 72%|███████▏  | 7945/11066 [29:06<11:07,  4.68it/s]
 72%|███████▏  | 7946/11066 [29:06<11:14,  4.62it/s]
                                                    

 72%|███████▏  | 7946/11066 [29:06<11:14,  4.62it/s]
 72%|███████▏  | 7947/11066 [29:06<11:21,  4.58it/s]
                                                    

 72%|███████▏  | 7947/11066 [29:06<11:21,  4.58it/s]
 72%|███████▏  | 7948/11066 [29:06<11:24,  4.55it/s]
                                                    

 72%|███████▏  | 7948/11066 [29:06<11:24,  4.55it/s]
 72%|███████▏  | 7949/11066 [29:06<11:21,  4.57it/s]
                                                    

 72%|███████▏  | 7949/11066 [29:06<11:21,  4.57it/s]
 72%|███████▏  | 7950/11066 [29:07<11:20,  4.58it/s]
                                                    

 72%|███████▏  | 7950/11066 [29:07<11:20,  4.58it/s]
 72%|███████▏  | 7951/11066 [29:07<11:25,  4.54it/s]
                                                    

 72%|███████▏  | 7951/11066 [29:07<11:25,  4.54it/s]
 72%|███████▏  | 7952/11066 [29:07<11:22,  4.56it/s]
                                                    

 72%|███████▏  | 7952/11066 [29:07<11:22,  4.56it/s]
 72%|███████▏  | 7953/11066 [29:07<11:18,  4.59it/s]
                                                    

 72%|███████▏  | 7953/11066 [29:07<11:18,  4.59it/s]
 72%|███████▏  | 7954/11066 [29:08<11:18,  4.59it/s]
                                                    

 72%|███████▏  | 7954/11066 [29:08<11:18,  4.59it/s]
 72%|███████▏  | 7955/11066 [29:08<11:13,  4.62it/s]
                                                    

 72%|███████▏  | 7955/11066 [29:08<11:13,  4.62it/s]
 72%|███████▏  | 7956/11066 [29:08<11:16,  4.60it/s]
                                                    

 72%|███████▏  | 7956/11066 [29:08<11:16,  4.60it/s]
 72%|███████▏  | 7957/11066 [29:08<11:19,  4.57it/s]
                                                    

 72%|███████▏  | 7957/11066 [29:08<11:19,  4.57it/s]
 72%|███████▏  | 7958/11066 [29:08<11:18,  4.58it/s]
                                                    

 72%|███████▏  | 7958/11066 [29:08<11:18,  4.58it/s]
 72%|███████▏  | 7959/11066 [29:09<11:19,  4.57it/s]
                                                    

 72%|███████▏  | 7959/11066 [29:09<11:19,  4.57it/s]
 72%|███████▏  | 7960/11066 [29:09<11:23,  4.54it/s]
                                                    

 72%|███████▏  | 7960/11066 [29:09<11:23,  4.54it/s]
 72%|███████▏  | 7961/11066 [29:09<11:20,  4.56it/s]
                                                    

 72%|███████▏  | 7961/11066 [29:09<11:20,  4.56it/s]
 72%|███████▏  | 7962/11066 [29:09<11:17,  4.58it/s]
                                                    

 72%|███████▏  | 7962/11066 [29:09<11:17,  4.58it/s]
 72%|███████▏  | 7963/11066 [29:10<11:16,  4.59it/s]
                                                    

 72%|███████▏  | 7963/11066 [29:10<11:16,  4.59it/s]
 72%|███████▏  | 7964/11066 [29:10<11:11,  4.62it/s]
                                                    

 72%|███████▏  | 7964/11066 [29:10<11:11,  4.62it/s]
 72%|███████▏  | 7965/11066 [29:10<11:15,  4.59it/s]
                                                    

 72%|███████▏  | 7965/11066 [29:10<11:15,  4.59it/s]
 72%|███████▏  | 7966/11066 [29:10<11:11,  4.61it/s]
                                                    

 72%|███████▏  | 7966/11066 [29:10<11:11,  4.61it/s]
 72%|███████▏  | 7967/11066 [29:10<11:09,  4.63it/s]
                                                    

 72%|███████▏  | 7967/11066 [29:10<11:09,  4.63it/s]
 72%|███████▏  | 7968/11066 [29:11<11:08,  4.64it/s]
                                                    

 72%|███████▏  | 7968/11066 [29:11<11:08,  4.64it/s]
 72%|███████▏  | 7969/11066 [29:11<11:14,  4.59it/s]
                                                    

 72%|███████▏  | 7969/11066 [29:11<11:14,  4.59it/s]
 72%|███████▏  | 7970/11066 [29:11<11:13,  4.60it/s]
                                                    

 72%|███████▏  | 7970/11066 [29:11<11:13,  4.60it/s]
 72%|███████▏  | 7971/11066 [29:11<11:13,  4.60it/s]
                                                    

 72%|███████▏  | 7971/11066 [29:11<11:13,  4.60it/s]
 72%|███████▏  | 7972/11066 [29:11<11:13,  4.59it/s]
                                                    

 72%|███████▏  | 7972/11066 [29:11<11:13,  4.59it/s]
 72%|███████▏  | 7973/11066 [29:12<11:08,  4.62it/s]
                                                    

 72%|███████▏  | 7973/11066 [29:12<11:08,  4.62it/s]
 72%|███████▏  | 7974/11066 [29:12<11:14,  4.58it/s]
                                                    

 72%|███████▏  | 7974/11066 [29:12<11:14,  4.58it/s]
 72%|███████▏  | 7975/11066 [29:12<11:17,  4.56it/s]
                                                    

 72%|███████▏  | 7975/11066 [29:12<11:17,  4.56it/s]
 72%|███████▏  | 7976/11066 [29:12<11:20,  4.54it/s]
                                                    

 72%|███████▏  | 7976/11066 [29:12<11:20,  4.54it/s]
 72%|███████▏  | 7977/11066 [29:13<11:22,  4.53it/s]
                                                    

 72%|███████▏  | 7977/11066 [29:13<11:22,  4.53it/s]
 72%|███████▏  | 7978/11066 [29:13<11:13,  4.58it/s]
                                                    

 72%|███████▏  | 7978/11066 [29:13<11:13,  4.58it/s]
 72%|███████▏  | 7979/11066 [29:13<11:11,  4.59it/s]
                                                    

 72%|███████▏  | 7979/11066 [29:13<11:11,  4.59it/s]
 72%|███████▏  | 7980/11066 [29:13<11:19,  4.54it/s]
                                                    

 72%|███████▏  | 7980/11066 [29:13<11:19,  4.54it/s]
 72%|███████▏  | 7981/11066 [29:13<11:32,  4.46it/s]
                                                    

 72%|███████▏  | 7981/11066 [29:13<11:32,  4.46it/s]
 72%|███████▏  | 7982/11066 [29:14<11:31,  4.46it/s]
                                                    

 72%|███████▏  | 7982/11066 [29:14<11:31,  4.46it/s]
 72%|███████▏  | 7983/11066 [29:14<11:24,  4.50it/s]
                                                    

 72%|███████▏  | 7983/11066 [29:14<11:24,  4.50it/s]
 72%|███████▏  | 7984/11066 [29:14<11:30,  4.46it/s]
                                                    

 72%|███████▏  | 7984/11066 [29:14<11:30,  4.46it/s]
 72%|███████▏  | 7985/11066 [29:14<11:23,  4.51it/s]
                                                    

 72%|███████▏  | 7985/11066 [29:14<11:23,  4.51it/s]
 72%|███████▏  | 7986/11066 [29:15<11:20,  4.53it/s]
                                                    

 72%|███████▏  | 7986/11066 [29:15<11:20,  4.53it/s]
 72%|███████▏  | 7987/11066 [29:15<11:21,  4.52it/s]
                                                    

 72%|███████▏  | 7987/11066 [29:15<11:21,  4.52it/s]
 72%|███████▏  | 7988/11066 [29:15<11:17,  4.54it/s]
                                                    

 72%|███████▏  | 7988/11066 [29:15<11:17,  4.54it/s]
 72%|███████▏  | 7989/11066 [29:15<11:11,  4.58it/s]
                                                    

 72%|███████▏  | 7989/11066 [29:15<11:11,  4.58it/s]
 72%|███████▏  | 7990/11066 [29:15<11:11,  4.58it/s]
                                                    

 72%|███████▏  | 7990/11066 [29:15<11:11,  4.58it/s]
 72%|███████▏  | 7991/11066 [29:16<11:07,  4.61it/s]
                                                    

 72%|███████▏  | 7991/11066 [29:16<11:07,  4.61it/s]
 72%|███████▏  | 7992/11066 [29:16<11:10,  4.58it/s]
                                                    

 72%|███████▏  | 7992/11066 [29:16<11:10,  4.58it/s]
 72%|███████▏  | 7993/11066 [29:16<11:09,  4.59it/s]
                                                    

 72%|███████▏  | 7993/11066 [29:16<11:09,  4.59it/s]
 72%|███████▏  | 7994/11066 [29:16<11:06,  4.61it/s]
                                                    
{'loss': 0.7687, 'learning_rate': 8.637267305259354e-06, 'epoch': 1.42}
{'loss': 0.5185, 'learning_rate': 8.634556298572202e-06, 'epoch': 1.42}
{'loss': 0.4892, 'learning_rate': 8.631845291885054e-06, 'epoch': 1.42}
{'loss': 0.9252, 'learning_rate': 8.629134285197904e-06, 'epoch': 1.42}
{'loss': 1.0747, 'learning_rate': 8.626423278510754e-06, 'epoch': 1.42}
{'loss': 0.4029, 'learning_rate': 8.623712271823603e-06, 'epoch': 1.43}
{'loss': 1.1343, 'learning_rate': 8.621001265136454e-06, 'epoch': 1.43}
{'loss': 0.882, 'learning_rate': 8.618290258449305e-06, 'epoch': 1.43}
{'loss': 0.7702, 'learning_rate': 8.615579251762155e-06, 'epoch': 1.43}
{'loss': 0.7618, 'learning_rate': 8.612868245075005e-06, 'epoch': 1.43}
{'loss': 0.7589, 'learning_rate': 8.610157238387855e-06, 'epoch': 1.43}
{'loss': 0.6345, 'learning_rate': 8.607446231700705e-06, 'epoch': 1.43}
{'loss': 1.9347, 'learning_rate': 8.604735225013555e-06, 'epoch': 1.43}
{'loss': 0.5055, 'learning_rate': 8.602024218326405e-06, 'epoch': 1.43}
{'loss': 0.5183, 'learning_rate': 8.599313211639255e-06, 'epoch': 1.43}
{'loss': 0.8486, 'learning_rate': 8.596602204952106e-06, 'epoch': 1.43}
{'loss': 0.7643, 'learning_rate': 8.593891198264956e-06, 'epoch': 1.43}
{'loss': 0.9265, 'learning_rate': 8.591180191577806e-06, 'epoch': 1.43}
{'loss': 0.7024, 'learning_rate': 8.588469184890656e-06, 'epoch': 1.43}
{'loss': 1.0878, 'learning_rate': 8.585758178203506e-06, 'epoch': 1.43}
{'loss': 0.4413, 'learning_rate': 8.583047171516358e-06, 'epoch': 1.43}
{'loss': 0.6243, 'learning_rate': 8.580336164829206e-06, 'epoch': 1.43}
{'loss': 1.1599, 'learning_rate': 8.577625158142057e-06, 'epoch': 1.43}
{'loss': 0.5533, 'learning_rate': 8.574914151454907e-06, 'epoch': 1.43}
{'loss': 0.9817, 'learning_rate': 8.572203144767759e-06, 'epoch': 1.43}
{'loss': 0.4128, 'learning_rate': 8.569492138080607e-06, 'epoch': 1.43}
{'loss': 0.5666, 'learning_rate': 8.566781131393457e-06, 'epoch': 1.43}
{'loss': 0.5893, 'learning_rate': 8.564070124706307e-06, 'epoch': 1.43}
{'loss': 0.6555, 'learning_rate': 8.561359118019159e-06, 'epoch': 1.43}
{'loss': 0.9207, 'learning_rate': 8.558648111332008e-06, 'epoch': 1.43}
{'loss': 0.7565, 'learning_rate': 8.555937104644858e-06, 'epoch': 1.43}
{'loss': 0.9737, 'learning_rate': 8.55322609795771e-06, 'epoch': 1.43}
{'loss': 0.7928, 'learning_rate': 8.55051509127056e-06, 'epoch': 1.43}
{'loss': 0.5413, 'learning_rate': 8.547804084583408e-06, 'epoch': 1.43}
{'loss': 0.5051, 'learning_rate': 8.545093077896258e-06, 'epoch': 1.43}
{'loss': 1.0011, 'learning_rate': 8.54238207120911e-06, 'epoch': 1.43}
{'loss': 0.4157, 'learning_rate': 8.53967106452196e-06, 'epoch': 1.43}
{'loss': 0.883, 'learning_rate': 8.536960057834809e-06, 'epoch': 1.43}
{'loss': 0.3563, 'learning_rate': 8.534249051147659e-06, 'epoch': 1.43}
{'loss': 0.8108, 'learning_rate': 8.53153804446051e-06, 'epoch': 1.43}
{'loss': 0.6694, 'learning_rate': 8.52882703777336e-06, 'epoch': 1.43}
{'loss': 0.7477, 'learning_rate': 8.526116031086209e-06, 'epoch': 1.43}
{'loss': 0.7262, 'learning_rate': 8.523405024399061e-06, 'epoch': 1.43}
{'loss': 1.0015, 'learning_rate': 8.520694017711911e-06, 'epoch': 1.43}
{'loss': 0.7528, 'learning_rate': 8.517983011024761e-06, 'epoch': 1.43}
{'loss': 0.5466, 'learning_rate': 8.51527200433761e-06, 'epoch': 1.43}
{'loss': 0.6371, 'learning_rate': 8.512560997650461e-06, 'epoch': 1.43}
{'loss': 0.8153, 'learning_rate': 8.509849990963312e-06, 'epoch': 1.43}
{'loss': 0.3913, 'learning_rate': 8.507138984276162e-06, 'epoch': 1.43}
{'loss': 0.2268, 'learning_rate': 8.50442797758901e-06, 'epoch': 1.43}
{'loss': 0.9791, 'learning_rate': 8.501716970901862e-06, 'epoch': 1.43}
{'loss': 0.5287, 'learning_rate': 8.499005964214712e-06, 'epoch': 1.43}
{'loss': 0.383, 'learning_rate': 8.496294957527562e-06, 'epoch': 1.43}
{'loss': 1.348, 'learning_rate': 8.493583950840412e-06, 'epoch': 1.43}
{'loss': 0.4886, 'learning_rate': 8.490872944153263e-06, 'epoch': 1.43}
{'loss': 1.3195, 'learning_rate': 8.488161937466113e-06, 'epoch': 1.43}
{'loss': 0.6721, 'learning_rate': 8.485450930778963e-06, 'epoch': 1.43}
{'loss': 0.9531, 'learning_rate': 8.482739924091813e-06, 'epoch': 1.43}
{'loss': 0.5794, 'learning_rate': 8.480028917404663e-06, 'epoch': 1.43}
{'loss': 0.5709, 'learning_rate': 8.477317910717513e-06, 'epoch': 1.43}
{'loss': 0.2856, 'learning_rate': 8.474606904030363e-06, 'epoch': 1.44}
{'loss': 0.4421, 'learning_rate': 8.471895897343213e-06, 'epoch': 1.44}
{'loss': 0.9459, 'learning_rate': 8.469184890656064e-06, 'epoch': 1.44}
{'loss': 0.5614, 'learning_rate': 8.466473883968914e-06, 'epoch': 1.44}
{'loss': 0.4854, 'learning_rate': 8.463762877281766e-06, 'epoch': 1.44}
{'loss': 0.9023, 'learning_rate': 8.461051870594614e-06, 'epoch': 1.44}
{'loss': 1.1129, 'learning_rate': 8.458340863907464e-06, 'epoch': 1.44}
{'loss': 0.7425, 'learning_rate': 8.455629857220314e-06, 'epoch': 1.44}
{'loss': 1.661, 'learning_rate': 8.452918850533166e-06, 'epoch': 1.44}
{'loss': 0.7432, 'learning_rate': 8.450207843846015e-06, 'epoch': 1.44}
{'loss': 0.3599, 'learning_rate': 8.447496837158865e-06, 'epoch': 1.44}
{'loss': 0.3183, 'learning_rate': 8.444785830471717e-06, 'epoch': 1.44}
{'loss': 1.0078, 'learning_rate': 8.442074823784567e-06, 'epoch': 1.44}
{'loss': 0.4438, 'learning_rate': 8.439363817097415e-06, 'epoch': 1.44}
{'loss': 0.7385, 'learning_rate': 8.436652810410265e-06, 'epoch': 1.44}
{'loss': 0.5553, 'learning_rate': 8.433941803723117e-06, 'epoch': 1.44}
{'loss': 0.8928, 'learning_rate': 8.431230797035967e-06, 'epoch': 1.44}
{'loss': 1.4796, 'learning_rate': 8.428519790348816e-06, 'epoch': 1.44}
{'loss': 0.6722, 'learning_rate': 8.425808783661666e-06, 'epoch': 1.44}
{'loss': 0.9029, 'learning_rate': 8.423097776974518e-06, 'epoch': 1.44}
{'loss': 1.0676, 'learning_rate': 8.420386770287368e-06, 'epoch': 1.44}
{'loss': 1.1192, 'learning_rate': 8.417675763600216e-06, 'epoch': 1.44}
{'loss': 0.7194, 'learning_rate': 8.414964756913068e-06, 'epoch': 1.44}
{'loss': 0.7491, 'learning_rate': 8.412253750225918e-06, 'epoch': 1.44}
{'loss': 0.2499, 'learning_rate': 8.409542743538768e-06, 'epoch': 1.44}
{'loss': 0.6886, 'learning_rate': 8.406831736851617e-06, 'epoch': 1.44}
{'loss': 0.4873, 'learning_rate': 8.404120730164469e-06, 'epoch': 1.44}
{'loss': 0.903, 'learning_rate': 8.401409723477319e-06, 'epoch': 1.44}
{'loss': 0.25, 'learning_rate': 8.398698716790169e-06, 'epoch': 1.44}
{'loss': 0.7368, 'learning_rate': 8.395987710103017e-06, 'epoch': 1.44}
{'loss': 0.8572, 'learning_rate': 8.393276703415869e-06, 'epoch': 1.44}
{'loss': 0.6121, 'learning_rate': 8.39056569672872e-06, 'epoch': 1.44}
{'loss': 0.9512, 'learning_rate': 8.38785469004157e-06, 'epoch': 1.44}
{'loss': 0.7775, 'learning_rate': 8.38514368335442e-06, 'epoch': 1.44}
{'loss': 0.6394, 'learning_rate': 8.38243267666727e-06, 'epoch': 1.44}
{'loss': 0.4587, 'learning_rate': 8.37972166998012e-06, 'epoch': 1.44}
{'loss': 0.6746, 'learning_rate': 8.37701066329297e-06, 'epoch': 1.44}
{'loss': 1.1504, 'learning_rate': 8.37429965660582e-06, 'epoch': 1.44}
{'loss': 0.5547, 'learning_rate': 8.37158864991867e-06, 'epoch': 1.44}
{'loss': 1.2446, 'learning_rate': 8.36887764323152e-06, 'epoch': 1.44}
{'loss': 0.8101, 'learning_rate': 8.366166636544369e-06, 'epoch': 1.44}
{'loss': 0.9884, 'learning_rate': 8.36345562985722e-06, 'epoch': 1.44}
{'loss': 0.2551, 'learning_rate': 8.36074462317007e-06, 'epoch': 1.44}
{'loss': 1.1404, 'learning_rate': 8.35803361648292e-06, 'epoch': 1.44}
{'loss': 0.9342, 'learning_rate': 8.355322609795771e-06, 'epoch': 1.44}
{'loss': 0.8623, 'learning_rate': 8.352611603108621e-06, 'epoch': 1.44}
{'loss': 0.8029, 'learning_rate': 8.349900596421471e-06, 'epoch': 1.44}
{'loss': 0.6882, 'learning_rate': 8.347189589734321e-06, 'epoch': 1.44}
{'loss': 1.022, 'learning_rate': 8.344478583047172e-06, 'epoch': 1.44}
{'loss': 0.6312, 'learning_rate': 8.341767576360022e-06, 'epoch': 1.44}
{'loss': 0.9081, 'learning_rate': 8.339056569672872e-06, 'epoch': 1.44}
{'loss': 1.1878, 'learning_rate': 8.336345562985722e-06, 'epoch': 1.44}
{'loss': 0.7175, 'learning_rate': 8.333634556298572e-06, 'epoch': 1.44}
{'loss': 0.6466, 'learning_rate': 8.330923549611422e-06, 'epoch': 1.44}

 72%|███████▏  | 7994/11066 [29:16<11:06,  4.61it/s]
 72%|███████▏  | 7995/11066 [29:17<11:12,  4.56it/s]
                                                    

 72%|███████▏  | 7995/11066 [29:17<11:12,  4.56it/s]
 72%|███████▏  | 7996/11066 [29:17<11:07,  4.60it/s]
                                                    

 72%|███████▏  | 7996/11066 [29:17<11:07,  4.60it/s]
 72%|███████▏  | 7997/11066 [29:17<11:12,  4.56it/s]
                                                    

 72%|███████▏  | 7997/11066 [29:17<11:12,  4.56it/s]
 72%|███████▏  | 7998/11066 [29:17<11:15,  4.54it/s]
                                                    

 72%|███████▏  | 7998/11066 [29:17<11:15,  4.54it/s]
 72%|███████▏  | 7999/11066 [29:17<11:17,  4.53it/s]
                                                    

 72%|███████▏  | 7999/11066 [29:17<11:17,  4.53it/s]
 72%|███████▏  | 8000/11066 [29:18<11:19,  4.51it/s]
                                                    

 72%|███████▏  | 8000/11066 [29:18<11:19,  4.51it/s]
 72%|███████▏  | 8001/11066 [29:18<11:20,  4.50it/s]
                                                    

 72%|███████▏  | 8001/11066 [29:18<11:20,  4.50it/s]
 72%|███████▏  | 8002/11066 [29:18<11:15,  4.53it/s]
                                                    

 72%|███████▏  | 8002/11066 [29:18<11:15,  4.53it/s]
 72%|███████▏  | 8003/11066 [29:18<11:08,  4.58it/s]
                                                    

 72%|███████▏  | 8003/11066 [29:18<11:08,  4.58it/s]
 72%|███████▏  | 8004/11066 [29:19<11:10,  4.57it/s]
                                                    

 72%|███████▏  | 8004/11066 [29:19<11:10,  4.57it/s]
 72%|███████▏  | 8005/11066 [29:19<11:14,  4.54it/s]
                                                    

 72%|███████▏  | 8005/11066 [29:19<11:14,  4.54it/s]
 72%|███████▏  | 8006/11066 [29:19<11:11,  4.56it/s]
                                                    

 72%|███████▏  | 8006/11066 [29:19<11:11,  4.56it/s]
 72%|███████▏  | 8007/11066 [29:19<11:14,  4.53it/s]
                                                    

 72%|███████▏  | 8007/11066 [29:19<11:14,  4.53it/s]
 72%|███████▏  | 8008/11066 [29:19<11:10,  4.56it/s]
                                                    

 72%|███████▏  | 8008/11066 [29:19<11:10,  4.56it/s]
 72%|███████▏  | 8009/11066 [29:20<11:07,  4.58it/s]
                                                    

 72%|███████▏  | 8009/11066 [29:20<11:07,  4.58it/s]
 72%|███████▏  | 8010/11066 [29:20<11:11,  4.55it/s]
                                                    

 72%|███████▏  | 8010/11066 [29:20<11:11,  4.55it/s]
 72%|███████▏  | 8011/11066 [29:20<11:14,  4.53it/s]
                                                    

 72%|███████▏  | 8011/11066 [29:20<11:14,  4.53it/s]
 72%|███████▏  | 8012/11066 [29:20<11:13,  4.53it/s]
                                                    

 72%|███████▏  | 8012/11066 [29:20<11:13,  4.53it/s]
 72%|███████▏  | 8013/11066 [29:21<11:16,  4.51it/s]
                                                    

 72%|███████▏  | 8013/11066 [29:21<11:16,  4.51it/s]
 72%|███████▏  | 8014/11066 [29:21<11:18,  4.50it/s]
                                                    

 72%|███████▏  | 8014/11066 [29:21<11:18,  4.50it/s]
 72%|███████▏  | 8015/11066 [29:21<11:14,  4.53it/s]
                                                    

 72%|███████▏  | 8015/11066 [29:21<11:14,  4.53it/s]
 72%|███████▏  | 8016/11066 [29:21<11:11,  4.54it/s]
                                                    

 72%|███████▏  | 8016/11066 [29:21<11:11,  4.54it/s]
 72%|███████▏  | 8017/11066 [29:21<11:08,  4.56it/s]
                                                    

 72%|███████▏  | 8017/11066 [29:21<11:08,  4.56it/s]
 72%|███████▏  | 8018/11066 [29:22<11:02,  4.60it/s]
                                                    

 72%|███████▏  | 8018/11066 [29:22<11:02,  4.60it/s]
 72%|███████▏  | 8019/11066 [29:22<11:04,  4.59it/s]
                                                    

 72%|███████▏  | 8019/11066 [29:22<11:04,  4.59it/s]
 72%|███████▏  | 8020/11066 [29:22<11:08,  4.56it/s]
                                                    

 72%|███████▏  | 8020/11066 [29:22<11:08,  4.56it/s]
 72%|███████▏  | 8021/11066 [29:22<11:03,  4.59it/s]
                                                    

 72%|███████▏  | 8021/11066 [29:22<11:03,  4.59it/s]
 72%|███████▏  | 8022/11066 [29:22<11:00,  4.61it/s]
                                                    

 72%|███████▏  | 8022/11066 [29:22<11:00,  4.61it/s]
 73%|███████▎  | 8023/11066 [29:23<11:06,  4.56it/s]
                                                    

 73%|███████▎  | 8023/11066 [29:23<11:06,  4.56it/s]
 73%|███████▎  | 8024/11066 [29:23<11:04,  4.58it/s]
                                                    

 73%|███████▎  | 8024/11066 [29:23<11:04,  4.58it/s]
 73%|███████▎  | 8025/11066 [29:23<11:00,  4.60it/s]
                                                    

 73%|███████▎  | 8025/11066 [29:23<11:00,  4.60it/s]
 73%|███████▎  | 8026/11066 [29:23<11:00,  4.60it/s]
                                                    

 73%|███████▎  | 8026/11066 [29:23<11:00,  4.60it/s]
 73%|███████▎  | 8027/11066 [29:24<10:55,  4.64it/s]
                                                    

 73%|███████▎  | 8027/11066 [29:24<10:55,  4.64it/s]
 73%|███████▎  | 8028/11066 [29:24<10:52,  4.66it/s]
                                                    

 73%|███████▎  | 8028/11066 [29:24<10:52,  4.66it/s]
 73%|███████▎  | 8029/11066 [29:24<10:58,  4.61it/s]
                                                    

 73%|███████▎  | 8029/11066 [29:24<10:58,  4.61it/s]
 73%|███████▎  | 8030/11066 [29:24<11:03,  4.58it/s]
                                                    

 73%|███████▎  | 8030/11066 [29:24<11:03,  4.58it/s]
 73%|███████▎  | 8031/11066 [29:24<11:06,  4.55it/s]
                                                    

 73%|███████▎  | 8031/11066 [29:24<11:06,  4.55it/s]
 73%|███████▎  | 8032/11066 [29:25<11:09,  4.53it/s]
                                                    

 73%|███████▎  | 8032/11066 [29:25<11:09,  4.53it/s]
 73%|███████▎  | 8033/11066 [29:25<11:10,  4.52it/s]
                                                    

 73%|███████▎  | 8033/11066 [29:25<11:10,  4.52it/s]
 73%|███████▎  | 8034/11066 [29:25<11:12,  4.51it/s]
                                                    

 73%|███████▎  | 8034/11066 [29:25<11:12,  4.51it/s]
 73%|███████▎  | 8035/11066 [29:25<11:13,  4.50it/s]
                                                    

 73%|███████▎  | 8035/11066 [29:25<11:13,  4.50it/s]
 73%|███████▎  | 8036/11066 [29:26<11:12,  4.50it/s]
                                                    

 73%|███████▎  | 8036/11066 [29:26<11:12,  4.50it/s]
 73%|███████▎  | 8037/11066 [29:26<11:12,  4.50it/s]
                                                    

 73%|███████▎  | 8037/11066 [29:26<11:12,  4.50it/s]
 73%|███████▎  | 8038/11066 [29:26<11:13,  4.50it/s]
                                                    

 73%|███████▎  | 8038/11066 [29:26<11:13,  4.50it/s]
 73%|███████▎  | 8039/11066 [29:26<11:13,  4.49it/s]
                                                    

 73%|███████▎  | 8039/11066 [29:26<11:13,  4.49it/s]
 73%|███████▎  | 8040/11066 [29:26<11:13,  4.49it/s]
                                                    

 73%|███████▎  | 8040/11066 [29:26<11:13,  4.49it/s]
 73%|███████▎  | 8041/11066 [29:27<11:12,  4.50it/s]
                                                    

 73%|███████▎  | 8041/11066 [29:27<11:12,  4.50it/s]
 73%|███████▎  | 8042/11066 [29:27<11:13,  4.49it/s]
                                                    

 73%|███████▎  | 8042/11066 [29:27<11:13,  4.49it/s]
 73%|███████▎  | 8043/11066 [29:27<11:12,  4.49it/s]
                                                    

 73%|███████▎  | 8043/11066 [29:27<11:12,  4.49it/s]
 73%|███████▎  | 8044/11066 [29:27<11:12,  4.50it/s]
                                                    

 73%|███████▎  | 8044/11066 [29:27<11:12,  4.50it/s]
 73%|███████▎  | 8045/11066 [29:28<11:12,  4.49it/s]
                                                    

 73%|███████▎  | 8045/11066 [29:28<11:12,  4.49it/s]
 73%|███████▎  | 8046/11066 [29:28<11:12,  4.49it/s]
                                                    

 73%|███████▎  | 8046/11066 [29:28<11:12,  4.49it/s]
 73%|███████▎  | 8047/11066 [29:28<11:11,  4.49it/s]
                                                    

 73%|███████▎  | 8047/11066 [29:28<11:11,  4.49it/s]
 73%|███████▎  | 8048/11066 [29:28<11:12,  4.49it/s]
                                                    

 73%|███████▎  | 8048/11066 [29:28<11:12,  4.49it/s]
 73%|███████▎  | 8049/11066 [29:28<11:11,  4.49it/s]
                                                    

 73%|███████▎  | 8049/11066 [29:28<11:11,  4.49it/s]
 73%|███████▎  | 8050/11066 [29:29<11:10,  4.50it/s]
                                                    

 73%|███████▎  | 8050/11066 [29:29<11:10,  4.50it/s]
 73%|███████▎  | 8051/11066 [29:29<11:11,  4.49it/s]
                                                    

 73%|███████▎  | 8051/11066 [29:29<11:11,  4.49it/s]
 73%|███████▎  | 8052/11066 [29:29<11:11,  4.49it/s]
                                                    

 73%|███████▎  | 8052/11066 [29:29<11:11,  4.49it/s]
 73%|███████▎  | 8053/11066 [29:29<11:11,  4.49it/s]
                                                    

 73%|███████▎  | 8053/11066 [29:29<11:11,  4.49it/s]
 73%|███████▎  | 8054/11066 [29:30<11:10,  4.49it/s]
                                                    

 73%|███████▎  | 8054/11066 [29:30<11:10,  4.49it/s]
 73%|███████▎  | 8055/11066 [29:30<11:10,  4.49it/s]
                                                    

 73%|███████▎  | 8055/11066 [29:30<11:10,  4.49it/s]
 73%|███████▎  | 8056/11066 [29:30<11:10,  4.49it/s]
                                                    

 73%|███████▎  | 8056/11066 [29:30<11:10,  4.49it/s]
 73%|███████▎  | 8057/11066 [29:30<11:09,  4.49it/s]
                                                    

 73%|███████▎  | 8057/11066 [29:30<11:09,  4.49it/s]
 73%|███████▎  | 8058/11066 [29:30<11:09,  4.49it/s]
                                                    

 73%|███████▎  | 8058/11066 [29:30<11:09,  4.49it/s]
 73%|███████▎  | 8059/11066 [29:31<11:10,  4.49it/s]
                                                    

 73%|███████▎  | 8059/11066 [29:31<11:10,  4.49it/s]
 73%|███████▎  | 8060/11066 [29:31<11:10,  4.48it/s]
                                                    

 73%|███████▎  | 8060/11066 [29:31<11:10,  4.48it/s]
 73%|███████▎  | 8061/11066 [29:31<11:10,  4.48it/s]
                                                    

 73%|███████▎  | 8061/11066 [29:31<11:10,  4.48it/s]
 73%|███████▎  | 8062/11066 [29:31<11:10,  4.48it/s]
                                                    

 73%|███████▎  | 8062/11066 [29:31<11:10,  4.48it/s]
 73%|███████▎  | 8063/11066 [29:32<11:11,  4.47it/s]
                                                    

 73%|███████▎  | 8063/11066 [29:32<11:11,  4.47it/s]
 73%|███████▎  | 8064/11066 [29:32<11:06,  4.50it/s]
                                                    

 73%|███████▎  | 8064/11066 [29:32<11:06,  4.50it/s]
 73%|███████▎  | 8065/11066 [29:32<11:17,  4.43it/s]
                                                    

 73%|███████▎  | 8065/11066 [29:32<11:17,  4.43it/s]
 73%|███████▎  | 8066/11066 [29:32<11:15,  4.44it/s]
                                                    

 73%|███████▎  | 8066/11066 [29:32<11:15,  4.44it/s]
 73%|███████▎  | 8067/11066 [29:32<11:12,  4.46it/s]
                                                    

 73%|███████▎  | 8067/11066 [29:32<11:12,  4.46it/s]
 73%|███████▎  | 8068/11066 [29:33<11:10,  4.47it/s]
                                                    

 73%|███████▎  | 8068/11066 [29:33<11:10,  4.47it/s]
 73%|███████▎  | 8069/11066 [29:33<11:09,  4.48it/s]
                                                    

 73%|███████▎  | 8069/11066 [29:33<11:09,  4.48it/s]
 73%|███████▎  | 8070/11066 [29:33<11:07,  4.49it/s]
                                                    

 73%|███████▎  | 8070/11066 [29:33<11:07,  4.49it/s]
 73%|███████▎  | 8071/11066 [29:33<11:07,  4.49it/s]
                                                    

 73%|███████▎  | 8071/11066 [29:33<11:07,  4.49it/s]
 73%|███████▎  | 8072/11066 [29:34<11:07,  4.49it/s]
                                                    

 73%|███████▎  | 8072/11066 [29:34<11:07,  4.49it/s]
 73%|███████▎  | 8073/11066 [29:34<11:05,  4.49it/s]
                                                    

 73%|███████▎  | 8073/11066 [29:34<11:05,  4.49it/s]
 73%|███████▎  | 8074/11066 [29:34<11:01,  4.52it/s]
                                                    

 73%|███████▎  | 8074/11066 [29:34<11:01,  4.52it/s]
 73%|███████▎  | 8075/11066 [29:34<11:05,  4.50it/s]
                                                    

 73%|███████▎  | 8075/11066 [29:34<11:05,  4.50it/s]
 73%|███████▎  | 8076/11066 [29:34<11:05,  4.49it/s]
                                                    

 73%|███████▎  | 8076/11066 [29:34<11:05,  4.49it/s]
 73%|███████▎  | 8077/11066 [29:35<11:05,  4.49it/s]
                                                    

 73%|███████▎  | 8077/11066 [29:35<11:05,  4.49it/s]
 73%|███████▎  | 8078/11066 [29:35<11:04,  4.50it/s]
                                                    

 73%|███████▎  | 8078/11066 [29:35<11:04,  4.50it/s]
 73%|███████▎  | 8079/11066 [29:35<11:03,  4.50it/s]
                                                    

 73%|███████▎  | 8079/11066 [29:35<11:03,  4.50it/s]
 73%|███████▎  | 8080/11066 [29:35<11:02,  4.50it/s]
                                                    

 73%|███████▎  | 8080/11066 [29:35<11:02,  4.50it/s]
 73%|███████▎  | 8081/11066 [29:36<11:02,  4.50it/s]
                                                    

 73%|███████▎  | 8081/11066 [29:36<11:02,  4.50it/s]
 73%|███████▎  | 8082/11066 [29:36<11:02,  4.50it/s]
                                                    

 73%|███████▎  | 8082/11066 [29:36<11:02,  4.50it/s]
 73%|███████▎  | 8083/11066 [29:36<10:54,  4.56it/s]
                                                    

 73%|███████▎  | 8083/11066 [29:36<10:54,  4.56it/s]
 73%|███████▎  | 8084/11066 [29:36<10:56,  4.54it/s]
                                                    

 73%|███████▎  | 8084/11066 [29:36<10:56,  4.54it/s]
 73%|███████▎  | 8085/11066 [29:36<10:57,  4.53it/s]
                                                    

 73%|███████▎  | 8085/11066 [29:36<10:57,  4.53it/s]
 73%|███████▎  | 8086/11066 [29:37<10:58,  4.52it/s]
                                                    

 73%|███████▎  | 8086/11066 [29:37<10:58,  4.52it/s]
 73%|███████▎  | 8087/11066 [29:37<10:59,  4.52it/s]
                                                    

 73%|███████▎  | 8087/11066 [29:37<10:59,  4.52it/s]
 73%|███████▎  | 8088/11066 [29:37<11:00,  4.51it/s]
                                                    

 73%|███████▎  | 8088/11066 [29:37<11:00,  4.51it/s]
 73%|███████▎  | 8089/11066 [29:37<11:01,  4.50it/s]
                                                    

 73%|███████▎  | 8089/11066 [29:37<11:01,  4.50it/s]
 73%|███████▎  | 8090/11066 [29:38<11:01,  4.50it/s]
                                                    

 73%|███████▎  | 8090/11066 [29:38<11:01,  4.50it/s]
 73%|███████▎  | 8091/11066 [29:38<11:00,  4.50it/s]
                                                    

 73%|███████▎  | 8091/11066 [29:38<11:00,  4.50it/s]
 73%|███████▎  | 8092/11066 [29:38<11:00,  4.51it/s]
                                                    

 73%|███████▎  | 8092/11066 [29:38<11:00,  4.51it/s]
 73%|███████▎  | 8093/11066 [29:38<11:00,  4.50it/s]
                                                    

 73%|███████▎  | 8093/11066 [29:38<11:00,  4.50it/s]
 73%|███████▎  | 8094/11066 [29:38<11:00,  4.50it/s]
                                                    

 73%|███████▎  | 8094/11066 [29:38<11:00,  4.50it/s]
 73%|███████▎  | 8095/11066 [29:39<11:01,  4.49it/s]
                                                    

 73%|███████▎  | 8095/11066 [29:39<11:01,  4.49it/s]
 73%|███████▎  | 8096/11066 [29:39<11:01,  4.49it/s]
                                                    

 73%|███████▎  | 8096/11066 [29:39<11:01,  4.49it/s]
 73%|███████▎  | 8097/11066 [29:39<11:00,  4.50it/s]
                                                    

 73%|███████▎  | 8097/11066 [29:39<11:00,  4.50it/s]
 73%|███████▎  | 8098/11066 [29:39<10:59,  4.50it/s]
                                                    

 73%|███████▎  | 8098/11066 [29:39<10:59,  4.50it/s]
 73%|███████▎  | 8099/11066 [29:40<10:58,  4.50it/s]
                                                    

 73%|███████▎  | 8099/11066 [29:40<10:58,  4.50it/s]
 73%|███████▎  | 8100/11066 [29:40<10:58,  4.50it/s]
                                                    

 73%|███████▎  | 8100/11066 [29:40<10:58,  4.50it/s]
 73%|███████▎  | 8101/11066 [29:40<10:59,  4.50it/s]
                                                    

 73%|███████▎  | 8101/11066 [29:40<10:59,  4.50it/s]
 73%|███████▎  | 8102/11066 [29:40<11:08,  4.43it/s]
                                                    

 73%|███████▎  | 8102/11066 [29:40<11:08,  4.43it/s]
 73%|███████▎  | 8103/11066 [29:40<11:12,  4.41it/s]
                                                    

 73%|███████▎  | 8103/11066 [29:40<11:12,  4.41it/s]
 73%|███████▎  | 8104/11066 [29:41<11:09,  4.43it/s]
                                                    

 73%|███████▎  | 8104/11066 [29:41<11:09,  4.43it/s]
 73%|███████▎  | 8105/11066 [29:41<11:05,  4.45it/s]
                                                    

 73%|███████▎  | 8105/11066 [29:41<11:05,  4.45it/s]
 73%|███████▎  | 8106/11066 [29:41<11:03,  4.46it/s]
                                                    

 73%|███████▎  | 8106/11066 [29:41<11:03,  4.46it/s]
 73%|███████▎  | 8107/11066 [29:41<11:02,  4.47it/s]
                                                    

 73%|███████▎  | 8107/11066 [29:41<11:02,  4.47it/s]
 73%|███████▎  | 8108/11066 [29:42<11:00,  4.48it/s]
                                                    
{'loss': 0.7424, 'learning_rate': 8.328212542924272e-06, 'epoch': 1.44}
{'loss': 0.2923, 'learning_rate': 8.325501536237124e-06, 'epoch': 1.44}
{'loss': 0.9585, 'learning_rate': 8.322790529549973e-06, 'epoch': 1.45}
{'loss': 1.4892, 'learning_rate': 8.320079522862823e-06, 'epoch': 1.45}
{'loss': 0.9758, 'learning_rate': 8.317368516175673e-06, 'epoch': 1.45}
{'loss': 0.9613, 'learning_rate': 8.314657509488525e-06, 'epoch': 1.45}
{'loss': 0.6733, 'learning_rate': 8.311946502801373e-06, 'epoch': 1.45}
{'loss': 0.5166, 'learning_rate': 8.309235496114223e-06, 'epoch': 1.45}
{'loss': 0.5047, 'learning_rate': 8.306524489427073e-06, 'epoch': 1.45}
{'loss': 0.5987, 'learning_rate': 8.303813482739925e-06, 'epoch': 1.45}
{'loss': 0.69, 'learning_rate': 8.301102476052774e-06, 'epoch': 1.45}
{'loss': 0.3259, 'learning_rate': 8.298391469365624e-06, 'epoch': 1.45}
{'loss': 0.829, 'learning_rate': 8.295680462678476e-06, 'epoch': 1.45}
{'loss': 1.4828, 'learning_rate': 8.292969455991326e-06, 'epoch': 1.45}
{'loss': 0.4466, 'learning_rate': 8.290258449304174e-06, 'epoch': 1.45}
{'loss': 0.8714, 'learning_rate': 8.287547442617024e-06, 'epoch': 1.45}
{'loss': 0.6558, 'learning_rate': 8.284836435929876e-06, 'epoch': 1.45}
{'loss': 0.7123, 'learning_rate': 8.282125429242726e-06, 'epoch': 1.45}
{'loss': 0.6129, 'learning_rate': 8.279414422555575e-06, 'epoch': 1.45}
{'loss': 0.5505, 'learning_rate': 8.276703415868427e-06, 'epoch': 1.45}
{'loss': 0.7377, 'learning_rate': 8.273992409181277e-06, 'epoch': 1.45}
{'loss': 0.708, 'learning_rate': 8.271281402494127e-06, 'epoch': 1.45}
{'loss': 1.2659, 'learning_rate': 8.268570395806975e-06, 'epoch': 1.45}
{'loss': 0.4903, 'learning_rate': 8.265859389119827e-06, 'epoch': 1.45}
{'loss': 0.9393, 'learning_rate': 8.263148382432677e-06, 'epoch': 1.45}
{'loss': 0.5652, 'learning_rate': 8.260437375745527e-06, 'epoch': 1.45}
{'loss': 0.5657, 'learning_rate': 8.257726369058376e-06, 'epoch': 1.45}
{'loss': 1.3215, 'learning_rate': 8.255015362371228e-06, 'epoch': 1.45}
{'loss': 0.5898, 'learning_rate': 8.252304355684078e-06, 'epoch': 1.45}
{'loss': 0.554, 'learning_rate': 8.249593348996928e-06, 'epoch': 1.45}
{'loss': 0.8496, 'learning_rate': 8.246882342309778e-06, 'epoch': 1.45}
{'loss': 0.4834, 'learning_rate': 8.244171335622628e-06, 'epoch': 1.45}
{'loss': 0.4574, 'learning_rate': 8.241460328935478e-06, 'epoch': 1.45}
{'loss': 0.7754, 'learning_rate': 8.238749322248328e-06, 'epoch': 1.45}
{'loss': 0.6865, 'learning_rate': 8.236038315561179e-06, 'epoch': 1.45}
{'loss': 0.4726, 'learning_rate': 8.233327308874029e-06, 'epoch': 1.45}
{'loss': 0.7753, 'learning_rate': 8.230616302186879e-06, 'epoch': 1.45}
{'loss': 0.6418, 'learning_rate': 8.227905295499729e-06, 'epoch': 1.45}
{'loss': 1.2401, 'learning_rate': 8.225194288812579e-06, 'epoch': 1.45}
{'loss': 1.252, 'learning_rate': 8.22248328212543e-06, 'epoch': 1.45}
{'loss': 0.744, 'learning_rate': 8.21977227543828e-06, 'epoch': 1.45}
{'loss': 0.9983, 'learning_rate': 8.217061268751131e-06, 'epoch': 1.45}
{'loss': 0.3009, 'learning_rate': 8.21435026206398e-06, 'epoch': 1.45}
{'loss': 0.9089, 'learning_rate': 8.21163925537683e-06, 'epoch': 1.45}
{'loss': 0.5436, 'learning_rate': 8.20892824868968e-06, 'epoch': 1.45}
{'loss': 0.5979, 'learning_rate': 8.206217242002532e-06, 'epoch': 1.45}
{'loss': 0.6548, 'learning_rate': 8.20350623531538e-06, 'epoch': 1.45}
{'loss': 0.8132, 'learning_rate': 8.20079522862823e-06, 'epoch': 1.45}
{'loss': 1.0955, 'learning_rate': 8.19808422194108e-06, 'epoch': 1.45}
{'loss': 0.7672, 'learning_rate': 8.195373215253932e-06, 'epoch': 1.45}
{'loss': 0.5935, 'learning_rate': 8.19266220856678e-06, 'epoch': 1.45}
{'loss': 0.5704, 'learning_rate': 8.189951201879631e-06, 'epoch': 1.45}
{'loss': 0.9381, 'learning_rate': 8.187240195192483e-06, 'epoch': 1.45}
{'loss': 0.7598, 'learning_rate': 8.184529188505333e-06, 'epoch': 1.45}
{'loss': 0.2614, 'learning_rate': 8.181818181818181e-06, 'epoch': 1.45}
{'loss': 0.6536, 'learning_rate': 8.179107175131031e-06, 'epoch': 1.45}
{'loss': 0.3815, 'learning_rate': 8.176396168443883e-06, 'epoch': 1.45}
{'loss': 0.6303, 'learning_rate': 8.173685161756733e-06, 'epoch': 1.46}
{'loss': 0.4688, 'learning_rate': 8.170974155069582e-06, 'epoch': 1.46}
{'loss': 0.5326, 'learning_rate': 8.168263148382432e-06, 'epoch': 1.46}
{'loss': 0.6305, 'learning_rate': 8.165552141695284e-06, 'epoch': 1.46}
{'loss': 0.3807, 'learning_rate': 8.162841135008134e-06, 'epoch': 1.46}
{'loss': 1.2247, 'learning_rate': 8.160130128320982e-06, 'epoch': 1.46}
{'loss': 0.4463, 'learning_rate': 8.157419121633834e-06, 'epoch': 1.46}
{'loss': 0.3788, 'learning_rate': 8.154708114946684e-06, 'epoch': 1.46}
{'loss': 0.4599, 'learning_rate': 8.151997108259534e-06, 'epoch': 1.46}
{'loss': 1.2463, 'learning_rate': 8.149286101572383e-06, 'epoch': 1.46}
{'loss': 0.4884, 'learning_rate': 8.146575094885235e-06, 'epoch': 1.46}
{'loss': 0.8776, 'learning_rate': 8.143864088198085e-06, 'epoch': 1.46}
{'loss': 0.7688, 'learning_rate': 8.141153081510935e-06, 'epoch': 1.46}
{'loss': 0.9937, 'learning_rate': 8.138442074823783e-06, 'epoch': 1.46}
{'loss': 0.74, 'learning_rate': 8.135731068136635e-06, 'epoch': 1.46}
{'loss': 0.5054, 'learning_rate': 8.133020061449485e-06, 'epoch': 1.46}
{'loss': 0.5043, 'learning_rate': 8.130309054762336e-06, 'epoch': 1.46}
{'loss': 0.3956, 'learning_rate': 8.127598048075186e-06, 'epoch': 1.46}
{'loss': 0.7983, 'learning_rate': 8.124887041388036e-06, 'epoch': 1.46}
{'loss': 0.6048, 'learning_rate': 8.122176034700886e-06, 'epoch': 1.46}
{'loss': 0.5847, 'learning_rate': 8.119465028013736e-06, 'epoch': 1.46}
{'loss': 0.4008, 'learning_rate': 8.116754021326586e-06, 'epoch': 1.46}
{'loss': 0.4078, 'learning_rate': 8.114043014639436e-06, 'epoch': 1.46}
{'loss': 0.5409, 'learning_rate': 8.111332007952286e-06, 'epoch': 1.46}
{'loss': 0.5566, 'learning_rate': 8.108621001265137e-06, 'epoch': 1.46}
{'loss': 0.8103, 'learning_rate': 8.105909994577987e-06, 'epoch': 1.46}
{'loss': 1.1829, 'learning_rate': 8.103198987890837e-06, 'epoch': 1.46}
{'loss': 0.7847, 'learning_rate': 8.100487981203687e-06, 'epoch': 1.46}
{'loss': 0.5455, 'learning_rate': 8.097776974516539e-06, 'epoch': 1.46}
{'loss': 0.7883, 'learning_rate': 8.095065967829387e-06, 'epoch': 1.46}
{'loss': 0.3697, 'learning_rate': 8.092354961142237e-06, 'epoch': 1.46}
{'loss': 0.6079, 'learning_rate': 8.089643954455088e-06, 'epoch': 1.46}
{'loss': 1.0136, 'learning_rate': 8.08693294776794e-06, 'epoch': 1.46}
{'loss': 0.6293, 'learning_rate': 8.084221941080788e-06, 'epoch': 1.46}
{'loss': 0.4942, 'learning_rate': 8.081510934393638e-06, 'epoch': 1.46}
{'loss': 0.8216, 'learning_rate': 8.078799927706488e-06, 'epoch': 1.46}
{'loss': 0.5227, 'learning_rate': 8.07608892101934e-06, 'epoch': 1.46}
{'loss': 0.8849, 'learning_rate': 8.073377914332188e-06, 'epoch': 1.46}
{'loss': 0.4059, 'learning_rate': 8.070666907645038e-06, 'epoch': 1.46}
{'loss': 1.0278, 'learning_rate': 8.06795590095789e-06, 'epoch': 1.46}
{'loss': 1.0014, 'learning_rate': 8.06524489427074e-06, 'epoch': 1.46}
{'loss': 0.3208, 'learning_rate': 8.062533887583589e-06, 'epoch': 1.46}
{'loss': 0.8024, 'learning_rate': 8.059822880896439e-06, 'epoch': 1.46}
{'loss': 0.6556, 'learning_rate': 8.05711187420929e-06, 'epoch': 1.46}
{'loss': 0.487, 'learning_rate': 8.054400867522141e-06, 'epoch': 1.46}
{'loss': 0.8235, 'learning_rate': 8.05168986083499e-06, 'epoch': 1.46}
{'loss': 0.7265, 'learning_rate': 8.048978854147841e-06, 'epoch': 1.46}
{'loss': 1.5138, 'learning_rate': 8.046267847460691e-06, 'epoch': 1.46}
{'loss': 0.478, 'learning_rate': 8.043556840773541e-06, 'epoch': 1.46}
{'loss': 0.3258, 'learning_rate': 8.04084583408639e-06, 'epoch': 1.46}
{'loss': 0.452, 'learning_rate': 8.038134827399242e-06, 'epoch': 1.46}
{'loss': 0.7487, 'learning_rate': 8.035423820712092e-06, 'epoch': 1.46}
{'loss': 0.4042, 'learning_rate': 8.032712814024942e-06, 'epoch': 1.46}
{'loss': 0.8215, 'learning_rate': 8.03000180733779e-06, 'epoch': 1.46}
{'loss': 0.9311, 'learning_rate': 8.027290800650642e-06, 'epoch': 1.46}
{'loss': 0.3339, 'learning_rate': 8.024579793963492e-06, 'epoch': 1.47}
{'loss': 0.672, 'learning_rate': 8.021868787276341e-06, 'epoch': 1.47}

 73%|███████▎  | 8108/11066 [29:42<11:00,  4.48it/s]
 73%|███████▎  | 8109/11066 [29:42<10:59,  4.49it/s]
                                                    

 73%|███████▎  | 8109/11066 [29:42<10:59,  4.49it/s]
 73%|███████▎  | 8110/11066 [29:42<10:59,  4.48it/s]
                                                    

 73%|███████▎  | 8110/11066 [29:42<10:59,  4.48it/s]
 73%|███████▎  | 8111/11066 [29:42<10:58,  4.49it/s]
                                                    

 73%|███████▎  | 8111/11066 [29:42<10:58,  4.49it/s]
 73%|███████▎  | 8112/11066 [29:42<10:57,  4.49it/s]
                                                    

 73%|███████▎  | 8112/11066 [29:42<10:57,  4.49it/s]
 73%|███████▎  | 8113/11066 [29:43<10:56,  4.50it/s]
                                                    

 73%|███████▎  | 8113/11066 [29:43<10:56,  4.50it/s]
 73%|███████▎  | 8114/11066 [29:43<10:55,  4.50it/s]
                                                    

 73%|███████▎  | 8114/11066 [29:43<10:55,  4.50it/s]
 73%|███████▎  | 8115/11066 [29:43<10:56,  4.50it/s]
                                                    

 73%|███████▎  | 8115/11066 [29:43<10:56,  4.50it/s]
 73%|███████▎  | 8116/11066 [29:43<10:56,  4.49it/s]
                                                    

 73%|███████▎  | 8116/11066 [29:43<10:56,  4.49it/s]
 73%|███████▎  | 8117/11066 [29:44<10:56,  4.49it/s]
                                                    

 73%|███████▎  | 8117/11066 [29:44<10:56,  4.49it/s]
 73%|███████▎  | 8118/11066 [29:44<10:56,  4.49it/s]
                                                    

 73%|███████▎  | 8118/11066 [29:44<10:56,  4.49it/s]
 73%|███████▎  | 8119/11066 [29:44<10:52,  4.51it/s]
                                                    

 73%|███████▎  | 8119/11066 [29:44<10:52,  4.51it/s]
 73%|███████▎  | 8120/11066 [29:44<10:54,  4.50it/s]
                                                    

 73%|███████▎  | 8120/11066 [29:44<10:54,  4.50it/s]
 73%|███████▎  | 8121/11066 [29:44<10:54,  4.50it/s]
                                                    

 73%|███████▎  | 8121/11066 [29:44<10:54,  4.50it/s]
 73%|███████▎  | 8122/11066 [29:45<10:54,  4.50it/s]
                                                    

 73%|███████▎  | 8122/11066 [29:45<10:54,  4.50it/s]
 73%|███████▎  | 8123/11066 [29:45<10:54,  4.50it/s]
                                                    

 73%|███████▎  | 8123/11066 [29:45<10:54,  4.50it/s]
 73%|███████▎  | 8124/11066 [29:45<10:54,  4.49it/s]
                                                    

 73%|███████▎  | 8124/11066 [29:45<10:54,  4.49it/s]
 73%|███████▎  | 8125/11066 [29:45<10:54,  4.49it/s]
                                                    

 73%|███████▎  | 8125/11066 [29:45<10:54,  4.49it/s]
 73%|███████▎  | 8126/11066 [29:46<10:49,  4.53it/s]
                                                    

 73%|███████▎  | 8126/11066 [29:46<10:49,  4.53it/s]
 73%|███████▎  | 8127/11066 [29:46<10:53,  4.50it/s]
                                                    

 73%|███████▎  | 8127/11066 [29:46<10:53,  4.50it/s]
 73%|███████▎  | 8128/11066 [29:46<10:45,  4.55it/s]
                                                    

 73%|███████▎  | 8128/11066 [29:46<10:45,  4.55it/s]
 73%|███████▎  | 8129/11066 [29:46<10:39,  4.59it/s]
                                                    

 73%|███████▎  | 8129/11066 [29:46<10:39,  4.59it/s]
 73%|███████▎  | 8130/11066 [29:46<10:44,  4.56it/s]
                                                    

 73%|███████▎  | 8130/11066 [29:46<10:44,  4.56it/s]
 73%|███████▎  | 8131/11066 [29:47<10:46,  4.54it/s]
                                                    

 73%|███████▎  | 8131/11066 [29:47<10:46,  4.54it/s]
 73%|███████▎  | 8132/11066 [29:47<10:48,  4.53it/s]
                                                    

 73%|███████▎  | 8132/11066 [29:47<10:48,  4.53it/s]
 73%|███████▎  | 8133/11066 [29:47<10:49,  4.52it/s]
                                                    

 73%|███████▎  | 8133/11066 [29:47<10:49,  4.52it/s]
 74%|███████▎  | 8134/11066 [29:47<10:46,  4.54it/s]
                                                    

 74%|███████▎  | 8134/11066 [29:47<10:46,  4.54it/s]
 74%|███████▎  | 8135/11066 [29:48<10:40,  4.58it/s]
                                                    

 74%|███████▎  | 8135/11066 [29:48<10:40,  4.58it/s]
 74%|███████▎  | 8136/11066 [29:48<10:44,  4.54it/s]
                                                    

 74%|███████▎  | 8136/11066 [29:48<10:44,  4.54it/s]
 74%|███████▎  | 8137/11066 [29:48<10:47,  4.52it/s]
                                                    

 74%|███████▎  | 8137/11066 [29:48<10:47,  4.52it/s]
 74%|███████▎  | 8138/11066 [29:48<10:48,  4.51it/s]
                                                    

 74%|███████▎  | 8138/11066 [29:48<10:48,  4.51it/s]
 74%|███████▎  | 8139/11066 [29:48<10:49,  4.51it/s]
                                                    

 74%|███████▎  | 8139/11066 [29:48<10:49,  4.51it/s]
 74%|███████▎  | 8140/11066 [29:49<10:49,  4.50it/s]
                                                    

 74%|███████▎  | 8140/11066 [29:49<10:49,  4.50it/s]
 74%|███████▎  | 8141/11066 [29:49<10:49,  4.50it/s]
                                                    

 74%|███████▎  | 8141/11066 [29:49<10:49,  4.50it/s]
 74%|███████▎  | 8142/11066 [29:49<10:50,  4.50it/s]
                                                    

 74%|███████▎  | 8142/11066 [29:49<10:50,  4.50it/s]
 74%|███████▎  | 8143/11066 [29:49<10:50,  4.50it/s]
                                                    

 74%|███████▎  | 8143/11066 [29:49<10:50,  4.50it/s]
 74%|███████▎  | 8144/11066 [29:50<10:50,  4.49it/s]
                                                    

 74%|███████▎  | 8144/11066 [29:50<10:50,  4.49it/s]
 74%|███████▎  | 8145/11066 [29:50<10:49,  4.49it/s]
                                                    

 74%|███████▎  | 8145/11066 [29:50<10:49,  4.49it/s]
 74%|███████▎  | 8146/11066 [29:50<10:49,  4.50it/s]
                                                    

 74%|███████▎  | 8146/11066 [29:50<10:49,  4.50it/s]
 74%|███████▎  | 8147/11066 [29:50<10:48,  4.50it/s]
                                                    

 74%|███████▎  | 8147/11066 [29:50<10:48,  4.50it/s]
 74%|███████▎  | 8148/11066 [29:50<10:48,  4.50it/s]
                                                    

 74%|███████▎  | 8148/11066 [29:50<10:48,  4.50it/s]
 74%|███████▎  | 8149/11066 [29:51<10:48,  4.50it/s]
                                                    

 74%|███████▎  | 8149/11066 [29:51<10:48,  4.50it/s]
 74%|███████▎  | 8150/11066 [29:51<10:48,  4.49it/s]
                                                    

 74%|███████▎  | 8150/11066 [29:51<10:48,  4.49it/s]
 74%|███████▎  | 8151/11066 [29:51<10:48,  4.50it/s]
                                                    

 74%|███████▎  | 8151/11066 [29:51<10:48,  4.50it/s]
 74%|███████▎  | 8152/11066 [29:51<10:47,  4.50it/s]
                                                    

 74%|███████▎  | 8152/11066 [29:51<10:47,  4.50it/s]
 74%|███████▎  | 8153/11066 [29:52<10:47,  4.50it/s]
                                                    

 74%|███████▎  | 8153/11066 [29:52<10:47,  4.50it/s]
 74%|███████▎  | 8154/11066 [29:52<10:47,  4.50it/s]
                                                    

 74%|███████▎  | 8154/11066 [29:52<10:47,  4.50it/s]
 74%|███████▎  | 8155/11066 [29:52<10:47,  4.50it/s]
                                                    

 74%|███████▎  | 8155/11066 [29:52<10:47,  4.50it/s]
 74%|███████▎  | 8156/11066 [29:52<10:48,  4.49it/s]
                                                    

 74%|███████▎  | 8156/11066 [29:52<10:48,  4.49it/s]
 74%|███████▎  | 8157/11066 [29:52<10:49,  4.48it/s]
                                                    

 74%|███████▎  | 8157/11066 [29:52<10:49,  4.48it/s]
 74%|███████▎  | 8158/11066 [29:53<10:49,  4.47it/s]
                                                    

 74%|███████▎  | 8158/11066 [29:53<10:49,  4.47it/s]
 74%|███████▎  | 8159/11066 [29:53<10:51,  4.46it/s]
                                                    

 74%|███████▎  | 8159/11066 [29:53<10:51,  4.46it/s]
 74%|███████▎  | 8160/11066 [29:53<10:51,  4.46it/s]
                                                    

 74%|███████▎  | 8160/11066 [29:53<10:51,  4.46it/s]
 74%|███████▎  | 8161/11066 [29:53<10:49,  4.47it/s]
                                                    

 74%|███████▎  | 8161/11066 [29:53<10:49,  4.47it/s]
 74%|███████▍  | 8162/11066 [29:54<10:48,  4.48it/s]
                                                    

 74%|███████▍  | 8162/11066 [29:54<10:48,  4.48it/s]
 74%|███████▍  | 8163/11066 [29:54<10:47,  4.48it/s]
                                                    

 74%|███████▍  | 8163/11066 [29:54<10:47,  4.48it/s]
 74%|███████▍  | 8164/11066 [29:54<10:46,  4.49it/s]
                                                    

 74%|███████▍  | 8164/11066 [29:54<10:46,  4.49it/s]
 74%|███████▍  | 8165/11066 [29:54<10:46,  4.49it/s]
                                                    

 74%|███████▍  | 8165/11066 [29:54<10:46,  4.49it/s]
 74%|███████▍  | 8166/11066 [29:54<10:44,  4.50it/s]
                                                    

 74%|███████▍  | 8166/11066 [29:54<10:44,  4.50it/s]
 74%|███████▍  | 8167/11066 [29:55<10:43,  4.50it/s]
                                                    

 74%|███████▍  | 8167/11066 [29:55<10:43,  4.50it/s]
 74%|███████▍  | 8168/11066 [29:55<10:43,  4.50it/s]
                                                    

 74%|███████▍  | 8168/11066 [29:55<10:43,  4.50it/s]
 74%|███████▍  | 8169/11066 [29:55<10:43,  4.51it/s]
                                                    

 74%|███████▍  | 8169/11066 [29:55<10:43,  4.51it/s]
 74%|███████▍  | 8170/11066 [29:55<10:31,  4.59it/s]
                                                    

 74%|███████▍  | 8170/11066 [29:55<10:31,  4.59it/s]
 74%|███████▍  | 8171/11066 [29:56<10:36,  4.55it/s]
                                                    

 74%|███████▍  | 8171/11066 [29:56<10:36,  4.55it/s]
 74%|███████▍  | 8172/11066 [29:56<10:39,  4.53it/s]
                                                    

 74%|███████▍  | 8172/11066 [29:56<10:39,  4.53it/s]
 74%|███████▍  | 8173/11066 [29:56<10:40,  4.52it/s]
                                                    

 74%|███████▍  | 8173/11066 [29:56<10:40,  4.52it/s]
 74%|███████▍  | 8174/11066 [29:56<10:41,  4.51it/s]
                                                    

 74%|███████▍  | 8174/11066 [29:56<10:41,  4.51it/s]
 74%|███████▍  | 8175/11066 [29:56<10:37,  4.54it/s]
                                                    

 74%|███████▍  | 8175/11066 [29:56<10:37,  4.54it/s]
 74%|███████▍  | 8176/11066 [29:57<10:37,  4.53it/s]
                                                    

 74%|███████▍  | 8176/11066 [29:57<10:37,  4.53it/s]
 74%|███████▍  | 8177/11066 [29:57<10:28,  4.60it/s]
                                                    

 74%|███████▍  | 8177/11066 [29:57<10:28,  4.60it/s]
 74%|███████▍  | 8178/11066 [29:57<10:23,  4.63it/s]
                                                    

 74%|███████▍  | 8178/11066 [29:57<10:23,  4.63it/s]
 74%|███████▍  | 8179/11066 [29:57<10:23,  4.63it/s]
                                                    

 74%|███████▍  | 8179/11066 [29:57<10:23,  4.63it/s]
 74%|███████▍  | 8180/11066 [29:58<10:22,  4.64it/s]
                                                    

 74%|███████▍  | 8180/11066 [29:58<10:22,  4.64it/s]
 74%|███████▍  | 8181/11066 [29:58<10:18,  4.66it/s]
                                                    

 74%|███████▍  | 8181/11066 [29:58<10:18,  4.66it/s]
 74%|███████▍  | 8182/11066 [29:58<10:26,  4.60it/s]
                                                    

 74%|███████▍  | 8182/11066 [29:58<10:26,  4.60it/s]
 74%|███████▍  | 8183/11066 [29:58<10:21,  4.64it/s]
                                                    

 74%|███████▍  | 8183/11066 [29:58<10:21,  4.64it/s]
 74%|███████▍  | 8184/11066 [29:58<10:23,  4.62it/s]
                                                    

 74%|███████▍  | 8184/11066 [29:58<10:23,  4.62it/s]
 74%|███████▍  | 8185/11066 [29:59<10:30,  4.57it/s]
                                                    

 74%|███████▍  | 8185/11066 [29:59<10:30,  4.57it/s]
 74%|███████▍  | 8186/11066 [29:59<10:34,  4.54it/s]
                                                    

 74%|███████▍  | 8186/11066 [29:59<10:34,  4.54it/s]
 74%|███████▍  | 8187/11066 [29:59<10:31,  4.56it/s]
                                                    

 74%|███████▍  | 8187/11066 [29:59<10:31,  4.56it/s]
 74%|███████▍  | 8188/11066 [29:59<10:23,  4.61it/s]
                                                    

 74%|███████▍  | 8188/11066 [29:59<10:23,  4.61it/s]
 74%|███████▍  | 8189/11066 [29:59<10:21,  4.63it/s]
                                                    

 74%|███████▍  | 8189/11066 [29:59<10:21,  4.63it/s]
 74%|███████▍  | 8190/11066 [30:00<10:23,  4.61it/s]
                                                    

 74%|███████▍  | 8190/11066 [30:00<10:23,  4.61it/s]
 74%|███████▍  | 8191/11066 [30:00<10:19,  4.64it/s]
                                                    

 74%|███████▍  | 8191/11066 [30:00<10:19,  4.64it/s]
 74%|███████▍  | 8192/11066 [30:00<10:22,  4.62it/s]
                                                    

 74%|███████▍  | 8192/11066 [30:00<10:22,  4.62it/s]
 74%|███████▍  | 8193/11066 [30:00<10:21,  4.62it/s]
                                                    

 74%|███████▍  | 8193/11066 [30:00<10:21,  4.62it/s]
 74%|███████▍  | 8194/11066 [30:01<10:25,  4.59it/s]
                                                    

 74%|███████▍  | 8194/11066 [30:01<10:25,  4.59it/s]
 74%|███████▍  | 8195/11066 [30:01<10:30,  4.55it/s]
                                                    

 74%|███████▍  | 8195/11066 [30:01<10:30,  4.55it/s]
 74%|███████▍  | 8196/11066 [30:01<10:23,  4.60it/s]
                                                    

 74%|███████▍  | 8196/11066 [30:01<10:23,  4.60it/s]
 74%|███████▍  | 8197/11066 [30:01<10:17,  4.65it/s]
                                                    

 74%|███████▍  | 8197/11066 [30:01<10:17,  4.65it/s]
 74%|███████▍  | 8198/11066 [30:01<10:25,  4.59it/s]
                                                    

 74%|███████▍  | 8198/11066 [30:01<10:25,  4.59it/s]
 74%|███████▍  | 8199/11066 [30:02<10:30,  4.55it/s]
                                                    

 74%|███████▍  | 8199/11066 [30:02<10:30,  4.55it/s]
 74%|███████▍  | 8200/11066 [30:02<10:28,  4.56it/s]
                                                    

 74%|███████▍  | 8200/11066 [30:02<10:28,  4.56it/s]
 74%|███████▍  | 8201/11066 [30:02<10:27,  4.56it/s]
                                                    

 74%|███████▍  | 8201/11066 [30:02<10:27,  4.56it/s]
 74%|███████▍  | 8202/11066 [30:02<10:25,  4.58it/s]
                                                    

 74%|███████▍  | 8202/11066 [30:02<10:25,  4.58it/s]
 74%|███████▍  | 8203/11066 [30:03<10:29,  4.55it/s]
                                                    

 74%|███████▍  | 8203/11066 [30:03<10:29,  4.55it/s]
 74%|███████▍  | 8204/11066 [30:03<10:33,  4.52it/s]
                                                    

 74%|███████▍  | 8204/11066 [30:03<10:33,  4.52it/s]
 74%|███████▍  | 8205/11066 [30:03<10:30,  4.54it/s]
                                                    

 74%|███████▍  | 8205/11066 [30:03<10:30,  4.54it/s]
 74%|███████▍  | 8206/11066 [30:03<10:24,  4.58it/s]
                                                    

 74%|███████▍  | 8206/11066 [30:03<10:24,  4.58it/s]
 74%|███████▍  | 8207/11066 [30:03<10:26,  4.57it/s]
                                                    

 74%|███████▍  | 8207/11066 [30:03<10:26,  4.57it/s]
 74%|███████▍  | 8208/11066 [30:04<10:21,  4.60it/s]
                                                    

 74%|███████▍  | 8208/11066 [30:04<10:21,  4.60it/s]
 74%|███████▍  | 8209/11066 [30:04<10:20,  4.61it/s]
                                                    

 74%|███████▍  | 8209/11066 [30:04<10:20,  4.61it/s]
 74%|███████▍  | 8210/11066 [30:04<10:24,  4.57it/s]
                                                    

 74%|███████▍  | 8210/11066 [30:04<10:24,  4.57it/s]
 74%|███████▍  | 8211/11066 [30:04<10:22,  4.58it/s]
                                                    

 74%|███████▍  | 8211/11066 [30:04<10:22,  4.58it/s]
 74%|███████▍  | 8212/11066 [30:05<10:27,  4.55it/s]
                                                    

 74%|███████▍  | 8212/11066 [30:05<10:27,  4.55it/s]
 74%|███████▍  | 8213/11066 [30:05<10:32,  4.51it/s]
                                                    

 74%|███████▍  | 8213/11066 [30:05<10:32,  4.51it/s]
 74%|███████▍  | 8214/11066 [30:05<10:33,  4.50it/s]
                                                    

 74%|███████▍  | 8214/11066 [30:05<10:33,  4.50it/s]
 74%|███████▍  | 8215/11066 [30:05<10:33,  4.50it/s]
                                                    

 74%|███████▍  | 8215/11066 [30:05<10:33,  4.50it/s]
 74%|███████▍  | 8216/11066 [30:05<10:34,  4.49it/s]
                                                    

 74%|███████▍  | 8216/11066 [30:05<10:34,  4.49it/s]
 74%|███████▍  | 8217/11066 [30:06<10:29,  4.52it/s]
                                                    

 74%|███████▍  | 8217/11066 [30:06<10:29,  4.52it/s]
 74%|███████▍  | 8218/11066 [30:06<10:33,  4.49it/s]
                                                    

 74%|███████▍  | 8218/11066 [30:06<10:33,  4.49it/s]
 74%|███████▍  | 8219/11066 [30:06<10:33,  4.49it/s]
                                                    

 74%|███████▍  | 8219/11066 [30:06<10:33,  4.49it/s]
 74%|███████▍  | 8220/11066 [30:06<10:29,  4.52it/s]
                                                    

 74%|███████▍  | 8220/11066 [30:06<10:29,  4.52it/s]
 74%|███████▍  | 8221/11066 [30:07<10:17,  4.60it/s]
                                                    

 74%|███████▍  | 8221/11066 [30:07<10:17,  4.60it/s]
 74%|███████▍  | 8222/11066 [30:07<10:23,  4.56it/s]
                                                    
{'loss': 0.5144, 'learning_rate': 8.019157780589193e-06, 'epoch': 1.47}
{'loss': 1.6358, 'learning_rate': 8.016446773902043e-06, 'epoch': 1.47}
{'loss': 1.0063, 'learning_rate': 8.013735767214893e-06, 'epoch': 1.47}
{'loss': 1.2398, 'learning_rate': 8.011024760527741e-06, 'epoch': 1.47}
{'loss': 0.1627, 'learning_rate': 8.008313753840593e-06, 'epoch': 1.47}
{'loss': 0.6331, 'learning_rate': 8.005602747153443e-06, 'epoch': 1.47}
{'loss': 1.0265, 'learning_rate': 8.002891740466294e-06, 'epoch': 1.47}
{'loss': 0.4923, 'learning_rate': 8.000180733779142e-06, 'epoch': 1.47}
{'loss': 0.467, 'learning_rate': 7.997469727091994e-06, 'epoch': 1.47}
{'loss': 0.4376, 'learning_rate': 7.994758720404844e-06, 'epoch': 1.47}
{'loss': 0.542, 'learning_rate': 7.992047713717694e-06, 'epoch': 1.47}
{'loss': 0.9454, 'learning_rate': 7.989336707030544e-06, 'epoch': 1.47}
{'loss': 0.3885, 'learning_rate': 7.986625700343394e-06, 'epoch': 1.47}
{'loss': 0.5236, 'learning_rate': 7.983914693656244e-06, 'epoch': 1.47}
{'loss': 0.7626, 'learning_rate': 7.981203686969095e-06, 'epoch': 1.47}
{'loss': 0.4572, 'learning_rate': 7.978492680281945e-06, 'epoch': 1.47}
{'loss': 0.397, 'learning_rate': 7.975781673594795e-06, 'epoch': 1.47}
{'loss': 1.16, 'learning_rate': 7.973070666907645e-06, 'epoch': 1.47}
{'loss': 0.46, 'learning_rate': 7.970359660220495e-06, 'epoch': 1.47}
{'loss': 0.4757, 'learning_rate': 7.967648653533345e-06, 'epoch': 1.47}
{'loss': 0.6473, 'learning_rate': 7.964937646846195e-06, 'epoch': 1.47}
{'loss': 0.377, 'learning_rate': 7.962226640159046e-06, 'epoch': 1.47}
{'loss': 0.5781, 'learning_rate': 7.959515633471897e-06, 'epoch': 1.47}
{'loss': 0.9883, 'learning_rate': 7.956804626784746e-06, 'epoch': 1.47}
{'loss': 1.5251, 'learning_rate': 7.954093620097596e-06, 'epoch': 1.47}
{'loss': 1.0381, 'learning_rate': 7.951382613410446e-06, 'epoch': 1.47}
{'loss': 0.4876, 'learning_rate': 7.948671606723298e-06, 'epoch': 1.47}
{'loss': 0.5931, 'learning_rate': 7.945960600036146e-06, 'epoch': 1.47}
{'loss': 0.4648, 'learning_rate': 7.943249593348996e-06, 'epoch': 1.47}
{'loss': 0.6156, 'learning_rate': 7.940538586661847e-06, 'epoch': 1.47}
{'loss': 0.2568, 'learning_rate': 7.937827579974698e-06, 'epoch': 1.47}
{'loss': 1.0615, 'learning_rate': 7.935116573287547e-06, 'epoch': 1.47}
{'loss': 0.457, 'learning_rate': 7.932405566600397e-06, 'epoch': 1.47}
{'loss': 0.8284, 'learning_rate': 7.929694559913249e-06, 'epoch': 1.47}
{'loss': 0.9705, 'learning_rate': 7.926983553226099e-06, 'epoch': 1.47}
{'loss': 0.8207, 'learning_rate': 7.924272546538947e-06, 'epoch': 1.47}
{'loss': 1.1405, 'learning_rate': 7.921561539851798e-06, 'epoch': 1.47}
{'loss': 0.478, 'learning_rate': 7.91885053316465e-06, 'epoch': 1.47}
{'loss': 0.3899, 'learning_rate': 7.9161395264775e-06, 'epoch': 1.47}
{'loss': 0.3261, 'learning_rate': 7.913428519790348e-06, 'epoch': 1.47}
{'loss': 1.0203, 'learning_rate': 7.910717513103198e-06, 'epoch': 1.47}
{'loss': 0.3252, 'learning_rate': 7.90800650641605e-06, 'epoch': 1.47}
{'loss': 0.5061, 'learning_rate': 7.9052954997289e-06, 'epoch': 1.47}
{'loss': 0.5262, 'learning_rate': 7.902584493041748e-06, 'epoch': 1.47}
{'loss': 0.9248, 'learning_rate': 7.8998734863546e-06, 'epoch': 1.47}
{'loss': 0.8459, 'learning_rate': 7.89716247966745e-06, 'epoch': 1.47}
{'loss': 0.6797, 'learning_rate': 7.8944514729803e-06, 'epoch': 1.47}
{'loss': 0.763, 'learning_rate': 7.891740466293149e-06, 'epoch': 1.47}
{'loss': 0.7339, 'learning_rate': 7.889029459606e-06, 'epoch': 1.47}
{'loss': 0.7194, 'learning_rate': 7.886318452918851e-06, 'epoch': 1.47}
{'loss': 0.5753, 'learning_rate': 7.883607446231701e-06, 'epoch': 1.47}
{'loss': 0.2518, 'learning_rate': 7.880896439544551e-06, 'epoch': 1.47}
{'loss': 0.4833, 'learning_rate': 7.878185432857401e-06, 'epoch': 1.47}
{'loss': 0.4611, 'learning_rate': 7.875474426170252e-06, 'epoch': 1.47}
{'loss': 0.4131, 'learning_rate': 7.872763419483102e-06, 'epoch': 1.48}
{'loss': 1.3127, 'learning_rate': 7.870052412795952e-06, 'epoch': 1.48}
{'loss': 0.5046, 'learning_rate': 7.867341406108802e-06, 'epoch': 1.48}
{'loss': 0.796, 'learning_rate': 7.864630399421652e-06, 'epoch': 1.48}
{'loss': 0.6103, 'learning_rate': 7.861919392734502e-06, 'epoch': 1.48}
{'loss': 0.6812, 'learning_rate': 7.859208386047352e-06, 'epoch': 1.48}
{'loss': 1.124, 'learning_rate': 7.856497379360202e-06, 'epoch': 1.48}
{'loss': 0.5555, 'learning_rate': 7.853786372673053e-06, 'epoch': 1.48}
{'loss': 0.8996, 'learning_rate': 7.851075365985904e-06, 'epoch': 1.48}
{'loss': 1.0582, 'learning_rate': 7.848364359298753e-06, 'epoch': 1.48}
{'loss': 0.6904, 'learning_rate': 7.845653352611603e-06, 'epoch': 1.48}
{'loss': 0.5264, 'learning_rate': 7.842942345924453e-06, 'epoch': 1.48}
{'loss': 0.879, 'learning_rate': 7.840231339237305e-06, 'epoch': 1.48}
{'loss': 0.5707, 'learning_rate': 7.837520332550153e-06, 'epoch': 1.48}
{'loss': 0.2619, 'learning_rate': 7.834809325863004e-06, 'epoch': 1.48}
{'loss': 1.1625, 'learning_rate': 7.832098319175854e-06, 'epoch': 1.48}
{'loss': 0.7555, 'learning_rate': 7.829387312488705e-06, 'epoch': 1.48}
{'loss': 0.3682, 'learning_rate': 7.826676305801554e-06, 'epoch': 1.48}
{'loss': 0.3796, 'learning_rate': 7.823965299114404e-06, 'epoch': 1.48}
{'loss': 0.6894, 'learning_rate': 7.821254292427256e-06, 'epoch': 1.48}
{'loss': 0.8114, 'learning_rate': 7.818543285740106e-06, 'epoch': 1.48}
{'loss': 0.6023, 'learning_rate': 7.815832279052954e-06, 'epoch': 1.48}
{'loss': 0.5902, 'learning_rate': 7.813121272365805e-06, 'epoch': 1.48}
{'loss': 0.5486, 'learning_rate': 7.810410265678656e-06, 'epoch': 1.48}
{'loss': 0.5045, 'learning_rate': 7.807699258991507e-06, 'epoch': 1.48}
{'loss': 0.696, 'learning_rate': 7.804988252304355e-06, 'epoch': 1.48}
{'loss': 0.8677, 'learning_rate': 7.802277245617205e-06, 'epoch': 1.48}
{'loss': 0.7395, 'learning_rate': 7.799566238930057e-06, 'epoch': 1.48}
{'loss': 0.4621, 'learning_rate': 7.796855232242907e-06, 'epoch': 1.48}
{'loss': 0.5944, 'learning_rate': 7.794144225555756e-06, 'epoch': 1.48}
{'loss': 0.3721, 'learning_rate': 7.791433218868607e-06, 'epoch': 1.48}
{'loss': 0.8495, 'learning_rate': 7.788722212181458e-06, 'epoch': 1.48}
{'loss': 0.9928, 'learning_rate': 7.786011205494308e-06, 'epoch': 1.48}
{'loss': 0.6327, 'learning_rate': 7.783300198807156e-06, 'epoch': 1.48}
{'loss': 0.6868, 'learning_rate': 7.780589192120008e-06, 'epoch': 1.48}
{'loss': 0.5273, 'learning_rate': 7.777878185432858e-06, 'epoch': 1.48}
{'loss': 1.0884, 'learning_rate': 7.775167178745708e-06, 'epoch': 1.48}
{'loss': 0.5793, 'learning_rate': 7.772456172058557e-06, 'epoch': 1.48}
{'loss': 1.0678, 'learning_rate': 7.769745165371408e-06, 'epoch': 1.48}
{'loss': 0.8874, 'learning_rate': 7.767034158684259e-06, 'epoch': 1.48}
{'loss': 0.5946, 'learning_rate': 7.764323151997109e-06, 'epoch': 1.48}
{'loss': 0.6136, 'learning_rate': 7.761612145309959e-06, 'epoch': 1.48}
{'loss': 0.8007, 'learning_rate': 7.758901138622809e-06, 'epoch': 1.48}
{'loss': 0.6009, 'learning_rate': 7.756190131935659e-06, 'epoch': 1.48}
{'loss': 0.3995, 'learning_rate': 7.75347912524851e-06, 'epoch': 1.48}
{'loss': 0.8846, 'learning_rate': 7.75076811856136e-06, 'epoch': 1.48}
{'loss': 1.2433, 'learning_rate': 7.74805711187421e-06, 'epoch': 1.48}
{'loss': 0.8688, 'learning_rate': 7.74534610518706e-06, 'epoch': 1.48}
{'loss': 0.895, 'learning_rate': 7.74263509849991e-06, 'epoch': 1.48}
{'loss': 1.0233, 'learning_rate': 7.73992409181276e-06, 'epoch': 1.48}
{'loss': 0.2502, 'learning_rate': 7.73721308512561e-06, 'epoch': 1.48}
{'loss': 0.9848, 'learning_rate': 7.73450207843846e-06, 'epoch': 1.48}
{'loss': 0.4661, 'learning_rate': 7.731791071751312e-06, 'epoch': 1.48}
{'loss': 0.2313, 'learning_rate': 7.72908006506416e-06, 'epoch': 1.48}
{'loss': 0.7625, 'learning_rate': 7.72636905837701e-06, 'epoch': 1.48}
{'loss': 0.4381, 'learning_rate': 7.72365805168986e-06, 'epoch': 1.49}
{'loss': 1.0334, 'learning_rate': 7.720947045002713e-06, 'epoch': 1.49}
{'loss': 0.4756, 'learning_rate': 7.718236038315561e-06, 'epoch': 1.49}
{'loss': 0.6965, 'learning_rate': 7.715525031628411e-06, 'epoch': 1.49}
{'loss': 0.5987, 'learning_rate': 7.712814024941261e-06, 'epoch': 1.49}

 74%|███████▍  | 8222/11066 [30:07<10:23,  4.56it/s]
 74%|███████▍  | 8223/11066 [30:07<10:17,  4.60it/s]
                                                    

 74%|███████▍  | 8223/11066 [30:07<10:17,  4.60it/s]
 74%|███████▍  | 8224/11066 [30:07<10:12,  4.64it/s]
                                                    

 74%|███████▍  | 8224/11066 [30:07<10:12,  4.64it/s]
 74%|███████▍  | 8225/11066 [30:07<10:13,  4.63it/s]
                                                    

 74%|███████▍  | 8225/11066 [30:07<10:13,  4.63it/s]
 74%|███████▍  | 8226/11066 [30:08<10:19,  4.58it/s]
                                                    

 74%|███████▍  | 8226/11066 [30:08<10:19,  4.58it/s]
 74%|███████▍  | 8227/11066 [30:08<10:14,  4.62it/s]
                                                    

 74%|███████▍  | 8227/11066 [30:08<10:14,  4.62it/s]
 74%|███████▍  | 8228/11066 [30:08<10:11,  4.64it/s]
                                                    

 74%|███████▍  | 8228/11066 [30:08<10:11,  4.64it/s]
 74%|███████▍  | 8229/11066 [30:08<10:12,  4.63it/s]
                                                    

 74%|███████▍  | 8229/11066 [30:08<10:12,  4.63it/s]
 74%|███████▍  | 8230/11066 [30:08<10:09,  4.65it/s]
                                                    

 74%|███████▍  | 8230/11066 [30:08<10:09,  4.65it/s]
 74%|███████▍  | 8231/11066 [30:09<10:10,  4.64it/s]
                                                    

 74%|███████▍  | 8231/11066 [30:09<10:10,  4.64it/s]
 74%|███████▍  | 8232/11066 [30:09<10:06,  4.67it/s]
                                                    

 74%|███████▍  | 8232/11066 [30:09<10:06,  4.67it/s]
 74%|███████▍  | 8233/11066 [30:09<10:01,  4.71it/s]
                                                    

 74%|███████▍  | 8233/11066 [30:09<10:01,  4.71it/s]
 74%|███████▍  | 8234/11066 [30:09<10:02,  4.70it/s]
                                                    

 74%|███████▍  | 8234/11066 [30:09<10:02,  4.70it/s]
 74%|███████▍  | 8235/11066 [30:10<10:09,  4.64it/s]
                                                    

 74%|███████▍  | 8235/11066 [30:10<10:09,  4.64it/s]
 74%|███████▍  | 8236/11066 [30:10<10:10,  4.63it/s]
                                                    

 74%|███████▍  | 8236/11066 [30:10<10:10,  4.63it/s]
 74%|███████▍  | 8237/11066 [30:10<10:08,  4.65it/s]
                                                    

 74%|███████▍  | 8237/11066 [30:10<10:08,  4.65it/s]
 74%|███████▍  | 8238/11066 [30:10<10:11,  4.62it/s]
                                                    

 74%|███████▍  | 8238/11066 [30:10<10:11,  4.62it/s]
 74%|███████▍  | 8239/11066 [30:10<10:11,  4.62it/s]
                                                    

 74%|███████▍  | 8239/11066 [30:10<10:11,  4.62it/s]
 74%|███████▍  | 8240/11066 [30:11<10:13,  4.61it/s]
                                                    

 74%|███████▍  | 8240/11066 [30:11<10:13,  4.61it/s]
 74%|███████▍  | 8241/11066 [30:11<10:18,  4.57it/s]
                                                    

 74%|███████▍  | 8241/11066 [30:11<10:18,  4.57it/s]
 74%|███████▍  | 8242/11066 [30:11<10:15,  4.59it/s]
                                                    

 74%|███████▍  | 8242/11066 [30:11<10:15,  4.59it/s]
 74%|███████▍  | 8243/11066 [30:11<10:15,  4.59it/s]
                                                    

 74%|███████▍  | 8243/11066 [30:11<10:15,  4.59it/s]
 74%|███████▍  | 8244/11066 [30:11<10:14,  4.59it/s]
                                                    

 74%|███████▍  | 8244/11066 [30:11<10:14,  4.59it/s]
 75%|███████▍  | 8245/11066 [30:12<10:14,  4.59it/s]
                                                    

 75%|███████▍  | 8245/11066 [30:12<10:14,  4.59it/s]
 75%|███████▍  | 8246/11066 [30:12<10:10,  4.62it/s]
                                                    

 75%|███████▍  | 8246/11066 [30:12<10:10,  4.62it/s]
 75%|███████▍  | 8247/11066 [30:12<10:10,  4.61it/s]
                                                    

 75%|███████▍  | 8247/11066 [30:12<10:10,  4.61it/s]
 75%|███████▍  | 8248/11066 [30:12<10:06,  4.64it/s]
                                                    

 75%|███████▍  | 8248/11066 [30:12<10:06,  4.64it/s]
 75%|███████▍  | 8249/11066 [30:13<10:08,  4.63it/s]
                                                    

 75%|███████▍  | 8249/11066 [30:13<10:08,  4.63it/s]
 75%|███████▍  | 8250/11066 [30:13<10:02,  4.67it/s]
                                                    

 75%|███████▍  | 8250/11066 [30:13<10:02,  4.67it/s]
 75%|███████▍  | 8251/11066 [30:13<09:58,  4.71it/s]
                                                    

 75%|███████▍  | 8251/11066 [30:13<09:58,  4.71it/s]
 75%|███████▍  | 8252/11066 [30:13<09:58,  4.70it/s]
                                                    

 75%|███████▍  | 8252/11066 [30:13<09:58,  4.70it/s]
 75%|███████▍  | 8253/11066 [30:13<10:11,  4.60it/s]
                                                    

 75%|███████▍  | 8253/11066 [30:13<10:11,  4.60it/s]
 75%|███████▍  | 8254/11066 [30:14<10:21,  4.53it/s]
                                                    

 75%|███████▍  | 8254/11066 [30:14<10:21,  4.53it/s]
 75%|███████▍  | 8255/11066 [30:14<10:25,  4.49it/s]
                                                    

 75%|███████▍  | 8255/11066 [30:14<10:25,  4.49it/s]
 75%|███████▍  | 8256/11066 [30:14<10:17,  4.55it/s]
                                                    

 75%|███████▍  | 8256/11066 [30:14<10:17,  4.55it/s]
 75%|███████▍  | 8257/11066 [30:14<10:30,  4.45it/s]
                                                    

 75%|███████▍  | 8257/11066 [30:14<10:30,  4.45it/s]
 75%|███████▍  | 8258/11066 [30:15<10:32,  4.44it/s]
                                                    

 75%|███████▍  | 8258/11066 [30:15<10:32,  4.44it/s]
 75%|███████▍  | 8259/11066 [30:15<10:31,  4.44it/s]
                                                    

 75%|███████▍  | 8259/11066 [30:15<10:31,  4.44it/s]
 75%|███████▍  | 8260/11066 [30:15<10:29,  4.46it/s]
                                                    

 75%|███████▍  | 8260/11066 [30:15<10:29,  4.46it/s]
 75%|███████▍  | 8261/11066 [30:15<10:27,  4.47it/s]
                                                    

 75%|███████▍  | 8261/11066 [30:15<10:27,  4.47it/s]
 75%|███████▍  | 8262/11066 [30:15<10:26,  4.48it/s]
                                                    

 75%|███████▍  | 8262/11066 [30:15<10:26,  4.48it/s]
 75%|███████▍  | 8263/11066 [30:16<10:24,  4.49it/s]
                                                    

 75%|███████▍  | 8263/11066 [30:16<10:24,  4.49it/s]
 75%|███████▍  | 8264/11066 [30:16<10:23,  4.49it/s]
                                                    

 75%|███████▍  | 8264/11066 [30:16<10:23,  4.49it/s]
 75%|███████▍  | 8265/11066 [30:16<10:23,  4.49it/s]
                                                    

 75%|███████▍  | 8265/11066 [30:16<10:23,  4.49it/s]
 75%|███████▍  | 8266/11066 [30:16<10:31,  4.43it/s]
                                                    

 75%|███████▍  | 8266/11066 [30:16<10:31,  4.43it/s]
 75%|███████▍  | 8267/11066 [30:17<10:41,  4.36it/s]
                                                    

 75%|███████▍  | 8267/11066 [30:17<10:41,  4.36it/s]
 75%|███████▍  | 8268/11066 [30:17<10:38,  4.38it/s]
                                                    

 75%|███████▍  | 8268/11066 [30:17<10:38,  4.38it/s]
 75%|███████▍  | 8269/11066 [30:17<10:34,  4.41it/s]
                                                    

 75%|███████▍  | 8269/11066 [30:17<10:34,  4.41it/s]
 75%|███████▍  | 8270/11066 [30:17<10:19,  4.51it/s]
                                                    

 75%|███████▍  | 8270/11066 [30:17<10:19,  4.51it/s]
 75%|███████▍  | 8271/11066 [30:17<10:21,  4.50it/s]
                                                    

 75%|███████▍  | 8271/11066 [30:17<10:21,  4.50it/s]
 75%|███████▍  | 8272/11066 [30:18<10:21,  4.49it/s]
                                                    

 75%|███████▍  | 8272/11066 [30:18<10:21,  4.49it/s]
 75%|███████▍  | 8273/11066 [30:18<10:16,  4.53it/s]
                                                    

 75%|███████▍  | 8273/11066 [30:18<10:16,  4.53it/s]
 75%|███████▍  | 8274/11066 [30:18<10:16,  4.53it/s]
                                                    

 75%|███████▍  | 8274/11066 [30:18<10:16,  4.53it/s]
 75%|███████▍  | 8275/11066 [30:18<10:11,  4.57it/s]
                                                    

 75%|███████▍  | 8275/11066 [30:18<10:11,  4.57it/s]
 75%|███████▍  | 8276/11066 [30:19<10:09,  4.58it/s]
                                                    

 75%|███████▍  | 8276/11066 [30:19<10:09,  4.58it/s]
 75%|███████▍  | 8277/11066 [30:19<10:11,  4.56it/s]
                                                    

 75%|███████▍  | 8277/11066 [30:19<10:11,  4.56it/s]
 75%|███████▍  | 8278/11066 [30:19<10:08,  4.58it/s]
                                                    

 75%|███████▍  | 8278/11066 [30:19<10:08,  4.58it/s]
 75%|███████▍  | 8279/11066 [30:19<09:59,  4.65it/s]
                                                    

 75%|███████▍  | 8279/11066 [30:19<09:59,  4.65it/s]
 75%|███████▍  | 8280/11066 [30:19<10:06,  4.59it/s]
                                                    

 75%|███████▍  | 8280/11066 [30:19<10:06,  4.59it/s]
 75%|███████▍  | 8281/11066 [30:20<10:10,  4.56it/s]
                                                    

 75%|███████▍  | 8281/11066 [30:20<10:10,  4.56it/s]
 75%|███████▍  | 8282/11066 [30:20<10:12,  4.54it/s]
                                                    

 75%|███████▍  | 8282/11066 [30:20<10:12,  4.54it/s]
 75%|███████▍  | 8283/11066 [30:20<10:14,  4.53it/s]
                                                    

 75%|███████▍  | 8283/11066 [30:20<10:14,  4.53it/s]
 75%|███████▍  | 8284/11066 [30:20<10:15,  4.52it/s]
                                                    

 75%|███████▍  | 8284/11066 [30:20<10:15,  4.52it/s]
 75%|███████▍  | 8285/11066 [30:21<10:16,  4.51it/s]
                                                    

 75%|███████▍  | 8285/11066 [30:21<10:16,  4.51it/s]
 75%|███████▍  | 8286/11066 [30:21<10:11,  4.55it/s]
                                                    

 75%|███████▍  | 8286/11066 [30:21<10:11,  4.55it/s]
 75%|███████▍  | 8287/11066 [30:21<10:06,  4.58it/s]
                                                    

 75%|███████▍  | 8287/11066 [30:21<10:06,  4.58it/s]
 75%|███████▍  | 8288/11066 [30:21<10:00,  4.63it/s]
                                                    

 75%|███████▍  | 8288/11066 [30:21<10:00,  4.63it/s]
 75%|███████▍  | 8289/11066 [30:21<09:54,  4.67it/s]
                                                    

 75%|███████▍  | 8289/11066 [30:21<09:54,  4.67it/s]
 75%|███████▍  | 8290/11066 [30:22<09:53,  4.68it/s]
                                                    

 75%|███████▍  | 8290/11066 [30:22<09:53,  4.68it/s]
 75%|███████▍  | 8291/11066 [30:22<09:52,  4.68it/s]
                                                    

 75%|███████▍  | 8291/11066 [30:22<09:52,  4.68it/s]
 75%|███████▍  | 8292/11066 [30:22<09:55,  4.65it/s]
                                                    

 75%|███████▍  | 8292/11066 [30:22<09:55,  4.65it/s]
 75%|███████▍  | 8293/11066 [30:22<09:53,  4.67it/s]
                                                    

 75%|███████▍  | 8293/11066 [30:22<09:53,  4.67it/s]
 75%|███████▍  | 8294/11066 [30:22<09:56,  4.65it/s]
                                                    

 75%|███████▍  | 8294/11066 [30:22<09:56,  4.65it/s]
 75%|███████▍  | 8295/11066 [30:23<09:56,  4.65it/s]
                                                    

 75%|███████▍  | 8295/11066 [30:23<09:56,  4.65it/s]
 75%|███████▍  | 8296/11066 [30:23<09:54,  4.66it/s]
                                                    

 75%|███████▍  | 8296/11066 [30:23<09:54,  4.66it/s]
 75%|███████▍  | 8297/11066 [30:23<09:52,  4.68it/s]
                                                    

 75%|███████▍  | 8297/11066 [30:23<09:52,  4.68it/s]
 75%|███████▍  | 8298/11066 [30:23<09:50,  4.69it/s]
                                                    

 75%|███████▍  | 8298/11066 [30:23<09:50,  4.69it/s]
 75%|███████▍  | 8299/11066 [30:24<09:59,  4.62it/s]
                                                    

 75%|███████▍  | 8299/11066 [30:24<09:59,  4.62it/s]
 75%|███████▌  | 8300/11066 [30:24<09:58,  4.62it/s]
                                                    

 75%|███████▌  | 8300/11066 [30:24<09:58,  4.62it/s]
 75%|███████▌  | 8301/11066 [30:24<09:56,  4.64it/s]
                                                    

 75%|███████▌  | 8301/11066 [30:24<09:56,  4.64it/s]
 75%|███████▌  | 8302/11066 [30:24<09:57,  4.62it/s]
                                                    

 75%|███████▌  | 8302/11066 [30:24<09:57,  4.62it/s]
 75%|███████▌  | 8303/11066 [30:24<09:53,  4.65it/s]
                                                    

 75%|███████▌  | 8303/11066 [30:24<09:53,  4.65it/s]
 75%|███████▌  | 8304/11066 [30:25<09:52,  4.67it/s]
                                                    

 75%|███████▌  | 8304/11066 [30:25<09:52,  4.67it/s]
 75%|███████▌  | 8305/11066 [30:25<09:46,  4.71it/s]
                                                    

 75%|███████▌  | 8305/11066 [30:25<09:46,  4.71it/s]
 75%|███████▌  | 8306/11066 [30:25<09:47,  4.70it/s]
                                                    

 75%|███████▌  | 8306/11066 [30:25<09:47,  4.70it/s]
 75%|███████▌  | 8307/11066 [30:25<09:52,  4.65it/s]
                                                    

 75%|███████▌  | 8307/11066 [30:25<09:52,  4.65it/s]
 75%|███████▌  | 8308/11066 [30:25<10:00,  4.59it/s]
                                                    

 75%|███████▌  | 8308/11066 [30:25<10:00,  4.59it/s]
 75%|███████▌  | 8309/11066 [30:26<10:05,  4.55it/s]
                                                    

 75%|███████▌  | 8309/11066 [30:26<10:05,  4.55it/s]
 75%|███████▌  | 8310/11066 [30:26<09:59,  4.60it/s]
                                                    

 75%|███████▌  | 8310/11066 [30:26<09:59,  4.60it/s]
 75%|███████▌  | 8311/11066 [30:26<10:03,  4.56it/s]
                                                    

 75%|███████▌  | 8311/11066 [30:26<10:03,  4.56it/s]
 75%|███████▌  | 8312/11066 [30:26<10:08,  4.52it/s]
                                                    

 75%|███████▌  | 8312/11066 [30:26<10:08,  4.52it/s]
 75%|███████▌  | 8313/11066 [30:27<10:03,  4.56it/s]
                                                    

 75%|███████▌  | 8313/11066 [30:27<10:03,  4.56it/s]
 75%|███████▌  | 8314/11066 [30:27<10:09,  4.52it/s]
                                                    

 75%|███████▌  | 8314/11066 [30:27<10:09,  4.52it/s]
 75%|███████▌  | 8315/11066 [30:27<10:20,  4.44it/s]
                                                    

 75%|███████▌  | 8315/11066 [30:27<10:20,  4.44it/s]
 75%|███████▌  | 8316/11066 [30:27<10:19,  4.44it/s]
                                                    

 75%|███████▌  | 8316/11066 [30:27<10:19,  4.44it/s]
 75%|███████▌  | 8317/11066 [30:27<10:20,  4.43it/s]
                                                    

 75%|███████▌  | 8317/11066 [30:27<10:20,  4.43it/s]
 75%|███████▌  | 8318/11066 [30:28<10:20,  4.43it/s]
                                                    

 75%|███████▌  | 8318/11066 [30:28<10:20,  4.43it/s]
 75%|███████▌  | 8319/11066 [30:28<10:18,  4.44it/s]
                                                    

 75%|███████▌  | 8319/11066 [30:28<10:18,  4.44it/s]
 75%|███████▌  | 8320/11066 [30:28<10:17,  4.45it/s]
                                                    

 75%|███████▌  | 8320/11066 [30:28<10:17,  4.45it/s]
 75%|███████▌  | 8321/11066 [30:28<10:15,  4.46it/s]
                                                    

 75%|███████▌  | 8321/11066 [30:28<10:15,  4.46it/s]
 75%|███████▌  | 8322/11066 [30:29<10:14,  4.46it/s]
                                                    

 75%|███████▌  | 8322/11066 [30:29<10:14,  4.46it/s]
 75%|███████▌  | 8323/11066 [30:29<10:13,  4.47it/s]
                                                    

 75%|███████▌  | 8323/11066 [30:29<10:13,  4.47it/s]
 75%|███████▌  | 8324/11066 [30:29<10:11,  4.48it/s]
                                                    

 75%|███████▌  | 8324/11066 [30:29<10:11,  4.48it/s]
 75%|███████▌  | 8325/11066 [30:29<10:10,  4.49it/s]
                                                    

 75%|███████▌  | 8325/11066 [30:29<10:10,  4.49it/s]
 75%|███████▌  | 8326/11066 [30:29<10:10,  4.49it/s]
                                                    

 75%|███████▌  | 8326/11066 [30:30<10:10,  4.49it/s]
 75%|███████▌  | 8327/11066 [30:30<10:09,  4.50it/s]
                                                    

 75%|███████▌  | 8327/11066 [30:30<10:09,  4.50it/s]
 75%|███████▌  | 8328/11066 [30:30<10:08,  4.50it/s]
                                                    

 75%|███████▌  | 8328/11066 [30:30<10:08,  4.50it/s]
 75%|███████▌  | 8329/11066 [30:30<10:08,  4.50it/s]
                                                    

 75%|███████▌  | 8329/11066 [30:30<10:08,  4.50it/s]
 75%|███████▌  | 8330/11066 [30:30<10:08,  4.50it/s]
                                                    

 75%|███████▌  | 8330/11066 [30:30<10:08,  4.50it/s]
 75%|███████▌  | 8331/11066 [30:31<10:08,  4.50it/s]
                                                    

 75%|███████▌  | 8331/11066 [30:31<10:08,  4.50it/s]
 75%|███████▌  | 8332/11066 [30:31<10:07,  4.50it/s]
                                                    

 75%|███████▌  | 8332/11066 [30:31<10:07,  4.50it/s]
 75%|███████▌  | 8333/11066 [30:31<10:07,  4.50it/s]
                                                    

 75%|███████▌  | 8333/11066 [30:31<10:07,  4.50it/s]
 75%|███████▌  | 8334/11066 [30:31<10:07,  4.50it/s]
                                                    

 75%|███████▌  | 8334/11066 [30:31<10:07,  4.50it/s]
 75%|███████▌  | 8335/11066 [30:32<10:08,  4.49it/s]
                                                    

 75%|███████▌  | 8335/11066 [30:32<10:08,  4.49it/s]
 75%|███████▌  | 8336/11066 [30:32<10:10,  4.47it/s]
                                                    
{'loss': 0.7566, 'learning_rate': 7.710103018254113e-06, 'epoch': 1.49}
{'loss': 0.6, 'learning_rate': 7.707392011566962e-06, 'epoch': 1.49}
{'loss': 0.8949, 'learning_rate': 7.704681004879812e-06, 'epoch': 1.49}
{'loss': 0.922, 'learning_rate': 7.701969998192663e-06, 'epoch': 1.49}
{'loss': 0.4133, 'learning_rate': 7.699258991505514e-06, 'epoch': 1.49}
{'loss': 0.9684, 'learning_rate': 7.696547984818362e-06, 'epoch': 1.49}
{'loss': 1.3043, 'learning_rate': 7.693836978131212e-06, 'epoch': 1.49}
{'loss': 0.6065, 'learning_rate': 7.691125971444064e-06, 'epoch': 1.49}
{'loss': 0.55, 'learning_rate': 7.688414964756914e-06, 'epoch': 1.49}
{'loss': 0.9427, 'learning_rate': 7.685703958069763e-06, 'epoch': 1.49}
{'loss': 0.6407, 'learning_rate': 7.682992951382614e-06, 'epoch': 1.49}
{'loss': 0.5488, 'learning_rate': 7.680281944695465e-06, 'epoch': 1.49}
{'loss': 0.6753, 'learning_rate': 7.677570938008315e-06, 'epoch': 1.49}
{'loss': 0.5487, 'learning_rate': 7.674859931321163e-06, 'epoch': 1.49}
{'loss': 0.9619, 'learning_rate': 7.672148924634015e-06, 'epoch': 1.49}
{'loss': 1.2972, 'learning_rate': 7.669437917946865e-06, 'epoch': 1.49}
{'loss': 0.6472, 'learning_rate': 7.666726911259714e-06, 'epoch': 1.49}
{'loss': 0.3026, 'learning_rate': 7.664015904572564e-06, 'epoch': 1.49}
{'loss': 0.5636, 'learning_rate': 7.661304897885416e-06, 'epoch': 1.49}
{'loss': 1.1247, 'learning_rate': 7.658593891198266e-06, 'epoch': 1.49}
{'loss': 0.8533, 'learning_rate': 7.655882884511114e-06, 'epoch': 1.49}
{'loss': 0.59, 'learning_rate': 7.653171877823966e-06, 'epoch': 1.49}
{'loss': 0.3753, 'learning_rate': 7.650460871136816e-06, 'epoch': 1.49}
{'loss': 1.2643, 'learning_rate': 7.647749864449666e-06, 'epoch': 1.49}
{'loss': 1.4287, 'learning_rate': 7.645038857762515e-06, 'epoch': 1.49}
{'loss': 0.2773, 'learning_rate': 7.642327851075366e-06, 'epoch': 1.49}
{'loss': 1.1414, 'learning_rate': 7.639616844388217e-06, 'epoch': 1.49}
{'loss': 1.0673, 'learning_rate': 7.636905837701067e-06, 'epoch': 1.49}
{'loss': 0.7876, 'learning_rate': 7.634194831013915e-06, 'epoch': 1.49}
{'loss': 0.3465, 'learning_rate': 7.631483824326767e-06, 'epoch': 1.49}
{'loss': 0.501, 'learning_rate': 7.628772817639617e-06, 'epoch': 1.49}
{'loss': 1.028, 'learning_rate': 7.626061810952468e-06, 'epoch': 1.49}
{'loss': 0.5837, 'learning_rate': 7.6233508042653165e-06, 'epoch': 1.49}
{'loss': 0.456, 'learning_rate': 7.6206397975781675e-06, 'epoch': 1.49}
{'loss': 0.9573, 'learning_rate': 7.617928790891018e-06, 'epoch': 1.49}
{'loss': 0.7422, 'learning_rate': 7.615217784203869e-06, 'epoch': 1.49}
{'loss': 0.2222, 'learning_rate': 7.612506777516717e-06, 'epoch': 1.49}
{'loss': 0.6923, 'learning_rate': 7.609795770829568e-06, 'epoch': 1.49}
{'loss': 0.8448, 'learning_rate': 7.607084764142418e-06, 'epoch': 1.49}
{'loss': 1.0488, 'learning_rate': 7.604373757455269e-06, 'epoch': 1.49}
{'loss': 0.5789, 'learning_rate': 7.601662750768118e-06, 'epoch': 1.49}
{'loss': 1.1445, 'learning_rate': 7.598951744080969e-06, 'epoch': 1.49}
{'loss': 0.7405, 'learning_rate': 7.5962407373938196e-06, 'epoch': 1.49}
{'loss': 0.8426, 'learning_rate': 7.59352973070667e-06, 'epoch': 1.49}
{'loss': 1.1669, 'learning_rate': 7.590818724019519e-06, 'epoch': 1.49}
{'loss': 0.5056, 'learning_rate': 7.588107717332369e-06, 'epoch': 1.49}
{'loss': 0.9213, 'learning_rate': 7.58539671064522e-06, 'epoch': 1.49}
{'loss': 0.7409, 'learning_rate': 7.58268570395807e-06, 'epoch': 1.49}
{'loss': 0.867, 'learning_rate': 7.5799746972709195e-06, 'epoch': 1.49}
{'loss': 0.4947, 'learning_rate': 7.57726369058377e-06, 'epoch': 1.49}
{'loss': 0.1851, 'learning_rate': 7.574552683896621e-06, 'epoch': 1.5}
{'loss': 0.5097, 'learning_rate': 7.571841677209471e-06, 'epoch': 1.5}
{'loss': 0.8268, 'learning_rate': 7.56913067052232e-06, 'epoch': 1.5}
{'loss': 1.1039, 'learning_rate': 7.566419663835171e-06, 'epoch': 1.5}
{'loss': 0.7724, 'learning_rate': 7.563708657148021e-06, 'epoch': 1.5}
{'loss': 0.7055, 'learning_rate': 7.560997650460872e-06, 'epoch': 1.5}
{'loss': 0.7112, 'learning_rate': 7.558286643773721e-06, 'epoch': 1.5}
{'loss': 0.6859, 'learning_rate': 7.555575637086572e-06, 'epoch': 1.5}
{'loss': 0.9108, 'learning_rate': 7.552864630399422e-06, 'epoch': 1.5}
{'loss': 0.6967, 'learning_rate': 7.550153623712273e-06, 'epoch': 1.5}
{'loss': 0.669, 'learning_rate': 7.547442617025121e-06, 'epoch': 1.5}
{'loss': 0.4187, 'learning_rate': 7.544731610337972e-06, 'epoch': 1.5}
{'loss': 0.7563, 'learning_rate': 7.542020603650823e-06, 'epoch': 1.5}
{'loss': 0.6327, 'learning_rate': 7.539309596963673e-06, 'epoch': 1.5}
{'loss': 0.3952, 'learning_rate': 7.5365985902765225e-06, 'epoch': 1.5}
{'loss': 0.5436, 'learning_rate': 7.533887583589373e-06, 'epoch': 1.5}
{'loss': 0.7845, 'learning_rate': 7.531176576902224e-06, 'epoch': 1.5}
{'loss': 1.043, 'learning_rate': 7.528465570215074e-06, 'epoch': 1.5}
{'loss': 0.9082, 'learning_rate': 7.525754563527923e-06, 'epoch': 1.5}
{'loss': 0.802, 'learning_rate': 7.523043556840773e-06, 'epoch': 1.5}
{'loss': 0.3468, 'learning_rate': 7.520332550153624e-06, 'epoch': 1.5}
{'loss': 0.5884, 'learning_rate': 7.517621543466474e-06, 'epoch': 1.5}
{'loss': 0.4866, 'learning_rate': 7.514910536779324e-06, 'epoch': 1.5}
{'loss': 0.3712, 'learning_rate': 7.512199530092175e-06, 'epoch': 1.5}
{'loss': 0.6535, 'learning_rate': 7.509488523405025e-06, 'epoch': 1.5}
{'loss': 0.4255, 'learning_rate': 7.506777516717876e-06, 'epoch': 1.5}
{'loss': 0.4746, 'learning_rate': 7.504066510030724e-06, 'epoch': 1.5}
{'loss': 0.6884, 'learning_rate': 7.501355503343575e-06, 'epoch': 1.5}
{'loss': 1.0978, 'learning_rate': 7.498644496656425e-06, 'epoch': 1.5}
{'loss': 0.6193, 'learning_rate': 7.495933489969275e-06, 'epoch': 1.5}
{'loss': 0.586, 'learning_rate': 7.4932224832821255e-06, 'epoch': 1.5}
{'loss': 0.939, 'learning_rate': 7.490511476594976e-06, 'epoch': 1.5}
{'loss': 0.6739, 'learning_rate': 7.487800469907826e-06, 'epoch': 1.5}
{'loss': 1.0132, 'learning_rate': 7.485089463220676e-06, 'epoch': 1.5}
{'loss': 0.552, 'learning_rate': 7.482378456533527e-06, 'epoch': 1.5}
{'loss': 0.5083, 'learning_rate': 7.479667449846376e-06, 'epoch': 1.5}
{'loss': 0.3576, 'learning_rate': 7.476956443159227e-06, 'epoch': 1.5}
{'loss': 0.4419, 'learning_rate': 7.4742454364720765e-06, 'epoch': 1.5}
{'loss': 0.796, 'learning_rate': 7.4715344297849274e-06, 'epoch': 1.5}
{'loss': 0.9608, 'learning_rate': 7.468823423097777e-06, 'epoch': 1.5}
{'loss': 0.3453, 'learning_rate': 7.466112416410628e-06, 'epoch': 1.5}
{'loss': 0.3931, 'learning_rate': 7.463401409723477e-06, 'epoch': 1.5}
{'loss': 0.9507, 'learning_rate': 7.460690403036328e-06, 'epoch': 1.5}
{'loss': 0.5254, 'learning_rate': 7.457979396349177e-06, 'epoch': 1.5}
{'loss': 0.6834, 'learning_rate': 7.455268389662028e-06, 'epoch': 1.5}
{'loss': 0.6183, 'learning_rate': 7.452557382974878e-06, 'epoch': 1.5}
{'loss': 0.5268, 'learning_rate': 7.4498463762877285e-06, 'epoch': 1.5}
{'loss': 0.723, 'learning_rate': 7.447135369600579e-06, 'epoch': 1.5}
{'loss': 0.8636, 'learning_rate': 7.444424362913429e-06, 'epoch': 1.5}
{'loss': 1.0019, 'learning_rate': 7.441713356226279e-06, 'epoch': 1.5}
{'loss': 0.4219, 'learning_rate': 7.439002349539129e-06, 'epoch': 1.5}
{'loss': 0.7839, 'learning_rate': 7.436291342851979e-06, 'epoch': 1.5}
{'loss': 0.7367, 'learning_rate': 7.433580336164829e-06, 'epoch': 1.5}
{'loss': 0.3546, 'learning_rate': 7.4308693294776795e-06, 'epoch': 1.5}
{'loss': 0.7369, 'learning_rate': 7.4281583227905304e-06, 'epoch': 1.5}
{'loss': 1.0476, 'learning_rate': 7.42544731610338e-06, 'epoch': 1.5}
{'loss': 0.8574, 'learning_rate': 7.422736309416231e-06, 'epoch': 1.51}
{'loss': 0.785, 'learning_rate': 7.42002530272908e-06, 'epoch': 1.51}
{'loss': 0.3442, 'learning_rate': 7.417314296041931e-06, 'epoch': 1.51}
{'loss': 0.4353, 'learning_rate': 7.41460328935478e-06, 'epoch': 1.51}
{'loss': 1.0711, 'learning_rate': 7.411892282667631e-06, 'epoch': 1.51}
{'loss': 0.8475, 'learning_rate': 7.4091812759804805e-06, 'epoch': 1.51}
{'loss': 0.6347, 'learning_rate': 7.4064702692933315e-06, 'epoch': 1.51}
{'loss': 0.3825, 'learning_rate': 7.403759262606181e-06, 'epoch': 1.51}

 75%|███████▌  | 8336/11066 [30:32<10:10,  4.47it/s]
 75%|███████▌  | 8337/11066 [30:32<10:11,  4.46it/s]
                                                    

 75%|███████▌  | 8337/11066 [30:32<10:11,  4.46it/s]
 75%|███████▌  | 8338/11066 [30:32<10:10,  4.47it/s]
                                                    

 75%|███████▌  | 8338/11066 [30:32<10:10,  4.47it/s]
 75%|███████▌  | 8339/11066 [30:32<10:09,  4.47it/s]
                                                    

 75%|███████▌  | 8339/11066 [30:32<10:09,  4.47it/s]
 75%|███████▌  | 8340/11066 [30:33<10:08,  4.48it/s]
                                                    

 75%|███████▌  | 8340/11066 [30:33<10:08,  4.48it/s]
 75%|███████▌  | 8341/11066 [30:33<10:07,  4.49it/s]
                                                    

 75%|███████▌  | 8341/11066 [30:33<10:07,  4.49it/s]
 75%|███████▌  | 8342/11066 [30:33<10:06,  4.49it/s]
                                                    

 75%|███████▌  | 8342/11066 [30:33<10:06,  4.49it/s]
 75%|███████▌  | 8343/11066 [30:33<10:00,  4.54it/s]
                                                    

 75%|███████▌  | 8343/11066 [30:33<10:00,  4.54it/s]
 75%|███████▌  | 8344/11066 [30:34<10:01,  4.52it/s]
                                                    

 75%|███████▌  | 8344/11066 [30:34<10:01,  4.52it/s]
 75%|███████▌  | 8345/11066 [30:34<10:05,  4.50it/s]
                                                    

 75%|███████▌  | 8345/11066 [30:34<10:05,  4.50it/s]
 75%|███████▌  | 8346/11066 [30:34<10:06,  4.48it/s]
                                                    

 75%|███████▌  | 8346/11066 [30:34<10:06,  4.48it/s]
 75%|███████▌  | 8347/11066 [30:34<10:06,  4.49it/s]
                                                    

 75%|███████▌  | 8347/11066 [30:34<10:06,  4.49it/s]
 75%|███████▌  | 8348/11066 [30:34<10:04,  4.49it/s]
                                                    

 75%|███████▌  | 8348/11066 [30:34<10:04,  4.49it/s]
 75%|███████▌  | 8349/11066 [30:35<10:01,  4.51it/s]
                                                    

 75%|███████▌  | 8349/11066 [30:35<10:01,  4.51it/s]
 75%|███████▌  | 8350/11066 [30:35<10:03,  4.50it/s]
                                                    

 75%|███████▌  | 8350/11066 [30:35<10:03,  4.50it/s]
 75%|███████▌  | 8351/11066 [30:35<10:03,  4.50it/s]
                                                    

 75%|███████▌  | 8351/11066 [30:35<10:03,  4.50it/s]
 75%|███████▌  | 8352/11066 [30:35<10:10,  4.45it/s]
                                                    

 75%|███████▌  | 8352/11066 [30:35<10:10,  4.45it/s]
 75%|███████▌  | 8353/11066 [30:36<10:11,  4.44it/s]
                                                    

 75%|███████▌  | 8353/11066 [30:36<10:11,  4.44it/s]
 75%|███████▌  | 8354/11066 [30:36<10:02,  4.50it/s]
                                                    

 75%|███████▌  | 8354/11066 [30:36<10:02,  4.50it/s]
 76%|███████▌  | 8355/11066 [30:36<10:01,  4.51it/s]
                                                    

 76%|███████▌  | 8355/11066 [30:36<10:01,  4.51it/s]
 76%|███████▌  | 8356/11066 [30:36<10:04,  4.49it/s]
                                                    

 76%|███████▌  | 8356/11066 [30:36<10:04,  4.49it/s]
 76%|███████▌  | 8357/11066 [30:36<09:55,  4.55it/s]
                                                    

 76%|███████▌  | 8357/11066 [30:36<09:55,  4.55it/s]
 76%|███████▌  | 8358/11066 [30:37<09:49,  4.60it/s]
                                                    

 76%|███████▌  | 8358/11066 [30:37<09:49,  4.60it/s]
 76%|███████▌  | 8359/11066 [30:37<09:48,  4.60it/s]
                                                    

 76%|███████▌  | 8359/11066 [30:37<09:48,  4.60it/s]
 76%|███████▌  | 8360/11066 [30:37<09:44,  4.63it/s]
                                                    

 76%|███████▌  | 8360/11066 [30:37<09:44,  4.63it/s]
 76%|███████▌  | 8361/11066 [30:37<09:41,  4.65it/s]
                                                    

 76%|███████▌  | 8361/11066 [30:37<09:41,  4.65it/s]
 76%|███████▌  | 8362/11066 [30:37<09:48,  4.60it/s]
                                                    

 76%|███████▌  | 8362/11066 [30:37<09:48,  4.60it/s]
 76%|███████▌  | 8363/11066 [30:38<09:54,  4.55it/s]
                                                    

 76%|███████▌  | 8363/11066 [30:38<09:54,  4.55it/s]
 76%|███████▌  | 8364/11066 [30:38<09:57,  4.52it/s]
                                                    

 76%|███████▌  | 8364/11066 [30:38<09:57,  4.52it/s]
 76%|███████▌  | 8365/11066 [30:38<09:59,  4.50it/s]
                                                    

 76%|███████▌  | 8365/11066 [30:38<09:59,  4.50it/s]
 76%|███████▌  | 8366/11066 [30:38<09:55,  4.53it/s]
                                                    

 76%|███████▌  | 8366/11066 [30:38<09:55,  4.53it/s]
 76%|███████▌  | 8367/11066 [30:39<09:59,  4.50it/s]
                                                    

 76%|███████▌  | 8367/11066 [30:39<09:59,  4.50it/s]
 76%|███████▌  | 8368/11066 [30:39<10:00,  4.49it/s]
                                                    

 76%|███████▌  | 8368/11066 [30:39<10:00,  4.49it/s]
 76%|███████▌  | 8369/11066 [30:39<09:55,  4.53it/s]
                                                    

 76%|███████▌  | 8369/11066 [30:39<09:55,  4.53it/s]
 76%|███████▌  | 8370/11066 [30:39<09:58,  4.50it/s]
                                                    

 76%|███████▌  | 8370/11066 [30:39<09:58,  4.50it/s]
 76%|███████▌  | 8371/11066 [30:39<10:00,  4.49it/s]
                                                    

 76%|███████▌  | 8371/11066 [30:39<10:00,  4.49it/s]
 76%|███████▌  | 8372/11066 [30:40<09:55,  4.52it/s]
                                                    

 76%|███████▌  | 8372/11066 [30:40<09:55,  4.52it/s]
 76%|███████▌  | 8373/11066 [30:40<09:57,  4.51it/s]
                                                    

 76%|███████▌  | 8373/11066 [30:40<09:57,  4.51it/s]
 76%|███████▌  | 8374/11066 [30:40<09:57,  4.51it/s]
                                                    

 76%|███████▌  | 8374/11066 [30:40<09:57,  4.51it/s]
 76%|███████▌  | 8375/11066 [30:40<09:50,  4.55it/s]
                                                    

 76%|███████▌  | 8375/11066 [30:40<09:50,  4.55it/s]
 76%|███████▌  | 8376/11066 [30:41<09:51,  4.54it/s]
                                                    

 76%|███████▌  | 8376/11066 [30:41<09:51,  4.54it/s]
 76%|███████▌  | 8377/11066 [30:41<09:56,  4.51it/s]
                                                    

 76%|███████▌  | 8377/11066 [30:41<09:56,  4.51it/s]
 76%|███████▌  | 8378/11066 [30:41<09:53,  4.53it/s]
                                                    

 76%|███████▌  | 8378/11066 [30:41<09:53,  4.53it/s]
 76%|███████▌  | 8379/11066 [30:41<09:47,  4.57it/s]
                                                    

 76%|███████▌  | 8379/11066 [30:41<09:47,  4.57it/s]
 76%|███████▌  | 8380/11066 [30:41<09:45,  4.58it/s]
                                                    

 76%|███████▌  | 8380/11066 [30:41<09:45,  4.58it/s]
 76%|███████▌  | 8381/11066 [30:42<09:42,  4.61it/s]
                                                    

 76%|███████▌  | 8381/11066 [30:42<09:42,  4.61it/s]
 76%|███████▌  | 8382/11066 [30:42<09:38,  4.64it/s]
                                                    

 76%|███████▌  | 8382/11066 [30:42<09:38,  4.64it/s]
 76%|███████▌  | 8383/11066 [30:42<09:38,  4.64it/s]
                                                    

 76%|███████▌  | 8383/11066 [30:42<09:38,  4.64it/s]
 76%|███████▌  | 8384/11066 [30:42<09:37,  4.65it/s]
                                                    

 76%|███████▌  | 8384/11066 [30:42<09:37,  4.65it/s]
 76%|███████▌  | 8385/11066 [30:43<09:43,  4.60it/s]
                                                    

 76%|███████▌  | 8385/11066 [30:43<09:43,  4.60it/s]
 76%|███████▌  | 8386/11066 [30:43<09:48,  4.56it/s]
                                                    

 76%|███████▌  | 8386/11066 [30:43<09:48,  4.56it/s]
 76%|███████▌  | 8387/11066 [30:43<09:45,  4.57it/s]
                                                    

 76%|███████▌  | 8387/11066 [30:43<09:45,  4.57it/s]
 76%|███████▌  | 8388/11066 [30:43<09:40,  4.61it/s]
                                                    

 76%|███████▌  | 8388/11066 [30:43<09:40,  4.61it/s]
 76%|███████▌  | 8389/11066 [30:43<09:38,  4.63it/s]
                                                    

 76%|███████▌  | 8389/11066 [30:43<09:38,  4.63it/s]
 76%|███████▌  | 8390/11066 [30:44<09:45,  4.57it/s]
                                                    

 76%|███████▌  | 8390/11066 [30:44<09:45,  4.57it/s]
 76%|███████▌  | 8391/11066 [30:44<09:48,  4.54it/s]
                                                    

 76%|███████▌  | 8391/11066 [30:44<09:48,  4.54it/s]
 76%|███████▌  | 8392/11066 [30:44<09:50,  4.53it/s]
                                                    

 76%|███████▌  | 8392/11066 [30:44<09:50,  4.53it/s]
 76%|███████▌  | 8393/11066 [30:44<09:51,  4.52it/s]
                                                    

 76%|███████▌  | 8393/11066 [30:44<09:51,  4.52it/s]
 76%|███████▌  | 8394/11066 [30:45<09:47,  4.55it/s]
                                                    

 76%|███████▌  | 8394/11066 [30:45<09:47,  4.55it/s]
 76%|███████▌  | 8395/11066 [30:45<09:41,  4.59it/s]
                                                    

 76%|███████▌  | 8395/11066 [30:45<09:41,  4.59it/s]
 76%|███████▌  | 8396/11066 [30:45<09:42,  4.59it/s]
                                                    

 76%|███████▌  | 8396/11066 [30:45<09:42,  4.59it/s]
 76%|███████▌  | 8397/11066 [30:45<09:40,  4.60it/s]
                                                    

 76%|███████▌  | 8397/11066 [30:45<09:40,  4.60it/s]
 76%|███████▌  | 8398/11066 [30:45<09:37,  4.62it/s]
                                                    

 76%|███████▌  | 8398/11066 [30:45<09:37,  4.62it/s]
 76%|███████▌  | 8399/11066 [30:46<09:43,  4.57it/s]
                                                    

 76%|███████▌  | 8399/11066 [30:46<09:43,  4.57it/s]
 76%|███████▌  | 8400/11066 [30:46<09:41,  4.58it/s]
                                                    

 76%|███████▌  | 8400/11066 [30:46<09:41,  4.58it/s]
 76%|███████▌  | 8401/11066 [30:46<09:37,  4.62it/s]
                                                    

 76%|███████▌  | 8401/11066 [30:46<09:37,  4.62it/s]
 76%|███████▌  | 8402/11066 [30:46<09:41,  4.58it/s]
                                                    

 76%|███████▌  | 8402/11066 [30:46<09:41,  4.58it/s]
 76%|███████▌  | 8403/11066 [30:46<09:42,  4.57it/s]
                                                    

 76%|███████▌  | 8403/11066 [30:46<09:42,  4.57it/s]
 76%|███████▌  | 8404/11066 [30:47<09:46,  4.54it/s]
                                                    

 76%|███████▌  | 8404/11066 [30:47<09:46,  4.54it/s]
 76%|███████▌  | 8405/11066 [30:47<09:58,  4.45it/s]
                                                    

 76%|███████▌  | 8405/11066 [30:47<09:58,  4.45it/s]
 76%|███████▌  | 8406/11066 [30:47<10:01,  4.42it/s]
                                                    

 76%|███████▌  | 8406/11066 [30:47<10:01,  4.42it/s]
 76%|███████▌  | 8407/11066 [30:47<10:01,  4.42it/s]
                                                    

 76%|███████▌  | 8407/11066 [30:47<10:01,  4.42it/s]
 76%|███████▌  | 8408/11066 [30:48<10:01,  4.42it/s]
                                                    

 76%|███████▌  | 8408/11066 [30:48<10:01,  4.42it/s]
 76%|███████▌  | 8409/11066 [30:48<10:00,  4.43it/s]
                                                    

 76%|███████▌  | 8409/11066 [30:48<10:00,  4.43it/s]
 76%|███████▌  | 8410/11066 [30:48<10:00,  4.42it/s]
                                                    

 76%|███████▌  | 8410/11066 [30:48<10:00,  4.42it/s]
 76%|███████▌  | 8411/11066 [30:48<09:46,  4.53it/s]
                                                    

 76%|███████▌  | 8411/11066 [30:48<09:46,  4.53it/s]
 76%|███████▌  | 8412/11066 [30:48<09:50,  4.49it/s]
                                                    

 76%|███████▌  | 8412/11066 [30:48<09:50,  4.49it/s]
 76%|███████▌  | 8413/11066 [30:49<09:51,  4.49it/s]
                                                    

 76%|███████▌  | 8413/11066 [30:49<09:51,  4.49it/s]
 76%|███████▌  | 8414/11066 [30:49<09:51,  4.48it/s]
                                                    

 76%|███████▌  | 8414/11066 [30:49<09:51,  4.48it/s]
 76%|███████▌  | 8415/11066 [30:49<09:51,  4.48it/s]
                                                    

 76%|███████▌  | 8415/11066 [30:49<09:51,  4.48it/s]
 76%|███████▌  | 8416/11066 [30:49<09:51,  4.48it/s]
                                                    

 76%|███████▌  | 8416/11066 [30:49<09:51,  4.48it/s]
 76%|███████▌  | 8417/11066 [30:50<09:51,  4.48it/s]
                                                    

 76%|███████▌  | 8417/11066 [30:50<09:51,  4.48it/s]
 76%|███████▌  | 8418/11066 [30:50<09:50,  4.48it/s]
                                                    

 76%|███████▌  | 8418/11066 [30:50<09:50,  4.48it/s]
 76%|███████▌  | 8419/11066 [30:50<09:49,  4.49it/s]
                                                    

 76%|███████▌  | 8419/11066 [30:50<09:49,  4.49it/s]
 76%|███████▌  | 8420/11066 [30:50<09:48,  4.50it/s]
                                                    

 76%|███████▌  | 8420/11066 [30:50<09:48,  4.50it/s]
 76%|███████▌  | 8421/11066 [30:51<09:47,  4.50it/s]
                                                    

 76%|███████▌  | 8421/11066 [30:51<09:47,  4.50it/s]
 76%|███████▌  | 8422/11066 [30:51<09:47,  4.50it/s]
                                                    

 76%|███████▌  | 8422/11066 [30:51<09:47,  4.50it/s]
 76%|███████▌  | 8423/11066 [30:51<09:47,  4.50it/s]
                                                    

 76%|███████▌  | 8423/11066 [30:51<09:47,  4.50it/s]
 76%|███████▌  | 8424/11066 [30:51<09:46,  4.50it/s]
                                                    

 76%|███████▌  | 8424/11066 [30:51<09:46,  4.50it/s]
 76%|███████▌  | 8425/11066 [30:51<09:46,  4.50it/s]
                                                    

 76%|███████▌  | 8425/11066 [30:51<09:46,  4.50it/s]
 76%|███████▌  | 8426/11066 [30:52<09:46,  4.50it/s]
                                                    

 76%|███████▌  | 8426/11066 [30:52<09:46,  4.50it/s]
 76%|███████▌  | 8427/11066 [30:52<09:46,  4.50it/s]
                                                    

 76%|███████▌  | 8427/11066 [30:52<09:46,  4.50it/s]
 76%|███████▌  | 8428/11066 [30:52<09:46,  4.50it/s]
                                                    

 76%|███████▌  | 8428/11066 [30:52<09:46,  4.50it/s]
 76%|███████▌  | 8429/11066 [30:52<09:38,  4.56it/s]
                                                    

 76%|███████▌  | 8429/11066 [30:52<09:38,  4.56it/s]
 76%|███████▌  | 8430/11066 [30:52<09:39,  4.55it/s]
                                                    

 76%|███████▌  | 8430/11066 [30:52<09:39,  4.55it/s]
 76%|███████▌  | 8431/11066 [30:53<09:45,  4.50it/s]
                                                    

 76%|███████▌  | 8431/11066 [30:53<09:45,  4.50it/s]
 76%|███████▌  | 8432/11066 [30:53<09:47,  4.48it/s]
                                                    

 76%|███████▌  | 8432/11066 [30:53<09:47,  4.48it/s]
 76%|███████▌  | 8433/11066 [30:53<09:47,  4.48it/s]
                                                    

 76%|███████▌  | 8433/11066 [30:53<09:47,  4.48it/s]
 76%|███████▌  | 8434/11066 [30:53<09:38,  4.55it/s]
                                                    

 76%|███████▌  | 8434/11066 [30:53<09:38,  4.55it/s]
 76%|███████▌  | 8435/11066 [30:54<09:43,  4.51it/s]
                                                    

 76%|███████▌  | 8435/11066 [30:54<09:43,  4.51it/s]
 76%|███████▌  | 8436/11066 [30:54<09:47,  4.48it/s]
                                                    

 76%|███████▌  | 8436/11066 [30:54<09:47,  4.48it/s]
 76%|███████▌  | 8437/11066 [30:54<09:54,  4.42it/s]
                                                    

 76%|███████▌  | 8437/11066 [30:54<09:54,  4.42it/s]
 76%|███████▋  | 8438/11066 [30:54<09:51,  4.44it/s]
                                                    

 76%|███████▋  | 8438/11066 [30:54<09:51,  4.44it/s]
 76%|███████▋  | 8439/11066 [30:55<09:51,  4.44it/s]
                                                    

 76%|███████▋  | 8439/11066 [30:55<09:51,  4.44it/s]
 76%|███████▋  | 8440/11066 [30:55<09:51,  4.44it/s]
                                                    

 76%|███████▋  | 8440/11066 [30:55<09:51,  4.44it/s]
 76%|███████▋  | 8441/11066 [30:55<09:49,  4.45it/s]
                                                    

 76%|███████▋  | 8441/11066 [30:55<09:49,  4.45it/s]
 76%|███████▋  | 8442/11066 [30:55<09:47,  4.47it/s]
                                                    

 76%|███████▋  | 8442/11066 [30:55<09:47,  4.47it/s]
 76%|███████▋  | 8443/11066 [30:55<09:45,  4.48it/s]
                                                    

 76%|███████▋  | 8443/11066 [30:55<09:45,  4.48it/s]
 76%|███████▋  | 8444/11066 [30:56<09:44,  4.48it/s]
                                                    

 76%|███████▋  | 8444/11066 [30:56<09:44,  4.48it/s]
 76%|███████▋  | 8445/11066 [30:56<09:44,  4.48it/s]
                                                    

 76%|███████▋  | 8445/11066 [30:56<09:44,  4.48it/s]
 76%|███████▋  | 8446/11066 [30:56<09:43,  4.49it/s]
                                                    

 76%|███████▋  | 8446/11066 [30:56<09:43,  4.49it/s]
 76%|███████▋  | 8447/11066 [30:56<09:42,  4.50it/s]
                                                    

 76%|███████▋  | 8447/11066 [30:56<09:42,  4.50it/s]
 76%|███████▋  | 8448/11066 [30:57<09:42,  4.50it/s]
                                                    

 76%|███████▋  | 8448/11066 [30:57<09:42,  4.50it/s]
 76%|███████▋  | 8449/11066 [30:57<09:41,  4.50it/s]
                                                    
{'loss': 0.544, 'learning_rate': 7.401048255919032e-06, 'epoch': 1.51}
{'loss': 0.9881, 'learning_rate': 7.398337249231882e-06, 'epoch': 1.51}
{'loss': 0.8659, 'learning_rate': 7.395626242544732e-06, 'epoch': 1.51}
{'loss': 1.0478, 'learning_rate': 7.392915235857582e-06, 'epoch': 1.51}
{'loss': 0.3521, 'learning_rate': 7.390204229170432e-06, 'epoch': 1.51}
{'loss': 1.3313, 'learning_rate': 7.3874932224832825e-06, 'epoch': 1.51}
{'loss': 0.8493, 'learning_rate': 7.384782215796133e-06, 'epoch': 1.51}
{'loss': 1.0239, 'learning_rate': 7.382071209108983e-06, 'epoch': 1.51}
{'loss': 0.5812, 'learning_rate': 7.379360202421833e-06, 'epoch': 1.51}
{'loss': 0.6302, 'learning_rate': 7.376649195734683e-06, 'epoch': 1.51}
{'loss': 0.8121, 'learning_rate': 7.373938189047533e-06, 'epoch': 1.51}
{'loss': 0.5729, 'learning_rate': 7.371227182360383e-06, 'epoch': 1.51}
{'loss': 0.9677, 'learning_rate': 7.368516175673234e-06, 'epoch': 1.51}
{'loss': 0.863, 'learning_rate': 7.3658051689860835e-06, 'epoch': 1.51}
{'loss': 0.901, 'learning_rate': 7.3630941622989345e-06, 'epoch': 1.51}
{'loss': 0.5833, 'learning_rate': 7.360383155611784e-06, 'epoch': 1.51}
{'loss': 0.941, 'learning_rate': 7.357672148924635e-06, 'epoch': 1.51}
{'loss': 1.1317, 'learning_rate': 7.354961142237484e-06, 'epoch': 1.51}
{'loss': 0.5051, 'learning_rate': 7.352250135550335e-06, 'epoch': 1.51}
{'loss': 0.8127, 'learning_rate': 7.349539128863184e-06, 'epoch': 1.51}
{'loss': 1.2771, 'learning_rate': 7.346828122176035e-06, 'epoch': 1.51}
{'loss': 1.1447, 'learning_rate': 7.3441171154888855e-06, 'epoch': 1.51}
{'loss': 0.5847, 'learning_rate': 7.341406108801736e-06, 'epoch': 1.51}
{'loss': 0.4691, 'learning_rate': 7.338695102114586e-06, 'epoch': 1.51}
{'loss': 0.3858, 'learning_rate': 7.335984095427436e-06, 'epoch': 1.51}
{'loss': 0.7011, 'learning_rate': 7.333273088740286e-06, 'epoch': 1.51}
{'loss': 0.4833, 'learning_rate': 7.330562082053136e-06, 'epoch': 1.51}
{'loss': 0.596, 'learning_rate': 7.327851075365986e-06, 'epoch': 1.51}
{'loss': 0.8733, 'learning_rate': 7.3251400686788355e-06, 'epoch': 1.51}
{'loss': 0.7442, 'learning_rate': 7.3224290619916865e-06, 'epoch': 1.51}
{'loss': 0.5954, 'learning_rate': 7.319718055304536e-06, 'epoch': 1.51}
{'loss': 0.2545, 'learning_rate': 7.317007048617387e-06, 'epoch': 1.51}
{'loss': 0.7818, 'learning_rate': 7.314296041930237e-06, 'epoch': 1.51}
{'loss': 1.0704, 'learning_rate': 7.311585035243087e-06, 'epoch': 1.51}
{'loss': 0.3638, 'learning_rate': 7.308874028555937e-06, 'epoch': 1.51}
{'loss': 0.9443, 'learning_rate': 7.306163021868787e-06, 'epoch': 1.51}
{'loss': 0.5985, 'learning_rate': 7.3034520151816375e-06, 'epoch': 1.51}
{'loss': 0.6278, 'learning_rate': 7.300741008494488e-06, 'epoch': 1.51}
{'loss': 0.8745, 'learning_rate': 7.298030001807338e-06, 'epoch': 1.51}
{'loss': 0.3822, 'learning_rate': 7.295318995120188e-06, 'epoch': 1.51}
{'loss': 0.4006, 'learning_rate': 7.292607988433038e-06, 'epoch': 1.51}
{'loss': 0.5727, 'learning_rate': 7.289896981745888e-06, 'epoch': 1.51}
{'loss': 1.0015, 'learning_rate': 7.287185975058738e-06, 'epoch': 1.51}
{'loss': 0.6898, 'learning_rate': 7.284474968371589e-06, 'epoch': 1.51}
{'loss': 0.5028, 'learning_rate': 7.2817639616844385e-06, 'epoch': 1.51}
{'loss': 0.7508, 'learning_rate': 7.2790529549972895e-06, 'epoch': 1.51}
{'loss': 1.0986, 'learning_rate': 7.276341948310139e-06, 'epoch': 1.51}
{'loss': 0.6106, 'learning_rate': 7.27363094162299e-06, 'epoch': 1.52}
{'loss': 0.4873, 'learning_rate': 7.270919934935839e-06, 'epoch': 1.52}
{'loss': 0.5998, 'learning_rate': 7.26820892824869e-06, 'epoch': 1.52}
{'loss': 0.7228, 'learning_rate': 7.265497921561539e-06, 'epoch': 1.52}
{'loss': 0.9796, 'learning_rate': 7.26278691487439e-06, 'epoch': 1.52}
{'loss': 0.5247, 'learning_rate': 7.2600759081872405e-06, 'epoch': 1.52}
{'loss': 0.4997, 'learning_rate': 7.257364901500091e-06, 'epoch': 1.52}
{'loss': 0.359, 'learning_rate': 7.254653894812941e-06, 'epoch': 1.52}
{'loss': 1.0076, 'learning_rate': 7.251942888125791e-06, 'epoch': 1.52}
{'loss': 0.5428, 'learning_rate': 7.249231881438641e-06, 'epoch': 1.52}
{'loss': 0.8909, 'learning_rate': 7.246520874751491e-06, 'epoch': 1.52}
{'loss': 0.3545, 'learning_rate': 7.243809868064341e-06, 'epoch': 1.52}
{'loss': 0.4079, 'learning_rate': 7.241098861377191e-06, 'epoch': 1.52}
{'loss': 0.8445, 'learning_rate': 7.2383878546900415e-06, 'epoch': 1.52}
{'loss': 0.3583, 'learning_rate': 7.235676848002892e-06, 'epoch': 1.52}
{'loss': 0.5734, 'learning_rate': 7.232965841315742e-06, 'epoch': 1.52}
{'loss': 0.6661, 'learning_rate': 7.230254834628593e-06, 'epoch': 1.52}
{'loss': 0.4528, 'learning_rate': 7.227543827941442e-06, 'epoch': 1.52}
{'loss': 0.9728, 'learning_rate': 7.224832821254293e-06, 'epoch': 1.52}
{'loss': 0.8578, 'learning_rate': 7.222121814567142e-06, 'epoch': 1.52}
{'loss': 0.7047, 'learning_rate': 7.219410807879993e-06, 'epoch': 1.52}
{'loss': 0.7709, 'learning_rate': 7.216699801192843e-06, 'epoch': 1.52}
{'loss': 0.614, 'learning_rate': 7.213988794505694e-06, 'epoch': 1.52}
{'loss': 0.5528, 'learning_rate': 7.211277787818543e-06, 'epoch': 1.52}
{'loss': 0.4512, 'learning_rate': 7.208566781131394e-06, 'epoch': 1.52}
{'loss': 0.2948, 'learning_rate': 7.205855774444243e-06, 'epoch': 1.52}
{'loss': 1.4246, 'learning_rate': 7.203144767757094e-06, 'epoch': 1.52}
{'loss': 0.4908, 'learning_rate': 7.200433761069944e-06, 'epoch': 1.52}
{'loss': 0.6584, 'learning_rate': 7.197722754382794e-06, 'epoch': 1.52}
{'loss': 0.7397, 'learning_rate': 7.1950117476956445e-06, 'epoch': 1.52}
{'loss': 0.7471, 'learning_rate': 7.192300741008495e-06, 'epoch': 1.52}
{'loss': 0.6738, 'learning_rate': 7.189589734321345e-06, 'epoch': 1.52}
{'loss': 1.0142, 'learning_rate': 7.186878727634195e-06, 'epoch': 1.52}
{'loss': 0.5617, 'learning_rate': 7.184167720947045e-06, 'epoch': 1.52}
{'loss': 0.8871, 'learning_rate': 7.181456714259895e-06, 'epoch': 1.52}
{'loss': 0.753, 'learning_rate': 7.178745707572745e-06, 'epoch': 1.52}
{'loss': 0.774, 'learning_rate': 7.1760347008855955e-06, 'epoch': 1.52}
{'loss': 0.8231, 'learning_rate': 7.173323694198446e-06, 'epoch': 1.52}
{'loss': 0.7353, 'learning_rate': 7.170612687511297e-06, 'epoch': 1.52}
{'loss': 0.2894, 'learning_rate': 7.167901680824146e-06, 'epoch': 1.52}
{'loss': 0.869, 'learning_rate': 7.165190674136997e-06, 'epoch': 1.52}
{'loss': 0.9516, 'learning_rate': 7.162479667449846e-06, 'epoch': 1.52}
{'loss': 0.9238, 'learning_rate': 7.159768660762697e-06, 'epoch': 1.52}
{'loss': 1.003, 'learning_rate': 7.157057654075546e-06, 'epoch': 1.52}
{'loss': 0.7044, 'learning_rate': 7.154346647388397e-06, 'epoch': 1.52}
{'loss': 0.7875, 'learning_rate': 7.151635640701247e-06, 'epoch': 1.52}
{'loss': 1.1253, 'learning_rate': 7.148924634014098e-06, 'epoch': 1.52}
{'loss': 0.8505, 'learning_rate': 7.146213627326948e-06, 'epoch': 1.52}
{'loss': 1.2931, 'learning_rate': 7.143502620639798e-06, 'epoch': 1.52}
{'loss': 1.0084, 'learning_rate': 7.140791613952648e-06, 'epoch': 1.52}
{'loss': 0.1755, 'learning_rate': 7.138080607265498e-06, 'epoch': 1.52}
{'loss': 0.5311, 'learning_rate': 7.135369600578348e-06, 'epoch': 1.52}
{'loss': 0.8491, 'learning_rate': 7.1326585938911985e-06, 'epoch': 1.52}
{'loss': 0.834, 'learning_rate': 7.129947587204049e-06, 'epoch': 1.52}
{'loss': 0.688, 'learning_rate': 7.127236580516899e-06, 'epoch': 1.52}
{'loss': 0.6879, 'learning_rate': 7.124525573829749e-06, 'epoch': 1.53}
{'loss': 0.4357, 'learning_rate': 7.121814567142599e-06, 'epoch': 1.53}
{'loss': 0.52, 'learning_rate': 7.119103560455449e-06, 'epoch': 1.53}
{'loss': 1.3684, 'learning_rate': 7.1163925537683e-06, 'epoch': 1.53}
{'loss': 0.8686, 'learning_rate': 7.113681547081149e-06, 'epoch': 1.53}
{'loss': 1.1816, 'learning_rate': 7.110970540394e-06, 'epoch': 1.53}
{'loss': 0.5505, 'learning_rate': 7.10825953370685e-06, 'epoch': 1.53}
{'loss': 0.9164, 'learning_rate': 7.105548527019701e-06, 'epoch': 1.53}
{'loss': 0.7786, 'learning_rate': 7.10283752033255e-06, 'epoch': 1.53}
{'loss': 0.3617, 'learning_rate': 7.100126513645401e-06, 'epoch': 1.53}
{'loss': 1.1011, 'learning_rate': 7.09741550695825e-06, 'epoch': 1.53}

 76%|███████▋  | 8449/11066 [30:57<09:41,  4.50it/s]
 76%|███████▋  | 8450/11066 [30:57<09:40,  4.50it/s]
                                                    

 76%|███████▋  | 8450/11066 [30:57<09:40,  4.50it/s]
 76%|███████▋  | 8451/11066 [30:57<09:40,  4.50it/s]
                                                    

 76%|███████▋  | 8451/11066 [30:57<09:40,  4.50it/s]
 76%|███████▋  | 8452/11066 [30:57<09:40,  4.50it/s]
                                                    

 76%|███████▋  | 8452/11066 [30:57<09:40,  4.50it/s]
 76%|███████▋  | 8453/11066 [30:58<09:40,  4.50it/s]
                                                    

 76%|███████▋  | 8453/11066 [30:58<09:40,  4.50it/s]
 76%|███████▋  | 8454/11066 [30:58<09:39,  4.50it/s]
                                                    

 76%|███████▋  | 8454/11066 [30:58<09:39,  4.50it/s]
 76%|███████▋  | 8455/11066 [30:58<09:39,  4.51it/s]
                                                    

 76%|███████▋  | 8455/11066 [30:58<09:39,  4.51it/s]
 76%|███████▋  | 8456/11066 [30:58<09:39,  4.50it/s]
                                                    

 76%|███████▋  | 8456/11066 [30:58<09:39,  4.50it/s]
 76%|███████▋  | 8457/11066 [30:59<09:39,  4.50it/s]
                                                    

 76%|███████▋  | 8457/11066 [30:59<09:39,  4.50it/s]
 76%|███████▋  | 8458/11066 [30:59<09:39,  4.50it/s]
                                                    

 76%|███████▋  | 8458/11066 [30:59<09:39,  4.50it/s]
 76%|███████▋  | 8459/11066 [30:59<09:38,  4.51it/s]
                                                    

 76%|███████▋  | 8459/11066 [30:59<09:38,  4.51it/s]
 76%|███████▋  | 8460/11066 [30:59<09:41,  4.48it/s]
                                                    

 76%|███████▋  | 8460/11066 [30:59<09:41,  4.48it/s]
 76%|███████▋  | 8461/11066 [30:59<09:43,  4.46it/s]
                                                    

 76%|███████▋  | 8461/11066 [30:59<09:43,  4.46it/s]
 76%|███████▋  | 8462/11066 [31:00<09:49,  4.42it/s]
                                                    

 76%|███████▋  | 8462/11066 [31:00<09:49,  4.42it/s]
 76%|███████▋  | 8463/11066 [31:00<09:47,  4.43it/s]
                                                    

 76%|███████▋  | 8463/11066 [31:00<09:47,  4.43it/s]
 76%|███████▋  | 8464/11066 [31:00<09:40,  4.48it/s]
                                                    

 76%|███████▋  | 8464/11066 [31:00<09:40,  4.48it/s]
 76%|███████▋  | 8465/11066 [31:00<09:32,  4.54it/s]
                                                    

 76%|███████▋  | 8465/11066 [31:00<09:32,  4.54it/s]
 77%|███████▋  | 8466/11066 [31:01<09:38,  4.50it/s]
                                                    

 77%|███████▋  | 8466/11066 [31:01<09:38,  4.50it/s]
 77%|███████▋  | 8467/11066 [31:01<09:37,  4.50it/s]
                                                    

 77%|███████▋  | 8467/11066 [31:01<09:37,  4.50it/s]
 77%|███████▋  | 8468/11066 [31:01<09:38,  4.49it/s]
                                                    

 77%|███████▋  | 8468/11066 [31:01<09:38,  4.49it/s]
 77%|███████▋  | 8469/11066 [31:01<09:32,  4.53it/s]
                                                    

 77%|███████▋  | 8469/11066 [31:01<09:32,  4.53it/s]
 77%|███████▋  | 8470/11066 [31:01<09:31,  4.54it/s]
                                                    

 77%|███████▋  | 8470/11066 [31:01<09:31,  4.54it/s]
 77%|███████▋  | 8471/11066 [31:02<09:32,  4.53it/s]
                                                    

 77%|███████▋  | 8471/11066 [31:02<09:32,  4.53it/s]
 77%|███████▋  | 8472/11066 [31:02<09:33,  4.52it/s]
                                                    

 77%|███████▋  | 8472/11066 [31:02<09:33,  4.52it/s]
 77%|███████▋  | 8473/11066 [31:02<09:34,  4.51it/s]
                                                    

 77%|███████▋  | 8473/11066 [31:02<09:34,  4.51it/s]
 77%|███████▋  | 8474/11066 [31:02<09:35,  4.50it/s]
                                                    

 77%|███████▋  | 8474/11066 [31:02<09:35,  4.50it/s]
 77%|███████▋  | 8475/11066 [31:03<09:35,  4.50it/s]
                                                    

 77%|███████▋  | 8475/11066 [31:03<09:35,  4.50it/s]
 77%|███████▋  | 8476/11066 [31:03<09:35,  4.50it/s]
                                                    

 77%|███████▋  | 8476/11066 [31:03<09:35,  4.50it/s]
 77%|███████▋  | 8477/11066 [31:03<09:35,  4.50it/s]
                                                    

 77%|███████▋  | 8477/11066 [31:03<09:35,  4.50it/s]
 77%|███████▋  | 8478/11066 [31:03<09:35,  4.50it/s]
                                                    

 77%|███████▋  | 8478/11066 [31:03<09:35,  4.50it/s]
 77%|███████▋  | 8479/11066 [31:03<09:34,  4.50it/s]
                                                    

 77%|███████▋  | 8479/11066 [31:03<09:34,  4.50it/s]
 77%|███████▋  | 8480/11066 [31:04<09:30,  4.53it/s]
                                                    

 77%|███████▋  | 8480/11066 [31:04<09:30,  4.53it/s]
 77%|███████▋  | 8481/11066 [31:04<09:24,  4.58it/s]
                                                    

 77%|███████▋  | 8481/11066 [31:04<09:24,  4.58it/s]
 77%|███████▋  | 8482/11066 [31:04<09:22,  4.59it/s]
                                                    

 77%|███████▋  | 8482/11066 [31:04<09:22,  4.59it/s]
 77%|███████▋  | 8483/11066 [31:04<09:25,  4.56it/s]
                                                    

 77%|███████▋  | 8483/11066 [31:04<09:25,  4.56it/s]
 77%|███████▋  | 8484/11066 [31:04<09:28,  4.54it/s]
                                                    

 77%|███████▋  | 8484/11066 [31:04<09:28,  4.54it/s]
 77%|███████▋  | 8485/11066 [31:05<09:26,  4.56it/s]
                                                    

 77%|███████▋  | 8485/11066 [31:05<09:26,  4.56it/s]
 77%|███████▋  | 8486/11066 [31:05<09:31,  4.52it/s]
                                                    

 77%|███████▋  | 8486/11066 [31:05<09:31,  4.52it/s]
 77%|███████▋  | 8487/11066 [31:05<09:32,  4.50it/s]
                                                    

 77%|███████▋  | 8487/11066 [31:05<09:32,  4.50it/s]
 77%|███████▋  | 8488/11066 [31:05<09:32,  4.51it/s]
                                                    

 77%|███████▋  | 8488/11066 [31:05<09:32,  4.51it/s]
 77%|███████▋  | 8489/11066 [31:06<09:37,  4.47it/s]
                                                    

 77%|███████▋  | 8489/11066 [31:06<09:37,  4.47it/s]
 77%|███████▋  | 8490/11066 [31:06<09:38,  4.45it/s]
                                                    

 77%|███████▋  | 8490/11066 [31:06<09:38,  4.45it/s]
 77%|███████▋  | 8491/11066 [31:06<09:25,  4.55it/s]
                                                    

 77%|███████▋  | 8491/11066 [31:06<09:25,  4.55it/s]
 77%|███████▋  | 8492/11066 [31:06<09:24,  4.56it/s]
                                                    

 77%|███████▋  | 8492/11066 [31:06<09:24,  4.56it/s]
 77%|███████▋  | 8493/11066 [31:06<09:20,  4.59it/s]
                                                    

 77%|███████▋  | 8493/11066 [31:06<09:20,  4.59it/s]
 77%|███████▋  | 8494/11066 [31:07<09:24,  4.56it/s]
                                                    

 77%|███████▋  | 8494/11066 [31:07<09:24,  4.56it/s]
 77%|███████▋  | 8495/11066 [31:07<09:18,  4.60it/s]
                                                    

 77%|███████▋  | 8495/11066 [31:07<09:18,  4.60it/s]
 77%|███████▋  | 8496/11066 [31:07<09:14,  4.63it/s]
                                                    

 77%|███████▋  | 8496/11066 [31:07<09:14,  4.63it/s]
 77%|███████▋  | 8497/11066 [31:07<09:12,  4.65it/s]
                                                    

 77%|███████▋  | 8497/11066 [31:07<09:12,  4.65it/s]
 77%|███████▋  | 8498/11066 [31:08<09:18,  4.60it/s]
                                                    

 77%|███████▋  | 8498/11066 [31:08<09:18,  4.60it/s]
 77%|███████▋  | 8499/11066 [31:08<09:13,  4.63it/s]
                                                    

 77%|███████▋  | 8499/11066 [31:08<09:13,  4.63it/s]
 77%|███████▋  | 8500/11066 [31:08<09:19,  4.59it/s]
                                                    

 77%|███████▋  | 8500/11066 [31:08<09:19,  4.59it/s]
 77%|███████▋  | 8501/11066 [31:08<09:22,  4.56it/s]
                                                    

 77%|███████▋  | 8501/11066 [31:08<09:22,  4.56it/s]
 77%|███████▋  | 8502/11066 [31:08<09:17,  4.60it/s]
                                                    

 77%|███████▋  | 8502/11066 [31:08<09:17,  4.60it/s]
 77%|███████▋  | 8503/11066 [31:09<09:16,  4.61it/s]
                                                    

 77%|███████▋  | 8503/11066 [31:09<09:16,  4.61it/s]
 77%|███████▋  | 8504/11066 [31:09<09:10,  4.65it/s]
                                                    

 77%|███████▋  | 8504/11066 [31:09<09:10,  4.65it/s]
 77%|███████▋  | 8505/11066 [31:09<09:05,  4.69it/s]
                                                    

 77%|███████▋  | 8505/11066 [31:09<09:05,  4.69it/s]
 77%|███████▋  | 8506/11066 [31:09<09:05,  4.69it/s]
                                                    

 77%|███████▋  | 8506/11066 [31:09<09:05,  4.69it/s]
 77%|███████▋  | 8507/11066 [31:10<09:07,  4.67it/s]
                                                    

 77%|███████▋  | 8507/11066 [31:10<09:07,  4.67it/s]
 77%|███████▋  | 8508/11066 [31:10<09:08,  4.67it/s]
                                                    

 77%|███████▋  | 8508/11066 [31:10<09:08,  4.67it/s]
 77%|███████▋  | 8509/11066 [31:10<09:07,  4.67it/s]
                                                    

 77%|███████▋  | 8509/11066 [31:10<09:07,  4.67it/s]
 77%|███████▋  | 8510/11066 [31:10<09:05,  4.69it/s]
                                                    

 77%|███████▋  | 8510/11066 [31:10<09:05,  4.69it/s]
 77%|███████▋  | 8511/11066 [31:10<09:04,  4.69it/s]
                                                    

 77%|███████▋  | 8511/11066 [31:10<09:04,  4.69it/s]
 77%|███████▋  | 8512/11066 [31:11<09:06,  4.67it/s]
                                                    

 77%|███████▋  | 8512/11066 [31:11<09:06,  4.67it/s]
 77%|███████▋  | 8513/11066 [31:11<09:10,  4.63it/s]
                                                    

 77%|███████▋  | 8513/11066 [31:11<09:10,  4.63it/s]
 77%|███████▋  | 8514/11066 [31:11<09:16,  4.58it/s]
                                                    

 77%|███████▋  | 8514/11066 [31:11<09:16,  4.58it/s]
 77%|███████▋  | 8515/11066 [31:11<09:11,  4.62it/s]
                                                    

 77%|███████▋  | 8515/11066 [31:11<09:11,  4.62it/s]
 77%|███████▋  | 8516/11066 [31:11<09:06,  4.66it/s]
                                                    

 77%|███████▋  | 8516/11066 [31:11<09:06,  4.66it/s]
 77%|███████▋  | 8517/11066 [31:12<09:09,  4.64it/s]
                                                    

 77%|███████▋  | 8517/11066 [31:12<09:09,  4.64it/s]
 77%|███████▋  | 8518/11066 [31:12<09:07,  4.65it/s]
                                                    

 77%|███████▋  | 8518/11066 [31:12<09:07,  4.65it/s]
 77%|███████▋  | 8519/11066 [31:12<09:05,  4.67it/s]
                                                    

 77%|███████▋  | 8519/11066 [31:12<09:05,  4.67it/s]
 77%|███████▋  | 8520/11066 [31:12<09:07,  4.65it/s]
                                                    

 77%|███████▋  | 8520/11066 [31:12<09:07,  4.65it/s]
 77%|███████▋  | 8521/11066 [31:13<09:09,  4.63it/s]
                                                    

 77%|███████▋  | 8521/11066 [31:13<09:09,  4.63it/s]
 77%|███████▋  | 8522/11066 [31:13<09:06,  4.65it/s]
                                                    

 77%|███████▋  | 8522/11066 [31:13<09:06,  4.65it/s]
 77%|███████▋  | 8523/11066 [31:13<09:04,  4.67it/s]
                                                    

 77%|███████▋  | 8523/11066 [31:13<09:04,  4.67it/s]
 77%|███████▋  | 8524/11066 [31:13<09:02,  4.69it/s]
                                                    

 77%|███████▋  | 8524/11066 [31:13<09:02,  4.69it/s]
 77%|███████▋  | 8525/11066 [31:13<09:00,  4.70it/s]
                                                    

 77%|███████▋  | 8525/11066 [31:13<09:00,  4.70it/s]
 77%|███████▋  | 8526/11066 [31:14<09:08,  4.63it/s]
                                                    

 77%|███████▋  | 8526/11066 [31:14<09:08,  4.63it/s]
 77%|███████▋  | 8527/11066 [31:14<09:05,  4.65it/s]
                                                    

 77%|███████▋  | 8527/11066 [31:14<09:05,  4.65it/s]
 77%|███████▋  | 8528/11066 [31:14<09:11,  4.60it/s]
                                                    

 77%|███████▋  | 8528/11066 [31:14<09:11,  4.60it/s]
 77%|███████▋  | 8529/11066 [31:14<09:10,  4.60it/s]
                                                    

 77%|███████▋  | 8529/11066 [31:14<09:10,  4.60it/s]
 77%|███████▋  | 8530/11066 [31:14<09:10,  4.61it/s]
                                                    

 77%|███████▋  | 8530/11066 [31:14<09:10,  4.61it/s]
 77%|███████▋  | 8531/11066 [31:15<09:13,  4.58it/s]
                                                    

 77%|███████▋  | 8531/11066 [31:15<09:13,  4.58it/s]
 77%|███████▋  | 8532/11066 [31:15<09:17,  4.55it/s]
                                                    

 77%|███████▋  | 8532/11066 [31:15<09:17,  4.55it/s]
 77%|███████▋  | 8533/11066 [31:15<09:11,  4.59it/s]
                                                    

 77%|███████▋  | 8533/11066 [31:15<09:11,  4.59it/s]
 77%|███████▋  | 8534/11066 [31:15<09:10,  4.60it/s]
                                                    

 77%|███████▋  | 8534/11066 [31:15<09:10,  4.60it/s]
 77%|███████▋  | 8535/11066 [31:16<09:11,  4.59it/s]
                                                    

 77%|███████▋  | 8535/11066 [31:16<09:11,  4.59it/s]
 77%|███████▋  | 8536/11066 [31:16<09:14,  4.57it/s]
                                                    

 77%|███████▋  | 8536/11066 [31:16<09:14,  4.57it/s]
 77%|███████▋  | 8537/11066 [31:16<09:16,  4.55it/s]
                                                    

 77%|███████▋  | 8537/11066 [31:16<09:16,  4.55it/s]
 77%|███████▋  | 8538/11066 [31:16<09:13,  4.56it/s]
                                                    

 77%|███████▋  | 8538/11066 [31:16<09:13,  4.56it/s]
 77%|███████▋  | 8539/11066 [31:16<09:11,  4.58it/s]
                                                    

 77%|███████▋  | 8539/11066 [31:16<09:11,  4.58it/s]
 77%|███████▋  | 8540/11066 [31:17<09:15,  4.55it/s]
                                                    

 77%|███████▋  | 8540/11066 [31:17<09:15,  4.55it/s]
 77%|███████▋  | 8541/11066 [31:17<09:13,  4.56it/s]
                                                    

 77%|███████▋  | 8541/11066 [31:17<09:13,  4.56it/s]
 77%|███████▋  | 8542/11066 [31:17<09:20,  4.50it/s]
                                                    

 77%|███████▋  | 8542/11066 [31:17<09:20,  4.50it/s]
 77%|███████▋  | 8543/11066 [31:17<09:16,  4.53it/s]
                                                    

 77%|███████▋  | 8543/11066 [31:17<09:16,  4.53it/s]
 77%|███████▋  | 8544/11066 [31:18<09:19,  4.51it/s]
                                                    

 77%|███████▋  | 8544/11066 [31:18<09:19,  4.51it/s]
 77%|███████▋  | 8545/11066 [31:18<09:15,  4.54it/s]
                                                    

 77%|███████▋  | 8545/11066 [31:18<09:15,  4.54it/s]
 77%|███████▋  | 8546/11066 [31:18<09:10,  4.58it/s]
                                                    

 77%|███████▋  | 8546/11066 [31:18<09:10,  4.58it/s]
 77%|███████▋  | 8547/11066 [31:18<09:14,  4.54it/s]
                                                    

 77%|███████▋  | 8547/11066 [31:18<09:14,  4.54it/s]
 77%|███████▋  | 8548/11066 [31:18<09:16,  4.52it/s]
                                                    

 77%|███████▋  | 8548/11066 [31:18<09:16,  4.52it/s]
 77%|███████▋  | 8549/11066 [31:19<09:14,  4.54it/s]
                                                    

 77%|███████▋  | 8549/11066 [31:19<09:14,  4.54it/s]
 77%|███████▋  | 8550/11066 [31:19<09:16,  4.52it/s]
                                                    

 77%|███████▋  | 8550/11066 [31:19<09:16,  4.52it/s]
 77%|███████▋  | 8551/11066 [31:19<09:13,  4.54it/s]
                                                    

 77%|███████▋  | 8551/11066 [31:19<09:13,  4.54it/s]
 77%|███████▋  | 8552/11066 [31:19<09:13,  4.54it/s]
                                                    

 77%|███████▋  | 8552/11066 [31:19<09:13,  4.54it/s]
 77%|███████▋  | 8553/11066 [31:20<09:10,  4.57it/s]
                                                    

 77%|███████▋  | 8553/11066 [31:20<09:10,  4.57it/s]
 77%|███████▋  | 8554/11066 [31:20<09:09,  4.57it/s]
                                                    

 77%|███████▋  | 8554/11066 [31:20<09:09,  4.57it/s]
 77%|███████▋  | 8555/11066 [31:20<09:07,  4.58it/s]
                                                    

 77%|███████▋  | 8555/11066 [31:20<09:07,  4.58it/s]
 77%|███████▋  | 8556/11066 [31:20<09:08,  4.58it/s]
                                                    

 77%|███████▋  | 8556/11066 [31:20<09:08,  4.58it/s]
 77%|███████▋  | 8557/11066 [31:20<09:08,  4.58it/s]
                                                    

 77%|███████▋  | 8557/11066 [31:20<09:08,  4.58it/s]
 77%|███████▋  | 8558/11066 [31:21<09:06,  4.59it/s]
                                                    

 77%|███████▋  | 8558/11066 [31:21<09:06,  4.59it/s]
 77%|███████▋  | 8559/11066 [31:21<09:03,  4.61it/s]
                                                    

 77%|███████▋  | 8559/11066 [31:21<09:03,  4.61it/s]
 77%|███████▋  | 8560/11066 [31:21<09:07,  4.58it/s]
                                                    

 77%|███████▋  | 8560/11066 [31:21<09:07,  4.58it/s]
 77%|███████▋  | 8561/11066 [31:21<09:03,  4.61it/s]
                                                    

 77%|███████▋  | 8561/11066 [31:21<09:03,  4.61it/s]
 77%|███████▋  | 8562/11066 [31:21<09:08,  4.57it/s]
                                                    
{'loss': 0.8007, 'learning_rate': 7.094704500271101e-06, 'epoch': 1.53}
{'loss': 0.8459, 'learning_rate': 7.0919934935839505e-06, 'epoch': 1.53}
{'loss': 0.4651, 'learning_rate': 7.0892824868968015e-06, 'epoch': 1.53}
{'loss': 0.5697, 'learning_rate': 7.086571480209652e-06, 'epoch': 1.53}
{'loss': 0.6735, 'learning_rate': 7.083860473522502e-06, 'epoch': 1.53}
{'loss': 0.4451, 'learning_rate': 7.081149466835352e-06, 'epoch': 1.53}
{'loss': 0.444, 'learning_rate': 7.078438460148202e-06, 'epoch': 1.53}
{'loss': 0.9431, 'learning_rate': 7.075727453461052e-06, 'epoch': 1.53}
{'loss': 0.8925, 'learning_rate': 7.073016446773902e-06, 'epoch': 1.53}
{'loss': 0.6176, 'learning_rate': 7.070305440086752e-06, 'epoch': 1.53}
{'loss': 0.6532, 'learning_rate': 7.0675944333996025e-06, 'epoch': 1.53}
{'loss': 0.6747, 'learning_rate': 7.064883426712453e-06, 'epoch': 1.53}
{'loss': 0.3023, 'learning_rate': 7.062172420025303e-06, 'epoch': 1.53}
{'loss': 0.5022, 'learning_rate': 7.059461413338153e-06, 'epoch': 1.53}
{'loss': 1.1917, 'learning_rate': 7.056750406651004e-06, 'epoch': 1.53}
{'loss': 0.4532, 'learning_rate': 7.054039399963853e-06, 'epoch': 1.53}
{'loss': 1.0085, 'learning_rate': 7.051328393276704e-06, 'epoch': 1.53}
{'loss': 0.7288, 'learning_rate': 7.0486173865895535e-06, 'epoch': 1.53}
{'loss': 0.5697, 'learning_rate': 7.0459063799024045e-06, 'epoch': 1.53}
{'loss': 0.9053, 'learning_rate': 7.043195373215254e-06, 'epoch': 1.53}
{'loss': 0.671, 'learning_rate': 7.040484366528105e-06, 'epoch': 1.53}
{'loss': 1.6087, 'learning_rate': 7.037773359840954e-06, 'epoch': 1.53}
{'loss': 1.4068, 'learning_rate': 7.035062353153805e-06, 'epoch': 1.53}
{'loss': 0.209, 'learning_rate': 7.032351346466655e-06, 'epoch': 1.53}
{'loss': 0.7848, 'learning_rate': 7.029640339779505e-06, 'epoch': 1.53}
{'loss': 0.4969, 'learning_rate': 7.026929333092355e-06, 'epoch': 1.53}
{'loss': 0.3174, 'learning_rate': 7.0242183264052055e-06, 'epoch': 1.53}
{'loss': 0.5952, 'learning_rate': 7.021507319718056e-06, 'epoch': 1.53}
{'loss': 0.7228, 'learning_rate': 7.018796313030906e-06, 'epoch': 1.53}
{'loss': 0.7072, 'learning_rate': 7.016085306343756e-06, 'epoch': 1.53}
{'loss': 0.7552, 'learning_rate': 7.013374299656606e-06, 'epoch': 1.53}
{'loss': 0.6156, 'learning_rate': 7.010663292969456e-06, 'epoch': 1.53}
{'loss': 0.6532, 'learning_rate': 7.007952286282306e-06, 'epoch': 1.53}
{'loss': 0.7468, 'learning_rate': 7.0052412795951565e-06, 'epoch': 1.53}
{'loss': 1.342, 'learning_rate': 7.0025302729080075e-06, 'epoch': 1.53}
{'loss': 0.791, 'learning_rate': 6.999819266220857e-06, 'epoch': 1.53}
{'loss': 1.6015, 'learning_rate': 6.997108259533708e-06, 'epoch': 1.53}
{'loss': 0.7344, 'learning_rate': 6.994397252846557e-06, 'epoch': 1.53}
{'loss': 0.5428, 'learning_rate': 6.991686246159408e-06, 'epoch': 1.53}
{'loss': 0.4249, 'learning_rate': 6.988975239472257e-06, 'epoch': 1.53}
{'loss': 0.355, 'learning_rate': 6.986264232785108e-06, 'epoch': 1.53}
{'loss': 0.6635, 'learning_rate': 6.9835532260979575e-06, 'epoch': 1.53}
{'loss': 0.8606, 'learning_rate': 6.9808422194108085e-06, 'epoch': 1.53}
{'loss': 0.9154, 'learning_rate': 6.978131212723658e-06, 'epoch': 1.53}
{'loss': 0.6457, 'learning_rate': 6.975420206036508e-06, 'epoch': 1.53}
{'loss': 0.5231, 'learning_rate': 6.972709199349359e-06, 'epoch': 1.54}
{'loss': 0.6569, 'learning_rate': 6.969998192662208e-06, 'epoch': 1.54}
{'loss': 0.343, 'learning_rate': 6.967287185975059e-06, 'epoch': 1.54}
{'loss': 0.8034, 'learning_rate': 6.9645761792879085e-06, 'epoch': 1.54}
{'loss': 1.2258, 'learning_rate': 6.9618651726007595e-06, 'epoch': 1.54}
{'loss': 0.8054, 'learning_rate': 6.959154165913609e-06, 'epoch': 1.54}
{'loss': 0.9699, 'learning_rate': 6.95644315922646e-06, 'epoch': 1.54}
{'loss': 1.1778, 'learning_rate': 6.953732152539309e-06, 'epoch': 1.54}
{'loss': 0.7753, 'learning_rate': 6.95102114585216e-06, 'epoch': 1.54}
{'loss': 0.4886, 'learning_rate': 6.94831013916501e-06, 'epoch': 1.54}
{'loss': 0.6477, 'learning_rate': 6.94559913247786e-06, 'epoch': 1.54}
{'loss': 0.3436, 'learning_rate': 6.94288812579071e-06, 'epoch': 1.54}
{'loss': 0.7044, 'learning_rate': 6.9401771191035605e-06, 'epoch': 1.54}
{'loss': 0.8918, 'learning_rate': 6.937466112416411e-06, 'epoch': 1.54}
{'loss': 0.3289, 'learning_rate': 6.934755105729261e-06, 'epoch': 1.54}
{'loss': 0.6832, 'learning_rate': 6.932044099042111e-06, 'epoch': 1.54}
{'loss': 0.8814, 'learning_rate': 6.929333092354961e-06, 'epoch': 1.54}
{'loss': 0.7411, 'learning_rate': 6.926622085667811e-06, 'epoch': 1.54}
{'loss': 0.4909, 'learning_rate': 6.923911078980661e-06, 'epoch': 1.54}
{'loss': 0.7341, 'learning_rate': 6.9212000722935115e-06, 'epoch': 1.54}
{'loss': 0.7814, 'learning_rate': 6.9184890656063625e-06, 'epoch': 1.54}
{'loss': 1.6679, 'learning_rate': 6.915778058919212e-06, 'epoch': 1.54}
{'loss': 0.616, 'learning_rate': 6.913067052232063e-06, 'epoch': 1.54}
{'loss': 0.7942, 'learning_rate': 6.910356045544912e-06, 'epoch': 1.54}
{'loss': 0.5756, 'learning_rate': 6.907645038857763e-06, 'epoch': 1.54}
{'loss': 0.7993, 'learning_rate': 6.904934032170612e-06, 'epoch': 1.54}
{'loss': 0.5581, 'learning_rate': 6.902223025483463e-06, 'epoch': 1.54}
{'loss': 1.9331, 'learning_rate': 6.8995120187963126e-06, 'epoch': 1.54}
{'loss': 1.5581, 'learning_rate': 6.8968010121091635e-06, 'epoch': 1.54}
{'loss': 1.1671, 'learning_rate': 6.894090005422013e-06, 'epoch': 1.54}
{'loss': 0.4594, 'learning_rate': 6.891378998734864e-06, 'epoch': 1.54}
{'loss': 0.7586, 'learning_rate': 6.888667992047714e-06, 'epoch': 1.54}
{'loss': 1.313, 'learning_rate': 6.885956985360564e-06, 'epoch': 1.54}
{'loss': 0.5281, 'learning_rate': 6.883245978673414e-06, 'epoch': 1.54}
{'loss': 0.5902, 'learning_rate': 6.880534971986264e-06, 'epoch': 1.54}
{'loss': 1.5184, 'learning_rate': 6.8778239652991145e-06, 'epoch': 1.54}
{'loss': 0.6719, 'learning_rate': 6.875112958611965e-06, 'epoch': 1.54}
{'loss': 1.6231, 'learning_rate': 6.872401951924815e-06, 'epoch': 1.54}
{'loss': 1.2459, 'learning_rate': 6.869690945237665e-06, 'epoch': 1.54}
{'loss': 0.8367, 'learning_rate': 6.866979938550515e-06, 'epoch': 1.54}
{'loss': 0.569, 'learning_rate': 6.864268931863365e-06, 'epoch': 1.54}
{'loss': 0.9468, 'learning_rate': 6.861557925176215e-06, 'epoch': 1.54}
{'loss': 0.4397, 'learning_rate': 6.858846918489066e-06, 'epoch': 1.54}
{'loss': 0.5984, 'learning_rate': 6.8561359118019156e-06, 'epoch': 1.54}
{'loss': 0.5644, 'learning_rate': 6.8534249051147665e-06, 'epoch': 1.54}
{'loss': 0.863, 'learning_rate': 6.850713898427616e-06, 'epoch': 1.54}
{'loss': 1.091, 'learning_rate': 6.848002891740467e-06, 'epoch': 1.54}
{'loss': 0.6102, 'learning_rate': 6.845291885053316e-06, 'epoch': 1.54}
{'loss': 0.4846, 'learning_rate': 6.842580878366167e-06, 'epoch': 1.54}
{'loss': 0.5137, 'learning_rate': 6.839869871679016e-06, 'epoch': 1.54}
{'loss': 0.8453, 'learning_rate': 6.837158864991867e-06, 'epoch': 1.54}
{'loss': 0.9524, 'learning_rate': 6.8344478583047175e-06, 'epoch': 1.54}
{'loss': 0.7491, 'learning_rate': 6.831736851617568e-06, 'epoch': 1.54}
{'loss': 0.7067, 'learning_rate': 6.829025844930418e-06, 'epoch': 1.54}
{'loss': 1.1253, 'learning_rate': 6.826314838243268e-06, 'epoch': 1.54}
{'loss': 0.6747, 'learning_rate': 6.823603831556118e-06, 'epoch': 1.55}
{'loss': 1.2118, 'learning_rate': 6.820892824868968e-06, 'epoch': 1.55}
{'loss': 1.0043, 'learning_rate': 6.818181818181818e-06, 'epoch': 1.55}
{'loss': 0.3632, 'learning_rate': 6.815470811494668e-06, 'epoch': 1.55}
{'loss': 0.559, 'learning_rate': 6.8127598048075185e-06, 'epoch': 1.55}
{'loss': 0.9913, 'learning_rate': 6.810048798120369e-06, 'epoch': 1.55}
{'loss': 1.0954, 'learning_rate': 6.807337791433219e-06, 'epoch': 1.55}
{'loss': 1.1664, 'learning_rate': 6.80462678474607e-06, 'epoch': 1.55}
{'loss': 1.1034, 'learning_rate': 6.801915778058919e-06, 'epoch': 1.55}
{'loss': 0.693, 'learning_rate': 6.79920477137177e-06, 'epoch': 1.55}
{'loss': 0.6172, 'learning_rate': 6.796493764684619e-06, 'epoch': 1.55}
{'loss': 0.5212, 'learning_rate': 6.79378275799747e-06, 'epoch': 1.55}
{'loss': 0.8275, 'learning_rate': 6.79107175131032e-06, 'epoch': 1.55}

 77%|███████▋  | 8562/11066 [31:21<09:08,  4.57it/s]
 77%|███████▋  | 8563/11066 [31:22<09:06,  4.58it/s]
                                                    

 77%|███████▋  | 8563/11066 [31:22<09:06,  4.58it/s]
 77%|███████▋  | 8564/11066 [31:22<09:02,  4.61it/s]
                                                    

 77%|███████▋  | 8564/11066 [31:22<09:02,  4.61it/s]
 77%|███████▋  | 8565/11066 [31:22<09:02,  4.61it/s]
                                                    

 77%|███████▋  | 8565/11066 [31:22<09:02,  4.61it/s]
 77%|███████▋  | 8566/11066 [31:22<09:01,  4.61it/s]
                                                    

 77%|███████▋  | 8566/11066 [31:22<09:01,  4.61it/s]
 77%|███████▋  | 8567/11066 [31:23<09:07,  4.56it/s]
                                                    

 77%|███████▋  | 8567/11066 [31:23<09:07,  4.56it/s]
 77%|███████▋  | 8568/11066 [31:23<09:11,  4.53it/s]
                                                    

 77%|███████▋  | 8568/11066 [31:23<09:11,  4.53it/s]
 77%|███████▋  | 8569/11066 [31:23<09:13,  4.51it/s]
                                                    

 77%|███████▋  | 8569/11066 [31:23<09:13,  4.51it/s]
 77%|███████▋  | 8570/11066 [31:23<09:09,  4.54it/s]
                                                    

 77%|███████▋  | 8570/11066 [31:23<09:09,  4.54it/s]
 77%|███████▋  | 8571/11066 [31:23<09:05,  4.57it/s]
                                                    

 77%|███████▋  | 8571/11066 [31:23<09:05,  4.57it/s]
 77%|███████▋  | 8572/11066 [31:24<09:04,  4.58it/s]
                                                    

 77%|███████▋  | 8572/11066 [31:24<09:04,  4.58it/s]
 77%|███████▋  | 8573/11066 [31:24<09:00,  4.61it/s]
                                                    

 77%|███████▋  | 8573/11066 [31:24<09:00,  4.61it/s]
 77%|███████▋  | 8574/11066 [31:24<08:59,  4.62it/s]
                                                    

 77%|███████▋  | 8574/11066 [31:24<08:59,  4.62it/s]
 77%|███████▋  | 8575/11066 [31:24<08:59,  4.61it/s]
                                                    

 77%|███████▋  | 8575/11066 [31:24<08:59,  4.61it/s]
 77%|███████▋  | 8576/11066 [31:25<09:02,  4.59it/s]
                                                    

 77%|███████▋  | 8576/11066 [31:25<09:02,  4.59it/s]
 78%|███████▊  | 8577/11066 [31:25<09:02,  4.59it/s]
                                                    

 78%|███████▊  | 8577/11066 [31:25<09:02,  4.59it/s]
 78%|███████▊  | 8578/11066 [31:25<09:01,  4.59it/s]
                                                    

 78%|███████▊  | 8578/11066 [31:25<09:01,  4.59it/s]
 78%|███████▊  | 8579/11066 [31:25<09:00,  4.60it/s]
                                                    

 78%|███████▊  | 8579/11066 [31:25<09:00,  4.60it/s]
 78%|███████▊  | 8580/11066 [31:25<09:00,  4.60it/s]
                                                    

 78%|███████▊  | 8580/11066 [31:25<09:00,  4.60it/s]
 78%|███████▊  | 8581/11066 [31:26<08:59,  4.61it/s]
                                                    

 78%|███████▊  | 8581/11066 [31:26<08:59,  4.61it/s]
 78%|███████▊  | 8582/11066 [31:26<08:59,  4.60it/s]
                                                    

 78%|███████▊  | 8582/11066 [31:26<08:59,  4.60it/s]
 78%|███████▊  | 8583/11066 [31:26<09:06,  4.54it/s]
                                                    

 78%|███████▊  | 8583/11066 [31:26<09:06,  4.54it/s]
 78%|███████▊  | 8584/11066 [31:26<09:09,  4.52it/s]
                                                    

 78%|███████▊  | 8584/11066 [31:26<09:09,  4.52it/s]
 78%|███████▊  | 8585/11066 [31:27<09:09,  4.51it/s]
                                                    

 78%|███████▊  | 8585/11066 [31:27<09:09,  4.51it/s]
 78%|███████▊  | 8586/11066 [31:27<09:10,  4.51it/s]
                                                    

 78%|███████▊  | 8586/11066 [31:27<09:10,  4.51it/s]
 78%|███████▊  | 8587/11066 [31:27<09:06,  4.54it/s]
                                                    

 78%|███████▊  | 8587/11066 [31:27<09:06,  4.54it/s]
 78%|███████▊  | 8588/11066 [31:27<09:01,  4.58it/s]
                                                    

 78%|███████▊  | 8588/11066 [31:27<09:01,  4.58it/s]
 78%|███████▊  | 8589/11066 [31:27<09:00,  4.58it/s]
                                                    

 78%|███████▊  | 8589/11066 [31:27<09:00,  4.58it/s]
 78%|███████▊  | 8590/11066 [31:28<08:59,  4.59it/s]
                                                    

 78%|███████▊  | 8590/11066 [31:28<08:59,  4.59it/s]
 78%|███████▊  | 8591/11066 [31:28<08:56,  4.61it/s]
                                                    

 78%|███████▊  | 8591/11066 [31:28<08:56,  4.61it/s]
 78%|███████▊  | 8592/11066 [31:28<08:57,  4.61it/s]
                                                    

 78%|███████▊  | 8592/11066 [31:28<08:57,  4.61it/s]
 78%|███████▊  | 8593/11066 [31:28<08:58,  4.59it/s]
                                                    

 78%|███████▊  | 8593/11066 [31:28<08:58,  4.59it/s]
 78%|███████▊  | 8594/11066 [31:28<08:57,  4.60it/s]
                                                    

 78%|███████▊  | 8594/11066 [31:28<08:57,  4.60it/s]
 78%|███████▊  | 8595/11066 [31:29<08:55,  4.61it/s]
                                                    

 78%|███████▊  | 8595/11066 [31:29<08:55,  4.61it/s]
 78%|███████▊  | 8596/11066 [31:29<09:00,  4.57it/s]
                                                    

 78%|███████▊  | 8596/11066 [31:29<09:00,  4.57it/s]
 78%|███████▊  | 8597/11066 [31:29<08:59,  4.58it/s]
                                                    

 78%|███████▊  | 8597/11066 [31:29<08:59,  4.58it/s]
 78%|███████▊  | 8598/11066 [31:29<08:54,  4.62it/s]
                                                    

 78%|███████▊  | 8598/11066 [31:29<08:54,  4.62it/s]
 78%|███████▊  | 8599/11066 [31:30<08:51,  4.64it/s]
                                                    

 78%|███████▊  | 8599/11066 [31:30<08:51,  4.64it/s]
 78%|███████▊  | 8600/11066 [31:30<08:55,  4.61it/s]
                                                    

 78%|███████▊  | 8600/11066 [31:30<08:55,  4.61it/s]
 78%|███████▊  | 8601/11066 [31:30<09:00,  4.56it/s]
                                                    

 78%|███████▊  | 8601/11066 [31:30<09:00,  4.56it/s]
 78%|███████▊  | 8602/11066 [31:30<09:03,  4.53it/s]
                                                    

 78%|███████▊  | 8602/11066 [31:30<09:03,  4.53it/s]
 78%|███████▊  | 8603/11066 [31:30<09:02,  4.54it/s]
                                                    

 78%|███████▊  | 8603/11066 [31:30<09:02,  4.54it/s]
 78%|███████▊  | 8604/11066 [31:31<08:58,  4.57it/s]
                                                    

 78%|███████▊  | 8604/11066 [31:31<08:58,  4.57it/s]
 78%|███████▊  | 8605/11066 [31:31<08:56,  4.59it/s]
                                                    

 78%|███████▊  | 8605/11066 [31:31<08:56,  4.59it/s]
 78%|███████▊  | 8606/11066 [31:31<08:55,  4.60it/s]
                                                    

 78%|███████▊  | 8606/11066 [31:31<08:55,  4.60it/s]
 78%|███████▊  | 8607/11066 [31:31<08:51,  4.62it/s]
                                                    

 78%|███████▊  | 8607/11066 [31:31<08:51,  4.62it/s]
 78%|███████▊  | 8608/11066 [31:32<08:52,  4.61it/s]
                                                    

 78%|███████▊  | 8608/11066 [31:32<08:52,  4.61it/s]
 78%|███████▊  | 8609/11066 [31:32<08:52,  4.61it/s]
                                                    

 78%|███████▊  | 8609/11066 [31:32<08:52,  4.61it/s]
 78%|███████▊  | 8610/11066 [31:32<08:53,  4.60it/s]
                                                    

 78%|███████▊  | 8610/11066 [31:32<08:53,  4.60it/s]
 78%|███████▊  | 8611/11066 [31:32<08:58,  4.56it/s]
                                                    

 78%|███████▊  | 8611/11066 [31:32<08:58,  4.56it/s]
 78%|███████▊  | 8612/11066 [31:32<09:01,  4.54it/s]
                                                    

 78%|███████▊  | 8612/11066 [31:32<09:01,  4.54it/s]
 78%|███████▊  | 8613/11066 [31:33<09:03,  4.51it/s]
                                                    

 78%|███████▊  | 8613/11066 [31:33<09:03,  4.51it/s]
 78%|███████▊  | 8614/11066 [31:33<08:59,  4.55it/s]
                                                    

 78%|███████▊  | 8614/11066 [31:33<08:59,  4.55it/s]
 78%|███████▊  | 8615/11066 [31:33<08:57,  4.56it/s]
                                                    

 78%|███████▊  | 8615/11066 [31:33<08:57,  4.56it/s]
 78%|███████▊  | 8616/11066 [31:33<08:56,  4.57it/s]
                                                    

 78%|███████▊  | 8616/11066 [31:33<08:56,  4.57it/s]
 78%|███████▊  | 8617/11066 [31:33<08:50,  4.61it/s]
                                                    

 78%|███████▊  | 8617/11066 [31:33<08:50,  4.61it/s]
 78%|███████▊  | 8618/11066 [31:34<08:50,  4.61it/s]
                                                    

 78%|███████▊  | 8618/11066 [31:34<08:50,  4.61it/s]
 78%|███████▊  | 8619/11066 [31:34<08:47,  4.64it/s]
                                                    

 78%|███████▊  | 8619/11066 [31:34<08:47,  4.64it/s]
 78%|███████▊  | 8620/11066 [31:34<08:45,  4.66it/s]
                                                    

 78%|███████▊  | 8620/11066 [31:34<08:45,  4.66it/s]
 78%|███████▊  | 8621/11066 [31:34<08:48,  4.63it/s]
                                                    

 78%|███████▊  | 8621/11066 [31:34<08:48,  4.63it/s]
 78%|███████▊  | 8622/11066 [31:35<08:43,  4.67it/s]
                                                    

 78%|███████▊  | 8622/11066 [31:35<08:43,  4.67it/s]
 78%|███████▊  | 8623/11066 [31:35<08:49,  4.61it/s]
                                                    

 78%|███████▊  | 8623/11066 [31:35<08:49,  4.61it/s]
 78%|███████▊  | 8624/11066 [31:35<08:49,  4.61it/s]
                                                    

 78%|███████▊  | 8624/11066 [31:35<08:49,  4.61it/s]
 78%|███████▊  | 8625/11066 [31:35<08:49,  4.61it/s]
                                                    

 78%|███████▊  | 8625/11066 [31:35<08:49,  4.61it/s]
 78%|███████▊  | 8626/11066 [31:35<08:48,  4.61it/s]
                                                    

 78%|███████▊  | 8626/11066 [31:35<08:48,  4.61it/s]
 78%|███████▊  | 8627/11066 [31:36<08:46,  4.63it/s]
                                                    

 78%|███████▊  | 8627/11066 [31:36<08:46,  4.63it/s]
 78%|███████▊  | 8628/11066 [31:36<08:48,  4.62it/s]
                                                    

 78%|███████▊  | 8628/11066 [31:36<08:48,  4.62it/s]
 78%|███████▊  | 8629/11066 [31:36<08:53,  4.57it/s]
                                                    

 78%|███████▊  | 8629/11066 [31:36<08:53,  4.57it/s]
 78%|███████▊  | 8630/11066 [31:36<08:58,  4.53it/s]
                                                    

 78%|███████▊  | 8630/11066 [31:36<08:58,  4.53it/s]
 78%|███████▊  | 8631/11066 [31:37<08:55,  4.55it/s]
                                                    

 78%|███████▊  | 8631/11066 [31:37<08:55,  4.55it/s]
 78%|███████▊  | 8632/11066 [31:37<08:54,  4.55it/s]
                                                    

 78%|███████▊  | 8632/11066 [31:37<08:54,  4.55it/s]
 78%|███████▊  | 8633/11066 [31:37<08:51,  4.58it/s]
                                                    

 78%|███████▊  | 8633/11066 [31:37<08:51,  4.58it/s]
 78%|███████▊  | 8634/11066 [31:37<08:47,  4.61it/s]
                                                    

 78%|███████▊  | 8634/11066 [31:37<08:47,  4.61it/s]
 78%|███████▊  | 8635/11066 [31:37<08:45,  4.62it/s]
                                                    

 78%|███████▊  | 8635/11066 [31:37<08:45,  4.62it/s]
 78%|███████▊  | 8636/11066 [31:38<08:46,  4.61it/s]
                                                    

 78%|███████▊  | 8636/11066 [31:38<08:46,  4.61it/s]
 78%|███████▊  | 8637/11066 [31:38<08:48,  4.60it/s]
                                                    

 78%|███████▊  | 8637/11066 [31:38<08:48,  4.60it/s]
 78%|███████▊  | 8638/11066 [31:38<08:42,  4.65it/s]
                                                    

 78%|███████▊  | 8638/11066 [31:38<08:42,  4.65it/s]
 78%|███████▊  | 8639/11066 [31:38<08:51,  4.57it/s]
                                                    

 78%|███████▊  | 8639/11066 [31:38<08:51,  4.57it/s]
 78%|███████▊  | 8640/11066 [31:38<08:57,  4.51it/s]
                                                    

 78%|███████▊  | 8640/11066 [31:38<08:57,  4.51it/s]
 78%|███████▊  | 8641/11066 [31:39<09:00,  4.48it/s]
                                                    

 78%|███████▊  | 8641/11066 [31:39<09:00,  4.48it/s]
 78%|███████▊  | 8642/11066 [31:39<08:59,  4.49it/s]
                                                    

 78%|███████▊  | 8642/11066 [31:39<08:59,  4.49it/s]
 78%|███████▊  | 8643/11066 [31:39<08:59,  4.49it/s]
                                                    

 78%|███████▊  | 8643/11066 [31:39<08:59,  4.49it/s]
 78%|███████▊  | 8644/11066 [31:39<08:51,  4.56it/s]
                                                    

 78%|███████▊  | 8644/11066 [31:39<08:51,  4.56it/s]
 78%|███████▊  | 8645/11066 [31:40<08:53,  4.54it/s]
                                                    

 78%|███████▊  | 8645/11066 [31:40<08:53,  4.54it/s]
 78%|███████▊  | 8646/11066 [31:40<08:54,  4.53it/s]
                                                    

 78%|███████▊  | 8646/11066 [31:40<08:54,  4.53it/s]
 78%|███████▊  | 8647/11066 [31:40<08:55,  4.52it/s]
                                                    

 78%|███████▊  | 8647/11066 [31:40<08:55,  4.52it/s]
 78%|███████▊  | 8648/11066 [31:40<08:55,  4.51it/s]
                                                    

 78%|███████▊  | 8648/11066 [31:40<08:55,  4.51it/s]
 78%|███████▊  | 8649/11066 [31:40<08:55,  4.51it/s]
                                                    

 78%|███████▊  | 8649/11066 [31:40<08:55,  4.51it/s]
 78%|███████▊  | 8650/11066 [31:41<08:56,  4.50it/s]
                                                    

 78%|███████▊  | 8650/11066 [31:41<08:56,  4.50it/s]
 78%|███████▊  | 8651/11066 [31:41<08:56,  4.50it/s]
                                                    

 78%|███████▊  | 8651/11066 [31:41<08:56,  4.50it/s]
 78%|███████▊  | 8652/11066 [31:41<08:56,  4.50it/s]
                                                    

 78%|███████▊  | 8652/11066 [31:41<08:56,  4.50it/s]
 78%|███████▊  | 8653/11066 [31:41<08:56,  4.50it/s]
                                                    

 78%|███████▊  | 8653/11066 [31:41<08:56,  4.50it/s]
 78%|███████▊  | 8654/11066 [31:42<08:56,  4.50it/s]
                                                    

 78%|███████▊  | 8654/11066 [31:42<08:56,  4.50it/s]
 78%|███████▊  | 8655/11066 [31:42<08:58,  4.48it/s]
                                                    

 78%|███████▊  | 8655/11066 [31:42<08:58,  4.48it/s]
 78%|███████▊  | 8656/11066 [31:42<08:59,  4.47it/s]
                                                    

 78%|███████▊  | 8656/11066 [31:42<08:59,  4.47it/s]
 78%|███████▊  | 8657/11066 [31:42<08:57,  4.48it/s]
                                                    

 78%|███████▊  | 8657/11066 [31:42<08:57,  4.48it/s]
 78%|███████▊  | 8658/11066 [31:42<08:56,  4.49it/s]
                                                    

 78%|███████▊  | 8658/11066 [31:42<08:56,  4.49it/s]
 78%|███████▊  | 8659/11066 [31:43<08:56,  4.49it/s]
                                                    

 78%|███████▊  | 8659/11066 [31:43<08:56,  4.49it/s]
 78%|███████▊  | 8660/11066 [31:43<08:55,  4.49it/s]
                                                    

 78%|███████▊  | 8660/11066 [31:43<08:55,  4.49it/s]
 78%|███████▊  | 8661/11066 [31:43<08:55,  4.49it/s]
                                                    

 78%|███████▊  | 8661/11066 [31:43<08:55,  4.49it/s]
 78%|███████▊  | 8662/11066 [31:43<08:51,  4.52it/s]
                                                    

 78%|███████▊  | 8662/11066 [31:43<08:51,  4.52it/s]
 78%|███████▊  | 8663/11066 [31:44<08:54,  4.50it/s]
                                                    

 78%|███████▊  | 8663/11066 [31:44<08:54,  4.50it/s]
 78%|███████▊  | 8664/11066 [31:44<08:54,  4.49it/s]
                                                    

 78%|███████▊  | 8664/11066 [31:44<08:54,  4.49it/s]
 78%|███████▊  | 8665/11066 [31:44<08:54,  4.49it/s]
                                                    

 78%|███████▊  | 8665/11066 [31:44<08:54,  4.49it/s]
 78%|███████▊  | 8666/11066 [31:44<08:54,  4.49it/s]
                                                    

 78%|███████▊  | 8666/11066 [31:44<08:54,  4.49it/s]
 78%|███████▊  | 8667/11066 [31:44<08:53,  4.49it/s]
                                                    

 78%|███████▊  | 8667/11066 [31:44<08:53,  4.49it/s]
 78%|███████▊  | 8668/11066 [31:45<08:53,  4.50it/s]
                                                    

 78%|███████▊  | 8668/11066 [31:45<08:53,  4.50it/s]
 78%|███████▊  | 8669/11066 [31:45<08:52,  4.50it/s]
                                                    

 78%|███████▊  | 8669/11066 [31:45<08:52,  4.50it/s]
 78%|███████▊  | 8670/11066 [31:45<08:52,  4.50it/s]
                                                    

 78%|███████▊  | 8670/11066 [31:45<08:52,  4.50it/s]
 78%|███████▊  | 8671/11066 [31:45<08:52,  4.50it/s]
                                                    

 78%|███████▊  | 8671/11066 [31:45<08:52,  4.50it/s]
 78%|███████▊  | 8672/11066 [31:46<08:51,  4.50it/s]
                                                    

 78%|███████▊  | 8672/11066 [31:46<08:51,  4.50it/s]
 78%|███████▊  | 8673/11066 [31:46<08:51,  4.50it/s]
                                                    

 78%|███████▊  | 8673/11066 [31:46<08:51,  4.50it/s]
 78%|███████▊  | 8674/11066 [31:46<08:51,  4.50it/s]
                                                    

 78%|███████▊  | 8674/11066 [31:46<08:51,  4.50it/s]
 78%|███████▊  | 8675/11066 [31:46<08:50,  4.51it/s]
                                                    
{'loss': 0.5996, 'learning_rate': 6.788360744623171e-06, 'epoch': 1.55}
{'loss': 0.7489, 'learning_rate': 6.78564973793602e-06, 'epoch': 1.55}
{'loss': 0.777, 'learning_rate': 6.782938731248871e-06, 'epoch': 1.55}
{'loss': 0.4875, 'learning_rate': 6.78022772456172e-06, 'epoch': 1.55}
{'loss': 0.6299, 'learning_rate': 6.777516717874571e-06, 'epoch': 1.55}
{'loss': 0.4112, 'learning_rate': 6.774805711187421e-06, 'epoch': 1.55}
{'loss': 0.4625, 'learning_rate': 6.772094704500271e-06, 'epoch': 1.55}
{'loss': 0.3211, 'learning_rate': 6.7693836978131215e-06, 'epoch': 1.55}
{'loss': 0.6223, 'learning_rate': 6.766672691125972e-06, 'epoch': 1.55}
{'loss': 1.1397, 'learning_rate': 6.763961684438822e-06, 'epoch': 1.55}
{'loss': 0.6395, 'learning_rate': 6.761250677751672e-06, 'epoch': 1.55}
{'loss': 1.2524, 'learning_rate': 6.758539671064522e-06, 'epoch': 1.55}
{'loss': 0.7462, 'learning_rate': 6.755828664377372e-06, 'epoch': 1.55}
{'loss': 0.7295, 'learning_rate': 6.753117657690222e-06, 'epoch': 1.55}
{'loss': 0.4818, 'learning_rate': 6.750406651003073e-06, 'epoch': 1.55}
{'loss': 0.836, 'learning_rate': 6.747695644315923e-06, 'epoch': 1.55}
{'loss': 1.8775, 'learning_rate': 6.744984637628774e-06, 'epoch': 1.55}
{'loss': 0.4003, 'learning_rate': 6.742273630941623e-06, 'epoch': 1.55}
{'loss': 0.7783, 'learning_rate': 6.739562624254474e-06, 'epoch': 1.55}
{'loss': 0.8992, 'learning_rate': 6.736851617567323e-06, 'epoch': 1.55}
{'loss': 0.6447, 'learning_rate': 6.734140610880174e-06, 'epoch': 1.55}
{'loss': 0.657, 'learning_rate': 6.731429604193023e-06, 'epoch': 1.55}
{'loss': 1.1998, 'learning_rate': 6.728718597505874e-06, 'epoch': 1.55}
{'loss': 0.4485, 'learning_rate': 6.726007590818724e-06, 'epoch': 1.55}
{'loss': 0.4304, 'learning_rate': 6.723296584131575e-06, 'epoch': 1.55}
{'loss': 0.784, 'learning_rate': 6.720585577444425e-06, 'epoch': 1.55}
{'loss': 0.4407, 'learning_rate': 6.717874570757275e-06, 'epoch': 1.55}
{'loss': 0.9332, 'learning_rate': 6.715163564070125e-06, 'epoch': 1.55}
{'loss': 0.673, 'learning_rate': 6.712452557382975e-06, 'epoch': 1.55}
{'loss': 0.8703, 'learning_rate': 6.709741550695825e-06, 'epoch': 1.55}
{'loss': 0.4873, 'learning_rate': 6.7070305440086755e-06, 'epoch': 1.55}
{'loss': 0.6134, 'learning_rate': 6.704319537321526e-06, 'epoch': 1.55}
{'loss': 0.8319, 'learning_rate': 6.701608530634376e-06, 'epoch': 1.55}
{'loss': 0.7386, 'learning_rate': 6.698897523947226e-06, 'epoch': 1.55}
{'loss': 0.5986, 'learning_rate': 6.696186517260076e-06, 'epoch': 1.55}
{'loss': 1.0678, 'learning_rate': 6.693475510572926e-06, 'epoch': 1.55}
{'loss': 0.9933, 'learning_rate': 6.690764503885777e-06, 'epoch': 1.55}
{'loss': 0.7352, 'learning_rate': 6.688053497198626e-06, 'epoch': 1.55}
{'loss': 0.6493, 'learning_rate': 6.685342490511477e-06, 'epoch': 1.55}
{'loss': 1.0013, 'learning_rate': 6.682631483824327e-06, 'epoch': 1.55}
{'loss': 0.7824, 'learning_rate': 6.679920477137178e-06, 'epoch': 1.55}
{'loss': 0.9829, 'learning_rate': 6.677209470450027e-06, 'epoch': 1.55}
{'loss': 0.6249, 'learning_rate': 6.674498463762878e-06, 'epoch': 1.56}
{'loss': 1.1069, 'learning_rate': 6.671787457075727e-06, 'epoch': 1.56}
{'loss': 0.7548, 'learning_rate': 6.669076450388578e-06, 'epoch': 1.56}
{'loss': 0.8153, 'learning_rate': 6.666365443701428e-06, 'epoch': 1.56}
{'loss': 0.5669, 'learning_rate': 6.6636544370142785e-06, 'epoch': 1.56}
{'loss': 0.7197, 'learning_rate': 6.660943430327129e-06, 'epoch': 1.56}
{'loss': 1.1128, 'learning_rate': 6.658232423639979e-06, 'epoch': 1.56}
{'loss': 0.7135, 'learning_rate': 6.655521416952829e-06, 'epoch': 1.56}
{'loss': 0.9771, 'learning_rate': 6.652810410265679e-06, 'epoch': 1.56}
{'loss': 0.7621, 'learning_rate': 6.650099403578529e-06, 'epoch': 1.56}
{'loss': 0.3773, 'learning_rate': 6.647388396891379e-06, 'epoch': 1.56}
{'loss': 0.9806, 'learning_rate': 6.644677390204229e-06, 'epoch': 1.56}
{'loss': 0.592, 'learning_rate': 6.6419663835170795e-06, 'epoch': 1.56}
{'loss': 0.8536, 'learning_rate': 6.63925537682993e-06, 'epoch': 1.56}
{'loss': 0.9502, 'learning_rate': 6.636544370142781e-06, 'epoch': 1.56}
{'loss': 0.8085, 'learning_rate': 6.63383336345563e-06, 'epoch': 1.56}
{'loss': 0.853, 'learning_rate': 6.631122356768481e-06, 'epoch': 1.56}
{'loss': 0.648, 'learning_rate': 6.62841135008133e-06, 'epoch': 1.56}
{'loss': 0.3217, 'learning_rate': 6.62570034339418e-06, 'epoch': 1.56}
{'loss': 0.8712, 'learning_rate': 6.6229893367070305e-06, 'epoch': 1.56}
{'loss': 0.5077, 'learning_rate': 6.620278330019881e-06, 'epoch': 1.56}
{'loss': 1.1509, 'learning_rate': 6.617567323332731e-06, 'epoch': 1.56}
{'loss': 1.1332, 'learning_rate': 6.614856316645581e-06, 'epoch': 1.56}
{'loss': 0.6361, 'learning_rate': 6.612145309958431e-06, 'epoch': 1.56}
{'loss': 0.6616, 'learning_rate': 6.609434303271281e-06, 'epoch': 1.56}
{'loss': 1.0817, 'learning_rate': 6.606723296584132e-06, 'epoch': 1.56}
{'loss': 0.7077, 'learning_rate': 6.6040122898969814e-06, 'epoch': 1.56}
{'loss': 0.8557, 'learning_rate': 6.601301283209832e-06, 'epoch': 1.56}
{'loss': 0.5243, 'learning_rate': 6.598590276522682e-06, 'epoch': 1.56}
{'loss': 0.5715, 'learning_rate': 6.595879269835533e-06, 'epoch': 1.56}
{'loss': 0.5524, 'learning_rate': 6.593168263148382e-06, 'epoch': 1.56}
{'loss': 0.5164, 'learning_rate': 6.590457256461233e-06, 'epoch': 1.56}
{'loss': 0.7603, 'learning_rate': 6.587746249774082e-06, 'epoch': 1.56}
{'loss': 0.4789, 'learning_rate': 6.585035243086933e-06, 'epoch': 1.56}
{'loss': 0.4926, 'learning_rate': 6.582324236399783e-06, 'epoch': 1.56}
{'loss': 0.7025, 'learning_rate': 6.5796132297126335e-06, 'epoch': 1.56}
{'loss': 0.9108, 'learning_rate': 6.576902223025484e-06, 'epoch': 1.56}
{'loss': 0.8879, 'learning_rate': 6.574191216338334e-06, 'epoch': 1.56}
{'loss': 0.8828, 'learning_rate': 6.571480209651184e-06, 'epoch': 1.56}
{'loss': 1.3115, 'learning_rate': 6.568769202964034e-06, 'epoch': 1.56}
{'loss': 0.9246, 'learning_rate': 6.566058196276884e-06, 'epoch': 1.56}
{'loss': 0.3729, 'learning_rate': 6.563347189589734e-06, 'epoch': 1.56}
{'loss': 0.5538, 'learning_rate': 6.560636182902584e-06, 'epoch': 1.56}
{'loss': 0.4809, 'learning_rate': 6.5579251762154346e-06, 'epoch': 1.56}
{'loss': 1.13, 'learning_rate': 6.555214169528285e-06, 'epoch': 1.56}
{'loss': 0.6287, 'learning_rate': 6.552503162841136e-06, 'epoch': 1.56}
{'loss': 0.7703, 'learning_rate': 6.549792156153985e-06, 'epoch': 1.56}
{'loss': 0.6717, 'learning_rate': 6.547081149466836e-06, 'epoch': 1.56}
{'loss': 1.2531, 'learning_rate': 6.544370142779685e-06, 'epoch': 1.56}
{'loss': 0.7819, 'learning_rate': 6.541659136092536e-06, 'epoch': 1.56}
{'loss': 0.5916, 'learning_rate': 6.5389481294053855e-06, 'epoch': 1.56}
{'loss': 0.4528, 'learning_rate': 6.5362371227182365e-06, 'epoch': 1.56}
{'loss': 0.6232, 'learning_rate': 6.533526116031086e-06, 'epoch': 1.56}
{'loss': 0.6878, 'learning_rate': 6.530815109343937e-06, 'epoch': 1.56}
{'loss': 1.8885, 'learning_rate': 6.528104102656786e-06, 'epoch': 1.56}
{'loss': 0.8755, 'learning_rate': 6.525393095969637e-06, 'epoch': 1.56}
{'loss': 1.0469, 'learning_rate': 6.522682089282487e-06, 'epoch': 1.57}
{'loss': 1.356, 'learning_rate': 6.519971082595337e-06, 'epoch': 1.57}
{'loss': 0.471, 'learning_rate': 6.517260075908187e-06, 'epoch': 1.57}
{'loss': 0.691, 'learning_rate': 6.5145490692210376e-06, 'epoch': 1.57}
{'loss': 1.0728, 'learning_rate': 6.511838062533888e-06, 'epoch': 1.57}
{'loss': 0.6957, 'learning_rate': 6.509127055846738e-06, 'epoch': 1.57}
{'loss': 0.7217, 'learning_rate': 6.506416049159588e-06, 'epoch': 1.57}
{'loss': 0.8706, 'learning_rate': 6.503705042472438e-06, 'epoch': 1.57}
{'loss': 0.6522, 'learning_rate': 6.500994035785288e-06, 'epoch': 1.57}
{'loss': 0.4959, 'learning_rate': 6.498283029098138e-06, 'epoch': 1.57}
{'loss': 0.6057, 'learning_rate': 6.4955720224109885e-06, 'epoch': 1.57}
{'loss': 0.781, 'learning_rate': 6.4928610157238395e-06, 'epoch': 1.57}
{'loss': 0.5593, 'learning_rate': 6.490150009036689e-06, 'epoch': 1.57}
{'loss': 0.9888, 'learning_rate': 6.48743900234954e-06, 'epoch': 1.57}
{'loss': 0.2368, 'learning_rate': 6.484727995662389e-06, 'epoch': 1.57}

 78%|███████▊  | 8675/11066 [31:46<08:50,  4.51it/s]
 78%|███████▊  | 8676/11066 [31:46<08:50,  4.51it/s]
                                                    

 78%|███████▊  | 8676/11066 [31:46<08:50,  4.51it/s]
 78%|███████▊  | 8677/11066 [31:47<08:49,  4.51it/s]
                                                    

 78%|███████▊  | 8677/11066 [31:47<08:49,  4.51it/s]
 78%|███████▊  | 8678/11066 [31:47<08:49,  4.51it/s]
                                                    

 78%|███████▊  | 8678/11066 [31:47<08:49,  4.51it/s]
 78%|███████▊  | 8679/11066 [31:47<08:49,  4.51it/s]
                                                    

 78%|███████▊  | 8679/11066 [31:47<08:49,  4.51it/s]
 78%|███████▊  | 8680/11066 [31:47<08:46,  4.54it/s]
                                                    

 78%|███████▊  | 8680/11066 [31:47<08:46,  4.54it/s]
 78%|███████▊  | 8681/11066 [31:48<08:48,  4.51it/s]
                                                    

 78%|███████▊  | 8681/11066 [31:48<08:48,  4.51it/s]
 78%|███████▊  | 8682/11066 [31:48<08:48,  4.51it/s]
                                                    

 78%|███████▊  | 8682/11066 [31:48<08:48,  4.51it/s]
 78%|███████▊  | 8683/11066 [31:48<08:49,  4.50it/s]
                                                    

 78%|███████▊  | 8683/11066 [31:48<08:49,  4.50it/s]
 78%|███████▊  | 8684/11066 [31:48<08:48,  4.50it/s]
                                                    

 78%|███████▊  | 8684/11066 [31:48<08:48,  4.50it/s]
 78%|███████▊  | 8685/11066 [31:48<08:49,  4.50it/s]
                                                    

 78%|███████▊  | 8685/11066 [31:48<08:49,  4.50it/s]
 78%|███████▊  | 8686/11066 [31:49<08:48,  4.50it/s]
                                                    

 78%|███████▊  | 8686/11066 [31:49<08:48,  4.50it/s]
 79%|███████▊  | 8687/11066 [31:49<08:48,  4.50it/s]
                                                    

 79%|███████▊  | 8687/11066 [31:49<08:48,  4.50it/s]
 79%|███████▊  | 8688/11066 [31:49<08:47,  4.50it/s]
                                                    

 79%|███████▊  | 8688/11066 [31:49<08:47,  4.50it/s]
 79%|███████▊  | 8689/11066 [31:49<08:47,  4.51it/s]
                                                    

 79%|███████▊  | 8689/11066 [31:49<08:47,  4.51it/s]
 79%|███████▊  | 8690/11066 [31:50<08:46,  4.51it/s]
                                                    

 79%|███████▊  | 8690/11066 [31:50<08:46,  4.51it/s]
 79%|███████▊  | 8691/11066 [31:50<08:47,  4.51it/s]
                                                    

 79%|███████▊  | 8691/11066 [31:50<08:47,  4.51it/s]
 79%|███████▊  | 8692/11066 [31:50<08:47,  4.50it/s]
                                                    

 79%|███████▊  | 8692/11066 [31:50<08:47,  4.50it/s]
 79%|███████▊  | 8693/11066 [31:50<08:47,  4.50it/s]
                                                    

 79%|███████▊  | 8693/11066 [31:50<08:47,  4.50it/s]
 79%|███████▊  | 8694/11066 [31:50<08:48,  4.49it/s]
                                                    

 79%|███████▊  | 8694/11066 [31:50<08:48,  4.49it/s]
 79%|███████▊  | 8695/11066 [31:51<08:49,  4.48it/s]
                                                    

 79%|███████▊  | 8695/11066 [31:51<08:49,  4.48it/s]
 79%|███████▊  | 8696/11066 [31:51<08:54,  4.44it/s]
                                                    

 79%|███████▊  | 8696/11066 [31:51<08:54,  4.44it/s]
 79%|███████▊  | 8697/11066 [31:51<08:54,  4.43it/s]
                                                    

 79%|███████▊  | 8697/11066 [31:51<08:54,  4.43it/s]
 79%|███████▊  | 8698/11066 [31:51<08:55,  4.42it/s]
                                                    

 79%|███████▊  | 8698/11066 [31:51<08:55,  4.42it/s]
 79%|███████▊  | 8699/11066 [31:52<08:54,  4.43it/s]
                                                    

 79%|███████▊  | 8699/11066 [31:52<08:54,  4.43it/s]
 79%|███████▊  | 8700/11066 [31:52<08:58,  4.39it/s]
                                                    

 79%|███████▊  | 8700/11066 [31:52<08:58,  4.39it/s]
 79%|███████▊  | 8701/11066 [31:52<08:46,  4.49it/s]
                                                    

 79%|███████▊  | 8701/11066 [31:52<08:46,  4.49it/s]
 79%|███████▊  | 8702/11066 [31:52<08:46,  4.49it/s]
                                                    

 79%|███████▊  | 8702/11066 [31:52<08:46,  4.49it/s]
 79%|███████▊  | 8703/11066 [31:53<08:47,  4.48it/s]
                                                    

 79%|███████▊  | 8703/11066 [31:53<08:47,  4.48it/s]
 79%|███████▊  | 8704/11066 [31:53<08:47,  4.48it/s]
                                                    

 79%|███████▊  | 8704/11066 [31:53<08:47,  4.48it/s]
 79%|███████▊  | 8705/11066 [31:53<08:53,  4.42it/s]
                                                    

 79%|███████▊  | 8705/11066 [31:53<08:53,  4.42it/s]
 79%|███████▊  | 8706/11066 [31:53<08:49,  4.46it/s]
                                                    

 79%|███████▊  | 8706/11066 [31:53<08:49,  4.46it/s]
 79%|███████▊  | 8707/11066 [31:53<08:51,  4.44it/s]
                                                    

 79%|███████▊  | 8707/11066 [31:53<08:51,  4.44it/s]
 79%|███████▊  | 8708/11066 [31:54<08:58,  4.38it/s]
                                                    

 79%|███████▊  | 8708/11066 [31:54<08:58,  4.38it/s]
 79%|███████▊  | 8709/11066 [31:54<08:51,  4.43it/s]
                                                    

 79%|███████▊  | 8709/11066 [31:54<08:51,  4.43it/s]
 79%|███████▊  | 8710/11066 [31:54<08:51,  4.43it/s]
                                                    

 79%|███████▊  | 8710/11066 [31:54<08:51,  4.43it/s]
 79%|███████▊  | 8711/11066 [31:54<08:51,  4.43it/s]
                                                    

 79%|███████▊  | 8711/11066 [31:54<08:51,  4.43it/s]
 79%|███████▊  | 8712/11066 [31:55<08:49,  4.45it/s]
                                                    

 79%|███████▊  | 8712/11066 [31:55<08:49,  4.45it/s]
 79%|███████▊  | 8713/11066 [31:55<08:51,  4.43it/s]
                                                    

 79%|███████▊  | 8713/11066 [31:55<08:51,  4.43it/s]
 79%|███████▊  | 8714/11066 [31:55<08:49,  4.44it/s]
                                                    

 79%|███████▊  | 8714/11066 [31:55<08:49,  4.44it/s]
 79%|███████▉  | 8715/11066 [31:55<08:47,  4.46it/s]
                                                    

 79%|███████▉  | 8715/11066 [31:55<08:47,  4.46it/s]
 79%|███████▉  | 8716/11066 [31:55<08:45,  4.47it/s]
                                                    

 79%|███████▉  | 8716/11066 [31:55<08:45,  4.47it/s]
 79%|███████▉  | 8717/11066 [31:56<08:44,  4.48it/s]
                                                    

 79%|███████▉  | 8717/11066 [31:56<08:44,  4.48it/s]
 79%|███████▉  | 8718/11066 [31:56<08:43,  4.49it/s]
                                                    

 79%|███████▉  | 8718/11066 [31:56<08:43,  4.49it/s]
 79%|███████▉  | 8719/11066 [31:56<08:49,  4.43it/s]
                                                    

 79%|███████▉  | 8719/11066 [31:56<08:49,  4.43it/s]
 79%|███████▉  | 8720/11066 [31:56<08:48,  4.44it/s]
                                                    

 79%|███████▉  | 8720/11066 [31:56<08:48,  4.44it/s]
 79%|███████▉  | 8721/11066 [31:57<08:45,  4.46it/s]
                                                    

 79%|███████▉  | 8721/11066 [31:57<08:45,  4.46it/s]
 79%|███████▉  | 8722/11066 [31:57<08:44,  4.47it/s]
                                                    

 79%|███████▉  | 8722/11066 [31:57<08:44,  4.47it/s]
 79%|███████▉  | 8723/11066 [31:57<08:42,  4.48it/s]
                                                    

 79%|███████▉  | 8723/11066 [31:57<08:42,  4.48it/s]
 79%|███████▉  | 8724/11066 [31:57<08:41,  4.49it/s]
                                                    

 79%|███████▉  | 8724/11066 [31:57<08:41,  4.49it/s]
 79%|███████▉  | 8725/11066 [31:57<08:41,  4.49it/s]
                                                    

 79%|███████▉  | 8725/11066 [31:57<08:41,  4.49it/s]
 79%|███████▉  | 8726/11066 [31:58<08:41,  4.49it/s]
                                                    

 79%|███████▉  | 8726/11066 [31:58<08:41,  4.49it/s]
 79%|███████▉  | 8727/11066 [31:58<08:37,  4.52it/s]
                                                    

 79%|███████▉  | 8727/11066 [31:58<08:37,  4.52it/s]
 79%|███████▉  | 8728/11066 [31:58<08:30,  4.58it/s]
                                                    

 79%|███████▉  | 8728/11066 [31:58<08:30,  4.58it/s]
 79%|███████▉  | 8729/11066 [31:58<08:30,  4.58it/s]
                                                    

 79%|███████▉  | 8729/11066 [31:58<08:30,  4.58it/s]
 79%|███████▉  | 8730/11066 [31:59<08:33,  4.55it/s]
                                                    

 79%|███████▉  | 8730/11066 [31:59<08:33,  4.55it/s]
 79%|███████▉  | 8731/11066 [31:59<08:35,  4.53it/s]
                                                    

 79%|███████▉  | 8731/11066 [31:59<08:35,  4.53it/s]
 79%|███████▉  | 8732/11066 [31:59<08:35,  4.53it/s]
                                                    

 79%|███████▉  | 8732/11066 [31:59<08:35,  4.53it/s]
 79%|███████▉  | 8733/11066 [31:59<08:33,  4.54it/s]
                                                    

 79%|███████▉  | 8733/11066 [31:59<08:33,  4.54it/s]
 79%|███████▉  | 8734/11066 [31:59<08:37,  4.51it/s]
                                                    

 79%|███████▉  | 8734/11066 [31:59<08:37,  4.51it/s]
 79%|███████▉  | 8735/11066 [32:00<08:38,  4.50it/s]
                                                    

 79%|███████▉  | 8735/11066 [32:00<08:38,  4.50it/s]
 79%|███████▉  | 8736/11066 [32:00<08:31,  4.56it/s]
                                                    

 79%|███████▉  | 8736/11066 [32:00<08:31,  4.56it/s]
 79%|███████▉  | 8737/11066 [32:00<08:25,  4.60it/s]
                                                    

 79%|███████▉  | 8737/11066 [32:00<08:25,  4.60it/s]
 79%|███████▉  | 8738/11066 [32:00<08:25,  4.61it/s]
                                                    

 79%|███████▉  | 8738/11066 [32:00<08:25,  4.61it/s]
 79%|███████▉  | 8739/11066 [32:01<08:30,  4.56it/s]
                                                    

 79%|███████▉  | 8739/11066 [32:01<08:30,  4.56it/s]
 79%|███████▉  | 8740/11066 [32:01<08:25,  4.60it/s]
                                                    

 79%|███████▉  | 8740/11066 [32:01<08:25,  4.60it/s]
 79%|███████▉  | 8741/11066 [32:01<08:24,  4.61it/s]
                                                    

 79%|███████▉  | 8741/11066 [32:01<08:24,  4.61it/s]
 79%|███████▉  | 8742/11066 [32:01<08:21,  4.63it/s]
                                                    

 79%|███████▉  | 8742/11066 [32:01<08:21,  4.63it/s]
 79%|███████▉  | 8743/11066 [32:01<08:22,  4.63it/s]
                                                    

 79%|███████▉  | 8743/11066 [32:01<08:22,  4.63it/s]
 79%|███████▉  | 8744/11066 [32:02<08:25,  4.59it/s]
                                                    

 79%|███████▉  | 8744/11066 [32:02<08:25,  4.59it/s]
 79%|███████▉  | 8745/11066 [32:02<08:21,  4.63it/s]
                                                    

 79%|███████▉  | 8745/11066 [32:02<08:21,  4.63it/s]
 79%|███████▉  | 8746/11066 [32:02<08:25,  4.59it/s]
                                                    

 79%|███████▉  | 8746/11066 [32:02<08:25,  4.59it/s]
 79%|███████▉  | 8747/11066 [32:02<08:22,  4.62it/s]
                                                    

 79%|███████▉  | 8747/11066 [32:02<08:22,  4.62it/s]
 79%|███████▉  | 8748/11066 [32:02<08:22,  4.61it/s]
                                                    

 79%|███████▉  | 8748/11066 [32:02<08:22,  4.61it/s]
 79%|███████▉  | 8749/11066 [32:03<08:26,  4.57it/s]
                                                    

 79%|███████▉  | 8749/11066 [32:03<08:26,  4.57it/s]
 79%|███████▉  | 8750/11066 [32:03<08:29,  4.55it/s]
                                                    

 79%|███████▉  | 8750/11066 [32:03<08:29,  4.55it/s]
 79%|███████▉  | 8751/11066 [32:03<08:26,  4.57it/s]
                                                    

 79%|███████▉  | 8751/11066 [32:03<08:26,  4.57it/s]
 79%|███████▉  | 8752/11066 [32:03<08:23,  4.60it/s]
                                                    

 79%|███████▉  | 8752/11066 [32:03<08:23,  4.60it/s]
 79%|███████▉  | 8753/11066 [32:04<08:21,  4.62it/s]
                                                    

 79%|███████▉  | 8753/11066 [32:04<08:21,  4.62it/s]
 79%|███████▉  | 8754/11066 [32:04<08:21,  4.61it/s]
                                                    

 79%|███████▉  | 8754/11066 [32:04<08:21,  4.61it/s]
 79%|███████▉  | 8755/11066 [32:04<08:40,  4.44it/s]
                                                    

 79%|███████▉  | 8755/11066 [32:04<08:40,  4.44it/s]
 79%|███████▉  | 8756/11066 [32:04<08:34,  4.49it/s]
                                                    

 79%|███████▉  | 8756/11066 [32:04<08:34,  4.49it/s]
 79%|███████▉  | 8757/11066 [32:04<08:33,  4.50it/s]
                                                    

 79%|███████▉  | 8757/11066 [32:04<08:33,  4.50it/s]
 79%|███████▉  | 8758/11066 [32:05<08:31,  4.51it/s]
                                                    

 79%|███████▉  | 8758/11066 [32:05<08:31,  4.51it/s]
 79%|███████▉  | 8759/11066 [32:05<08:25,  4.56it/s]
                                                    

 79%|███████▉  | 8759/11066 [32:05<08:25,  4.56it/s]
 79%|███████▉  | 8760/11066 [32:05<08:23,  4.58it/s]
                                                    

 79%|███████▉  | 8760/11066 [32:05<08:23,  4.58it/s]
 79%|███████▉  | 8761/11066 [32:05<08:18,  4.62it/s]
                                                    

 79%|███████▉  | 8761/11066 [32:05<08:18,  4.62it/s]
 79%|███████▉  | 8762/11066 [32:06<08:21,  4.60it/s]
                                                    

 79%|███████▉  | 8762/11066 [32:06<08:21,  4.60it/s]
 79%|███████▉  | 8763/11066 [32:06<08:20,  4.61it/s]
                                                    

 79%|███████▉  | 8763/11066 [32:06<08:20,  4.61it/s]
 79%|███████▉  | 8764/11066 [32:06<08:22,  4.58it/s]
                                                    

 79%|███████▉  | 8764/11066 [32:06<08:22,  4.58it/s]
 79%|███████▉  | 8765/11066 [32:06<08:27,  4.54it/s]
                                                    

 79%|███████▉  | 8765/11066 [32:06<08:27,  4.54it/s]
 79%|███████▉  | 8766/11066 [32:06<08:24,  4.56it/s]
                                                    

 79%|███████▉  | 8766/11066 [32:06<08:24,  4.56it/s]
 79%|███████▉  | 8767/11066 [32:07<08:23,  4.57it/s]
                                                    

 79%|███████▉  | 8767/11066 [32:07<08:23,  4.57it/s]
 79%|███████▉  | 8768/11066 [32:07<08:25,  4.54it/s]
                                                    

 79%|███████▉  | 8768/11066 [32:07<08:25,  4.54it/s]
 79%|███████▉  | 8769/11066 [32:07<08:27,  4.53it/s]
                                                    

 79%|███████▉  | 8769/11066 [32:07<08:27,  4.53it/s]
 79%|███████▉  | 8770/11066 [32:07<08:26,  4.54it/s]
                                                    

 79%|███████▉  | 8770/11066 [32:07<08:26,  4.54it/s]
 79%|███████▉  | 8771/11066 [32:08<08:27,  4.52it/s]
                                                    

 79%|███████▉  | 8771/11066 [32:08<08:27,  4.52it/s]
 79%|███████▉  | 8772/11066 [32:08<08:24,  4.54it/s]
                                                    

 79%|███████▉  | 8772/11066 [32:08<08:24,  4.54it/s]
 79%|███████▉  | 8773/11066 [32:08<08:20,  4.58it/s]
                                                    

 79%|███████▉  | 8773/11066 [32:08<08:20,  4.58it/s]
 79%|███████▉  | 8774/11066 [32:08<08:24,  4.55it/s]
                                                    

 79%|███████▉  | 8774/11066 [32:08<08:24,  4.55it/s]
 79%|███████▉  | 8775/11066 [32:08<08:22,  4.56it/s]
                                                    

 79%|███████▉  | 8775/11066 [32:08<08:22,  4.56it/s]
 79%|███████▉  | 8776/11066 [32:09<08:23,  4.55it/s]
                                                    

 79%|███████▉  | 8776/11066 [32:09<08:23,  4.55it/s]
 79%|███████▉  | 8777/11066 [32:09<08:16,  4.61it/s]
                                                    

 79%|███████▉  | 8777/11066 [32:09<08:16,  4.61it/s]
 79%|███████▉  | 8778/11066 [32:09<08:15,  4.62it/s]
                                                    

 79%|███████▉  | 8778/11066 [32:09<08:15,  4.62it/s]
 79%|███████▉  | 8779/11066 [32:09<08:18,  4.58it/s]
                                                    

 79%|███████▉  | 8779/11066 [32:09<08:18,  4.58it/s]
 79%|███████▉  | 8780/11066 [32:09<08:23,  4.54it/s]
                                                    

 79%|███████▉  | 8780/11066 [32:09<08:23,  4.54it/s]
 79%|███████▉  | 8781/11066 [32:10<08:21,  4.56it/s]
                                                    

 79%|███████▉  | 8781/11066 [32:10<08:21,  4.56it/s]
 79%|███████▉  | 8782/11066 [32:10<08:18,  4.58it/s]
                                                    

 79%|███████▉  | 8782/11066 [32:10<08:18,  4.58it/s]
 79%|███████▉  | 8783/11066 [32:10<08:17,  4.59it/s]
                                                    

 79%|███████▉  | 8783/11066 [32:10<08:17,  4.59it/s]
 79%|███████▉  | 8784/11066 [32:10<08:30,  4.47it/s]
                                                    

 79%|███████▉  | 8784/11066 [32:10<08:30,  4.47it/s]
 79%|███████▉  | 8785/11066 [32:11<08:36,  4.42it/s]
                                                    

 79%|███████▉  | 8785/11066 [32:11<08:36,  4.42it/s]
 79%|███████▉  | 8786/11066 [32:11<08:33,  4.44it/s]
                                                    

 79%|███████▉  | 8786/11066 [32:11<08:33,  4.44it/s]
 79%|███████▉  | 8787/11066 [32:11<08:31,  4.46it/s]
                                                    

 79%|███████▉  | 8787/11066 [32:11<08:31,  4.46it/s]
 79%|███████▉  | 8788/11066 [32:11<08:30,  4.46it/s]
                                                    
{'loss': 0.42, 'learning_rate': 6.48201698897524e-06, 'epoch': 1.57}
{'loss': 0.7071, 'learning_rate': 6.479305982288089e-06, 'epoch': 1.57}
{'loss': 1.1776, 'learning_rate': 6.47659497560094e-06, 'epoch': 1.57}
{'loss': 0.7175, 'learning_rate': 6.4738839689137896e-06, 'epoch': 1.57}
{'loss': 1.2072, 'learning_rate': 6.4711729622266405e-06, 'epoch': 1.57}
{'loss': 0.624, 'learning_rate': 6.468461955539491e-06, 'epoch': 1.57}
{'loss': 1.0989, 'learning_rate': 6.465750948852341e-06, 'epoch': 1.57}
{'loss': 0.7008, 'learning_rate': 6.463039942165191e-06, 'epoch': 1.57}
{'loss': 0.3796, 'learning_rate': 6.460328935478041e-06, 'epoch': 1.57}
{'loss': 0.5342, 'learning_rate': 6.457617928790891e-06, 'epoch': 1.57}
{'loss': 0.6983, 'learning_rate': 6.454906922103741e-06, 'epoch': 1.57}
{'loss': 0.5084, 'learning_rate': 6.4521959154165915e-06, 'epoch': 1.57}
{'loss': 0.533, 'learning_rate': 6.449484908729442e-06, 'epoch': 1.57}
{'loss': 0.9049, 'learning_rate': 6.446773902042292e-06, 'epoch': 1.57}
{'loss': 0.9739, 'learning_rate': 6.444062895355142e-06, 'epoch': 1.57}
{'loss': 0.6287, 'learning_rate': 6.441351888667992e-06, 'epoch': 1.57}
{'loss': 0.7055, 'learning_rate': 6.438640881980843e-06, 'epoch': 1.57}
{'loss': 0.8758, 'learning_rate': 6.435929875293692e-06, 'epoch': 1.57}
{'loss': 0.8909, 'learning_rate': 6.433218868606543e-06, 'epoch': 1.57}
{'loss': 0.6485, 'learning_rate': 6.4305078619193926e-06, 'epoch': 1.57}
{'loss': 0.8112, 'learning_rate': 6.4277968552322435e-06, 'epoch': 1.57}
{'loss': 0.4544, 'learning_rate': 6.425085848545093e-06, 'epoch': 1.57}
{'loss': 0.6546, 'learning_rate': 6.422374841857944e-06, 'epoch': 1.57}
{'loss': 0.6754, 'learning_rate': 6.419663835170793e-06, 'epoch': 1.57}
{'loss': 0.5298, 'learning_rate': 6.416952828483644e-06, 'epoch': 1.57}
{'loss': 0.2845, 'learning_rate': 6.414241821796493e-06, 'epoch': 1.57}
{'loss': 0.7181, 'learning_rate': 6.411530815109344e-06, 'epoch': 1.57}
{'loss': 0.509, 'learning_rate': 6.4088198084221945e-06, 'epoch': 1.57}
{'loss': 0.6829, 'learning_rate': 6.406108801735045e-06, 'epoch': 1.57}
{'loss': 0.3071, 'learning_rate': 6.403397795047895e-06, 'epoch': 1.57}
{'loss': 0.7668, 'learning_rate': 6.400686788360745e-06, 'epoch': 1.57}
{'loss': 0.7801, 'learning_rate': 6.397975781673595e-06, 'epoch': 1.57}
{'loss': 0.9597, 'learning_rate': 6.395264774986445e-06, 'epoch': 1.57}
{'loss': 0.6261, 'learning_rate': 6.392553768299295e-06, 'epoch': 1.57}
{'loss': 0.4166, 'learning_rate': 6.389842761612145e-06, 'epoch': 1.57}
{'loss': 1.147, 'learning_rate': 6.3871317549249956e-06, 'epoch': 1.57}
{'loss': 1.2534, 'learning_rate': 6.384420748237846e-06, 'epoch': 1.57}
{'loss': 0.9894, 'learning_rate': 6.381709741550696e-06, 'epoch': 1.57}
{'loss': 0.9123, 'learning_rate': 6.378998734863547e-06, 'epoch': 1.57}
{'loss': 0.7348, 'learning_rate': 6.376287728176396e-06, 'epoch': 1.57}
{'loss': 1.1816, 'learning_rate': 6.373576721489247e-06, 'epoch': 1.58}
{'loss': 0.8072, 'learning_rate': 6.370865714802096e-06, 'epoch': 1.58}
{'loss': 0.5074, 'learning_rate': 6.368154708114947e-06, 'epoch': 1.58}
{'loss': 0.9935, 'learning_rate': 6.365443701427797e-06, 'epoch': 1.58}
{'loss': 1.0297, 'learning_rate': 6.362732694740648e-06, 'epoch': 1.58}
{'loss': 0.798, 'learning_rate': 6.360021688053497e-06, 'epoch': 1.58}
{'loss': 0.9234, 'learning_rate': 6.357310681366348e-06, 'epoch': 1.58}
{'loss': 0.7363, 'learning_rate': 6.354599674679198e-06, 'epoch': 1.58}
{'loss': 0.6379, 'learning_rate': 6.351888667992048e-06, 'epoch': 1.58}
{'loss': 0.5436, 'learning_rate': 6.349177661304898e-06, 'epoch': 1.58}
{'loss': 0.617, 'learning_rate': 6.346466654617748e-06, 'epoch': 1.58}
{'loss': 0.5502, 'learning_rate': 6.3437556479305986e-06, 'epoch': 1.58}
{'loss': 1.0478, 'learning_rate': 6.341044641243449e-06, 'epoch': 1.58}
{'loss': 0.8771, 'learning_rate': 6.338333634556299e-06, 'epoch': 1.58}
{'loss': 0.6438, 'learning_rate': 6.335622627869149e-06, 'epoch': 1.58}
{'loss': 0.5523, 'learning_rate': 6.332911621181999e-06, 'epoch': 1.58}
{'loss': 0.9454, 'learning_rate': 6.330200614494849e-06, 'epoch': 1.58}
{'loss': 0.7091, 'learning_rate': 6.327489607807699e-06, 'epoch': 1.58}
{'loss': 0.5218, 'learning_rate': 6.32477860112055e-06, 'epoch': 1.58}
{'loss': 0.8287, 'learning_rate': 6.3220675944334e-06, 'epoch': 1.58}
{'loss': 0.4317, 'learning_rate': 6.319356587746251e-06, 'epoch': 1.58}
{'loss': 0.4041, 'learning_rate': 6.3166455810591e-06, 'epoch': 1.58}
{'loss': 0.7773, 'learning_rate': 6.313934574371951e-06, 'epoch': 1.58}
{'loss': 0.6891, 'learning_rate': 6.3112235676848e-06, 'epoch': 1.58}
{'loss': 0.4886, 'learning_rate': 6.308512560997651e-06, 'epoch': 1.58}
{'loss': 0.5094, 'learning_rate': 6.3058015543105004e-06, 'epoch': 1.58}
{'loss': 0.1469, 'learning_rate': 6.303090547623351e-06, 'epoch': 1.58}
{'loss': 1.0671, 'learning_rate': 6.300379540936201e-06, 'epoch': 1.58}
{'loss': 0.5897, 'learning_rate': 6.297668534249052e-06, 'epoch': 1.58}
{'loss': 1.0532, 'learning_rate': 6.294957527561902e-06, 'epoch': 1.58}
{'loss': 0.9879, 'learning_rate': 6.292246520874752e-06, 'epoch': 1.58}
{'loss': 0.9693, 'learning_rate': 6.289535514187602e-06, 'epoch': 1.58}
{'loss': 0.5236, 'learning_rate': 6.286824507500452e-06, 'epoch': 1.58}
{'loss': 0.7199, 'learning_rate': 6.284113500813302e-06, 'epoch': 1.58}
{'loss': 0.3578, 'learning_rate': 6.2814024941261525e-06, 'epoch': 1.58}
{'loss': 0.7723, 'learning_rate': 6.278691487439003e-06, 'epoch': 1.58}
{'loss': 0.7054, 'learning_rate': 6.275980480751852e-06, 'epoch': 1.58}
{'loss': 0.7483, 'learning_rate': 6.273269474064703e-06, 'epoch': 1.58}
{'loss': 0.6075, 'learning_rate': 6.270558467377553e-06, 'epoch': 1.58}
{'loss': 0.6399, 'learning_rate': 6.267847460690403e-06, 'epoch': 1.58}
{'loss': 0.5812, 'learning_rate': 6.265136454003253e-06, 'epoch': 1.58}
{'loss': 0.5053, 'learning_rate': 6.2624254473161034e-06, 'epoch': 1.58}
{'loss': 0.5182, 'learning_rate': 6.2597144406289536e-06, 'epoch': 1.58}
{'loss': 0.5506, 'learning_rate': 6.257003433941804e-06, 'epoch': 1.58}
{'loss': 1.297, 'learning_rate': 6.254292427254654e-06, 'epoch': 1.58}
{'loss': 0.8934, 'learning_rate': 6.251581420567504e-06, 'epoch': 1.58}
{'loss': 0.5544, 'learning_rate': 6.248870413880354e-06, 'epoch': 1.58}
{'loss': 1.0436, 'learning_rate': 6.246159407193204e-06, 'epoch': 1.58}
{'loss': 0.2801, 'learning_rate': 6.243448400506054e-06, 'epoch': 1.58}
{'loss': 0.5361, 'learning_rate': 6.240737393818905e-06, 'epoch': 1.58}
{'loss': 0.9106, 'learning_rate': 6.238026387131755e-06, 'epoch': 1.58}
{'loss': 0.4074, 'learning_rate': 6.235315380444606e-06, 'epoch': 1.58}
{'loss': 0.2991, 'learning_rate': 6.232604373757455e-06, 'epoch': 1.58}
{'loss': 0.4592, 'learning_rate': 6.229893367070306e-06, 'epoch': 1.58}
{'loss': 0.5734, 'learning_rate': 6.227182360383155e-06, 'epoch': 1.58}
{'loss': 0.9326, 'learning_rate': 6.224471353696006e-06, 'epoch': 1.59}
{'loss': 0.546, 'learning_rate': 6.2217603470088554e-06, 'epoch': 1.59}
{'loss': 0.5449, 'learning_rate': 6.219049340321706e-06, 'epoch': 1.59}
{'loss': 0.5751, 'learning_rate': 6.216338333634556e-06, 'epoch': 1.59}
{'loss': 1.0262, 'learning_rate': 6.213627326947407e-06, 'epoch': 1.59}
{'loss': 0.6826, 'learning_rate': 6.210916320260257e-06, 'epoch': 1.59}
{'loss': 0.718, 'learning_rate': 6.208205313573107e-06, 'epoch': 1.59}
{'loss': 1.0161, 'learning_rate': 6.205494306885957e-06, 'epoch': 1.59}
{'loss': 0.8099, 'learning_rate': 6.202783300198807e-06, 'epoch': 1.59}
{'loss': 0.6308, 'learning_rate': 6.200072293511657e-06, 'epoch': 1.59}
{'loss': 0.5657, 'learning_rate': 6.1973612868245075e-06, 'epoch': 1.59}
{'loss': 0.4828, 'learning_rate': 6.194650280137358e-06, 'epoch': 1.59}
{'loss': 1.3101, 'learning_rate': 6.191939273450208e-06, 'epoch': 1.59}
{'loss': 0.9839, 'learning_rate': 6.189228266763058e-06, 'epoch': 1.59}
{'loss': 0.8069, 'learning_rate': 6.186517260075908e-06, 'epoch': 1.59}
{'loss': 0.757, 'learning_rate': 6.183806253388758e-06, 'epoch': 1.59}
{'loss': 0.6693, 'learning_rate': 6.181095246701609e-06, 'epoch': 1.59}
{'loss': 0.7423, 'learning_rate': 6.1783842400144584e-06, 'epoch': 1.59}

 79%|███████▉  | 8788/11066 [32:11<08:30,  4.46it/s]
 79%|███████▉  | 8789/11066 [32:12<08:29,  4.47it/s]
                                                    

 79%|███████▉  | 8789/11066 [32:12<08:29,  4.47it/s]
 79%|███████▉  | 8790/11066 [32:12<08:24,  4.51it/s]
                                                    

 79%|███████▉  | 8790/11066 [32:12<08:24,  4.51it/s]
 79%|███████▉  | 8791/11066 [32:12<08:17,  4.57it/s]
                                                    

 79%|███████▉  | 8791/11066 [32:12<08:17,  4.57it/s]
 79%|███████▉  | 8792/11066 [32:12<08:16,  4.58it/s]
                                                    

 79%|███████▉  | 8792/11066 [32:12<08:16,  4.58it/s]
 79%|███████▉  | 8793/11066 [32:12<08:10,  4.63it/s]
                                                    

 79%|███████▉  | 8793/11066 [32:12<08:10,  4.63it/s]
 79%|███████▉  | 8794/11066 [32:13<08:14,  4.59it/s]
                                                    

 79%|███████▉  | 8794/11066 [32:13<08:14,  4.59it/s]
 79%|███████▉  | 8795/11066 [32:13<08:13,  4.60it/s]
                                                    

 79%|███████▉  | 8795/11066 [32:13<08:13,  4.60it/s]
 79%|███████▉  | 8796/11066 [32:13<08:15,  4.58it/s]
                                                    

 79%|███████▉  | 8796/11066 [32:13<08:15,  4.58it/s]
 79%|███████▉  | 8797/11066 [32:13<08:18,  4.55it/s]
                                                    

 79%|███████▉  | 8797/11066 [32:13<08:18,  4.55it/s]
 80%|███████▉  | 8798/11066 [32:13<08:21,  4.52it/s]
                                                    

 80%|███████▉  | 8798/11066 [32:13<08:21,  4.52it/s]
 80%|███████▉  | 8799/11066 [32:14<08:18,  4.55it/s]
                                                    

 80%|███████▉  | 8799/11066 [32:14<08:18,  4.55it/s]
 80%|███████▉  | 8800/11066 [32:14<08:14,  4.58it/s]
                                                    

 80%|███████▉  | 8800/11066 [32:14<08:14,  4.58it/s]
 80%|███████▉  | 8801/11066 [32:14<08:10,  4.62it/s]
                                                    

 80%|███████▉  | 8801/11066 [32:14<08:10,  4.62it/s]
 80%|███████▉  | 8802/11066 [32:14<08:13,  4.59it/s]
                                                    

 80%|███████▉  | 8802/11066 [32:14<08:13,  4.59it/s]
 80%|███████▉  | 8803/11066 [32:15<08:17,  4.54it/s]
                                                    

 80%|███████▉  | 8803/11066 [32:15<08:17,  4.54it/s]
 80%|███████▉  | 8804/11066 [32:15<08:19,  4.53it/s]
                                                    

 80%|███████▉  | 8804/11066 [32:15<08:19,  4.53it/s]
 80%|███████▉  | 8805/11066 [32:15<08:20,  4.52it/s]
                                                    

 80%|███████▉  | 8805/11066 [32:15<08:20,  4.52it/s]
 80%|███████▉  | 8806/11066 [32:15<08:20,  4.52it/s]
                                                    

 80%|███████▉  | 8806/11066 [32:15<08:20,  4.52it/s]
 80%|███████▉  | 8807/11066 [32:15<08:21,  4.51it/s]
                                                    

 80%|███████▉  | 8807/11066 [32:15<08:21,  4.51it/s]
 80%|███████▉  | 8808/11066 [32:16<08:21,  4.51it/s]
                                                    

 80%|███████▉  | 8808/11066 [32:16<08:21,  4.51it/s]
 80%|███████▉  | 8809/11066 [32:16<08:17,  4.54it/s]
                                                    

 80%|███████▉  | 8809/11066 [32:16<08:17,  4.54it/s]
 80%|███████▉  | 8810/11066 [32:16<08:20,  4.51it/s]
                                                    

 80%|███████▉  | 8810/11066 [32:16<08:20,  4.51it/s]
 80%|███████▉  | 8811/11066 [32:16<08:21,  4.50it/s]
                                                    

 80%|███████▉  | 8811/11066 [32:16<08:21,  4.50it/s]
 80%|███████▉  | 8812/11066 [32:17<08:21,  4.49it/s]
                                                    

 80%|███████▉  | 8812/11066 [32:17<08:21,  4.49it/s]
 80%|███████▉  | 8813/11066 [32:17<08:17,  4.53it/s]
                                                    

 80%|███████▉  | 8813/11066 [32:17<08:17,  4.53it/s]
 80%|███████▉  | 8814/11066 [32:17<08:20,  4.50it/s]
                                                    

 80%|███████▉  | 8814/11066 [32:17<08:20,  4.50it/s]
 80%|███████▉  | 8815/11066 [32:17<08:19,  4.51it/s]
                                                    

 80%|███████▉  | 8815/11066 [32:17<08:19,  4.51it/s]
 80%|███████▉  | 8816/11066 [32:17<08:21,  4.49it/s]
                                                    

 80%|███████▉  | 8816/11066 [32:17<08:21,  4.49it/s]
 80%|███████▉  | 8817/11066 [32:18<08:20,  4.49it/s]
                                                    

 80%|███████▉  | 8817/11066 [32:18<08:20,  4.49it/s]
 80%|███████▉  | 8818/11066 [32:18<08:20,  4.49it/s]
                                                    

 80%|███████▉  | 8818/11066 [32:18<08:20,  4.49it/s]
 80%|███████▉  | 8819/11066 [32:18<08:20,  4.49it/s]
                                                    

 80%|███████▉  | 8819/11066 [32:18<08:20,  4.49it/s]
 80%|███████▉  | 8820/11066 [32:18<08:20,  4.49it/s]
                                                    

 80%|███████▉  | 8820/11066 [32:18<08:20,  4.49it/s]
 80%|███████▉  | 8821/11066 [32:19<08:19,  4.49it/s]
                                                    

 80%|███████▉  | 8821/11066 [32:19<08:19,  4.49it/s]
 80%|███████▉  | 8822/11066 [32:19<08:19,  4.50it/s]
                                                    

 80%|███████▉  | 8822/11066 [32:19<08:19,  4.50it/s]
 80%|███████▉  | 8823/11066 [32:19<08:18,  4.50it/s]
                                                    

 80%|███████▉  | 8823/11066 [32:19<08:18,  4.50it/s]
 80%|███████▉  | 8824/11066 [32:19<08:14,  4.53it/s]
                                                    

 80%|███████▉  | 8824/11066 [32:19<08:14,  4.53it/s]
 80%|███████▉  | 8825/11066 [32:19<08:10,  4.57it/s]
                                                    

 80%|███████▉  | 8825/11066 [32:19<08:10,  4.57it/s]
 80%|███████▉  | 8826/11066 [32:20<08:09,  4.58it/s]
                                                    

 80%|███████▉  | 8826/11066 [32:20<08:09,  4.58it/s]
 80%|███████▉  | 8827/11066 [32:20<08:05,  4.61it/s]
                                                    

 80%|███████▉  | 8827/11066 [32:20<08:05,  4.61it/s]
 80%|███████▉  | 8828/11066 [32:20<08:04,  4.62it/s]
                                                    

 80%|███████▉  | 8828/11066 [32:20<08:04,  4.62it/s]
 80%|███████▉  | 8829/11066 [32:20<08:09,  4.57it/s]
                                                    

 80%|███████▉  | 8829/11066 [32:20<08:09,  4.57it/s]
 80%|███████▉  | 8830/11066 [32:21<08:08,  4.58it/s]
                                                    

 80%|███████▉  | 8830/11066 [32:21<08:08,  4.58it/s]
 80%|███████▉  | 8831/11066 [32:21<08:11,  4.55it/s]
                                                    

 80%|███████▉  | 8831/11066 [32:21<08:11,  4.55it/s]
 80%|███████▉  | 8832/11066 [32:21<08:07,  4.58it/s]
                                                    

 80%|███████▉  | 8832/11066 [32:21<08:07,  4.58it/s]
 80%|███████▉  | 8833/11066 [32:21<08:09,  4.56it/s]
                                                    

 80%|███████▉  | 8833/11066 [32:21<08:09,  4.56it/s]
 80%|███████▉  | 8834/11066 [32:21<08:07,  4.57it/s]
                                                    

 80%|███████▉  | 8834/11066 [32:21<08:07,  4.57it/s]
 80%|███████▉  | 8835/11066 [32:22<08:04,  4.60it/s]
                                                    

 80%|███████▉  | 8835/11066 [32:22<08:04,  4.60it/s]
 80%|███████▉  | 8836/11066 [32:22<08:05,  4.60it/s]
                                                    

 80%|███████▉  | 8836/11066 [32:22<08:05,  4.60it/s]
 80%|███████▉  | 8837/11066 [32:22<08:02,  4.62it/s]
                                                    

 80%|███████▉  | 8837/11066 [32:22<08:02,  4.62it/s]
 80%|███████▉  | 8838/11066 [32:22<08:00,  4.64it/s]
                                                    

 80%|███████▉  | 8838/11066 [32:22<08:00,  4.64it/s]
 80%|███████▉  | 8839/11066 [32:22<08:02,  4.62it/s]
                                                    

 80%|███████▉  | 8839/11066 [32:22<08:02,  4.62it/s]
 80%|███████▉  | 8840/11066 [32:23<08:06,  4.58it/s]
                                                    

 80%|███████▉  | 8840/11066 [32:23<08:06,  4.58it/s]
 80%|███████▉  | 8841/11066 [32:23<08:09,  4.54it/s]
                                                    

 80%|███████▉  | 8841/11066 [32:23<08:09,  4.54it/s]
 80%|███████▉  | 8842/11066 [32:23<08:13,  4.51it/s]
                                                    

 80%|███████▉  | 8842/11066 [32:23<08:13,  4.51it/s]
 80%|███████▉  | 8843/11066 [32:23<08:14,  4.49it/s]
                                                    

 80%|███████▉  | 8843/11066 [32:23<08:14,  4.49it/s]
 80%|███████▉  | 8844/11066 [32:24<08:14,  4.49it/s]
                                                    

 80%|███████▉  | 8844/11066 [32:24<08:14,  4.49it/s]
 80%|███████▉  | 8845/11066 [32:24<08:13,  4.50it/s]
                                                    

 80%|███████▉  | 8845/11066 [32:24<08:13,  4.50it/s]
 80%|███████▉  | 8846/11066 [32:24<08:13,  4.50it/s]
                                                    

 80%|███████▉  | 8846/11066 [32:24<08:13,  4.50it/s]
 80%|███████▉  | 8847/11066 [32:24<08:13,  4.50it/s]
                                                    

 80%|███████▉  | 8847/11066 [32:24<08:13,  4.50it/s]
 80%|███████▉  | 8848/11066 [32:24<08:13,  4.50it/s]
                                                    

 80%|███████▉  | 8848/11066 [32:24<08:13,  4.50it/s]
 80%|███████▉  | 8849/11066 [32:25<08:12,  4.50it/s]
                                                    

 80%|███████▉  | 8849/11066 [32:25<08:12,  4.50it/s]
 80%|███████▉  | 8850/11066 [32:25<08:09,  4.52it/s]
                                                    

 80%|███████▉  | 8850/11066 [32:25<08:09,  4.52it/s]
 80%|███████▉  | 8851/11066 [32:25<08:09,  4.52it/s]
                                                    

 80%|███████▉  | 8851/11066 [32:25<08:09,  4.52it/s]
 80%|███████▉  | 8852/11066 [32:25<08:12,  4.50it/s]
                                                    

 80%|███████▉  | 8852/11066 [32:25<08:12,  4.50it/s]
 80%|████████  | 8853/11066 [32:26<08:13,  4.49it/s]
                                                    

 80%|████████  | 8853/11066 [32:26<08:13,  4.49it/s]
 80%|████████  | 8854/11066 [32:26<08:09,  4.52it/s]
                                                    

 80%|████████  | 8854/11066 [32:26<08:09,  4.52it/s]
 80%|████████  | 8855/11066 [32:26<08:11,  4.49it/s]
                                                    

 80%|████████  | 8855/11066 [32:26<08:11,  4.49it/s]
 80%|████████  | 8856/11066 [32:26<08:03,  4.57it/s]
                                                    

 80%|████████  | 8856/11066 [32:26<08:03,  4.57it/s]
 80%|████████  | 8857/11066 [32:26<08:12,  4.49it/s]
                                                    

 80%|████████  | 8857/11066 [32:26<08:12,  4.49it/s]
 80%|████████  | 8858/11066 [32:27<08:13,  4.47it/s]
                                                    

 80%|████████  | 8858/11066 [32:27<08:13,  4.47it/s]
 80%|████████  | 8859/11066 [32:27<08:12,  4.48it/s]
                                                    

 80%|████████  | 8859/11066 [32:27<08:12,  4.48it/s]
 80%|████████  | 8860/11066 [32:27<08:11,  4.49it/s]
                                                    

 80%|████████  | 8860/11066 [32:27<08:11,  4.49it/s]
 80%|████████  | 8861/11066 [32:27<08:16,  4.44it/s]
                                                    

 80%|████████  | 8861/11066 [32:27<08:16,  4.44it/s]
 80%|████████  | 8862/11066 [32:28<08:09,  4.50it/s]
                                                    

 80%|████████  | 8862/11066 [32:28<08:09,  4.50it/s]
 80%|████████  | 8863/11066 [32:28<08:04,  4.55it/s]
                                                    

 80%|████████  | 8863/11066 [32:28<08:04,  4.55it/s]
 80%|████████  | 8864/11066 [32:28<08:08,  4.51it/s]
                                                    

 80%|████████  | 8864/11066 [32:28<08:08,  4.51it/s]
 80%|████████  | 8865/11066 [32:28<08:17,  4.42it/s]
                                                    

 80%|████████  | 8865/11066 [32:28<08:17,  4.42it/s]
 80%|████████  | 8866/11066 [32:28<08:14,  4.45it/s]
                                                    

 80%|████████  | 8866/11066 [32:28<08:14,  4.45it/s]
 80%|████████  | 8867/11066 [32:29<08:08,  4.51it/s]
                                                    

 80%|████████  | 8867/11066 [32:29<08:08,  4.51it/s]
 80%|████████  | 8868/11066 [32:29<08:10,  4.48it/s]
                                                    

 80%|████████  | 8868/11066 [32:29<08:10,  4.48it/s]
 80%|████████  | 8869/11066 [32:29<08:06,  4.52it/s]
                                                    

 80%|████████  | 8869/11066 [32:29<08:06,  4.52it/s]
 80%|████████  | 8870/11066 [32:29<07:59,  4.58it/s]
                                                    

 80%|████████  | 8870/11066 [32:29<07:59,  4.58it/s]
 80%|████████  | 8871/11066 [32:30<07:56,  4.61it/s]
                                                    

 80%|████████  | 8871/11066 [32:30<07:56,  4.61it/s]
 80%|████████  | 8872/11066 [32:30<07:58,  4.58it/s]
                                                    

 80%|████████  | 8872/11066 [32:30<07:58,  4.58it/s]
 80%|████████  | 8873/11066 [32:30<07:57,  4.60it/s]
                                                    

 80%|████████  | 8873/11066 [32:30<07:57,  4.60it/s]
 80%|████████  | 8874/11066 [32:30<07:56,  4.60it/s]
                                                    

 80%|████████  | 8874/11066 [32:30<07:56,  4.60it/s]
 80%|████████  | 8875/11066 [32:30<07:54,  4.62it/s]
                                                    

 80%|████████  | 8875/11066 [32:30<07:54,  4.62it/s]
 80%|████████  | 8876/11066 [32:31<07:52,  4.64it/s]
                                                    

 80%|████████  | 8876/11066 [32:31<07:52,  4.64it/s]
 80%|████████  | 8877/11066 [32:31<08:00,  4.56it/s]
                                                    

 80%|████████  | 8877/11066 [32:31<08:00,  4.56it/s]
 80%|████████  | 8878/11066 [32:31<08:04,  4.52it/s]
                                                    

 80%|████████  | 8878/11066 [32:31<08:04,  4.52it/s]
 80%|████████  | 8879/11066 [32:31<08:01,  4.54it/s]
                                                    

 80%|████████  | 8879/11066 [32:31<08:01,  4.54it/s]
 80%|████████  | 8880/11066 [32:32<07:56,  4.58it/s]
                                                    

 80%|████████  | 8880/11066 [32:32<07:56,  4.58it/s]
 80%|████████  | 8881/11066 [32:32<07:55,  4.59it/s]
                                                    

 80%|████████  | 8881/11066 [32:32<07:55,  4.59it/s]
 80%|████████  | 8882/11066 [32:32<07:55,  4.59it/s]
                                                    

 80%|████████  | 8882/11066 [32:32<07:55,  4.59it/s]
 80%|████████  | 8883/11066 [32:32<07:55,  4.59it/s]
                                                    

 80%|████████  | 8883/11066 [32:32<07:55,  4.59it/s]
 80%|████████  | 8884/11066 [32:32<08:01,  4.53it/s]
                                                    

 80%|████████  | 8884/11066 [32:32<08:01,  4.53it/s]
 80%|████████  | 8885/11066 [32:33<08:07,  4.48it/s]
                                                    

 80%|████████  | 8885/11066 [32:33<08:07,  4.48it/s]
 80%|████████  | 8886/11066 [32:33<08:04,  4.50it/s]
                                                    

 80%|████████  | 8886/11066 [32:33<08:04,  4.50it/s]
 80%|████████  | 8887/11066 [32:33<07:57,  4.56it/s]
                                                    

 80%|████████  | 8887/11066 [32:33<07:57,  4.56it/s]
 80%|████████  | 8888/11066 [32:33<07:58,  4.55it/s]
                                                    

 80%|████████  | 8888/11066 [32:33<07:58,  4.55it/s]
 80%|████████  | 8889/11066 [32:34<07:56,  4.57it/s]
                                                    

 80%|████████  | 8889/11066 [32:34<07:56,  4.57it/s]
 80%|████████  | 8890/11066 [32:34<07:55,  4.57it/s]
                                                    

 80%|████████  | 8890/11066 [32:34<07:55,  4.57it/s]
 80%|████████  | 8891/11066 [32:34<07:53,  4.59it/s]
                                                    

 80%|████████  | 8891/11066 [32:34<07:53,  4.59it/s]
 80%|████████  | 8892/11066 [32:34<07:51,  4.61it/s]
                                                    

 80%|████████  | 8892/11066 [32:34<07:51,  4.61it/s]
 80%|████████  | 8893/11066 [32:34<07:55,  4.57it/s]
                                                    

 80%|████████  | 8893/11066 [32:34<07:55,  4.57it/s]
 80%|████████  | 8894/11066 [32:35<07:57,  4.55it/s]
                                                    

 80%|████████  | 8894/11066 [32:35<07:57,  4.55it/s]
 80%|████████  | 8895/11066 [32:35<07:59,  4.53it/s]
                                                    

 80%|████████  | 8895/11066 [32:35<07:59,  4.53it/s]
 80%|████████  | 8896/11066 [32:35<07:56,  4.55it/s]
                                                    

 80%|████████  | 8896/11066 [32:35<07:56,  4.55it/s]
 80%|████████  | 8897/11066 [32:35<07:52,  4.59it/s]
                                                    

 80%|████████  | 8897/11066 [32:35<07:52,  4.59it/s]
 80%|████████  | 8898/11066 [32:35<07:56,  4.55it/s]
                                                    

 80%|████████  | 8898/11066 [32:35<07:56,  4.55it/s]
 80%|████████  | 8899/11066 [32:36<07:52,  4.59it/s]
                                                    

 80%|████████  | 8899/11066 [32:36<07:52,  4.59it/s]
 80%|████████  | 8900/11066 [32:36<08:03,  4.48it/s]
                                                    

 80%|████████  | 8900/11066 [32:36<08:03,  4.48it/s]
 80%|████████  | 8901/11066 [32:36<08:01,  4.49it/s]
                                                    

 80%|████████  | 8901/11066 [32:36<08:01,  4.49it/s]
 80%|████████  | 8902/11066 [32:36<08:01,  4.50it/s]
                                                    
{'loss': 1.0856, 'learning_rate': 6.175673233327309e-06, 'epoch': 1.59}
{'loss': 0.6278, 'learning_rate': 6.172962226640159e-06, 'epoch': 1.59}
{'loss': 0.4967, 'learning_rate': 6.17025121995301e-06, 'epoch': 1.59}
{'loss': 1.2782, 'learning_rate': 6.167540213265859e-06, 'epoch': 1.59}
{'loss': 0.6197, 'learning_rate': 6.16482920657871e-06, 'epoch': 1.59}
{'loss': 0.6058, 'learning_rate': 6.162118199891559e-06, 'epoch': 1.59}
{'loss': 0.4606, 'learning_rate': 6.15940719320441e-06, 'epoch': 1.59}
{'loss': 0.8129, 'learning_rate': 6.15669618651726e-06, 'epoch': 1.59}
{'loss': 0.3179, 'learning_rate': 6.1539851798301105e-06, 'epoch': 1.59}
{'loss': 1.268, 'learning_rate': 6.151274173142961e-06, 'epoch': 1.59}
{'loss': 0.816, 'learning_rate': 6.148563166455811e-06, 'epoch': 1.59}
{'loss': 0.4757, 'learning_rate': 6.145852159768661e-06, 'epoch': 1.59}
{'loss': 0.6696, 'learning_rate': 6.143141153081511e-06, 'epoch': 1.59}
{'loss': 0.3763, 'learning_rate': 6.140430146394361e-06, 'epoch': 1.59}
{'loss': 1.0589, 'learning_rate': 6.137719139707211e-06, 'epoch': 1.59}
{'loss': 0.531, 'learning_rate': 6.1350081330200614e-06, 'epoch': 1.59}
{'loss': 0.5036, 'learning_rate': 6.1322971263329116e-06, 'epoch': 1.59}
{'loss': 0.7865, 'learning_rate': 6.129586119645762e-06, 'epoch': 1.59}
{'loss': 0.5736, 'learning_rate': 6.126875112958613e-06, 'epoch': 1.59}
{'loss': 0.5102, 'learning_rate': 6.124164106271462e-06, 'epoch': 1.59}
{'loss': 0.7812, 'learning_rate': 6.121453099584313e-06, 'epoch': 1.59}
{'loss': 0.6978, 'learning_rate': 6.118742092897162e-06, 'epoch': 1.59}
{'loss': 0.6072, 'learning_rate': 6.116031086210013e-06, 'epoch': 1.59}
{'loss': 1.086, 'learning_rate': 6.1133200795228625e-06, 'epoch': 1.59}
{'loss': 0.9041, 'learning_rate': 6.1106090728357135e-06, 'epoch': 1.59}
{'loss': 0.7278, 'learning_rate': 6.107898066148563e-06, 'epoch': 1.59}
{'loss': 0.4973, 'learning_rate': 6.105187059461414e-06, 'epoch': 1.59}
{'loss': 0.5898, 'learning_rate': 6.102476052774263e-06, 'epoch': 1.59}
{'loss': 0.6626, 'learning_rate': 6.099765046087114e-06, 'epoch': 1.59}
{'loss': 0.5354, 'learning_rate': 6.097054039399964e-06, 'epoch': 1.59}
{'loss': 0.6949, 'learning_rate': 6.094343032712814e-06, 'epoch': 1.59}
{'loss': 0.5048, 'learning_rate': 6.0916320260256644e-06, 'epoch': 1.59}
{'loss': 0.4692, 'learning_rate': 6.0889210193385146e-06, 'epoch': 1.59}
{'loss': 0.8737, 'learning_rate': 6.086210012651365e-06, 'epoch': 1.59}
{'loss': 0.1897, 'learning_rate': 6.083499005964215e-06, 'epoch': 1.59}
{'loss': 1.5147, 'learning_rate': 6.080787999277065e-06, 'epoch': 1.59}
{'loss': 0.3551, 'learning_rate': 6.078076992589915e-06, 'epoch': 1.59}
{'loss': 1.0718, 'learning_rate': 6.075365985902765e-06, 'epoch': 1.59}
{'loss': 0.7521, 'learning_rate': 6.072654979215616e-06, 'epoch': 1.6}
{'loss': 0.8257, 'learning_rate': 6.0699439725284655e-06, 'epoch': 1.6}
{'loss': 0.7786, 'learning_rate': 6.0672329658413165e-06, 'epoch': 1.6}
{'loss': 0.5013, 'learning_rate': 6.064521959154166e-06, 'epoch': 1.6}
{'loss': 0.5438, 'learning_rate': 6.061810952467017e-06, 'epoch': 1.6}
{'loss': 0.9802, 'learning_rate': 6.059099945779866e-06, 'epoch': 1.6}
{'loss': 0.7648, 'learning_rate': 6.056388939092717e-06, 'epoch': 1.6}
{'loss': 0.5853, 'learning_rate': 6.053677932405566e-06, 'epoch': 1.6}
{'loss': 0.4936, 'learning_rate': 6.050966925718417e-06, 'epoch': 1.6}
{'loss': 0.8174, 'learning_rate': 6.0482559190312666e-06, 'epoch': 1.6}
{'loss': 1.0442, 'learning_rate': 6.0455449123441176e-06, 'epoch': 1.6}
{'loss': 0.7055, 'learning_rate': 6.042833905656968e-06, 'epoch': 1.6}
{'loss': 0.4862, 'learning_rate': 6.040122898969818e-06, 'epoch': 1.6}
{'loss': 1.451, 'learning_rate': 6.037411892282668e-06, 'epoch': 1.6}
{'loss': 0.3204, 'learning_rate': 6.034700885595518e-06, 'epoch': 1.6}
{'loss': 1.0529, 'learning_rate': 6.031989878908368e-06, 'epoch': 1.6}
{'loss': 0.8512, 'learning_rate': 6.029278872221218e-06, 'epoch': 1.6}
{'loss': 0.7907, 'learning_rate': 6.0265678655340685e-06, 'epoch': 1.6}
{'loss': 0.6741, 'learning_rate': 6.023856858846919e-06, 'epoch': 1.6}
{'loss': 0.4705, 'learning_rate': 6.021145852159769e-06, 'epoch': 1.6}
{'loss': 0.7518, 'learning_rate': 6.018434845472619e-06, 'epoch': 1.6}
{'loss': 1.0986, 'learning_rate': 6.015723838785469e-06, 'epoch': 1.6}
{'loss': 0.6649, 'learning_rate': 6.01301283209832e-06, 'epoch': 1.6}
{'loss': 0.7486, 'learning_rate': 6.010301825411169e-06, 'epoch': 1.6}
{'loss': 0.5806, 'learning_rate': 6.00759081872402e-06, 'epoch': 1.6}
{'loss': 1.1544, 'learning_rate': 6.0048798120368696e-06, 'epoch': 1.6}
{'loss': 0.9651, 'learning_rate': 6.0021688053497206e-06, 'epoch': 1.6}
{'loss': 0.6697, 'learning_rate': 5.99945779866257e-06, 'epoch': 1.6}
{'loss': 1.5782, 'learning_rate': 5.996746791975421e-06, 'epoch': 1.6}
{'loss': 1.5109, 'learning_rate': 5.99403578528827e-06, 'epoch': 1.6}
{'loss': 0.7533, 'learning_rate': 5.991324778601121e-06, 'epoch': 1.6}
{'loss': 0.629, 'learning_rate': 5.988613771913971e-06, 'epoch': 1.6}
{'loss': 0.632, 'learning_rate': 5.985902765226821e-06, 'epoch': 1.6}
{'loss': 0.3751, 'learning_rate': 5.9831917585396715e-06, 'epoch': 1.6}
{'loss': 0.4738, 'learning_rate': 5.980480751852522e-06, 'epoch': 1.6}
{'loss': 0.631, 'learning_rate': 5.977769745165372e-06, 'epoch': 1.6}
{'loss': 1.4597, 'learning_rate': 5.975058738478222e-06, 'epoch': 1.6}
{'loss': 0.4903, 'learning_rate': 5.972347731791072e-06, 'epoch': 1.6}
{'loss': 1.0206, 'learning_rate': 5.969636725103922e-06, 'epoch': 1.6}
{'loss': 0.9624, 'learning_rate': 5.966925718416772e-06, 'epoch': 1.6}
{'loss': 0.9267, 'learning_rate': 5.9642147117296224e-06, 'epoch': 1.6}
{'loss': 0.3251, 'learning_rate': 5.9615037050424726e-06, 'epoch': 1.6}
{'loss': 0.654, 'learning_rate': 5.9587926983553235e-06, 'epoch': 1.6}
{'loss': 0.5509, 'learning_rate': 5.956081691668173e-06, 'epoch': 1.6}
{'loss': 1.1019, 'learning_rate': 5.953370684981024e-06, 'epoch': 1.6}
{'loss': 0.9747, 'learning_rate': 5.950659678293873e-06, 'epoch': 1.6}
{'loss': 0.527, 'learning_rate': 5.947948671606724e-06, 'epoch': 1.6}
{'loss': 0.7298, 'learning_rate': 5.945237664919573e-06, 'epoch': 1.6}
{'loss': 0.7865, 'learning_rate': 5.942526658232424e-06, 'epoch': 1.6}
{'loss': 0.8983, 'learning_rate': 5.939815651545274e-06, 'epoch': 1.6}
{'loss': 0.9977, 'learning_rate': 5.937104644858125e-06, 'epoch': 1.6}
{'loss': 0.7884, 'learning_rate': 5.934393638170974e-06, 'epoch': 1.6}
{'loss': 1.0159, 'learning_rate': 5.931682631483825e-06, 'epoch': 1.6}
{'loss': 0.8029, 'learning_rate': 5.928971624796675e-06, 'epoch': 1.6}
{'loss': 0.6148, 'learning_rate': 5.926260618109524e-06, 'epoch': 1.6}
{'loss': 0.4329, 'learning_rate': 5.923549611422375e-06, 'epoch': 1.61}
{'loss': 0.2583, 'learning_rate': 5.920838604735225e-06, 'epoch': 1.61}
{'loss': 0.4888, 'learning_rate': 5.9181275980480756e-06, 'epoch': 1.61}
{'loss': 1.0132, 'learning_rate': 5.915416591360925e-06, 'epoch': 1.61}
{'loss': 0.6623, 'learning_rate': 5.912705584673776e-06, 'epoch': 1.61}
{'loss': 0.2688, 'learning_rate': 5.909994577986625e-06, 'epoch': 1.61}
{'loss': 0.6678, 'learning_rate': 5.907283571299476e-06, 'epoch': 1.61}
{'loss': 0.7663, 'learning_rate': 5.904572564612325e-06, 'epoch': 1.61}
{'loss': 1.2094, 'learning_rate': 5.901861557925176e-06, 'epoch': 1.61}
{'loss': 0.6238, 'learning_rate': 5.8991505512380265e-06, 'epoch': 1.61}
{'loss': 0.9928, 'learning_rate': 5.896439544550877e-06, 'epoch': 1.61}
{'loss': 0.8429, 'learning_rate': 5.893728537863727e-06, 'epoch': 1.61}
{'loss': 0.9018, 'learning_rate': 5.891017531176577e-06, 'epoch': 1.61}
{'loss': 0.3631, 'learning_rate': 5.888306524489427e-06, 'epoch': 1.61}
{'loss': 0.7923, 'learning_rate': 5.885595517802277e-06, 'epoch': 1.61}
{'loss': 0.8326, 'learning_rate': 5.882884511115127e-06, 'epoch': 1.61}
{'loss': 0.3312, 'learning_rate': 5.8801735044279774e-06, 'epoch': 1.61}
{'loss': 0.809, 'learning_rate': 5.877462497740828e-06, 'epoch': 1.61}
{'loss': 1.03, 'learning_rate': 5.8747514910536786e-06, 'epoch': 1.61}
{'loss': 0.468, 'learning_rate': 5.872040484366528e-06, 'epoch': 1.61}
{'loss': 0.6469, 'learning_rate': 5.869329477679379e-06, 'epoch': 1.61}

 80%|████████  | 8902/11066 [32:36<08:01,  4.50it/s]
 80%|████████  | 8903/11066 [32:37<07:57,  4.53it/s]
                                                    

 80%|████████  | 8903/11066 [32:37<07:57,  4.53it/s]
 80%|████████  | 8904/11066 [32:37<07:52,  4.58it/s]
                                                    

 80%|████████  | 8904/11066 [32:37<07:52,  4.58it/s]
 80%|████████  | 8905/11066 [32:37<07:49,  4.61it/s]
                                                    

 80%|████████  | 8905/11066 [32:37<07:49,  4.61it/s]
 80%|████████  | 8906/11066 [32:37<07:49,  4.60it/s]
                                                    

 80%|████████  | 8906/11066 [32:37<07:49,  4.60it/s]
 80%|████████  | 8907/11066 [32:37<07:46,  4.63it/s]
                                                    

 80%|████████  | 8907/11066 [32:37<07:46,  4.63it/s]
 80%|████████  | 8908/11066 [32:38<07:41,  4.67it/s]
                                                    

 80%|████████  | 8908/11066 [32:38<07:41,  4.67it/s]
 81%|████████  | 8909/11066 [32:38<07:43,  4.65it/s]
                                                    

 81%|████████  | 8909/11066 [32:38<07:43,  4.65it/s]
 81%|████████  | 8910/11066 [32:38<07:44,  4.65it/s]
                                                    

 81%|████████  | 8910/11066 [32:38<07:44,  4.65it/s]
 81%|████████  | 8911/11066 [32:38<07:48,  4.60it/s]
                                                    

 81%|████████  | 8911/11066 [32:38<07:48,  4.60it/s]
 81%|████████  | 8912/11066 [32:39<07:53,  4.55it/s]
                                                    

 81%|████████  | 8912/11066 [32:39<07:53,  4.55it/s]
 81%|████████  | 8913/11066 [32:39<08:00,  4.48it/s]
                                                    

 81%|████████  | 8913/11066 [32:39<08:00,  4.48it/s]
 81%|████████  | 8914/11066 [32:39<07:59,  4.49it/s]
                                                    

 81%|████████  | 8914/11066 [32:39<07:59,  4.49it/s]
 81%|████████  | 8915/11066 [32:39<07:58,  4.49it/s]
                                                    

 81%|████████  | 8915/11066 [32:39<07:58,  4.49it/s]
 81%|████████  | 8916/11066 [32:39<07:58,  4.49it/s]
                                                    

 81%|████████  | 8916/11066 [32:39<07:58,  4.49it/s]
 81%|████████  | 8917/11066 [32:40<07:58,  4.49it/s]
                                                    

 81%|████████  | 8917/11066 [32:40<07:58,  4.49it/s]
 81%|████████  | 8918/11066 [32:40<07:57,  4.50it/s]
                                                    

 81%|████████  | 8918/11066 [32:40<07:57,  4.50it/s]
 81%|████████  | 8919/11066 [32:40<07:56,  4.50it/s]
                                                    

 81%|████████  | 8919/11066 [32:40<07:56,  4.50it/s]
 81%|████████  | 8920/11066 [32:40<07:52,  4.54it/s]
                                                    

 81%|████████  | 8920/11066 [32:40<07:52,  4.54it/s]
 81%|████████  | 8921/11066 [32:41<07:56,  4.51it/s]
                                                    

 81%|████████  | 8921/11066 [32:41<07:56,  4.51it/s]
 81%|████████  | 8922/11066 [32:41<07:56,  4.50it/s]
                                                    

 81%|████████  | 8922/11066 [32:41<07:56,  4.50it/s]
 81%|████████  | 8923/11066 [32:41<08:03,  4.43it/s]
                                                    

 81%|████████  | 8923/11066 [32:41<08:03,  4.43it/s]
 81%|████████  | 8924/11066 [32:41<08:01,  4.45it/s]
                                                    

 81%|████████  | 8924/11066 [32:41<08:01,  4.45it/s]
 81%|████████  | 8925/11066 [32:41<08:05,  4.41it/s]
                                                    

 81%|████████  | 8925/11066 [32:41<08:05,  4.41it/s]
 81%|████████  | 8926/11066 [32:42<08:02,  4.44it/s]
                                                    

 81%|████████  | 8926/11066 [32:42<08:02,  4.44it/s]
 81%|████████  | 8927/11066 [32:42<08:00,  4.45it/s]
                                                    

 81%|████████  | 8927/11066 [32:42<08:00,  4.45it/s]
 81%|████████  | 8928/11066 [32:42<07:54,  4.50it/s]
                                                    

 81%|████████  | 8928/11066 [32:42<07:54,  4.50it/s]
 81%|████████  | 8929/11066 [32:42<07:49,  4.55it/s]
                                                    

 81%|████████  | 8929/11066 [32:42<07:49,  4.55it/s]
 81%|████████  | 8930/11066 [32:43<07:48,  4.56it/s]
                                                    

 81%|████████  | 8930/11066 [32:43<07:48,  4.56it/s]
 81%|████████  | 8931/11066 [32:43<07:47,  4.57it/s]
                                                    

 81%|████████  | 8931/11066 [32:43<07:47,  4.57it/s]
 81%|████████  | 8932/11066 [32:43<07:49,  4.54it/s]
                                                    

 81%|████████  | 8932/11066 [32:43<07:49,  4.54it/s]
 81%|████████  | 8933/11066 [32:43<07:48,  4.55it/s]
                                                    

 81%|████████  | 8933/11066 [32:43<07:48,  4.55it/s]
 81%|████████  | 8934/11066 [32:43<07:50,  4.53it/s]
                                                    

 81%|████████  | 8934/11066 [32:43<07:50,  4.53it/s]
 81%|████████  | 8935/11066 [32:44<07:48,  4.55it/s]
                                                    

 81%|████████  | 8935/11066 [32:44<07:48,  4.55it/s]
 81%|████████  | 8936/11066 [32:44<07:41,  4.61it/s]
                                                    

 81%|████████  | 8936/11066 [32:44<07:41,  4.61it/s]
 81%|████████  | 8937/11066 [32:44<07:36,  4.66it/s]
                                                    

 81%|████████  | 8937/11066 [32:44<07:36,  4.66it/s]
 81%|████████  | 8938/11066 [32:44<07:35,  4.67it/s]
                                                    

 81%|████████  | 8938/11066 [32:44<07:35,  4.67it/s]
 81%|████████  | 8939/11066 [32:45<07:41,  4.61it/s]
                                                    

 81%|████████  | 8939/11066 [32:45<07:41,  4.61it/s]
 81%|████████  | 8940/11066 [32:45<07:44,  4.58it/s]
                                                    

 81%|████████  | 8940/11066 [32:45<07:44,  4.58it/s]
 81%|████████  | 8941/11066 [32:45<07:46,  4.56it/s]
                                                    

 81%|████████  | 8941/11066 [32:45<07:46,  4.56it/s]
 81%|████████  | 8942/11066 [32:45<07:48,  4.53it/s]
                                                    

 81%|████████  | 8942/11066 [32:45<07:48,  4.53it/s]
 81%|████████  | 8943/11066 [32:45<07:46,  4.55it/s]
                                                    

 81%|████████  | 8943/11066 [32:45<07:46,  4.55it/s]
 81%|████████  | 8944/11066 [32:46<07:45,  4.56it/s]
                                                    

 81%|████████  | 8944/11066 [32:46<07:45,  4.56it/s]
 81%|████████  | 8945/11066 [32:46<07:43,  4.58it/s]
                                                    

 81%|████████  | 8945/11066 [32:46<07:43,  4.58it/s]
 81%|████████  | 8946/11066 [32:46<07:49,  4.52it/s]
                                                    

 81%|████████  | 8946/11066 [32:46<07:49,  4.52it/s]
 81%|████████  | 8947/11066 [32:46<07:51,  4.50it/s]
                                                    

 81%|████████  | 8947/11066 [32:46<07:51,  4.50it/s]
 81%|████████  | 8948/11066 [32:47<07:49,  4.51it/s]
                                                    

 81%|████████  | 8948/11066 [32:47<07:49,  4.51it/s]
 81%|████████  | 8949/11066 [32:47<07:50,  4.50it/s]
                                                    

 81%|████████  | 8949/11066 [32:47<07:50,  4.50it/s]
 81%|████████  | 8950/11066 [32:47<07:51,  4.49it/s]
                                                    

 81%|████████  | 8950/11066 [32:47<07:51,  4.49it/s]
 81%|████████  | 8951/11066 [32:47<07:46,  4.53it/s]
                                                    

 81%|████████  | 8951/11066 [32:47<07:46,  4.53it/s]
 81%|████████  | 8952/11066 [32:47<07:40,  4.59it/s]
                                                    

 81%|████████  | 8952/11066 [32:47<07:40,  4.59it/s]
 81%|████████  | 8953/11066 [32:48<07:41,  4.58it/s]
                                                    

 81%|████████  | 8953/11066 [32:48<07:41,  4.58it/s]
 81%|████████  | 8954/11066 [32:48<07:37,  4.61it/s]
                                                    

 81%|████████  | 8954/11066 [32:48<07:37,  4.61it/s]
 81%|████████  | 8955/11066 [32:48<07:40,  4.58it/s]
                                                    

 81%|████████  | 8955/11066 [32:48<07:40,  4.58it/s]
 81%|████████  | 8956/11066 [32:48<07:36,  4.62it/s]
                                                    

 81%|████████  | 8956/11066 [32:48<07:36,  4.62it/s]
 81%|████████  | 8957/11066 [32:48<07:31,  4.67it/s]
                                                    

 81%|████████  | 8957/11066 [32:48<07:31,  4.67it/s]
 81%|████████  | 8958/11066 [32:49<07:37,  4.61it/s]
                                                    

 81%|████████  | 8958/11066 [32:49<07:37,  4.61it/s]
 81%|████████  | 8959/11066 [32:49<07:33,  4.64it/s]
                                                    

 81%|████████  | 8959/11066 [32:49<07:33,  4.64it/s]
 81%|████████  | 8960/11066 [32:49<07:37,  4.60it/s]
                                                    

 81%|████████  | 8960/11066 [32:49<07:37,  4.60it/s]
 81%|████████  | 8961/11066 [32:49<07:34,  4.63it/s]
                                                    

 81%|████████  | 8961/11066 [32:49<07:34,  4.63it/s]
 81%|████████  | 8962/11066 [32:50<07:36,  4.61it/s]
                                                    

 81%|████████  | 8962/11066 [32:50<07:36,  4.61it/s]
 81%|████████  | 8963/11066 [32:50<07:36,  4.60it/s]
                                                    

 81%|████████  | 8963/11066 [32:50<07:36,  4.60it/s]
 81%|████████  | 8964/11066 [32:50<07:34,  4.62it/s]
                                                    

 81%|████████  | 8964/11066 [32:50<07:34,  4.62it/s]
 81%|████████  | 8965/11066 [32:50<07:36,  4.61it/s]
                                                    

 81%|████████  | 8965/11066 [32:50<07:36,  4.61it/s]
 81%|████████  | 8966/11066 [32:50<07:40,  4.56it/s]
                                                    

 81%|████████  | 8966/11066 [32:50<07:40,  4.56it/s]
 81%|████████  | 8967/11066 [32:51<07:44,  4.52it/s]
                                                    

 81%|████████  | 8967/11066 [32:51<07:44,  4.52it/s]
 81%|████████  | 8968/11066 [32:51<07:38,  4.57it/s]
                                                    

 81%|████████  | 8968/11066 [32:51<07:38,  4.57it/s]
 81%|████████  | 8969/11066 [32:51<07:48,  4.47it/s]
                                                    

 81%|████████  | 8969/11066 [32:51<07:48,  4.47it/s]
 81%|████████  | 8970/11066 [32:51<07:43,  4.52it/s]
                                                    

 81%|████████  | 8970/11066 [32:51<07:43,  4.52it/s]
 81%|████████  | 8971/11066 [32:52<07:41,  4.54it/s]
                                                    

 81%|████████  | 8971/11066 [32:52<07:41,  4.54it/s]
 81%|████████  | 8972/11066 [32:52<07:40,  4.54it/s]
                                                    

 81%|████████  | 8972/11066 [32:52<07:40,  4.54it/s]
 81%|████████  | 8973/11066 [32:52<07:35,  4.60it/s]
                                                    

 81%|████████  | 8973/11066 [32:52<07:35,  4.60it/s]
 81%|████████  | 8974/11066 [32:52<07:34,  4.60it/s]
                                                    

 81%|████████  | 8974/11066 [32:52<07:34,  4.60it/s]
 81%|████████  | 8975/11066 [32:52<07:30,  4.64it/s]
                                                    

 81%|████████  | 8975/11066 [32:52<07:30,  4.64it/s]
 81%|████████  | 8976/11066 [32:53<07:28,  4.66it/s]
                                                    

 81%|████████  | 8976/11066 [32:53<07:28,  4.66it/s]
 81%|████████  | 8977/11066 [32:53<07:27,  4.67it/s]
                                                    

 81%|████████  | 8977/11066 [32:53<07:27,  4.67it/s]
 81%|████████  | 8978/11066 [32:53<07:29,  4.65it/s]
                                                    

 81%|████████  | 8978/11066 [32:53<07:29,  4.65it/s]
 81%|████████  | 8979/11066 [32:53<07:30,  4.63it/s]
                                                    

 81%|████████  | 8979/11066 [32:53<07:30,  4.63it/s]
 81%|████████  | 8980/11066 [32:53<07:36,  4.57it/s]
                                                    

 81%|████████  | 8980/11066 [32:53<07:36,  4.57it/s]
 81%|████████  | 8981/11066 [32:54<07:38,  4.55it/s]
                                                    

 81%|████████  | 8981/11066 [32:54<07:38,  4.55it/s]
 81%|████████  | 8982/11066 [32:54<07:40,  4.52it/s]
                                                    

 81%|████████  | 8982/11066 [32:54<07:40,  4.52it/s]
 81%|████████  | 8983/11066 [32:54<07:42,  4.50it/s]
                                                    

 81%|████████  | 8983/11066 [32:54<07:42,  4.50it/s]
 81%|████████  | 8984/11066 [32:54<07:44,  4.48it/s]
                                                    

 81%|████████  | 8984/11066 [32:54<07:44,  4.48it/s]
 81%|████████  | 8985/11066 [32:55<07:44,  4.48it/s]
                                                    

 81%|████████  | 8985/11066 [32:55<07:44,  4.48it/s]
 81%|████████  | 8986/11066 [32:55<07:43,  4.49it/s]
                                                    

 81%|████████  | 8986/11066 [32:55<07:43,  4.49it/s]
 81%|████████  | 8987/11066 [32:55<07:42,  4.49it/s]
                                                    

 81%|████████  | 8987/11066 [32:55<07:42,  4.49it/s]
 81%|████████  | 8988/11066 [32:55<07:41,  4.50it/s]
                                                    

 81%|████████  | 8988/11066 [32:55<07:41,  4.50it/s]
 81%|████████  | 8989/11066 [32:55<07:41,  4.50it/s]
                                                    

 81%|████████  | 8989/11066 [32:55<07:41,  4.50it/s]
 81%|████████  | 8990/11066 [32:56<07:37,  4.53it/s]
                                                    

 81%|████████  | 8990/11066 [32:56<07:37,  4.53it/s]
 81%|████████  | 8991/11066 [32:56<07:40,  4.50it/s]
                                                    

 81%|████████  | 8991/11066 [32:56<07:40,  4.50it/s]
 81%|████████▏ | 8992/11066 [32:56<07:37,  4.53it/s]
                                                    

 81%|████████▏ | 8992/11066 [32:56<07:37,  4.53it/s]
 81%|████████▏ | 8993/11066 [32:56<07:33,  4.57it/s]
                                                    

 81%|████████▏ | 8993/11066 [32:56<07:33,  4.57it/s]
 81%|████████▏ | 8994/11066 [32:57<07:37,  4.53it/s]
                                                    

 81%|████████▏ | 8994/11066 [32:57<07:37,  4.53it/s]
 81%|████████▏ | 8995/11066 [32:57<07:38,  4.51it/s]
                                                    

 81%|████████▏ | 8995/11066 [32:57<07:38,  4.51it/s]
 81%|████████▏ | 8996/11066 [32:57<07:39,  4.51it/s]
                                                    

 81%|████████▏ | 8996/11066 [32:57<07:39,  4.51it/s]
 81%|████████▏ | 8997/11066 [32:57<07:39,  4.50it/s]
                                                    

 81%|████████▏ | 8997/11066 [32:57<07:39,  4.50it/s]
 81%|████████▏ | 8998/11066 [32:57<07:39,  4.50it/s]
                                                    

 81%|████████▏ | 8998/11066 [32:57<07:39,  4.50it/s]
 81%|████████▏ | 8999/11066 [32:58<07:38,  4.50it/s]
                                                    

 81%|████████▏ | 8999/11066 [32:58<07:38,  4.50it/s]
 81%|████████▏ | 9000/11066 [32:58<07:38,  4.50it/s]
                                                    

 81%|████████▏ | 9000/11066 [32:58<07:38,  4.50it/s]
 81%|████████▏ | 9001/11066 [32:58<07:37,  4.51it/s]
                                                    

 81%|████████▏ | 9001/11066 [32:58<07:37,  4.51it/s]
 81%|████████▏ | 9002/11066 [32:58<07:38,  4.50it/s]
                                                    

 81%|████████▏ | 9002/11066 [32:58<07:38,  4.50it/s]
 81%|████████▏ | 9003/11066 [32:59<07:38,  4.50it/s]
                                                    

 81%|████████▏ | 9003/11066 [32:59<07:38,  4.50it/s]
 81%|████████▏ | 9004/11066 [32:59<07:37,  4.50it/s]
                                                    

 81%|████████▏ | 9004/11066 [32:59<07:37,  4.50it/s]
 81%|████████▏ | 9005/11066 [32:59<07:37,  4.50it/s]
                                                    

 81%|████████▏ | 9005/11066 [32:59<07:37,  4.50it/s]
 81%|████████▏ | 9006/11066 [32:59<07:37,  4.50it/s]
                                                    

 81%|████████▏ | 9006/11066 [32:59<07:37,  4.50it/s]
 81%|████████▏ | 9007/11066 [32:59<07:38,  4.49it/s]
                                                    

 81%|████████▏ | 9007/11066 [32:59<07:38,  4.49it/s]
 81%|████████▏ | 9008/11066 [33:00<07:38,  4.49it/s]
                                                    

 81%|████████▏ | 9008/11066 [33:00<07:38,  4.49it/s]
 81%|████████▏ | 9009/11066 [33:00<07:38,  4.49it/s]
                                                    

 81%|████████▏ | 9009/11066 [33:00<07:38,  4.49it/s]
 81%|████████▏ | 9010/11066 [33:00<07:39,  4.47it/s]
                                                    

 81%|████████▏ | 9010/11066 [33:00<07:39,  4.47it/s]
 81%|████████▏ | 9011/11066 [33:00<07:40,  4.47it/s]
                                                    

 81%|████████▏ | 9011/11066 [33:00<07:40,  4.47it/s]
 81%|████████▏ | 9012/11066 [33:01<07:39,  4.47it/s]
                                                    

 81%|████████▏ | 9012/11066 [33:01<07:39,  4.47it/s]
 81%|████████▏ | 9013/11066 [33:01<07:32,  4.54it/s]
                                                    

 81%|████████▏ | 9013/11066 [33:01<07:32,  4.54it/s]
 81%|████████▏ | 9014/11066 [33:01<07:33,  4.52it/s]
                                                    

 81%|████████▏ | 9014/11066 [33:01<07:33,  4.52it/s]
 81%|████████▏ | 9015/11066 [33:01<07:32,  4.53it/s]
                                                    
{'loss': 0.4146, 'learning_rate': 5.866618470992228e-06, 'epoch': 1.61}
{'loss': 0.9671, 'learning_rate': 5.863907464305079e-06, 'epoch': 1.61}
{'loss': 1.0443, 'learning_rate': 5.861196457617928e-06, 'epoch': 1.61}
{'loss': 0.6905, 'learning_rate': 5.858485450930779e-06, 'epoch': 1.61}
{'loss': 0.6864, 'learning_rate': 5.855774444243629e-06, 'epoch': 1.61}
{'loss': 0.6882, 'learning_rate': 5.85306343755648e-06, 'epoch': 1.61}
{'loss': 0.6852, 'learning_rate': 5.850352430869329e-06, 'epoch': 1.61}
{'loss': 0.4812, 'learning_rate': 5.84764142418218e-06, 'epoch': 1.61}
{'loss': 0.4285, 'learning_rate': 5.84493041749503e-06, 'epoch': 1.61}
{'loss': 0.4574, 'learning_rate': 5.84221941080788e-06, 'epoch': 1.61}
{'loss': 0.9009, 'learning_rate': 5.83950840412073e-06, 'epoch': 1.61}
{'loss': 0.909, 'learning_rate': 5.8367973974335804e-06, 'epoch': 1.61}
{'loss': 1.2897, 'learning_rate': 5.8340863907464306e-06, 'epoch': 1.61}
{'loss': 0.495, 'learning_rate': 5.831375384059281e-06, 'epoch': 1.61}
{'loss': 0.5055, 'learning_rate': 5.828664377372131e-06, 'epoch': 1.61}
{'loss': 0.6995, 'learning_rate': 5.825953370684981e-06, 'epoch': 1.61}
{'loss': 0.5062, 'learning_rate': 5.823242363997831e-06, 'epoch': 1.61}
{'loss': 0.5657, 'learning_rate': 5.820531357310681e-06, 'epoch': 1.61}
{'loss': 0.8868, 'learning_rate': 5.817820350623531e-06, 'epoch': 1.61}
{'loss': 1.5595, 'learning_rate': 5.815109343936382e-06, 'epoch': 1.61}
{'loss': 0.8119, 'learning_rate': 5.812398337249232e-06, 'epoch': 1.61}
{'loss': 0.5477, 'learning_rate': 5.809687330562083e-06, 'epoch': 1.61}
{'loss': 1.5898, 'learning_rate': 5.806976323874932e-06, 'epoch': 1.61}
{'loss': 0.6719, 'learning_rate': 5.804265317187783e-06, 'epoch': 1.61}
{'loss': 0.9601, 'learning_rate': 5.801554310500632e-06, 'epoch': 1.61}
{'loss': 0.4697, 'learning_rate': 5.798843303813483e-06, 'epoch': 1.61}
{'loss': 1.0032, 'learning_rate': 5.7961322971263325e-06, 'epoch': 1.61}
{'loss': 0.4334, 'learning_rate': 5.7934212904391834e-06, 'epoch': 1.61}
{'loss': 0.9229, 'learning_rate': 5.7907102837520336e-06, 'epoch': 1.61}
{'loss': 0.3579, 'learning_rate': 5.787999277064884e-06, 'epoch': 1.61}
{'loss': 1.1131, 'learning_rate': 5.785288270377734e-06, 'epoch': 1.61}
{'loss': 1.2466, 'learning_rate': 5.782577263690584e-06, 'epoch': 1.61}
{'loss': 0.8599, 'learning_rate': 5.779866257003434e-06, 'epoch': 1.61}
{'loss': 0.9328, 'learning_rate': 5.777155250316284e-06, 'epoch': 1.61}
{'loss': 0.3379, 'learning_rate': 5.774444243629134e-06, 'epoch': 1.62}
{'loss': 0.8112, 'learning_rate': 5.7717332369419845e-06, 'epoch': 1.62}
{'loss': 0.8241, 'learning_rate': 5.769022230254835e-06, 'epoch': 1.62}
{'loss': 0.9322, 'learning_rate': 5.766311223567685e-06, 'epoch': 1.62}
{'loss': 1.472, 'learning_rate': 5.763600216880535e-06, 'epoch': 1.62}
{'loss': 0.3924, 'learning_rate': 5.760889210193386e-06, 'epoch': 1.62}
{'loss': 1.0491, 'learning_rate': 5.758178203506235e-06, 'epoch': 1.62}
{'loss': 1.0881, 'learning_rate': 5.755467196819086e-06, 'epoch': 1.62}
{'loss': 0.4402, 'learning_rate': 5.7527561901319354e-06, 'epoch': 1.62}
{'loss': 0.8205, 'learning_rate': 5.7500451834447864e-06, 'epoch': 1.62}
{'loss': 0.6428, 'learning_rate': 5.747334176757636e-06, 'epoch': 1.62}
{'loss': 0.7527, 'learning_rate': 5.744623170070487e-06, 'epoch': 1.62}
{'loss': 0.577, 'learning_rate': 5.741912163383336e-06, 'epoch': 1.62}
{'loss': 1.0935, 'learning_rate': 5.739201156696187e-06, 'epoch': 1.62}
{'loss': 0.5463, 'learning_rate': 5.736490150009036e-06, 'epoch': 1.62}
{'loss': 0.6127, 'learning_rate': 5.733779143321887e-06, 'epoch': 1.62}
{'loss': 0.2697, 'learning_rate': 5.731068136634737e-06, 'epoch': 1.62}
{'loss': 0.9077, 'learning_rate': 5.7283571299475875e-06, 'epoch': 1.62}
{'loss': 0.7328, 'learning_rate': 5.725646123260438e-06, 'epoch': 1.62}
{'loss': 0.6086, 'learning_rate': 5.722935116573288e-06, 'epoch': 1.62}
{'loss': 0.4658, 'learning_rate': 5.720224109886138e-06, 'epoch': 1.62}
{'loss': 0.3283, 'learning_rate': 5.717513103198988e-06, 'epoch': 1.62}
{'loss': 0.9804, 'learning_rate': 5.714802096511838e-06, 'epoch': 1.62}
{'loss': 0.7795, 'learning_rate': 5.712091089824688e-06, 'epoch': 1.62}
{'loss': 1.1836, 'learning_rate': 5.7093800831375384e-06, 'epoch': 1.62}
{'loss': 0.3803, 'learning_rate': 5.706669076450389e-06, 'epoch': 1.62}
{'loss': 0.9068, 'learning_rate': 5.703958069763239e-06, 'epoch': 1.62}
{'loss': 0.524, 'learning_rate': 5.70124706307609e-06, 'epoch': 1.62}
{'loss': 1.0942, 'learning_rate': 5.698536056388939e-06, 'epoch': 1.62}
{'loss': 1.4476, 'learning_rate': 5.69582504970179e-06, 'epoch': 1.62}
{'loss': 0.6086, 'learning_rate': 5.693114043014639e-06, 'epoch': 1.62}
{'loss': 0.8255, 'learning_rate': 5.69040303632749e-06, 'epoch': 1.62}
{'loss': 0.3942, 'learning_rate': 5.6876920296403395e-06, 'epoch': 1.62}
{'loss': 0.7527, 'learning_rate': 5.6849810229531905e-06, 'epoch': 1.62}
{'loss': 0.4681, 'learning_rate': 5.68227001626604e-06, 'epoch': 1.62}
{'loss': 0.3638, 'learning_rate': 5.679559009578891e-06, 'epoch': 1.62}
{'loss': 0.8736, 'learning_rate': 5.676848002891741e-06, 'epoch': 1.62}
{'loss': 0.532, 'learning_rate': 5.674136996204591e-06, 'epoch': 1.62}
{'loss': 0.7048, 'learning_rate': 5.671425989517441e-06, 'epoch': 1.62}
{'loss': 0.7523, 'learning_rate': 5.668714982830291e-06, 'epoch': 1.62}
{'loss': 1.3392, 'learning_rate': 5.6660039761431414e-06, 'epoch': 1.62}
{'loss': 0.8277, 'learning_rate': 5.6632929694559916e-06, 'epoch': 1.62}
{'loss': 0.5555, 'learning_rate': 5.660581962768842e-06, 'epoch': 1.62}
{'loss': 0.3566, 'learning_rate': 5.657870956081692e-06, 'epoch': 1.62}
{'loss': 0.2832, 'learning_rate': 5.655159949394542e-06, 'epoch': 1.62}
{'loss': 0.9535, 'learning_rate': 5.652448942707392e-06, 'epoch': 1.62}
{'loss': 0.7351, 'learning_rate': 5.649737936020242e-06, 'epoch': 1.62}
{'loss': 0.4079, 'learning_rate': 5.647026929333093e-06, 'epoch': 1.62}
{'loss': 0.6665, 'learning_rate': 5.6443159226459425e-06, 'epoch': 1.62}
{'loss': 0.8965, 'learning_rate': 5.6416049159587935e-06, 'epoch': 1.62}
{'loss': 0.415, 'learning_rate': 5.638893909271643e-06, 'epoch': 1.62}
{'loss': 0.523, 'learning_rate': 5.636182902584494e-06, 'epoch': 1.62}
{'loss': 1.0581, 'learning_rate': 5.633471895897343e-06, 'epoch': 1.62}
{'loss': 0.3374, 'learning_rate': 5.630760889210194e-06, 'epoch': 1.62}
{'loss': 0.9544, 'learning_rate': 5.628049882523043e-06, 'epoch': 1.62}
{'loss': 0.4447, 'learning_rate': 5.625338875835894e-06, 'epoch': 1.62}
{'loss': 0.5051, 'learning_rate': 5.622627869148744e-06, 'epoch': 1.63}
{'loss': 0.785, 'learning_rate': 5.6199168624615946e-06, 'epoch': 1.63}
{'loss': 0.8372, 'learning_rate': 5.617205855774445e-06, 'epoch': 1.63}
{'loss': 0.4577, 'learning_rate': 5.614494849087295e-06, 'epoch': 1.63}
{'loss': 0.5649, 'learning_rate': 5.611783842400145e-06, 'epoch': 1.63}
{'loss': 0.8379, 'learning_rate': 5.609072835712995e-06, 'epoch': 1.63}
{'loss': 0.5767, 'learning_rate': 5.606361829025845e-06, 'epoch': 1.63}
{'loss': 0.9685, 'learning_rate': 5.603650822338695e-06, 'epoch': 1.63}
{'loss': 0.1959, 'learning_rate': 5.6009398156515455e-06, 'epoch': 1.63}
{'loss': 0.3945, 'learning_rate': 5.598228808964396e-06, 'epoch': 1.63}
{'loss': 1.0678, 'learning_rate': 5.595517802277246e-06, 'epoch': 1.63}
{'loss': 0.9341, 'learning_rate': 5.592806795590096e-06, 'epoch': 1.63}
{'loss': 0.9933, 'learning_rate': 5.590095788902946e-06, 'epoch': 1.63}
{'loss': 0.288, 'learning_rate': 5.587384782215797e-06, 'epoch': 1.63}
{'loss': 0.7586, 'learning_rate': 5.584673775528646e-06, 'epoch': 1.63}
{'loss': 0.5916, 'learning_rate': 5.581962768841497e-06, 'epoch': 1.63}
{'loss': 0.3848, 'learning_rate': 5.579251762154347e-06, 'epoch': 1.63}
{'loss': 0.5213, 'learning_rate': 5.576540755467197e-06, 'epoch': 1.63}
{'loss': 0.676, 'learning_rate': 5.573829748780047e-06, 'epoch': 1.63}
{'loss': 0.2758, 'learning_rate': 5.571118742092897e-06, 'epoch': 1.63}
{'loss': 0.4299, 'learning_rate': 5.568407735405747e-06, 'epoch': 1.63}
{'loss': 0.5613, 'learning_rate': 5.565696728718597e-06, 'epoch': 1.63}
{'loss': 0.5301, 'learning_rate': 5.562985722031448e-06, 'epoch': 1.63}

 81%|████████▏ | 9015/11066 [33:01<07:32,  4.53it/s]
 81%|████████▏ | 9016/11066 [33:01<07:33,  4.52it/s]
                                                    

 81%|████████▏ | 9016/11066 [33:01<07:33,  4.52it/s]
 81%|████████▏ | 9017/11066 [33:02<07:33,  4.52it/s]
                                                    

 81%|████████▏ | 9017/11066 [33:02<07:33,  4.52it/s]
 81%|████████▏ | 9018/11066 [33:02<07:33,  4.51it/s]
                                                    

 81%|████████▏ | 9018/11066 [33:02<07:33,  4.51it/s]
 82%|████████▏ | 9019/11066 [33:02<07:30,  4.54it/s]
                                                    

 82%|████████▏ | 9019/11066 [33:02<07:30,  4.54it/s]
 82%|████████▏ | 9020/11066 [33:02<07:32,  4.52it/s]
                                                    

 82%|████████▏ | 9020/11066 [33:02<07:32,  4.52it/s]
 82%|████████▏ | 9021/11066 [33:03<07:35,  4.49it/s]
                                                    

 82%|████████▏ | 9021/11066 [33:03<07:35,  4.49it/s]
 82%|████████▏ | 9022/11066 [33:03<07:35,  4.49it/s]
                                                    

 82%|████████▏ | 9022/11066 [33:03<07:35,  4.49it/s]
 82%|████████▏ | 9023/11066 [33:03<07:34,  4.49it/s]
                                                    

 82%|████████▏ | 9023/11066 [33:03<07:34,  4.49it/s]
 82%|████████▏ | 9024/11066 [33:03<07:34,  4.50it/s]
                                                    

 82%|████████▏ | 9024/11066 [33:03<07:34,  4.50it/s]
 82%|████████▏ | 9025/11066 [33:03<07:33,  4.50it/s]
                                                    

 82%|████████▏ | 9025/11066 [33:03<07:33,  4.50it/s]
 82%|████████▏ | 9026/11066 [33:04<07:33,  4.50it/s]
                                                    

 82%|████████▏ | 9026/11066 [33:04<07:33,  4.50it/s]
 82%|████████▏ | 9027/11066 [33:04<07:32,  4.50it/s]
                                                    

 82%|████████▏ | 9027/11066 [33:04<07:32,  4.50it/s]
 82%|████████▏ | 9028/11066 [33:04<07:32,  4.51it/s]
                                                    

 82%|████████▏ | 9028/11066 [33:04<07:32,  4.51it/s]
 82%|████████▏ | 9029/11066 [33:04<07:28,  4.54it/s]
                                                    

 82%|████████▏ | 9029/11066 [33:04<07:28,  4.54it/s]
 82%|████████▏ | 9030/11066 [33:05<07:31,  4.51it/s]
                                                    

 82%|████████▏ | 9030/11066 [33:05<07:31,  4.51it/s]
 82%|████████▏ | 9031/11066 [33:05<07:32,  4.50it/s]
                                                    

 82%|████████▏ | 9031/11066 [33:05<07:32,  4.50it/s]
 82%|████████▏ | 9032/11066 [33:05<07:32,  4.50it/s]
                                                    

 82%|████████▏ | 9032/11066 [33:05<07:32,  4.50it/s]
 82%|████████▏ | 9033/11066 [33:05<07:32,  4.50it/s]
                                                    

 82%|████████▏ | 9033/11066 [33:05<07:32,  4.50it/s]
 82%|████████▏ | 9034/11066 [33:05<07:32,  4.49it/s]
                                                    

 82%|████████▏ | 9034/11066 [33:05<07:32,  4.49it/s]
 82%|████████▏ | 9035/11066 [33:06<07:32,  4.49it/s]
                                                    

 82%|████████▏ | 9035/11066 [33:06<07:32,  4.49it/s]
 82%|████████▏ | 9036/11066 [33:06<07:25,  4.55it/s]
                                                    

 82%|████████▏ | 9036/11066 [33:06<07:25,  4.55it/s]
 82%|████████▏ | 9037/11066 [33:06<07:26,  4.54it/s]
                                                    

 82%|████████▏ | 9037/11066 [33:06<07:26,  4.54it/s]
 82%|████████▏ | 9038/11066 [33:06<07:21,  4.59it/s]
                                                    

 82%|████████▏ | 9038/11066 [33:06<07:21,  4.59it/s]
 82%|████████▏ | 9039/11066 [33:07<07:23,  4.57it/s]
                                                    

 82%|████████▏ | 9039/11066 [33:07<07:23,  4.57it/s]
 82%|████████▏ | 9040/11066 [33:07<07:25,  4.55it/s]
                                                    

 82%|████████▏ | 9040/11066 [33:07<07:25,  4.55it/s]
 82%|████████▏ | 9041/11066 [33:07<07:26,  4.53it/s]
                                                    

 82%|████████▏ | 9041/11066 [33:07<07:26,  4.53it/s]
 82%|████████▏ | 9042/11066 [33:07<07:20,  4.59it/s]
                                                    

 82%|████████▏ | 9042/11066 [33:07<07:20,  4.59it/s]
 82%|████████▏ | 9043/11066 [33:07<07:23,  4.57it/s]
                                                    

 82%|████████▏ | 9043/11066 [33:07<07:23,  4.57it/s]
 82%|████████▏ | 9044/11066 [33:08<07:25,  4.54it/s]
                                                    

 82%|████████▏ | 9044/11066 [33:08<07:25,  4.54it/s]
 82%|████████▏ | 9045/11066 [33:08<07:25,  4.53it/s]
                                                    

 82%|████████▏ | 9045/11066 [33:08<07:25,  4.53it/s]
 82%|████████▏ | 9046/11066 [33:08<07:22,  4.56it/s]
                                                    

 82%|████████▏ | 9046/11066 [33:08<07:22,  4.56it/s]
 82%|████████▏ | 9047/11066 [33:08<07:20,  4.58it/s]
                                                    

 82%|████████▏ | 9047/11066 [33:08<07:20,  4.58it/s]
 82%|████████▏ | 9048/11066 [33:09<07:23,  4.55it/s]
                                                    

 82%|████████▏ | 9048/11066 [33:09<07:23,  4.55it/s]
 82%|████████▏ | 9049/11066 [33:09<07:25,  4.53it/s]
                                                    

 82%|████████▏ | 9049/11066 [33:09<07:25,  4.53it/s]
 82%|████████▏ | 9050/11066 [33:09<07:20,  4.58it/s]
                                                    

 82%|████████▏ | 9050/11066 [33:09<07:20,  4.58it/s]
 82%|████████▏ | 9051/11066 [33:09<07:23,  4.55it/s]
                                                    

 82%|████████▏ | 9051/11066 [33:09<07:23,  4.55it/s]
 82%|████████▏ | 9052/11066 [33:09<07:26,  4.51it/s]
                                                    

 82%|████████▏ | 9052/11066 [33:09<07:26,  4.51it/s]
 82%|████████▏ | 9053/11066 [33:10<07:27,  4.50it/s]
                                                    

 82%|████████▏ | 9053/11066 [33:10<07:27,  4.50it/s]
 82%|████████▏ | 9054/11066 [33:10<07:27,  4.50it/s]
                                                    

 82%|████████▏ | 9054/11066 [33:10<07:27,  4.50it/s]
 82%|████████▏ | 9055/11066 [33:10<07:23,  4.53it/s]
                                                    

 82%|████████▏ | 9055/11066 [33:10<07:23,  4.53it/s]
 82%|████████▏ | 9056/11066 [33:10<07:22,  4.54it/s]
                                                    

 82%|████████▏ | 9056/11066 [33:10<07:22,  4.54it/s]
 82%|████████▏ | 9057/11066 [33:11<07:20,  4.56it/s]
                                                    

 82%|████████▏ | 9057/11066 [33:11<07:20,  4.56it/s]
 82%|████████▏ | 9058/11066 [33:11<07:23,  4.53it/s]
                                                    

 82%|████████▏ | 9058/11066 [33:11<07:23,  4.53it/s]
 82%|████████▏ | 9059/11066 [33:11<07:17,  4.58it/s]
                                                    

 82%|████████▏ | 9059/11066 [33:11<07:17,  4.58it/s]
 82%|████████▏ | 9060/11066 [33:11<07:20,  4.55it/s]
                                                    

 82%|████████▏ | 9060/11066 [33:11<07:20,  4.55it/s]
 82%|████████▏ | 9061/11066 [33:11<07:21,  4.54it/s]
                                                    

 82%|████████▏ | 9061/11066 [33:11<07:21,  4.54it/s]
 82%|████████▏ | 9062/11066 [33:12<07:18,  4.58it/s]
                                                    

 82%|████████▏ | 9062/11066 [33:12<07:18,  4.58it/s]
 82%|████████▏ | 9063/11066 [33:12<07:12,  4.63it/s]
                                                    

 82%|████████▏ | 9063/11066 [33:12<07:12,  4.63it/s]
 82%|████████▏ | 9064/11066 [33:12<07:10,  4.65it/s]
                                                    

 82%|████████▏ | 9064/11066 [33:12<07:10,  4.65it/s]
 82%|████████▏ | 9065/11066 [33:12<07:15,  4.59it/s]
                                                    

 82%|████████▏ | 9065/11066 [33:12<07:15,  4.59it/s]
 82%|████████▏ | 9066/11066 [33:12<07:16,  4.58it/s]
                                                    

 82%|████████▏ | 9066/11066 [33:12<07:16,  4.58it/s]
 82%|████████▏ | 9067/11066 [33:13<07:13,  4.62it/s]
                                                    

 82%|████████▏ | 9067/11066 [33:13<07:13,  4.62it/s]
 82%|████████▏ | 9068/11066 [33:13<07:08,  4.66it/s]
                                                    

 82%|████████▏ | 9068/11066 [33:13<07:08,  4.66it/s]
 82%|████████▏ | 9069/11066 [33:13<07:09,  4.65it/s]
                                                    

 82%|████████▏ | 9069/11066 [33:13<07:09,  4.65it/s]
 82%|████████▏ | 9070/11066 [33:13<07:06,  4.68it/s]
                                                    

 82%|████████▏ | 9070/11066 [33:13<07:06,  4.68it/s]
 82%|████████▏ | 9071/11066 [33:14<07:06,  4.68it/s]
                                                    

 82%|████████▏ | 9071/11066 [33:14<07:06,  4.68it/s]
 82%|████████▏ | 9072/11066 [33:14<07:08,  4.65it/s]
                                                    

 82%|████████▏ | 9072/11066 [33:14<07:08,  4.65it/s]
 82%|████████▏ | 9073/11066 [33:14<07:09,  4.64it/s]
                                                    

 82%|████████▏ | 9073/11066 [33:14<07:09,  4.64it/s]
 82%|████████▏ | 9074/11066 [33:14<07:12,  4.61it/s]
                                                    

 82%|████████▏ | 9074/11066 [33:14<07:12,  4.61it/s]
 82%|████████▏ | 9075/11066 [33:14<07:15,  4.57it/s]
                                                    

 82%|████████▏ | 9075/11066 [33:14<07:15,  4.57it/s]
 82%|████████▏ | 9076/11066 [33:15<07:25,  4.46it/s]
                                                    

 82%|████████▏ | 9076/11066 [33:15<07:25,  4.46it/s]
 82%|████████▏ | 9077/11066 [33:15<07:26,  4.45it/s]
                                                    

 82%|████████▏ | 9077/11066 [33:15<07:26,  4.45it/s]
 82%|████████▏ | 9078/11066 [33:15<07:24,  4.47it/s]
                                                    

 82%|████████▏ | 9078/11066 [33:15<07:24,  4.47it/s]
 82%|████████▏ | 9079/11066 [33:15<07:23,  4.48it/s]
                                                    

 82%|████████▏ | 9079/11066 [33:15<07:23,  4.48it/s]
 82%|████████▏ | 9080/11066 [33:16<07:22,  4.49it/s]
                                                    

 82%|████████▏ | 9080/11066 [33:16<07:22,  4.49it/s]
 82%|████████▏ | 9081/11066 [33:16<07:22,  4.49it/s]
                                                    

 82%|████████▏ | 9081/11066 [33:16<07:22,  4.49it/s]
 82%|████████▏ | 9082/11066 [33:16<07:21,  4.49it/s]
                                                    

 82%|████████▏ | 9082/11066 [33:16<07:21,  4.49it/s]
 82%|████████▏ | 9083/11066 [33:16<07:21,  4.49it/s]
                                                    

 82%|████████▏ | 9083/11066 [33:16<07:21,  4.49it/s]
 82%|████████▏ | 9084/11066 [33:16<07:21,  4.49it/s]
                                                    

 82%|████████▏ | 9084/11066 [33:16<07:21,  4.49it/s]
 82%|████████▏ | 9085/11066 [33:17<07:20,  4.50it/s]
                                                    

 82%|████████▏ | 9085/11066 [33:17<07:20,  4.50it/s]
 82%|████████▏ | 9086/11066 [33:17<07:15,  4.54it/s]
                                                    

 82%|████████▏ | 9086/11066 [33:17<07:15,  4.54it/s]
 82%|████████▏ | 9087/11066 [33:17<07:17,  4.53it/s]
                                                    

 82%|████████▏ | 9087/11066 [33:17<07:17,  4.53it/s]
 82%|████████▏ | 9088/11066 [33:17<07:16,  4.53it/s]
                                                    

 82%|████████▏ | 9088/11066 [33:17<07:16,  4.53it/s]
 82%|████████▏ | 9089/11066 [33:18<07:13,  4.56it/s]
                                                    

 82%|████████▏ | 9089/11066 [33:18<07:13,  4.56it/s]
 82%|████████▏ | 9090/11066 [33:18<07:17,  4.52it/s]
                                                    

 82%|████████▏ | 9090/11066 [33:18<07:17,  4.52it/s]
 82%|████████▏ | 9091/11066 [33:18<07:14,  4.55it/s]
                                                    

 82%|████████▏ | 9091/11066 [33:18<07:14,  4.55it/s]
 82%|████████▏ | 9092/11066 [33:18<07:11,  4.58it/s]
                                                    

 82%|████████▏ | 9092/11066 [33:18<07:11,  4.58it/s]
 82%|████████▏ | 9093/11066 [33:18<07:14,  4.54it/s]
                                                    

 82%|████████▏ | 9093/11066 [33:18<07:14,  4.54it/s]
 82%|████████▏ | 9094/11066 [33:19<07:11,  4.56it/s]
                                                    

 82%|████████▏ | 9094/11066 [33:19<07:11,  4.56it/s]
 82%|████████▏ | 9095/11066 [33:19<07:14,  4.53it/s]
                                                    

 82%|████████▏ | 9095/11066 [33:19<07:14,  4.53it/s]
 82%|████████▏ | 9096/11066 [33:19<07:16,  4.51it/s]
                                                    

 82%|████████▏ | 9096/11066 [33:19<07:16,  4.51it/s]
 82%|████████▏ | 9097/11066 [33:19<07:17,  4.50it/s]
                                                    

 82%|████████▏ | 9097/11066 [33:19<07:17,  4.50it/s]
 82%|████████▏ | 9098/11066 [33:20<07:17,  4.50it/s]
                                                    

 82%|████████▏ | 9098/11066 [33:20<07:17,  4.50it/s]
 82%|████████▏ | 9099/11066 [33:20<07:16,  4.50it/s]
                                                    

 82%|████████▏ | 9099/11066 [33:20<07:16,  4.50it/s]
 82%|████████▏ | 9100/11066 [33:20<07:16,  4.50it/s]
                                                    

 82%|████████▏ | 9100/11066 [33:20<07:16,  4.50it/s]
 82%|████████▏ | 9101/11066 [33:20<07:13,  4.53it/s]
                                                    

 82%|████████▏ | 9101/11066 [33:20<07:13,  4.53it/s]
 82%|████████▏ | 9102/11066 [33:20<07:11,  4.55it/s]
                                                    

 82%|████████▏ | 9102/11066 [33:20<07:11,  4.55it/s]
 82%|████████▏ | 9103/11066 [33:21<07:08,  4.58it/s]
                                                    

 82%|████████▏ | 9103/11066 [33:21<07:08,  4.58it/s]
 82%|████████▏ | 9104/11066 [33:21<07:06,  4.60it/s]
                                                    

 82%|████████▏ | 9104/11066 [33:21<07:06,  4.60it/s]
 82%|████████▏ | 9105/11066 [33:21<07:06,  4.60it/s]
                                                    

 82%|████████▏ | 9105/11066 [33:21<07:06,  4.60it/s]
 82%|████████▏ | 9106/11066 [33:21<07:08,  4.58it/s]
                                                    

 82%|████████▏ | 9106/11066 [33:21<07:08,  4.58it/s]
 82%|████████▏ | 9107/11066 [33:22<07:08,  4.57it/s]
                                                    

 82%|████████▏ | 9107/11066 [33:22<07:08,  4.57it/s]
 82%|████████▏ | 9108/11066 [33:22<07:07,  4.58it/s]
                                                    

 82%|████████▏ | 9108/11066 [33:22<07:07,  4.58it/s]
 82%|████████▏ | 9109/11066 [33:22<07:03,  4.62it/s]
                                                    

 82%|████████▏ | 9109/11066 [33:22<07:03,  4.62it/s]
 82%|████████▏ | 9110/11066 [33:22<07:07,  4.58it/s]
                                                    

 82%|████████▏ | 9110/11066 [33:22<07:07,  4.58it/s]
 82%|████████▏ | 9111/11066 [33:22<07:06,  4.59it/s]
                                                    

 82%|████████▏ | 9111/11066 [33:22<07:06,  4.59it/s]
 82%|████████▏ | 9112/11066 [33:23<07:17,  4.47it/s]
                                                    

 82%|████████▏ | 9112/11066 [33:23<07:17,  4.47it/s]
 82%|████████▏ | 9113/11066 [33:23<07:16,  4.47it/s]
                                                    

 82%|████████▏ | 9113/11066 [33:23<07:16,  4.47it/s]
 82%|████████▏ | 9114/11066 [33:23<07:12,  4.51it/s]
                                                    

 82%|████████▏ | 9114/11066 [33:23<07:12,  4.51it/s]
 82%|████████▏ | 9115/11066 [33:23<07:10,  4.53it/s]
                                                    

 82%|████████▏ | 9115/11066 [33:23<07:10,  4.53it/s]
 82%|████████▏ | 9116/11066 [33:23<07:10,  4.52it/s]
                                                    

 82%|████████▏ | 9116/11066 [33:23<07:10,  4.52it/s]
 82%|████████▏ | 9117/11066 [33:24<07:12,  4.51it/s]
                                                    

 82%|████████▏ | 9117/11066 [33:24<07:12,  4.51it/s]
 82%|████████▏ | 9118/11066 [33:24<07:12,  4.50it/s]
                                                    

 82%|████████▏ | 9118/11066 [33:24<07:12,  4.50it/s]
 82%|████████▏ | 9119/11066 [33:24<07:09,  4.54it/s]
                                                    

 82%|████████▏ | 9119/11066 [33:24<07:09,  4.54it/s]
 82%|████████▏ | 9120/11066 [33:24<07:05,  4.57it/s]
                                                    

 82%|████████▏ | 9120/11066 [33:24<07:05,  4.57it/s]
 82%|████████▏ | 9121/11066 [33:25<07:07,  4.55it/s]
                                                    

 82%|████████▏ | 9121/11066 [33:25<07:07,  4.55it/s]
 82%|████████▏ | 9122/11066 [33:25<07:06,  4.56it/s]
                                                    

 82%|████████▏ | 9122/11066 [33:25<07:06,  4.56it/s]
 82%|████████▏ | 9123/11066 [33:25<07:02,  4.60it/s]
                                                    

 82%|████████▏ | 9123/11066 [33:25<07:02,  4.60it/s]
 82%|████████▏ | 9124/11066 [33:25<07:05,  4.57it/s]
                                                    

 82%|████████▏ | 9124/11066 [33:25<07:05,  4.57it/s]
 82%|████████▏ | 9125/11066 [33:25<07:07,  4.54it/s]
                                                    

 82%|████████▏ | 9125/11066 [33:25<07:07,  4.54it/s]
 82%|████████▏ | 9126/11066 [33:26<07:09,  4.52it/s]
                                                    

 82%|████████▏ | 9126/11066 [33:26<07:09,  4.52it/s]
 82%|████████▏ | 9127/11066 [33:26<07:09,  4.51it/s]
                                                    

 82%|████████▏ | 9127/11066 [33:26<07:09,  4.51it/s]
 82%|████████▏ | 9128/11066 [33:26<07:10,  4.50it/s]
                                                    
{'loss': 0.5746, 'learning_rate': 5.5602747153442975e-06, 'epoch': 1.63}
{'loss': 0.9516, 'learning_rate': 5.5575637086571485e-06, 'epoch': 1.63}
{'loss': 0.5654, 'learning_rate': 5.554852701969998e-06, 'epoch': 1.63}
{'loss': 0.8581, 'learning_rate': 5.552141695282849e-06, 'epoch': 1.63}
{'loss': 0.613, 'learning_rate': 5.549430688595698e-06, 'epoch': 1.63}
{'loss': 0.2718, 'learning_rate': 5.546719681908549e-06, 'epoch': 1.63}
{'loss': 0.6314, 'learning_rate': 5.544008675221398e-06, 'epoch': 1.63}
{'loss': 0.8215, 'learning_rate': 5.541297668534249e-06, 'epoch': 1.63}
{'loss': 0.526, 'learning_rate': 5.538586661847099e-06, 'epoch': 1.63}
{'loss': 0.5649, 'learning_rate': 5.53587565515995e-06, 'epoch': 1.63}
{'loss': 0.384, 'learning_rate': 5.5331646484728e-06, 'epoch': 1.63}
{'loss': 0.6154, 'learning_rate': 5.53045364178565e-06, 'epoch': 1.63}
{'loss': 0.5309, 'learning_rate': 5.5277426350985e-06, 'epoch': 1.63}
{'loss': 0.9858, 'learning_rate': 5.52503162841135e-06, 'epoch': 1.63}
{'loss': 0.5709, 'learning_rate': 5.5223206217242e-06, 'epoch': 1.63}
{'loss': 0.5436, 'learning_rate': 5.51960961503705e-06, 'epoch': 1.63}
{'loss': 0.6554, 'learning_rate': 5.5168986083499005e-06, 'epoch': 1.63}
{'loss': 0.9473, 'learning_rate': 5.514187601662751e-06, 'epoch': 1.63}
{'loss': 1.3622, 'learning_rate': 5.511476594975601e-06, 'epoch': 1.63}
{'loss': 0.5045, 'learning_rate': 5.508765588288451e-06, 'epoch': 1.63}
{'loss': 0.7349, 'learning_rate': 5.506054581601301e-06, 'epoch': 1.63}
{'loss': 0.5615, 'learning_rate': 5.503343574914152e-06, 'epoch': 1.63}
{'loss': 0.5963, 'learning_rate': 5.500632568227001e-06, 'epoch': 1.63}
{'loss': 0.8136, 'learning_rate': 5.497921561539852e-06, 'epoch': 1.63}
{'loss': 1.2939, 'learning_rate': 5.495210554852702e-06, 'epoch': 1.63}
{'loss': 0.657, 'learning_rate': 5.4924995481655526e-06, 'epoch': 1.63}
{'loss': 0.5236, 'learning_rate': 5.489788541478402e-06, 'epoch': 1.63}
{'loss': 0.7494, 'learning_rate': 5.487077534791253e-06, 'epoch': 1.63}
{'loss': 0.7784, 'learning_rate': 5.484366528104102e-06, 'epoch': 1.63}
{'loss': 0.4958, 'learning_rate': 5.481655521416953e-06, 'epoch': 1.63}
{'loss': 0.3821, 'learning_rate': 5.478944514729803e-06, 'epoch': 1.63}
{'loss': 0.7203, 'learning_rate': 5.476233508042653e-06, 'epoch': 1.63}
{'loss': 0.8321, 'learning_rate': 5.4735225013555035e-06, 'epoch': 1.64}
{'loss': 1.0463, 'learning_rate': 5.470811494668354e-06, 'epoch': 1.64}
{'loss': 0.5348, 'learning_rate': 5.468100487981204e-06, 'epoch': 1.64}
{'loss': 0.575, 'learning_rate': 5.465389481294054e-06, 'epoch': 1.64}
{'loss': 1.0249, 'learning_rate': 5.462678474606904e-06, 'epoch': 1.64}
{'loss': 0.9024, 'learning_rate': 5.459967467919754e-06, 'epoch': 1.64}
{'loss': 1.1388, 'learning_rate': 5.457256461232604e-06, 'epoch': 1.64}
{'loss': 0.3164, 'learning_rate': 5.4545454545454545e-06, 'epoch': 1.64}
{'loss': 0.4322, 'learning_rate': 5.451834447858305e-06, 'epoch': 1.64}
{'loss': 0.5523, 'learning_rate': 5.4491234411711556e-06, 'epoch': 1.64}
{'loss': 0.5881, 'learning_rate': 5.446412434484005e-06, 'epoch': 1.64}
{'loss': 0.7437, 'learning_rate': 5.443701427796856e-06, 'epoch': 1.64}
{'loss': 0.6966, 'learning_rate': 5.440990421109705e-06, 'epoch': 1.64}
{'loss': 0.9957, 'learning_rate': 5.438279414422556e-06, 'epoch': 1.64}
{'loss': 0.7646, 'learning_rate': 5.435568407735405e-06, 'epoch': 1.64}
{'loss': 0.8973, 'learning_rate': 5.432857401048256e-06, 'epoch': 1.64}
{'loss': 1.2159, 'learning_rate': 5.430146394361106e-06, 'epoch': 1.64}
{'loss': 0.4425, 'learning_rate': 5.427435387673957e-06, 'epoch': 1.64}
{'loss': 0.6749, 'learning_rate': 5.424724380986806e-06, 'epoch': 1.64}
{'loss': 0.9409, 'learning_rate': 5.422013374299657e-06, 'epoch': 1.64}
{'loss': 0.4682, 'learning_rate': 5.419302367612507e-06, 'epoch': 1.64}
{'loss': 0.8415, 'learning_rate': 5.416591360925357e-06, 'epoch': 1.64}
{'loss': 0.9882, 'learning_rate': 5.413880354238207e-06, 'epoch': 1.64}
{'loss': 0.6476, 'learning_rate': 5.4111693475510574e-06, 'epoch': 1.64}
{'loss': 0.5787, 'learning_rate': 5.408458340863908e-06, 'epoch': 1.64}
{'loss': 0.516, 'learning_rate': 5.405747334176758e-06, 'epoch': 1.64}
{'loss': 0.3166, 'learning_rate': 5.403036327489608e-06, 'epoch': 1.64}
{'loss': 0.5086, 'learning_rate': 5.400325320802458e-06, 'epoch': 1.64}
{'loss': 0.6484, 'learning_rate': 5.397614314115308e-06, 'epoch': 1.64}
{'loss': 0.8418, 'learning_rate': 5.394903307428159e-06, 'epoch': 1.64}
{'loss': 0.3318, 'learning_rate': 5.392192300741008e-06, 'epoch': 1.64}
{'loss': 0.5553, 'learning_rate': 5.389481294053859e-06, 'epoch': 1.64}
{'loss': 0.6631, 'learning_rate': 5.386770287366709e-06, 'epoch': 1.64}
{'loss': 0.4087, 'learning_rate': 5.38405928067956e-06, 'epoch': 1.64}
{'loss': 0.437, 'learning_rate': 5.381348273992409e-06, 'epoch': 1.64}
{'loss': 0.1442, 'learning_rate': 5.37863726730526e-06, 'epoch': 1.64}
{'loss': 0.3968, 'learning_rate': 5.375926260618109e-06, 'epoch': 1.64}
{'loss': 1.3358, 'learning_rate': 5.37321525393096e-06, 'epoch': 1.64}
{'loss': 0.8383, 'learning_rate': 5.3705042472438095e-06, 'epoch': 1.64}
{'loss': 1.0276, 'learning_rate': 5.3677932405566604e-06, 'epoch': 1.64}
{'loss': 0.5964, 'learning_rate': 5.365082233869511e-06, 'epoch': 1.64}
{'loss': 0.5379, 'learning_rate': 5.362371227182361e-06, 'epoch': 1.64}
{'loss': 0.5839, 'learning_rate': 5.359660220495211e-06, 'epoch': 1.64}
{'loss': 0.3382, 'learning_rate': 5.356949213808061e-06, 'epoch': 1.64}
{'loss': 0.5306, 'learning_rate': 5.354238207120911e-06, 'epoch': 1.64}
{'loss': 0.4372, 'learning_rate': 5.351527200433761e-06, 'epoch': 1.64}
{'loss': 0.9238, 'learning_rate': 5.348816193746611e-06, 'epoch': 1.64}
{'loss': 0.6682, 'learning_rate': 5.3461051870594615e-06, 'epoch': 1.64}
{'loss': 0.5171, 'learning_rate': 5.343394180372312e-06, 'epoch': 1.64}
{'loss': 0.7511, 'learning_rate': 5.340683173685162e-06, 'epoch': 1.64}
{'loss': 0.4449, 'learning_rate': 5.337972166998012e-06, 'epoch': 1.64}
{'loss': 0.5947, 'learning_rate': 5.335261160310863e-06, 'epoch': 1.64}
{'loss': 0.5406, 'learning_rate': 5.332550153623712e-06, 'epoch': 1.64}
{'loss': 1.1446, 'learning_rate': 5.329839146936563e-06, 'epoch': 1.64}
{'loss': 0.818, 'learning_rate': 5.3271281402494125e-06, 'epoch': 1.64}
{'loss': 0.6685, 'learning_rate': 5.3244171335622634e-06, 'epoch': 1.65}
{'loss': 0.7771, 'learning_rate': 5.321706126875113e-06, 'epoch': 1.65}
{'loss': 0.5684, 'learning_rate': 5.318995120187964e-06, 'epoch': 1.65}
{'loss': 0.8451, 'learning_rate': 5.316284113500813e-06, 'epoch': 1.65}
{'loss': 0.9076, 'learning_rate': 5.313573106813664e-06, 'epoch': 1.65}
{'loss': 0.4679, 'learning_rate': 5.310862100126513e-06, 'epoch': 1.65}
{'loss': 0.964, 'learning_rate': 5.308151093439364e-06, 'epoch': 1.65}
{'loss': 0.9337, 'learning_rate': 5.305440086752214e-06, 'epoch': 1.65}
{'loss': 0.4526, 'learning_rate': 5.3027290800650645e-06, 'epoch': 1.65}
{'loss': 0.7673, 'learning_rate': 5.300018073377915e-06, 'epoch': 1.65}
{'loss': 0.7421, 'learning_rate': 5.297307066690765e-06, 'epoch': 1.65}
{'loss': 0.6718, 'learning_rate': 5.294596060003615e-06, 'epoch': 1.65}
{'loss': 1.5562, 'learning_rate': 5.291885053316465e-06, 'epoch': 1.65}
{'loss': 0.5488, 'learning_rate': 5.289174046629315e-06, 'epoch': 1.65}
{'loss': 0.3437, 'learning_rate': 5.286463039942165e-06, 'epoch': 1.65}
{'loss': 0.8671, 'learning_rate': 5.2837520332550155e-06, 'epoch': 1.65}
{'loss': 0.6606, 'learning_rate': 5.2810410265678664e-06, 'epoch': 1.65}
{'loss': 0.6802, 'learning_rate': 5.278330019880716e-06, 'epoch': 1.65}
{'loss': 1.1018, 'learning_rate': 5.275619013193567e-06, 'epoch': 1.65}
{'loss': 1.1308, 'learning_rate': 5.272908006506416e-06, 'epoch': 1.65}
{'loss': 0.6085, 'learning_rate': 5.270196999819267e-06, 'epoch': 1.65}
{'loss': 0.9535, 'learning_rate': 5.267485993132116e-06, 'epoch': 1.65}
{'loss': 1.3685, 'learning_rate': 5.264774986444967e-06, 'epoch': 1.65}
{'loss': 0.7666, 'learning_rate': 5.2620639797578165e-06, 'epoch': 1.65}
{'loss': 0.3552, 'learning_rate': 5.2593529730706675e-06, 'epoch': 1.65}
{'loss': 1.4132, 'learning_rate': 5.256641966383517e-06, 'epoch': 1.65}

 82%|████████▏ | 9128/11066 [33:26<07:10,  4.50it/s]
 82%|████████▏ | 9129/11066 [33:26<07:06,  4.54it/s]
                                                    

 82%|████████▏ | 9129/11066 [33:26<07:06,  4.54it/s]
 83%|████████▎ | 9130/11066 [33:27<07:03,  4.58it/s]
                                                    

 83%|████████▎ | 9130/11066 [33:27<07:03,  4.58it/s]
 83%|████████▎ | 9131/11066 [33:27<07:06,  4.54it/s]
                                                    

 83%|████████▎ | 9131/11066 [33:27<07:06,  4.54it/s]
 83%|████████▎ | 9132/11066 [33:27<07:08,  4.52it/s]
                                                    

 83%|████████▎ | 9132/11066 [33:27<07:08,  4.52it/s]
 83%|████████▎ | 9133/11066 [33:27<07:05,  4.55it/s]
                                                    

 83%|████████▎ | 9133/11066 [33:27<07:05,  4.55it/s]
 83%|████████▎ | 9134/11066 [33:27<07:06,  4.53it/s]
                                                    

 83%|████████▎ | 9134/11066 [33:27<07:06,  4.53it/s]
 83%|████████▎ | 9135/11066 [33:28<07:04,  4.55it/s]
                                                    

 83%|████████▎ | 9135/11066 [33:28<07:04,  4.55it/s]
 83%|████████▎ | 9136/11066 [33:28<07:05,  4.53it/s]
                                                    

 83%|████████▎ | 9136/11066 [33:28<07:05,  4.53it/s]
 83%|████████▎ | 9137/11066 [33:28<07:06,  4.52it/s]
                                                    

 83%|████████▎ | 9137/11066 [33:28<07:06,  4.52it/s]
 83%|████████▎ | 9138/11066 [33:28<07:07,  4.51it/s]
                                                    

 83%|████████▎ | 9138/11066 [33:28<07:07,  4.51it/s]
 83%|████████▎ | 9139/11066 [33:29<07:07,  4.51it/s]
                                                    

 83%|████████▎ | 9139/11066 [33:29<07:07,  4.51it/s]
 83%|████████▎ | 9140/11066 [33:29<07:04,  4.54it/s]
                                                    

 83%|████████▎ | 9140/11066 [33:29<07:04,  4.54it/s]
 83%|████████▎ | 9141/11066 [33:29<07:00,  4.58it/s]
                                                    

 83%|████████▎ | 9141/11066 [33:29<07:00,  4.58it/s]
 83%|████████▎ | 9142/11066 [33:29<06:57,  4.61it/s]
                                                    

 83%|████████▎ | 9142/11066 [33:29<06:57,  4.61it/s]
 83%|████████▎ | 9143/11066 [33:29<07:01,  4.57it/s]
                                                    

 83%|████████▎ | 9143/11066 [33:29<07:01,  4.57it/s]
 83%|████████▎ | 9144/11066 [33:30<07:00,  4.57it/s]
                                                    

 83%|████████▎ | 9144/11066 [33:30<07:00,  4.57it/s]
 83%|████████▎ | 9145/11066 [33:30<07:01,  4.56it/s]
                                                    

 83%|████████▎ | 9145/11066 [33:30<07:01,  4.56it/s]
 83%|████████▎ | 9146/11066 [33:30<06:57,  4.60it/s]
                                                    

 83%|████████▎ | 9146/11066 [33:30<06:57,  4.60it/s]
 83%|████████▎ | 9147/11066 [33:30<06:55,  4.62it/s]
                                                    

 83%|████████▎ | 9147/11066 [33:30<06:55,  4.62it/s]
 83%|████████▎ | 9148/11066 [33:31<06:59,  4.57it/s]
                                                    

 83%|████████▎ | 9148/11066 [33:31<06:59,  4.57it/s]
 83%|████████▎ | 9149/11066 [33:31<07:02,  4.54it/s]
                                                    

 83%|████████▎ | 9149/11066 [33:31<07:02,  4.54it/s]
 83%|████████▎ | 9150/11066 [33:31<07:00,  4.56it/s]
                                                    

 83%|████████▎ | 9150/11066 [33:31<07:00,  4.56it/s]
 83%|████████▎ | 9151/11066 [33:31<07:03,  4.52it/s]
                                                    

 83%|████████▎ | 9151/11066 [33:31<07:03,  4.52it/s]
 83%|████████▎ | 9152/11066 [33:31<07:05,  4.50it/s]
                                                    

 83%|████████▎ | 9152/11066 [33:31<07:05,  4.50it/s]
 83%|████████▎ | 9153/11066 [33:32<07:01,  4.54it/s]
                                                    

 83%|████████▎ | 9153/11066 [33:32<07:01,  4.54it/s]
 83%|████████▎ | 9154/11066 [33:32<06:56,  4.59it/s]
                                                    

 83%|████████▎ | 9154/11066 [33:32<06:56,  4.59it/s]
 83%|████████▎ | 9155/11066 [33:32<06:53,  4.62it/s]
                                                    

 83%|████████▎ | 9155/11066 [33:32<06:53,  4.62it/s]
 83%|████████▎ | 9156/11066 [33:32<06:51,  4.64it/s]
                                                    

 83%|████████▎ | 9156/11066 [33:32<06:51,  4.64it/s]
 83%|████████▎ | 9157/11066 [33:32<06:55,  4.59it/s]
                                                    

 83%|████████▎ | 9157/11066 [33:32<06:55,  4.59it/s]
 83%|████████▎ | 9158/11066 [33:33<06:59,  4.55it/s]
                                                    

 83%|████████▎ | 9158/11066 [33:33<06:59,  4.55it/s]
 83%|████████▎ | 9159/11066 [33:33<07:01,  4.52it/s]
                                                    

 83%|████████▎ | 9159/11066 [33:33<07:01,  4.52it/s]
 83%|████████▎ | 9160/11066 [33:33<06:59,  4.54it/s]
                                                    

 83%|████████▎ | 9160/11066 [33:33<06:59,  4.54it/s]
 83%|████████▎ | 9161/11066 [33:33<06:58,  4.56it/s]
                                                    

 83%|████████▎ | 9161/11066 [33:33<06:58,  4.56it/s]
 83%|████████▎ | 9162/11066 [33:34<06:59,  4.54it/s]
                                                    

 83%|████████▎ | 9162/11066 [33:34<06:59,  4.54it/s]
 83%|████████▎ | 9163/11066 [33:34<06:54,  4.59it/s]
                                                    

 83%|████████▎ | 9163/11066 [33:34<06:54,  4.59it/s]
 83%|████████▎ | 9164/11066 [33:34<06:54,  4.59it/s]
                                                    

 83%|████████▎ | 9164/11066 [33:34<06:54,  4.59it/s]
 83%|████████▎ | 9165/11066 [33:34<06:51,  4.62it/s]
                                                    

 83%|████████▎ | 9165/11066 [33:34<06:51,  4.62it/s]
 83%|████████▎ | 9166/11066 [33:34<06:55,  4.58it/s]
                                                    

 83%|████████▎ | 9166/11066 [33:34<06:55,  4.58it/s]
 83%|████████▎ | 9167/11066 [33:35<06:58,  4.54it/s]
                                                    

 83%|████████▎ | 9167/11066 [33:35<06:58,  4.54it/s]
 83%|████████▎ | 9168/11066 [33:35<06:59,  4.53it/s]
                                                    

 83%|████████▎ | 9168/11066 [33:35<06:59,  4.53it/s]
 83%|████████▎ | 9169/11066 [33:35<06:57,  4.55it/s]
                                                    

 83%|████████▎ | 9169/11066 [33:35<06:57,  4.55it/s]
 83%|████████▎ | 9170/11066 [33:35<06:53,  4.58it/s]
                                                    

 83%|████████▎ | 9170/11066 [33:35<06:53,  4.58it/s]
 83%|████████▎ | 9171/11066 [33:36<06:52,  4.59it/s]
                                                    

 83%|████████▎ | 9171/11066 [33:36<06:52,  4.59it/s]
 83%|████████▎ | 9172/11066 [33:36<06:49,  4.62it/s]
                                                    

 83%|████████▎ | 9172/11066 [33:36<06:49,  4.62it/s]
 83%|████████▎ | 9173/11066 [33:36<06:49,  4.62it/s]
                                                    

 83%|████████▎ | 9173/11066 [33:36<06:49,  4.62it/s]
 83%|████████▎ | 9174/11066 [33:36<06:54,  4.56it/s]
                                                    

 83%|████████▎ | 9174/11066 [33:36<06:54,  4.56it/s]
 83%|████████▎ | 9175/11066 [33:36<06:56,  4.54it/s]
                                                    

 83%|████████▎ | 9175/11066 [33:36<06:56,  4.54it/s]
 83%|████████▎ | 9176/11066 [33:37<06:54,  4.56it/s]
                                                    

 83%|████████▎ | 9176/11066 [33:37<06:54,  4.56it/s]
 83%|████████▎ | 9177/11066 [33:37<06:50,  4.60it/s]
                                                    

 83%|████████▎ | 9177/11066 [33:37<06:50,  4.60it/s]
 83%|████████▎ | 9178/11066 [33:37<06:48,  4.62it/s]
                                                    

 83%|████████▎ | 9178/11066 [33:37<06:48,  4.62it/s]
 83%|████████▎ | 9179/11066 [33:37<06:49,  4.61it/s]
                                                    

 83%|████████▎ | 9179/11066 [33:37<06:49,  4.61it/s]
 83%|████████▎ | 9180/11066 [33:38<06:52,  4.58it/s]
                                                    

 83%|████████▎ | 9180/11066 [33:38<06:52,  4.58it/s]
 83%|████████▎ | 9181/11066 [33:38<06:50,  4.59it/s]
                                                    

 83%|████████▎ | 9181/11066 [33:38<06:50,  4.59it/s]
 83%|████████▎ | 9182/11066 [33:38<06:48,  4.61it/s]
                                                    

 83%|████████▎ | 9182/11066 [33:38<06:48,  4.61it/s]
 83%|████████▎ | 9183/11066 [33:38<06:52,  4.57it/s]
                                                    

 83%|████████▎ | 9183/11066 [33:38<06:52,  4.57it/s]
 83%|████████▎ | 9184/11066 [33:38<06:51,  4.58it/s]
                                                    

 83%|████████▎ | 9184/11066 [33:38<06:51,  4.58it/s]
 83%|████████▎ | 9185/11066 [33:39<06:48,  4.61it/s]
                                                    

 83%|████████▎ | 9185/11066 [33:39<06:48,  4.61it/s]
 83%|████████▎ | 9186/11066 [33:39<06:53,  4.55it/s]
                                                    

 83%|████████▎ | 9186/11066 [33:39<06:53,  4.55it/s]
 83%|████████▎ | 9187/11066 [33:39<06:54,  4.53it/s]
                                                    

 83%|████████▎ | 9187/11066 [33:39<06:54,  4.53it/s]
 83%|████████▎ | 9188/11066 [33:39<06:52,  4.55it/s]
                                                    

 83%|████████▎ | 9188/11066 [33:39<06:52,  4.55it/s]
 83%|████████▎ | 9189/11066 [33:39<06:55,  4.51it/s]
                                                    

 83%|████████▎ | 9189/11066 [33:40<06:55,  4.51it/s]
 83%|████████▎ | 9190/11066 [33:40<06:53,  4.54it/s]
                                                    

 83%|████████▎ | 9190/11066 [33:40<06:53,  4.54it/s]
 83%|████████▎ | 9191/11066 [33:40<06:51,  4.55it/s]
                                                    

 83%|████████▎ | 9191/11066 [33:40<06:51,  4.55it/s]
 83%|████████▎ | 9192/11066 [33:40<06:50,  4.57it/s]
                                                    

 83%|████████▎ | 9192/11066 [33:40<06:50,  4.57it/s]
 83%|████████▎ | 9193/11066 [33:40<06:46,  4.61it/s]
                                                    

 83%|████████▎ | 9193/11066 [33:40<06:46,  4.61it/s]
 83%|████████▎ | 9194/11066 [33:41<06:51,  4.55it/s]
                                                    

 83%|████████▎ | 9194/11066 [33:41<06:51,  4.55it/s]
 83%|████████▎ | 9195/11066 [33:41<06:49,  4.57it/s]
                                                    

 83%|████████▎ | 9195/11066 [33:41<06:49,  4.57it/s]
 83%|████████▎ | 9196/11066 [33:41<06:46,  4.60it/s]
                                                    

 83%|████████▎ | 9196/11066 [33:41<06:46,  4.60it/s]
 83%|████████▎ | 9197/11066 [33:41<06:50,  4.55it/s]
                                                    

 83%|████████▎ | 9197/11066 [33:41<06:50,  4.55it/s]
 83%|████████▎ | 9198/11066 [33:41<06:52,  4.53it/s]
                                                    

 83%|████████▎ | 9198/11066 [33:41<06:52,  4.53it/s]
 83%|████████▎ | 9199/11066 [33:42<06:50,  4.55it/s]
                                                    

 83%|████████▎ | 9199/11066 [33:42<06:50,  4.55it/s]
 83%|████████▎ | 9200/11066 [33:42<06:52,  4.53it/s]
                                                    

 83%|████████▎ | 9200/11066 [33:42<06:52,  4.53it/s]
 83%|████████▎ | 9201/11066 [33:42<06:54,  4.50it/s]
                                                    

 83%|████████▎ | 9201/11066 [33:42<06:54,  4.50it/s]
 83%|████████▎ | 9202/11066 [33:42<06:55,  4.49it/s]
                                                    

 83%|████████▎ | 9202/11066 [33:42<06:55,  4.49it/s]
 83%|████████▎ | 9203/11066 [33:43<06:54,  4.49it/s]
                                                    

 83%|████████▎ | 9203/11066 [33:43<06:54,  4.49it/s]
 83%|████████▎ | 9204/11066 [33:43<06:54,  4.50it/s]
                                                    

 83%|████████▎ | 9204/11066 [33:43<06:54,  4.50it/s]
 83%|████████▎ | 9205/11066 [33:43<06:50,  4.53it/s]
                                                    

 83%|████████▎ | 9205/11066 [33:43<06:50,  4.53it/s]
 83%|████████▎ | 9206/11066 [33:43<06:49,  4.54it/s]
                                                    

 83%|████████▎ | 9206/11066 [33:43<06:49,  4.54it/s]
 83%|████████▎ | 9207/11066 [33:43<06:50,  4.53it/s]
                                                    

 83%|████████▎ | 9207/11066 [33:43<06:50,  4.53it/s]
 83%|████████▎ | 9208/11066 [33:44<06:47,  4.56it/s]
                                                    

 83%|████████▎ | 9208/11066 [33:44<06:47,  4.56it/s]
 83%|████████▎ | 9209/11066 [33:44<06:44,  4.60it/s]
                                                    

 83%|████████▎ | 9209/11066 [33:44<06:44,  4.60it/s]
 83%|████████▎ | 9210/11066 [33:44<06:42,  4.61it/s]
                                                    

 83%|████████▎ | 9210/11066 [33:44<06:42,  4.61it/s]
 83%|████████▎ | 9211/11066 [33:44<06:42,  4.61it/s]
                                                    

 83%|████████▎ | 9211/11066 [33:44<06:42,  4.61it/s]
 83%|████████▎ | 9212/11066 [33:45<06:46,  4.56it/s]
                                                    

 83%|████████▎ | 9212/11066 [33:45<06:46,  4.56it/s]
 83%|████████▎ | 9213/11066 [33:45<06:41,  4.62it/s]
                                                    

 83%|████████▎ | 9213/11066 [33:45<06:41,  4.62it/s]
 83%|████████▎ | 9214/11066 [33:45<06:46,  4.56it/s]
                                                    

 83%|████████▎ | 9214/11066 [33:45<06:46,  4.56it/s]
 83%|████████▎ | 9215/11066 [33:45<06:48,  4.53it/s]
                                                    

 83%|████████▎ | 9215/11066 [33:45<06:48,  4.53it/s]
 83%|████████▎ | 9216/11066 [33:45<06:49,  4.52it/s]
                                                    

 83%|████████▎ | 9216/11066 [33:45<06:49,  4.52it/s]
 83%|████████▎ | 9217/11066 [33:46<06:49,  4.52it/s]
                                                    

 83%|████████▎ | 9217/11066 [33:46<06:49,  4.52it/s]
 83%|████████▎ | 9218/11066 [33:46<06:48,  4.53it/s]
                                                    

 83%|████████▎ | 9218/11066 [33:46<06:48,  4.53it/s]
 83%|████████▎ | 9219/11066 [33:46<06:46,  4.55it/s]
                                                    

 83%|████████▎ | 9219/11066 [33:46<06:46,  4.55it/s]
 83%|████████▎ | 9220/11066 [33:46<06:44,  4.57it/s]
                                                    

 83%|████████▎ | 9220/11066 [33:46<06:44,  4.57it/s]
 83%|████████▎ | 9221/11066 [33:47<06:46,  4.54it/s]
                                                    

 83%|████████▎ | 9221/11066 [33:47<06:46,  4.54it/s]
 83%|████████▎ | 9222/11066 [33:47<06:47,  4.53it/s]
                                                    

 83%|████████▎ | 9222/11066 [33:47<06:47,  4.53it/s]
 83%|████████▎ | 9223/11066 [33:47<06:45,  4.55it/s]
                                                    

 83%|████████▎ | 9223/11066 [33:47<06:45,  4.55it/s]
 83%|████████▎ | 9224/11066 [33:47<06:41,  4.59it/s]
                                                    

 83%|████████▎ | 9224/11066 [33:47<06:41,  4.59it/s]
 83%|████████▎ | 9225/11066 [33:47<06:42,  4.57it/s]
                                                    

 83%|████████▎ | 9225/11066 [33:47<06:42,  4.57it/s]
 83%|████████▎ | 9226/11066 [33:48<06:45,  4.53it/s]
                                                    

 83%|████████▎ | 9226/11066 [33:48<06:45,  4.53it/s]
 83%|████████▎ | 9227/11066 [33:48<06:39,  4.60it/s]
                                                    

 83%|████████▎ | 9227/11066 [33:48<06:39,  4.60it/s]
 83%|████████▎ | 9228/11066 [33:48<06:39,  4.60it/s]
                                                    

 83%|████████▎ | 9228/11066 [33:48<06:39,  4.60it/s]
 83%|████████▎ | 9229/11066 [33:48<06:39,  4.60it/s]
                                                    

 83%|████████▎ | 9229/11066 [33:48<06:39,  4.60it/s]
 83%|████████▎ | 9230/11066 [33:48<06:42,  4.56it/s]
                                                    

 83%|████████▎ | 9230/11066 [33:48<06:42,  4.56it/s]
 83%|████████▎ | 9231/11066 [33:49<06:41,  4.58it/s]
                                                    

 83%|████████▎ | 9231/11066 [33:49<06:41,  4.58it/s]
 83%|████████▎ | 9232/11066 [33:49<06:43,  4.55it/s]
                                                    

 83%|████████▎ | 9232/11066 [33:49<06:43,  4.55it/s]
 83%|████████▎ | 9233/11066 [33:49<06:44,  4.53it/s]
                                                    

 83%|████████▎ | 9233/11066 [33:49<06:44,  4.53it/s]
 83%|████████▎ | 9234/11066 [33:49<06:42,  4.56it/s]
                                                    

 83%|████████▎ | 9234/11066 [33:49<06:42,  4.56it/s]
 83%|████████▎ | 9235/11066 [33:50<06:41,  4.56it/s]
                                                    

 83%|████████▎ | 9235/11066 [33:50<06:41,  4.56it/s]
 83%|████████▎ | 9236/11066 [33:50<06:42,  4.54it/s]
                                                    

 83%|████████▎ | 9236/11066 [33:50<06:42,  4.54it/s]
 83%|████████▎ | 9237/11066 [33:50<06:41,  4.56it/s]
                                                    

 83%|████████▎ | 9237/11066 [33:50<06:41,  4.56it/s]
 83%|████████▎ | 9238/11066 [33:50<06:40,  4.57it/s]
                                                    

 83%|████████▎ | 9238/11066 [33:50<06:40,  4.57it/s]
 83%|████████▎ | 9239/11066 [33:50<06:41,  4.55it/s]
                                                    

 83%|████████▎ | 9239/11066 [33:50<06:41,  4.55it/s]
 83%|████████▎ | 9240/11066 [33:51<06:42,  4.54it/s]
                                                    

 83%|████████▎ | 9240/11066 [33:51<06:42,  4.54it/s]
 84%|████████▎ | 9241/11066 [33:51<06:47,  4.48it/s]
                                                    
{'loss': 0.9901, 'learning_rate': 5.253930959696368e-06, 'epoch': 1.65}
{'loss': 0.9036, 'learning_rate': 5.251219953009218e-06, 'epoch': 1.65}
{'loss': 1.131, 'learning_rate': 5.248508946322068e-06, 'epoch': 1.65}
{'loss': 0.841, 'learning_rate': 5.245797939634918e-06, 'epoch': 1.65}
{'loss': 0.6469, 'learning_rate': 5.243086932947768e-06, 'epoch': 1.65}
{'loss': 1.1074, 'learning_rate': 5.2403759262606184e-06, 'epoch': 1.65}
{'loss': 1.2591, 'learning_rate': 5.237664919573469e-06, 'epoch': 1.65}
{'loss': 0.6127, 'learning_rate': 5.234953912886319e-06, 'epoch': 1.65}
{'loss': 0.6614, 'learning_rate': 5.232242906199168e-06, 'epoch': 1.65}
{'loss': 0.4573, 'learning_rate': 5.229531899512019e-06, 'epoch': 1.65}
{'loss': 0.7872, 'learning_rate': 5.226820892824868e-06, 'epoch': 1.65}
{'loss': 0.8656, 'learning_rate': 5.224109886137719e-06, 'epoch': 1.65}
{'loss': 0.7673, 'learning_rate': 5.221398879450569e-06, 'epoch': 1.65}
{'loss': 0.9613, 'learning_rate': 5.2186878727634195e-06, 'epoch': 1.65}
{'loss': 0.6804, 'learning_rate': 5.21597686607627e-06, 'epoch': 1.65}
{'loss': 0.6187, 'learning_rate': 5.21326585938912e-06, 'epoch': 1.65}
{'loss': 0.5984, 'learning_rate': 5.21055485270197e-06, 'epoch': 1.65}
{'loss': 0.56, 'learning_rate': 5.20784384601482e-06, 'epoch': 1.65}
{'loss': 0.5804, 'learning_rate': 5.20513283932767e-06, 'epoch': 1.65}
{'loss': 0.8158, 'learning_rate': 5.20242183264052e-06, 'epoch': 1.65}
{'loss': 0.6699, 'learning_rate': 5.1997108259533705e-06, 'epoch': 1.65}
{'loss': 0.4738, 'learning_rate': 5.1969998192662214e-06, 'epoch': 1.65}
{'loss': 1.2853, 'learning_rate': 5.194288812579071e-06, 'epoch': 1.65}
{'loss': 0.6053, 'learning_rate': 5.191577805891922e-06, 'epoch': 1.65}
{'loss': 0.4979, 'learning_rate': 5.188866799204771e-06, 'epoch': 1.65}
{'loss': 0.2864, 'learning_rate': 5.186155792517622e-06, 'epoch': 1.65}
{'loss': 0.7486, 'learning_rate': 5.183444785830471e-06, 'epoch': 1.65}
{'loss': 0.8892, 'learning_rate': 5.180733779143322e-06, 'epoch': 1.65}
{'loss': 0.729, 'learning_rate': 5.1780227724561715e-06, 'epoch': 1.65}
{'loss': 0.5572, 'learning_rate': 5.1753117657690225e-06, 'epoch': 1.65}
{'loss': 0.3771, 'learning_rate': 5.172600759081872e-06, 'epoch': 1.66}
{'loss': 0.7284, 'learning_rate': 5.169889752394723e-06, 'epoch': 1.66}
{'loss': 0.452, 'learning_rate': 5.167178745707573e-06, 'epoch': 1.66}
{'loss': 0.9758, 'learning_rate': 5.164467739020423e-06, 'epoch': 1.66}
{'loss': 0.4953, 'learning_rate': 5.161756732333273e-06, 'epoch': 1.66}
{'loss': 0.7589, 'learning_rate': 5.159045725646123e-06, 'epoch': 1.66}
{'loss': 0.4634, 'learning_rate': 5.1563347189589735e-06, 'epoch': 1.66}
{'loss': 0.4688, 'learning_rate': 5.153623712271824e-06, 'epoch': 1.66}
{'loss': 0.7659, 'learning_rate': 5.150912705584674e-06, 'epoch': 1.66}
{'loss': 0.9163, 'learning_rate': 5.148201698897524e-06, 'epoch': 1.66}
{'loss': 0.4319, 'learning_rate': 5.145490692210374e-06, 'epoch': 1.66}
{'loss': 0.8272, 'learning_rate': 5.142779685523224e-06, 'epoch': 1.66}
{'loss': 0.6712, 'learning_rate': 5.140068678836074e-06, 'epoch': 1.66}
{'loss': 0.8178, 'learning_rate': 5.137357672148925e-06, 'epoch': 1.66}
{'loss': 0.6627, 'learning_rate': 5.1346466654617745e-06, 'epoch': 1.66}
{'loss': 0.5641, 'learning_rate': 5.1319356587746255e-06, 'epoch': 1.66}
{'loss': 0.4089, 'learning_rate': 5.129224652087475e-06, 'epoch': 1.66}
{'loss': 0.7003, 'learning_rate': 5.126513645400326e-06, 'epoch': 1.66}
{'loss': 0.4074, 'learning_rate': 5.123802638713175e-06, 'epoch': 1.66}
{'loss': 0.7352, 'learning_rate': 5.121091632026026e-06, 'epoch': 1.66}
{'loss': 0.4527, 'learning_rate': 5.118380625338875e-06, 'epoch': 1.66}
{'loss': 0.502, 'learning_rate': 5.115669618651726e-06, 'epoch': 1.66}
{'loss': 0.5731, 'learning_rate': 5.1129586119645765e-06, 'epoch': 1.66}
{'loss': 0.6958, 'learning_rate': 5.110247605277427e-06, 'epoch': 1.66}
{'loss': 1.0391, 'learning_rate': 5.107536598590277e-06, 'epoch': 1.66}
{'loss': 1.1297, 'learning_rate': 5.104825591903127e-06, 'epoch': 1.66}
{'loss': 0.2758, 'learning_rate': 5.102114585215977e-06, 'epoch': 1.66}
{'loss': 0.5251, 'learning_rate': 5.099403578528827e-06, 'epoch': 1.66}
{'loss': 0.6624, 'learning_rate': 5.096692571841677e-06, 'epoch': 1.66}
{'loss': 0.8752, 'learning_rate': 5.093981565154527e-06, 'epoch': 1.66}
{'loss': 0.703, 'learning_rate': 5.0912705584673775e-06, 'epoch': 1.66}
{'loss': 0.7894, 'learning_rate': 5.088559551780228e-06, 'epoch': 1.66}
{'loss': 0.9821, 'learning_rate': 5.085848545093078e-06, 'epoch': 1.66}
{'loss': 0.8873, 'learning_rate': 5.083137538405929e-06, 'epoch': 1.66}
{'loss': 0.7287, 'learning_rate': 5.080426531718778e-06, 'epoch': 1.66}
{'loss': 0.8343, 'learning_rate': 5.077715525031629e-06, 'epoch': 1.66}
{'loss': 1.0999, 'learning_rate': 5.075004518344478e-06, 'epoch': 1.66}
{'loss': 1.0766, 'learning_rate': 5.072293511657329e-06, 'epoch': 1.66}
{'loss': 0.6023, 'learning_rate': 5.069582504970179e-06, 'epoch': 1.66}
{'loss': 0.7197, 'learning_rate': 5.06687149828303e-06, 'epoch': 1.66}
{'loss': 0.6274, 'learning_rate': 5.064160491595879e-06, 'epoch': 1.66}
{'loss': 0.9422, 'learning_rate': 5.06144948490873e-06, 'epoch': 1.66}
{'loss': 0.2697, 'learning_rate': 5.058738478221579e-06, 'epoch': 1.66}
{'loss': 0.323, 'learning_rate': 5.05602747153443e-06, 'epoch': 1.66}
{'loss': 0.3066, 'learning_rate': 5.05331646484728e-06, 'epoch': 1.66}
{'loss': 0.613, 'learning_rate': 5.05060545816013e-06, 'epoch': 1.66}
{'loss': 0.1395, 'learning_rate': 5.0478944514729805e-06, 'epoch': 1.66}
{'loss': 0.5995, 'learning_rate': 5.045183444785831e-06, 'epoch': 1.66}
{'loss': 0.3757, 'learning_rate': 5.042472438098681e-06, 'epoch': 1.66}
{'loss': 0.8189, 'learning_rate': 5.039761431411531e-06, 'epoch': 1.66}
{'loss': 0.9125, 'learning_rate': 5.037050424724381e-06, 'epoch': 1.66}
{'loss': 0.5833, 'learning_rate': 5.034339418037231e-06, 'epoch': 1.66}
{'loss': 1.0466, 'learning_rate': 5.031628411350081e-06, 'epoch': 1.66}
{'loss': 0.8143, 'learning_rate': 5.0289174046629315e-06, 'epoch': 1.66}
{'loss': 0.4819, 'learning_rate': 5.026206397975782e-06, 'epoch': 1.66}
{'loss': 0.4987, 'learning_rate': 5.023495391288633e-06, 'epoch': 1.67}
{'loss': 0.4315, 'learning_rate': 5.020784384601482e-06, 'epoch': 1.67}
{'loss': 0.9148, 'learning_rate': 5.018073377914333e-06, 'epoch': 1.67}
{'loss': 0.9529, 'learning_rate': 5.015362371227182e-06, 'epoch': 1.67}
{'loss': 0.3067, 'learning_rate': 5.012651364540033e-06, 'epoch': 1.67}
{'loss': 0.5968, 'learning_rate': 5.009940357852882e-06, 'epoch': 1.67}
{'loss': 0.887, 'learning_rate': 5.007229351165733e-06, 'epoch': 1.67}
{'loss': 0.5938, 'learning_rate': 5.004518344478583e-06, 'epoch': 1.67}
{'loss': 0.666, 'learning_rate': 5.001807337791434e-06, 'epoch': 1.67}
{'loss': 0.3989, 'learning_rate': 4.999096331104284e-06, 'epoch': 1.67}
{'loss': 0.9631, 'learning_rate': 4.996385324417134e-06, 'epoch': 1.67}
{'loss': 0.6709, 'learning_rate': 4.993674317729984e-06, 'epoch': 1.67}
{'loss': 0.9908, 'learning_rate': 4.990963311042834e-06, 'epoch': 1.67}
{'loss': 0.3785, 'learning_rate': 4.988252304355684e-06, 'epoch': 1.67}
{'loss': 1.1736, 'learning_rate': 4.9855412976685345e-06, 'epoch': 1.67}
{'loss': 0.5567, 'learning_rate': 4.982830290981385e-06, 'epoch': 1.67}
{'loss': 1.0523, 'learning_rate': 4.980119284294235e-06, 'epoch': 1.67}
{'loss': 0.6438, 'learning_rate': 4.977408277607085e-06, 'epoch': 1.67}
{'loss': 1.0762, 'learning_rate': 4.974697270919935e-06, 'epoch': 1.67}
{'loss': 0.4437, 'learning_rate': 4.971986264232785e-06, 'epoch': 1.67}
{'loss': 1.0203, 'learning_rate': 4.969275257545636e-06, 'epoch': 1.67}
{'loss': 0.3124, 'learning_rate': 4.966564250858485e-06, 'epoch': 1.67}
{'loss': 1.0323, 'learning_rate': 4.963853244171336e-06, 'epoch': 1.67}
{'loss': 0.6006, 'learning_rate': 4.961142237484186e-06, 'epoch': 1.67}
{'loss': 0.5913, 'learning_rate': 4.958431230797037e-06, 'epoch': 1.67}
{'loss': 0.5179, 'learning_rate': 4.955720224109886e-06, 'epoch': 1.67}
{'loss': 0.2668, 'learning_rate': 4.953009217422737e-06, 'epoch': 1.67}
{'loss': 0.5129, 'learning_rate': 4.950298210735586e-06, 'epoch': 1.67}

 84%|████████▎ | 9241/11066 [33:51<06:47,  4.48it/s]
 84%|████████▎ | 9242/11066 [33:51<06:47,  4.47it/s]
                                                    

 84%|████████▎ | 9242/11066 [33:51<06:47,  4.47it/s]
 84%|████████▎ | 9243/11066 [33:51<06:43,  4.51it/s]
                                                    

 84%|████████▎ | 9243/11066 [33:51<06:43,  4.51it/s]
 84%|████████▎ | 9244/11066 [33:52<06:46,  4.49it/s]
                                                    

 84%|████████▎ | 9244/11066 [33:52<06:46,  4.49it/s]
 84%|████████▎ | 9245/11066 [33:52<06:42,  4.52it/s]
                                                    

 84%|████████▎ | 9245/11066 [33:52<06:42,  4.52it/s]
 84%|████████▎ | 9246/11066 [33:52<06:38,  4.57it/s]
                                                    

 84%|████████▎ | 9246/11066 [33:52<06:38,  4.57it/s]
 84%|████████▎ | 9247/11066 [33:52<06:35,  4.59it/s]
                                                    

 84%|████████▎ | 9247/11066 [33:52<06:35,  4.59it/s]
 84%|████████▎ | 9248/11066 [33:52<06:38,  4.56it/s]
                                                    

 84%|████████▎ | 9248/11066 [33:52<06:38,  4.56it/s]
 84%|████████▎ | 9249/11066 [33:53<06:35,  4.60it/s]
                                                    

 84%|████████▎ | 9249/11066 [33:53<06:35,  4.60it/s]
 84%|████████▎ | 9250/11066 [33:53<06:35,  4.59it/s]
                                                    

 84%|████████▎ | 9250/11066 [33:53<06:35,  4.59it/s]
 84%|████████▎ | 9251/11066 [33:53<06:38,  4.55it/s]
                                                    

 84%|████████▎ | 9251/11066 [33:53<06:38,  4.55it/s]
 84%|████████▎ | 9252/11066 [33:53<06:37,  4.57it/s]
                                                    

 84%|████████▎ | 9252/11066 [33:53<06:37,  4.57it/s]
 84%|████████▎ | 9253/11066 [33:54<06:40,  4.53it/s]
                                                    

 84%|████████▎ | 9253/11066 [33:54<06:40,  4.53it/s]
 84%|████████▎ | 9254/11066 [33:54<06:42,  4.50it/s]
                                                    

 84%|████████▎ | 9254/11066 [33:54<06:42,  4.50it/s]
 84%|████████▎ | 9255/11066 [33:54<06:43,  4.48it/s]
                                                    

 84%|████████▎ | 9255/11066 [33:54<06:43,  4.48it/s]
 84%|████████▎ | 9256/11066 [33:54<06:44,  4.48it/s]
                                                    

 84%|████████▎ | 9256/11066 [33:54<06:44,  4.48it/s]
 84%|████████▎ | 9257/11066 [33:54<06:45,  4.46it/s]
                                                    

 84%|████████▎ | 9257/11066 [33:54<06:45,  4.46it/s]
 84%|████████▎ | 9258/11066 [33:55<06:45,  4.46it/s]
                                                    

 84%|████████▎ | 9258/11066 [33:55<06:45,  4.46it/s]
 84%|████████▎ | 9259/11066 [33:55<06:49,  4.41it/s]
                                                    

 84%|████████▎ | 9259/11066 [33:55<06:49,  4.41it/s]
 84%|████████▎ | 9260/11066 [33:55<06:41,  4.50it/s]
                                                    

 84%|████████▎ | 9260/11066 [33:55<06:41,  4.50it/s]
 84%|████████▎ | 9261/11066 [33:55<06:44,  4.47it/s]
                                                    

 84%|████████▎ | 9261/11066 [33:55<06:44,  4.47it/s]
 84%|████████▎ | 9262/11066 [33:56<06:49,  4.41it/s]
                                                    

 84%|████████▎ | 9262/11066 [33:56<06:49,  4.41it/s]
 84%|████████▎ | 9263/11066 [33:56<06:44,  4.46it/s]
                                                    

 84%|████████▎ | 9263/11066 [33:56<06:44,  4.46it/s]
 84%|████████▎ | 9264/11066 [33:56<06:45,  4.45it/s]
                                                    

 84%|████████▎ | 9264/11066 [33:56<06:45,  4.45it/s]
 84%|████████▎ | 9265/11066 [33:56<06:45,  4.44it/s]
                                                    

 84%|████████▎ | 9265/11066 [33:56<06:45,  4.44it/s]
 84%|████████▎ | 9266/11066 [33:56<06:47,  4.42it/s]
                                                    

 84%|████████▎ | 9266/11066 [33:56<06:47,  4.42it/s]
 84%|████████▎ | 9267/11066 [33:57<06:50,  4.38it/s]
                                                    

 84%|████████▎ | 9267/11066 [33:57<06:50,  4.38it/s]
 84%|████████▍ | 9268/11066 [33:57<06:47,  4.41it/s]
                                                    

 84%|████████▍ | 9268/11066 [33:57<06:47,  4.41it/s]
 84%|████████▍ | 9269/11066 [33:57<06:43,  4.45it/s]
                                                    

 84%|████████▍ | 9269/11066 [33:57<06:43,  4.45it/s]
 84%|████████▍ | 9270/11066 [33:57<06:39,  4.49it/s]
                                                    

 84%|████████▍ | 9270/11066 [33:57<06:39,  4.49it/s]
 84%|████████▍ | 9271/11066 [33:58<06:36,  4.53it/s]
                                                    

 84%|████████▍ | 9271/11066 [33:58<06:36,  4.53it/s]
 84%|████████▍ | 9272/11066 [33:58<06:35,  4.54it/s]
                                                    

 84%|████████▍ | 9272/11066 [33:58<06:35,  4.54it/s]
 84%|████████▍ | 9273/11066 [33:58<06:31,  4.58it/s]
                                                    

 84%|████████▍ | 9273/11066 [33:58<06:31,  4.58it/s]
 84%|████████▍ | 9274/11066 [33:58<06:28,  4.61it/s]
                                                    

 84%|████████▍ | 9274/11066 [33:58<06:28,  4.61it/s]
 84%|████████▍ | 9275/11066 [33:58<06:28,  4.61it/s]
                                                    

 84%|████████▍ | 9275/11066 [33:58<06:28,  4.61it/s]
 84%|████████▍ | 9276/11066 [33:59<06:28,  4.61it/s]
                                                    

 84%|████████▍ | 9276/11066 [33:59<06:28,  4.61it/s]
 84%|████████▍ | 9277/11066 [33:59<06:30,  4.58it/s]
                                                    

 84%|████████▍ | 9277/11066 [33:59<06:30,  4.58it/s]
 84%|████████▍ | 9278/11066 [33:59<06:30,  4.58it/s]
                                                    

 84%|████████▍ | 9278/11066 [33:59<06:30,  4.58it/s]
 84%|████████▍ | 9279/11066 [33:59<06:25,  4.63it/s]
                                                    

 84%|████████▍ | 9279/11066 [33:59<06:25,  4.63it/s]
 84%|████████▍ | 9280/11066 [34:00<06:29,  4.59it/s]
                                                    

 84%|████████▍ | 9280/11066 [34:00<06:29,  4.59it/s]
 84%|████████▍ | 9281/11066 [34:00<06:31,  4.56it/s]
                                                    

 84%|████████▍ | 9281/11066 [34:00<06:31,  4.56it/s]
 84%|████████▍ | 9282/11066 [34:00<06:33,  4.54it/s]
                                                    

 84%|████████▍ | 9282/11066 [34:00<06:33,  4.54it/s]
 84%|████████▍ | 9283/11066 [34:00<06:33,  4.53it/s]
                                                    

 84%|████████▍ | 9283/11066 [34:00<06:33,  4.53it/s]
 84%|████████▍ | 9284/11066 [34:00<06:34,  4.52it/s]
                                                    

 84%|████████▍ | 9284/11066 [34:00<06:34,  4.52it/s]
 84%|████████▍ | 9285/11066 [34:01<06:34,  4.52it/s]
                                                    

 84%|████████▍ | 9285/11066 [34:01<06:34,  4.52it/s]
 84%|████████▍ | 9286/11066 [34:01<06:32,  4.54it/s]
                                                    

 84%|████████▍ | 9286/11066 [34:01<06:32,  4.54it/s]
 84%|████████▍ | 9287/11066 [34:01<06:32,  4.53it/s]
                                                    

 84%|████████▍ | 9287/11066 [34:01<06:32,  4.53it/s]
 84%|████████▍ | 9288/11066 [34:01<06:28,  4.58it/s]
                                                    

 84%|████████▍ | 9288/11066 [34:01<06:28,  4.58it/s]
 84%|████████▍ | 9289/11066 [34:02<06:28,  4.57it/s]
                                                    

 84%|████████▍ | 9289/11066 [34:02<06:28,  4.57it/s]
 84%|████████▍ | 9290/11066 [34:02<06:30,  4.55it/s]
                                                    

 84%|████████▍ | 9290/11066 [34:02<06:30,  4.55it/s]
 84%|████████▍ | 9291/11066 [34:02<06:28,  4.57it/s]
                                                    

 84%|████████▍ | 9291/11066 [34:02<06:28,  4.57it/s]
 84%|████████▍ | 9292/11066 [34:02<06:30,  4.55it/s]
                                                    

 84%|████████▍ | 9292/11066 [34:02<06:30,  4.55it/s]
 84%|████████▍ | 9293/11066 [34:02<06:32,  4.52it/s]
                                                    

 84%|████████▍ | 9293/11066 [34:02<06:32,  4.52it/s]
 84%|████████▍ | 9294/11066 [34:03<06:33,  4.50it/s]
                                                    

 84%|████████▍ | 9294/11066 [34:03<06:33,  4.50it/s]
 84%|████████▍ | 9295/11066 [34:03<06:31,  4.53it/s]
                                                    

 84%|████████▍ | 9295/11066 [34:03<06:31,  4.53it/s]
 84%|████████▍ | 9296/11066 [34:03<06:27,  4.57it/s]
                                                    

 84%|████████▍ | 9296/11066 [34:03<06:27,  4.57it/s]
 84%|████████▍ | 9297/11066 [34:03<06:24,  4.60it/s]
                                                    

 84%|████████▍ | 9297/11066 [34:03<06:24,  4.60it/s]
 84%|████████▍ | 9298/11066 [34:04<06:28,  4.55it/s]
                                                    

 84%|████████▍ | 9298/11066 [34:04<06:28,  4.55it/s]
 84%|████████▍ | 9299/11066 [34:04<06:27,  4.56it/s]
                                                    

 84%|████████▍ | 9299/11066 [34:04<06:27,  4.56it/s]
 84%|████████▍ | 9300/11066 [34:04<06:24,  4.60it/s]
                                                    

 84%|████████▍ | 9300/11066 [34:04<06:24,  4.60it/s]
 84%|████████▍ | 9301/11066 [34:04<06:24,  4.59it/s]
                                                    

 84%|████████▍ | 9301/11066 [34:04<06:24,  4.59it/s]
 84%|████████▍ | 9302/11066 [34:04<06:21,  4.63it/s]
                                                    

 84%|████████▍ | 9302/11066 [34:04<06:21,  4.63it/s]
 84%|████████▍ | 9303/11066 [34:05<06:25,  4.58it/s]
                                                    

 84%|████████▍ | 9303/11066 [34:05<06:25,  4.58it/s]
 84%|████████▍ | 9304/11066 [34:05<06:28,  4.54it/s]
                                                    

 84%|████████▍ | 9304/11066 [34:05<06:28,  4.54it/s]
 84%|████████▍ | 9305/11066 [34:05<06:27,  4.55it/s]
                                                    

 84%|████████▍ | 9305/11066 [34:05<06:27,  4.55it/s]
 84%|████████▍ | 9306/11066 [34:05<06:25,  4.57it/s]
                                                    

 84%|████████▍ | 9306/11066 [34:05<06:25,  4.57it/s]
 84%|████████▍ | 9307/11066 [34:05<06:27,  4.54it/s]
                                                    

 84%|████████▍ | 9307/11066 [34:05<06:27,  4.54it/s]
 84%|████████▍ | 9308/11066 [34:06<06:26,  4.55it/s]
                                                    

 84%|████████▍ | 9308/11066 [34:06<06:26,  4.55it/s]
 84%|████████▍ | 9309/11066 [34:06<06:23,  4.58it/s]
                                                    

 84%|████████▍ | 9309/11066 [34:06<06:23,  4.58it/s]
 84%|████████▍ | 9310/11066 [34:06<06:24,  4.57it/s]
                                                    

 84%|████████▍ | 9310/11066 [34:06<06:24,  4.57it/s]
 84%|████████▍ | 9311/11066 [34:06<06:20,  4.62it/s]
                                                    

 84%|████████▍ | 9311/11066 [34:06<06:20,  4.62it/s]
 84%|████████▍ | 9312/11066 [34:07<06:24,  4.56it/s]
                                                    

 84%|████████▍ | 9312/11066 [34:07<06:24,  4.56it/s]
 84%|████████▍ | 9313/11066 [34:07<06:27,  4.53it/s]
                                                    

 84%|████████▍ | 9313/11066 [34:07<06:27,  4.53it/s]
 84%|████████▍ | 9314/11066 [34:07<06:25,  4.55it/s]
                                                    

 84%|████████▍ | 9314/11066 [34:07<06:25,  4.55it/s]
 84%|████████▍ | 9315/11066 [34:07<06:21,  4.59it/s]
                                                    

 84%|████████▍ | 9315/11066 [34:07<06:21,  4.59it/s]
 84%|████████▍ | 9316/11066 [34:07<06:19,  4.61it/s]
                                                    

 84%|████████▍ | 9316/11066 [34:07<06:19,  4.61it/s]
 84%|████████▍ | 9317/11066 [34:08<06:19,  4.60it/s]
                                                    

 84%|████████▍ | 9317/11066 [34:08<06:19,  4.60it/s]
 84%|████████▍ | 9318/11066 [34:08<06:17,  4.63it/s]
                                                    

 84%|████████▍ | 9318/11066 [34:08<06:17,  4.63it/s]
 84%|████████▍ | 9319/11066 [34:08<06:18,  4.61it/s]
                                                    

 84%|████████▍ | 9319/11066 [34:08<06:18,  4.61it/s]
 84%|████████▍ | 9320/11066 [34:08<06:18,  4.62it/s]
                                                    

 84%|████████▍ | 9320/11066 [34:08<06:18,  4.62it/s]
 84%|████████▍ | 9321/11066 [34:09<06:19,  4.59it/s]
                                                    

 84%|████████▍ | 9321/11066 [34:09<06:19,  4.59it/s]
 84%|████████▍ | 9322/11066 [34:09<06:31,  4.46it/s]
                                                    

 84%|████████▍ | 9322/11066 [34:09<06:31,  4.46it/s]
 84%|████████▍ | 9323/11066 [34:09<06:30,  4.46it/s]
                                                    

 84%|████████▍ | 9323/11066 [34:09<06:30,  4.46it/s]
 84%|████████▍ | 9324/11066 [34:09<06:31,  4.45it/s]
                                                    

 84%|████████▍ | 9324/11066 [34:09<06:31,  4.45it/s]
 84%|████████▍ | 9325/11066 [34:09<06:36,  4.39it/s]
                                                    

 84%|████████▍ | 9325/11066 [34:09<06:36,  4.39it/s]
 84%|████████▍ | 9326/11066 [34:10<06:34,  4.42it/s]
                                                    

 84%|████████▍ | 9326/11066 [34:10<06:34,  4.42it/s]
 84%|████████▍ | 9327/11066 [34:10<06:32,  4.43it/s]
                                                    

 84%|████████▍ | 9327/11066 [34:10<06:32,  4.43it/s]
 84%|████████▍ | 9328/11066 [34:10<06:28,  4.48it/s]
                                                    

 84%|████████▍ | 9328/11066 [34:10<06:28,  4.48it/s]
 84%|████████▍ | 9329/11066 [34:10<06:25,  4.51it/s]
                                                    

 84%|████████▍ | 9329/11066 [34:10<06:25,  4.51it/s]
 84%|████████▍ | 9330/11066 [34:11<06:22,  4.53it/s]
                                                    

 84%|████████▍ | 9330/11066 [34:11<06:22,  4.53it/s]
 84%|████████▍ | 9331/11066 [34:11<06:24,  4.52it/s]
                                                    

 84%|████████▍ | 9331/11066 [34:11<06:24,  4.52it/s]
 84%|████████▍ | 9332/11066 [34:11<06:22,  4.54it/s]
                                                    

 84%|████████▍ | 9332/11066 [34:11<06:22,  4.54it/s]
 84%|████████▍ | 9333/11066 [34:11<06:24,  4.51it/s]
                                                    

 84%|████████▍ | 9333/11066 [34:11<06:24,  4.51it/s]
 84%|████████▍ | 9334/11066 [34:11<06:22,  4.53it/s]
                                                    

 84%|████████▍ | 9334/11066 [34:11<06:22,  4.53it/s]
 84%|████████▍ | 9335/11066 [34:12<06:21,  4.54it/s]
                                                    

 84%|████████▍ | 9335/11066 [34:12<06:21,  4.54it/s]
 84%|████████▍ | 9336/11066 [34:12<06:22,  4.52it/s]
                                                    

 84%|████████▍ | 9336/11066 [34:12<06:22,  4.52it/s]
 84%|████████▍ | 9337/11066 [34:12<06:20,  4.55it/s]
                                                    

 84%|████████▍ | 9337/11066 [34:12<06:20,  4.55it/s]
 84%|████████▍ | 9338/11066 [34:12<06:21,  4.53it/s]
                                                    

 84%|████████▍ | 9338/11066 [34:12<06:21,  4.53it/s]
 84%|████████▍ | 9339/11066 [34:13<06:22,  4.52it/s]
                                                    

 84%|████████▍ | 9339/11066 [34:13<06:22,  4.52it/s]
 84%|████████▍ | 9340/11066 [34:13<06:20,  4.53it/s]
                                                    

 84%|████████▍ | 9340/11066 [34:13<06:20,  4.53it/s]
 84%|████████▍ | 9341/11066 [34:13<06:16,  4.58it/s]
                                                    

 84%|████████▍ | 9341/11066 [34:13<06:16,  4.58it/s]
 84%|████████▍ | 9342/11066 [34:13<06:11,  4.65it/s]
                                                    

 84%|████████▍ | 9342/11066 [34:13<06:11,  4.65it/s]
 84%|████████▍ | 9343/11066 [34:13<06:15,  4.59it/s]
                                                    

 84%|████████▍ | 9343/11066 [34:13<06:15,  4.59it/s]
 84%|████████▍ | 9344/11066 [34:14<06:14,  4.60it/s]
                                                    

 84%|████████▍ | 9344/11066 [34:14<06:14,  4.60it/s]
 84%|████████▍ | 9345/11066 [34:14<06:16,  4.57it/s]
                                                    

 84%|████████▍ | 9345/11066 [34:14<06:16,  4.57it/s]
 84%|████████▍ | 9346/11066 [34:14<06:13,  4.60it/s]
                                                    

 84%|████████▍ | 9346/11066 [34:14<06:13,  4.60it/s]
 84%|████████▍ | 9347/11066 [34:14<06:14,  4.60it/s]
                                                    

 84%|████████▍ | 9347/11066 [34:14<06:14,  4.60it/s]
 84%|████████▍ | 9348/11066 [34:15<06:17,  4.55it/s]
                                                    

 84%|████████▍ | 9348/11066 [34:15<06:17,  4.55it/s]
 84%|████████▍ | 9349/11066 [34:15<06:19,  4.52it/s]
                                                    

 84%|████████▍ | 9349/11066 [34:15<06:19,  4.52it/s]
 84%|████████▍ | 9350/11066 [34:15<06:21,  4.50it/s]
                                                    

 84%|████████▍ | 9350/11066 [34:15<06:21,  4.50it/s]
 85%|████████▍ | 9351/11066 [34:15<06:21,  4.50it/s]
                                                    

 85%|████████▍ | 9351/11066 [34:15<06:21,  4.50it/s]
 85%|████████▍ | 9352/11066 [34:15<06:20,  4.50it/s]
                                                    

 85%|████████▍ | 9352/11066 [34:15<06:20,  4.50it/s]
 85%|████████▍ | 9353/11066 [34:16<06:20,  4.50it/s]
                                                    

 85%|████████▍ | 9353/11066 [34:16<06:20,  4.50it/s]
 85%|████████▍ | 9354/11066 [34:16<06:17,  4.54it/s]
                                                    
{'loss': 1.3762, 'learning_rate': 4.947587204048437e-06, 'epoch': 1.67}
{'loss': 0.4117, 'learning_rate': 4.9448761973612865e-06, 'epoch': 1.67}
{'loss': 0.8037, 'learning_rate': 4.9421651906741375e-06, 'epoch': 1.67}
{'loss': 0.4175, 'learning_rate': 4.939454183986988e-06, 'epoch': 1.67}
{'loss': 0.7665, 'learning_rate': 4.936743177299838e-06, 'epoch': 1.67}
{'loss': 0.5787, 'learning_rate': 4.934032170612688e-06, 'epoch': 1.67}
{'loss': 0.7871, 'learning_rate': 4.931321163925538e-06, 'epoch': 1.67}
{'loss': 0.8295, 'learning_rate': 4.928610157238388e-06, 'epoch': 1.67}
{'loss': 1.0227, 'learning_rate': 4.925899150551238e-06, 'epoch': 1.67}
{'loss': 0.4973, 'learning_rate': 4.923188143864088e-06, 'epoch': 1.67}
{'loss': 1.1122, 'learning_rate': 4.9204771371769385e-06, 'epoch': 1.67}
{'loss': 0.246, 'learning_rate': 4.917766130489789e-06, 'epoch': 1.67}
{'loss': 0.8189, 'learning_rate': 4.915055123802639e-06, 'epoch': 1.67}
{'loss': 0.6513, 'learning_rate': 4.912344117115489e-06, 'epoch': 1.67}
{'loss': 0.917, 'learning_rate': 4.90963311042834e-06, 'epoch': 1.67}
{'loss': 1.0399, 'learning_rate': 4.906922103741189e-06, 'epoch': 1.67}
{'loss': 0.2941, 'learning_rate': 4.90421109705404e-06, 'epoch': 1.67}
{'loss': 0.7664, 'learning_rate': 4.9015000903668895e-06, 'epoch': 1.67}
{'loss': 0.9145, 'learning_rate': 4.8987890836797404e-06, 'epoch': 1.67}
{'loss': 0.671, 'learning_rate': 4.89607807699259e-06, 'epoch': 1.67}
{'loss': 1.2319, 'learning_rate': 4.893367070305441e-06, 'epoch': 1.67}
{'loss': 0.6252, 'learning_rate': 4.89065606361829e-06, 'epoch': 1.67}
{'loss': 0.8278, 'learning_rate': 4.887945056931141e-06, 'epoch': 1.67}
{'loss': 0.6311, 'learning_rate': 4.885234050243991e-06, 'epoch': 1.67}
{'loss': 0.655, 'learning_rate': 4.88252304355684e-06, 'epoch': 1.67}
{'loss': 0.8095, 'learning_rate': 4.879812036869691e-06, 'epoch': 1.67}
{'loss': 1.2631, 'learning_rate': 4.877101030182541e-06, 'epoch': 1.67}
{'loss': 0.7002, 'learning_rate': 4.874390023495392e-06, 'epoch': 1.68}
{'loss': 0.3073, 'learning_rate': 4.871679016808241e-06, 'epoch': 1.68}
{'loss': 0.5114, 'learning_rate': 4.868968010121092e-06, 'epoch': 1.68}
{'loss': 0.6907, 'learning_rate': 4.866257003433941e-06, 'epoch': 1.68}
{'loss': 1.1049, 'learning_rate': 4.863545996746792e-06, 'epoch': 1.68}
{'loss': 0.6588, 'learning_rate': 4.8608349900596415e-06, 'epoch': 1.68}
{'loss': 0.9416, 'learning_rate': 4.8581239833724925e-06, 'epoch': 1.68}
{'loss': 0.5644, 'learning_rate': 4.855412976685343e-06, 'epoch': 1.68}
{'loss': 0.8426, 'learning_rate': 4.852701969998193e-06, 'epoch': 1.68}
{'loss': 0.47, 'learning_rate': 4.849990963311043e-06, 'epoch': 1.68}
{'loss': 0.4525, 'learning_rate': 4.847279956623893e-06, 'epoch': 1.68}
{'loss': 0.6251, 'learning_rate': 4.844568949936743e-06, 'epoch': 1.68}
{'loss': 0.5869, 'learning_rate': 4.841857943249593e-06, 'epoch': 1.68}
{'loss': 0.5483, 'learning_rate': 4.839146936562443e-06, 'epoch': 1.68}
{'loss': 1.0304, 'learning_rate': 4.8364359298752935e-06, 'epoch': 1.68}
{'loss': 0.703, 'learning_rate': 4.833724923188144e-06, 'epoch': 1.68}
{'loss': 0.7922, 'learning_rate': 4.831013916500994e-06, 'epoch': 1.68}
{'loss': 0.7747, 'learning_rate': 4.828302909813844e-06, 'epoch': 1.68}
{'loss': 1.3807, 'learning_rate': 4.825591903126695e-06, 'epoch': 1.68}
{'loss': 0.2207, 'learning_rate': 4.822880896439544e-06, 'epoch': 1.68}
{'loss': 0.9782, 'learning_rate': 4.820169889752395e-06, 'epoch': 1.68}
{'loss': 0.6662, 'learning_rate': 4.8174588830652445e-06, 'epoch': 1.68}
{'loss': 0.3307, 'learning_rate': 4.8147478763780955e-06, 'epoch': 1.68}
{'loss': 0.3111, 'learning_rate': 4.812036869690945e-06, 'epoch': 1.68}
{'loss': 1.012, 'learning_rate': 4.809325863003796e-06, 'epoch': 1.68}
{'loss': 0.6079, 'learning_rate': 4.806614856316645e-06, 'epoch': 1.68}
{'loss': 0.2598, 'learning_rate': 4.803903849629496e-06, 'epoch': 1.68}
{'loss': 0.4644, 'learning_rate': 4.801192842942346e-06, 'epoch': 1.68}
{'loss': 0.5839, 'learning_rate': 4.798481836255196e-06, 'epoch': 1.68}
{'loss': 0.409, 'learning_rate': 4.795770829568046e-06, 'epoch': 1.68}
{'loss': 0.5416, 'learning_rate': 4.7930598228808965e-06, 'epoch': 1.68}
{'loss': 0.9995, 'learning_rate': 4.790348816193747e-06, 'epoch': 1.68}
{'loss': 0.619, 'learning_rate': 4.787637809506597e-06, 'epoch': 1.68}
{'loss': 0.6852, 'learning_rate': 4.784926802819447e-06, 'epoch': 1.68}
{'loss': 0.5877, 'learning_rate': 4.782215796132297e-06, 'epoch': 1.68}
{'loss': 0.5699, 'learning_rate': 4.779504789445147e-06, 'epoch': 1.68}
{'loss': 1.0485, 'learning_rate': 4.776793782757997e-06, 'epoch': 1.68}
{'loss': 0.6142, 'learning_rate': 4.7740827760708475e-06, 'epoch': 1.68}
{'loss': 0.4487, 'learning_rate': 4.7713717693836985e-06, 'epoch': 1.68}
{'loss': 1.0232, 'learning_rate': 4.768660762696548e-06, 'epoch': 1.68}
{'loss': 0.6001, 'learning_rate': 4.765949756009399e-06, 'epoch': 1.68}
{'loss': 0.8298, 'learning_rate': 4.763238749322248e-06, 'epoch': 1.68}
{'loss': 0.5678, 'learning_rate': 4.760527742635099e-06, 'epoch': 1.68}
{'loss': 0.5596, 'learning_rate': 4.757816735947948e-06, 'epoch': 1.68}
{'loss': 1.1565, 'learning_rate': 4.755105729260799e-06, 'epoch': 1.68}
{'loss': 0.9954, 'learning_rate': 4.7523947225736485e-06, 'epoch': 1.68}
{'loss': 0.5722, 'learning_rate': 4.7496837158864995e-06, 'epoch': 1.68}
{'loss': 0.5954, 'learning_rate': 4.746972709199349e-06, 'epoch': 1.68}
{'loss': 0.2294, 'learning_rate': 4.7442617025122e-06, 'epoch': 1.68}
{'loss': 0.71, 'learning_rate': 4.74155069582505e-06, 'epoch': 1.68}
{'loss': 0.3191, 'learning_rate': 4.7388396891379e-06, 'epoch': 1.68}
{'loss': 0.4105, 'learning_rate': 4.73612868245075e-06, 'epoch': 1.68}
{'loss': 0.6767, 'learning_rate': 4.7334176757636e-06, 'epoch': 1.68}
{'loss': 0.8348, 'learning_rate': 4.7307066690764505e-06, 'epoch': 1.68}
{'loss': 0.4041, 'learning_rate': 4.727995662389301e-06, 'epoch': 1.68}
{'loss': 0.3117, 'learning_rate': 4.725284655702151e-06, 'epoch': 1.68}
{'loss': 0.5348, 'learning_rate': 4.722573649015001e-06, 'epoch': 1.69}
{'loss': 0.7442, 'learning_rate': 4.719862642327851e-06, 'epoch': 1.69}
{'loss': 1.0833, 'learning_rate': 4.717151635640702e-06, 'epoch': 1.69}
{'loss': 1.1485, 'learning_rate': 4.714440628953551e-06, 'epoch': 1.69}
{'loss': 1.9149, 'learning_rate': 4.711729622266402e-06, 'epoch': 1.69}
{'loss': 0.8764, 'learning_rate': 4.7090186155792515e-06, 'epoch': 1.69}
{'loss': 0.5323, 'learning_rate': 4.7063076088921025e-06, 'epoch': 1.69}
{'loss': 0.9726, 'learning_rate': 4.703596602204952e-06, 'epoch': 1.69}
{'loss': 0.5225, 'learning_rate': 4.700885595517803e-06, 'epoch': 1.69}
{'loss': 0.3363, 'learning_rate': 4.698174588830652e-06, 'epoch': 1.69}
{'loss': 0.7363, 'learning_rate': 4.695463582143503e-06, 'epoch': 1.69}
{'loss': 0.584, 'learning_rate': 4.692752575456352e-06, 'epoch': 1.69}
{'loss': 0.74, 'learning_rate': 4.690041568769203e-06, 'epoch': 1.69}
{'loss': 1.2045, 'learning_rate': 4.6873305620820535e-06, 'epoch': 1.69}
{'loss': 0.6439, 'learning_rate': 4.684619555394904e-06, 'epoch': 1.69}
{'loss': 0.3403, 'learning_rate': 4.681908548707754e-06, 'epoch': 1.69}
{'loss': 0.4441, 'learning_rate': 4.679197542020604e-06, 'epoch': 1.69}
{'loss': 1.1893, 'learning_rate': 4.676486535333454e-06, 'epoch': 1.69}
{'loss': 0.4219, 'learning_rate': 4.673775528646304e-06, 'epoch': 1.69}
{'loss': 0.8455, 'learning_rate': 4.671064521959154e-06, 'epoch': 1.69}
{'loss': 0.698, 'learning_rate': 4.668353515272004e-06, 'epoch': 1.69}
{'loss': 1.3332, 'learning_rate': 4.6656425085848545e-06, 'epoch': 1.69}
{'loss': 0.8969, 'learning_rate': 4.662931501897705e-06, 'epoch': 1.69}
{'loss': 0.5274, 'learning_rate': 4.660220495210555e-06, 'epoch': 1.69}
{'loss': 0.5607, 'learning_rate': 4.657509488523406e-06, 'epoch': 1.69}
{'loss': 0.5054, 'learning_rate': 4.654798481836255e-06, 'epoch': 1.69}
{'loss': 0.5613, 'learning_rate': 4.652087475149106e-06, 'epoch': 1.69}
{'loss': 0.6604, 'learning_rate': 4.649376468461955e-06, 'epoch': 1.69}
{'loss': 0.4759, 'learning_rate': 4.646665461774806e-06, 'epoch': 1.69}
{'loss': 0.8697, 'learning_rate': 4.643954455087656e-06, 'epoch': 1.69}

 85%|████████▍ | 9354/11066 [34:16<06:17,  4.54it/s]
 85%|████████▍ | 9355/11066 [34:16<06:13,  4.58it/s]
                                                    

 85%|████████▍ | 9355/11066 [34:16<06:13,  4.58it/s]
 85%|████████▍ | 9356/11066 [34:16<06:16,  4.54it/s]
                                                    

 85%|████████▍ | 9356/11066 [34:16<06:16,  4.54it/s]
 85%|████████▍ | 9357/11066 [34:16<06:15,  4.56it/s]
                                                    

 85%|████████▍ | 9357/11066 [34:16<06:15,  4.56it/s]
 85%|████████▍ | 9358/11066 [34:17<06:12,  4.59it/s]
                                                    

 85%|████████▍ | 9358/11066 [34:17<06:12,  4.59it/s]
 85%|████████▍ | 9359/11066 [34:17<06:10,  4.61it/s]
                                                    

 85%|████████▍ | 9359/11066 [34:17<06:10,  4.61it/s]
 85%|████████▍ | 9360/11066 [34:17<06:10,  4.60it/s]
                                                    

 85%|████████▍ | 9360/11066 [34:17<06:10,  4.60it/s]
 85%|████████▍ | 9361/11066 [34:17<06:08,  4.63it/s]
                                                    

 85%|████████▍ | 9361/11066 [34:17<06:08,  4.63it/s]
 85%|████████▍ | 9362/11066 [34:18<06:10,  4.60it/s]
                                                    

 85%|████████▍ | 9362/11066 [34:18<06:10,  4.60it/s]
 85%|████████▍ | 9363/11066 [34:18<06:07,  4.63it/s]
                                                    

 85%|████████▍ | 9363/11066 [34:18<06:07,  4.63it/s]
 85%|████████▍ | 9364/11066 [34:18<06:11,  4.58it/s]
                                                    

 85%|████████▍ | 9364/11066 [34:18<06:11,  4.58it/s]
 85%|████████▍ | 9365/11066 [34:18<06:15,  4.54it/s]
                                                    

 85%|████████▍ | 9365/11066 [34:18<06:15,  4.54it/s]
 85%|████████▍ | 9366/11066 [34:18<06:16,  4.51it/s]
                                                    

 85%|████████▍ | 9366/11066 [34:18<06:16,  4.51it/s]
 85%|████████▍ | 9367/11066 [34:19<06:16,  4.51it/s]
                                                    

 85%|████████▍ | 9367/11066 [34:19<06:16,  4.51it/s]
 85%|████████▍ | 9368/11066 [34:19<06:17,  4.50it/s]
                                                    

 85%|████████▍ | 9368/11066 [34:19<06:17,  4.50it/s]
 85%|████████▍ | 9369/11066 [34:19<06:11,  4.57it/s]
                                                    

 85%|████████▍ | 9369/11066 [34:19<06:11,  4.57it/s]
 85%|████████▍ | 9370/11066 [34:19<06:09,  4.58it/s]
                                                    

 85%|████████▍ | 9370/11066 [34:19<06:09,  4.58it/s]
 85%|████████▍ | 9371/11066 [34:20<06:10,  4.57it/s]
                                                    

 85%|████████▍ | 9371/11066 [34:20<06:10,  4.57it/s]
 85%|████████▍ | 9372/11066 [34:20<06:11,  4.56it/s]
                                                    

 85%|████████▍ | 9372/11066 [34:20<06:11,  4.56it/s]
 85%|████████▍ | 9373/11066 [34:20<06:09,  4.58it/s]
                                                    

 85%|████████▍ | 9373/11066 [34:20<06:09,  4.58it/s]
 85%|████████▍ | 9374/11066 [34:20<06:05,  4.63it/s]
                                                    

 85%|████████▍ | 9374/11066 [34:20<06:05,  4.63it/s]
 85%|████████▍ | 9375/11066 [34:20<06:03,  4.65it/s]
                                                    

 85%|████████▍ | 9375/11066 [34:20<06:03,  4.65it/s]
 85%|████████▍ | 9376/11066 [34:21<06:05,  4.62it/s]
                                                    

 85%|████████▍ | 9376/11066 [34:21<06:05,  4.62it/s]
 85%|████████▍ | 9377/11066 [34:21<06:05,  4.63it/s]
                                                    

 85%|████████▍ | 9377/11066 [34:21<06:05,  4.63it/s]
 85%|████████▍ | 9378/11066 [34:21<06:01,  4.66it/s]
                                                    

 85%|████████▍ | 9378/11066 [34:21<06:01,  4.66it/s]
 85%|████████▍ | 9379/11066 [34:21<06:06,  4.61it/s]
                                                    

 85%|████████▍ | 9379/11066 [34:21<06:06,  4.61it/s]
 85%|████████▍ | 9380/11066 [34:22<06:05,  4.62it/s]
                                                    

 85%|████████▍ | 9380/11066 [34:22<06:05,  4.62it/s]
 85%|████████▍ | 9381/11066 [34:22<06:05,  4.61it/s]
                                                    

 85%|████████▍ | 9381/11066 [34:22<06:05,  4.61it/s]
 85%|████████▍ | 9382/11066 [34:22<06:04,  4.63it/s]
                                                    

 85%|████████▍ | 9382/11066 [34:22<06:04,  4.63it/s]
 85%|████████▍ | 9383/11066 [34:22<06:07,  4.59it/s]
                                                    

 85%|████████▍ | 9383/11066 [34:22<06:07,  4.59it/s]
 85%|████████▍ | 9384/11066 [34:22<06:04,  4.62it/s]
                                                    

 85%|████████▍ | 9384/11066 [34:22<06:04,  4.62it/s]
 85%|████████▍ | 9385/11066 [34:23<06:07,  4.58it/s]
                                                    

 85%|████████▍ | 9385/11066 [34:23<06:07,  4.58it/s]
 85%|████████▍ | 9386/11066 [34:23<06:10,  4.54it/s]
                                                    

 85%|████████▍ | 9386/11066 [34:23<06:10,  4.54it/s]
 85%|████████▍ | 9387/11066 [34:23<06:08,  4.56it/s]
                                                    

 85%|████████▍ | 9387/11066 [34:23<06:08,  4.56it/s]
 85%|████████▍ | 9388/11066 [34:23<06:05,  4.60it/s]
                                                    

 85%|████████▍ | 9388/11066 [34:23<06:05,  4.60it/s]
 85%|████████▍ | 9389/11066 [34:23<06:05,  4.59it/s]
                                                    

 85%|████████▍ | 9389/11066 [34:23<06:05,  4.59it/s]
 85%|████████▍ | 9390/11066 [34:24<06:02,  4.62it/s]
                                                    

 85%|████████▍ | 9390/11066 [34:24<06:02,  4.62it/s]
 85%|████████▍ | 9391/11066 [34:24<06:01,  4.64it/s]
                                                    

 85%|████████▍ | 9391/11066 [34:24<06:01,  4.64it/s]
 85%|████████▍ | 9392/11066 [34:24<06:06,  4.57it/s]
                                                    

 85%|████████▍ | 9392/11066 [34:24<06:06,  4.57it/s]
 85%|████████▍ | 9393/11066 [34:24<06:06,  4.57it/s]
                                                    

 85%|████████▍ | 9393/11066 [34:24<06:06,  4.57it/s]
 85%|████████▍ | 9394/11066 [34:25<06:09,  4.53it/s]
                                                    

 85%|████████▍ | 9394/11066 [34:25<06:09,  4.53it/s]
 85%|████████▍ | 9395/11066 [34:25<06:10,  4.51it/s]
                                                    

 85%|████████▍ | 9395/11066 [34:25<06:10,  4.51it/s]
 85%|████████▍ | 9396/11066 [34:25<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9396/11066 [34:25<06:10,  4.50it/s]
 85%|████████▍ | 9397/11066 [34:25<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9397/11066 [34:25<06:10,  4.50it/s]
 85%|████████▍ | 9398/11066 [34:25<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9398/11066 [34:25<06:10,  4.50it/s]
 85%|████████▍ | 9399/11066 [34:26<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9399/11066 [34:26<06:10,  4.50it/s]
 85%|████████▍ | 9400/11066 [34:26<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9400/11066 [34:26<06:10,  4.50it/s]
 85%|████████▍ | 9401/11066 [34:26<06:10,  4.50it/s]
                                                    

 85%|████████▍ | 9401/11066 [34:26<06:10,  4.50it/s]
 85%|████████▍ | 9402/11066 [34:26<06:09,  4.50it/s]
                                                    

 85%|████████▍ | 9402/11066 [34:26<06:09,  4.50it/s]
 85%|████████▍ | 9403/11066 [34:27<06:09,  4.50it/s]
                                                    

 85%|████████▍ | 9403/11066 [34:27<06:09,  4.50it/s]
 85%|████████▍ | 9404/11066 [34:27<06:09,  4.50it/s]
                                                    

 85%|████████▍ | 9404/11066 [34:27<06:09,  4.50it/s]
 85%|████████▍ | 9405/11066 [34:27<06:02,  4.58it/s]
                                                    

 85%|████████▍ | 9405/11066 [34:27<06:02,  4.58it/s]
 85%|████████▍ | 9406/11066 [34:27<06:06,  4.53it/s]
                                                    

 85%|████████▍ | 9406/11066 [34:27<06:06,  4.53it/s]
 85%|████████▌ | 9407/11066 [34:27<06:07,  4.52it/s]
                                                    

 85%|████████▌ | 9407/11066 [34:27<06:07,  4.52it/s]
 85%|████████▌ | 9408/11066 [34:28<06:07,  4.52it/s]
                                                    

 85%|████████▌ | 9408/11066 [34:28<06:07,  4.52it/s]
 85%|████████▌ | 9409/11066 [34:28<06:07,  4.51it/s]
                                                    

 85%|████████▌ | 9409/11066 [34:28<06:07,  4.51it/s]
 85%|████████▌ | 9410/11066 [34:28<06:07,  4.51it/s]
                                                    

 85%|████████▌ | 9410/11066 [34:28<06:07,  4.51it/s]
 85%|████████▌ | 9411/11066 [34:28<06:07,  4.50it/s]
                                                    

 85%|████████▌ | 9411/11066 [34:28<06:07,  4.50it/s]
 85%|████████▌ | 9412/11066 [34:29<06:12,  4.44it/s]
                                                    

 85%|████████▌ | 9412/11066 [34:29<06:12,  4.44it/s]
 85%|████████▌ | 9413/11066 [34:29<06:08,  4.49it/s]
                                                    

 85%|████████▌ | 9413/11066 [34:29<06:08,  4.49it/s]
 85%|████████▌ | 9414/11066 [34:29<06:04,  4.54it/s]
                                                    

 85%|████████▌ | 9414/11066 [34:29<06:04,  4.54it/s]
 85%|████████▌ | 9415/11066 [34:29<06:05,  4.52it/s]
                                                    

 85%|████████▌ | 9415/11066 [34:29<06:05,  4.52it/s]
 85%|████████▌ | 9416/11066 [34:29<06:02,  4.55it/s]
                                                    

 85%|████████▌ | 9416/11066 [34:29<06:02,  4.55it/s]
 85%|████████▌ | 9417/11066 [34:30<05:59,  4.59it/s]
                                                    

 85%|████████▌ | 9417/11066 [34:30<05:59,  4.59it/s]
 85%|████████▌ | 9418/11066 [34:30<05:59,  4.58it/s]
                                                    

 85%|████████▌ | 9418/11066 [34:30<05:59,  4.58it/s]
 85%|████████▌ | 9419/11066 [34:30<05:57,  4.61it/s]
                                                    

 85%|████████▌ | 9419/11066 [34:30<05:57,  4.61it/s]
 85%|████████▌ | 9420/11066 [34:30<05:55,  4.63it/s]
                                                    

 85%|████████▌ | 9420/11066 [34:30<05:55,  4.63it/s]
 85%|████████▌ | 9421/11066 [34:31<05:56,  4.62it/s]
                                                    

 85%|████████▌ | 9421/11066 [34:31<05:56,  4.62it/s]
 85%|████████▌ | 9422/11066 [34:31<05:59,  4.58it/s]
                                                    

 85%|████████▌ | 9422/11066 [34:31<05:59,  4.58it/s]
 85%|████████▌ | 9423/11066 [34:31<05:58,  4.58it/s]
                                                    

 85%|████████▌ | 9423/11066 [34:31<05:58,  4.58it/s]
 85%|████████▌ | 9424/11066 [34:31<05:57,  4.59it/s]
                                                    

 85%|████████▌ | 9424/11066 [34:31<05:57,  4.59it/s]
 85%|████████▌ | 9425/11066 [34:31<05:59,  4.56it/s]
                                                    

 85%|████████▌ | 9425/11066 [34:31<05:59,  4.56it/s]
 85%|████████▌ | 9426/11066 [34:32<06:00,  4.54it/s]
                                                    

 85%|████████▌ | 9426/11066 [34:32<06:00,  4.54it/s]
 85%|████████▌ | 9427/11066 [34:32<06:02,  4.53it/s]
                                                    

 85%|████████▌ | 9427/11066 [34:32<06:02,  4.53it/s]
 85%|████████▌ | 9428/11066 [34:32<05:59,  4.56it/s]
                                                    

 85%|████████▌ | 9428/11066 [34:32<05:59,  4.56it/s]
 85%|████████▌ | 9429/11066 [34:32<05:56,  4.59it/s]
                                                    

 85%|████████▌ | 9429/11066 [34:32<05:56,  4.59it/s]
 85%|████████▌ | 9430/11066 [34:32<05:56,  4.59it/s]
                                                    

 85%|████████▌ | 9430/11066 [34:32<05:56,  4.59it/s]
 85%|████████▌ | 9431/11066 [34:33<05:59,  4.55it/s]
                                                    

 85%|████████▌ | 9431/11066 [34:33<05:59,  4.55it/s]
 85%|████████▌ | 9432/11066 [34:33<06:00,  4.53it/s]
                                                    

 85%|████████▌ | 9432/11066 [34:33<06:00,  4.53it/s]
 85%|████████▌ | 9433/11066 [34:33<06:03,  4.50it/s]
                                                    

 85%|████████▌ | 9433/11066 [34:33<06:03,  4.50it/s]
 85%|████████▌ | 9434/11066 [34:33<06:03,  4.49it/s]
                                                    

 85%|████████▌ | 9434/11066 [34:33<06:03,  4.49it/s]
 85%|████████▌ | 9435/11066 [34:34<06:03,  4.49it/s]
                                                    

 85%|████████▌ | 9435/11066 [34:34<06:03,  4.49it/s]
 85%|████████▌ | 9436/11066 [34:34<06:00,  4.52it/s]
                                                    

 85%|████████▌ | 9436/11066 [34:34<06:00,  4.52it/s]
 85%|████████▌ | 9437/11066 [34:34<06:01,  4.51it/s]
                                                    

 85%|████████▌ | 9437/11066 [34:34<06:01,  4.51it/s]
 85%|████████▌ | 9438/11066 [34:34<05:59,  4.53it/s]
                                                    

 85%|████████▌ | 9438/11066 [34:34<05:59,  4.53it/s]
 85%|████████▌ | 9439/11066 [34:34<06:01,  4.50it/s]
                                                    

 85%|████████▌ | 9439/11066 [34:34<06:01,  4.50it/s]
 85%|████████▌ | 9440/11066 [34:35<06:02,  4.49it/s]
                                                    

 85%|████████▌ | 9440/11066 [34:35<06:02,  4.49it/s]
 85%|████████▌ | 9441/11066 [34:35<06:02,  4.49it/s]
                                                    

 85%|████████▌ | 9441/11066 [34:35<06:02,  4.49it/s]
 85%|████████▌ | 9442/11066 [34:35<06:01,  4.49it/s]
                                                    

 85%|████████▌ | 9442/11066 [34:35<06:01,  4.49it/s]
 85%|████████▌ | 9443/11066 [34:35<06:01,  4.49it/s]
                                                    

 85%|████████▌ | 9443/11066 [34:35<06:01,  4.49it/s]
 85%|████████▌ | 9444/11066 [34:36<06:01,  4.49it/s]
                                                    

 85%|████████▌ | 9444/11066 [34:36<06:01,  4.49it/s]
 85%|████████▌ | 9445/11066 [34:36<06:00,  4.49it/s]
                                                    

 85%|████████▌ | 9445/11066 [34:36<06:00,  4.49it/s]
 85%|████████▌ | 9446/11066 [34:36<06:00,  4.50it/s]
                                                    

 85%|████████▌ | 9446/11066 [34:36<06:00,  4.50it/s]
 85%|████████▌ | 9447/11066 [34:36<06:00,  4.49it/s]
                                                    

 85%|████████▌ | 9447/11066 [34:36<06:00,  4.49it/s]
 85%|████████▌ | 9448/11066 [34:36<05:59,  4.50it/s]
                                                    

 85%|████████▌ | 9448/11066 [34:36<05:59,  4.50it/s]
 85%|████████▌ | 9449/11066 [34:37<05:58,  4.51it/s]
                                                    

 85%|████████▌ | 9449/11066 [34:37<05:58,  4.51it/s]
 85%|████████▌ | 9450/11066 [34:37<05:53,  4.57it/s]
                                                    

 85%|████████▌ | 9450/11066 [34:37<05:53,  4.57it/s]
 85%|████████▌ | 9451/11066 [34:37<05:52,  4.58it/s]
                                                    

 85%|████████▌ | 9451/11066 [34:37<05:52,  4.58it/s]
 85%|████████▌ | 9452/11066 [34:37<05:50,  4.60it/s]
                                                    

 85%|████████▌ | 9452/11066 [34:37<05:50,  4.60it/s]
 85%|████████▌ | 9453/11066 [34:38<05:52,  4.58it/s]
                                                    

 85%|████████▌ | 9453/11066 [34:38<05:52,  4.58it/s]
 85%|████████▌ | 9454/11066 [34:38<05:55,  4.54it/s]
                                                    

 85%|████████▌ | 9454/11066 [34:38<05:55,  4.54it/s]
 85%|████████▌ | 9455/11066 [34:38<05:54,  4.55it/s]
                                                    

 85%|████████▌ | 9455/11066 [34:38<05:54,  4.55it/s]
 85%|████████▌ | 9456/11066 [34:38<05:56,  4.51it/s]
                                                    

 85%|████████▌ | 9456/11066 [34:38<05:56,  4.51it/s]
 85%|████████▌ | 9457/11066 [34:38<05:57,  4.50it/s]
                                                    

 85%|████████▌ | 9457/11066 [34:38<05:57,  4.50it/s]
 85%|████████▌ | 9458/11066 [34:39<05:57,  4.49it/s]
                                                    

 85%|████████▌ | 9458/11066 [34:39<05:57,  4.49it/s]
 85%|████████▌ | 9459/11066 [34:39<05:57,  4.49it/s]
                                                    

 85%|████████▌ | 9459/11066 [34:39<05:57,  4.49it/s]
 85%|████████▌ | 9460/11066 [34:39<05:57,  4.49it/s]
                                                    

 85%|████████▌ | 9460/11066 [34:39<05:57,  4.49it/s]
 85%|████████▌ | 9461/11066 [34:39<05:56,  4.50it/s]
                                                    

 85%|████████▌ | 9461/11066 [34:39<05:56,  4.50it/s]
 86%|████████▌ | 9462/11066 [34:40<05:56,  4.50it/s]
                                                    

 86%|████████▌ | 9462/11066 [34:40<05:56,  4.50it/s]
 86%|████████▌ | 9463/11066 [34:40<05:55,  4.50it/s]
                                                    

 86%|████████▌ | 9463/11066 [34:40<05:55,  4.50it/s]
 86%|████████▌ | 9464/11066 [34:40<05:55,  4.50it/s]
                                                    

 86%|████████▌ | 9464/11066 [34:40<05:55,  4.50it/s]
 86%|████████▌ | 9465/11066 [34:40<05:55,  4.50it/s]
                                                    

 86%|████████▌ | 9465/11066 [34:40<05:55,  4.50it/s]
 86%|████████▌ | 9466/11066 [34:40<05:55,  4.50it/s]
                                                    

 86%|████████▌ | 9466/11066 [34:40<05:55,  4.50it/s]
 86%|████████▌ | 9467/11066 [34:41<05:55,  4.50it/s]
                                                    

 86%|████████▌ | 9467/11066 [34:41<05:55,  4.50it/s]
 86%|████████▌ | 9468/11066 [34:41<05:54,  4.50it/s]
                                                    
{'loss': 0.7276, 'learning_rate': 4.641243448400507e-06, 'epoch': 1.69}
{'loss': 0.4265, 'learning_rate': 4.638532441713356e-06, 'epoch': 1.69}
{'loss': 0.8218, 'learning_rate': 4.635821435026207e-06, 'epoch': 1.69}
{'loss': 0.4626, 'learning_rate': 4.633110428339056e-06, 'epoch': 1.69}
{'loss': 1.165, 'learning_rate': 4.630399421651907e-06, 'epoch': 1.69}
{'loss': 0.5941, 'learning_rate': 4.627688414964757e-06, 'epoch': 1.69}
{'loss': 0.7853, 'learning_rate': 4.624977408277607e-06, 'epoch': 1.69}
{'loss': 0.4446, 'learning_rate': 4.6222664015904575e-06, 'epoch': 1.69}
{'loss': 0.933, 'learning_rate': 4.619555394903308e-06, 'epoch': 1.69}
{'loss': 0.5116, 'learning_rate': 4.616844388216158e-06, 'epoch': 1.69}
{'loss': 0.4605, 'learning_rate': 4.614133381529008e-06, 'epoch': 1.69}
{'loss': 0.5189, 'learning_rate': 4.611422374841858e-06, 'epoch': 1.69}
{'loss': 1.1852, 'learning_rate': 4.608711368154708e-06, 'epoch': 1.69}
{'loss': 1.4361, 'learning_rate': 4.606000361467558e-06, 'epoch': 1.69}
{'loss': 0.8671, 'learning_rate': 4.603289354780409e-06, 'epoch': 1.69}
{'loss': 1.4349, 'learning_rate': 4.600578348093259e-06, 'epoch': 1.69}
{'loss': 0.9449, 'learning_rate': 4.59786734140611e-06, 'epoch': 1.69}
{'loss': 0.3471, 'learning_rate': 4.595156334718959e-06, 'epoch': 1.69}
{'loss': 0.3512, 'learning_rate': 4.59244532803181e-06, 'epoch': 1.69}
{'loss': 0.8349, 'learning_rate': 4.589734321344659e-06, 'epoch': 1.69}
{'loss': 0.2901, 'learning_rate': 4.58702331465751e-06, 'epoch': 1.69}
{'loss': 1.9117, 'learning_rate': 4.584312307970359e-06, 'epoch': 1.69}
{'loss': 0.4059, 'learning_rate': 4.58160130128321e-06, 'epoch': 1.69}
{'loss': 1.1586, 'learning_rate': 4.57889029459606e-06, 'epoch': 1.69}
{'loss': 0.7952, 'learning_rate': 4.576179287908911e-06, 'epoch': 1.69}
{'loss': 1.3387, 'learning_rate': 4.573468281221761e-06, 'epoch': 1.7}
{'loss': 0.7304, 'learning_rate': 4.570757274534611e-06, 'epoch': 1.7}
{'loss': 0.6082, 'learning_rate': 4.568046267847461e-06, 'epoch': 1.7}
{'loss': 1.2664, 'learning_rate': 4.565335261160311e-06, 'epoch': 1.7}
{'loss': 0.5841, 'learning_rate': 4.562624254473161e-06, 'epoch': 1.7}
{'loss': 0.6167, 'learning_rate': 4.5599132477860115e-06, 'epoch': 1.7}
{'loss': 0.5878, 'learning_rate': 4.557202241098862e-06, 'epoch': 1.7}
{'loss': 0.775, 'learning_rate': 4.554491234411712e-06, 'epoch': 1.7}
{'loss': 0.6783, 'learning_rate': 4.551780227724562e-06, 'epoch': 1.7}
{'loss': 1.2785, 'learning_rate': 4.549069221037412e-06, 'epoch': 1.7}
{'loss': 0.3626, 'learning_rate': 4.546358214350262e-06, 'epoch': 1.7}
{'loss': 0.5547, 'learning_rate': 4.543647207663113e-06, 'epoch': 1.7}
{'loss': 0.829, 'learning_rate': 4.540936200975962e-06, 'epoch': 1.7}
{'loss': 0.4338, 'learning_rate': 4.538225194288813e-06, 'epoch': 1.7}
{'loss': 0.7174, 'learning_rate': 4.535514187601663e-06, 'epoch': 1.7}
{'loss': 0.4823, 'learning_rate': 4.532803180914513e-06, 'epoch': 1.7}
{'loss': 0.5559, 'learning_rate': 4.530092174227363e-06, 'epoch': 1.7}
{'loss': 0.3606, 'learning_rate': 4.527381167540213e-06, 'epoch': 1.7}
{'loss': 0.659, 'learning_rate': 4.524670160853063e-06, 'epoch': 1.7}
{'loss': 0.9755, 'learning_rate': 4.521959154165913e-06, 'epoch': 1.7}
{'loss': 0.914, 'learning_rate': 4.519248147478764e-06, 'epoch': 1.7}
{'loss': 0.4922, 'learning_rate': 4.516537140791614e-06, 'epoch': 1.7}
{'loss': 0.4213, 'learning_rate': 4.513826134104465e-06, 'epoch': 1.7}
{'loss': 0.6501, 'learning_rate': 4.511115127417314e-06, 'epoch': 1.7}
{'loss': 0.3864, 'learning_rate': 4.508404120730165e-06, 'epoch': 1.7}
{'loss': 0.3071, 'learning_rate': 4.505693114043014e-06, 'epoch': 1.7}
{'loss': 0.5461, 'learning_rate': 4.502982107355865e-06, 'epoch': 1.7}
{'loss': 0.3507, 'learning_rate': 4.500271100668714e-06, 'epoch': 1.7}
{'loss': 1.2569, 'learning_rate': 4.497560093981565e-06, 'epoch': 1.7}
{'loss': 0.3066, 'learning_rate': 4.494849087294415e-06, 'epoch': 1.7}
{'loss': 0.5371, 'learning_rate': 4.492138080607266e-06, 'epoch': 1.7}
{'loss': 1.3385, 'learning_rate': 4.489427073920116e-06, 'epoch': 1.7}
{'loss': 1.0904, 'learning_rate': 4.486716067232966e-06, 'epoch': 1.7}
{'loss': 0.3749, 'learning_rate': 4.484005060545816e-06, 'epoch': 1.7}
{'loss': 1.3792, 'learning_rate': 4.481294053858666e-06, 'epoch': 1.7}
{'loss': 0.9067, 'learning_rate': 4.478583047171516e-06, 'epoch': 1.7}
{'loss': 0.7861, 'learning_rate': 4.4758720404843665e-06, 'epoch': 1.7}
{'loss': 0.4449, 'learning_rate': 4.473161033797217e-06, 'epoch': 1.7}
{'loss': 0.9723, 'learning_rate': 4.470450027110067e-06, 'epoch': 1.7}
{'loss': 0.7365, 'learning_rate': 4.467739020422917e-06, 'epoch': 1.7}
{'loss': 0.8308, 'learning_rate': 4.465028013735767e-06, 'epoch': 1.7}
{'loss': 1.1629, 'learning_rate': 4.462317007048617e-06, 'epoch': 1.7}
{'loss': 0.7567, 'learning_rate': 4.459606000361468e-06, 'epoch': 1.7}
{'loss': 0.4649, 'learning_rate': 4.456894993674317e-06, 'epoch': 1.7}
{'loss': 0.6058, 'learning_rate': 4.454183986987168e-06, 'epoch': 1.7}
{'loss': 0.3447, 'learning_rate': 4.451472980300018e-06, 'epoch': 1.7}
{'loss': 0.1818, 'learning_rate': 4.448761973612869e-06, 'epoch': 1.7}
{'loss': 0.7973, 'learning_rate': 4.446050966925718e-06, 'epoch': 1.7}
{'loss': 0.8365, 'learning_rate': 4.443339960238569e-06, 'epoch': 1.7}
{'loss': 0.4018, 'learning_rate': 4.440628953551418e-06, 'epoch': 1.7}
{'loss': 0.5036, 'learning_rate': 4.437917946864269e-06, 'epoch': 1.7}
{'loss': 0.9588, 'learning_rate': 4.435206940177119e-06, 'epoch': 1.7}
{'loss': 0.4034, 'learning_rate': 4.4324959334899695e-06, 'epoch': 1.7}
{'loss': 0.3665, 'learning_rate': 4.42978492680282e-06, 'epoch': 1.7}
{'loss': 0.7348, 'learning_rate': 4.42707392011567e-06, 'epoch': 1.7}
{'loss': 0.6643, 'learning_rate': 4.42436291342852e-06, 'epoch': 1.71}
{'loss': 1.2816, 'learning_rate': 4.42165190674137e-06, 'epoch': 1.71}
{'loss': 0.5374, 'learning_rate': 4.41894090005422e-06, 'epoch': 1.71}
{'loss': 0.336, 'learning_rate': 4.41622989336707e-06, 'epoch': 1.71}
{'loss': 0.7675, 'learning_rate': 4.41351888667992e-06, 'epoch': 1.71}
{'loss': 0.7727, 'learning_rate': 4.4108078799927705e-06, 'epoch': 1.71}
{'loss': 0.4359, 'learning_rate': 4.408096873305621e-06, 'epoch': 1.71}
{'loss': 0.6603, 'learning_rate': 4.405385866618472e-06, 'epoch': 1.71}
{'loss': 0.7595, 'learning_rate': 4.402674859931321e-06, 'epoch': 1.71}
{'loss': 0.9059, 'learning_rate': 4.399963853244172e-06, 'epoch': 1.71}
{'loss': 0.4436, 'learning_rate': 4.397252846557021e-06, 'epoch': 1.71}
{'loss': 0.6836, 'learning_rate': 4.394541839869872e-06, 'epoch': 1.71}
{'loss': 0.8947, 'learning_rate': 4.3918308331827215e-06, 'epoch': 1.71}
{'loss': 0.4465, 'learning_rate': 4.3891198264955725e-06, 'epoch': 1.71}
{'loss': 0.8442, 'learning_rate': 4.386408819808422e-06, 'epoch': 1.71}
{'loss': 0.9494, 'learning_rate': 4.383697813121273e-06, 'epoch': 1.71}
{'loss': 0.377, 'learning_rate': 4.380986806434122e-06, 'epoch': 1.71}
{'loss': 0.4394, 'learning_rate': 4.378275799746973e-06, 'epoch': 1.71}
{'loss': 0.5691, 'learning_rate': 4.375564793059823e-06, 'epoch': 1.71}
{'loss': 0.7425, 'learning_rate': 4.372853786372673e-06, 'epoch': 1.71}
{'loss': 0.449, 'learning_rate': 4.370142779685523e-06, 'epoch': 1.71}
{'loss': 0.8619, 'learning_rate': 4.3674317729983735e-06, 'epoch': 1.71}
{'loss': 0.4276, 'learning_rate': 4.364720766311224e-06, 'epoch': 1.71}
{'loss': 0.9992, 'learning_rate': 4.362009759624074e-06, 'epoch': 1.71}
{'loss': 0.5713, 'learning_rate': 4.359298752936924e-06, 'epoch': 1.71}
{'loss': 0.5813, 'learning_rate': 4.356587746249774e-06, 'epoch': 1.71}
{'loss': 0.8345, 'learning_rate': 4.353876739562624e-06, 'epoch': 1.71}
{'loss': 0.883, 'learning_rate': 4.351165732875474e-06, 'epoch': 1.71}
{'loss': 0.6273, 'learning_rate': 4.3484547261883245e-06, 'epoch': 1.71}
{'loss': 0.5962, 'learning_rate': 4.3457437195011755e-06, 'epoch': 1.71}
{'loss': 0.4972, 'learning_rate': 4.343032712814025e-06, 'epoch': 1.71}
{'loss': 0.3704, 'learning_rate': 4.340321706126876e-06, 'epoch': 1.71}
{'loss': 0.6251, 'learning_rate': 4.337610699439725e-06, 'epoch': 1.71}
{'loss': 0.9535, 'learning_rate': 4.334899692752576e-06, 'epoch': 1.71}

 86%|████████▌ | 9468/11066 [34:41<05:54,  4.50it/s]
 86%|████████▌ | 9469/11066 [34:41<05:54,  4.50it/s]
                                                    

 86%|████████▌ | 9469/11066 [34:41<05:54,  4.50it/s]
 86%|████████▌ | 9470/11066 [34:41<05:54,  4.50it/s]
                                                    

 86%|████████▌ | 9470/11066 [34:41<05:54,  4.50it/s]
 86%|████████▌ | 9471/11066 [34:42<05:54,  4.50it/s]
                                                    

 86%|████████▌ | 9471/11066 [34:42<05:54,  4.50it/s]
 86%|████████▌ | 9472/11066 [34:42<05:51,  4.53it/s]
                                                    

 86%|████████▌ | 9472/11066 [34:42<05:51,  4.53it/s]
 86%|████████▌ | 9473/11066 [34:42<05:53,  4.50it/s]
                                                    

 86%|████████▌ | 9473/11066 [34:42<05:53,  4.50it/s]
 86%|████████▌ | 9474/11066 [34:42<05:51,  4.53it/s]
                                                    

 86%|████████▌ | 9474/11066 [34:42<05:51,  4.53it/s]
 86%|████████▌ | 9475/11066 [34:42<05:54,  4.49it/s]
                                                    

 86%|████████▌ | 9475/11066 [34:42<05:54,  4.49it/s]
 86%|████████▌ | 9476/11066 [34:43<05:54,  4.49it/s]
                                                    

 86%|████████▌ | 9476/11066 [34:43<05:54,  4.49it/s]
 86%|████████▌ | 9477/11066 [34:43<05:54,  4.48it/s]
                                                    

 86%|████████▌ | 9477/11066 [34:43<05:54,  4.48it/s]
 86%|████████▌ | 9478/11066 [34:43<05:54,  4.49it/s]
                                                    

 86%|████████▌ | 9478/11066 [34:43<05:54,  4.49it/s]
 86%|████████▌ | 9479/11066 [34:43<05:53,  4.49it/s]
                                                    

 86%|████████▌ | 9479/11066 [34:43<05:53,  4.49it/s]
 86%|████████▌ | 9480/11066 [34:44<05:52,  4.50it/s]
                                                    

 86%|████████▌ | 9480/11066 [34:44<05:52,  4.50it/s]
 86%|████████▌ | 9481/11066 [34:44<05:52,  4.50it/s]
                                                    

 86%|████████▌ | 9481/11066 [34:44<05:52,  4.50it/s]
 86%|████████▌ | 9482/11066 [34:44<05:49,  4.53it/s]
                                                    

 86%|████████▌ | 9482/11066 [34:44<05:49,  4.53it/s]
 86%|████████▌ | 9483/11066 [34:44<05:46,  4.57it/s]
                                                    

 86%|████████▌ | 9483/11066 [34:44<05:46,  4.57it/s]
 86%|████████▌ | 9484/11066 [34:44<05:45,  4.58it/s]
                                                    

 86%|████████▌ | 9484/11066 [34:44<05:45,  4.58it/s]
 86%|████████▌ | 9485/11066 [34:45<05:46,  4.56it/s]
                                                    

 86%|████████▌ | 9485/11066 [34:45<05:46,  4.56it/s]
 86%|████████▌ | 9486/11066 [34:45<05:47,  4.54it/s]
                                                    

 86%|████████▌ | 9486/11066 [34:45<05:47,  4.54it/s]
 86%|████████▌ | 9487/11066 [34:45<05:46,  4.56it/s]
                                                    

 86%|████████▌ | 9487/11066 [34:45<05:46,  4.56it/s]
 86%|████████▌ | 9488/11066 [34:45<05:46,  4.56it/s]
                                                    

 86%|████████▌ | 9488/11066 [34:45<05:46,  4.56it/s]
 86%|████████▌ | 9489/11066 [34:46<05:45,  4.57it/s]
                                                    

 86%|████████▌ | 9489/11066 [34:46<05:45,  4.57it/s]
 86%|████████▌ | 9490/11066 [34:46<05:44,  4.57it/s]
                                                    

 86%|████████▌ | 9490/11066 [34:46<05:44,  4.57it/s]
 86%|████████▌ | 9491/11066 [34:46<05:44,  4.57it/s]
                                                    

 86%|████████▌ | 9491/11066 [34:46<05:44,  4.57it/s]
 86%|████████▌ | 9492/11066 [34:46<05:42,  4.59it/s]
                                                    

 86%|████████▌ | 9492/11066 [34:46<05:42,  4.59it/s]
 86%|████████▌ | 9493/11066 [34:46<05:40,  4.62it/s]
                                                    

 86%|████████▌ | 9493/11066 [34:46<05:40,  4.62it/s]
 86%|████████▌ | 9494/11066 [34:47<05:41,  4.60it/s]
                                                    

 86%|████████▌ | 9494/11066 [34:47<05:41,  4.60it/s]
 86%|████████▌ | 9495/11066 [34:47<05:42,  4.59it/s]
                                                    

 86%|████████▌ | 9495/11066 [34:47<05:42,  4.59it/s]
 86%|████████▌ | 9496/11066 [34:47<05:41,  4.60it/s]
                                                    

 86%|████████▌ | 9496/11066 [34:47<05:41,  4.60it/s]
 86%|████████▌ | 9497/11066 [34:47<05:39,  4.62it/s]
                                                    

 86%|████████▌ | 9497/11066 [34:47<05:39,  4.62it/s]
 86%|████████▌ | 9498/11066 [34:48<05:40,  4.61it/s]
                                                    

 86%|████████▌ | 9498/11066 [34:48<05:40,  4.61it/s]
 86%|████████▌ | 9499/11066 [34:48<05:40,  4.61it/s]
                                                    

 86%|████████▌ | 9499/11066 [34:48<05:40,  4.61it/s]
 86%|████████▌ | 9500/11066 [34:48<05:40,  4.60it/s]
                                                    

 86%|████████▌ | 9500/11066 [34:48<05:40,  4.60it/s]
 86%|████████▌ | 9501/11066 [34:48<05:40,  4.60it/s]
                                                    

 86%|████████▌ | 9501/11066 [34:48<05:40,  4.60it/s]
 86%|████████▌ | 9502/11066 [34:48<05:40,  4.60it/s]
                                                    

 86%|████████▌ | 9502/11066 [34:48<05:40,  4.60it/s]
 86%|████████▌ | 9503/11066 [34:49<05:43,  4.55it/s]
                                                    

 86%|████████▌ | 9503/11066 [34:49<05:43,  4.55it/s]
 86%|████████▌ | 9504/11066 [34:49<05:42,  4.56it/s]
                                                    

 86%|████████▌ | 9504/11066 [34:49<05:42,  4.56it/s]
 86%|████████▌ | 9505/11066 [34:49<05:39,  4.60it/s]
                                                    

 86%|████████▌ | 9505/11066 [34:49<05:39,  4.60it/s]
 86%|████████▌ | 9506/11066 [34:49<05:40,  4.58it/s]
                                                    

 86%|████████▌ | 9506/11066 [34:49<05:40,  4.58it/s]
 86%|████████▌ | 9507/11066 [34:49<05:38,  4.61it/s]
                                                    

 86%|████████▌ | 9507/11066 [34:49<05:38,  4.61it/s]
 86%|████████▌ | 9508/11066 [34:50<05:41,  4.56it/s]
                                                    

 86%|████████▌ | 9508/11066 [34:50<05:41,  4.56it/s]
 86%|████████▌ | 9509/11066 [34:50<05:43,  4.54it/s]
                                                    

 86%|████████▌ | 9509/11066 [34:50<05:43,  4.54it/s]
 86%|████████▌ | 9510/11066 [34:50<05:44,  4.52it/s]
                                                    

 86%|████████▌ | 9510/11066 [34:50<05:44,  4.52it/s]
 86%|████████▌ | 9511/11066 [34:50<05:41,  4.55it/s]
                                                    

 86%|████████▌ | 9511/11066 [34:50<05:41,  4.55it/s]
 86%|████████▌ | 9512/11066 [34:51<05:43,  4.52it/s]
                                                    

 86%|████████▌ | 9512/11066 [34:51<05:43,  4.52it/s]
 86%|████████▌ | 9513/11066 [34:51<05:45,  4.50it/s]
                                                    

 86%|████████▌ | 9513/11066 [34:51<05:45,  4.50it/s]
 86%|████████▌ | 9514/11066 [34:51<05:42,  4.53it/s]
                                                    

 86%|████████▌ | 9514/11066 [34:51<05:42,  4.53it/s]
 86%|████████▌ | 9515/11066 [34:51<05:45,  4.49it/s]
                                                    

 86%|████████▌ | 9515/11066 [34:51<05:45,  4.49it/s]
 86%|████████▌ | 9516/11066 [34:51<05:45,  4.49it/s]
                                                    

 86%|████████▌ | 9516/11066 [34:51<05:45,  4.49it/s]
 86%|████████▌ | 9517/11066 [34:52<05:42,  4.53it/s]
                                                    

 86%|████████▌ | 9517/11066 [34:52<05:42,  4.53it/s]
 86%|████████▌ | 9518/11066 [34:52<05:41,  4.53it/s]
                                                    

 86%|████████▌ | 9518/11066 [34:52<05:41,  4.53it/s]
 86%|████████▌ | 9519/11066 [34:52<05:39,  4.55it/s]
                                                    

 86%|████████▌ | 9519/11066 [34:52<05:39,  4.55it/s]
 86%|████████▌ | 9520/11066 [34:52<05:41,  4.53it/s]
                                                    

 86%|████████▌ | 9520/11066 [34:52<05:41,  4.53it/s]
 86%|████████▌ | 9521/11066 [34:53<05:42,  4.51it/s]
                                                    

 86%|████████▌ | 9521/11066 [34:53<05:42,  4.51it/s]
 86%|████████▌ | 9522/11066 [34:53<05:42,  4.51it/s]
                                                    

 86%|████████▌ | 9522/11066 [34:53<05:42,  4.51it/s]
 86%|████████▌ | 9523/11066 [34:53<05:42,  4.51it/s]
                                                    

 86%|████████▌ | 9523/11066 [34:53<05:42,  4.51it/s]
 86%|████████▌ | 9524/11066 [34:53<05:39,  4.54it/s]
                                                    

 86%|████████▌ | 9524/11066 [34:53<05:39,  4.54it/s]
 86%|████████▌ | 9525/11066 [34:53<05:41,  4.52it/s]
                                                    

 86%|████████▌ | 9525/11066 [34:53<05:41,  4.52it/s]
 86%|████████▌ | 9526/11066 [34:54<05:42,  4.50it/s]
                                                    

 86%|████████▌ | 9526/11066 [34:54<05:42,  4.50it/s]
 86%|████████▌ | 9527/11066 [34:54<05:40,  4.52it/s]
                                                    

 86%|████████▌ | 9527/11066 [34:54<05:40,  4.52it/s]
 86%|████████▌ | 9528/11066 [34:54<05:37,  4.56it/s]
                                                    

 86%|████████▌ | 9528/11066 [34:54<05:37,  4.56it/s]
 86%|████████▌ | 9529/11066 [34:54<05:39,  4.53it/s]
                                                    

 86%|████████▌ | 9529/11066 [34:54<05:39,  4.53it/s]
 86%|████████▌ | 9530/11066 [34:55<05:37,  4.56it/s]
                                                    

 86%|████████▌ | 9530/11066 [34:55<05:37,  4.56it/s]
 86%|████████▌ | 9531/11066 [34:55<05:39,  4.52it/s]
                                                    

 86%|████████▌ | 9531/11066 [34:55<05:39,  4.52it/s]
 86%|████████▌ | 9532/11066 [34:55<05:37,  4.54it/s]
                                                    

 86%|████████▌ | 9532/11066 [34:55<05:37,  4.54it/s]
 86%|████████▌ | 9533/11066 [34:55<05:34,  4.59it/s]
                                                    

 86%|████████▌ | 9533/11066 [34:55<05:34,  4.59it/s]
 86%|████████▌ | 9534/11066 [34:55<05:31,  4.62it/s]
                                                    

 86%|████████▌ | 9534/11066 [34:55<05:31,  4.62it/s]
 86%|████████▌ | 9535/11066 [34:56<05:32,  4.61it/s]
                                                    

 86%|████████▌ | 9535/11066 [34:56<05:32,  4.61it/s]
 86%|████████▌ | 9536/11066 [34:56<05:29,  4.64it/s]
                                                    

 86%|████████▌ | 9536/11066 [34:56<05:29,  4.64it/s]
 86%|████████▌ | 9537/11066 [34:56<05:28,  4.66it/s]
                                                    

 86%|████████▌ | 9537/11066 [34:56<05:28,  4.66it/s]
 86%|████████▌ | 9538/11066 [34:56<05:31,  4.61it/s]
                                                    

 86%|████████▌ | 9538/11066 [34:56<05:31,  4.61it/s]
 86%|████████▌ | 9539/11066 [34:57<05:29,  4.63it/s]
                                                    

 86%|████████▌ | 9539/11066 [34:57<05:29,  4.63it/s]
 86%|████████▌ | 9540/11066 [34:57<05:33,  4.58it/s]
                                                    

 86%|████████▌ | 9540/11066 [34:57<05:33,  4.58it/s]
 86%|████████▌ | 9541/11066 [34:57<05:32,  4.58it/s]
                                                    

 86%|████████▌ | 9541/11066 [34:57<05:32,  4.58it/s]
 86%|████████▌ | 9542/11066 [34:57<05:30,  4.61it/s]
                                                    

 86%|████████▌ | 9542/11066 [34:57<05:30,  4.61it/s]
 86%|████████▌ | 9543/11066 [34:57<05:32,  4.58it/s]
                                                    

 86%|████████▌ | 9543/11066 [34:57<05:32,  4.58it/s]
 86%|████████▌ | 9544/11066 [34:58<05:33,  4.57it/s]
                                                    

 86%|████████▌ | 9544/11066 [34:58<05:33,  4.57it/s]
 86%|████████▋ | 9545/11066 [34:58<05:30,  4.60it/s]
                                                    

 86%|████████▋ | 9545/11066 [34:58<05:30,  4.60it/s]
 86%|████████▋ | 9546/11066 [34:58<05:32,  4.57it/s]
                                                    

 86%|████████▋ | 9546/11066 [34:58<05:32,  4.57it/s]
 86%|████████▋ | 9547/11066 [34:58<05:34,  4.54it/s]
                                                    

 86%|████████▋ | 9547/11066 [34:58<05:34,  4.54it/s]
 86%|████████▋ | 9548/11066 [34:58<05:33,  4.56it/s]
                                                    

 86%|████████▋ | 9548/11066 [34:58<05:33,  4.56it/s]
 86%|████████▋ | 9549/11066 [34:59<05:35,  4.53it/s]
                                                    

 86%|████████▋ | 9549/11066 [34:59<05:35,  4.53it/s]
 86%|████████▋ | 9550/11066 [34:59<05:36,  4.50it/s]
                                                    

 86%|████████▋ | 9550/11066 [34:59<05:36,  4.50it/s]
 86%|████████▋ | 9551/11066 [34:59<05:37,  4.49it/s]
                                                    

 86%|████████▋ | 9551/11066 [34:59<05:37,  4.49it/s]
 86%|████████▋ | 9552/11066 [34:59<05:37,  4.49it/s]
                                                    

 86%|████████▋ | 9552/11066 [34:59<05:37,  4.49it/s]
 86%|████████▋ | 9553/11066 [35:00<05:36,  4.49it/s]
                                                    

 86%|████████▋ | 9553/11066 [35:00<05:36,  4.49it/s]
 86%|████████▋ | 9554/11066 [35:00<05:36,  4.49it/s]
                                                    

 86%|████████▋ | 9554/11066 [35:00<05:36,  4.49it/s]
 86%|████████▋ | 9555/11066 [35:00<05:33,  4.53it/s]
                                                    

 86%|████████▋ | 9555/11066 [35:00<05:33,  4.53it/s]
 86%|████████▋ | 9556/11066 [35:00<05:34,  4.51it/s]
                                                    

 86%|████████▋ | 9556/11066 [35:00<05:34,  4.51it/s]
 86%|████████▋ | 9557/11066 [35:00<05:33,  4.52it/s]
                                                    

 86%|████████▋ | 9557/11066 [35:00<05:33,  4.52it/s]
 86%|████████▋ | 9558/11066 [35:01<05:31,  4.54it/s]
                                                    

 86%|████████▋ | 9558/11066 [35:01<05:31,  4.54it/s]
 86%|████████▋ | 9559/11066 [35:01<05:30,  4.56it/s]
                                                    

 86%|████████▋ | 9559/11066 [35:01<05:30,  4.56it/s]
 86%|████████▋ | 9560/11066 [35:01<05:29,  4.57it/s]
                                                    

 86%|████████▋ | 9560/11066 [35:01<05:29,  4.57it/s]
 86%|████████▋ | 9561/11066 [35:01<05:31,  4.54it/s]
                                                    

 86%|████████▋ | 9561/11066 [35:01<05:31,  4.54it/s]
 86%|████████▋ | 9562/11066 [35:02<05:31,  4.53it/s]
                                                    

 86%|████████▋ | 9562/11066 [35:02<05:31,  4.53it/s]
 86%|████████▋ | 9563/11066 [35:02<05:32,  4.52it/s]
                                                    

 86%|████████▋ | 9563/11066 [35:02<05:32,  4.52it/s]
 86%|████████▋ | 9564/11066 [35:02<05:30,  4.55it/s]
                                                    

 86%|████████▋ | 9564/11066 [35:02<05:30,  4.55it/s]
 86%|████████▋ | 9565/11066 [35:02<05:29,  4.56it/s]
                                                    

 86%|████████▋ | 9565/11066 [35:02<05:29,  4.56it/s]
 86%|████████▋ | 9566/11066 [35:02<05:28,  4.57it/s]
                                                    

 86%|████████▋ | 9566/11066 [35:02<05:28,  4.57it/s]
 86%|████████▋ | 9567/11066 [35:03<05:30,  4.53it/s]
                                                    

 86%|████████▋ | 9567/11066 [35:03<05:30,  4.53it/s]
 86%|████████▋ | 9568/11066 [35:03<05:29,  4.55it/s]
                                                    

 86%|████████▋ | 9568/11066 [35:03<05:29,  4.55it/s]
 86%|████████▋ | 9569/11066 [35:03<05:25,  4.60it/s]
                                                    

 86%|████████▋ | 9569/11066 [35:03<05:25,  4.60it/s]
 86%|████████▋ | 9570/11066 [35:03<05:28,  4.56it/s]
                                                    

 86%|████████▋ | 9570/11066 [35:03<05:28,  4.56it/s]
 86%|████████▋ | 9571/11066 [35:04<05:30,  4.52it/s]
                                                    

 86%|████████▋ | 9571/11066 [35:04<05:30,  4.52it/s]
 86%|████████▋ | 9572/11066 [35:04<05:31,  4.51it/s]
                                                    

 86%|████████▋ | 9572/11066 [35:04<05:31,  4.51it/s]
 87%|████████▋ | 9573/11066 [35:04<05:31,  4.50it/s]
                                                    

 87%|████████▋ | 9573/11066 [35:04<05:31,  4.50it/s]
 87%|████████▋ | 9574/11066 [35:04<05:31,  4.50it/s]
                                                    

 87%|████████▋ | 9574/11066 [35:04<05:31,  4.50it/s]
 87%|████████▋ | 9575/11066 [35:04<05:29,  4.53it/s]
                                                    

 87%|████████▋ | 9575/11066 [35:04<05:29,  4.53it/s]
 87%|████████▋ | 9576/11066 [35:05<05:29,  4.52it/s]
                                                    

 87%|████████▋ | 9576/11066 [35:05<05:29,  4.52it/s]
 87%|████████▋ | 9577/11066 [35:05<05:30,  4.51it/s]
                                                    

 87%|████████▋ | 9577/11066 [35:05<05:30,  4.51it/s]
 87%|████████▋ | 9578/11066 [35:05<05:28,  4.53it/s]
                                                    

 87%|████████▋ | 9578/11066 [35:05<05:28,  4.53it/s]
 87%|████████▋ | 9579/11066 [35:05<05:24,  4.58it/s]
                                                    

 87%|████████▋ | 9579/11066 [35:05<05:24,  4.58it/s]
 87%|████████▋ | 9580/11066 [35:06<05:22,  4.61it/s]
                                                    

 87%|████████▋ | 9580/11066 [35:06<05:22,  4.61it/s]
 87%|████████▋ | 9581/11066 [35:06<05:21,  4.62it/s]
                                                    
{'loss': 0.7574, 'learning_rate': 4.332188686065425e-06, 'epoch': 1.71}
{'loss': 1.0524, 'learning_rate': 4.329477679378276e-06, 'epoch': 1.71}
{'loss': 0.621, 'learning_rate': 4.3267666726911256e-06, 'epoch': 1.71}
{'loss': 0.7422, 'learning_rate': 4.3240556660039765e-06, 'epoch': 1.71}
{'loss': 0.7913, 'learning_rate': 4.321344659316827e-06, 'epoch': 1.71}
{'loss': 0.6737, 'learning_rate': 4.318633652629677e-06, 'epoch': 1.71}
{'loss': 0.6045, 'learning_rate': 4.315922645942527e-06, 'epoch': 1.71}
{'loss': 1.1083, 'learning_rate': 4.313211639255377e-06, 'epoch': 1.71}
{'loss': 0.9874, 'learning_rate': 4.310500632568227e-06, 'epoch': 1.71}
{'loss': 0.8202, 'learning_rate': 4.307789625881077e-06, 'epoch': 1.71}
{'loss': 0.7764, 'learning_rate': 4.3050786191939275e-06, 'epoch': 1.71}
{'loss': 0.4286, 'learning_rate': 4.302367612506778e-06, 'epoch': 1.71}
{'loss': 0.9113, 'learning_rate': 4.299656605819628e-06, 'epoch': 1.71}
{'loss': 0.5784, 'learning_rate': 4.296945599132478e-06, 'epoch': 1.71}
{'loss': 0.4473, 'learning_rate': 4.294234592445328e-06, 'epoch': 1.71}
{'loss': 0.8275, 'learning_rate': 4.291523585758179e-06, 'epoch': 1.71}
{'loss': 0.7862, 'learning_rate': 4.288812579071028e-06, 'epoch': 1.71}
{'loss': 0.8375, 'learning_rate': 4.286101572383879e-06, 'epoch': 1.71}
{'loss': 0.6301, 'learning_rate': 4.2833905656967286e-06, 'epoch': 1.71}
{'loss': 0.6484, 'learning_rate': 4.2806795590095795e-06, 'epoch': 1.71}
{'loss': 0.1563, 'learning_rate': 4.277968552322429e-06, 'epoch': 1.71}
{'loss': 0.6369, 'learning_rate': 4.27525754563528e-06, 'epoch': 1.71}
{'loss': 1.2608, 'learning_rate': 4.272546538948129e-06, 'epoch': 1.72}
{'loss': 0.366, 'learning_rate': 4.26983553226098e-06, 'epoch': 1.72}
{'loss': 1.3092, 'learning_rate': 4.267124525573829e-06, 'epoch': 1.72}
{'loss': 0.459, 'learning_rate': 4.26441351888668e-06, 'epoch': 1.72}
{'loss': 0.8614, 'learning_rate': 4.2617025121995305e-06, 'epoch': 1.72}
{'loss': 0.7238, 'learning_rate': 4.258991505512381e-06, 'epoch': 1.72}
{'loss': 0.9773, 'learning_rate': 4.256280498825231e-06, 'epoch': 1.72}
{'loss': 0.7692, 'learning_rate': 4.253569492138081e-06, 'epoch': 1.72}
{'loss': 1.1718, 'learning_rate': 4.250858485450931e-06, 'epoch': 1.72}
{'loss': 0.5024, 'learning_rate': 4.248147478763781e-06, 'epoch': 1.72}
{'loss': 0.6558, 'learning_rate': 4.245436472076631e-06, 'epoch': 1.72}
{'loss': 1.1175, 'learning_rate': 4.242725465389481e-06, 'epoch': 1.72}
{'loss': 0.4521, 'learning_rate': 4.2400144587023315e-06, 'epoch': 1.72}
{'loss': 1.1415, 'learning_rate': 4.237303452015182e-06, 'epoch': 1.72}
{'loss': 0.4923, 'learning_rate': 4.234592445328032e-06, 'epoch': 1.72}
{'loss': 0.8468, 'learning_rate': 4.231881438640883e-06, 'epoch': 1.72}
{'loss': 0.7066, 'learning_rate': 4.229170431953732e-06, 'epoch': 1.72}
{'loss': 0.774, 'learning_rate': 4.226459425266583e-06, 'epoch': 1.72}
{'loss': 0.2755, 'learning_rate': 4.223748418579432e-06, 'epoch': 1.72}
{'loss': 1.411, 'learning_rate': 4.221037411892283e-06, 'epoch': 1.72}
{'loss': 0.7229, 'learning_rate': 4.218326405205133e-06, 'epoch': 1.72}
{'loss': 0.7627, 'learning_rate': 4.215615398517984e-06, 'epoch': 1.72}
{'loss': 0.3823, 'learning_rate': 4.212904391830833e-06, 'epoch': 1.72}
{'loss': 0.3822, 'learning_rate': 4.210193385143684e-06, 'epoch': 1.72}
{'loss': 0.6873, 'learning_rate': 4.207482378456534e-06, 'epoch': 1.72}
{'loss': 0.8223, 'learning_rate': 4.204771371769384e-06, 'epoch': 1.72}
{'loss': 1.5011, 'learning_rate': 4.202060365082234e-06, 'epoch': 1.72}
{'loss': 0.6902, 'learning_rate': 4.199349358395084e-06, 'epoch': 1.72}
{'loss': 0.4249, 'learning_rate': 4.1966383517079345e-06, 'epoch': 1.72}
{'loss': 0.3499, 'learning_rate': 4.193927345020785e-06, 'epoch': 1.72}
{'loss': 0.4396, 'learning_rate': 4.191216338333635e-06, 'epoch': 1.72}
{'loss': 0.6095, 'learning_rate': 4.188505331646485e-06, 'epoch': 1.72}
{'loss': 0.4936, 'learning_rate': 4.185794324959335e-06, 'epoch': 1.72}
{'loss': 0.7856, 'learning_rate': 4.183083318272184e-06, 'epoch': 1.72}
{'loss': 0.6175, 'learning_rate': 4.180372311585035e-06, 'epoch': 1.72}
{'loss': 0.6013, 'learning_rate': 4.1776613048978855e-06, 'epoch': 1.72}
{'loss': 0.528, 'learning_rate': 4.174950298210736e-06, 'epoch': 1.72}
{'loss': 0.6692, 'learning_rate': 4.172239291523586e-06, 'epoch': 1.72}
{'loss': 0.9641, 'learning_rate': 4.169528284836436e-06, 'epoch': 1.72}
{'loss': 0.3313, 'learning_rate': 4.166817278149286e-06, 'epoch': 1.72}
{'loss': 0.2831, 'learning_rate': 4.164106271462136e-06, 'epoch': 1.72}
{'loss': 0.8702, 'learning_rate': 4.161395264774986e-06, 'epoch': 1.72}
{'loss': 0.9746, 'learning_rate': 4.1586842580878364e-06, 'epoch': 1.72}
{'loss': 1.1049, 'learning_rate': 4.1559732514006866e-06, 'epoch': 1.72}
{'loss': 0.4998, 'learning_rate': 4.153262244713537e-06, 'epoch': 1.72}
{'loss': 0.8555, 'learning_rate': 4.150551238026387e-06, 'epoch': 1.72}
{'loss': 0.8808, 'learning_rate': 4.147840231339238e-06, 'epoch': 1.72}
{'loss': 1.2132, 'learning_rate': 4.145129224652087e-06, 'epoch': 1.72}
{'loss': 0.4083, 'learning_rate': 4.142418217964938e-06, 'epoch': 1.72}
{'loss': 0.5109, 'learning_rate': 4.139707211277787e-06, 'epoch': 1.72}
{'loss': 0.9875, 'learning_rate': 4.136996204590638e-06, 'epoch': 1.72}
{'loss': 0.8492, 'learning_rate': 4.134285197903488e-06, 'epoch': 1.72}
{'loss': 0.2111, 'learning_rate': 4.131574191216339e-06, 'epoch': 1.72}
{'loss': 0.759, 'learning_rate': 4.128863184529188e-06, 'epoch': 1.72}
{'loss': 1.254, 'learning_rate': 4.126152177842039e-06, 'epoch': 1.72}
{'loss': 0.6364, 'learning_rate': 4.123441171154889e-06, 'epoch': 1.73}
{'loss': 0.4625, 'learning_rate': 4.120730164467739e-06, 'epoch': 1.73}
{'loss': 0.3963, 'learning_rate': 4.118019157780589e-06, 'epoch': 1.73}
{'loss': 0.4284, 'learning_rate': 4.115308151093439e-06, 'epoch': 1.73}
{'loss': 0.4909, 'learning_rate': 4.1125971444062896e-06, 'epoch': 1.73}
{'loss': 0.6381, 'learning_rate': 4.10988613771914e-06, 'epoch': 1.73}
{'loss': 1.1513, 'learning_rate': 4.10717513103199e-06, 'epoch': 1.73}
{'loss': 0.8098, 'learning_rate': 4.10446412434484e-06, 'epoch': 1.73}
{'loss': 0.8029, 'learning_rate': 4.10175311765769e-06, 'epoch': 1.73}
{'loss': 1.1326, 'learning_rate': 4.09904211097054e-06, 'epoch': 1.73}
{'loss': 1.2485, 'learning_rate': 4.09633110428339e-06, 'epoch': 1.73}
{'loss': 1.1415, 'learning_rate': 4.093620097596241e-06, 'epoch': 1.73}
{'loss': 0.5008, 'learning_rate': 4.090909090909091e-06, 'epoch': 1.73}
{'loss': 0.523, 'learning_rate': 4.088198084221942e-06, 'epoch': 1.73}
{'loss': 0.4192, 'learning_rate': 4.085487077534791e-06, 'epoch': 1.73}
{'loss': 0.7489, 'learning_rate': 4.082776070847642e-06, 'epoch': 1.73}
{'loss': 0.7571, 'learning_rate': 4.080065064160491e-06, 'epoch': 1.73}
{'loss': 0.8337, 'learning_rate': 4.077354057473342e-06, 'epoch': 1.73}
{'loss': 0.445, 'learning_rate': 4.0746430507861914e-06, 'epoch': 1.73}
{'loss': 0.902, 'learning_rate': 4.071932044099042e-06, 'epoch': 1.73}
{'loss': 1.0017, 'learning_rate': 4.069221037411892e-06, 'epoch': 1.73}
{'loss': 0.5746, 'learning_rate': 4.066510030724743e-06, 'epoch': 1.73}
{'loss': 1.11, 'learning_rate': 4.063799024037593e-06, 'epoch': 1.73}
{'loss': 0.6818, 'learning_rate': 4.061088017350443e-06, 'epoch': 1.73}
{'loss': 0.8883, 'learning_rate': 4.058377010663293e-06, 'epoch': 1.73}
{'loss': 1.2243, 'learning_rate': 4.055666003976143e-06, 'epoch': 1.73}
{'loss': 0.3715, 'learning_rate': 4.052954997288993e-06, 'epoch': 1.73}
{'loss': 1.948, 'learning_rate': 4.0502439906018435e-06, 'epoch': 1.73}
{'loss': 0.7942, 'learning_rate': 4.047532983914694e-06, 'epoch': 1.73}
{'loss': 0.8005, 'learning_rate': 4.044821977227544e-06, 'epoch': 1.73}
{'loss': 0.3224, 'learning_rate': 4.042110970540394e-06, 'epoch': 1.73}
{'loss': 0.4293, 'learning_rate': 4.039399963853244e-06, 'epoch': 1.73}
{'loss': 0.5868, 'learning_rate': 4.036688957166094e-06, 'epoch': 1.73}
{'loss': 0.3092, 'learning_rate': 4.033977950478945e-06, 'epoch': 1.73}
{'loss': 0.4705, 'learning_rate': 4.0312669437917944e-06, 'epoch': 1.73}
{'loss': 0.4655, 'learning_rate': 4.028555937104645e-06, 'epoch': 1.73}

 87%|████████▋ | 9581/11066 [35:06<05:21,  4.62it/s]
 87%|████████▋ | 9582/11066 [35:06<05:23,  4.58it/s]
                                                    

 87%|████████▋ | 9582/11066 [35:06<05:23,  4.58it/s]
 87%|████████▋ | 9583/11066 [35:06<05:25,  4.55it/s]
                                                    

 87%|████████▋ | 9583/11066 [35:06<05:25,  4.55it/s]
 87%|████████▋ | 9584/11066 [35:06<05:27,  4.53it/s]
                                                    

 87%|████████▋ | 9584/11066 [35:06<05:27,  4.53it/s]
 87%|████████▋ | 9585/11066 [35:07<05:27,  4.52it/s]
                                                    

 87%|████████▋ | 9585/11066 [35:07<05:27,  4.52it/s]
 87%|████████▋ | 9586/11066 [35:07<05:23,  4.57it/s]
                                                    

 87%|████████▋ | 9586/11066 [35:07<05:23,  4.57it/s]
 87%|████████▋ | 9587/11066 [35:07<05:20,  4.61it/s]
                                                    

 87%|████████▋ | 9587/11066 [35:07<05:20,  4.61it/s]
 87%|████████▋ | 9588/11066 [35:07<05:21,  4.60it/s]
                                                    

 87%|████████▋ | 9588/11066 [35:07<05:21,  4.60it/s]
 87%|████████▋ | 9589/11066 [35:07<05:19,  4.63it/s]
                                                    

 87%|████████▋ | 9589/11066 [35:08<05:19,  4.63it/s]
 87%|████████▋ | 9590/11066 [35:08<05:18,  4.63it/s]
                                                    

 87%|████████▋ | 9590/11066 [35:08<05:18,  4.63it/s]
 87%|████████▋ | 9591/11066 [35:08<05:18,  4.64it/s]
                                                    

 87%|████████▋ | 9591/11066 [35:08<05:18,  4.64it/s]
 87%|████████▋ | 9592/11066 [35:08<05:20,  4.59it/s]
                                                    

 87%|████████▋ | 9592/11066 [35:08<05:20,  4.59it/s]
 87%|████████▋ | 9593/11066 [35:08<05:20,  4.60it/s]
                                                    

 87%|████████▋ | 9593/11066 [35:08<05:20,  4.60it/s]
 87%|████████▋ | 9594/11066 [35:09<05:21,  4.59it/s]
                                                    

 87%|████████▋ | 9594/11066 [35:09<05:21,  4.59it/s]
 87%|████████▋ | 9595/11066 [35:09<05:19,  4.60it/s]
                                                    

 87%|████████▋ | 9595/11066 [35:09<05:19,  4.60it/s]
 87%|████████▋ | 9596/11066 [35:09<05:19,  4.60it/s]
                                                    

 87%|████████▋ | 9596/11066 [35:09<05:19,  4.60it/s]
 87%|████████▋ | 9597/11066 [35:09<05:24,  4.53it/s]
                                                    

 87%|████████▋ | 9597/11066 [35:09<05:24,  4.53it/s]
 87%|████████▋ | 9598/11066 [35:09<05:26,  4.50it/s]
                                                    

 87%|████████▋ | 9598/11066 [35:09<05:26,  4.50it/s]
 87%|████████▋ | 9599/11066 [35:10<05:25,  4.50it/s]
                                                    

 87%|████████▋ | 9599/11066 [35:10<05:25,  4.50it/s]
 87%|████████▋ | 9600/11066 [35:10<05:25,  4.50it/s]
                                                    

 87%|████████▋ | 9600/11066 [35:10<05:25,  4.50it/s]
 87%|████████▋ | 9601/11066 [35:10<05:22,  4.54it/s]
                                                    

 87%|████████▋ | 9601/11066 [35:10<05:22,  4.54it/s]
 87%|████████▋ | 9602/11066 [35:10<05:19,  4.58it/s]
                                                    

 87%|████████▋ | 9602/11066 [35:10<05:19,  4.58it/s]
 87%|████████▋ | 9603/11066 [35:11<05:17,  4.61it/s]
                                                    

 87%|████████▋ | 9603/11066 [35:11<05:17,  4.61it/s]
 87%|████████▋ | 9604/11066 [35:11<05:20,  4.57it/s]
                                                    

 87%|████████▋ | 9604/11066 [35:11<05:20,  4.57it/s]
 87%|████████▋ | 9605/11066 [35:11<05:18,  4.58it/s]
                                                    

 87%|████████▋ | 9605/11066 [35:11<05:18,  4.58it/s]
 87%|████████▋ | 9606/11066 [35:11<05:20,  4.55it/s]
                                                    

 87%|████████▋ | 9606/11066 [35:11<05:20,  4.55it/s]
 87%|████████▋ | 9607/11066 [35:11<05:22,  4.52it/s]
                                                    

 87%|████████▋ | 9607/11066 [35:11<05:22,  4.52it/s]
 87%|████████▋ | 9608/11066 [35:12<05:23,  4.51it/s]
                                                    

 87%|████████▋ | 9608/11066 [35:12<05:23,  4.51it/s]
 87%|████████▋ | 9609/11066 [35:12<05:21,  4.54it/s]
                                                    

 87%|████████▋ | 9609/11066 [35:12<05:21,  4.54it/s]
 87%|████████▋ | 9610/11066 [35:12<05:18,  4.57it/s]
                                                    

 87%|████████▋ | 9610/11066 [35:12<05:18,  4.57it/s]
 87%|████████▋ | 9611/11066 [35:12<05:21,  4.53it/s]
                                                    

 87%|████████▋ | 9611/11066 [35:12<05:21,  4.53it/s]
 87%|████████▋ | 9612/11066 [35:13<05:19,  4.55it/s]
                                                    

 87%|████████▋ | 9612/11066 [35:13<05:19,  4.55it/s]
 87%|████████▋ | 9613/11066 [35:13<05:19,  4.55it/s]
                                                    

 87%|████████▋ | 9613/11066 [35:13<05:19,  4.55it/s]
 87%|████████▋ | 9614/11066 [35:13<05:17,  4.58it/s]
                                                    

 87%|████████▋ | 9614/11066 [35:13<05:17,  4.58it/s]
 87%|████████▋ | 9615/11066 [35:13<05:19,  4.55it/s]
                                                    

 87%|████████▋ | 9615/11066 [35:13<05:19,  4.55it/s]
 87%|████████▋ | 9616/11066 [35:13<05:18,  4.56it/s]
                                                    

 87%|████████▋ | 9616/11066 [35:13<05:18,  4.56it/s]
 87%|████████▋ | 9617/11066 [35:14<05:18,  4.55it/s]
                                                    

 87%|████████▋ | 9617/11066 [35:14<05:18,  4.55it/s]
 87%|████████▋ | 9618/11066 [35:14<05:16,  4.58it/s]
                                                    

 87%|████████▋ | 9618/11066 [35:14<05:16,  4.58it/s]
 87%|████████▋ | 9619/11066 [35:14<05:15,  4.58it/s]
                                                    

 87%|████████▋ | 9619/11066 [35:14<05:15,  4.58it/s]
 87%|████████▋ | 9620/11066 [35:14<05:15,  4.58it/s]
                                                    

 87%|████████▋ | 9620/11066 [35:14<05:15,  4.58it/s]
 87%|████████▋ | 9621/11066 [35:15<05:17,  4.55it/s]
                                                    

 87%|████████▋ | 9621/11066 [35:15<05:17,  4.55it/s]
 87%|████████▋ | 9622/11066 [35:15<05:18,  4.53it/s]
                                                    

 87%|████████▋ | 9622/11066 [35:15<05:18,  4.53it/s]
 87%|████████▋ | 9623/11066 [35:15<05:16,  4.56it/s]
                                                    

 87%|████████▋ | 9623/11066 [35:15<05:16,  4.56it/s]
 87%|████████▋ | 9624/11066 [35:15<05:14,  4.59it/s]
                                                    

 87%|████████▋ | 9624/11066 [35:15<05:14,  4.59it/s]
 87%|████████▋ | 9625/11066 [35:15<05:17,  4.54it/s]
                                                    

 87%|████████▋ | 9625/11066 [35:15<05:17,  4.54it/s]
 87%|████████▋ | 9626/11066 [35:16<05:18,  4.52it/s]
                                                    

 87%|████████▋ | 9626/11066 [35:16<05:18,  4.52it/s]
 87%|████████▋ | 9627/11066 [35:16<05:18,  4.51it/s]
                                                    

 87%|████████▋ | 9627/11066 [35:16<05:18,  4.51it/s]
 87%|████████▋ | 9628/11066 [35:16<05:16,  4.54it/s]
                                                    

 87%|████████▋ | 9628/11066 [35:16<05:16,  4.54it/s]
 87%|████████▋ | 9629/11066 [35:16<05:14,  4.58it/s]
                                                    

 87%|████████▋ | 9629/11066 [35:16<05:14,  4.58it/s]
 87%|████████▋ | 9630/11066 [35:16<05:13,  4.58it/s]
                                                    

 87%|████████▋ | 9630/11066 [35:16<05:13,  4.58it/s]
 87%|████████▋ | 9631/11066 [35:17<05:13,  4.58it/s]
                                                    

 87%|████████▋ | 9631/11066 [35:17<05:13,  4.58it/s]
 87%|████████▋ | 9632/11066 [35:17<05:14,  4.55it/s]
                                                    

 87%|████████▋ | 9632/11066 [35:17<05:14,  4.55it/s]
 87%|████████▋ | 9633/11066 [35:17<05:13,  4.57it/s]
                                                    

 87%|████████▋ | 9633/11066 [35:17<05:13,  4.57it/s]
 87%|████████▋ | 9634/11066 [35:17<05:11,  4.60it/s]
                                                    

 87%|████████▋ | 9634/11066 [35:17<05:11,  4.60it/s]
 87%|████████▋ | 9635/11066 [35:18<05:11,  4.60it/s]
                                                    

 87%|████████▋ | 9635/11066 [35:18<05:11,  4.60it/s]
 87%|████████▋ | 9636/11066 [35:18<05:10,  4.60it/s]
                                                    

 87%|████████▋ | 9636/11066 [35:18<05:10,  4.60it/s]
 87%|████████▋ | 9637/11066 [35:18<05:10,  4.60it/s]
                                                    

 87%|████████▋ | 9637/11066 [35:18<05:10,  4.60it/s]
 87%|████████▋ | 9638/11066 [35:18<05:09,  4.62it/s]
                                                    

 87%|████████▋ | 9638/11066 [35:18<05:09,  4.62it/s]
 87%|████████▋ | 9639/11066 [35:18<05:12,  4.57it/s]
                                                    

 87%|████████▋ | 9639/11066 [35:18<05:12,  4.57it/s]
 87%|████████▋ | 9640/11066 [35:19<05:11,  4.58it/s]
                                                    

 87%|████████▋ | 9640/11066 [35:19<05:11,  4.58it/s]
 87%|████████▋ | 9641/11066 [35:19<05:13,  4.54it/s]
                                                    

 87%|████████▋ | 9641/11066 [35:19<05:13,  4.54it/s]
 87%|████████▋ | 9642/11066 [35:19<05:12,  4.55it/s]
                                                    

 87%|████████▋ | 9642/11066 [35:19<05:12,  4.55it/s]
 87%|████████▋ | 9643/11066 [35:19<05:09,  4.60it/s]
                                                    

 87%|████████▋ | 9643/11066 [35:19<05:09,  4.60it/s]
 87%|████████▋ | 9644/11066 [35:20<05:07,  4.63it/s]
                                                    

 87%|████████▋ | 9644/11066 [35:20<05:07,  4.63it/s]
 87%|████████▋ | 9645/11066 [35:20<05:07,  4.62it/s]
                                                    

 87%|████████▋ | 9645/11066 [35:20<05:07,  4.62it/s]
 87%|████████▋ | 9646/11066 [35:20<05:10,  4.58it/s]
                                                    

 87%|████████▋ | 9646/11066 [35:20<05:10,  4.58it/s]
 87%|████████▋ | 9647/11066 [35:20<05:09,  4.59it/s]
                                                    

 87%|████████▋ | 9647/11066 [35:20<05:09,  4.59it/s]
 87%|████████▋ | 9648/11066 [35:20<05:07,  4.61it/s]
                                                    

 87%|████████▋ | 9648/11066 [35:20<05:07,  4.61it/s]
 87%|████████▋ | 9649/11066 [35:21<05:07,  4.61it/s]
                                                    

 87%|████████▋ | 9649/11066 [35:21<05:07,  4.61it/s]
 87%|████████▋ | 9650/11066 [35:21<05:05,  4.63it/s]
                                                    

 87%|████████▋ | 9650/11066 [35:21<05:05,  4.63it/s]
 87%|████████▋ | 9651/11066 [35:21<05:06,  4.61it/s]
                                                    

 87%|████████▋ | 9651/11066 [35:21<05:06,  4.61it/s]
 87%|████████▋ | 9652/11066 [35:21<05:10,  4.55it/s]
                                                    

 87%|████████▋ | 9652/11066 [35:21<05:10,  4.55it/s]
 87%|████████▋ | 9653/11066 [35:22<05:16,  4.46it/s]
                                                    

 87%|████████▋ | 9653/11066 [35:22<05:16,  4.46it/s]
 87%|████████▋ | 9654/11066 [35:22<05:16,  4.46it/s]
                                                    

 87%|████████▋ | 9654/11066 [35:22<05:16,  4.46it/s]
 87%|████████▋ | 9655/11066 [35:22<05:16,  4.46it/s]
                                                    

 87%|████████▋ | 9655/11066 [35:22<05:16,  4.46it/s]
 87%|████████▋ | 9656/11066 [35:22<05:15,  4.47it/s]
                                                    

 87%|████████▋ | 9656/11066 [35:22<05:15,  4.47it/s]
 87%|████████▋ | 9657/11066 [35:22<05:14,  4.48it/s]
                                                    

 87%|████████▋ | 9657/11066 [35:22<05:14,  4.48it/s]
 87%|████████▋ | 9658/11066 [35:23<05:12,  4.50it/s]
                                                    

 87%|████████▋ | 9658/11066 [35:23<05:12,  4.50it/s]
 87%|████████▋ | 9659/11066 [35:23<05:12,  4.50it/s]
                                                    

 87%|████████▋ | 9659/11066 [35:23<05:12,  4.50it/s]
 87%|████████▋ | 9660/11066 [35:23<05:13,  4.49it/s]
                                                    

 87%|████████▋ | 9660/11066 [35:23<05:13,  4.49it/s]
 87%|████████▋ | 9661/11066 [35:23<05:12,  4.49it/s]
                                                    

 87%|████████▋ | 9661/11066 [35:23<05:12,  4.49it/s]
 87%|████████▋ | 9662/11066 [35:24<05:12,  4.49it/s]
                                                    

 87%|████████▋ | 9662/11066 [35:24<05:12,  4.49it/s]
 87%|████████▋ | 9663/11066 [35:24<05:12,  4.49it/s]
                                                    

 87%|████████▋ | 9663/11066 [35:24<05:12,  4.49it/s]
 87%|████████▋ | 9664/11066 [35:24<05:11,  4.49it/s]
                                                    

 87%|████████▋ | 9664/11066 [35:24<05:11,  4.49it/s]
 87%|████████▋ | 9665/11066 [35:24<05:11,  4.50it/s]
                                                    

 87%|████████▋ | 9665/11066 [35:24<05:11,  4.50it/s]
 87%|████████▋ | 9666/11066 [35:24<05:11,  4.49it/s]
                                                    

 87%|████████▋ | 9666/11066 [35:24<05:11,  4.49it/s]
 87%|████████▋ | 9667/11066 [35:25<05:11,  4.48it/s]
                                                    

 87%|████████▋ | 9667/11066 [35:25<05:11,  4.48it/s]
 87%|████████▋ | 9668/11066 [35:25<05:06,  4.57it/s]
                                                    

 87%|████████▋ | 9668/11066 [35:25<05:06,  4.57it/s]
 87%|████████▋ | 9669/11066 [35:25<05:03,  4.61it/s]
                                                    

 87%|████████▋ | 9669/11066 [35:25<05:03,  4.61it/s]
 87%|████████▋ | 9670/11066 [35:25<05:04,  4.58it/s]
                                                    

 87%|████████▋ | 9670/11066 [35:25<05:04,  4.58it/s]
 87%|████████▋ | 9671/11066 [35:26<05:03,  4.60it/s]
                                                    

 87%|████████▋ | 9671/11066 [35:26<05:03,  4.60it/s]
 87%|████████▋ | 9672/11066 [35:26<05:04,  4.58it/s]
                                                    

 87%|████████▋ | 9672/11066 [35:26<05:04,  4.58it/s]
 87%|████████▋ | 9673/11066 [35:26<05:02,  4.60it/s]
                                                    

 87%|████████▋ | 9673/11066 [35:26<05:02,  4.60it/s]
 87%|████████▋ | 9674/11066 [35:26<05:00,  4.63it/s]
                                                    

 87%|████████▋ | 9674/11066 [35:26<05:00,  4.63it/s]
 87%|████████▋ | 9675/11066 [35:26<05:03,  4.59it/s]
                                                    

 87%|████████▋ | 9675/11066 [35:26<05:03,  4.59it/s]
 87%|████████▋ | 9676/11066 [35:27<05:02,  4.59it/s]
                                                    

 87%|████████▋ | 9676/11066 [35:27<05:02,  4.59it/s]
 87%|████████▋ | 9677/11066 [35:27<05:05,  4.55it/s]
                                                    

 87%|████████▋ | 9677/11066 [35:27<05:05,  4.55it/s]
 87%|████████▋ | 9678/11066 [35:27<05:02,  4.59it/s]
                                                    

 87%|████████▋ | 9678/11066 [35:27<05:02,  4.59it/s]
 87%|████████▋ | 9679/11066 [35:27<04:59,  4.63it/s]
                                                    

 87%|████████▋ | 9679/11066 [35:27<04:59,  4.63it/s]
 87%|████████▋ | 9680/11066 [35:27<05:03,  4.57it/s]
                                                    

 87%|████████▋ | 9680/11066 [35:27<05:03,  4.57it/s]
 87%|████████▋ | 9681/11066 [35:28<05:00,  4.61it/s]
                                                    

 87%|████████▋ | 9681/11066 [35:28<05:00,  4.61it/s]
 87%|████████▋ | 9682/11066 [35:28<05:01,  4.59it/s]
                                                    

 87%|████████▋ | 9682/11066 [35:28<05:01,  4.59it/s]
 88%|████████▊ | 9683/11066 [35:28<04:58,  4.63it/s]
                                                    

 88%|████████▊ | 9683/11066 [35:28<04:58,  4.63it/s]
 88%|████████▊ | 9684/11066 [35:28<04:59,  4.62it/s]
                                                    

 88%|████████▊ | 9684/11066 [35:28<04:59,  4.62it/s]
 88%|████████▊ | 9685/11066 [35:29<04:56,  4.66it/s]
                                                    

 88%|████████▊ | 9685/11066 [35:29<04:56,  4.66it/s]
 88%|████████▊ | 9686/11066 [35:29<04:55,  4.67it/s]
                                                    

 88%|████████▊ | 9686/11066 [35:29<04:55,  4.67it/s]
 88%|████████▊ | 9687/11066 [35:29<04:54,  4.69it/s]
                                                    

 88%|████████▊ | 9687/11066 [35:29<04:54,  4.69it/s]
 88%|████████▊ | 9688/11066 [35:29<04:57,  4.63it/s]
                                                    

 88%|████████▊ | 9688/11066 [35:29<04:57,  4.63it/s]
 88%|████████▊ | 9689/11066 [35:29<04:59,  4.59it/s]
                                                    

 88%|████████▊ | 9689/11066 [35:29<04:59,  4.59it/s]
 88%|████████▊ | 9690/11066 [35:30<04:56,  4.63it/s]
                                                    

 88%|████████▊ | 9690/11066 [35:30<04:56,  4.63it/s]
 88%|████████▊ | 9691/11066 [35:30<04:57,  4.63it/s]
                                                    

 88%|████████▊ | 9691/11066 [35:30<04:57,  4.63it/s]
 88%|████████▊ | 9692/11066 [35:30<04:55,  4.65it/s]
                                                    

 88%|████████▊ | 9692/11066 [35:30<04:55,  4.65it/s]
 88%|████████▊ | 9693/11066 [35:30<04:54,  4.67it/s]
                                                    

 88%|████████▊ | 9693/11066 [35:30<04:54,  4.67it/s]
 88%|████████▊ | 9694/11066 [35:30<04:58,  4.60it/s]
                                                    
{'loss': 0.5963, 'learning_rate': 4.025844930417495e-06, 'epoch': 1.73}
{'loss': 0.5361, 'learning_rate': 4.023133923730346e-06, 'epoch': 1.73}
{'loss': 0.4996, 'learning_rate': 4.020422917043195e-06, 'epoch': 1.73}
{'loss': 1.1415, 'learning_rate': 4.017711910356046e-06, 'epoch': 1.73}
{'loss': 0.9153, 'learning_rate': 4.015000903668895e-06, 'epoch': 1.73}
{'loss': 0.7583, 'learning_rate': 4.012289896981746e-06, 'epoch': 1.73}
{'loss': 1.1842, 'learning_rate': 4.009578890294596e-06, 'epoch': 1.73}
{'loss': 0.6722, 'learning_rate': 4.0068678836074465e-06, 'epoch': 1.73}
{'loss': 0.5988, 'learning_rate': 4.004156876920297e-06, 'epoch': 1.73}
{'loss': 1.2633, 'learning_rate': 4.001445870233147e-06, 'epoch': 1.73}
{'loss': 1.0151, 'learning_rate': 3.998734863545997e-06, 'epoch': 1.73}
{'loss': 0.4393, 'learning_rate': 3.996023856858847e-06, 'epoch': 1.73}
{'loss': 1.2709, 'learning_rate': 3.993312850171697e-06, 'epoch': 1.73}
{'loss': 0.3904, 'learning_rate': 3.990601843484547e-06, 'epoch': 1.73}
{'loss': 0.6969, 'learning_rate': 3.9878908367973974e-06, 'epoch': 1.73}
{'loss': 0.939, 'learning_rate': 3.9851798301102476e-06, 'epoch': 1.73}
{'loss': 0.7608, 'learning_rate': 3.982468823423098e-06, 'epoch': 1.73}
{'loss': 0.6325, 'learning_rate': 3.979757816735949e-06, 'epoch': 1.73}
{'loss': 0.6731, 'learning_rate': 3.977046810048798e-06, 'epoch': 1.73}
{'loss': 0.4779, 'learning_rate': 3.974335803361649e-06, 'epoch': 1.74}
{'loss': 0.4265, 'learning_rate': 3.971624796674498e-06, 'epoch': 1.74}
{'loss': 0.6696, 'learning_rate': 3.968913789987349e-06, 'epoch': 1.74}
{'loss': 0.8213, 'learning_rate': 3.9662027833001985e-06, 'epoch': 1.74}
{'loss': 0.7875, 'learning_rate': 3.9634917766130495e-06, 'epoch': 1.74}
{'loss': 1.2326, 'learning_rate': 3.960780769925899e-06, 'epoch': 1.74}
{'loss': 0.6739, 'learning_rate': 3.95806976323875e-06, 'epoch': 1.74}
{'loss': 0.9987, 'learning_rate': 3.955358756551599e-06, 'epoch': 1.74}
{'loss': 0.4666, 'learning_rate': 3.95264774986445e-06, 'epoch': 1.74}
{'loss': 0.6388, 'learning_rate': 3.9499367431773e-06, 'epoch': 1.74}
{'loss': 0.4243, 'learning_rate': 3.94722573649015e-06, 'epoch': 1.74}
{'loss': 0.9779, 'learning_rate': 3.944514729803e-06, 'epoch': 1.74}
{'loss': 0.5404, 'learning_rate': 3.9418037231158506e-06, 'epoch': 1.74}
{'loss': 0.9921, 'learning_rate': 3.939092716428701e-06, 'epoch': 1.74}
{'loss': 0.7023, 'learning_rate': 3.936381709741551e-06, 'epoch': 1.74}
{'loss': 0.3834, 'learning_rate': 3.933670703054401e-06, 'epoch': 1.74}
{'loss': 0.39, 'learning_rate': 3.930959696367251e-06, 'epoch': 1.74}
{'loss': 0.2781, 'learning_rate': 3.928248689680101e-06, 'epoch': 1.74}
{'loss': 0.4108, 'learning_rate': 3.925537682992952e-06, 'epoch': 1.74}
{'loss': 0.8558, 'learning_rate': 3.9228266763058015e-06, 'epoch': 1.74}
{'loss': 0.2474, 'learning_rate': 3.9201156696186525e-06, 'epoch': 1.74}
{'loss': 1.2344, 'learning_rate': 3.917404662931502e-06, 'epoch': 1.74}
{'loss': 1.1337, 'learning_rate': 3.914693656244353e-06, 'epoch': 1.74}
{'loss': 1.0948, 'learning_rate': 3.911982649557202e-06, 'epoch': 1.74}
{'loss': 0.2201, 'learning_rate': 3.909271642870053e-06, 'epoch': 1.74}
{'loss': 0.7572, 'learning_rate': 3.906560636182902e-06, 'epoch': 1.74}
{'loss': 0.9082, 'learning_rate': 3.903849629495753e-06, 'epoch': 1.74}
{'loss': 0.4791, 'learning_rate': 3.9011386228086026e-06, 'epoch': 1.74}
{'loss': 0.3645, 'learning_rate': 3.8984276161214535e-06, 'epoch': 1.74}
{'loss': 0.6059, 'learning_rate': 3.895716609434304e-06, 'epoch': 1.74}
{'loss': 0.7769, 'learning_rate': 3.893005602747154e-06, 'epoch': 1.74}
{'loss': 0.761, 'learning_rate': 3.890294596060004e-06, 'epoch': 1.74}
{'loss': 1.1946, 'learning_rate': 3.887583589372854e-06, 'epoch': 1.74}
{'loss': 1.0597, 'learning_rate': 3.884872582685704e-06, 'epoch': 1.74}
{'loss': 0.332, 'learning_rate': 3.882161575998554e-06, 'epoch': 1.74}
{'loss': 0.7806, 'learning_rate': 3.8794505693114045e-06, 'epoch': 1.74}
{'loss': 0.9545, 'learning_rate': 3.876739562624255e-06, 'epoch': 1.74}
{'loss': 0.3832, 'learning_rate': 3.874028555937105e-06, 'epoch': 1.74}
{'loss': 0.4418, 'learning_rate': 3.871317549249955e-06, 'epoch': 1.74}
{'loss': 0.4998, 'learning_rate': 3.868606542562805e-06, 'epoch': 1.74}
{'loss': 0.6852, 'learning_rate': 3.865895535875656e-06, 'epoch': 1.74}
{'loss': 1.0239, 'learning_rate': 3.863184529188505e-06, 'epoch': 1.74}
{'loss': 2.0141, 'learning_rate': 3.860473522501356e-06, 'epoch': 1.74}
{'loss': 1.022, 'learning_rate': 3.8577625158142056e-06, 'epoch': 1.74}
{'loss': 0.8086, 'learning_rate': 3.8550515091270565e-06, 'epoch': 1.74}
{'loss': 0.8456, 'learning_rate': 3.852340502439906e-06, 'epoch': 1.74}
{'loss': 1.0007, 'learning_rate': 3.849629495752757e-06, 'epoch': 1.74}
{'loss': 1.0984, 'learning_rate': 3.846918489065606e-06, 'epoch': 1.74}
{'loss': 1.0914, 'learning_rate': 3.844207482378457e-06, 'epoch': 1.74}
{'loss': 0.8604, 'learning_rate': 3.841496475691307e-06, 'epoch': 1.74}
{'loss': 0.8404, 'learning_rate': 3.838785469004157e-06, 'epoch': 1.74}
{'loss': 0.3993, 'learning_rate': 3.8360744623170075e-06, 'epoch': 1.74}
{'loss': 0.9564, 'learning_rate': 3.833363455629857e-06, 'epoch': 1.74}
{'loss': 0.8051, 'learning_rate': 3.830652448942708e-06, 'epoch': 1.74}
{'loss': 0.6171, 'learning_rate': 3.827941442255557e-06, 'epoch': 1.74}
{'loss': 0.3182, 'learning_rate': 3.825230435568408e-06, 'epoch': 1.74}
{'loss': 0.4127, 'learning_rate': 3.822519428881257e-06, 'epoch': 1.75}
{'loss': 0.6127, 'learning_rate': 3.819808422194108e-06, 'epoch': 1.75}
{'loss': 0.7271, 'learning_rate': 3.817097415506958e-06, 'epoch': 1.75}
{'loss': 1.0005, 'learning_rate': 3.8143864088198086e-06, 'epoch': 1.75}
{'loss': 0.5633, 'learning_rate': 3.8116754021326583e-06, 'epoch': 1.75}
{'loss': 0.7104, 'learning_rate': 3.808964395445509e-06, 'epoch': 1.75}
{'loss': 0.5262, 'learning_rate': 3.8062533887583585e-06, 'epoch': 1.75}
{'loss': 0.7421, 'learning_rate': 3.803542382071209e-06, 'epoch': 1.75}
{'loss': 0.511, 'learning_rate': 3.800831375384059e-06, 'epoch': 1.75}
{'loss': 0.8114, 'learning_rate': 3.7981203686969098e-06, 'epoch': 1.75}
{'loss': 0.3933, 'learning_rate': 3.7954093620097595e-06, 'epoch': 1.75}
{'loss': 0.8046, 'learning_rate': 3.79269835532261e-06, 'epoch': 1.75}
{'loss': 0.9466, 'learning_rate': 3.7899873486354598e-06, 'epoch': 1.75}
{'loss': 0.8342, 'learning_rate': 3.7872763419483103e-06, 'epoch': 1.75}
{'loss': 0.3141, 'learning_rate': 3.78456533526116e-06, 'epoch': 1.75}
{'loss': 1.3991, 'learning_rate': 3.7818543285740106e-06, 'epoch': 1.75}
{'loss': 0.4658, 'learning_rate': 3.7791433218868603e-06, 'epoch': 1.75}
{'loss': 0.9234, 'learning_rate': 3.776432315199711e-06, 'epoch': 1.75}
{'loss': 1.1364, 'learning_rate': 3.7737213085125606e-06, 'epoch': 1.75}
{'loss': 0.2972, 'learning_rate': 3.7710103018254116e-06, 'epoch': 1.75}
{'loss': 0.7504, 'learning_rate': 3.7682992951382613e-06, 'epoch': 1.75}
{'loss': 0.859, 'learning_rate': 3.765588288451112e-06, 'epoch': 1.75}
{'loss': 0.2717, 'learning_rate': 3.7628772817639615e-06, 'epoch': 1.75}
{'loss': 0.5946, 'learning_rate': 3.760166275076812e-06, 'epoch': 1.75}
{'loss': 0.8904, 'learning_rate': 3.757455268389662e-06, 'epoch': 1.75}
{'loss': 1.1015, 'learning_rate': 3.7547442617025124e-06, 'epoch': 1.75}
{'loss': 0.3232, 'learning_rate': 3.752033255015362e-06, 'epoch': 1.75}
{'loss': 1.6057, 'learning_rate': 3.7493222483282126e-06, 'epoch': 1.75}
{'loss': 0.7313, 'learning_rate': 3.7466112416410628e-06, 'epoch': 1.75}
{'loss': 0.4386, 'learning_rate': 3.743900234953913e-06, 'epoch': 1.75}
{'loss': 0.8, 'learning_rate': 3.7411892282667635e-06, 'epoch': 1.75}
{'loss': 0.6676, 'learning_rate': 3.7384782215796136e-06, 'epoch': 1.75}
{'loss': 0.4684, 'learning_rate': 3.7357672148924637e-06, 'epoch': 1.75}
{'loss': 0.8062, 'learning_rate': 3.733056208205314e-06, 'epoch': 1.75}
{'loss': 0.5703, 'learning_rate': 3.730345201518164e-06, 'epoch': 1.75}
{'loss': 0.6991, 'learning_rate': 3.727634194831014e-06, 'epoch': 1.75}
{'loss': 0.525, 'learning_rate': 3.7249231881438643e-06, 'epoch': 1.75}
{'loss': 0.988, 'learning_rate': 3.7222121814567144e-06, 'epoch': 1.75}

 88%|████████▊ | 9694/11066 [35:30<04:58,  4.60it/s]
 88%|████████▊ | 9695/11066 [35:31<05:00,  4.57it/s]
                                                    

 88%|████████▊ | 9695/11066 [35:31<05:00,  4.57it/s]
 88%|████████▊ | 9696/11066 [35:31<04:58,  4.58it/s]
                                                    

 88%|████████▊ | 9696/11066 [35:31<04:58,  4.58it/s]
 88%|████████▊ | 9697/11066 [35:31<05:01,  4.54it/s]
                                                    

 88%|████████▊ | 9697/11066 [35:31<05:01,  4.54it/s]
 88%|████████▊ | 9698/11066 [35:31<05:02,  4.52it/s]
                                                    

 88%|████████▊ | 9698/11066 [35:31<05:02,  4.52it/s]
 88%|████████▊ | 9699/11066 [35:32<05:03,  4.51it/s]
                                                    

 88%|████████▊ | 9699/11066 [35:32<05:03,  4.51it/s]
 88%|████████▊ | 9700/11066 [35:32<04:59,  4.56it/s]
                                                    

 88%|████████▊ | 9700/11066 [35:32<04:59,  4.56it/s]
 88%|████████▊ | 9701/11066 [35:32<04:56,  4.61it/s]
                                                    

 88%|████████▊ | 9701/11066 [35:32<04:56,  4.61it/s]
 88%|████████▊ | 9702/11066 [35:32<04:58,  4.57it/s]
                                                    

 88%|████████▊ | 9702/11066 [35:32<04:58,  4.57it/s]
 88%|████████▊ | 9703/11066 [35:32<04:55,  4.62it/s]
                                                    

 88%|████████▊ | 9703/11066 [35:32<04:55,  4.62it/s]
 88%|████████▊ | 9704/11066 [35:33<04:51,  4.67it/s]
                                                    

 88%|████████▊ | 9704/11066 [35:33<04:51,  4.67it/s]
 88%|████████▊ | 9705/11066 [35:33<04:55,  4.61it/s]
                                                    

 88%|████████▊ | 9705/11066 [35:33<04:55,  4.61it/s]
 88%|████████▊ | 9706/11066 [35:33<04:54,  4.61it/s]
                                                    

 88%|████████▊ | 9706/11066 [35:33<04:54,  4.61it/s]
 88%|████████▊ | 9707/11066 [35:33<04:53,  4.62it/s]
                                                    

 88%|████████▊ | 9707/11066 [35:33<04:53,  4.62it/s]
 88%|████████▊ | 9708/11066 [35:34<04:57,  4.57it/s]
                                                    

 88%|████████▊ | 9708/11066 [35:34<04:57,  4.57it/s]
 88%|████████▊ | 9709/11066 [35:34<04:56,  4.58it/s]
                                                    

 88%|████████▊ | 9709/11066 [35:34<04:56,  4.58it/s]
 88%|████████▊ | 9710/11066 [35:34<04:57,  4.56it/s]
                                                    

 88%|████████▊ | 9710/11066 [35:34<04:57,  4.56it/s]
 88%|████████▊ | 9711/11066 [35:34<04:59,  4.52it/s]
                                                    

 88%|████████▊ | 9711/11066 [35:34<04:59,  4.52it/s]
 88%|████████▊ | 9712/11066 [35:34<04:58,  4.54it/s]
                                                    

 88%|████████▊ | 9712/11066 [35:34<04:58,  4.54it/s]
 88%|████████▊ | 9713/11066 [35:35<04:59,  4.52it/s]
                                                    

 88%|████████▊ | 9713/11066 [35:35<04:59,  4.52it/s]
 88%|████████▊ | 9714/11066 [35:35<04:57,  4.54it/s]
                                                    

 88%|████████▊ | 9714/11066 [35:35<04:57,  4.54it/s]
 88%|████████▊ | 9715/11066 [35:35<04:54,  4.59it/s]
                                                    

 88%|████████▊ | 9715/11066 [35:35<04:54,  4.59it/s]
 88%|████████▊ | 9716/11066 [35:35<04:53,  4.61it/s]
                                                    

 88%|████████▊ | 9716/11066 [35:35<04:53,  4.61it/s]
 88%|████████▊ | 9717/11066 [35:36<04:54,  4.58it/s]
                                                    

 88%|████████▊ | 9717/11066 [35:36<04:54,  4.58it/s]
 88%|████████▊ | 9718/11066 [35:36<04:51,  4.62it/s]
                                                    

 88%|████████▊ | 9718/11066 [35:36<04:51,  4.62it/s]
 88%|████████▊ | 9719/11066 [35:36<04:50,  4.64it/s]
                                                    

 88%|████████▊ | 9719/11066 [35:36<04:50,  4.64it/s]
 88%|████████▊ | 9720/11066 [35:36<04:54,  4.58it/s]
                                                    

 88%|████████▊ | 9720/11066 [35:36<04:54,  4.58it/s]
 88%|████████▊ | 9721/11066 [35:36<04:57,  4.52it/s]
                                                    

 88%|████████▊ | 9721/11066 [35:36<04:57,  4.52it/s]
 88%|████████▊ | 9722/11066 [35:37<04:59,  4.49it/s]
                                                    

 88%|████████▊ | 9722/11066 [35:37<04:59,  4.49it/s]
 88%|████████▊ | 9723/11066 [35:37<04:59,  4.49it/s]
                                                    

 88%|████████▊ | 9723/11066 [35:37<04:59,  4.49it/s]
 88%|████████▊ | 9724/11066 [35:37<04:58,  4.49it/s]
                                                    

 88%|████████▊ | 9724/11066 [35:37<04:58,  4.49it/s]
 88%|████████▊ | 9725/11066 [35:37<04:58,  4.49it/s]
                                                    

 88%|████████▊ | 9725/11066 [35:37<04:58,  4.49it/s]
 88%|████████▊ | 9726/11066 [35:38<04:58,  4.49it/s]
                                                    

 88%|████████▊ | 9726/11066 [35:38<04:58,  4.49it/s]
 88%|████████▊ | 9727/11066 [35:38<04:57,  4.50it/s]
                                                    

 88%|████████▊ | 9727/11066 [35:38<04:57,  4.50it/s]
 88%|████████▊ | 9728/11066 [35:38<04:57,  4.50it/s]
                                                    

 88%|████████▊ | 9728/11066 [35:38<04:57,  4.50it/s]
 88%|████████▊ | 9729/11066 [35:38<04:57,  4.50it/s]
                                                    

 88%|████████▊ | 9729/11066 [35:38<04:57,  4.50it/s]
 88%|████████▊ | 9730/11066 [35:38<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9730/11066 [35:38<04:56,  4.50it/s]
 88%|████████▊ | 9731/11066 [35:39<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9731/11066 [35:39<04:56,  4.50it/s]
 88%|████████▊ | 9732/11066 [35:39<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9732/11066 [35:39<04:56,  4.50it/s]
 88%|████████▊ | 9733/11066 [35:39<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9733/11066 [35:39<04:56,  4.50it/s]
 88%|████████▊ | 9734/11066 [35:39<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9734/11066 [35:39<04:56,  4.50it/s]
 88%|████████▊ | 9735/11066 [35:40<04:56,  4.50it/s]
                                                    

 88%|████████▊ | 9735/11066 [35:40<04:56,  4.50it/s]
 88%|████████▊ | 9736/11066 [35:40<04:55,  4.50it/s]
                                                    

 88%|████████▊ | 9736/11066 [35:40<04:55,  4.50it/s]
 88%|████████▊ | 9737/11066 [35:40<04:55,  4.50it/s]
                                                    

 88%|████████▊ | 9737/11066 [35:40<04:55,  4.50it/s]
 88%|████████▊ | 9738/11066 [35:40<04:55,  4.50it/s]
                                                    

 88%|████████▊ | 9738/11066 [35:40<04:55,  4.50it/s]
 88%|████████▊ | 9739/11066 [35:40<04:54,  4.50it/s]
                                                    

 88%|████████▊ | 9739/11066 [35:40<04:54,  4.50it/s]
 88%|████████▊ | 9740/11066 [35:41<04:54,  4.50it/s]
                                                    

 88%|████████▊ | 9740/11066 [35:41<04:54,  4.50it/s]
 88%|████████▊ | 9741/11066 [35:41<04:54,  4.50it/s]
                                                    

 88%|████████▊ | 9741/11066 [35:41<04:54,  4.50it/s]
 88%|████████▊ | 9742/11066 [35:41<04:54,  4.50it/s]
                                                    

 88%|████████▊ | 9742/11066 [35:41<04:54,  4.50it/s]
 88%|████████▊ | 9743/11066 [35:41<04:56,  4.46it/s]
                                                    

 88%|████████▊ | 9743/11066 [35:41<04:56,  4.46it/s]
 88%|████████▊ | 9744/11066 [35:42<04:56,  4.46it/s]
                                                    

 88%|████████▊ | 9744/11066 [35:42<04:56,  4.46it/s]
 88%|████████▊ | 9745/11066 [35:42<04:55,  4.47it/s]
                                                    

 88%|████████▊ | 9745/11066 [35:42<04:55,  4.47it/s]
 88%|████████▊ | 9746/11066 [35:42<04:54,  4.48it/s]
                                                    

 88%|████████▊ | 9746/11066 [35:42<04:54,  4.48it/s]
 88%|████████▊ | 9747/11066 [35:42<04:54,  4.48it/s]
                                                    

 88%|████████▊ | 9747/11066 [35:42<04:54,  4.48it/s]
 88%|████████▊ | 9748/11066 [35:42<04:53,  4.50it/s]
                                                    

 88%|████████▊ | 9748/11066 [35:42<04:53,  4.50it/s]
 88%|████████▊ | 9749/11066 [35:43<04:53,  4.49it/s]
                                                    

 88%|████████▊ | 9749/11066 [35:43<04:53,  4.49it/s]
 88%|████████▊ | 9750/11066 [35:43<04:53,  4.49it/s]
                                                    

 88%|████████▊ | 9750/11066 [35:43<04:53,  4.49it/s]
 88%|████████▊ | 9751/11066 [35:43<04:49,  4.55it/s]
                                                    

 88%|████████▊ | 9751/11066 [35:43<04:49,  4.55it/s]
 88%|████████▊ | 9752/11066 [35:43<04:50,  4.52it/s]
                                                    

 88%|████████▊ | 9752/11066 [35:43<04:50,  4.52it/s]
 88%|████████▊ | 9753/11066 [35:44<04:52,  4.49it/s]
                                                    

 88%|████████▊ | 9753/11066 [35:44<04:52,  4.49it/s]
 88%|████████▊ | 9754/11066 [35:44<04:52,  4.49it/s]
                                                    

 88%|████████▊ | 9754/11066 [35:44<04:52,  4.49it/s]
 88%|████████▊ | 9755/11066 [35:44<04:51,  4.49it/s]
                                                    

 88%|████████▊ | 9755/11066 [35:44<04:51,  4.49it/s]
 88%|████████▊ | 9756/11066 [35:44<04:51,  4.50it/s]
                                                    

 88%|████████▊ | 9756/11066 [35:44<04:51,  4.50it/s]
 88%|████████▊ | 9757/11066 [35:44<04:51,  4.50it/s]
                                                    

 88%|████████▊ | 9757/11066 [35:44<04:51,  4.50it/s]
 88%|████████▊ | 9758/11066 [35:45<04:51,  4.49it/s]
                                                    

 88%|████████▊ | 9758/11066 [35:45<04:51,  4.49it/s]
 88%|████████▊ | 9759/11066 [35:45<04:51,  4.49it/s]
                                                    

 88%|████████▊ | 9759/11066 [35:45<04:51,  4.49it/s]
 88%|████████▊ | 9760/11066 [35:45<04:48,  4.52it/s]
                                                    

 88%|████████▊ | 9760/11066 [35:45<04:48,  4.52it/s]
 88%|████████▊ | 9761/11066 [35:45<04:50,  4.50it/s]
                                                    

 88%|████████▊ | 9761/11066 [35:45<04:50,  4.50it/s]
 88%|████████▊ | 9762/11066 [35:46<04:47,  4.53it/s]
                                                    

 88%|████████▊ | 9762/11066 [35:46<04:47,  4.53it/s]
 88%|████████▊ | 9763/11066 [35:46<04:50,  4.48it/s]
                                                    

 88%|████████▊ | 9763/11066 [35:46<04:50,  4.48it/s]
 88%|████████▊ | 9764/11066 [35:46<04:50,  4.48it/s]
                                                    

 88%|████████▊ | 9764/11066 [35:46<04:50,  4.48it/s]
 88%|████████▊ | 9765/11066 [35:46<04:50,  4.48it/s]
                                                    

 88%|████████▊ | 9765/11066 [35:46<04:50,  4.48it/s]
 88%|████████▊ | 9766/11066 [35:46<04:49,  4.49it/s]
                                                    

 88%|████████▊ | 9766/11066 [35:46<04:49,  4.49it/s]
 88%|████████▊ | 9767/11066 [35:47<04:49,  4.49it/s]
                                                    

 88%|████████▊ | 9767/11066 [35:47<04:49,  4.49it/s]
 88%|████████▊ | 9768/11066 [35:47<04:48,  4.49it/s]
                                                    

 88%|████████▊ | 9768/11066 [35:47<04:48,  4.49it/s]
 88%|████████▊ | 9769/11066 [35:47<04:48,  4.50it/s]
                                                    

 88%|████████▊ | 9769/11066 [35:47<04:48,  4.50it/s]
 88%|████████▊ | 9770/11066 [35:47<04:48,  4.49it/s]
                                                    

 88%|████████▊ | 9770/11066 [35:47<04:48,  4.49it/s]
 88%|████████▊ | 9771/11066 [35:48<04:48,  4.50it/s]
                                                    

 88%|████████▊ | 9771/11066 [35:48<04:48,  4.50it/s]
 88%|████████▊ | 9772/11066 [35:48<04:47,  4.50it/s]
                                                    

 88%|████████▊ | 9772/11066 [35:48<04:47,  4.50it/s]
 88%|████████▊ | 9773/11066 [35:48<04:47,  4.50it/s]
                                                    

 88%|████████▊ | 9773/11066 [35:48<04:47,  4.50it/s]
 88%|████████▊ | 9774/11066 [35:48<04:47,  4.50it/s]
                                                    

 88%|████████▊ | 9774/11066 [35:48<04:47,  4.50it/s]
 88%|████████▊ | 9775/11066 [35:48<04:47,  4.49it/s]
                                                    

 88%|████████▊ | 9775/11066 [35:48<04:47,  4.49it/s]
 88%|████████▊ | 9776/11066 [35:49<04:47,  4.48it/s]
                                                    

 88%|████████▊ | 9776/11066 [35:49<04:47,  4.48it/s]
 88%|████████▊ | 9777/11066 [35:49<04:49,  4.45it/s]
                                                    

 88%|████████▊ | 9777/11066 [35:49<04:49,  4.45it/s]
 88%|████████▊ | 9778/11066 [35:49<04:49,  4.45it/s]
                                                    

 88%|████████▊ | 9778/11066 [35:49<04:49,  4.45it/s]
 88%|████████▊ | 9779/11066 [35:49<04:52,  4.41it/s]
                                                    

 88%|████████▊ | 9779/11066 [35:49<04:52,  4.41it/s]
 88%|████████▊ | 9780/11066 [35:50<04:45,  4.50it/s]
                                                    

 88%|████████▊ | 9780/11066 [35:50<04:45,  4.50it/s]
 88%|████████▊ | 9781/11066 [35:50<04:51,  4.41it/s]
                                                    

 88%|████████▊ | 9781/11066 [35:50<04:51,  4.41it/s]
 88%|████████▊ | 9782/11066 [35:50<04:50,  4.42it/s]
                                                    

 88%|████████▊ | 9782/11066 [35:50<04:50,  4.42it/s]
 88%|████████▊ | 9783/11066 [35:50<04:48,  4.45it/s]
                                                    

 88%|████████▊ | 9783/11066 [35:50<04:48,  4.45it/s]
 88%|████████▊ | 9784/11066 [35:50<04:46,  4.47it/s]
                                                    

 88%|████████▊ | 9784/11066 [35:50<04:46,  4.47it/s]
 88%|████████▊ | 9785/11066 [35:51<04:45,  4.48it/s]
                                                    

 88%|████████▊ | 9785/11066 [35:51<04:45,  4.48it/s]
 88%|████████▊ | 9786/11066 [35:51<04:47,  4.46it/s]
                                                    

 88%|████████▊ | 9786/11066 [35:51<04:47,  4.46it/s]
 88%|████████▊ | 9787/11066 [35:51<04:47,  4.45it/s]
                                                    

 88%|████████▊ | 9787/11066 [35:51<04:47,  4.45it/s]
 88%|████████▊ | 9788/11066 [35:51<04:46,  4.45it/s]
                                                    

 88%|████████▊ | 9788/11066 [35:51<04:46,  4.45it/s]
 88%|████████▊ | 9789/11066 [35:52<04:46,  4.46it/s]
                                                    

 88%|████████▊ | 9789/11066 [35:52<04:46,  4.46it/s]
 88%|████████▊ | 9790/11066 [35:52<04:45,  4.47it/s]
                                                    

 88%|████████▊ | 9790/11066 [35:52<04:45,  4.47it/s]
 88%|████████▊ | 9791/11066 [35:52<04:44,  4.48it/s]
                                                    

 88%|████████▊ | 9791/11066 [35:52<04:44,  4.48it/s]
 88%|████████▊ | 9792/11066 [35:52<04:43,  4.49it/s]
                                                    

 88%|████████▊ | 9792/11066 [35:52<04:43,  4.49it/s]
 88%|████████▊ | 9793/11066 [35:52<04:43,  4.49it/s]
                                                    

 88%|████████▊ | 9793/11066 [35:52<04:43,  4.49it/s]
 89%|████████▊ | 9794/11066 [35:53<04:43,  4.49it/s]
                                                    

 89%|████████▊ | 9794/11066 [35:53<04:43,  4.49it/s]
 89%|████████▊ | 9795/11066 [35:53<04:42,  4.49it/s]
                                                    

 89%|████████▊ | 9795/11066 [35:53<04:42,  4.49it/s]
 89%|████████▊ | 9796/11066 [35:53<04:42,  4.50it/s]
                                                    

 89%|████████▊ | 9796/11066 [35:53<04:42,  4.50it/s]
 89%|████████▊ | 9797/11066 [35:53<04:41,  4.51it/s]
                                                    

 89%|████████▊ | 9797/11066 [35:53<04:41,  4.51it/s]
 89%|████████▊ | 9798/11066 [35:54<04:41,  4.50it/s]
                                                    

 89%|████████▊ | 9798/11066 [35:54<04:41,  4.50it/s]
 89%|████████▊ | 9799/11066 [35:54<04:47,  4.40it/s]
                                                    

 89%|████████▊ | 9799/11066 [35:54<04:47,  4.40it/s]
 89%|████████▊ | 9800/11066 [35:54<04:46,  4.42it/s]
                                                    

 89%|████████▊ | 9800/11066 [35:54<04:46,  4.42it/s]
 89%|████████▊ | 9801/11066 [35:54<04:44,  4.44it/s]
                                                    

 89%|████████▊ | 9801/11066 [35:54<04:44,  4.44it/s]
 89%|████████▊ | 9802/11066 [35:54<04:43,  4.45it/s]
                                                    

 89%|████████▊ | 9802/11066 [35:54<04:43,  4.45it/s]
 89%|████████▊ | 9803/11066 [35:55<04:42,  4.46it/s]
                                                    

 89%|████████▊ | 9803/11066 [35:55<04:42,  4.46it/s]
 89%|████████▊ | 9804/11066 [35:55<04:41,  4.48it/s]
                                                    

 89%|████████▊ | 9804/11066 [35:55<04:41,  4.48it/s]
 89%|████████▊ | 9805/11066 [35:55<04:41,  4.48it/s]
                                                    

 89%|████████▊ | 9805/11066 [35:55<04:41,  4.48it/s]
 89%|████████▊ | 9806/11066 [35:55<04:40,  4.49it/s]
                                                    

 89%|████████▊ | 9806/11066 [35:55<04:40,  4.49it/s]
 89%|████████▊ | 9807/11066 [35:56<04:40,  4.49it/s]
                                                    
{'loss': 0.816, 'learning_rate': 3.7195011747695645e-06, 'epoch': 1.75}
{'loss': 0.5835, 'learning_rate': 3.7167901680824147e-06, 'epoch': 1.75}
{'loss': 0.6724, 'learning_rate': 3.7140791613952652e-06, 'epoch': 1.75}
{'loss': 0.6507, 'learning_rate': 3.7113681547081154e-06, 'epoch': 1.75}
{'loss': 1.057, 'learning_rate': 3.7086571480209655e-06, 'epoch': 1.75}
{'loss': 0.5659, 'learning_rate': 3.7059461413338156e-06, 'epoch': 1.75}
{'loss': 1.067, 'learning_rate': 3.7032351346466658e-06, 'epoch': 1.75}
{'loss': 0.541, 'learning_rate': 3.700524127959516e-06, 'epoch': 1.75}
{'loss': 1.313, 'learning_rate': 3.697813121272366e-06, 'epoch': 1.75}
{'loss': 0.5392, 'learning_rate': 3.695102114585216e-06, 'epoch': 1.75}
{'loss': 1.1528, 'learning_rate': 3.6923911078980663e-06, 'epoch': 1.75}
{'loss': 0.3625, 'learning_rate': 3.6896801012109164e-06, 'epoch': 1.75}
{'loss': 1.1705, 'learning_rate': 3.6869690945237666e-06, 'epoch': 1.75}
{'loss': 0.8562, 'learning_rate': 3.684258087836617e-06, 'epoch': 1.75}
{'loss': 0.6913, 'learning_rate': 3.6815470811494673e-06, 'epoch': 1.75}
{'loss': 0.6998, 'learning_rate': 3.6788360744623174e-06, 'epoch': 1.75}
{'loss': 0.3408, 'learning_rate': 3.6761250677751675e-06, 'epoch': 1.75}
{'loss': 0.28, 'learning_rate': 3.6734140610880177e-06, 'epoch': 1.76}
{'loss': 0.9793, 'learning_rate': 3.670703054400868e-06, 'epoch': 1.76}
{'loss': 0.6835, 'learning_rate': 3.667992047713718e-06, 'epoch': 1.76}
{'loss': 0.8273, 'learning_rate': 3.665281041026568e-06, 'epoch': 1.76}
{'loss': 0.6126, 'learning_rate': 3.6625700343394178e-06, 'epoch': 1.76}
{'loss': 1.2518, 'learning_rate': 3.659859027652268e-06, 'epoch': 1.76}
{'loss': 0.7079, 'learning_rate': 3.6571480209651185e-06, 'epoch': 1.76}
{'loss': 0.4783, 'learning_rate': 3.6544370142779686e-06, 'epoch': 1.76}
{'loss': 0.8771, 'learning_rate': 3.6517260075908187e-06, 'epoch': 1.76}
{'loss': 0.9096, 'learning_rate': 3.649015000903669e-06, 'epoch': 1.76}
{'loss': 1.0454, 'learning_rate': 3.646303994216519e-06, 'epoch': 1.76}
{'loss': 0.4047, 'learning_rate': 3.643592987529369e-06, 'epoch': 1.76}
{'loss': 0.7325, 'learning_rate': 3.6408819808422193e-06, 'epoch': 1.76}
{'loss': 0.431, 'learning_rate': 3.6381709741550694e-06, 'epoch': 1.76}
{'loss': 0.605, 'learning_rate': 3.6354599674679195e-06, 'epoch': 1.76}
{'loss': 0.9432, 'learning_rate': 3.6327489607807697e-06, 'epoch': 1.76}
{'loss': 1.3015, 'learning_rate': 3.6300379540936202e-06, 'epoch': 1.76}
{'loss': 0.6279, 'learning_rate': 3.6273269474064704e-06, 'epoch': 1.76}
{'loss': 0.8901, 'learning_rate': 3.6246159407193205e-06, 'epoch': 1.76}
{'loss': 0.553, 'learning_rate': 3.6219049340321706e-06, 'epoch': 1.76}
{'loss': 1.6206, 'learning_rate': 3.6191939273450208e-06, 'epoch': 1.76}
{'loss': 0.4881, 'learning_rate': 3.616482920657871e-06, 'epoch': 1.76}
{'loss': 0.9155, 'learning_rate': 3.613771913970721e-06, 'epoch': 1.76}
{'loss': 0.471, 'learning_rate': 3.611060907283571e-06, 'epoch': 1.76}
{'loss': 0.5447, 'learning_rate': 3.6083499005964213e-06, 'epoch': 1.76}
{'loss': 0.471, 'learning_rate': 3.6056388939092714e-06, 'epoch': 1.76}
{'loss': 0.3651, 'learning_rate': 3.6029278872221216e-06, 'epoch': 1.76}
{'loss': 0.6613, 'learning_rate': 3.600216880534972e-06, 'epoch': 1.76}
{'loss': 0.5009, 'learning_rate': 3.5975058738478223e-06, 'epoch': 1.76}
{'loss': 0.8997, 'learning_rate': 3.5947948671606724e-06, 'epoch': 1.76}
{'loss': 0.5292, 'learning_rate': 3.5920838604735225e-06, 'epoch': 1.76}
{'loss': 0.5906, 'learning_rate': 3.5893728537863727e-06, 'epoch': 1.76}
{'loss': 0.6701, 'learning_rate': 3.586661847099223e-06, 'epoch': 1.76}
{'loss': 0.8378, 'learning_rate': 3.583950840412073e-06, 'epoch': 1.76}
{'loss': 0.5185, 'learning_rate': 3.581239833724923e-06, 'epoch': 1.76}
{'loss': 0.476, 'learning_rate': 3.578528827037773e-06, 'epoch': 1.76}
{'loss': 0.6434, 'learning_rate': 3.5758178203506233e-06, 'epoch': 1.76}
{'loss': 0.875, 'learning_rate': 3.573106813663474e-06, 'epoch': 1.76}
{'loss': 0.8034, 'learning_rate': 3.570395806976324e-06, 'epoch': 1.76}
{'loss': 0.6604, 'learning_rate': 3.567684800289174e-06, 'epoch': 1.76}
{'loss': 0.576, 'learning_rate': 3.5649737936020243e-06, 'epoch': 1.76}
{'loss': 0.4867, 'learning_rate': 3.5622627869148744e-06, 'epoch': 1.76}
{'loss': 0.6011, 'learning_rate': 3.5595517802277246e-06, 'epoch': 1.76}
{'loss': 1.1433, 'learning_rate': 3.5568407735405747e-06, 'epoch': 1.76}
{'loss': 0.8277, 'learning_rate': 3.554129766853425e-06, 'epoch': 1.76}
{'loss': 0.6959, 'learning_rate': 3.551418760166275e-06, 'epoch': 1.76}
{'loss': 0.9101, 'learning_rate': 3.548707753479125e-06, 'epoch': 1.76}
{'loss': 1.0671, 'learning_rate': 3.5459967467919752e-06, 'epoch': 1.76}
{'loss': 0.3417, 'learning_rate': 3.543285740104826e-06, 'epoch': 1.76}
{'loss': 0.3381, 'learning_rate': 3.540574733417676e-06, 'epoch': 1.76}
{'loss': 0.6561, 'learning_rate': 3.537863726730526e-06, 'epoch': 1.76}
{'loss': 1.0139, 'learning_rate': 3.535152720043376e-06, 'epoch': 1.76}
{'loss': 1.0067, 'learning_rate': 3.5324417133562263e-06, 'epoch': 1.76}
{'loss': 0.5368, 'learning_rate': 3.5297307066690765e-06, 'epoch': 1.76}
{'loss': 1.6751, 'learning_rate': 3.5270196999819266e-06, 'epoch': 1.76}
{'loss': 0.554, 'learning_rate': 3.5243086932947767e-06, 'epoch': 1.77}
{'loss': 0.7174, 'learning_rate': 3.521597686607627e-06, 'epoch': 1.77}
{'loss': 1.5647, 'learning_rate': 3.518886679920477e-06, 'epoch': 1.77}
{'loss': 0.6134, 'learning_rate': 3.5161756732333276e-06, 'epoch': 1.77}
{'loss': 0.5974, 'learning_rate': 3.5134646665461777e-06, 'epoch': 1.77}
{'loss': 1.3361, 'learning_rate': 3.510753659859028e-06, 'epoch': 1.77}
{'loss': 1.0205, 'learning_rate': 3.508042653171878e-06, 'epoch': 1.77}
{'loss': 0.9668, 'learning_rate': 3.505331646484728e-06, 'epoch': 1.77}
{'loss': 0.7642, 'learning_rate': 3.5026206397975782e-06, 'epoch': 1.77}
{'loss': 1.0051, 'learning_rate': 3.4999096331104284e-06, 'epoch': 1.77}
{'loss': 0.4828, 'learning_rate': 3.4971986264232785e-06, 'epoch': 1.77}
{'loss': 0.8115, 'learning_rate': 3.4944876197361286e-06, 'epoch': 1.77}
{'loss': 0.8454, 'learning_rate': 3.4917766130489788e-06, 'epoch': 1.77}
{'loss': 0.7556, 'learning_rate': 3.489065606361829e-06, 'epoch': 1.77}
{'loss': 0.7336, 'learning_rate': 3.4863545996746795e-06, 'epoch': 1.77}
{'loss': 0.5414, 'learning_rate': 3.4836435929875296e-06, 'epoch': 1.77}
{'loss': 0.9604, 'learning_rate': 3.4809325863003797e-06, 'epoch': 1.77}
{'loss': 0.8943, 'learning_rate': 3.47822157961323e-06, 'epoch': 1.77}
{'loss': 0.6449, 'learning_rate': 3.47551057292608e-06, 'epoch': 1.77}
{'loss': 0.9081, 'learning_rate': 3.47279956623893e-06, 'epoch': 1.77}
{'loss': 0.4128, 'learning_rate': 3.4700885595517803e-06, 'epoch': 1.77}
{'loss': 0.8146, 'learning_rate': 3.4673775528646304e-06, 'epoch': 1.77}
{'loss': 0.9921, 'learning_rate': 3.4646665461774805e-06, 'epoch': 1.77}
{'loss': 0.4494, 'learning_rate': 3.4619555394903307e-06, 'epoch': 1.77}
{'loss': 0.7012, 'learning_rate': 3.4592445328031812e-06, 'epoch': 1.77}
{'loss': 0.952, 'learning_rate': 3.4565335261160314e-06, 'epoch': 1.77}
{'loss': 0.456, 'learning_rate': 3.4538225194288815e-06, 'epoch': 1.77}
{'loss': 1.187, 'learning_rate': 3.4511115127417316e-06, 'epoch': 1.77}
{'loss': 0.6563, 'learning_rate': 3.4484005060545818e-06, 'epoch': 1.77}
{'loss': 1.1464, 'learning_rate': 3.445689499367432e-06, 'epoch': 1.77}
{'loss': 0.616, 'learning_rate': 3.442978492680282e-06, 'epoch': 1.77}
{'loss': 0.4379, 'learning_rate': 3.440267485993132e-06, 'epoch': 1.77}
{'loss': 0.7548, 'learning_rate': 3.4375564793059823e-06, 'epoch': 1.77}
{'loss': 0.482, 'learning_rate': 3.4348454726188324e-06, 'epoch': 1.77}
{'loss': 1.0727, 'learning_rate': 3.4321344659316826e-06, 'epoch': 1.77}
{'loss': 0.3801, 'learning_rate': 3.429423459244533e-06, 'epoch': 1.77}
{'loss': 0.6252, 'learning_rate': 3.4267124525573833e-06, 'epoch': 1.77}
{'loss': 0.8532, 'learning_rate': 3.4240014458702334e-06, 'epoch': 1.77}
{'loss': 0.647, 'learning_rate': 3.4212904391830835e-06, 'epoch': 1.77}
{'loss': 0.9253, 'learning_rate': 3.4185794324959337e-06, 'epoch': 1.77}
{'loss': 0.62, 'learning_rate': 3.415868425808784e-06, 'epoch': 1.77}

 89%|████████▊ | 9807/11066 [35:56<04:40,  4.49it/s]
 89%|████████▊ | 9808/11066 [35:56<04:39,  4.49it/s]
                                                    

 89%|████████▊ | 9808/11066 [35:56<04:39,  4.49it/s]
 89%|████████▊ | 9809/11066 [35:56<04:39,  4.50it/s]
                                                    

 89%|████████▊ | 9809/11066 [35:56<04:39,  4.50it/s]
 89%|████████▊ | 9810/11066 [35:56<04:39,  4.50it/s]
                                                    

 89%|████████▊ | 9810/11066 [35:56<04:39,  4.50it/s]
 89%|████████▊ | 9811/11066 [35:56<04:38,  4.50it/s]
                                                    

 89%|████████▊ | 9811/11066 [35:56<04:38,  4.50it/s]
 89%|████████▊ | 9812/11066 [35:57<04:38,  4.50it/s]
                                                    

 89%|████████▊ | 9812/11066 [35:57<04:38,  4.50it/s]
 89%|████████▊ | 9813/11066 [35:57<04:36,  4.54it/s]
                                                    

 89%|████████▊ | 9813/11066 [35:57<04:36,  4.54it/s]
 89%|████████▊ | 9814/11066 [35:57<04:33,  4.57it/s]
                                                    

 89%|████████▊ | 9814/11066 [35:57<04:33,  4.57it/s]
 89%|████████▊ | 9815/11066 [35:57<04:31,  4.61it/s]
                                                    

 89%|████████▊ | 9815/11066 [35:57<04:31,  4.61it/s]
 89%|████████▊ | 9816/11066 [35:58<04:29,  4.64it/s]
                                                    

 89%|████████▊ | 9816/11066 [35:58<04:29,  4.64it/s]
 89%|████████▊ | 9817/11066 [35:58<04:34,  4.55it/s]
                                                    

 89%|████████▊ | 9817/11066 [35:58<04:34,  4.55it/s]
 89%|████████▊ | 9818/11066 [35:58<04:36,  4.52it/s]
                                                    

 89%|████████▊ | 9818/11066 [35:58<04:36,  4.52it/s]
 89%|████████▊ | 9819/11066 [35:58<04:40,  4.44it/s]
                                                    

 89%|████████▊ | 9819/11066 [35:58<04:40,  4.44it/s]
 89%|████████▊ | 9820/11066 [35:58<04:39,  4.45it/s]
                                                    

 89%|████████▊ | 9820/11066 [35:58<04:39,  4.45it/s]
 89%|████████▊ | 9821/11066 [35:59<04:38,  4.47it/s]
                                                    

 89%|████████▊ | 9821/11066 [35:59<04:38,  4.47it/s]
 89%|████████▉ | 9822/11066 [35:59<04:38,  4.47it/s]
                                                    

 89%|████████▉ | 9822/11066 [35:59<04:38,  4.47it/s]
 89%|████████▉ | 9823/11066 [35:59<04:35,  4.52it/s]
                                                    

 89%|████████▉ | 9823/11066 [35:59<04:35,  4.52it/s]
 89%|████████▉ | 9824/11066 [35:59<04:31,  4.57it/s]
                                                    

 89%|████████▉ | 9824/11066 [35:59<04:31,  4.57it/s]
 89%|████████▉ | 9825/11066 [36:00<04:34,  4.53it/s]
                                                    

 89%|████████▉ | 9825/11066 [36:00<04:34,  4.53it/s]
 89%|████████▉ | 9826/11066 [36:00<04:34,  4.52it/s]
                                                    

 89%|████████▉ | 9826/11066 [36:00<04:34,  4.52it/s]
 89%|████████▉ | 9827/11066 [36:00<04:32,  4.54it/s]
                                                    

 89%|████████▉ | 9827/11066 [36:00<04:32,  4.54it/s]
 89%|████████▉ | 9828/11066 [36:00<04:31,  4.56it/s]
                                                    

 89%|████████▉ | 9828/11066 [36:00<04:31,  4.56it/s]
 89%|████████▉ | 9829/11066 [36:00<04:31,  4.56it/s]
                                                    

 89%|████████▉ | 9829/11066 [36:00<04:31,  4.56it/s]
 89%|████████▉ | 9830/11066 [36:01<04:33,  4.52it/s]
                                                    

 89%|████████▉ | 9830/11066 [36:01<04:33,  4.52it/s]
 89%|████████▉ | 9831/11066 [36:01<04:34,  4.51it/s]
                                                    

 89%|████████▉ | 9831/11066 [36:01<04:34,  4.51it/s]
 89%|████████▉ | 9832/11066 [36:01<04:30,  4.56it/s]
                                                    

 89%|████████▉ | 9832/11066 [36:01<04:30,  4.56it/s]
 89%|████████▉ | 9833/11066 [36:01<04:31,  4.54it/s]
                                                    

 89%|████████▉ | 9833/11066 [36:01<04:31,  4.54it/s]
 89%|████████▉ | 9834/11066 [36:02<04:32,  4.52it/s]
                                                    

 89%|████████▉ | 9834/11066 [36:02<04:32,  4.52it/s]
 89%|████████▉ | 9835/11066 [36:02<04:33,  4.50it/s]
                                                    

 89%|████████▉ | 9835/11066 [36:02<04:33,  4.50it/s]
 89%|████████▉ | 9836/11066 [36:02<04:31,  4.53it/s]
                                                    

 89%|████████▉ | 9836/11066 [36:02<04:31,  4.53it/s]
 89%|████████▉ | 9837/11066 [36:02<04:29,  4.57it/s]
                                                    

 89%|████████▉ | 9837/11066 [36:02<04:29,  4.57it/s]
 89%|████████▉ | 9838/11066 [36:02<04:28,  4.57it/s]
                                                    

 89%|████████▉ | 9838/11066 [36:02<04:28,  4.57it/s]
 89%|████████▉ | 9839/11066 [36:03<04:27,  4.58it/s]
                                                    

 89%|████████▉ | 9839/11066 [36:03<04:27,  4.58it/s]
 89%|████████▉ | 9840/11066 [36:03<04:29,  4.55it/s]
                                                    

 89%|████████▉ | 9840/11066 [36:03<04:29,  4.55it/s]
 89%|████████▉ | 9841/11066 [36:03<04:29,  4.55it/s]
                                                    

 89%|████████▉ | 9841/11066 [36:03<04:29,  4.55it/s]
 89%|████████▉ | 9842/11066 [36:03<04:30,  4.53it/s]
                                                    

 89%|████████▉ | 9842/11066 [36:03<04:30,  4.53it/s]
 89%|████████▉ | 9843/11066 [36:04<04:29,  4.54it/s]
                                                    

 89%|████████▉ | 9843/11066 [36:04<04:29,  4.54it/s]
 89%|████████▉ | 9844/11066 [36:04<04:31,  4.51it/s]
                                                    

 89%|████████▉ | 9844/11066 [36:04<04:31,  4.51it/s]
 89%|████████▉ | 9845/11066 [36:04<04:29,  4.53it/s]
                                                    

 89%|████████▉ | 9845/11066 [36:04<04:29,  4.53it/s]
 89%|████████▉ | 9846/11066 [36:04<04:25,  4.59it/s]
                                                    

 89%|████████▉ | 9846/11066 [36:04<04:25,  4.59it/s]
 89%|████████▉ | 9847/11066 [36:04<04:24,  4.61it/s]
                                                    

 89%|████████▉ | 9847/11066 [36:04<04:24,  4.61it/s]
 89%|████████▉ | 9848/11066 [36:05<04:26,  4.57it/s]
                                                    

 89%|████████▉ | 9848/11066 [36:05<04:26,  4.57it/s]
 89%|████████▉ | 9849/11066 [36:05<04:27,  4.54it/s]
                                                    

 89%|████████▉ | 9849/11066 [36:05<04:27,  4.54it/s]
 89%|████████▉ | 9850/11066 [36:05<04:28,  4.53it/s]
                                                    

 89%|████████▉ | 9850/11066 [36:05<04:28,  4.53it/s]
 89%|████████▉ | 9851/11066 [36:05<04:28,  4.53it/s]
                                                    

 89%|████████▉ | 9851/11066 [36:05<04:28,  4.53it/s]
 89%|████████▉ | 9852/11066 [36:05<04:27,  4.55it/s]
                                                    

 89%|████████▉ | 9852/11066 [36:05<04:27,  4.55it/s]
 89%|████████▉ | 9853/11066 [36:06<04:26,  4.55it/s]
                                                    

 89%|████████▉ | 9853/11066 [36:06<04:26,  4.55it/s]
 89%|████████▉ | 9854/11066 [36:06<04:23,  4.60it/s]
                                                    

 89%|████████▉ | 9854/11066 [36:06<04:23,  4.60it/s]
 89%|████████▉ | 9855/11066 [36:06<04:21,  4.63it/s]
                                                    

 89%|████████▉ | 9855/11066 [36:06<04:21,  4.63it/s]
 89%|████████▉ | 9856/11066 [36:06<04:20,  4.65it/s]
                                                    

 89%|████████▉ | 9856/11066 [36:06<04:20,  4.65it/s]
 89%|████████▉ | 9857/11066 [36:07<04:20,  4.65it/s]
                                                    

 89%|████████▉ | 9857/11066 [36:07<04:20,  4.65it/s]
 89%|████████▉ | 9858/11066 [36:07<04:23,  4.59it/s]
                                                    

 89%|████████▉ | 9858/11066 [36:07<04:23,  4.59it/s]
 89%|████████▉ | 9859/11066 [36:07<04:22,  4.59it/s]
                                                    

 89%|████████▉ | 9859/11066 [36:07<04:22,  4.59it/s]
 89%|████████▉ | 9860/11066 [36:07<04:20,  4.64it/s]
                                                    

 89%|████████▉ | 9860/11066 [36:07<04:20,  4.64it/s]
 89%|████████▉ | 9861/11066 [36:07<04:19,  4.64it/s]
                                                    

 89%|████████▉ | 9861/11066 [36:07<04:19,  4.64it/s]
 89%|████████▉ | 9862/11066 [36:08<04:22,  4.59it/s]
                                                    

 89%|████████▉ | 9862/11066 [36:08<04:22,  4.59it/s]
 89%|████████▉ | 9863/11066 [36:08<04:22,  4.57it/s]
                                                    

 89%|████████▉ | 9863/11066 [36:08<04:22,  4.57it/s]
 89%|████████▉ | 9864/11066 [36:08<04:22,  4.57it/s]
                                                    

 89%|████████▉ | 9864/11066 [36:08<04:22,  4.57it/s]
 89%|████████▉ | 9865/11066 [36:08<04:21,  4.60it/s]
                                                    

 89%|████████▉ | 9865/11066 [36:08<04:21,  4.60it/s]
 89%|████████▉ | 9866/11066 [36:09<04:23,  4.56it/s]
                                                    

 89%|████████▉ | 9866/11066 [36:09<04:23,  4.56it/s]
 89%|████████▉ | 9867/11066 [36:09<04:24,  4.53it/s]
                                                    

 89%|████████▉ | 9867/11066 [36:09<04:24,  4.53it/s]
 89%|████████▉ | 9868/11066 [36:09<04:25,  4.52it/s]
                                                    

 89%|████████▉ | 9868/11066 [36:09<04:25,  4.52it/s]
 89%|████████▉ | 9869/11066 [36:09<04:21,  4.57it/s]
                                                    

 89%|████████▉ | 9869/11066 [36:09<04:21,  4.57it/s]
 89%|████████▉ | 9870/11066 [36:09<04:20,  4.59it/s]
                                                    

 89%|████████▉ | 9870/11066 [36:09<04:20,  4.59it/s]
 89%|████████▉ | 9871/11066 [36:10<04:23,  4.54it/s]
                                                    

 89%|████████▉ | 9871/11066 [36:10<04:23,  4.54it/s]
 89%|████████▉ | 9872/11066 [36:10<04:23,  4.52it/s]
                                                    

 89%|████████▉ | 9872/11066 [36:10<04:23,  4.52it/s]
 89%|████████▉ | 9873/11066 [36:10<04:22,  4.54it/s]
                                                    

 89%|████████▉ | 9873/11066 [36:10<04:22,  4.54it/s]
 89%|████████▉ | 9874/11066 [36:10<04:19,  4.59it/s]
                                                    

 89%|████████▉ | 9874/11066 [36:10<04:19,  4.59it/s]
 89%|████████▉ | 9875/11066 [36:11<04:22,  4.54it/s]
                                                    

 89%|████████▉ | 9875/11066 [36:11<04:22,  4.54it/s]
 89%|████████▉ | 9876/11066 [36:11<04:23,  4.52it/s]
                                                    

 89%|████████▉ | 9876/11066 [36:11<04:23,  4.52it/s]
 89%|████████▉ | 9877/11066 [36:11<04:22,  4.52it/s]
                                                    

 89%|████████▉ | 9877/11066 [36:11<04:22,  4.52it/s]
 89%|████████▉ | 9878/11066 [36:11<04:21,  4.55it/s]
                                                    

 89%|████████▉ | 9878/11066 [36:11<04:21,  4.55it/s]
 89%|████████▉ | 9879/11066 [36:11<04:22,  4.53it/s]
                                                    

 89%|████████▉ | 9879/11066 [36:11<04:22,  4.53it/s]
 89%|████████▉ | 9880/11066 [36:12<04:23,  4.51it/s]
                                                    

 89%|████████▉ | 9880/11066 [36:12<04:23,  4.51it/s]
 89%|████████▉ | 9881/11066 [36:12<04:23,  4.49it/s]
                                                    

 89%|████████▉ | 9881/11066 [36:12<04:23,  4.49it/s]
 89%|████████▉ | 9882/11066 [36:12<04:21,  4.53it/s]
                                                    

 89%|████████▉ | 9882/11066 [36:12<04:21,  4.53it/s]
 89%|████████▉ | 9883/11066 [36:12<04:18,  4.57it/s]
                                                    

 89%|████████▉ | 9883/11066 [36:12<04:18,  4.57it/s]
 89%|████████▉ | 9884/11066 [36:13<04:20,  4.54it/s]
                                                    

 89%|████████▉ | 9884/11066 [36:13<04:20,  4.54it/s]
 89%|████████▉ | 9885/11066 [36:13<04:21,  4.52it/s]
                                                    

 89%|████████▉ | 9885/11066 [36:13<04:21,  4.52it/s]
 89%|████████▉ | 9886/11066 [36:13<04:21,  4.50it/s]
                                                    

 89%|████████▉ | 9886/11066 [36:13<04:21,  4.50it/s]
 89%|████████▉ | 9887/11066 [36:13<04:17,  4.59it/s]
                                                    

 89%|████████▉ | 9887/11066 [36:13<04:17,  4.59it/s]
 89%|████████▉ | 9888/11066 [36:13<04:16,  4.59it/s]
                                                    

 89%|████████▉ | 9888/11066 [36:13<04:16,  4.59it/s]
 89%|████████▉ | 9889/11066 [36:14<04:17,  4.58it/s]
                                                    

 89%|████████▉ | 9889/11066 [36:14<04:17,  4.58it/s]
 89%|████████▉ | 9890/11066 [36:14<04:18,  4.56it/s]
                                                    

 89%|████████▉ | 9890/11066 [36:14<04:18,  4.56it/s]
 89%|████████▉ | 9891/11066 [36:14<04:15,  4.60it/s]
                                                    

 89%|████████▉ | 9891/11066 [36:14<04:15,  4.60it/s]
 89%|████████▉ | 9892/11066 [36:14<04:13,  4.63it/s]
                                                    

 89%|████████▉ | 9892/11066 [36:14<04:13,  4.63it/s]
 89%|████████▉ | 9893/11066 [36:14<04:12,  4.65it/s]
                                                    

 89%|████████▉ | 9893/11066 [36:14<04:12,  4.65it/s]
 89%|████████▉ | 9894/11066 [36:15<04:15,  4.59it/s]
                                                    

 89%|████████▉ | 9894/11066 [36:15<04:15,  4.59it/s]
 89%|████████▉ | 9895/11066 [36:15<04:17,  4.55it/s]
                                                    

 89%|████████▉ | 9895/11066 [36:15<04:17,  4.55it/s]
 89%|████████▉ | 9896/11066 [36:15<04:18,  4.53it/s]
                                                    

 89%|████████▉ | 9896/11066 [36:15<04:18,  4.53it/s]
 89%|████████▉ | 9897/11066 [36:15<04:18,  4.52it/s]
                                                    

 89%|████████▉ | 9897/11066 [36:15<04:18,  4.52it/s]
 89%|████████▉ | 9898/11066 [36:16<04:19,  4.51it/s]
                                                    

 89%|████████▉ | 9898/11066 [36:16<04:19,  4.51it/s]
 89%|████████▉ | 9899/11066 [36:16<04:19,  4.50it/s]
                                                    

 89%|████████▉ | 9899/11066 [36:16<04:19,  4.50it/s]
 89%|████████▉ | 9900/11066 [36:16<04:18,  4.50it/s]
                                                    

 89%|████████▉ | 9900/11066 [36:16<04:18,  4.50it/s]
 89%|████████▉ | 9901/11066 [36:16<04:15,  4.56it/s]
                                                    

 89%|████████▉ | 9901/11066 [36:16<04:15,  4.56it/s]
 89%|████████▉ | 9902/11066 [36:16<04:16,  4.55it/s]
                                                    

 89%|████████▉ | 9902/11066 [36:16<04:16,  4.55it/s]
 89%|████████▉ | 9903/11066 [36:17<04:14,  4.57it/s]
                                                    

 89%|████████▉ | 9903/11066 [36:17<04:14,  4.57it/s]
 89%|████████▉ | 9904/11066 [36:17<04:14,  4.56it/s]
                                                    

 89%|████████▉ | 9904/11066 [36:17<04:14,  4.56it/s]
 90%|████████▉ | 9905/11066 [36:17<04:12,  4.60it/s]
                                                    

 90%|████████▉ | 9905/11066 [36:17<04:12,  4.60it/s]
 90%|████████▉ | 9906/11066 [36:17<04:11,  4.61it/s]
                                                    

 90%|████████▉ | 9906/11066 [36:17<04:11,  4.61it/s]
 90%|████████▉ | 9907/11066 [36:18<04:13,  4.57it/s]
                                                    

 90%|████████▉ | 9907/11066 [36:18<04:13,  4.57it/s]
 90%|████████▉ | 9908/11066 [36:18<04:14,  4.55it/s]
                                                    

 90%|████████▉ | 9908/11066 [36:18<04:14,  4.55it/s]
 90%|████████▉ | 9909/11066 [36:18<04:13,  4.57it/s]
                                                    

 90%|████████▉ | 9909/11066 [36:18<04:13,  4.57it/s]
 90%|████████▉ | 9910/11066 [36:18<04:10,  4.62it/s]
                                                    

 90%|████████▉ | 9910/11066 [36:18<04:10,  4.62it/s]
 90%|████████▉ | 9911/11066 [36:18<04:08,  4.64it/s]
                                                    

 90%|████████▉ | 9911/11066 [36:18<04:08,  4.64it/s]
 90%|████████▉ | 9912/11066 [36:19<04:10,  4.60it/s]
                                                    

 90%|████████▉ | 9912/11066 [36:19<04:10,  4.60it/s]
 90%|████████▉ | 9913/11066 [36:19<04:13,  4.55it/s]
                                                    

 90%|████████▉ | 9913/11066 [36:19<04:13,  4.55it/s]
 90%|████████▉ | 9914/11066 [36:19<04:12,  4.56it/s]
                                                    

 90%|████████▉ | 9914/11066 [36:19<04:12,  4.56it/s]
 90%|████████▉ | 9915/11066 [36:19<04:09,  4.62it/s]
                                                    

 90%|████████▉ | 9915/11066 [36:19<04:09,  4.62it/s]
 90%|████████▉ | 9916/11066 [36:19<04:07,  4.64it/s]
                                                    

 90%|████████▉ | 9916/11066 [36:19<04:07,  4.64it/s]
 90%|████████▉ | 9917/11066 [36:20<04:06,  4.65it/s]
                                                    

 90%|████████▉ | 9917/11066 [36:20<04:06,  4.65it/s]
 90%|████████▉ | 9918/11066 [36:20<04:06,  4.66it/s]
                                                    

 90%|████████▉ | 9918/11066 [36:20<04:06,  4.66it/s]
 90%|████████▉ | 9919/11066 [36:20<04:09,  4.60it/s]
                                                    

 90%|████████▉ | 9919/11066 [36:20<04:09,  4.60it/s]
 90%|████████▉ | 9920/11066 [36:20<04:07,  4.63it/s]
                                                    
{'loss': 0.4528, 'learning_rate': 3.413157419121634e-06, 'epoch': 1.77}
{'loss': 0.6543, 'learning_rate': 3.410446412434484e-06, 'epoch': 1.77}
{'loss': 0.8096, 'learning_rate': 3.407735405747334e-06, 'epoch': 1.77}
{'loss': 0.6247, 'learning_rate': 3.4050243990601843e-06, 'epoch': 1.77}
{'loss': 0.4869, 'learning_rate': 3.402313392373035e-06, 'epoch': 1.77}
{'loss': 0.6954, 'learning_rate': 3.399602385685885e-06, 'epoch': 1.77}
{'loss': 0.4137, 'learning_rate': 3.396891378998735e-06, 'epoch': 1.77}
{'loss': 0.8669, 'learning_rate': 3.3941803723115853e-06, 'epoch': 1.77}
{'loss': 0.8351, 'learning_rate': 3.3914693656244354e-06, 'epoch': 1.77}
{'loss': 1.2858, 'learning_rate': 3.3887583589372856e-06, 'epoch': 1.77}
{'loss': 0.6756, 'learning_rate': 3.3860473522501357e-06, 'epoch': 1.77}
{'loss': 0.3924, 'learning_rate': 3.383336345562986e-06, 'epoch': 1.77}
{'loss': 0.6874, 'learning_rate': 3.380625338875836e-06, 'epoch': 1.77}
{'loss': 0.7277, 'learning_rate': 3.377914332188686e-06, 'epoch': 1.77}
{'loss': 0.812, 'learning_rate': 3.3752033255015367e-06, 'epoch': 1.77}
{'loss': 0.6922, 'learning_rate': 3.372492318814387e-06, 'epoch': 1.78}
{'loss': 0.4951, 'learning_rate': 3.369781312127237e-06, 'epoch': 1.78}
{'loss': 0.7613, 'learning_rate': 3.367070305440087e-06, 'epoch': 1.78}
{'loss': 0.7569, 'learning_rate': 3.364359298752937e-06, 'epoch': 1.78}
{'loss': 0.4706, 'learning_rate': 3.3616482920657873e-06, 'epoch': 1.78}
{'loss': 0.4986, 'learning_rate': 3.3589372853786375e-06, 'epoch': 1.78}
{'loss': 0.7534, 'learning_rate': 3.3562262786914876e-06, 'epoch': 1.78}
{'loss': 0.9283, 'learning_rate': 3.3535152720043377e-06, 'epoch': 1.78}
{'loss': 0.7925, 'learning_rate': 3.350804265317188e-06, 'epoch': 1.78}
{'loss': 0.7321, 'learning_rate': 3.348093258630038e-06, 'epoch': 1.78}
{'loss': 1.1766, 'learning_rate': 3.3453822519428886e-06, 'epoch': 1.78}
{'loss': 0.5265, 'learning_rate': 3.3426712452557387e-06, 'epoch': 1.78}
{'loss': 1.0538, 'learning_rate': 3.339960238568589e-06, 'epoch': 1.78}
{'loss': 1.3031, 'learning_rate': 3.337249231881439e-06, 'epoch': 1.78}
{'loss': 0.5133, 'learning_rate': 3.334538225194289e-06, 'epoch': 1.78}
{'loss': 0.9593, 'learning_rate': 3.3318272185071392e-06, 'epoch': 1.78}
{'loss': 0.8543, 'learning_rate': 3.3291162118199894e-06, 'epoch': 1.78}
{'loss': 0.6113, 'learning_rate': 3.3264052051328395e-06, 'epoch': 1.78}
{'loss': 0.3548, 'learning_rate': 3.3236941984456896e-06, 'epoch': 1.78}
{'loss': 0.4825, 'learning_rate': 3.3209831917585398e-06, 'epoch': 1.78}
{'loss': 0.3474, 'learning_rate': 3.3182721850713903e-06, 'epoch': 1.78}
{'loss': 0.6888, 'learning_rate': 3.3155611783842405e-06, 'epoch': 1.78}
{'loss': 0.3539, 'learning_rate': 3.31285017169709e-06, 'epoch': 1.78}
{'loss': 0.8553, 'learning_rate': 3.3101391650099403e-06, 'epoch': 1.78}
{'loss': 0.9283, 'learning_rate': 3.3074281583227904e-06, 'epoch': 1.78}
{'loss': 0.4808, 'learning_rate': 3.3047171516356406e-06, 'epoch': 1.78}
{'loss': 0.7909, 'learning_rate': 3.3020061449484907e-06, 'epoch': 1.78}
{'loss': 0.4704, 'learning_rate': 3.299295138261341e-06, 'epoch': 1.78}
{'loss': 0.4734, 'learning_rate': 3.296584131574191e-06, 'epoch': 1.78}
{'loss': 0.6067, 'learning_rate': 3.293873124887041e-06, 'epoch': 1.78}
{'loss': 0.2858, 'learning_rate': 3.2911621181998917e-06, 'epoch': 1.78}
{'loss': 0.8828, 'learning_rate': 3.288451111512742e-06, 'epoch': 1.78}
{'loss': 0.9451, 'learning_rate': 3.285740104825592e-06, 'epoch': 1.78}
{'loss': 0.82, 'learning_rate': 3.283029098138442e-06, 'epoch': 1.78}
{'loss': 1.4849, 'learning_rate': 3.280318091451292e-06, 'epoch': 1.78}
{'loss': 0.8042, 'learning_rate': 3.2776070847641423e-06, 'epoch': 1.78}
{'loss': 0.857, 'learning_rate': 3.2748960780769925e-06, 'epoch': 1.78}
{'loss': 0.4337, 'learning_rate': 3.2721850713898426e-06, 'epoch': 1.78}
{'loss': 0.516, 'learning_rate': 3.2694740647026927e-06, 'epoch': 1.78}
{'loss': 1.2103, 'learning_rate': 3.266763058015543e-06, 'epoch': 1.78}
{'loss': 0.6992, 'learning_rate': 3.264052051328393e-06, 'epoch': 1.78}
{'loss': 1.2413, 'learning_rate': 3.2613410446412436e-06, 'epoch': 1.78}
{'loss': 0.6091, 'learning_rate': 3.2586300379540937e-06, 'epoch': 1.78}
{'loss': 1.7611, 'learning_rate': 3.255919031266944e-06, 'epoch': 1.78}
{'loss': 0.3433, 'learning_rate': 3.253208024579794e-06, 'epoch': 1.78}
{'loss': 0.5347, 'learning_rate': 3.250497017892644e-06, 'epoch': 1.78}
{'loss': 0.663, 'learning_rate': 3.2477860112054942e-06, 'epoch': 1.78}
{'loss': 1.308, 'learning_rate': 3.2450750045183444e-06, 'epoch': 1.78}
{'loss': 0.4179, 'learning_rate': 3.2423639978311945e-06, 'epoch': 1.78}
{'loss': 0.937, 'learning_rate': 3.2396529911440446e-06, 'epoch': 1.78}
{'loss': 0.9298, 'learning_rate': 3.2369419844568948e-06, 'epoch': 1.78}
{'loss': 1.0607, 'learning_rate': 3.2342309777697453e-06, 'epoch': 1.78}
{'loss': 0.6899, 'learning_rate': 3.2315199710825955e-06, 'epoch': 1.78}
{'loss': 1.1725, 'learning_rate': 3.2288089643954456e-06, 'epoch': 1.78}
{'loss': 0.4809, 'learning_rate': 3.2260979577082957e-06, 'epoch': 1.78}
{'loss': 1.179, 'learning_rate': 3.223386951021146e-06, 'epoch': 1.79}
{'loss': 0.7439, 'learning_rate': 3.220675944333996e-06, 'epoch': 1.79}
{'loss': 0.6429, 'learning_rate': 3.217964937646846e-06, 'epoch': 1.79}
{'loss': 1.1772, 'learning_rate': 3.2152539309596963e-06, 'epoch': 1.79}
{'loss': 0.4364, 'learning_rate': 3.2125429242725464e-06, 'epoch': 1.79}
{'loss': 1.1531, 'learning_rate': 3.2098319175853965e-06, 'epoch': 1.79}
{'loss': 0.4993, 'learning_rate': 3.2071209108982467e-06, 'epoch': 1.79}
{'loss': 1.3863, 'learning_rate': 3.2044099042110972e-06, 'epoch': 1.79}
{'loss': 1.0983, 'learning_rate': 3.2016988975239474e-06, 'epoch': 1.79}
{'loss': 0.7523, 'learning_rate': 3.1989878908367975e-06, 'epoch': 1.79}
{'loss': 0.3715, 'learning_rate': 3.1962768841496476e-06, 'epoch': 1.79}
{'loss': 0.8535, 'learning_rate': 3.1935658774624978e-06, 'epoch': 1.79}
{'loss': 0.614, 'learning_rate': 3.190854870775348e-06, 'epoch': 1.79}
{'loss': 0.644, 'learning_rate': 3.188143864088198e-06, 'epoch': 1.79}
{'loss': 0.1579, 'learning_rate': 3.185432857401048e-06, 'epoch': 1.79}
{'loss': 0.445, 'learning_rate': 3.1827218507138983e-06, 'epoch': 1.79}
{'loss': 0.8848, 'learning_rate': 3.1800108440267484e-06, 'epoch': 1.79}
{'loss': 0.8593, 'learning_rate': 3.177299837339599e-06, 'epoch': 1.79}
{'loss': 0.3292, 'learning_rate': 3.174588830652449e-06, 'epoch': 1.79}
{'loss': 0.6752, 'learning_rate': 3.1718778239652993e-06, 'epoch': 1.79}
{'loss': 0.7168, 'learning_rate': 3.1691668172781494e-06, 'epoch': 1.79}
{'loss': 0.5621, 'learning_rate': 3.1664558105909995e-06, 'epoch': 1.79}
{'loss': 0.7576, 'learning_rate': 3.1637448039038497e-06, 'epoch': 1.79}
{'loss': 0.4026, 'learning_rate': 3.1610337972167e-06, 'epoch': 1.79}
{'loss': 0.4536, 'learning_rate': 3.15832279052955e-06, 'epoch': 1.79}
{'loss': 0.7091, 'learning_rate': 3.1556117838424e-06, 'epoch': 1.79}
{'loss': 0.4421, 'learning_rate': 3.1529007771552502e-06, 'epoch': 1.79}
{'loss': 0.4083, 'learning_rate': 3.1501897704681004e-06, 'epoch': 1.79}
{'loss': 1.158, 'learning_rate': 3.147478763780951e-06, 'epoch': 1.79}
{'loss': 0.546, 'learning_rate': 3.144767757093801e-06, 'epoch': 1.79}
{'loss': 0.3709, 'learning_rate': 3.142056750406651e-06, 'epoch': 1.79}
{'loss': 0.6616, 'learning_rate': 3.1393457437195013e-06, 'epoch': 1.79}
{'loss': 0.5863, 'learning_rate': 3.1366347370323514e-06, 'epoch': 1.79}
{'loss': 0.7143, 'learning_rate': 3.1339237303452016e-06, 'epoch': 1.79}
{'loss': 0.7278, 'learning_rate': 3.1312127236580517e-06, 'epoch': 1.79}
{'loss': 0.7436, 'learning_rate': 3.128501716970902e-06, 'epoch': 1.79}
{'loss': 0.2662, 'learning_rate': 3.125790710283752e-06, 'epoch': 1.79}
{'loss': 0.6911, 'learning_rate': 3.123079703596602e-06, 'epoch': 1.79}
{'loss': 1.2497, 'learning_rate': 3.1203686969094527e-06, 'epoch': 1.79}
{'loss': 0.8006, 'learning_rate': 3.117657690222303e-06, 'epoch': 1.79}
{'loss': 1.1769, 'learning_rate': 3.114946683535153e-06, 'epoch': 1.79}
{'loss': 1.1592, 'learning_rate': 3.112235676848003e-06, 'epoch': 1.79}
{'loss': 0.78, 'learning_rate': 3.109524670160853e-06, 'epoch': 1.79}

 90%|████████▉ | 9920/11066 [36:20<04:07,  4.63it/s]
 90%|████████▉ | 9921/11066 [36:21<04:13,  4.52it/s]
                                                    

 90%|████████▉ | 9921/11066 [36:21<04:13,  4.52it/s]
 90%|████████▉ | 9922/11066 [36:21<04:13,  4.52it/s]
                                                    

 90%|████████▉ | 9922/11066 [36:21<04:13,  4.52it/s]
 90%|████████▉ | 9923/11066 [36:21<04:13,  4.51it/s]
                                                    

 90%|████████▉ | 9923/11066 [36:21<04:13,  4.51it/s]
 90%|████████▉ | 9924/11066 [36:21<04:10,  4.56it/s]
                                                    

 90%|████████▉ | 9924/11066 [36:21<04:10,  4.56it/s]
 90%|████████▉ | 9925/11066 [36:21<04:11,  4.53it/s]
                                                    

 90%|████████▉ | 9925/11066 [36:21<04:11,  4.53it/s]
 90%|████████▉ | 9926/11066 [36:22<04:13,  4.49it/s]
                                                    

 90%|████████▉ | 9926/11066 [36:22<04:13,  4.49it/s]
 90%|████████▉ | 9927/11066 [36:22<04:13,  4.49it/s]
                                                    

 90%|████████▉ | 9927/11066 [36:22<04:13,  4.49it/s]
 90%|████████▉ | 9928/11066 [36:22<04:11,  4.53it/s]
                                                    

 90%|████████▉ | 9928/11066 [36:22<04:11,  4.53it/s]
 90%|████████▉ | 9929/11066 [36:22<04:08,  4.57it/s]
                                                    

 90%|████████▉ | 9929/11066 [36:22<04:08,  4.57it/s]
 90%|████████▉ | 9930/11066 [36:23<04:10,  4.54it/s]
                                                    

 90%|████████▉ | 9930/11066 [36:23<04:10,  4.54it/s]
 90%|████████▉ | 9931/11066 [36:23<04:15,  4.44it/s]
                                                    

 90%|████████▉ | 9931/11066 [36:23<04:15,  4.44it/s]
 90%|████████▉ | 9932/11066 [36:23<04:16,  4.42it/s]
                                                    

 90%|████████▉ | 9932/11066 [36:23<04:16,  4.42it/s]
 90%|████████▉ | 9933/11066 [36:23<04:13,  4.47it/s]
                                                    

 90%|████████▉ | 9933/11066 [36:23<04:13,  4.47it/s]
 90%|████████▉ | 9934/11066 [36:23<04:10,  4.53it/s]
                                                    

 90%|████████▉ | 9934/11066 [36:23<04:10,  4.53it/s]
 90%|████████▉ | 9935/11066 [36:24<04:10,  4.52it/s]
                                                    

 90%|████████▉ | 9935/11066 [36:24<04:10,  4.52it/s]
 90%|████████▉ | 9936/11066 [36:24<04:09,  4.53it/s]
                                                    

 90%|████████▉ | 9936/11066 [36:24<04:09,  4.53it/s]
 90%|████████▉ | 9937/11066 [36:24<04:05,  4.59it/s]
                                                    

 90%|████████▉ | 9937/11066 [36:24<04:05,  4.59it/s]
 90%|████████▉ | 9938/11066 [36:24<04:04,  4.61it/s]
                                                    

 90%|████████▉ | 9938/11066 [36:24<04:04,  4.61it/s]
 90%|████████▉ | 9939/11066 [36:25<04:07,  4.55it/s]
                                                    

 90%|████████▉ | 9939/11066 [36:25<04:07,  4.55it/s]
 90%|████████▉ | 9940/11066 [36:25<04:08,  4.53it/s]
                                                    

 90%|████████▉ | 9940/11066 [36:25<04:08,  4.53it/s]
 90%|████████▉ | 9941/11066 [36:25<04:06,  4.56it/s]
                                                    

 90%|████████▉ | 9941/11066 [36:25<04:06,  4.56it/s]
 90%|████████▉ | 9942/11066 [36:25<04:03,  4.61it/s]
                                                    

 90%|████████▉ | 9942/11066 [36:25<04:03,  4.61it/s]
 90%|████████▉ | 9943/11066 [36:25<04:02,  4.63it/s]
                                                    

 90%|████████▉ | 9943/11066 [36:25<04:02,  4.63it/s]
 90%|████████▉ | 9944/11066 [36:26<04:05,  4.56it/s]
                                                    

 90%|████████▉ | 9944/11066 [36:26<04:05,  4.56it/s]
 90%|████████▉ | 9945/11066 [36:26<04:06,  4.55it/s]
                                                    

 90%|████████▉ | 9945/11066 [36:26<04:06,  4.55it/s]
 90%|████████▉ | 9946/11066 [36:26<04:05,  4.56it/s]
                                                    

 90%|████████▉ | 9946/11066 [36:26<04:05,  4.56it/s]
 90%|████████▉ | 9947/11066 [36:26<04:04,  4.58it/s]
                                                    

 90%|████████▉ | 9947/11066 [36:26<04:04,  4.58it/s]
 90%|████████▉ | 9948/11066 [36:27<04:05,  4.56it/s]
                                                    

 90%|████████▉ | 9948/11066 [36:27<04:05,  4.56it/s]
 90%|████████▉ | 9949/11066 [36:27<04:06,  4.54it/s]
                                                    

 90%|████████▉ | 9949/11066 [36:27<04:06,  4.54it/s]
 90%|████████▉ | 9950/11066 [36:27<04:04,  4.56it/s]
                                                    

 90%|████████▉ | 9950/11066 [36:27<04:04,  4.56it/s]
 90%|████████▉ | 9951/11066 [36:27<04:01,  4.61it/s]
                                                    

 90%|████████▉ | 9951/11066 [36:27<04:01,  4.61it/s]
 90%|████████▉ | 9952/11066 [36:27<04:00,  4.63it/s]
                                                    

 90%|████████▉ | 9952/11066 [36:27<04:00,  4.63it/s]
 90%|████████▉ | 9953/11066 [36:28<04:03,  4.57it/s]
                                                    

 90%|████████▉ | 9953/11066 [36:28<04:03,  4.57it/s]
 90%|████████▉ | 9954/11066 [36:28<04:05,  4.53it/s]
                                                    

 90%|████████▉ | 9954/11066 [36:28<04:05,  4.53it/s]
 90%|████████▉ | 9955/11066 [36:28<04:07,  4.50it/s]
                                                    

 90%|████████▉ | 9955/11066 [36:28<04:07,  4.50it/s]
 90%|████████▉ | 9956/11066 [36:28<04:08,  4.47it/s]
                                                    

 90%|████████▉ | 9956/11066 [36:28<04:08,  4.47it/s]
 90%|████████▉ | 9957/11066 [36:29<04:10,  4.44it/s]
                                                    

 90%|████████▉ | 9957/11066 [36:29<04:10,  4.44it/s]
 90%|████████▉ | 9958/11066 [36:29<04:09,  4.44it/s]
                                                    

 90%|████████▉ | 9958/11066 [36:29<04:09,  4.44it/s]
 90%|████████▉ | 9959/11066 [36:29<04:08,  4.46it/s]
                                                    

 90%|████████▉ | 9959/11066 [36:29<04:08,  4.46it/s]
 90%|█████████ | 9960/11066 [36:29<04:07,  4.47it/s]
                                                    

 90%|█████████ | 9960/11066 [36:29<04:07,  4.47it/s]
 90%|█████████ | 9961/11066 [36:29<04:06,  4.48it/s]
                                                    

 90%|█████████ | 9961/11066 [36:29<04:06,  4.48it/s]
 90%|█████████ | 9962/11066 [36:30<04:06,  4.49it/s]
                                                    

 90%|█████████ | 9962/11066 [36:30<04:06,  4.49it/s]
 90%|█████████ | 9963/11066 [36:30<04:07,  4.47it/s]
                                                    

 90%|█████████ | 9963/11066 [36:30<04:07,  4.47it/s]
 90%|█████████ | 9964/11066 [36:30<04:07,  4.46it/s]
                                                    

 90%|█████████ | 9964/11066 [36:30<04:07,  4.46it/s]
 90%|█████████ | 9965/11066 [36:30<04:06,  4.47it/s]
                                                    

 90%|█████████ | 9965/11066 [36:30<04:06,  4.47it/s]
 90%|█████████ | 9966/11066 [36:31<04:05,  4.48it/s]
                                                    

 90%|█████████ | 9966/11066 [36:31<04:05,  4.48it/s]
 90%|█████████ | 9967/11066 [36:31<04:05,  4.48it/s]
                                                    

 90%|█████████ | 9967/11066 [36:31<04:05,  4.48it/s]
 90%|█████████ | 9968/11066 [36:31<04:03,  4.51it/s]
                                                    

 90%|█████████ | 9968/11066 [36:31<04:03,  4.51it/s]
 90%|█████████ | 9969/11066 [36:31<04:03,  4.50it/s]
                                                    

 90%|█████████ | 9969/11066 [36:31<04:03,  4.50it/s]
 90%|█████████ | 9970/11066 [36:31<04:03,  4.50it/s]
                                                    

 90%|█████████ | 9970/11066 [36:31<04:03,  4.50it/s]
 90%|█████████ | 9971/11066 [36:32<04:03,  4.50it/s]
                                                    

 90%|█████████ | 9971/11066 [36:32<04:03,  4.50it/s]
 90%|█████████ | 9972/11066 [36:32<04:03,  4.50it/s]
                                                    

 90%|█████████ | 9972/11066 [36:32<04:03,  4.50it/s]
 90%|█████████ | 9973/11066 [36:32<04:02,  4.50it/s]
                                                    

 90%|█████████ | 9973/11066 [36:32<04:02,  4.50it/s]
 90%|█████████ | 9974/11066 [36:32<04:02,  4.50it/s]
                                                    

 90%|█████████ | 9974/11066 [36:32<04:02,  4.50it/s]
 90%|█████████ | 9975/11066 [36:33<04:02,  4.50it/s]
                                                    

 90%|█████████ | 9975/11066 [36:33<04:02,  4.50it/s]
 90%|█████████ | 9976/11066 [36:33<03:59,  4.55it/s]
                                                    

 90%|█████████ | 9976/11066 [36:33<03:59,  4.55it/s]
 90%|█████████ | 9977/11066 [36:33<03:58,  4.56it/s]
                                                    

 90%|█████████ | 9977/11066 [36:33<03:58,  4.56it/s]
 90%|█████████ | 9978/11066 [36:33<03:59,  4.54it/s]
                                                    

 90%|█████████ | 9978/11066 [36:33<03:59,  4.54it/s]
 90%|█████████ | 9979/11066 [36:33<04:00,  4.52it/s]
                                                    

 90%|█████████ | 9979/11066 [36:33<04:00,  4.52it/s]
 90%|█████████ | 9980/11066 [36:34<03:58,  4.55it/s]
                                                    

 90%|█████████ | 9980/11066 [36:34<03:58,  4.55it/s]
 90%|█████████ | 9981/11066 [36:34<03:59,  4.54it/s]
                                                    

 90%|█████████ | 9981/11066 [36:34<03:59,  4.54it/s]
 90%|█████████ | 9982/11066 [36:34<04:00,  4.51it/s]
                                                    

 90%|█████████ | 9982/11066 [36:34<04:00,  4.51it/s]
 90%|█████████ | 9983/11066 [36:34<04:00,  4.50it/s]
                                                    

 90%|█████████ | 9983/11066 [36:34<04:00,  4.50it/s]
 90%|█████████ | 9984/11066 [36:35<04:00,  4.50it/s]
                                                    

 90%|█████████ | 9984/11066 [36:35<04:00,  4.50it/s]
 90%|█████████ | 9985/11066 [36:35<04:00,  4.50it/s]
                                                    

 90%|█████████ | 9985/11066 [36:35<04:00,  4.50it/s]
 90%|█████████ | 9986/11066 [36:35<03:57,  4.54it/s]
                                                    

 90%|█████████ | 9986/11066 [36:35<03:57,  4.54it/s]
 90%|█████████ | 9987/11066 [36:35<03:59,  4.51it/s]
                                                    

 90%|█████████ | 9987/11066 [36:35<03:59,  4.51it/s]
 90%|█████████ | 9988/11066 [36:35<03:57,  4.54it/s]
                                                    

 90%|█████████ | 9988/11066 [36:35<03:57,  4.54it/s]
 90%|█████████ | 9989/11066 [36:36<03:55,  4.58it/s]
                                                    

 90%|█████████ | 9989/11066 [36:36<03:55,  4.58it/s]
 90%|█████████ | 9990/11066 [36:36<03:56,  4.54it/s]
                                                    

 90%|█████████ | 9990/11066 [36:36<03:56,  4.54it/s]
 90%|█████████ | 9991/11066 [36:36<03:57,  4.52it/s]
                                                    

 90%|█████████ | 9991/11066 [36:36<03:57,  4.52it/s]
 90%|█████████ | 9992/11066 [36:36<03:56,  4.54it/s]
                                                    

 90%|█████████ | 9992/11066 [36:36<03:56,  4.54it/s]
 90%|█████████ | 9993/11066 [36:37<03:57,  4.51it/s]
                                                    

 90%|█████████ | 9993/11066 [36:37<03:57,  4.51it/s]
 90%|█████████ | 9994/11066 [36:37<03:58,  4.50it/s]
                                                    

 90%|█████████ | 9994/11066 [36:37<03:58,  4.50it/s]
 90%|█████████ | 9995/11066 [36:37<03:58,  4.50it/s]
                                                    

 90%|█████████ | 9995/11066 [36:37<03:58,  4.50it/s]
 90%|█████████ | 9996/11066 [36:37<03:56,  4.53it/s]
                                                    

 90%|█████████ | 9996/11066 [36:37<03:56,  4.53it/s]
 90%|█████████ | 9997/11066 [36:37<03:54,  4.56it/s]
                                                    

 90%|█████████ | 9997/11066 [36:37<03:54,  4.56it/s]
 90%|█████████ | 9998/11066 [36:38<03:55,  4.54it/s]
                                                    

 90%|█████████ | 9998/11066 [36:38<03:55,  4.54it/s]
 90%|█████████ | 9999/11066 [36:38<03:55,  4.52it/s]
                                                    

 90%|█████████ | 9999/11066 [36:38<03:55,  4.52it/s]
 90%|█████████ | 10000/11066 [36:38<03:54,  4.55it/s]
                                                     

 90%|█████████ | 10000/11066 [36:38<03:54,  4.55it/s][INFO|trainer.py:1935] 2021-10-20 22:24:54,480 >> Saving model checkpoint to bert-based-uncased-squad/checkpoint-10000
[INFO|configuration_utils.py:391] 2021-10-20 22:24:54,481 >> Configuration saved in bert-based-uncased-squad/checkpoint-10000/config.json
[INFO|modeling_utils.py:1001] 2021-10-20 22:24:54,983 >> Model weights saved in bert-based-uncased-squad/checkpoint-10000/pytorch_model.bin
[INFO|tokenization_utils_base.py:2020] 2021-10-20 22:24:54,983 >> tokenizer config file saved in bert-based-uncased-squad/checkpoint-10000/tokenizer_config.json
[INFO|tokenization_utils_base.py:2026] 2021-10-20 22:24:54,984 >> Special tokens file saved in bert-based-uncased-squad/checkpoint-10000/special_tokens_map.json

 90%|█████████ | 10001/11066 [36:40<12:30,  1.42it/s]
                                                     

 90%|█████████ | 10001/11066 [36:40<12:30,  1.42it/s]
 90%|█████████ | 10002/11066 [36:40<09:54,  1.79it/s]
                                                     

 90%|█████████ | 10002/11066 [36:40<09:54,  1.79it/s]
 90%|█████████ | 10003/11066 [36:40<08:03,  2.20it/s]
                                                     

 90%|█████████ | 10003/11066 [36:40<08:03,  2.20it/s]
 90%|█████████ | 10004/11066 [36:41<06:47,  2.61it/s]
                                                     

 90%|█████████ | 10004/11066 [36:41<06:47,  2.61it/s]
 90%|█████████ | 10005/11066 [36:41<05:52,  3.01it/s]
                                                     

 90%|█████████ | 10005/11066 [36:41<05:52,  3.01it/s]
 90%|█████████ | 10006/11066 [36:41<05:16,  3.35it/s]
                                                     

 90%|█████████ | 10006/11066 [36:41<05:16,  3.35it/s]
 90%|█████████ | 10007/11066 [36:41<04:52,  3.62it/s]
                                                     

 90%|█████████ | 10007/11066 [36:41<04:52,  3.62it/s]
 90%|█████████ | 10008/11066 [36:41<04:33,  3.87it/s]
                                                     

 90%|█████████ | 10008/11066 [36:41<04:33,  3.87it/s]
 90%|█████████ | 10009/11066 [36:42<04:21,  4.04it/s]
                                                     

 90%|█████████ | 10009/11066 [36:42<04:21,  4.04it/s]
 90%|█████████ | 10010/11066 [36:42<04:13,  4.17it/s]
                                                     

 90%|█████████ | 10010/11066 [36:42<04:13,  4.17it/s]
 90%|█████████ | 10011/11066 [36:42<04:05,  4.29it/s]
                                                     

 90%|█████████ | 10011/11066 [36:42<04:05,  4.29it/s]
 90%|█████████ | 10012/11066 [36:42<04:01,  4.37it/s]
                                                     

 90%|█████████ | 10012/11066 [36:42<04:01,  4.37it/s]
 90%|█████████ | 10013/11066 [36:43<03:59,  4.39it/s]
                                                     

 90%|█████████ | 10013/11066 [36:43<03:59,  4.39it/s]
 90%|█████████ | 10014/11066 [36:43<04:01,  4.36it/s]
                                                     

 90%|█████████ | 10014/11066 [36:43<04:01,  4.36it/s]
 91%|█████████ | 10015/11066 [36:43<04:00,  4.37it/s]
                                                     

 91%|█████████ | 10015/11066 [36:43<04:00,  4.37it/s]
 91%|█████████ | 10016/11066 [36:43<03:57,  4.42it/s]
                                                     

 91%|█████████ | 10016/11066 [36:43<03:57,  4.42it/s]
 91%|█████████ | 10017/11066 [36:43<04:00,  4.36it/s]
                                                     

 91%|█████████ | 10017/11066 [36:43<04:00,  4.36it/s]
 91%|█████████ | 10018/11066 [36:44<03:59,  4.38it/s]
                                                     

 91%|█████████ | 10018/11066 [36:44<03:59,  4.38it/s]
 91%|█████████ | 10019/11066 [36:44<03:55,  4.45it/s]
                                                     

 91%|█████████ | 10019/11066 [36:44<03:55,  4.45it/s]
 91%|█████████ | 10020/11066 [36:44<03:55,  4.44it/s]
                                                     

 91%|█████████ | 10020/11066 [36:44<03:55,  4.44it/s]
 91%|█████████ | 10021/11066 [36:44<03:55,  4.44it/s]
                                                     

 91%|█████████ | 10021/11066 [36:44<03:55,  4.44it/s]
 91%|█████████ | 10022/11066 [36:45<03:59,  4.36it/s]
                                                     

 91%|█████████ | 10022/11066 [36:45<03:59,  4.36it/s]
 91%|█████████ | 10023/11066 [36:45<03:59,  4.35it/s]
                                                     

 91%|█████████ | 10023/11066 [36:45<03:59,  4.35it/s]
 91%|█████████ | 10024/11066 [36:45<03:58,  4.37it/s]
                                                     

 91%|█████████ | 10024/11066 [36:45<03:58,  4.37it/s]
 91%|█████████ | 10025/11066 [36:45<03:57,  4.39it/s]
                                                     

 91%|█████████ | 10025/11066 [36:45<03:57,  4.39it/s]
 91%|█████████ | 10026/11066 [36:45<03:52,  4.48it/s]
                                                     

 91%|█████████ | 10026/11066 [36:45<03:52,  4.48it/s]
 91%|█████████ | 10027/11066 [36:46<03:52,  4.46it/s]
                                                     

 91%|█████████ | 10027/11066 [36:46<03:52,  4.46it/s]
 91%|█████████ | 10028/11066 [36:46<03:48,  4.55it/s]
                                                     

 91%|█████████ | 10028/11066 [36:46<03:48,  4.55it/s]
 91%|█████████ | 10029/11066 [36:46<03:50,  4.49it/s]
                                                     

 91%|█████████ | 10029/11066 [36:46<03:50,  4.49it/s]
 91%|█████████ | 10030/11066 [36:46<03:51,  4.48it/s]
                                                     

 91%|█████████ | 10030/11066 [36:46<03:51,  4.48it/s]
 91%|█████████ | 10031/11066 [36:47<03:54,  4.41it/s]
                                                     

 91%|█████████ | 10031/11066 [36:47<03:54,  4.41it/s]
 91%|█████████ | 10032/11066 [36:47<03:52,  4.44it/s]
                                                     

 91%|█████████ | 10032/11066 [36:47<03:52,  4.44it/s]
 91%|█████████ | 10033/11066 [36:47<03:51,  4.46it/s]
                                                     
{'loss': 1.2233, 'learning_rate': 3.1068136634737033e-06, 'epoch': 1.79}
{'loss': 0.4786, 'learning_rate': 3.1041026567865535e-06, 'epoch': 1.79}
{'loss': 1.0258, 'learning_rate': 3.1013916500994036e-06, 'epoch': 1.79}
{'loss': 0.3603, 'learning_rate': 3.0986806434122537e-06, 'epoch': 1.79}
{'loss': 0.8764, 'learning_rate': 3.095969636725104e-06, 'epoch': 1.79}
{'loss': 1.071, 'learning_rate': 3.093258630037954e-06, 'epoch': 1.79}
{'loss': 1.3105, 'learning_rate': 3.0905476233508046e-06, 'epoch': 1.79}
{'loss': 0.5938, 'learning_rate': 3.0878366166636547e-06, 'epoch': 1.79}
{'loss': 0.8896, 'learning_rate': 3.085125609976505e-06, 'epoch': 1.79}
{'loss': 0.4319, 'learning_rate': 3.082414603289355e-06, 'epoch': 1.79}
{'loss': 0.7746, 'learning_rate': 3.079703596602205e-06, 'epoch': 1.79}
{'loss': 0.5577, 'learning_rate': 3.0769925899150552e-06, 'epoch': 1.79}
{'loss': 0.8535, 'learning_rate': 3.0742815832279054e-06, 'epoch': 1.8}
{'loss': 0.4326, 'learning_rate': 3.0715705765407555e-06, 'epoch': 1.8}
{'loss': 0.3985, 'learning_rate': 3.0688595698536056e-06, 'epoch': 1.8}
{'loss': 0.9847, 'learning_rate': 3.0661485631664558e-06, 'epoch': 1.8}
{'loss': 1.1321, 'learning_rate': 3.0634375564793063e-06, 'epoch': 1.8}
{'loss': 0.7124, 'learning_rate': 3.0607265497921565e-06, 'epoch': 1.8}
{'loss': 0.7556, 'learning_rate': 3.0580155431050066e-06, 'epoch': 1.8}
{'loss': 0.6134, 'learning_rate': 3.0553045364178567e-06, 'epoch': 1.8}
{'loss': 0.8479, 'learning_rate': 3.052593529730707e-06, 'epoch': 1.8}
{'loss': 0.5303, 'learning_rate': 3.049882523043557e-06, 'epoch': 1.8}
{'loss': 1.388, 'learning_rate': 3.047171516356407e-06, 'epoch': 1.8}
{'loss': 0.5986, 'learning_rate': 3.0444605096692573e-06, 'epoch': 1.8}
{'loss': 0.3123, 'learning_rate': 3.0417495029821074e-06, 'epoch': 1.8}
{'loss': 0.9021, 'learning_rate': 3.0390384962949575e-06, 'epoch': 1.8}
{'loss': 0.4803, 'learning_rate': 3.036327489607808e-06, 'epoch': 1.8}
{'loss': 0.5428, 'learning_rate': 3.0336164829206582e-06, 'epoch': 1.8}
{'loss': 0.5711, 'learning_rate': 3.0309054762335084e-06, 'epoch': 1.8}
{'loss': 0.3289, 'learning_rate': 3.0281944695463585e-06, 'epoch': 1.8}
{'loss': 0.737, 'learning_rate': 3.0254834628592086e-06, 'epoch': 1.8}
{'loss': 0.9093, 'learning_rate': 3.0227724561720588e-06, 'epoch': 1.8}
{'loss': 1.4915, 'learning_rate': 3.020061449484909e-06, 'epoch': 1.8}
{'loss': 0.7855, 'learning_rate': 3.017350442797759e-06, 'epoch': 1.8}
{'loss': 0.5284, 'learning_rate': 3.014639436110609e-06, 'epoch': 1.8}
{'loss': 0.6052, 'learning_rate': 3.0119284294234593e-06, 'epoch': 1.8}
{'loss': 1.1309, 'learning_rate': 3.0092174227363095e-06, 'epoch': 1.8}
{'loss': 0.5737, 'learning_rate': 3.00650641604916e-06, 'epoch': 1.8}
{'loss': 0.6817, 'learning_rate': 3.00379540936201e-06, 'epoch': 1.8}
{'loss': 0.6194, 'learning_rate': 3.0010844026748603e-06, 'epoch': 1.8}
{'loss': 0.381, 'learning_rate': 2.9983733959877104e-06, 'epoch': 1.8}
{'loss': 1.6147, 'learning_rate': 2.9956623893005605e-06, 'epoch': 1.8}
{'loss': 0.6841, 'learning_rate': 2.9929513826134107e-06, 'epoch': 1.8}
{'loss': 0.6506, 'learning_rate': 2.990240375926261e-06, 'epoch': 1.8}
{'loss': 0.5511, 'learning_rate': 2.987529369239111e-06, 'epoch': 1.8}
{'loss': 0.6983, 'learning_rate': 2.984818362551961e-06, 'epoch': 1.8}
{'loss': 0.9454, 'learning_rate': 2.9821073558648112e-06, 'epoch': 1.8}
{'loss': 0.6412, 'learning_rate': 2.9793963491776618e-06, 'epoch': 1.8}
{'loss': 0.6684, 'learning_rate': 2.976685342490512e-06, 'epoch': 1.8}
{'loss': 0.7774, 'learning_rate': 2.973974335803362e-06, 'epoch': 1.8}
{'loss': 0.3701, 'learning_rate': 2.971263329116212e-06, 'epoch': 1.8}
{'loss': 0.5967, 'learning_rate': 2.9685523224290623e-06, 'epoch': 1.8}
{'loss': 0.7521, 'learning_rate': 2.9658413157419124e-06, 'epoch': 1.8}
{'loss': 0.3783, 'learning_rate': 2.963130309054762e-06, 'epoch': 1.8}
{'loss': 0.7262, 'learning_rate': 2.9604193023676123e-06, 'epoch': 1.8}
{'loss': 0.3602, 'learning_rate': 2.9577082956804624e-06, 'epoch': 1.8}
{'loss': 1.8659, 'learning_rate': 2.9549972889933126e-06, 'epoch': 1.8}
{'loss': 0.7844, 'learning_rate': 2.9522862823061627e-06, 'epoch': 1.8}
{'loss': 0.8235, 'learning_rate': 2.9495752756190133e-06, 'epoch': 1.8}
{'loss': 0.5405, 'learning_rate': 2.9468642689318634e-06, 'epoch': 1.8}
{'loss': 0.6533, 'learning_rate': 2.9441532622447135e-06, 'epoch': 1.8}
{'loss': 0.7635, 'learning_rate': 2.9414422555575637e-06, 'epoch': 1.8}
{'loss': 0.9399, 'learning_rate': 2.938731248870414e-06, 'epoch': 1.8}
{'loss': 0.7491, 'learning_rate': 2.936020242183264e-06, 'epoch': 1.8}
{'loss': 0.8449, 'learning_rate': 2.933309235496114e-06, 'epoch': 1.8}
{'loss': 0.6107, 'learning_rate': 2.930598228808964e-06, 'epoch': 1.8}
{'loss': 0.9974, 'learning_rate': 2.9278872221218143e-06, 'epoch': 1.8}
{'loss': 1.059, 'learning_rate': 2.9251762154346645e-06, 'epoch': 1.8}
{'loss': 0.3379, 'learning_rate': 2.922465208747515e-06, 'epoch': 1.81}
{'loss': 1.103, 'learning_rate': 2.919754202060365e-06, 'epoch': 1.81}
{'loss': 0.4525, 'learning_rate': 2.9170431953732153e-06, 'epoch': 1.81}
{'loss': 0.5262, 'learning_rate': 2.9143321886860654e-06, 'epoch': 1.81}
{'loss': 1.4366, 'learning_rate': 2.9116211819989156e-06, 'epoch': 1.81}
{'loss': 0.4769, 'learning_rate': 2.9089101753117657e-06, 'epoch': 1.81}
{'loss': 0.9024, 'learning_rate': 2.906199168624616e-06, 'epoch': 1.81}
{'loss': 0.3784, 'learning_rate': 2.903488161937466e-06, 'epoch': 1.81}
{'loss': 0.9575, 'learning_rate': 2.900777155250316e-06, 'epoch': 1.81}
{'loss': 0.5496, 'learning_rate': 2.8980661485631662e-06, 'epoch': 1.81}
{'loss': 0.7908, 'learning_rate': 2.8953551418760168e-06, 'epoch': 1.81}
{'loss': 0.6308, 'learning_rate': 2.892644135188867e-06, 'epoch': 1.81}
{'loss': 0.5062, 'learning_rate': 2.889933128501717e-06, 'epoch': 1.81}
{'loss': 0.755, 'learning_rate': 2.887222121814567e-06, 'epoch': 1.81}
{'loss': 0.8384, 'learning_rate': 2.8845111151274173e-06, 'epoch': 1.81}
{'loss': 0.5119, 'learning_rate': 2.8818001084402675e-06, 'epoch': 1.81}
{'loss': 0.4633, 'learning_rate': 2.8790891017531176e-06, 'epoch': 1.81}
{'loss': 0.6086, 'learning_rate': 2.8763780950659677e-06, 'epoch': 1.81}
{'loss': 0.5182, 'learning_rate': 2.873667088378818e-06, 'epoch': 1.81}
{'loss': 1.4092, 'learning_rate': 2.870956081691668e-06, 'epoch': 1.81}
{'loss': 0.773, 'learning_rate': 2.868245075004518e-06, 'epoch': 1.81}
{'loss': 0.6108, 'learning_rate': 2.8655340683173687e-06, 'epoch': 1.81}
{'loss': 0.5841, 'learning_rate': 2.862823061630219e-06, 'epoch': 1.81}
{'loss': 0.5781, 'learning_rate': 2.860112054943069e-06, 'epoch': 1.81}
{'loss': 0.9404, 'learning_rate': 2.857401048255919e-06, 'epoch': 1.81}
{'loss': 0.614, 'learning_rate': 2.8546900415687692e-06, 'epoch': 1.81}
{'loss': 0.6607, 'learning_rate': 2.8519790348816194e-06, 'epoch': 1.81}
{'loss': 0.5134, 'learning_rate': 2.8492680281944695e-06, 'epoch': 1.81}
{'loss': 0.7918, 'learning_rate': 2.8465570215073196e-06, 'epoch': 1.81}
{'loss': 0.4677, 'learning_rate': 2.8438460148201698e-06, 'epoch': 1.81}
{'loss': 0.4002, 'learning_rate': 2.84113500813302e-06, 'epoch': 1.81}
{'loss': 0.3726, 'learning_rate': 2.8384240014458705e-06, 'epoch': 1.81}
{'loss': 0.3862, 'learning_rate': 2.8357129947587206e-06, 'epoch': 1.81}
{'loss': 0.4107, 'learning_rate': 2.8330019880715707e-06, 'epoch': 1.81}
{'loss': 0.513, 'learning_rate': 2.830290981384421e-06, 'epoch': 1.81}
{'loss': 0.686, 'learning_rate': 2.827579974697271e-06, 'epoch': 1.81}
{'loss': 0.4302, 'learning_rate': 2.824868968010121e-06, 'epoch': 1.81}
{'loss': 0.9332, 'learning_rate': 2.8221579613229713e-06, 'epoch': 1.81}
{'loss': 0.7861, 'learning_rate': 2.8194469546358214e-06, 'epoch': 1.81}
{'loss': 0.6194, 'learning_rate': 2.8167359479486715e-06, 'epoch': 1.81}
{'loss': 0.6695, 'learning_rate': 2.8140249412615217e-06, 'epoch': 1.81}
{'loss': 0.3674, 'learning_rate': 2.811313934574372e-06, 'epoch': 1.81}
{'loss': 0.5039, 'learning_rate': 2.8086029278872224e-06, 'epoch': 1.81}
{'loss': 0.4844, 'learning_rate': 2.8058919212000725e-06, 'epoch': 1.81}
{'loss': 0.9962, 'learning_rate': 2.8031809145129226e-06, 'epoch': 1.81}

 91%|█████████ | 10033/11066 [36:47<03:51,  4.46it/s]
 91%|█████████ | 10034/11066 [36:47<03:51,  4.45it/s]
                                                     

 91%|█████████ | 10034/11066 [36:47<03:51,  4.45it/s]
 91%|█████████ | 10035/11066 [36:47<03:51,  4.45it/s]
                                                     

 91%|█████████ | 10035/11066 [36:47<03:51,  4.45it/s]
 91%|█████████ | 10036/11066 [36:48<03:52,  4.43it/s]
                                                     

 91%|█████████ | 10036/11066 [36:48<03:52,  4.43it/s]
 91%|█████████ | 10037/11066 [36:48<03:54,  4.39it/s]
                                                     

 91%|█████████ | 10037/11066 [36:48<03:54,  4.39it/s]
 91%|█████████ | 10038/11066 [36:48<03:55,  4.37it/s]
                                                     

 91%|█████████ | 10038/11066 [36:48<03:55,  4.37it/s]
 91%|█████████ | 10039/11066 [36:48<03:53,  4.40it/s]
                                                     

 91%|█████████ | 10039/11066 [36:48<03:53,  4.40it/s]
 91%|█████████ | 10040/11066 [36:49<03:51,  4.43it/s]
                                                     

 91%|█████████ | 10040/11066 [36:49<03:51,  4.43it/s]
 91%|█████████ | 10041/11066 [36:49<03:50,  4.45it/s]
                                                     

 91%|█████████ | 10041/11066 [36:49<03:50,  4.45it/s]
 91%|█████████ | 10042/11066 [36:49<03:46,  4.52it/s]
                                                     

 91%|█████████ | 10042/11066 [36:49<03:46,  4.52it/s]
 91%|█████████ | 10043/11066 [36:49<03:44,  4.57it/s]
                                                     

 91%|█████████ | 10043/11066 [36:49<03:44,  4.57it/s]
 91%|█████████ | 10044/11066 [36:49<03:44,  4.56it/s]
                                                     

 91%|█████████ | 10044/11066 [36:49<03:44,  4.56it/s]
 91%|█████████ | 10045/11066 [36:50<03:42,  4.59it/s]
                                                     

 91%|█████████ | 10045/11066 [36:50<03:42,  4.59it/s]
 91%|█████████ | 10046/11066 [36:50<03:43,  4.56it/s]
                                                     

 91%|█████████ | 10046/11066 [36:50<03:43,  4.56it/s]
 91%|█████████ | 10047/11066 [36:50<03:41,  4.60it/s]
                                                     

 91%|█████████ | 10047/11066 [36:50<03:41,  4.60it/s]
 91%|█████████ | 10048/11066 [36:50<03:41,  4.60it/s]
                                                     

 91%|█████████ | 10048/11066 [36:50<03:41,  4.60it/s]
 91%|█████████ | 10049/11066 [36:51<03:38,  4.65it/s]
                                                     

 91%|█████████ | 10049/11066 [36:51<03:38,  4.65it/s]
 91%|█████████ | 10050/11066 [36:51<03:40,  4.60it/s]
                                                     

 91%|█████████ | 10050/11066 [36:51<03:40,  4.60it/s]
 91%|█████████ | 10051/11066 [36:51<03:40,  4.61it/s]
                                                     

 91%|█████████ | 10051/11066 [36:51<03:40,  4.61it/s]
 91%|█████████ | 10052/11066 [36:51<03:42,  4.55it/s]
                                                     

 91%|█████████ | 10052/11066 [36:51<03:42,  4.55it/s]
 91%|█████████ | 10053/11066 [36:51<03:43,  4.53it/s]
                                                     

 91%|█████████ | 10053/11066 [36:51<03:43,  4.53it/s]
 91%|█████████ | 10054/11066 [36:52<03:41,  4.57it/s]
                                                     

 91%|█████████ | 10054/11066 [36:52<03:41,  4.57it/s]
 91%|█████████ | 10055/11066 [36:52<03:43,  4.53it/s]
                                                     

 91%|█████████ | 10055/11066 [36:52<03:43,  4.53it/s]
 91%|█████████ | 10056/11066 [36:52<03:44,  4.50it/s]
                                                     

 91%|█████████ | 10056/11066 [36:52<03:44,  4.50it/s]
 91%|█████████ | 10057/11066 [36:52<03:44,  4.50it/s]
                                                     

 91%|█████████ | 10057/11066 [36:52<03:44,  4.50it/s]
 91%|█████████ | 10058/11066 [36:53<03:44,  4.50it/s]
                                                     

 91%|█████████ | 10058/11066 [36:53<03:44,  4.50it/s]
 91%|█████████ | 10059/11066 [36:53<03:42,  4.53it/s]
                                                     

 91%|█████████ | 10059/11066 [36:53<03:42,  4.53it/s]
 91%|█████████ | 10060/11066 [36:53<03:40,  4.56it/s]
                                                     

 91%|█████████ | 10060/11066 [36:53<03:40,  4.56it/s]
 91%|█████████ | 10061/11066 [36:53<03:39,  4.58it/s]
                                                     

 91%|█████████ | 10061/11066 [36:53<03:39,  4.58it/s]
 91%|█████████ | 10062/11066 [36:53<03:40,  4.56it/s]
                                                     

 91%|█████████ | 10062/11066 [36:53<03:40,  4.56it/s]
 91%|█████████ | 10063/11066 [36:54<03:38,  4.59it/s]
                                                     

 91%|█████████ | 10063/11066 [36:54<03:38,  4.59it/s]
 91%|█████████ | 10064/11066 [36:54<03:40,  4.55it/s]
                                                     

 91%|█████████ | 10064/11066 [36:54<03:40,  4.55it/s]
 91%|█████████ | 10065/11066 [36:54<03:39,  4.56it/s]
                                                     

 91%|█████████ | 10065/11066 [36:54<03:39,  4.56it/s]
 91%|█████████ | 10066/11066 [36:54<03:41,  4.52it/s]
                                                     

 91%|█████████ | 10066/11066 [36:54<03:41,  4.52it/s]
 91%|█████████ | 10067/11066 [36:55<03:38,  4.57it/s]
                                                     

 91%|█████████ | 10067/11066 [36:55<03:38,  4.57it/s]
 91%|█████████ | 10068/11066 [36:55<03:39,  4.54it/s]
                                                     

 91%|█████████ | 10068/11066 [36:55<03:39,  4.54it/s]
 91%|█████████ | 10069/11066 [36:55<03:40,  4.52it/s]
                                                     

 91%|█████████ | 10069/11066 [36:55<03:40,  4.52it/s]
 91%|█████████ | 10070/11066 [36:55<03:40,  4.52it/s]
                                                     

 91%|█████████ | 10070/11066 [36:55<03:40,  4.52it/s]
 91%|█████████ | 10071/11066 [36:55<03:40,  4.51it/s]
                                                     

 91%|█████████ | 10071/11066 [36:55<03:40,  4.51it/s]
 91%|█████████ | 10072/11066 [36:56<03:39,  4.53it/s]
                                                     

 91%|█████████ | 10072/11066 [36:56<03:39,  4.53it/s]
 91%|█████████ | 10073/11066 [36:56<03:40,  4.50it/s]
                                                     

 91%|█████████ | 10073/11066 [36:56<03:40,  4.50it/s]
 91%|█████████ | 10074/11066 [36:56<03:38,  4.53it/s]
                                                     

 91%|█████████ | 10074/11066 [36:56<03:38,  4.53it/s]
 91%|█████████ | 10075/11066 [36:56<03:40,  4.50it/s]
                                                     

 91%|█████████ | 10075/11066 [36:56<03:40,  4.50it/s]
 91%|█████████ | 10076/11066 [36:57<03:40,  4.49it/s]
                                                     

 91%|█████████ | 10076/11066 [36:57<03:40,  4.49it/s]
 91%|█████████ | 10077/11066 [36:57<03:40,  4.49it/s]
                                                     

 91%|█████████ | 10077/11066 [36:57<03:40,  4.49it/s]
 91%|█████████ | 10078/11066 [36:57<03:39,  4.49it/s]
                                                     

 91%|█████████ | 10078/11066 [36:57<03:39,  4.49it/s]
 91%|█████████ | 10079/11066 [36:57<03:37,  4.53it/s]
                                                     

 91%|█████████ | 10079/11066 [36:57<03:37,  4.53it/s]
 91%|█████████ | 10080/11066 [36:57<03:37,  4.54it/s]
                                                     

 91%|█████████ | 10080/11066 [36:57<03:37,  4.54it/s]
 91%|█████████ | 10081/11066 [36:58<03:36,  4.55it/s]
                                                     

 91%|█████████ | 10081/11066 [36:58<03:36,  4.55it/s]
 91%|█████████ | 10082/11066 [36:58<03:37,  4.52it/s]
                                                     

 91%|█████████ | 10082/11066 [36:58<03:37,  4.52it/s]
 91%|█████████ | 10083/11066 [36:58<03:36,  4.55it/s]
                                                     

 91%|█████████ | 10083/11066 [36:58<03:36,  4.55it/s]
 91%|█████████ | 10084/11066 [36:58<03:34,  4.57it/s]
                                                     

 91%|█████████ | 10084/11066 [36:58<03:34,  4.57it/s]
 91%|█████████ | 10085/11066 [36:59<03:35,  4.54it/s]
                                                     

 91%|█████████ | 10085/11066 [36:59<03:35,  4.54it/s]
 91%|█████████ | 10086/11066 [36:59<03:36,  4.53it/s]
                                                     

 91%|█████████ | 10086/11066 [36:59<03:36,  4.53it/s]
 91%|█████████ | 10087/11066 [36:59<03:36,  4.52it/s]
                                                     

 91%|█████████ | 10087/11066 [36:59<03:36,  4.52it/s]
 91%|█████████ | 10088/11066 [36:59<03:36,  4.52it/s]
                                                     

 91%|█████████ | 10088/11066 [36:59<03:36,  4.52it/s]
 91%|█████████ | 10089/11066 [36:59<03:34,  4.55it/s]
                                                     

 91%|█████████ | 10089/11066 [36:59<03:34,  4.55it/s]
 91%|█████████ | 10090/11066 [37:00<03:36,  4.51it/s]
                                                     

 91%|█████████ | 10090/11066 [37:00<03:36,  4.51it/s]
 91%|█████████ | 10091/11066 [37:00<03:34,  4.54it/s]
                                                     

 91%|█████████ | 10091/11066 [37:00<03:34,  4.54it/s]
 91%|█████████ | 10092/11066 [37:00<03:34,  4.55it/s]
                                                     

 91%|█████████ | 10092/11066 [37:00<03:34,  4.55it/s]
 91%|█████████ | 10093/11066 [37:00<03:33,  4.56it/s]
                                                     

 91%|█████████ | 10093/11066 [37:00<03:33,  4.56it/s]
 91%|█████████ | 10094/11066 [37:01<03:34,  4.53it/s]
                                                     

 91%|█████████ | 10094/11066 [37:01<03:34,  4.53it/s]
 91%|█████████ | 10095/11066 [37:01<03:35,  4.51it/s]
                                                     

 91%|█████████ | 10095/11066 [37:01<03:35,  4.51it/s]
 91%|█████████ | 10096/11066 [37:01<03:35,  4.50it/s]
                                                     

 91%|█████████ | 10096/11066 [37:01<03:35,  4.50it/s]
 91%|█████████ | 10097/11066 [37:01<03:32,  4.56it/s]
                                                     

 91%|█████████ | 10097/11066 [37:01<03:32,  4.56it/s]
 91%|█████████▏| 10098/11066 [37:01<03:30,  4.60it/s]
                                                     

 91%|█████████▏| 10098/11066 [37:01<03:30,  4.60it/s]
 91%|█████████▏| 10099/11066 [37:02<03:31,  4.57it/s]
                                                     

 91%|█████████▏| 10099/11066 [37:02<03:31,  4.57it/s]
 91%|█████████▏| 10100/11066 [37:02<03:29,  4.61it/s]
                                                     

 91%|█████████▏| 10100/11066 [37:02<03:29,  4.61it/s]
 91%|█████████▏| 10101/11066 [37:02<03:28,  4.63it/s]
                                                     

 91%|█████████▏| 10101/11066 [37:02<03:28,  4.63it/s]
 91%|█████████▏| 10102/11066 [37:02<03:26,  4.67it/s]
                                                     

 91%|█████████▏| 10102/11066 [37:02<03:26,  4.67it/s]
 91%|█████████▏| 10103/11066 [37:02<03:24,  4.70it/s]
                                                     

 91%|█████████▏| 10103/11066 [37:02<03:24,  4.70it/s]
 91%|█████████▏| 10104/11066 [37:03<03:24,  4.70it/s]
                                                     

 91%|█████████▏| 10104/11066 [37:03<03:24,  4.70it/s]
 91%|█████████▏| 10105/11066 [37:03<03:24,  4.70it/s]
                                                     

 91%|█████████▏| 10105/11066 [37:03<03:24,  4.70it/s]
 91%|█████████▏| 10106/11066 [37:03<03:24,  4.70it/s]
                                                     

 91%|█████████▏| 10106/11066 [37:03<03:24,  4.70it/s]
 91%|█████████▏| 10107/11066 [37:03<03:22,  4.73it/s]
                                                     

 91%|█████████▏| 10107/11066 [37:03<03:22,  4.73it/s]
 91%|█████████▏| 10108/11066 [37:04<03:25,  4.66it/s]
                                                     

 91%|█████████▏| 10108/11066 [37:04<03:25,  4.66it/s]
 91%|█████████▏| 10109/11066 [37:04<03:24,  4.68it/s]
                                                     

 91%|█████████▏| 10109/11066 [37:04<03:24,  4.68it/s]
 91%|█████████▏| 10110/11066 [37:04<03:27,  4.61it/s]
                                                     

 91%|█████████▏| 10110/11066 [37:04<03:27,  4.61it/s]
 91%|█████████▏| 10111/11066 [37:04<03:28,  4.58it/s]
                                                     

 91%|█████████▏| 10111/11066 [37:04<03:28,  4.58it/s]
 91%|█████████▏| 10112/11066 [37:04<03:27,  4.60it/s]
                                                     

 91%|█████████▏| 10112/11066 [37:04<03:27,  4.60it/s]
 91%|█████████▏| 10113/11066 [37:05<03:26,  4.63it/s]
                                                     

 91%|█████████▏| 10113/11066 [37:05<03:26,  4.63it/s]
 91%|█████████▏| 10114/11066 [37:05<03:25,  4.64it/s]
                                                     

 91%|█████████▏| 10114/11066 [37:05<03:25,  4.64it/s]
 91%|█████████▏| 10115/11066 [37:05<03:24,  4.66it/s]
                                                     

 91%|█████████▏| 10115/11066 [37:05<03:24,  4.66it/s]
 91%|█████████▏| 10116/11066 [37:05<03:26,  4.60it/s]
                                                     

 91%|█████████▏| 10116/11066 [37:05<03:26,  4.60it/s]
 91%|█████████▏| 10117/11066 [37:05<03:26,  4.60it/s]
                                                     

 91%|█████████▏| 10117/11066 [37:05<03:26,  4.60it/s]
 91%|█████████▏| 10118/11066 [37:06<03:24,  4.63it/s]
                                                     

 91%|█████████▏| 10118/11066 [37:06<03:24,  4.63it/s]
 91%|█████████▏| 10119/11066 [37:06<03:24,  4.63it/s]
                                                     

 91%|█████████▏| 10119/11066 [37:06<03:24,  4.63it/s]
 91%|█████████▏| 10120/11066 [37:06<03:24,  4.62it/s]
                                                     

 91%|█████████▏| 10120/11066 [37:06<03:24,  4.62it/s]
 91%|█████████▏| 10121/11066 [37:06<03:25,  4.60it/s]
                                                     

 91%|█████████▏| 10121/11066 [37:06<03:25,  4.60it/s]
 91%|█████████▏| 10122/11066 [37:07<03:25,  4.60it/s]
                                                     

 91%|█████████▏| 10122/11066 [37:07<03:25,  4.60it/s]
 91%|█████████▏| 10123/11066 [37:07<03:27,  4.55it/s]
                                                     

 91%|█████████▏| 10123/11066 [37:07<03:27,  4.55it/s]
 91%|█████████▏| 10124/11066 [37:07<03:28,  4.53it/s]
                                                     

 91%|█████████▏| 10124/11066 [37:07<03:28,  4.53it/s]
 91%|█████████▏| 10125/11066 [37:07<03:30,  4.48it/s]
                                                     

 91%|█████████▏| 10125/11066 [37:07<03:30,  4.48it/s]
 92%|█████████▏| 10126/11066 [37:07<03:32,  4.43it/s]
                                                     

 92%|█████████▏| 10126/11066 [37:07<03:32,  4.43it/s]
 92%|█████████▏| 10127/11066 [37:08<03:30,  4.45it/s]
                                                     

 92%|█████████▏| 10127/11066 [37:08<03:30,  4.45it/s]
 92%|█████████▏| 10128/11066 [37:08<03:28,  4.50it/s]
                                                     

 92%|█████████▏| 10128/11066 [37:08<03:28,  4.50it/s]
 92%|█████████▏| 10129/11066 [37:08<03:27,  4.52it/s]
                                                     

 92%|█████████▏| 10129/11066 [37:08<03:27,  4.52it/s]
 92%|█████████▏| 10130/11066 [37:08<03:25,  4.55it/s]
                                                     

 92%|█████████▏| 10130/11066 [37:08<03:25,  4.55it/s]
 92%|█████████▏| 10131/11066 [37:09<03:23,  4.58it/s]
                                                     

 92%|█████████▏| 10131/11066 [37:09<03:23,  4.58it/s]
 92%|█████████▏| 10132/11066 [37:09<03:25,  4.55it/s]
                                                     

 92%|█████████▏| 10132/11066 [37:09<03:25,  4.55it/s]
 92%|█████████▏| 10133/11066 [37:09<03:25,  4.53it/s]
                                                     

 92%|█████████▏| 10133/11066 [37:09<03:25,  4.53it/s]
 92%|█████████▏| 10134/11066 [37:09<03:26,  4.52it/s]
                                                     

 92%|█████████▏| 10134/11066 [37:09<03:26,  4.52it/s]
 92%|█████████▏| 10135/11066 [37:09<03:25,  4.52it/s]
                                                     

 92%|█████████▏| 10135/11066 [37:09<03:25,  4.52it/s]
 92%|█████████▏| 10136/11066 [37:10<03:26,  4.51it/s]
                                                     

 92%|█████████▏| 10136/11066 [37:10<03:26,  4.51it/s]
 92%|█████████▏| 10137/11066 [37:10<03:26,  4.50it/s]
                                                     

 92%|█████████▏| 10137/11066 [37:10<03:26,  4.50it/s]
 92%|█████████▏| 10138/11066 [37:10<03:23,  4.56it/s]
                                                     

 92%|█████████▏| 10138/11066 [37:10<03:23,  4.56it/s]
 92%|█████████▏| 10139/11066 [37:10<03:21,  4.60it/s]
                                                     

 92%|█████████▏| 10139/11066 [37:10<03:21,  4.60it/s]
 92%|█████████▏| 10140/11066 [37:11<03:18,  4.66it/s]
                                                     

 92%|█████████▏| 10140/11066 [37:11<03:18,  4.66it/s]
 92%|█████████▏| 10141/11066 [37:11<03:20,  4.60it/s]
                                                     

 92%|█████████▏| 10141/11066 [37:11<03:20,  4.60it/s]
 92%|█████████▏| 10142/11066 [37:11<03:20,  4.60it/s]
                                                     

 92%|█████████▏| 10142/11066 [37:11<03:20,  4.60it/s]
 92%|█████████▏| 10143/11066 [37:11<03:23,  4.54it/s]
                                                     

 92%|█████████▏| 10143/11066 [37:11<03:23,  4.54it/s]
 92%|█████████▏| 10144/11066 [37:11<03:24,  4.50it/s]
                                                     

 92%|█████████▏| 10144/11066 [37:11<03:24,  4.50it/s]
 92%|█████████▏| 10145/11066 [37:12<03:25,  4.48it/s]
                                                     

 92%|█████████▏| 10145/11066 [37:12<03:25,  4.48it/s]
 92%|█████████▏| 10146/11066 [37:12<03:23,  4.52it/s]
                                                     
{'loss': 0.8146, 'learning_rate': 2.8004699078257728e-06, 'epoch': 1.81}
{'loss': 0.48, 'learning_rate': 2.797758901138623e-06, 'epoch': 1.81}
{'loss': 1.0203, 'learning_rate': 2.795047894451473e-06, 'epoch': 1.81}
{'loss': 0.6507, 'learning_rate': 2.792336887764323e-06, 'epoch': 1.81}
{'loss': 0.6475, 'learning_rate': 2.7896258810771733e-06, 'epoch': 1.81}
{'loss': 0.3103, 'learning_rate': 2.7869148743900234e-06, 'epoch': 1.81}
{'loss': 1.0561, 'learning_rate': 2.7842038677028736e-06, 'epoch': 1.81}
{'loss': 0.3481, 'learning_rate': 2.781492861015724e-06, 'epoch': 1.81}
{'loss': 0.6997, 'learning_rate': 2.7787818543285743e-06, 'epoch': 1.81}
{'loss': 1.0446, 'learning_rate': 2.7760708476414244e-06, 'epoch': 1.81}
{'loss': 1.1141, 'learning_rate': 2.7733598409542745e-06, 'epoch': 1.82}
{'loss': 0.1958, 'learning_rate': 2.7706488342671247e-06, 'epoch': 1.82}
{'loss': 0.6018, 'learning_rate': 2.767937827579975e-06, 'epoch': 1.82}
{'loss': 0.244, 'learning_rate': 2.765226820892825e-06, 'epoch': 1.82}
{'loss': 0.5705, 'learning_rate': 2.762515814205675e-06, 'epoch': 1.82}
{'loss': 0.5253, 'learning_rate': 2.759804807518525e-06, 'epoch': 1.82}
{'loss': 1.0956, 'learning_rate': 2.7570938008313753e-06, 'epoch': 1.82}
{'loss': 0.8115, 'learning_rate': 2.7543827941442255e-06, 'epoch': 1.82}
{'loss': 1.2263, 'learning_rate': 2.751671787457076e-06, 'epoch': 1.82}
{'loss': 0.5767, 'learning_rate': 2.748960780769926e-06, 'epoch': 1.82}
{'loss': 0.3492, 'learning_rate': 2.7462497740827763e-06, 'epoch': 1.82}
{'loss': 0.4542, 'learning_rate': 2.7435387673956264e-06, 'epoch': 1.82}
{'loss': 0.1409, 'learning_rate': 2.7408277607084766e-06, 'epoch': 1.82}
{'loss': 0.2844, 'learning_rate': 2.7381167540213267e-06, 'epoch': 1.82}
{'loss': 0.4808, 'learning_rate': 2.735405747334177e-06, 'epoch': 1.82}
{'loss': 0.3602, 'learning_rate': 2.732694740647027e-06, 'epoch': 1.82}
{'loss': 1.0641, 'learning_rate': 2.729983733959877e-06, 'epoch': 1.82}
{'loss': 1.067, 'learning_rate': 2.7272727272727272e-06, 'epoch': 1.82}
{'loss': 1.0052, 'learning_rate': 2.7245617205855778e-06, 'epoch': 1.82}
{'loss': 0.4045, 'learning_rate': 2.721850713898428e-06, 'epoch': 1.82}
{'loss': 0.6802, 'learning_rate': 2.719139707211278e-06, 'epoch': 1.82}
{'loss': 0.7177, 'learning_rate': 2.716428700524128e-06, 'epoch': 1.82}
{'loss': 0.7057, 'learning_rate': 2.7137176938369783e-06, 'epoch': 1.82}
{'loss': 0.4504, 'learning_rate': 2.7110066871498285e-06, 'epoch': 1.82}
{'loss': 1.2565, 'learning_rate': 2.7082956804626786e-06, 'epoch': 1.82}
{'loss': 0.9051, 'learning_rate': 2.7055846737755287e-06, 'epoch': 1.82}
{'loss': 0.6989, 'learning_rate': 2.702873667088379e-06, 'epoch': 1.82}
{'loss': 0.9877, 'learning_rate': 2.700162660401229e-06, 'epoch': 1.82}
{'loss': 0.851, 'learning_rate': 2.6974516537140796e-06, 'epoch': 1.82}
{'loss': 0.6756, 'learning_rate': 2.6947406470269297e-06, 'epoch': 1.82}
{'loss': 0.4935, 'learning_rate': 2.69202964033978e-06, 'epoch': 1.82}
{'loss': 0.5466, 'learning_rate': 2.68931863365263e-06, 'epoch': 1.82}
{'loss': 0.4573, 'learning_rate': 2.68660762696548e-06, 'epoch': 1.82}
{'loss': 0.7219, 'learning_rate': 2.6838966202783302e-06, 'epoch': 1.82}
{'loss': 0.9674, 'learning_rate': 2.6811856135911804e-06, 'epoch': 1.82}
{'loss': 0.6887, 'learning_rate': 2.6784746069040305e-06, 'epoch': 1.82}
{'loss': 0.7309, 'learning_rate': 2.6757636002168806e-06, 'epoch': 1.82}
{'loss': 0.6239, 'learning_rate': 2.6730525935297308e-06, 'epoch': 1.82}
{'loss': 0.6339, 'learning_rate': 2.670341586842581e-06, 'epoch': 1.82}
{'loss': 0.6514, 'learning_rate': 2.6676305801554315e-06, 'epoch': 1.82}
{'loss': 0.9033, 'learning_rate': 2.6649195734682816e-06, 'epoch': 1.82}
{'loss': 0.8428, 'learning_rate': 2.6622085667811317e-06, 'epoch': 1.82}
{'loss': 0.853, 'learning_rate': 2.659497560093982e-06, 'epoch': 1.82}
{'loss': 0.5933, 'learning_rate': 2.656786553406832e-06, 'epoch': 1.82}
{'loss': 0.4804, 'learning_rate': 2.654075546719682e-06, 'epoch': 1.82}
{'loss': 1.5426, 'learning_rate': 2.6513645400325323e-06, 'epoch': 1.82}
{'loss': 0.4933, 'learning_rate': 2.6486535333453824e-06, 'epoch': 1.82}
{'loss': 0.4915, 'learning_rate': 2.6459425266582325e-06, 'epoch': 1.82}
{'loss': 0.9157, 'learning_rate': 2.6432315199710827e-06, 'epoch': 1.82}
{'loss': 0.4462, 'learning_rate': 2.6405205132839332e-06, 'epoch': 1.82}
{'loss': 0.5005, 'learning_rate': 2.6378095065967834e-06, 'epoch': 1.82}
{'loss': 0.7214, 'learning_rate': 2.6350984999096335e-06, 'epoch': 1.82}
{'loss': 0.428, 'learning_rate': 2.6323874932224836e-06, 'epoch': 1.82}
{'loss': 0.5308, 'learning_rate': 2.6296764865353338e-06, 'epoch': 1.82}
{'loss': 0.2224, 'learning_rate': 2.626965479848184e-06, 'epoch': 1.82}
{'loss': 1.0586, 'learning_rate': 2.624254473161034e-06, 'epoch': 1.83}
{'loss': 0.4583, 'learning_rate': 2.621543466473884e-06, 'epoch': 1.83}
{'loss': 0.4739, 'learning_rate': 2.6188324597867343e-06, 'epoch': 1.83}
{'loss': 1.1552, 'learning_rate': 2.616121453099584e-06, 'epoch': 1.83}
{'loss': 0.7765, 'learning_rate': 2.613410446412434e-06, 'epoch': 1.83}
{'loss': 0.9269, 'learning_rate': 2.6106994397252847e-06, 'epoch': 1.83}
{'loss': 0.4049, 'learning_rate': 2.607988433038135e-06, 'epoch': 1.83}
{'loss': 0.6263, 'learning_rate': 2.605277426350985e-06, 'epoch': 1.83}
{'loss': 0.6983, 'learning_rate': 2.602566419663835e-06, 'epoch': 1.83}
{'loss': 0.7949, 'learning_rate': 2.5998554129766852e-06, 'epoch': 1.83}
{'loss': 0.6087, 'learning_rate': 2.5971444062895354e-06, 'epoch': 1.83}
{'loss': 0.4151, 'learning_rate': 2.5944333996023855e-06, 'epoch': 1.83}
{'loss': 0.4637, 'learning_rate': 2.5917223929152356e-06, 'epoch': 1.83}
{'loss': 0.8294, 'learning_rate': 2.5890113862280858e-06, 'epoch': 1.83}
{'loss': 0.5237, 'learning_rate': 2.586300379540936e-06, 'epoch': 1.83}
{'loss': 0.7152, 'learning_rate': 2.5835893728537865e-06, 'epoch': 1.83}
{'loss': 0.2683, 'learning_rate': 2.5808783661666366e-06, 'epoch': 1.83}
{'loss': 0.4688, 'learning_rate': 2.5781673594794867e-06, 'epoch': 1.83}
{'loss': 0.9487, 'learning_rate': 2.575456352792337e-06, 'epoch': 1.83}
{'loss': 0.7854, 'learning_rate': 2.572745346105187e-06, 'epoch': 1.83}
{'loss': 0.5271, 'learning_rate': 2.570034339418037e-06, 'epoch': 1.83}
{'loss': 0.3126, 'learning_rate': 2.5673233327308873e-06, 'epoch': 1.83}
{'loss': 0.8192, 'learning_rate': 2.5646123260437374e-06, 'epoch': 1.83}
{'loss': 1.3328, 'learning_rate': 2.5619013193565875e-06, 'epoch': 1.83}
{'loss': 0.6665, 'learning_rate': 2.5591903126694377e-06, 'epoch': 1.83}
{'loss': 0.5691, 'learning_rate': 2.5564793059822882e-06, 'epoch': 1.83}
{'loss': 1.0675, 'learning_rate': 2.5537682992951384e-06, 'epoch': 1.83}
{'loss': 0.4912, 'learning_rate': 2.5510572926079885e-06, 'epoch': 1.83}
{'loss': 0.7314, 'learning_rate': 2.5483462859208386e-06, 'epoch': 1.83}
{'loss': 0.9095, 'learning_rate': 2.5456352792336888e-06, 'epoch': 1.83}
{'loss': 0.5296, 'learning_rate': 2.542924272546539e-06, 'epoch': 1.83}
{'loss': 0.4498, 'learning_rate': 2.540213265859389e-06, 'epoch': 1.83}
{'loss': 0.542, 'learning_rate': 2.537502259172239e-06, 'epoch': 1.83}
{'loss': 0.5898, 'learning_rate': 2.5347912524850893e-06, 'epoch': 1.83}
{'loss': 0.4028, 'learning_rate': 2.5320802457979394e-06, 'epoch': 1.83}
{'loss': 1.0224, 'learning_rate': 2.5293692391107896e-06, 'epoch': 1.83}
{'loss': 0.884, 'learning_rate': 2.52665823242364e-06, 'epoch': 1.83}
{'loss': 0.634, 'learning_rate': 2.5239472257364903e-06, 'epoch': 1.83}
{'loss': 1.1597, 'learning_rate': 2.5212362190493404e-06, 'epoch': 1.83}
{'loss': 0.52, 'learning_rate': 2.5185252123621905e-06, 'epoch': 1.83}
{'loss': 0.4592, 'learning_rate': 2.5158142056750407e-06, 'epoch': 1.83}
{'loss': 0.3364, 'learning_rate': 2.513103198987891e-06, 'epoch': 1.83}
{'loss': 0.4622, 'learning_rate': 2.510392192300741e-06, 'epoch': 1.83}
{'loss': 0.3739, 'learning_rate': 2.507681185613591e-06, 'epoch': 1.83}
{'loss': 1.4028, 'learning_rate': 2.504970178926441e-06, 'epoch': 1.83}
{'loss': 0.3801, 'learning_rate': 2.5022591722392913e-06, 'epoch': 1.83}
{'loss': 0.6635, 'learning_rate': 2.499548165552142e-06, 'epoch': 1.83}
{'loss': 0.3824, 'learning_rate': 2.496837158864992e-06, 'epoch': 1.83}

 92%|█████████▏| 10146/11066 [37:12<03:23,  4.52it/s]
 92%|█████████▏| 10147/11066 [37:12<03:20,  4.59it/s]
                                                     

 92%|█████████▏| 10147/11066 [37:12<03:20,  4.59it/s]
 92%|█████████▏| 10148/11066 [37:12<03:18,  4.62it/s]
                                                     

 92%|█████████▏| 10148/11066 [37:12<03:18,  4.62it/s]
 92%|█████████▏| 10149/11066 [37:12<03:17,  4.65it/s]
                                                     

 92%|█████████▏| 10149/11066 [37:12<03:17,  4.65it/s]
 92%|█████████▏| 10150/11066 [37:13<03:15,  4.70it/s]
                                                     

 92%|█████████▏| 10150/11066 [37:13<03:15,  4.70it/s]
 92%|█████████▏| 10151/11066 [37:13<03:18,  4.62it/s]
                                                     

 92%|█████████▏| 10151/11066 [37:13<03:18,  4.62it/s]
 92%|█████████▏| 10152/11066 [37:13<03:17,  4.62it/s]
                                                     

 92%|█████████▏| 10152/11066 [37:13<03:17,  4.62it/s]
 92%|█████████▏| 10153/11066 [37:13<03:18,  4.59it/s]
                                                     

 92%|█████████▏| 10153/11066 [37:13<03:18,  4.59it/s]
 92%|█████████▏| 10154/11066 [37:14<03:20,  4.55it/s]
                                                     

 92%|█████████▏| 10154/11066 [37:14<03:20,  4.55it/s]
 92%|█████████▏| 10155/11066 [37:14<03:21,  4.52it/s]
                                                     

 92%|█████████▏| 10155/11066 [37:14<03:21,  4.52it/s]
 92%|█████████▏| 10156/11066 [37:14<03:21,  4.51it/s]
                                                     

 92%|█████████▏| 10156/11066 [37:14<03:21,  4.51it/s]
 92%|█████████▏| 10157/11066 [37:14<03:20,  4.54it/s]
                                                     

 92%|█████████▏| 10157/11066 [37:14<03:20,  4.54it/s]
 92%|█████████▏| 10158/11066 [37:14<03:18,  4.56it/s]
                                                     

 92%|█████████▏| 10158/11066 [37:14<03:18,  4.56it/s]
 92%|█████████▏| 10159/11066 [37:15<03:18,  4.58it/s]
                                                     

 92%|█████████▏| 10159/11066 [37:15<03:18,  4.58it/s]
 92%|█████████▏| 10160/11066 [37:15<03:17,  4.58it/s]
                                                     

 92%|█████████▏| 10160/11066 [37:15<03:17,  4.58it/s]
 92%|█████████▏| 10161/11066 [37:15<03:15,  4.62it/s]
                                                     

 92%|█████████▏| 10161/11066 [37:15<03:15,  4.62it/s]
 92%|█████████▏| 10162/11066 [37:15<03:17,  4.59it/s]
                                                     

 92%|█████████▏| 10162/11066 [37:15<03:17,  4.59it/s]
 92%|█████████▏| 10163/11066 [37:16<03:18,  4.55it/s]
                                                     

 92%|█████████▏| 10163/11066 [37:16<03:18,  4.55it/s]
 92%|█████████▏| 10164/11066 [37:16<03:16,  4.60it/s]
                                                     

 92%|█████████▏| 10164/11066 [37:16<03:16,  4.60it/s]
 92%|█████████▏| 10165/11066 [37:16<03:17,  4.57it/s]
                                                     

 92%|█████████▏| 10165/11066 [37:16<03:17,  4.57it/s]
 92%|█████████▏| 10166/11066 [37:16<03:17,  4.55it/s]
                                                     

 92%|█████████▏| 10166/11066 [37:16<03:17,  4.55it/s]
 92%|█████████▏| 10167/11066 [37:16<03:18,  4.53it/s]
                                                     

 92%|█████████▏| 10167/11066 [37:16<03:18,  4.53it/s]
 92%|█████████▏| 10168/11066 [37:17<03:18,  4.53it/s]
                                                     

 92%|█████████▏| 10168/11066 [37:17<03:18,  4.53it/s]
 92%|█████████▏| 10169/11066 [37:17<03:18,  4.52it/s]
                                                     

 92%|█████████▏| 10169/11066 [37:17<03:18,  4.52it/s]
 92%|█████████▏| 10170/11066 [37:17<03:16,  4.55it/s]
                                                     

 92%|█████████▏| 10170/11066 [37:17<03:16,  4.55it/s]
 92%|█████████▏| 10171/11066 [37:17<03:18,  4.52it/s]
                                                     

 92%|█████████▏| 10171/11066 [37:17<03:18,  4.52it/s]
 92%|█████████▏| 10172/11066 [37:18<03:18,  4.51it/s]
                                                     

 92%|█████████▏| 10172/11066 [37:18<03:18,  4.51it/s]
 92%|█████████▏| 10173/11066 [37:18<03:15,  4.56it/s]
                                                     

 92%|█████████▏| 10173/11066 [37:18<03:15,  4.56it/s]
 92%|█████████▏| 10174/11066 [37:18<03:16,  4.54it/s]
                                                     

 92%|█████████▏| 10174/11066 [37:18<03:16,  4.54it/s]
 92%|█████████▏| 10175/11066 [37:18<03:13,  4.59it/s]
                                                     

 92%|█████████▏| 10175/11066 [37:18<03:13,  4.59it/s]
 92%|█████████▏| 10176/11066 [37:18<03:14,  4.57it/s]
                                                     

 92%|█████████▏| 10176/11066 [37:18<03:14,  4.57it/s]
 92%|█████████▏| 10177/11066 [37:19<03:12,  4.61it/s]
                                                     

 92%|█████████▏| 10177/11066 [37:19<03:12,  4.61it/s]
 92%|█████████▏| 10178/11066 [37:19<03:10,  4.66it/s]
                                                     

 92%|█████████▏| 10178/11066 [37:19<03:10,  4.66it/s]
 92%|█████████▏| 10179/11066 [37:19<03:13,  4.59it/s]
                                                     

 92%|█████████▏| 10179/11066 [37:19<03:13,  4.59it/s]
 92%|█████████▏| 10180/11066 [37:19<03:12,  4.60it/s]
                                                     

 92%|█████████▏| 10180/11066 [37:19<03:12,  4.60it/s]
 92%|█████████▏| 10181/11066 [37:19<03:11,  4.62it/s]
                                                     

 92%|█████████▏| 10181/11066 [37:19<03:11,  4.62it/s]
 92%|█████████▏| 10182/11066 [37:20<03:11,  4.61it/s]
                                                     

 92%|█████████▏| 10182/11066 [37:20<03:11,  4.61it/s]
 92%|█████████▏| 10183/11066 [37:20<03:10,  4.63it/s]
                                                     

 92%|█████████▏| 10183/11066 [37:20<03:10,  4.63it/s]
 92%|█████████▏| 10184/11066 [37:20<03:11,  4.61it/s]
                                                     

 92%|█████████▏| 10184/11066 [37:20<03:11,  4.61it/s]
 92%|█████████▏| 10185/11066 [37:20<03:09,  4.64it/s]
                                                     

 92%|█████████▏| 10185/11066 [37:20<03:09,  4.64it/s]
 92%|█████████▏| 10186/11066 [37:21<03:08,  4.66it/s]
                                                     

 92%|█████████▏| 10186/11066 [37:21<03:08,  4.66it/s]
 92%|█████████▏| 10187/11066 [37:21<03:09,  4.63it/s]
                                                     

 92%|█████████▏| 10187/11066 [37:21<03:09,  4.63it/s]
 92%|█████████▏| 10188/11066 [37:21<03:10,  4.60it/s]
                                                     

 92%|█████████▏| 10188/11066 [37:21<03:10,  4.60it/s]
 92%|█████████▏| 10189/11066 [37:21<03:11,  4.57it/s]
                                                     

 92%|█████████▏| 10189/11066 [37:21<03:11,  4.57it/s]
 92%|█████████▏| 10190/11066 [37:21<03:12,  4.55it/s]
                                                     

 92%|█████████▏| 10190/11066 [37:21<03:12,  4.55it/s]
 92%|█████████▏| 10191/11066 [37:22<03:12,  4.54it/s]
                                                     

 92%|█████████▏| 10191/11066 [37:22<03:12,  4.54it/s]
 92%|█████████▏| 10192/11066 [37:22<03:10,  4.59it/s]
                                                     

 92%|█████████▏| 10192/11066 [37:22<03:10,  4.59it/s]
 92%|█████████▏| 10193/11066 [37:22<03:09,  4.60it/s]
                                                     

 92%|█████████▏| 10193/11066 [37:22<03:09,  4.60it/s]
 92%|█████████▏| 10194/11066 [37:22<03:09,  4.59it/s]
                                                     

 92%|█████████▏| 10194/11066 [37:22<03:09,  4.59it/s]
 92%|█████████▏| 10195/11066 [37:23<03:08,  4.63it/s]
                                                     

 92%|█████████▏| 10195/11066 [37:23<03:08,  4.63it/s]
 92%|█████████▏| 10196/11066 [37:23<03:09,  4.58it/s]
                                                     

 92%|█████████▏| 10196/11066 [37:23<03:09,  4.58it/s]
 92%|█████████▏| 10197/11066 [37:23<03:10,  4.57it/s]
                                                     

 92%|█████████▏| 10197/11066 [37:23<03:10,  4.57it/s]
 92%|█████████▏| 10198/11066 [37:23<03:09,  4.59it/s]
                                                     

 92%|█████████▏| 10198/11066 [37:23<03:09,  4.59it/s]
 92%|█████████▏| 10199/11066 [37:23<03:08,  4.61it/s]
                                                     

 92%|█████████▏| 10199/11066 [37:23<03:08,  4.61it/s]
 92%|█████████▏| 10200/11066 [37:24<03:08,  4.60it/s]
                                                     

 92%|█████████▏| 10200/11066 [37:24<03:08,  4.60it/s]
 92%|█████████▏| 10201/11066 [37:24<03:06,  4.63it/s]
                                                     

 92%|█████████▏| 10201/11066 [37:24<03:06,  4.63it/s]
 92%|█████████▏| 10202/11066 [37:24<03:05,  4.65it/s]
                                                     

 92%|█████████▏| 10202/11066 [37:24<03:05,  4.65it/s]
 92%|█████████▏| 10203/11066 [37:24<03:05,  4.65it/s]
                                                     

 92%|█████████▏| 10203/11066 [37:24<03:05,  4.65it/s]
 92%|█████████▏| 10204/11066 [37:24<03:06,  4.63it/s]
                                                     

 92%|█████████▏| 10204/11066 [37:24<03:06,  4.63it/s]
 92%|█████████▏| 10205/11066 [37:25<03:05,  4.64it/s]
                                                     

 92%|█████████▏| 10205/11066 [37:25<03:05,  4.64it/s]
 92%|█████████▏| 10206/11066 [37:25<03:08,  4.57it/s]
                                                     

 92%|█████████▏| 10206/11066 [37:25<03:08,  4.57it/s]
 92%|█████████▏| 10207/11066 [37:25<03:07,  4.58it/s]
                                                     

 92%|█████████▏| 10207/11066 [37:25<03:07,  4.58it/s]
 92%|█████████▏| 10208/11066 [37:25<03:12,  4.45it/s]
                                                     

 92%|█████████▏| 10208/11066 [37:25<03:12,  4.45it/s]
 92%|█████████▏| 10209/11066 [37:26<03:12,  4.45it/s]
                                                     

 92%|█████████▏| 10209/11066 [37:26<03:12,  4.45it/s]
 92%|█████████▏| 10210/11066 [37:26<03:12,  4.44it/s]
                                                     

 92%|█████████▏| 10210/11066 [37:26<03:12,  4.44it/s]
 92%|█████████▏| 10211/11066 [37:26<03:12,  4.44it/s]
                                                     

 92%|█████████▏| 10211/11066 [37:26<03:12,  4.44it/s]
 92%|█████████▏| 10212/11066 [37:26<03:11,  4.46it/s]
                                                     

 92%|█████████▏| 10212/11066 [37:26<03:11,  4.46it/s]
 92%|█████████▏| 10213/11066 [37:26<03:09,  4.50it/s]
                                                     

 92%|█████████▏| 10213/11066 [37:26<03:09,  4.50it/s]
 92%|█████████▏| 10214/11066 [37:27<03:10,  4.48it/s]
                                                     

 92%|█████████▏| 10214/11066 [37:27<03:10,  4.48it/s]
 92%|█████████▏| 10215/11066 [37:27<03:10,  4.48it/s]
                                                     

 92%|█████████▏| 10215/11066 [37:27<03:10,  4.48it/s]
 92%|█████████▏| 10216/11066 [37:27<03:08,  4.52it/s]
                                                     

 92%|█████████▏| 10216/11066 [37:27<03:08,  4.52it/s]
 92%|█████████▏| 10217/11066 [37:27<03:06,  4.56it/s]
                                                     

 92%|█████████▏| 10217/11066 [37:27<03:06,  4.56it/s]
 92%|█████████▏| 10218/11066 [37:28<03:05,  4.57it/s]
                                                     

 92%|█████████▏| 10218/11066 [37:28<03:05,  4.57it/s]
 92%|█████████▏| 10219/11066 [37:28<03:03,  4.63it/s]
                                                     

 92%|█████████▏| 10219/11066 [37:28<03:03,  4.63it/s]
 92%|█████████▏| 10220/11066 [37:28<03:04,  4.58it/s]
                                                     

 92%|█████████▏| 10220/11066 [37:28<03:04,  4.58it/s]
 92%|█████████▏| 10221/11066 [37:28<03:04,  4.59it/s]
                                                     

 92%|█████████▏| 10221/11066 [37:28<03:04,  4.59it/s]
 92%|█████████▏| 10222/11066 [37:28<03:05,  4.55it/s]
                                                     

 92%|█████████▏| 10222/11066 [37:28<03:05,  4.55it/s]
 92%|█████████▏| 10223/11066 [37:29<03:04,  4.56it/s]
                                                     

 92%|█████████▏| 10223/11066 [37:29<03:04,  4.56it/s]
 92%|█████████▏| 10224/11066 [37:29<03:05,  4.53it/s]
                                                     

 92%|█████████▏| 10224/11066 [37:29<03:05,  4.53it/s]
 92%|█████████▏| 10225/11066 [37:29<03:05,  4.54it/s]
                                                     

 92%|█████████▏| 10225/11066 [37:29<03:05,  4.54it/s]
 92%|█████████▏| 10226/11066 [37:29<03:03,  4.57it/s]
                                                     

 92%|█████████▏| 10226/11066 [37:29<03:03,  4.57it/s]
 92%|█████████▏| 10227/11066 [37:30<03:02,  4.59it/s]
                                                     

 92%|█████████▏| 10227/11066 [37:30<03:02,  4.59it/s]
 92%|█████████▏| 10228/11066 [37:30<03:03,  4.58it/s]
                                                     

 92%|█████████▏| 10228/11066 [37:30<03:03,  4.58it/s]
 92%|█████████▏| 10229/11066 [37:30<03:02,  4.58it/s]
                                                     

 92%|█████████▏| 10229/11066 [37:30<03:02,  4.58it/s]
 92%|█████████▏| 10230/11066 [37:30<03:01,  4.61it/s]
                                                     

 92%|█████████▏| 10230/11066 [37:30<03:01,  4.61it/s]
 92%|█████████▏| 10231/11066 [37:30<03:01,  4.60it/s]
                                                     

 92%|█████████▏| 10231/11066 [37:30<03:01,  4.60it/s]
 92%|█████████▏| 10232/11066 [37:31<03:01,  4.61it/s]
                                                     

 92%|█████████▏| 10232/11066 [37:31<03:01,  4.61it/s]
 92%|█████████▏| 10233/11066 [37:31<02:59,  4.64it/s]
                                                     

 92%|█████████▏| 10233/11066 [37:31<02:59,  4.64it/s]
 92%|█████████▏| 10234/11066 [37:31<03:00,  4.60it/s]
                                                     

 92%|█████████▏| 10234/11066 [37:31<03:00,  4.60it/s]
 92%|█████████▏| 10235/11066 [37:31<03:01,  4.58it/s]
                                                     

 92%|█████████▏| 10235/11066 [37:31<03:01,  4.58it/s]
 92%|█████████▏| 10236/11066 [37:32<02:59,  4.62it/s]
                                                     

 92%|█████████▏| 10236/11066 [37:32<02:59,  4.62it/s]
 93%|█████████▎| 10237/11066 [37:32<02:59,  4.62it/s]
                                                     

 93%|█████████▎| 10237/11066 [37:32<02:59,  4.62it/s]
 93%|█████████▎| 10238/11066 [37:32<02:57,  4.66it/s]
                                                     

 93%|█████████▎| 10238/11066 [37:32<02:57,  4.66it/s]
 93%|█████████▎| 10239/11066 [37:32<02:58,  4.63it/s]
                                                     

 93%|█████████▎| 10239/11066 [37:32<02:58,  4.63it/s]
 93%|█████████▎| 10240/11066 [37:32<02:57,  4.65it/s]
                                                     

 93%|█████████▎| 10240/11066 [37:32<02:57,  4.65it/s]
 93%|█████████▎| 10241/11066 [37:33<02:57,  4.66it/s]
                                                     

 93%|█████████▎| 10241/11066 [37:33<02:57,  4.66it/s]
 93%|█████████▎| 10242/11066 [37:33<02:58,  4.63it/s]
                                                     

 93%|█████████▎| 10242/11066 [37:33<02:58,  4.63it/s]
 93%|█████████▎| 10243/11066 [37:33<02:56,  4.65it/s]
                                                     

 93%|█████████▎| 10243/11066 [37:33<02:56,  4.65it/s]
 93%|█████████▎| 10244/11066 [37:33<02:58,  4.60it/s]
                                                     

 93%|█████████▎| 10244/11066 [37:33<02:58,  4.60it/s]
 93%|█████████▎| 10245/11066 [37:33<02:58,  4.59it/s]
                                                     

 93%|█████████▎| 10245/11066 [37:33<02:58,  4.59it/s]
 93%|█████████▎| 10246/11066 [37:34<02:58,  4.60it/s]
                                                     

 93%|█████████▎| 10246/11066 [37:34<02:58,  4.60it/s]
 93%|█████████▎| 10247/11066 [37:34<03:00,  4.55it/s]
                                                     

 93%|█████████▎| 10247/11066 [37:34<03:00,  4.55it/s]
 93%|█████████▎| 10248/11066 [37:34<03:03,  4.46it/s]
                                                     

 93%|█████████▎| 10248/11066 [37:34<03:03,  4.46it/s]
 93%|█████████▎| 10249/11066 [37:34<03:03,  4.46it/s]
                                                     

 93%|█████████▎| 10249/11066 [37:34<03:03,  4.46it/s]
 93%|█████████▎| 10250/11066 [37:35<03:01,  4.50it/s]
                                                     

 93%|█████████▎| 10250/11066 [37:35<03:01,  4.50it/s]
 93%|█████████▎| 10251/11066 [37:35<03:01,  4.49it/s]
                                                     

 93%|█████████▎| 10251/11066 [37:35<03:01,  4.49it/s]
 93%|█████████▎| 10252/11066 [37:35<03:01,  4.49it/s]
                                                     

 93%|█████████▎| 10252/11066 [37:35<03:01,  4.49it/s]
 93%|█████████▎| 10253/11066 [37:35<03:00,  4.49it/s]
                                                     

 93%|█████████▎| 10253/11066 [37:35<03:00,  4.49it/s]
 93%|█████████▎| 10254/11066 [37:35<02:59,  4.53it/s]
                                                     

 93%|█████████▎| 10254/11066 [37:35<02:59,  4.53it/s]
 93%|█████████▎| 10255/11066 [37:36<02:57,  4.57it/s]
                                                     

 93%|█████████▎| 10255/11066 [37:36<02:57,  4.57it/s]
 93%|█████████▎| 10256/11066 [37:36<02:57,  4.57it/s]
                                                     

 93%|█████████▎| 10256/11066 [37:36<02:57,  4.57it/s]
 93%|█████████▎| 10257/11066 [37:36<02:56,  4.58it/s]
                                                     

 93%|█████████▎| 10257/11066 [37:36<02:56,  4.58it/s]
 93%|█████████▎| 10258/11066 [37:36<02:57,  4.55it/s]
                                                     

 93%|█████████▎| 10258/11066 [37:36<02:57,  4.55it/s]
 93%|█████████▎| 10259/11066 [37:37<02:58,  4.53it/s]
                                                     
{'loss': 0.5158, 'learning_rate': 2.494126152177842e-06, 'epoch': 1.83}
{'loss': 0.2677, 'learning_rate': 2.4914151454906923e-06, 'epoch': 1.83}
{'loss': 1.0068, 'learning_rate': 2.4887041388035424e-06, 'epoch': 1.83}
{'loss': 0.583, 'learning_rate': 2.4859931321163926e-06, 'epoch': 1.83}
{'loss': 0.3757, 'learning_rate': 2.4832821254292427e-06, 'epoch': 1.83}
{'loss': 0.3284, 'learning_rate': 2.480571118742093e-06, 'epoch': 1.83}
{'loss': 0.4737, 'learning_rate': 2.477860112054943e-06, 'epoch': 1.83}
{'loss': 0.536, 'learning_rate': 2.475149105367793e-06, 'epoch': 1.83}
{'loss': 0.8751, 'learning_rate': 2.4724380986806432e-06, 'epoch': 1.84}
{'loss': 0.3968, 'learning_rate': 2.469727091993494e-06, 'epoch': 1.84}
{'loss': 0.4115, 'learning_rate': 2.467016085306344e-06, 'epoch': 1.84}
{'loss': 0.4183, 'learning_rate': 2.464305078619194e-06, 'epoch': 1.84}
{'loss': 0.6838, 'learning_rate': 2.461594071932044e-06, 'epoch': 1.84}
{'loss': 0.6603, 'learning_rate': 2.4588830652448943e-06, 'epoch': 1.84}
{'loss': 1.2613, 'learning_rate': 2.4561720585577445e-06, 'epoch': 1.84}
{'loss': 0.7936, 'learning_rate': 2.4534610518705946e-06, 'epoch': 1.84}
{'loss': 0.7797, 'learning_rate': 2.4507500451834447e-06, 'epoch': 1.84}
{'loss': 0.8824, 'learning_rate': 2.448039038496295e-06, 'epoch': 1.84}
{'loss': 0.3982, 'learning_rate': 2.445328031809145e-06, 'epoch': 1.84}
{'loss': 0.4417, 'learning_rate': 2.4426170251219956e-06, 'epoch': 1.84}
{'loss': 1.0556, 'learning_rate': 2.4399060184348457e-06, 'epoch': 1.84}
{'loss': 0.6784, 'learning_rate': 2.437195011747696e-06, 'epoch': 1.84}
{'loss': 0.7968, 'learning_rate': 2.434484005060546e-06, 'epoch': 1.84}
{'loss': 0.6599, 'learning_rate': 2.431772998373396e-06, 'epoch': 1.84}
{'loss': 0.6369, 'learning_rate': 2.4290619916862462e-06, 'epoch': 1.84}
{'loss': 0.7848, 'learning_rate': 2.4263509849990964e-06, 'epoch': 1.84}
{'loss': 0.3059, 'learning_rate': 2.4236399783119465e-06, 'epoch': 1.84}
{'loss': 0.8157, 'learning_rate': 2.4209289716247966e-06, 'epoch': 1.84}
{'loss': 0.4453, 'learning_rate': 2.4182179649376468e-06, 'epoch': 1.84}
{'loss': 0.6609, 'learning_rate': 2.415506958250497e-06, 'epoch': 1.84}
{'loss': 1.077, 'learning_rate': 2.4127959515633475e-06, 'epoch': 1.84}
{'loss': 1.32, 'learning_rate': 2.4100849448761976e-06, 'epoch': 1.84}
{'loss': 0.5393, 'learning_rate': 2.4073739381890477e-06, 'epoch': 1.84}
{'loss': 0.3613, 'learning_rate': 2.404662931501898e-06, 'epoch': 1.84}
{'loss': 0.5274, 'learning_rate': 2.401951924814748e-06, 'epoch': 1.84}
{'loss': 0.4968, 'learning_rate': 2.399240918127598e-06, 'epoch': 1.84}
{'loss': 0.8655, 'learning_rate': 2.3965299114404483e-06, 'epoch': 1.84}
{'loss': 0.5843, 'learning_rate': 2.3938189047532984e-06, 'epoch': 1.84}
{'loss': 1.7945, 'learning_rate': 2.3911078980661485e-06, 'epoch': 1.84}
{'loss': 0.5788, 'learning_rate': 2.3883968913789987e-06, 'epoch': 1.84}
{'loss': 1.0592, 'learning_rate': 2.3856858846918492e-06, 'epoch': 1.84}
{'loss': 0.8104, 'learning_rate': 2.3829748780046994e-06, 'epoch': 1.84}
{'loss': 0.4367, 'learning_rate': 2.3802638713175495e-06, 'epoch': 1.84}
{'loss': 0.5262, 'learning_rate': 2.3775528646303996e-06, 'epoch': 1.84}
{'loss': 0.6155, 'learning_rate': 2.3748418579432498e-06, 'epoch': 1.84}
{'loss': 0.4759, 'learning_rate': 2.3721308512561e-06, 'epoch': 1.84}
{'loss': 0.8325, 'learning_rate': 2.36941984456895e-06, 'epoch': 1.84}
{'loss': 0.8629, 'learning_rate': 2.3667088378818e-06, 'epoch': 1.84}
{'loss': 0.2424, 'learning_rate': 2.3639978311946503e-06, 'epoch': 1.84}
{'loss': 0.3772, 'learning_rate': 2.3612868245075004e-06, 'epoch': 1.84}
{'loss': 1.3057, 'learning_rate': 2.358575817820351e-06, 'epoch': 1.84}
{'loss': 0.6996, 'learning_rate': 2.355864811133201e-06, 'epoch': 1.84}
{'loss': 0.4544, 'learning_rate': 2.3531538044460513e-06, 'epoch': 1.84}
{'loss': 0.7745, 'learning_rate': 2.3504427977589014e-06, 'epoch': 1.84}
{'loss': 0.9951, 'learning_rate': 2.3477317910717515e-06, 'epoch': 1.84}
{'loss': 0.4146, 'learning_rate': 2.3450207843846017e-06, 'epoch': 1.84}
{'loss': 1.0268, 'learning_rate': 2.342309777697452e-06, 'epoch': 1.84}
{'loss': 0.3592, 'learning_rate': 2.339598771010302e-06, 'epoch': 1.84}
{'loss': 0.8202, 'learning_rate': 2.336887764323152e-06, 'epoch': 1.84}
{'loss': 0.5084, 'learning_rate': 2.334176757636002e-06, 'epoch': 1.84}
{'loss': 0.9406, 'learning_rate': 2.3314657509488523e-06, 'epoch': 1.84}
{'loss': 0.4275, 'learning_rate': 2.328754744261703e-06, 'epoch': 1.84}
{'loss': 1.1973, 'learning_rate': 2.326043737574553e-06, 'epoch': 1.84}
{'loss': 0.6664, 'learning_rate': 2.323332730887403e-06, 'epoch': 1.85}
{'loss': 0.3191, 'learning_rate': 2.3206217242002533e-06, 'epoch': 1.85}
{'loss': 0.6007, 'learning_rate': 2.3179107175131034e-06, 'epoch': 1.85}
{'loss': 0.5316, 'learning_rate': 2.3151997108259536e-06, 'epoch': 1.85}
{'loss': 0.5509, 'learning_rate': 2.3124887041388037e-06, 'epoch': 1.85}
{'loss': 0.7059, 'learning_rate': 2.309777697451654e-06, 'epoch': 1.85}
{'loss': 0.8001, 'learning_rate': 2.307066690764504e-06, 'epoch': 1.85}
{'loss': 0.3329, 'learning_rate': 2.304355684077354e-06, 'epoch': 1.85}
{'loss': 0.784, 'learning_rate': 2.3016446773902047e-06, 'epoch': 1.85}
{'loss': 0.6883, 'learning_rate': 2.298933670703055e-06, 'epoch': 1.85}
{'loss': 0.5989, 'learning_rate': 2.296222664015905e-06, 'epoch': 1.85}
{'loss': 0.5002, 'learning_rate': 2.293511657328755e-06, 'epoch': 1.85}
{'loss': 1.1605, 'learning_rate': 2.290800650641605e-06, 'epoch': 1.85}
{'loss': 0.5619, 'learning_rate': 2.2880896439544553e-06, 'epoch': 1.85}
{'loss': 0.4224, 'learning_rate': 2.2853786372673055e-06, 'epoch': 1.85}
{'loss': 0.731, 'learning_rate': 2.2826676305801556e-06, 'epoch': 1.85}
{'loss': 0.5458, 'learning_rate': 2.2799566238930057e-06, 'epoch': 1.85}
{'loss': 0.7749, 'learning_rate': 2.277245617205856e-06, 'epoch': 1.85}
{'loss': 0.9102, 'learning_rate': 2.274534610518706e-06, 'epoch': 1.85}
{'loss': 0.7312, 'learning_rate': 2.2718236038315566e-06, 'epoch': 1.85}
{'loss': 1.3478, 'learning_rate': 2.2691125971444067e-06, 'epoch': 1.85}
{'loss': 0.5408, 'learning_rate': 2.2664015904572564e-06, 'epoch': 1.85}
{'loss': 0.8135, 'learning_rate': 2.2636905837701065e-06, 'epoch': 1.85}
{'loss': 0.4361, 'learning_rate': 2.2609795770829567e-06, 'epoch': 1.85}
{'loss': 0.49, 'learning_rate': 2.258268570395807e-06, 'epoch': 1.85}
{'loss': 1.2824, 'learning_rate': 2.255557563708657e-06, 'epoch': 1.85}
{'loss': 0.4797, 'learning_rate': 2.252846557021507e-06, 'epoch': 1.85}
{'loss': 0.9736, 'learning_rate': 2.250135550334357e-06, 'epoch': 1.85}
{'loss': 0.4713, 'learning_rate': 2.2474245436472073e-06, 'epoch': 1.85}
{'loss': 1.0805, 'learning_rate': 2.244713536960058e-06, 'epoch': 1.85}
{'loss': 1.7266, 'learning_rate': 2.242002530272908e-06, 'epoch': 1.85}
{'loss': 0.2307, 'learning_rate': 2.239291523585758e-06, 'epoch': 1.85}
{'loss': 0.3809, 'learning_rate': 2.2365805168986083e-06, 'epoch': 1.85}
{'loss': 0.4033, 'learning_rate': 2.2338695102114584e-06, 'epoch': 1.85}
{'loss': 0.4056, 'learning_rate': 2.2311585035243086e-06, 'epoch': 1.85}
{'loss': 1.0608, 'learning_rate': 2.2284474968371587e-06, 'epoch': 1.85}
{'loss': 0.494, 'learning_rate': 2.225736490150009e-06, 'epoch': 1.85}
{'loss': 1.5838, 'learning_rate': 2.223025483462859e-06, 'epoch': 1.85}
{'loss': 0.7595, 'learning_rate': 2.220314476775709e-06, 'epoch': 1.85}
{'loss': 0.4973, 'learning_rate': 2.2176034700885597e-06, 'epoch': 1.85}
{'loss': 0.9759, 'learning_rate': 2.21489246340141e-06, 'epoch': 1.85}
{'loss': 0.6064, 'learning_rate': 2.21218145671426e-06, 'epoch': 1.85}
{'loss': 0.528, 'learning_rate': 2.20947045002711e-06, 'epoch': 1.85}
{'loss': 0.836, 'learning_rate': 2.20675944333996e-06, 'epoch': 1.85}
{'loss': 0.8167, 'learning_rate': 2.2040484366528103e-06, 'epoch': 1.85}
{'loss': 0.5798, 'learning_rate': 2.2013374299656605e-06, 'epoch': 1.85}
{'loss': 0.8744, 'learning_rate': 2.1986264232785106e-06, 'epoch': 1.85}
{'loss': 0.778, 'learning_rate': 2.1959154165913607e-06, 'epoch': 1.85}
{'loss': 0.7563, 'learning_rate': 2.193204409904211e-06, 'epoch': 1.85}
{'loss': 0.9175, 'learning_rate': 2.190493403217061e-06, 'epoch': 1.85}

 93%|█████████▎| 10259/11066 [37:37<02:58,  4.53it/s]
 93%|█████████▎| 10260/11066 [37:37<02:58,  4.51it/s]
                                                     

 93%|█████████▎| 10260/11066 [37:37<02:58,  4.51it/s]
 93%|█████████▎| 10261/11066 [37:37<03:00,  4.47it/s]
                                                     

 93%|█████████▎| 10261/11066 [37:37<03:00,  4.47it/s]
 93%|█████████▎| 10262/11066 [37:37<02:59,  4.47it/s]
                                                     

 93%|█████████▎| 10262/11066 [37:37<02:59,  4.47it/s]
 93%|█████████▎| 10263/11066 [37:37<02:58,  4.51it/s]
                                                     

 93%|█████████▎| 10263/11066 [37:37<02:58,  4.51it/s]
 93%|█████████▎| 10264/11066 [37:38<02:56,  4.55it/s]
                                                     

 93%|█████████▎| 10264/11066 [37:38<02:56,  4.55it/s]
 93%|█████████▎| 10265/11066 [37:38<02:55,  4.57it/s]
                                                     

 93%|█████████▎| 10265/11066 [37:38<02:55,  4.57it/s]
 93%|█████████▎| 10266/11066 [37:38<02:53,  4.60it/s]
                                                     

 93%|█████████▎| 10266/11066 [37:38<02:53,  4.60it/s]
 93%|█████████▎| 10267/11066 [37:38<02:52,  4.63it/s]
                                                     

 93%|█████████▎| 10267/11066 [37:38<02:52,  4.63it/s]
 93%|█████████▎| 10268/11066 [37:39<02:52,  4.63it/s]
                                                     

 93%|█████████▎| 10268/11066 [37:39<02:52,  4.63it/s]
 93%|█████████▎| 10269/11066 [37:39<02:53,  4.58it/s]
                                                     

 93%|█████████▎| 10269/11066 [37:39<02:53,  4.58it/s]
 93%|█████████▎| 10270/11066 [37:39<02:54,  4.56it/s]
                                                     

 93%|█████████▎| 10270/11066 [37:39<02:54,  4.56it/s]
 93%|█████████▎| 10271/11066 [37:39<02:53,  4.57it/s]
                                                     

 93%|█████████▎| 10271/11066 [37:39<02:53,  4.57it/s]
 93%|█████████▎| 10272/11066 [37:39<02:52,  4.61it/s]
                                                     

 93%|█████████▎| 10272/11066 [37:39<02:52,  4.61it/s]
 93%|█████████▎| 10273/11066 [37:40<02:51,  4.63it/s]
                                                     

 93%|█████████▎| 10273/11066 [37:40<02:51,  4.63it/s]
 93%|█████████▎| 10274/11066 [37:40<02:53,  4.57it/s]
                                                     

 93%|█████████▎| 10274/11066 [37:40<02:53,  4.57it/s]
 93%|█████████▎| 10275/11066 [37:40<02:53,  4.57it/s]
                                                     

 93%|█████████▎| 10275/11066 [37:40<02:53,  4.57it/s]
 93%|█████████▎| 10276/11066 [37:40<02:52,  4.58it/s]
                                                     

 93%|█████████▎| 10276/11066 [37:40<02:52,  4.58it/s]
 93%|█████████▎| 10277/11066 [37:40<02:51,  4.59it/s]
                                                     

 93%|█████████▎| 10277/11066 [37:40<02:51,  4.59it/s]
 93%|█████████▎| 10278/11066 [37:41<02:53,  4.55it/s]
                                                     

 93%|█████████▎| 10278/11066 [37:41<02:53,  4.55it/s]
 93%|█████████▎| 10279/11066 [37:41<02:54,  4.52it/s]
                                                     

 93%|█████████▎| 10279/11066 [37:41<02:54,  4.52it/s]
 93%|█████████▎| 10280/11066 [37:41<02:54,  4.51it/s]
                                                     

 93%|█████████▎| 10280/11066 [37:41<02:54,  4.51it/s]
 93%|█████████▎| 10281/11066 [37:41<02:53,  4.54it/s]
                                                     

 93%|█████████▎| 10281/11066 [37:41<02:53,  4.54it/s]
 93%|█████████▎| 10282/11066 [37:42<02:53,  4.51it/s]
                                                     

 93%|█████████▎| 10282/11066 [37:42<02:53,  4.51it/s]
 93%|█████████▎| 10283/11066 [37:42<02:52,  4.53it/s]
                                                     

 93%|█████████▎| 10283/11066 [37:42<02:52,  4.53it/s]
 93%|█████████▎| 10284/11066 [37:42<02:50,  4.58it/s]
                                                     

 93%|█████████▎| 10284/11066 [37:42<02:50,  4.58it/s]
 93%|█████████▎| 10285/11066 [37:42<02:49,  4.62it/s]
                                                     

 93%|█████████▎| 10285/11066 [37:42<02:49,  4.62it/s]
 93%|█████████▎| 10286/11066 [37:42<02:50,  4.58it/s]
                                                     

 93%|█████████▎| 10286/11066 [37:42<02:50,  4.58it/s]
 93%|█████████▎| 10287/11066 [37:43<02:51,  4.53it/s]
                                                     

 93%|█████████▎| 10287/11066 [37:43<02:51,  4.53it/s]
 93%|█████████▎| 10288/11066 [37:43<02:50,  4.57it/s]
                                                     

 93%|█████████▎| 10288/11066 [37:43<02:50,  4.57it/s]
 93%|█████████▎| 10289/11066 [37:43<02:49,  4.59it/s]
                                                     

 93%|█████████▎| 10289/11066 [37:43<02:49,  4.59it/s]
 93%|█████████▎| 10290/11066 [37:43<02:49,  4.57it/s]
                                                     

 93%|█████████▎| 10290/11066 [37:43<02:49,  4.57it/s]
 93%|█████████▎| 10291/11066 [37:44<02:48,  4.61it/s]
                                                     

 93%|█████████▎| 10291/11066 [37:44<02:48,  4.61it/s]
 93%|█████████▎| 10292/11066 [37:44<02:47,  4.63it/s]
                                                     

 93%|█████████▎| 10292/11066 [37:44<02:47,  4.63it/s]
 93%|█████████▎| 10293/11066 [37:44<02:46,  4.65it/s]
                                                     

 93%|█████████▎| 10293/11066 [37:44<02:46,  4.65it/s]
 93%|█████████▎| 10294/11066 [37:44<02:46,  4.63it/s]
                                                     

 93%|█████████▎| 10294/11066 [37:44<02:46,  4.63it/s]
 93%|█████████▎| 10295/11066 [37:44<02:48,  4.59it/s]
                                                     

 93%|█████████▎| 10295/11066 [37:44<02:48,  4.59it/s]
 93%|█████████▎| 10296/11066 [37:45<02:48,  4.57it/s]
                                                     

 93%|█████████▎| 10296/11066 [37:45<02:48,  4.57it/s]
 93%|█████████▎| 10297/11066 [37:45<02:48,  4.55it/s]
                                                     

 93%|█████████▎| 10297/11066 [37:45<02:48,  4.55it/s]
 93%|█████████▎| 10298/11066 [37:45<02:47,  4.57it/s]
                                                     

 93%|█████████▎| 10298/11066 [37:45<02:47,  4.57it/s]
 93%|█████████▎| 10299/11066 [37:45<02:49,  4.54it/s]
                                                     

 93%|█████████▎| 10299/11066 [37:45<02:49,  4.54it/s]
 93%|█████████▎| 10300/11066 [37:46<02:49,  4.51it/s]
                                                     

 93%|█████████▎| 10300/11066 [37:46<02:49,  4.51it/s]
 93%|█████████▎| 10301/11066 [37:46<02:49,  4.51it/s]
                                                     

 93%|█████████▎| 10301/11066 [37:46<02:49,  4.51it/s]
 93%|█████████▎| 10302/11066 [37:46<02:49,  4.50it/s]
                                                     

 93%|█████████▎| 10302/11066 [37:46<02:49,  4.50it/s]
 93%|█████████▎| 10303/11066 [37:46<02:49,  4.49it/s]
                                                     

 93%|█████████▎| 10303/11066 [37:46<02:49,  4.49it/s]
 93%|█████████▎| 10304/11066 [37:46<02:49,  4.50it/s]
                                                     

 93%|█████████▎| 10304/11066 [37:46<02:49,  4.50it/s]
 93%|█████████▎| 10305/11066 [37:47<02:49,  4.50it/s]
                                                     

 93%|█████████▎| 10305/11066 [37:47<02:49,  4.50it/s]
 93%|█████████▎| 10306/11066 [37:47<02:46,  4.55it/s]
                                                     

 93%|█████████▎| 10306/11066 [37:47<02:46,  4.55it/s]
 93%|█████████▎| 10307/11066 [37:47<02:46,  4.55it/s]
                                                     

 93%|█████████▎| 10307/11066 [37:47<02:46,  4.55it/s]
 93%|█████████▎| 10308/11066 [37:47<02:46,  4.55it/s]
                                                     

 93%|█████████▎| 10308/11066 [37:47<02:46,  4.55it/s]
 93%|█████████▎| 10309/11066 [37:48<02:45,  4.56it/s]
                                                     

 93%|█████████▎| 10309/11066 [37:48<02:45,  4.56it/s]
 93%|█████████▎| 10310/11066 [37:48<02:44,  4.60it/s]
                                                     

 93%|█████████▎| 10310/11066 [37:48<02:44,  4.60it/s]
 93%|█████████▎| 10311/11066 [37:48<02:43,  4.62it/s]
                                                     

 93%|█████████▎| 10311/11066 [37:48<02:43,  4.62it/s]
 93%|█████████▎| 10312/11066 [37:48<02:42,  4.64it/s]
                                                     

 93%|█████████▎| 10312/11066 [37:48<02:42,  4.64it/s]
 93%|█████████▎| 10313/11066 [37:48<02:44,  4.58it/s]
                                                     

 93%|█████████▎| 10313/11066 [37:48<02:44,  4.58it/s]
 93%|█████████▎| 10314/11066 [37:49<02:43,  4.59it/s]
                                                     

 93%|█████████▎| 10314/11066 [37:49<02:43,  4.59it/s]
 93%|█████████▎| 10315/11066 [37:49<02:43,  4.58it/s]
                                                     

 93%|█████████▎| 10315/11066 [37:49<02:43,  4.58it/s]
 93%|█████████▎| 10316/11066 [37:49<02:44,  4.57it/s]
                                                     

 93%|█████████▎| 10316/11066 [37:49<02:44,  4.57it/s]
 93%|█████████▎| 10317/11066 [37:49<02:43,  4.59it/s]
                                                     

 93%|█████████▎| 10317/11066 [37:49<02:43,  4.59it/s]
 93%|█████████▎| 10318/11066 [37:49<02:41,  4.63it/s]
                                                     

 93%|█████████▎| 10318/11066 [37:49<02:41,  4.63it/s]
 93%|█████████▎| 10319/11066 [37:50<02:42,  4.59it/s]
                                                     

 93%|█████████▎| 10319/11066 [37:50<02:42,  4.59it/s]
 93%|█████████▎| 10320/11066 [37:50<02:42,  4.60it/s]
                                                     

 93%|█████████▎| 10320/11066 [37:50<02:42,  4.60it/s]
 93%|█████████▎| 10321/11066 [37:50<02:42,  4.59it/s]
                                                     

 93%|█████████▎| 10321/11066 [37:50<02:42,  4.59it/s]
 93%|█████████▎| 10322/11066 [37:50<02:41,  4.60it/s]
                                                     

 93%|█████████▎| 10322/11066 [37:50<02:41,  4.60it/s]
 93%|█████████▎| 10323/11066 [37:51<02:41,  4.60it/s]
                                                     

 93%|█████████▎| 10323/11066 [37:51<02:41,  4.60it/s]
 93%|█████████▎| 10324/11066 [37:51<02:42,  4.57it/s]
                                                     

 93%|█████████▎| 10324/11066 [37:51<02:42,  4.57it/s]
 93%|█████████▎| 10325/11066 [37:51<02:42,  4.55it/s]
                                                     

 93%|█████████▎| 10325/11066 [37:51<02:42,  4.55it/s]
 93%|█████████▎| 10326/11066 [37:51<02:42,  4.54it/s]
                                                     

 93%|█████████▎| 10326/11066 [37:51<02:42,  4.54it/s]
 93%|█████████▎| 10327/11066 [37:51<02:43,  4.52it/s]
                                                     

 93%|█████████▎| 10327/11066 [37:51<02:43,  4.52it/s]
 93%|█████████▎| 10328/11066 [37:52<02:43,  4.50it/s]
                                                     

 93%|█████████▎| 10328/11066 [37:52<02:43,  4.50it/s]
 93%|█████████▎| 10329/11066 [37:52<02:44,  4.47it/s]
                                                     

 93%|█████████▎| 10329/11066 [37:52<02:44,  4.47it/s]
 93%|█████████▎| 10330/11066 [37:52<02:44,  4.47it/s]
                                                     

 93%|█████████▎| 10330/11066 [37:52<02:44,  4.47it/s]
 93%|█████████▎| 10331/11066 [37:52<02:44,  4.48it/s]
                                                     

 93%|█████████▎| 10331/11066 [37:52<02:44,  4.48it/s]
 93%|█████████▎| 10332/11066 [37:53<02:43,  4.49it/s]
                                                     

 93%|█████████▎| 10332/11066 [37:53<02:43,  4.49it/s]
 93%|█████████▎| 10333/11066 [37:53<02:43,  4.49it/s]
                                                     

 93%|█████████▎| 10333/11066 [37:53<02:43,  4.49it/s]
 93%|█████████▎| 10334/11066 [37:53<02:43,  4.49it/s]
                                                     

 93%|█████████▎| 10334/11066 [37:53<02:43,  4.49it/s]
 93%|█████████▎| 10335/11066 [37:53<02:42,  4.49it/s]
                                                     

 93%|█████████▎| 10335/11066 [37:53<02:42,  4.49it/s]
 93%|█████████▎| 10336/11066 [37:53<02:43,  4.48it/s]
                                                     

 93%|█████████▎| 10336/11066 [37:53<02:43,  4.48it/s]
 93%|█████████▎| 10337/11066 [37:54<02:43,  4.47it/s]
                                                     

 93%|█████████▎| 10337/11066 [37:54<02:43,  4.47it/s]
 93%|█████████▎| 10338/11066 [37:54<02:41,  4.50it/s]
                                                     

 93%|█████████▎| 10338/11066 [37:54<02:41,  4.50it/s]
 93%|█████████▎| 10339/11066 [37:54<02:39,  4.55it/s]
                                                     

 93%|█████████▎| 10339/11066 [37:54<02:39,  4.55it/s]
 93%|█████████▎| 10340/11066 [37:54<02:40,  4.53it/s]
                                                     

 93%|█████████▎| 10340/11066 [37:54<02:40,  4.53it/s]
 93%|█████████▎| 10341/11066 [37:55<02:38,  4.57it/s]
                                                     

 93%|█████████▎| 10341/11066 [37:55<02:38,  4.57it/s]
 93%|█████████▎| 10342/11066 [37:55<02:39,  4.55it/s]
                                                     

 93%|█████████▎| 10342/11066 [37:55<02:39,  4.55it/s]
 93%|█████████▎| 10343/11066 [37:55<02:39,  4.52it/s]
                                                     

 93%|█████████▎| 10343/11066 [37:55<02:39,  4.52it/s]
 93%|█████████▎| 10344/11066 [37:55<02:38,  4.55it/s]
                                                     

 93%|█████████▎| 10344/11066 [37:55<02:38,  4.55it/s]
 93%|█████████▎| 10345/11066 [37:55<02:37,  4.57it/s]
                                                     

 93%|█████████▎| 10345/11066 [37:55<02:37,  4.57it/s]
 93%|█████████▎| 10346/11066 [37:56<02:37,  4.56it/s]
                                                     

 93%|█████████▎| 10346/11066 [37:56<02:37,  4.56it/s]
 94%|█████████▎| 10347/11066 [37:56<02:37,  4.57it/s]
                                                     

 94%|█████████▎| 10347/11066 [37:56<02:37,  4.57it/s]
 94%|█████████▎| 10348/11066 [37:56<02:35,  4.63it/s]
                                                     

 94%|█████████▎| 10348/11066 [37:56<02:35,  4.63it/s]
 94%|█████████▎| 10349/11066 [37:56<02:34,  4.63it/s]
                                                     

 94%|█████████▎| 10349/11066 [37:56<02:34,  4.63it/s]
 94%|█████████▎| 10350/11066 [37:57<02:33,  4.66it/s]
                                                     

 94%|█████████▎| 10350/11066 [37:57<02:33,  4.66it/s]
 94%|█████████▎| 10351/11066 [37:57<02:33,  4.66it/s]
                                                     

 94%|█████████▎| 10351/11066 [37:57<02:33,  4.66it/s]
 94%|█████████▎| 10352/11066 [37:57<02:35,  4.60it/s]
                                                     

 94%|█████████▎| 10352/11066 [37:57<02:35,  4.60it/s]
 94%|█████████▎| 10353/11066 [37:57<02:35,  4.59it/s]
                                                     

 94%|█████████▎| 10353/11066 [37:57<02:35,  4.59it/s]
 94%|█████████▎| 10354/11066 [37:57<02:36,  4.55it/s]
                                                     

 94%|█████████▎| 10354/11066 [37:57<02:36,  4.55it/s]
 94%|█████████▎| 10355/11066 [37:58<02:35,  4.56it/s]
                                                     

 94%|█████████▎| 10355/11066 [37:58<02:35,  4.56it/s]
 94%|█████████▎| 10356/11066 [37:58<02:34,  4.60it/s]
                                                     

 94%|█████████▎| 10356/11066 [37:58<02:34,  4.60it/s]
 94%|█████████▎| 10357/11066 [37:58<02:35,  4.55it/s]
                                                     

 94%|█████████▎| 10357/11066 [37:58<02:35,  4.55it/s]
 94%|█████████▎| 10358/11066 [37:58<02:36,  4.53it/s]
                                                     

 94%|█████████▎| 10358/11066 [37:58<02:36,  4.53it/s]
 94%|█████████▎| 10359/11066 [37:58<02:36,  4.51it/s]
                                                     

 94%|█████████▎| 10359/11066 [37:59<02:36,  4.51it/s]
 94%|█████████▎| 10360/11066 [37:59<02:36,  4.51it/s]
                                                     

 94%|█████████▎| 10360/11066 [37:59<02:36,  4.51it/s]
 94%|█████████▎| 10361/11066 [37:59<02:36,  4.50it/s]
                                                     

 94%|█████████▎| 10361/11066 [37:59<02:36,  4.50it/s]
 94%|█████████▎| 10362/11066 [37:59<02:35,  4.54it/s]
                                                     

 94%|█████████▎| 10362/11066 [37:59<02:35,  4.54it/s]
 94%|█████████▎| 10363/11066 [37:59<02:33,  4.58it/s]
                                                     

 94%|█████████▎| 10363/11066 [37:59<02:33,  4.58it/s]
 94%|█████████▎| 10364/11066 [38:00<02:33,  4.58it/s]
                                                     

 94%|█████████▎| 10364/11066 [38:00<02:33,  4.58it/s]
 94%|█████████▎| 10365/11066 [38:00<02:31,  4.64it/s]
                                                     

 94%|█████████▎| 10365/11066 [38:00<02:31,  4.64it/s]
 94%|█████████▎| 10366/11066 [38:00<02:31,  4.63it/s]
                                                     

 94%|█████████▎| 10366/11066 [38:00<02:31,  4.63it/s]
 94%|█████████▎| 10367/11066 [38:00<02:29,  4.67it/s]
                                                     

 94%|█████████▎| 10367/11066 [38:00<02:29,  4.67it/s]
 94%|█████████▎| 10368/11066 [38:00<02:29,  4.67it/s]
                                                     

 94%|█████████▎| 10368/11066 [38:00<02:29,  4.67it/s]
 94%|█████████▎| 10369/11066 [38:01<02:28,  4.70it/s]
                                                     

 94%|█████████▎| 10369/11066 [38:01<02:28,  4.70it/s]
 94%|█████████▎| 10370/11066 [38:01<02:28,  4.70it/s]
                                                     

 94%|█████████▎| 10370/11066 [38:01<02:28,  4.70it/s]
 94%|█████████▎| 10371/11066 [38:01<02:30,  4.63it/s]
                                                     

 94%|█████████▎| 10371/11066 [38:01<02:30,  4.63it/s]
 94%|█████████▎| 10372/11066 [38:01<02:29,  4.64it/s]
                                                     
{'loss': 1.2403, 'learning_rate': 2.1877823965299116e-06, 'epoch': 1.85}
{'loss': 0.867, 'learning_rate': 2.1850713898427617e-06, 'epoch': 1.85}
{'loss': 0.9073, 'learning_rate': 2.182360383155612e-06, 'epoch': 1.85}
{'loss': 0.7223, 'learning_rate': 2.179649376468462e-06, 'epoch': 1.85}
{'loss': 0.958, 'learning_rate': 2.176938369781312e-06, 'epoch': 1.85}
{'loss': 0.4673, 'learning_rate': 2.1742273630941622e-06, 'epoch': 1.86}
{'loss': 0.6479, 'learning_rate': 2.1715163564070124e-06, 'epoch': 1.86}
{'loss': 1.4853, 'learning_rate': 2.1688053497198625e-06, 'epoch': 1.86}
{'loss': 0.8926, 'learning_rate': 2.1660943430327126e-06, 'epoch': 1.86}
{'loss': 0.9025, 'learning_rate': 2.1633833363455628e-06, 'epoch': 1.86}
{'loss': 0.7326, 'learning_rate': 2.1606723296584133e-06, 'epoch': 1.86}
{'loss': 0.6986, 'learning_rate': 2.1579613229712635e-06, 'epoch': 1.86}
{'loss': 0.4974, 'learning_rate': 2.1552503162841136e-06, 'epoch': 1.86}
{'loss': 0.7623, 'learning_rate': 2.1525393095969637e-06, 'epoch': 1.86}
{'loss': 0.4255, 'learning_rate': 2.149828302909814e-06, 'epoch': 1.86}
{'loss': 0.5093, 'learning_rate': 2.147117296222664e-06, 'epoch': 1.86}
{'loss': 0.7983, 'learning_rate': 2.144406289535514e-06, 'epoch': 1.86}
{'loss': 0.4706, 'learning_rate': 2.1416952828483643e-06, 'epoch': 1.86}
{'loss': 1.1749, 'learning_rate': 2.1389842761612144e-06, 'epoch': 1.86}
{'loss': 0.4182, 'learning_rate': 2.1362732694740645e-06, 'epoch': 1.86}
{'loss': 0.9088, 'learning_rate': 2.1335622627869147e-06, 'epoch': 1.86}
{'loss': 0.5313, 'learning_rate': 2.1308512560997652e-06, 'epoch': 1.86}
{'loss': 1.0063, 'learning_rate': 2.1281402494126154e-06, 'epoch': 1.86}
{'loss': 0.7883, 'learning_rate': 2.1254292427254655e-06, 'epoch': 1.86}
{'loss': 0.5137, 'learning_rate': 2.1227182360383156e-06, 'epoch': 1.86}
{'loss': 0.6751, 'learning_rate': 2.1200072293511658e-06, 'epoch': 1.86}
{'loss': 0.719, 'learning_rate': 2.117296222664016e-06, 'epoch': 1.86}
{'loss': 1.3688, 'learning_rate': 2.114585215976866e-06, 'epoch': 1.86}
{'loss': 0.5674, 'learning_rate': 2.111874209289716e-06, 'epoch': 1.86}
{'loss': 1.1287, 'learning_rate': 2.1091632026025663e-06, 'epoch': 1.86}
{'loss': 0.1908, 'learning_rate': 2.1064521959154164e-06, 'epoch': 1.86}
{'loss': 0.5055, 'learning_rate': 2.103741189228267e-06, 'epoch': 1.86}
{'loss': 0.5807, 'learning_rate': 2.101030182541117e-06, 'epoch': 1.86}
{'loss': 0.8923, 'learning_rate': 2.0983191758539673e-06, 'epoch': 1.86}
{'loss': 0.9181, 'learning_rate': 2.0956081691668174e-06, 'epoch': 1.86}
{'loss': 0.9167, 'learning_rate': 2.0928971624796675e-06, 'epoch': 1.86}
{'loss': 0.3454, 'learning_rate': 2.0901861557925177e-06, 'epoch': 1.86}
{'loss': 1.0884, 'learning_rate': 2.087475149105368e-06, 'epoch': 1.86}
{'loss': 0.8546, 'learning_rate': 2.084764142418218e-06, 'epoch': 1.86}
{'loss': 0.6183, 'learning_rate': 2.082053135731068e-06, 'epoch': 1.86}
{'loss': 0.3466, 'learning_rate': 2.0793421290439182e-06, 'epoch': 1.86}
{'loss': 0.2458, 'learning_rate': 2.0766311223567683e-06, 'epoch': 1.86}
{'loss': 1.3436, 'learning_rate': 2.073920115669619e-06, 'epoch': 1.86}
{'loss': 0.2736, 'learning_rate': 2.071209108982469e-06, 'epoch': 1.86}
{'loss': 1.3985, 'learning_rate': 2.068498102295319e-06, 'epoch': 1.86}
{'loss': 0.9754, 'learning_rate': 2.0657870956081693e-06, 'epoch': 1.86}
{'loss': 0.8038, 'learning_rate': 2.0630760889210194e-06, 'epoch': 1.86}
{'loss': 1.1964, 'learning_rate': 2.0603650822338696e-06, 'epoch': 1.86}
{'loss': 0.8602, 'learning_rate': 2.0576540755467197e-06, 'epoch': 1.86}
{'loss': 0.8117, 'learning_rate': 2.05494306885957e-06, 'epoch': 1.86}
{'loss': 0.6771, 'learning_rate': 2.05223206217242e-06, 'epoch': 1.86}
{'loss': 0.6393, 'learning_rate': 2.04952105548527e-06, 'epoch': 1.86}
{'loss': 1.1508, 'learning_rate': 2.0468100487981207e-06, 'epoch': 1.86}
{'loss': 1.0455, 'learning_rate': 2.044099042110971e-06, 'epoch': 1.86}
{'loss': 0.8888, 'learning_rate': 2.041388035423821e-06, 'epoch': 1.86}
{'loss': 0.6354, 'learning_rate': 2.038677028736671e-06, 'epoch': 1.86}
{'loss': 0.8028, 'learning_rate': 2.035966022049521e-06, 'epoch': 1.86}
{'loss': 0.5321, 'learning_rate': 2.0332550153623713e-06, 'epoch': 1.86}
{'loss': 0.2143, 'learning_rate': 2.0305440086752215e-06, 'epoch': 1.86}
{'loss': 1.0121, 'learning_rate': 2.0278330019880716e-06, 'epoch': 1.86}
{'loss': 0.8453, 'learning_rate': 2.0251219953009217e-06, 'epoch': 1.86}
{'loss': 0.5743, 'learning_rate': 2.022410988613772e-06, 'epoch': 1.87}
{'loss': 0.6393, 'learning_rate': 2.019699981926622e-06, 'epoch': 1.87}
{'loss': 1.0955, 'learning_rate': 2.0169889752394726e-06, 'epoch': 1.87}
{'loss': 0.7443, 'learning_rate': 2.0142779685523227e-06, 'epoch': 1.87}
{'loss': 1.1907, 'learning_rate': 2.011566961865173e-06, 'epoch': 1.87}
{'loss': 0.5677, 'learning_rate': 2.008855955178023e-06, 'epoch': 1.87}
{'loss': 0.814, 'learning_rate': 2.006144948490873e-06, 'epoch': 1.87}
{'loss': 0.6515, 'learning_rate': 2.0034339418037232e-06, 'epoch': 1.87}
{'loss': 0.2841, 'learning_rate': 2.0007229351165734e-06, 'epoch': 1.87}
{'loss': 0.3454, 'learning_rate': 1.9980119284294235e-06, 'epoch': 1.87}
{'loss': 0.9424, 'learning_rate': 1.9953009217422736e-06, 'epoch': 1.87}
{'loss': 0.8536, 'learning_rate': 1.9925899150551238e-06, 'epoch': 1.87}
{'loss': 0.519, 'learning_rate': 1.9898789083679743e-06, 'epoch': 1.87}
{'loss': 0.4993, 'learning_rate': 1.9871679016808245e-06, 'epoch': 1.87}
{'loss': 1.0661, 'learning_rate': 1.9844568949936746e-06, 'epoch': 1.87}
{'loss': 0.5924, 'learning_rate': 1.9817458883065247e-06, 'epoch': 1.87}
{'loss': 0.8777, 'learning_rate': 1.979034881619375e-06, 'epoch': 1.87}
{'loss': 1.345, 'learning_rate': 1.976323874932225e-06, 'epoch': 1.87}
{'loss': 1.0124, 'learning_rate': 1.973612868245075e-06, 'epoch': 1.87}
{'loss': 0.5424, 'learning_rate': 1.9709018615579253e-06, 'epoch': 1.87}
{'loss': 0.3028, 'learning_rate': 1.9681908548707754e-06, 'epoch': 1.87}
{'loss': 0.8006, 'learning_rate': 1.9654798481836255e-06, 'epoch': 1.87}
{'loss': 0.4343, 'learning_rate': 1.962768841496476e-06, 'epoch': 1.87}
{'loss': 0.4887, 'learning_rate': 1.9600578348093262e-06, 'epoch': 1.87}
{'loss': 0.6385, 'learning_rate': 1.9573468281221764e-06, 'epoch': 1.87}
{'loss': 0.382, 'learning_rate': 1.9546358214350265e-06, 'epoch': 1.87}
{'loss': 0.5754, 'learning_rate': 1.9519248147478766e-06, 'epoch': 1.87}
{'loss': 0.841, 'learning_rate': 1.9492138080607268e-06, 'epoch': 1.87}
{'loss': 0.3559, 'learning_rate': 1.946502801373577e-06, 'epoch': 1.87}
{'loss': 0.5123, 'learning_rate': 1.943791794686427e-06, 'epoch': 1.87}
{'loss': 1.1674, 'learning_rate': 1.941080787999277e-06, 'epoch': 1.87}
{'loss': 1.1815, 'learning_rate': 1.9383697813121273e-06, 'epoch': 1.87}
{'loss': 0.5617, 'learning_rate': 1.9356587746249774e-06, 'epoch': 1.87}
{'loss': 1.193, 'learning_rate': 1.932947767937828e-06, 'epoch': 1.87}
{'loss': 0.7035, 'learning_rate': 1.930236761250678e-06, 'epoch': 1.87}
{'loss': 0.6803, 'learning_rate': 1.9275257545635283e-06, 'epoch': 1.87}
{'loss': 0.836, 'learning_rate': 1.9248147478763784e-06, 'epoch': 1.87}
{'loss': 0.4997, 'learning_rate': 1.9221037411892285e-06, 'epoch': 1.87}
{'loss': 0.3195, 'learning_rate': 1.9193927345020787e-06, 'epoch': 1.87}
{'loss': 0.6498, 'learning_rate': 1.9166817278149284e-06, 'epoch': 1.87}
{'loss': 0.6987, 'learning_rate': 1.9139707211277785e-06, 'epoch': 1.87}
{'loss': 0.4904, 'learning_rate': 1.9112597144406287e-06, 'epoch': 1.87}
{'loss': 0.8545, 'learning_rate': 1.908548707753479e-06, 'epoch': 1.87}
{'loss': 0.571, 'learning_rate': 1.9058377010663291e-06, 'epoch': 1.87}
{'loss': 1.5356, 'learning_rate': 1.9031266943791793e-06, 'epoch': 1.87}
{'loss': 0.5474, 'learning_rate': 1.9004156876920294e-06, 'epoch': 1.87}
{'loss': 0.574, 'learning_rate': 1.8977046810048797e-06, 'epoch': 1.87}
{'loss': 0.2306, 'learning_rate': 1.8949936743177299e-06, 'epoch': 1.87}
{'loss': 0.5692, 'learning_rate': 1.89228266763058e-06, 'epoch': 1.87}
{'loss': 0.9575, 'learning_rate': 1.8895716609434302e-06, 'epoch': 1.87}
{'loss': 0.95, 'learning_rate': 1.8868606542562803e-06, 'epoch': 1.87}
{'loss': 0.3809, 'learning_rate': 1.8841496475691306e-06, 'epoch': 1.87}

 94%|█████████▎| 10372/11066 [38:01<02:29,  4.64it/s]
 94%|█████████▎| 10373/11066 [38:02<02:30,  4.59it/s]
                                                     

 94%|█████████▎| 10373/11066 [38:02<02:30,  4.59it/s]
 94%|█████████▎| 10374/11066 [38:02<02:31,  4.56it/s]
                                                     

 94%|█████████▎| 10374/11066 [38:02<02:31,  4.56it/s]
 94%|█████████▍| 10375/11066 [38:02<02:32,  4.54it/s]
                                                     

 94%|█████████▍| 10375/11066 [38:02<02:32,  4.54it/s]
 94%|█████████▍| 10376/11066 [38:02<02:30,  4.59it/s]
                                                     

 94%|█████████▍| 10376/11066 [38:02<02:30,  4.59it/s]
 94%|█████████▍| 10377/11066 [38:02<02:29,  4.60it/s]
                                                     

 94%|█████████▍| 10377/11066 [38:02<02:29,  4.60it/s]
 94%|█████████▍| 10378/11066 [38:03<02:27,  4.65it/s]
                                                     

 94%|█████████▍| 10378/11066 [38:03<02:27,  4.65it/s]
 94%|█████████▍| 10379/11066 [38:03<02:32,  4.50it/s]
                                                     

 94%|█████████▍| 10379/11066 [38:03<02:32,  4.50it/s]
 94%|█████████▍| 10380/11066 [38:03<02:32,  4.49it/s]
                                                     

 94%|█████████▍| 10380/11066 [38:03<02:32,  4.49it/s]
 94%|█████████▍| 10381/11066 [38:03<02:32,  4.49it/s]
                                                     

 94%|█████████▍| 10381/11066 [38:03<02:32,  4.49it/s]
 94%|█████████▍| 10382/11066 [38:04<02:32,  4.49it/s]
                                                     

 94%|█████████▍| 10382/11066 [38:04<02:32,  4.49it/s]
 94%|█████████▍| 10383/11066 [38:04<02:31,  4.50it/s]
                                                     

 94%|█████████▍| 10383/11066 [38:04<02:31,  4.50it/s]
 94%|█████████▍| 10384/11066 [38:04<02:31,  4.49it/s]
                                                     

 94%|█████████▍| 10384/11066 [38:04<02:31,  4.49it/s]
 94%|█████████▍| 10385/11066 [38:04<02:31,  4.50it/s]
                                                     

 94%|█████████▍| 10385/11066 [38:04<02:31,  4.50it/s]
 94%|█████████▍| 10386/11066 [38:04<02:29,  4.55it/s]
                                                     

 94%|█████████▍| 10386/11066 [38:04<02:29,  4.55it/s]
 94%|█████████▍| 10387/11066 [38:05<02:27,  4.59it/s]
                                                     

 94%|█████████▍| 10387/11066 [38:05<02:27,  4.59it/s]
 94%|█████████▍| 10388/11066 [38:05<02:26,  4.63it/s]
                                                     

 94%|█████████▍| 10388/11066 [38:05<02:26,  4.63it/s]
 94%|█████████▍| 10389/11066 [38:05<02:27,  4.59it/s]
                                                     

 94%|█████████▍| 10389/11066 [38:05<02:27,  4.59it/s]
 94%|█████████▍| 10390/11066 [38:05<02:26,  4.60it/s]
                                                     

 94%|█████████▍| 10390/11066 [38:05<02:26,  4.60it/s]
 94%|█████████▍| 10391/11066 [38:05<02:27,  4.58it/s]
                                                     

 94%|█████████▍| 10391/11066 [38:05<02:27,  4.58it/s]
 94%|█████████▍| 10392/11066 [38:06<02:26,  4.61it/s]
                                                     

 94%|█████████▍| 10392/11066 [38:06<02:26,  4.61it/s]
 94%|█████████▍| 10393/11066 [38:06<02:25,  4.61it/s]
                                                     

 94%|█████████▍| 10393/11066 [38:06<02:25,  4.61it/s]
 94%|█████████▍| 10394/11066 [38:06<02:25,  4.63it/s]
                                                     

 94%|█████████▍| 10394/11066 [38:06<02:25,  4.63it/s]
 94%|█████████▍| 10395/11066 [38:06<02:24,  4.65it/s]
                                                     

 94%|█████████▍| 10395/11066 [38:06<02:24,  4.65it/s]
 94%|█████████▍| 10396/11066 [38:07<02:25,  4.60it/s]
                                                     

 94%|█████████▍| 10396/11066 [38:07<02:25,  4.60it/s]
 94%|█████████▍| 10397/11066 [38:07<02:27,  4.54it/s]
                                                     

 94%|█████████▍| 10397/11066 [38:07<02:27,  4.54it/s]
 94%|█████████▍| 10398/11066 [38:07<02:26,  4.56it/s]
                                                     

 94%|█████████▍| 10398/11066 [38:07<02:26,  4.56it/s]
 94%|█████████▍| 10399/11066 [38:07<02:27,  4.51it/s]
                                                     

 94%|█████████▍| 10399/11066 [38:07<02:27,  4.51it/s]
 94%|█████████▍| 10400/11066 [38:07<02:27,  4.50it/s]
                                                     

 94%|█████████▍| 10400/11066 [38:07<02:27,  4.50it/s]
 94%|█████████▍| 10401/11066 [38:08<02:27,  4.50it/s]
                                                     

 94%|█████████▍| 10401/11066 [38:08<02:27,  4.50it/s]
 94%|█████████▍| 10402/11066 [38:08<02:27,  4.50it/s]
                                                     

 94%|█████████▍| 10402/11066 [38:08<02:27,  4.50it/s]
 94%|█████████▍| 10403/11066 [38:08<02:26,  4.54it/s]
                                                     

 94%|█████████▍| 10403/11066 [38:08<02:26,  4.54it/s]
 94%|█████████▍| 10404/11066 [38:08<02:23,  4.60it/s]
                                                     

 94%|█████████▍| 10404/11066 [38:08<02:23,  4.60it/s]
 94%|█████████▍| 10405/11066 [38:09<02:23,  4.61it/s]
                                                     

 94%|█████████▍| 10405/11066 [38:09<02:23,  4.61it/s]
 94%|█████████▍| 10406/11066 [38:09<02:24,  4.56it/s]
                                                     

 94%|█████████▍| 10406/11066 [38:09<02:24,  4.56it/s]
 94%|█████████▍| 10407/11066 [38:09<02:25,  4.53it/s]
                                                     

 94%|█████████▍| 10407/11066 [38:09<02:25,  4.53it/s]
 94%|█████████▍| 10408/11066 [38:09<02:25,  4.52it/s]
                                                     

 94%|█████████▍| 10408/11066 [38:09<02:25,  4.52it/s]
 94%|█████████▍| 10409/11066 [38:09<02:25,  4.52it/s]
                                                     

 94%|█████████▍| 10409/11066 [38:09<02:25,  4.52it/s]
 94%|█████████▍| 10410/11066 [38:10<02:25,  4.52it/s]
                                                     

 94%|█████████▍| 10410/11066 [38:10<02:25,  4.52it/s]
 94%|█████████▍| 10411/11066 [38:10<02:25,  4.52it/s]
                                                     

 94%|█████████▍| 10411/11066 [38:10<02:25,  4.52it/s]
 94%|█████████▍| 10412/11066 [38:10<02:25,  4.50it/s]
                                                     

 94%|█████████▍| 10412/11066 [38:10<02:25,  4.50it/s]
 94%|█████████▍| 10413/11066 [38:10<02:25,  4.49it/s]
                                                     

 94%|█████████▍| 10413/11066 [38:10<02:25,  4.49it/s]
 94%|█████████▍| 10414/11066 [38:11<02:25,  4.47it/s]
                                                     

 94%|█████████▍| 10414/11066 [38:11<02:25,  4.47it/s]
 94%|█████████▍| 10415/11066 [38:11<02:25,  4.47it/s]
                                                     

 94%|█████████▍| 10415/11066 [38:11<02:25,  4.47it/s]
 94%|█████████▍| 10416/11066 [38:11<02:25,  4.47it/s]
                                                     

 94%|█████████▍| 10416/11066 [38:11<02:25,  4.47it/s]
 94%|█████████▍| 10417/11066 [38:11<02:24,  4.48it/s]
                                                     

 94%|█████████▍| 10417/11066 [38:11<02:24,  4.48it/s]
 94%|█████████▍| 10418/11066 [38:11<02:24,  4.48it/s]
                                                     

 94%|█████████▍| 10418/11066 [38:11<02:24,  4.48it/s]
 94%|█████████▍| 10419/11066 [38:12<02:24,  4.49it/s]
                                                     

 94%|█████████▍| 10419/11066 [38:12<02:24,  4.49it/s]
 94%|█████████▍| 10420/11066 [38:12<02:22,  4.54it/s]
                                                     

 94%|█████████▍| 10420/11066 [38:12<02:22,  4.54it/s]
 94%|█████████▍| 10421/11066 [38:12<02:22,  4.53it/s]
                                                     

 94%|█████████▍| 10421/11066 [38:12<02:22,  4.53it/s]
 94%|█████████▍| 10422/11066 [38:12<02:22,  4.52it/s]
                                                     

 94%|█████████▍| 10422/11066 [38:12<02:22,  4.52it/s]
 94%|█████████▍| 10423/11066 [38:13<02:22,  4.52it/s]
                                                     

 94%|█████████▍| 10423/11066 [38:13<02:22,  4.52it/s]
 94%|█████████▍| 10424/11066 [38:13<02:21,  4.55it/s]
                                                     

 94%|█████████▍| 10424/11066 [38:13<02:21,  4.55it/s]
 94%|█████████▍| 10425/11066 [38:13<02:22,  4.49it/s]
                                                     

 94%|█████████▍| 10425/11066 [38:13<02:22,  4.49it/s]
 94%|█████████▍| 10426/11066 [38:13<02:24,  4.43it/s]
                                                     

 94%|█████████▍| 10426/11066 [38:13<02:24,  4.43it/s]
 94%|█████████▍| 10427/11066 [38:13<02:23,  4.45it/s]
                                                     

 94%|█████████▍| 10427/11066 [38:13<02:23,  4.45it/s]
 94%|█████████▍| 10428/11066 [38:14<02:24,  4.40it/s]
                                                     

 94%|█████████▍| 10428/11066 [38:14<02:24,  4.40it/s]
 94%|█████████▍| 10429/11066 [38:14<02:23,  4.43it/s]
                                                     

 94%|█████████▍| 10429/11066 [38:14<02:23,  4.43it/s]
 94%|█████████▍| 10430/11066 [38:14<02:22,  4.46it/s]
                                                     

 94%|█████████▍| 10430/11066 [38:14<02:22,  4.46it/s]
 94%|█████████▍| 10431/11066 [38:14<02:22,  4.47it/s]
                                                     

 94%|█████████▍| 10431/11066 [38:14<02:22,  4.47it/s]
 94%|█████████▍| 10432/11066 [38:15<02:21,  4.48it/s]
                                                     

 94%|█████████▍| 10432/11066 [38:15<02:21,  4.48it/s]
 94%|█████████▍| 10433/11066 [38:15<02:22,  4.44it/s]
                                                     

 94%|█████████▍| 10433/11066 [38:15<02:22,  4.44it/s]
 94%|█████████▍| 10434/11066 [38:15<02:22,  4.45it/s]
                                                     

 94%|█████████▍| 10434/11066 [38:15<02:22,  4.45it/s]
 94%|█████████▍| 10435/11066 [38:15<02:21,  4.46it/s]
                                                     

 94%|█████████▍| 10435/11066 [38:15<02:21,  4.46it/s]
 94%|█████████▍| 10436/11066 [38:15<02:19,  4.51it/s]
                                                     

 94%|█████████▍| 10436/11066 [38:15<02:19,  4.51it/s]
 94%|█████████▍| 10437/11066 [38:16<02:18,  4.55it/s]
                                                     

 94%|█████████▍| 10437/11066 [38:16<02:18,  4.55it/s]
 94%|█████████▍| 10438/11066 [38:16<02:16,  4.60it/s]
                                                     

 94%|█████████▍| 10438/11066 [38:16<02:16,  4.60it/s]
 94%|█████████▍| 10439/11066 [38:16<02:17,  4.55it/s]
                                                     

 94%|█████████▍| 10439/11066 [38:16<02:17,  4.55it/s]
 94%|█████████▍| 10440/11066 [38:16<02:18,  4.53it/s]
                                                     

 94%|█████████▍| 10440/11066 [38:16<02:18,  4.53it/s]
 94%|█████████▍| 10441/11066 [38:17<02:18,  4.52it/s]
                                                     

 94%|█████████▍| 10441/11066 [38:17<02:18,  4.52it/s]
 94%|█████████▍| 10442/11066 [38:17<02:18,  4.51it/s]
                                                     

 94%|█████████▍| 10442/11066 [38:17<02:18,  4.51it/s]
 94%|█████████▍| 10443/11066 [38:17<02:18,  4.51it/s]
                                                     

 94%|█████████▍| 10443/11066 [38:17<02:18,  4.51it/s]
 94%|█████████▍| 10444/11066 [38:17<02:18,  4.50it/s]
                                                     

 94%|█████████▍| 10444/11066 [38:17<02:18,  4.50it/s]
 94%|█████████▍| 10445/11066 [38:17<02:17,  4.51it/s]
                                                     

 94%|█████████▍| 10445/11066 [38:17<02:17,  4.51it/s]
 94%|█████████▍| 10446/11066 [38:18<02:17,  4.51it/s]
                                                     

 94%|█████████▍| 10446/11066 [38:18<02:17,  4.51it/s]
 94%|█████████▍| 10447/11066 [38:18<02:16,  4.54it/s]
                                                     

 94%|█████████▍| 10447/11066 [38:18<02:16,  4.54it/s]
 94%|█████████▍| 10448/11066 [38:18<02:14,  4.60it/s]
                                                     

 94%|█████████▍| 10448/11066 [38:18<02:14,  4.60it/s]
 94%|█████████▍| 10449/11066 [38:18<02:13,  4.62it/s]
                                                     

 94%|█████████▍| 10449/11066 [38:18<02:13,  4.62it/s]
 94%|█████████▍| 10450/11066 [38:19<02:14,  4.57it/s]
                                                     

 94%|█████████▍| 10450/11066 [38:19<02:14,  4.57it/s]
 94%|█████████▍| 10451/11066 [38:19<02:15,  4.55it/s]
                                                     

 94%|█████████▍| 10451/11066 [38:19<02:15,  4.55it/s]
 94%|█████████▍| 10452/11066 [38:19<02:15,  4.54it/s]
                                                     

 94%|█████████▍| 10452/11066 [38:19<02:15,  4.54it/s]
 94%|█████████▍| 10453/11066 [38:19<02:15,  4.52it/s]
                                                     

 94%|█████████▍| 10453/11066 [38:19<02:15,  4.52it/s]
 94%|█████████▍| 10454/11066 [38:19<02:15,  4.52it/s]
                                                     

 94%|█████████▍| 10454/11066 [38:19<02:15,  4.52it/s]
 94%|█████████▍| 10455/11066 [38:20<02:14,  4.55it/s]
                                                     

 94%|█████████▍| 10455/11066 [38:20<02:14,  4.55it/s]
 94%|█████████▍| 10456/11066 [38:20<02:14,  4.54it/s]
                                                     

 94%|█████████▍| 10456/11066 [38:20<02:14,  4.54it/s]
 94%|█████████▍| 10457/11066 [38:20<02:14,  4.53it/s]
                                                     

 94%|█████████▍| 10457/11066 [38:20<02:14,  4.53it/s]
 95%|█████████▍| 10458/11066 [38:20<02:15,  4.50it/s]
                                                     

 95%|█████████▍| 10458/11066 [38:20<02:15,  4.50it/s]
 95%|█████████▍| 10459/11066 [38:21<02:14,  4.53it/s]
                                                     

 95%|█████████▍| 10459/11066 [38:21<02:14,  4.53it/s]
 95%|█████████▍| 10460/11066 [38:21<02:14,  4.50it/s]
                                                     

 95%|█████████▍| 10460/11066 [38:21<02:14,  4.50it/s]
 95%|█████████▍| 10461/11066 [38:21<02:13,  4.53it/s]
                                                     

 95%|█████████▍| 10461/11066 [38:21<02:13,  4.53it/s]
 95%|█████████▍| 10462/11066 [38:21<02:13,  4.51it/s]
                                                     

 95%|█████████▍| 10462/11066 [38:21<02:13,  4.51it/s]
 95%|█████████▍| 10463/11066 [38:21<02:11,  4.57it/s]
                                                     

 95%|█████████▍| 10463/11066 [38:21<02:11,  4.57it/s]
 95%|█████████▍| 10464/11066 [38:22<02:11,  4.57it/s]
                                                     

 95%|█████████▍| 10464/11066 [38:22<02:11,  4.57it/s]
 95%|█████████▍| 10465/11066 [38:22<02:11,  4.58it/s]
                                                     

 95%|█████████▍| 10465/11066 [38:22<02:11,  4.58it/s]
 95%|█████████▍| 10466/11066 [38:22<02:12,  4.54it/s]
                                                     

 95%|█████████▍| 10466/11066 [38:22<02:12,  4.54it/s]
 95%|█████████▍| 10467/11066 [38:22<02:11,  4.56it/s]
                                                     

 95%|█████████▍| 10467/11066 [38:22<02:11,  4.56it/s]
 95%|█████████▍| 10468/11066 [38:23<02:12,  4.52it/s]
                                                     

 95%|█████████▍| 10468/11066 [38:23<02:12,  4.52it/s]
 95%|█████████▍| 10469/11066 [38:23<02:12,  4.50it/s]
                                                     

 95%|█████████▍| 10469/11066 [38:23<02:12,  4.50it/s]
 95%|█████████▍| 10470/11066 [38:23<02:12,  4.49it/s]
                                                     

 95%|█████████▍| 10470/11066 [38:23<02:12,  4.49it/s]
 95%|█████████▍| 10471/11066 [38:23<02:11,  4.53it/s]
                                                     

 95%|█████████▍| 10471/11066 [38:23<02:11,  4.53it/s]
 95%|█████████▍| 10472/11066 [38:23<02:09,  4.57it/s]
                                                     

 95%|█████████▍| 10472/11066 [38:23<02:09,  4.57it/s]
 95%|█████████▍| 10473/11066 [38:24<02:10,  4.54it/s]
                                                     

 95%|█████████▍| 10473/11066 [38:24<02:10,  4.54it/s]
 95%|█████████▍| 10474/11066 [38:24<02:11,  4.52it/s]
                                                     

 95%|█████████▍| 10474/11066 [38:24<02:11,  4.52it/s]
 95%|█████████▍| 10475/11066 [38:24<02:10,  4.54it/s]
                                                     

 95%|█████████▍| 10475/11066 [38:24<02:10,  4.54it/s]
 95%|█████████▍| 10476/11066 [38:24<02:09,  4.55it/s]
                                                     

 95%|█████████▍| 10476/11066 [38:24<02:09,  4.55it/s]
 95%|█████████▍| 10477/11066 [38:24<02:09,  4.56it/s]
                                                     

 95%|█████████▍| 10477/11066 [38:24<02:09,  4.56it/s]
 95%|█████████▍| 10478/11066 [38:25<02:09,  4.53it/s]
                                                     

 95%|█████████▍| 10478/11066 [38:25<02:09,  4.53it/s]
 95%|█████████▍| 10479/11066 [38:25<02:08,  4.55it/s]
                                                     

 95%|█████████▍| 10479/11066 [38:25<02:08,  4.55it/s]
 95%|█████████▍| 10480/11066 [38:25<02:07,  4.60it/s]
                                                     

 95%|█████████▍| 10480/11066 [38:25<02:07,  4.60it/s]
 95%|█████████▍| 10481/11066 [38:25<02:06,  4.62it/s]
                                                     

 95%|█████████▍| 10481/11066 [38:25<02:06,  4.62it/s]
 95%|█████████▍| 10482/11066 [38:26<02:06,  4.61it/s]
                                                     

 95%|█████████▍| 10482/11066 [38:26<02:06,  4.61it/s]
 95%|█████████▍| 10483/11066 [38:26<02:05,  4.64it/s]
                                                     

 95%|█████████▍| 10483/11066 [38:26<02:05,  4.64it/s]
 95%|█████████▍| 10484/11066 [38:26<02:05,  4.62it/s]
                                                     
{'loss': 0.4244, 'learning_rate': 1.8814386408819808e-06, 'epoch': 1.87}
{'loss': 0.9214, 'learning_rate': 1.878727634194831e-06, 'epoch': 1.87}
{'loss': 0.9124, 'learning_rate': 1.876016627507681e-06, 'epoch': 1.87}
{'loss': 0.5002, 'learning_rate': 1.8733056208205314e-06, 'epoch': 1.88}
{'loss': 0.5621, 'learning_rate': 1.8705946141333817e-06, 'epoch': 1.88}
{'loss': 0.4531, 'learning_rate': 1.8678836074462319e-06, 'epoch': 1.88}
{'loss': 0.9359, 'learning_rate': 1.865172600759082e-06, 'epoch': 1.88}
{'loss': 0.835, 'learning_rate': 1.8624615940719321e-06, 'epoch': 1.88}
{'loss': 0.7674, 'learning_rate': 1.8597505873847823e-06, 'epoch': 1.88}
{'loss': 0.7059, 'learning_rate': 1.8570395806976326e-06, 'epoch': 1.88}
{'loss': 0.7693, 'learning_rate': 1.8543285740104827e-06, 'epoch': 1.88}
{'loss': 1.2803, 'learning_rate': 1.8516175673233329e-06, 'epoch': 1.88}
{'loss': 0.6517, 'learning_rate': 1.848906560636183e-06, 'epoch': 1.88}
{'loss': 0.8029, 'learning_rate': 1.8461955539490331e-06, 'epoch': 1.88}
{'loss': 0.8352, 'learning_rate': 1.8434845472618833e-06, 'epoch': 1.88}
{'loss': 0.4797, 'learning_rate': 1.8407735405747336e-06, 'epoch': 1.88}
{'loss': 0.6228, 'learning_rate': 1.8380625338875838e-06, 'epoch': 1.88}
{'loss': 0.8097, 'learning_rate': 1.835351527200434e-06, 'epoch': 1.88}
{'loss': 1.0476, 'learning_rate': 1.832640520513284e-06, 'epoch': 1.88}
{'loss': 1.2135, 'learning_rate': 1.829929513826134e-06, 'epoch': 1.88}
{'loss': 0.3708, 'learning_rate': 1.8272185071389843e-06, 'epoch': 1.88}
{'loss': 1.1144, 'learning_rate': 1.8245075004518344e-06, 'epoch': 1.88}
{'loss': 0.5043, 'learning_rate': 1.8217964937646846e-06, 'epoch': 1.88}
{'loss': 1.399, 'learning_rate': 1.8190854870775347e-06, 'epoch': 1.88}
{'loss': 1.2086, 'learning_rate': 1.8163744803903848e-06, 'epoch': 1.88}
{'loss': 0.5265, 'learning_rate': 1.8136634737032352e-06, 'epoch': 1.88}
{'loss': 0.5771, 'learning_rate': 1.8109524670160853e-06, 'epoch': 1.88}
{'loss': 0.8652, 'learning_rate': 1.8082414603289355e-06, 'epoch': 1.88}
{'loss': 0.5774, 'learning_rate': 1.8055304536417856e-06, 'epoch': 1.88}
{'loss': 0.51, 'learning_rate': 1.8028194469546357e-06, 'epoch': 1.88}
{'loss': 0.9326, 'learning_rate': 1.800108440267486e-06, 'epoch': 1.88}
{'loss': 0.5035, 'learning_rate': 1.7973974335803362e-06, 'epoch': 1.88}
{'loss': 1.045, 'learning_rate': 1.7946864268931863e-06, 'epoch': 1.88}
{'loss': 0.7104, 'learning_rate': 1.7919754202060365e-06, 'epoch': 1.88}
{'loss': 0.9099, 'learning_rate': 1.7892644135188866e-06, 'epoch': 1.88}
{'loss': 0.742, 'learning_rate': 1.786553406831737e-06, 'epoch': 1.88}
{'loss': 0.7695, 'learning_rate': 1.783842400144587e-06, 'epoch': 1.88}
{'loss': 0.6477, 'learning_rate': 1.7811313934574372e-06, 'epoch': 1.88}
{'loss': 0.377, 'learning_rate': 1.7784203867702874e-06, 'epoch': 1.88}
{'loss': 0.3724, 'learning_rate': 1.7757093800831375e-06, 'epoch': 1.88}
{'loss': 0.8532, 'learning_rate': 1.7729983733959876e-06, 'epoch': 1.88}
{'loss': 0.773, 'learning_rate': 1.770287366708838e-06, 'epoch': 1.88}
{'loss': 1.1095, 'learning_rate': 1.767576360021688e-06, 'epoch': 1.88}
{'loss': 0.7127, 'learning_rate': 1.7648653533345382e-06, 'epoch': 1.88}
{'loss': 0.2894, 'learning_rate': 1.7621543466473884e-06, 'epoch': 1.88}
{'loss': 0.5705, 'learning_rate': 1.7594433399602385e-06, 'epoch': 1.88}
{'loss': 0.4046, 'learning_rate': 1.7567323332730888e-06, 'epoch': 1.88}
{'loss': 0.8602, 'learning_rate': 1.754021326585939e-06, 'epoch': 1.88}
{'loss': 0.8996, 'learning_rate': 1.7513103198987891e-06, 'epoch': 1.88}
{'loss': 0.8209, 'learning_rate': 1.7485993132116393e-06, 'epoch': 1.88}
{'loss': 1.0621, 'learning_rate': 1.7458883065244894e-06, 'epoch': 1.88}
{'loss': 0.5109, 'learning_rate': 1.7431772998373397e-06, 'epoch': 1.88}
{'loss': 0.4577, 'learning_rate': 1.7404662931501899e-06, 'epoch': 1.88}
{'loss': 0.7108, 'learning_rate': 1.73775528646304e-06, 'epoch': 1.88}
{'loss': 0.6516, 'learning_rate': 1.7350442797758901e-06, 'epoch': 1.88}
{'loss': 0.288, 'learning_rate': 1.7323332730887403e-06, 'epoch': 1.88}
{'loss': 0.7292, 'learning_rate': 1.7296222664015906e-06, 'epoch': 1.88}
{'loss': 0.886, 'learning_rate': 1.7269112597144407e-06, 'epoch': 1.88}
{'loss': 0.6064, 'learning_rate': 1.7242002530272909e-06, 'epoch': 1.89}
{'loss': 0.8024, 'learning_rate': 1.721489246340141e-06, 'epoch': 1.89}
{'loss': 1.0677, 'learning_rate': 1.7187782396529912e-06, 'epoch': 1.89}
{'loss': 0.8465, 'learning_rate': 1.7160672329658413e-06, 'epoch': 1.89}
{'loss': 0.7998, 'learning_rate': 1.7133562262786916e-06, 'epoch': 1.89}
{'loss': 0.7365, 'learning_rate': 1.7106452195915418e-06, 'epoch': 1.89}
{'loss': 1.3211, 'learning_rate': 1.707934212904392e-06, 'epoch': 1.89}
{'loss': 0.3939, 'learning_rate': 1.705223206217242e-06, 'epoch': 1.89}
{'loss': 1.2495, 'learning_rate': 1.7025121995300922e-06, 'epoch': 1.89}
{'loss': 0.2617, 'learning_rate': 1.6998011928429425e-06, 'epoch': 1.89}
{'loss': 0.5975, 'learning_rate': 1.6970901861557927e-06, 'epoch': 1.89}
{'loss': 0.8337, 'learning_rate': 1.6943791794686428e-06, 'epoch': 1.89}
{'loss': 0.5721, 'learning_rate': 1.691668172781493e-06, 'epoch': 1.89}
{'loss': 0.969, 'learning_rate': 1.688957166094343e-06, 'epoch': 1.89}
{'loss': 1.0905, 'learning_rate': 1.6862461594071934e-06, 'epoch': 1.89}
{'loss': 1.1851, 'learning_rate': 1.6835351527200435e-06, 'epoch': 1.89}
{'loss': 1.6319, 'learning_rate': 1.6808241460328937e-06, 'epoch': 1.89}
{'loss': 0.9048, 'learning_rate': 1.6781131393457438e-06, 'epoch': 1.89}
{'loss': 0.8106, 'learning_rate': 1.675402132658594e-06, 'epoch': 1.89}
{'loss': 0.513, 'learning_rate': 1.6726911259714443e-06, 'epoch': 1.89}
{'loss': 1.0035, 'learning_rate': 1.6699801192842944e-06, 'epoch': 1.89}
{'loss': 0.8802, 'learning_rate': 1.6672691125971446e-06, 'epoch': 1.89}
{'loss': 0.5418, 'learning_rate': 1.6645581059099947e-06, 'epoch': 1.89}
{'loss': 0.497, 'learning_rate': 1.6618470992228448e-06, 'epoch': 1.89}
{'loss': 0.4757, 'learning_rate': 1.6591360925356952e-06, 'epoch': 1.89}
{'loss': 0.3434, 'learning_rate': 1.656425085848545e-06, 'epoch': 1.89}
{'loss': 0.9826, 'learning_rate': 1.6537140791613952e-06, 'epoch': 1.89}
{'loss': 0.8279, 'learning_rate': 1.6510030724742454e-06, 'epoch': 1.89}
{'loss': 0.5949, 'learning_rate': 1.6482920657870955e-06, 'epoch': 1.89}
{'loss': 0.6174, 'learning_rate': 1.6455810590999458e-06, 'epoch': 1.89}
{'loss': 0.7034, 'learning_rate': 1.642870052412796e-06, 'epoch': 1.89}
{'loss': 0.2829, 'learning_rate': 1.640159045725646e-06, 'epoch': 1.89}
{'loss': 1.0014, 'learning_rate': 1.6374480390384962e-06, 'epoch': 1.89}
{'loss': 0.6543, 'learning_rate': 1.6347370323513464e-06, 'epoch': 1.89}
{'loss': 0.454, 'learning_rate': 1.6320260256641965e-06, 'epoch': 1.89}
{'loss': 1.005, 'learning_rate': 1.6293150189770469e-06, 'epoch': 1.89}
{'loss': 1.0408, 'learning_rate': 1.626604012289897e-06, 'epoch': 1.89}
{'loss': 0.6006, 'learning_rate': 1.6238930056027471e-06, 'epoch': 1.89}
{'loss': 0.6424, 'learning_rate': 1.6211819989155973e-06, 'epoch': 1.89}
{'loss': 0.9381, 'learning_rate': 1.6184709922284474e-06, 'epoch': 1.89}
{'loss': 0.9991, 'learning_rate': 1.6157599855412977e-06, 'epoch': 1.89}
{'loss': 0.9822, 'learning_rate': 1.6130489788541479e-06, 'epoch': 1.89}
{'loss': 0.3622, 'learning_rate': 1.610337972166998e-06, 'epoch': 1.89}
{'loss': 0.7503, 'learning_rate': 1.6076269654798481e-06, 'epoch': 1.89}
{'loss': 0.5281, 'learning_rate': 1.6049159587926983e-06, 'epoch': 1.89}
{'loss': 0.4735, 'learning_rate': 1.6022049521055486e-06, 'epoch': 1.89}
{'loss': 0.6558, 'learning_rate': 1.5994939454183988e-06, 'epoch': 1.89}
{'loss': 0.6747, 'learning_rate': 1.5967829387312489e-06, 'epoch': 1.89}
{'loss': 0.6185, 'learning_rate': 1.594071932044099e-06, 'epoch': 1.89}
{'loss': 1.2186, 'learning_rate': 1.5913609253569492e-06, 'epoch': 1.89}
{'loss': 0.611, 'learning_rate': 1.5886499186697995e-06, 'epoch': 1.89}
{'loss': 0.5137, 'learning_rate': 1.5859389119826496e-06, 'epoch': 1.89}
{'loss': 1.1754, 'learning_rate': 1.5832279052954998e-06, 'epoch': 1.89}
{'loss': 0.91, 'learning_rate': 1.58051689860835e-06, 'epoch': 1.89}

 95%|█████████▍| 10484/11066 [38:26<02:05,  4.62it/s]
 95%|█████████▍| 10485/11066 [38:26<02:06,  4.58it/s]
                                                     

 95%|█████████▍| 10485/11066 [38:26<02:06,  4.58it/s]
 95%|█████████▍| 10486/11066 [38:26<02:05,  4.62it/s]
                                                     

 95%|█████████▍| 10486/11066 [38:26<02:05,  4.62it/s]
 95%|█████████▍| 10487/11066 [38:27<02:06,  4.58it/s]
                                                     

 95%|█████████▍| 10487/11066 [38:27<02:06,  4.58it/s]
 95%|█████████▍| 10488/11066 [38:27<02:05,  4.59it/s]
                                                     

 95%|█████████▍| 10488/11066 [38:27<02:05,  4.59it/s]
 95%|█████████▍| 10489/11066 [38:27<02:06,  4.58it/s]
                                                     

 95%|█████████▍| 10489/11066 [38:27<02:06,  4.58it/s]
 95%|█████████▍| 10490/11066 [38:27<02:05,  4.58it/s]
                                                     

 95%|█████████▍| 10490/11066 [38:27<02:05,  4.58it/s]
 95%|█████████▍| 10491/11066 [38:28<02:05,  4.59it/s]
                                                     

 95%|█████████▍| 10491/11066 [38:28<02:05,  4.59it/s]
 95%|█████████▍| 10492/11066 [38:28<02:04,  4.61it/s]
                                                     

 95%|█████████▍| 10492/11066 [38:28<02:04,  4.61it/s]
 95%|█████████▍| 10493/11066 [38:28<02:04,  4.61it/s]
                                                     

 95%|█████████▍| 10493/11066 [38:28<02:04,  4.61it/s]
 95%|█████████▍| 10494/11066 [38:28<02:05,  4.57it/s]
                                                     

 95%|█████████▍| 10494/11066 [38:28<02:05,  4.57it/s]
 95%|█████████▍| 10495/11066 [38:28<02:04,  4.59it/s]
                                                     

 95%|█████████▍| 10495/11066 [38:28<02:04,  4.59it/s]
 95%|█████████▍| 10496/11066 [38:29<02:03,  4.61it/s]
                                                     

 95%|█████████▍| 10496/11066 [38:29<02:03,  4.61it/s]
 95%|█████████▍| 10497/11066 [38:29<02:04,  4.56it/s]
                                                     

 95%|█████████▍| 10497/11066 [38:29<02:04,  4.56it/s]
 95%|█████████▍| 10498/11066 [38:29<02:04,  4.54it/s]
                                                     

 95%|█████████▍| 10498/11066 [38:29<02:04,  4.54it/s]
 95%|█████████▍| 10499/11066 [38:29<02:04,  4.57it/s]
                                                     

 95%|█████████▍| 10499/11066 [38:29<02:04,  4.57it/s]
 95%|█████████▍| 10500/11066 [38:29<02:02,  4.63it/s]
                                                     

 95%|█████████▍| 10500/11066 [38:29<02:02,  4.63it/s]
 95%|█████████▍| 10501/11066 [38:30<02:01,  4.65it/s]
                                                     

 95%|█████████▍| 10501/11066 [38:30<02:01,  4.65it/s]
 95%|█████████▍| 10502/11066 [38:30<02:03,  4.56it/s]
                                                     

 95%|█████████▍| 10502/11066 [38:30<02:03,  4.56it/s]
 95%|█████████▍| 10503/11066 [38:30<02:02,  4.58it/s]
                                                     

 95%|█████████▍| 10503/11066 [38:30<02:02,  4.58it/s]
 95%|█████████▍| 10504/11066 [38:30<02:03,  4.55it/s]
                                                     

 95%|█████████▍| 10504/11066 [38:30<02:03,  4.55it/s]
 95%|█████████▍| 10505/11066 [38:31<02:02,  4.58it/s]
                                                     

 95%|█████████▍| 10505/11066 [38:31<02:02,  4.58it/s]
 95%|█████████▍| 10506/11066 [38:31<02:03,  4.55it/s]
                                                     

 95%|█████████▍| 10506/11066 [38:31<02:03,  4.55it/s]
 95%|█████████▍| 10507/11066 [38:31<02:05,  4.47it/s]
                                                     

 95%|█████████▍| 10507/11066 [38:31<02:05,  4.47it/s]
 95%|█████████▍| 10508/11066 [38:31<02:06,  4.42it/s]
                                                     

 95%|█████████▍| 10508/11066 [38:31<02:06,  4.42it/s]
 95%|█████████▍| 10509/11066 [38:32<02:07,  4.38it/s]
                                                     

 95%|█████████▍| 10509/11066 [38:32<02:07,  4.38it/s]
 95%|█████████▍| 10510/11066 [38:32<02:05,  4.42it/s]
                                                     

 95%|█████████▍| 10510/11066 [38:32<02:05,  4.42it/s]
 95%|█████████▍| 10511/11066 [38:32<02:04,  4.44it/s]
                                                     

 95%|█████████▍| 10511/11066 [38:32<02:04,  4.44it/s]
 95%|█████████▍| 10512/11066 [38:32<02:04,  4.46it/s]
                                                     

 95%|█████████▍| 10512/11066 [38:32<02:04,  4.46it/s]
 95%|█████████▌| 10513/11066 [38:32<02:03,  4.47it/s]
                                                     

 95%|█████████▌| 10513/11066 [38:32<02:03,  4.47it/s]
 95%|█████████▌| 10514/11066 [38:33<02:03,  4.48it/s]
                                                     

 95%|█████████▌| 10514/11066 [38:33<02:03,  4.48it/s]
 95%|█████████▌| 10515/11066 [38:33<02:02,  4.49it/s]
                                                     

 95%|█████████▌| 10515/11066 [38:33<02:02,  4.49it/s]
 95%|█████████▌| 10516/11066 [38:33<02:02,  4.49it/s]
                                                     

 95%|█████████▌| 10516/11066 [38:33<02:02,  4.49it/s]
 95%|█████████▌| 10517/11066 [38:33<02:02,  4.49it/s]
                                                     

 95%|█████████▌| 10517/11066 [38:33<02:02,  4.49it/s]
 95%|█████████▌| 10518/11066 [38:34<02:01,  4.50it/s]
                                                     

 95%|█████████▌| 10518/11066 [38:34<02:01,  4.50it/s]
 95%|█████████▌| 10519/11066 [38:34<02:01,  4.50it/s]
                                                     

 95%|█████████▌| 10519/11066 [38:34<02:01,  4.50it/s]
 95%|█████████▌| 10520/11066 [38:34<02:01,  4.50it/s]
                                                     

 95%|█████████▌| 10520/11066 [38:34<02:01,  4.50it/s]
 95%|█████████▌| 10521/11066 [38:34<02:01,  4.50it/s]
                                                     

 95%|█████████▌| 10521/11066 [38:34<02:01,  4.50it/s]
 95%|█████████▌| 10522/11066 [38:34<02:00,  4.50it/s]
                                                     

 95%|█████████▌| 10522/11066 [38:34<02:00,  4.50it/s]
 95%|█████████▌| 10523/11066 [38:35<02:00,  4.50it/s]
                                                     

 95%|█████████▌| 10523/11066 [38:35<02:00,  4.50it/s]
 95%|█████████▌| 10524/11066 [38:35<02:00,  4.51it/s]
                                                     

 95%|█████████▌| 10524/11066 [38:35<02:00,  4.51it/s]
 95%|█████████▌| 10525/11066 [38:35<02:00,  4.50it/s]
                                                     

 95%|█████████▌| 10525/11066 [38:35<02:00,  4.50it/s]
 95%|█████████▌| 10526/11066 [38:35<01:59,  4.50it/s]
                                                     

 95%|█████████▌| 10526/11066 [38:35<01:59,  4.50it/s]
 95%|█████████▌| 10527/11066 [38:36<01:59,  4.50it/s]
                                                     

 95%|█████████▌| 10527/11066 [38:36<01:59,  4.50it/s]
 95%|█████████▌| 10528/11066 [38:36<01:59,  4.50it/s]
                                                     

 95%|█████████▌| 10528/11066 [38:36<01:59,  4.50it/s]
 95%|█████████▌| 10529/11066 [38:36<01:59,  4.50it/s]
                                                     

 95%|█████████▌| 10529/11066 [38:36<01:59,  4.50it/s]
 95%|█████████▌| 10530/11066 [38:36<01:59,  4.50it/s]
                                                     

 95%|█████████▌| 10530/11066 [38:36<01:59,  4.50it/s]
 95%|█████████▌| 10531/11066 [38:36<01:58,  4.50it/s]
                                                     

 95%|█████████▌| 10531/11066 [38:36<01:58,  4.50it/s]
 95%|█████████▌| 10532/11066 [38:37<01:58,  4.50it/s]
                                                     

 95%|█████████▌| 10532/11066 [38:37<01:58,  4.50it/s]
 95%|█████████▌| 10533/11066 [38:37<01:58,  4.51it/s]
                                                     

 95%|█████████▌| 10533/11066 [38:37<01:58,  4.51it/s]
 95%|█████████▌| 10534/11066 [38:37<01:58,  4.50it/s]
                                                     

 95%|█████████▌| 10534/11066 [38:37<01:58,  4.50it/s]
 95%|█████████▌| 10535/11066 [38:37<01:58,  4.50it/s]
                                                     

 95%|█████████▌| 10535/11066 [38:37<01:58,  4.50it/s]
 95%|█████████▌| 10536/11066 [38:38<01:57,  4.50it/s]
                                                     

 95%|█████████▌| 10536/11066 [38:38<01:57,  4.50it/s]
 95%|█████████▌| 10537/11066 [38:38<01:57,  4.50it/s]
                                                     

 95%|█████████▌| 10537/11066 [38:38<01:57,  4.50it/s]
 95%|█████████▌| 10538/11066 [38:38<01:57,  4.50it/s]
                                                     

 95%|█████████▌| 10538/11066 [38:38<01:57,  4.50it/s]
 95%|█████████▌| 10539/11066 [38:38<01:57,  4.50it/s]
                                                     

 95%|█████████▌| 10539/11066 [38:38<01:57,  4.50it/s]
 95%|█████████▌| 10540/11066 [38:38<01:56,  4.51it/s]
                                                     

 95%|█████████▌| 10540/11066 [38:38<01:56,  4.51it/s]
 95%|█████████▌| 10541/11066 [38:39<01:56,  4.51it/s]
                                                     

 95%|█████████▌| 10541/11066 [38:39<01:56,  4.51it/s]
 95%|█████████▌| 10542/11066 [38:39<01:56,  4.51it/s]
                                                     

 95%|█████████▌| 10542/11066 [38:39<01:56,  4.51it/s]
 95%|█████████▌| 10543/11066 [38:39<01:56,  4.51it/s]
                                                     

 95%|█████████▌| 10543/11066 [38:39<01:56,  4.51it/s]
 95%|█████████▌| 10544/11066 [38:39<01:55,  4.50it/s]
                                                     

 95%|█████████▌| 10544/11066 [38:39<01:55,  4.50it/s]
 95%|█████████▌| 10545/11066 [38:40<01:55,  4.50it/s]
                                                     

 95%|█████████▌| 10545/11066 [38:40<01:55,  4.50it/s]
 95%|█████████▌| 10546/11066 [38:40<01:55,  4.50it/s]
                                                     

 95%|█████████▌| 10546/11066 [38:40<01:55,  4.50it/s]
 95%|█████████▌| 10547/11066 [38:40<01:55,  4.50it/s]
                                                     

 95%|█████████▌| 10547/11066 [38:40<01:55,  4.50it/s]
 95%|█████████▌| 10548/11066 [38:40<01:55,  4.50it/s]
                                                     

 95%|█████████▌| 10548/11066 [38:40<01:55,  4.50it/s]
 95%|█████████▌| 10549/11066 [38:40<01:54,  4.50it/s]
                                                     

 95%|█████████▌| 10549/11066 [38:40<01:54,  4.50it/s]
 95%|█████████▌| 10550/11066 [38:41<01:54,  4.50it/s]
                                                     

 95%|█████████▌| 10550/11066 [38:41<01:54,  4.50it/s]
 95%|█████████▌| 10551/11066 [38:41<01:54,  4.50it/s]
                                                     

 95%|█████████▌| 10551/11066 [38:41<01:54,  4.50it/s]
 95%|█████████▌| 10552/11066 [38:41<01:54,  4.50it/s]
                                                     

 95%|█████████▌| 10552/11066 [38:41<01:54,  4.50it/s]
 95%|█████████▌| 10553/11066 [38:41<01:53,  4.50it/s]
                                                     

 95%|█████████▌| 10553/11066 [38:41<01:53,  4.50it/s]
 95%|█████████▌| 10554/11066 [38:42<01:53,  4.50it/s]
                                                     

 95%|█████████▌| 10554/11066 [38:42<01:53,  4.50it/s]
 95%|█████████▌| 10555/11066 [38:42<01:53,  4.51it/s]
                                                     

 95%|█████████▌| 10555/11066 [38:42<01:53,  4.51it/s]
 95%|█████████▌| 10556/11066 [38:42<01:53,  4.50it/s]
                                                     

 95%|█████████▌| 10556/11066 [38:42<01:53,  4.50it/s]
 95%|█████████▌| 10557/11066 [38:42<01:52,  4.51it/s]
                                                     

 95%|█████████▌| 10557/11066 [38:42<01:52,  4.51it/s]
 95%|█████████▌| 10558/11066 [38:42<01:52,  4.50it/s]
                                                     

 95%|█████████▌| 10558/11066 [38:42<01:52,  4.50it/s]
 95%|█████████▌| 10559/11066 [38:43<01:52,  4.51it/s]
                                                     

 95%|█████████▌| 10559/11066 [38:43<01:52,  4.51it/s]
 95%|█████████▌| 10560/11066 [38:43<01:52,  4.51it/s]
                                                     

 95%|█████████▌| 10560/11066 [38:43<01:52,  4.51it/s]
 95%|█████████▌| 10561/11066 [38:43<01:49,  4.59it/s]
                                                     

 95%|█████████▌| 10561/11066 [38:43<01:49,  4.59it/s]
 95%|█████████▌| 10562/11066 [38:43<01:50,  4.55it/s]
                                                     

 95%|█████████▌| 10562/11066 [38:43<01:50,  4.55it/s]
 95%|█████████▌| 10563/11066 [38:43<01:50,  4.55it/s]
                                                     

 95%|█████████▌| 10563/11066 [38:43<01:50,  4.55it/s]
 95%|█████████▌| 10564/11066 [38:44<01:50,  4.56it/s]
                                                     

 95%|█████████▌| 10564/11066 [38:44<01:50,  4.56it/s]
 95%|█████████▌| 10565/11066 [38:44<01:49,  4.59it/s]
                                                     

 95%|█████████▌| 10565/11066 [38:44<01:49,  4.59it/s]
 95%|█████████▌| 10566/11066 [38:44<01:49,  4.55it/s]
                                                     

 95%|█████████▌| 10566/11066 [38:44<01:49,  4.55it/s]
 95%|█████████▌| 10567/11066 [38:44<01:49,  4.57it/s]
                                                     

 95%|█████████▌| 10567/11066 [38:44<01:49,  4.57it/s]
 95%|█████████▌| 10568/11066 [38:45<01:49,  4.57it/s]
                                                     

 95%|█████████▌| 10568/11066 [38:45<01:49,  4.57it/s]
 96%|█████████▌| 10569/11066 [38:45<01:48,  4.58it/s]
                                                     

 96%|█████████▌| 10569/11066 [38:45<01:48,  4.58it/s]
 96%|█████████▌| 10570/11066 [38:45<01:49,  4.55it/s]
                                                     

 96%|█████████▌| 10570/11066 [38:45<01:49,  4.55it/s]
 96%|█████████▌| 10571/11066 [38:45<01:49,  4.53it/s]
                                                     

 96%|█████████▌| 10571/11066 [38:45<01:49,  4.53it/s]
 96%|█████████▌| 10572/11066 [38:45<01:48,  4.55it/s]
                                                     

 96%|█████████▌| 10572/11066 [38:45<01:48,  4.55it/s]
 96%|█████████▌| 10573/11066 [38:46<01:47,  4.59it/s]
                                                     

 96%|█████████▌| 10573/11066 [38:46<01:47,  4.59it/s]
 96%|█████████▌| 10574/11066 [38:46<01:47,  4.59it/s]
                                                     

 96%|█████████▌| 10574/11066 [38:46<01:47,  4.59it/s]
 96%|█████████▌| 10575/11066 [38:46<01:45,  4.64it/s]
                                                     

 96%|█████████▌| 10575/11066 [38:46<01:45,  4.64it/s]
 96%|█████████▌| 10576/11066 [38:46<01:45,  4.65it/s]
                                                     

 96%|█████████▌| 10576/11066 [38:46<01:45,  4.65it/s]
 96%|█████████▌| 10577/11066 [38:47<01:46,  4.59it/s]
                                                     

 96%|█████████▌| 10577/11066 [38:47<01:46,  4.59it/s]
 96%|█████████▌| 10578/11066 [38:47<01:47,  4.54it/s]
                                                     

 96%|█████████▌| 10578/11066 [38:47<01:47,  4.54it/s]
 96%|█████████▌| 10579/11066 [38:47<01:46,  4.56it/s]
                                                     

 96%|█████████▌| 10579/11066 [38:47<01:46,  4.56it/s]
 96%|█████████▌| 10580/11066 [38:47<01:47,  4.53it/s]
                                                     

 96%|█████████▌| 10580/11066 [38:47<01:47,  4.53it/s]
 96%|█████████▌| 10581/11066 [38:47<01:46,  4.55it/s]
                                                     

 96%|█████████▌| 10581/11066 [38:47<01:46,  4.55it/s]
 96%|█████████▌| 10582/11066 [38:48<01:45,  4.57it/s]
                                                     

 96%|█████████▌| 10582/11066 [38:48<01:45,  4.57it/s]
 96%|█████████▌| 10583/11066 [38:48<01:44,  4.60it/s]
                                                     

 96%|█████████▌| 10583/11066 [38:48<01:44,  4.60it/s]
 96%|█████████▌| 10584/11066 [38:48<01:45,  4.56it/s]
                                                     

 96%|█████████▌| 10584/11066 [38:48<01:45,  4.56it/s]
 96%|█████████▌| 10585/11066 [38:48<01:45,  4.57it/s]
                                                     

 96%|█████████▌| 10585/11066 [38:48<01:45,  4.57it/s]
 96%|█████████▌| 10586/11066 [38:49<01:45,  4.54it/s]
                                                     

 96%|█████████▌| 10586/11066 [38:49<01:45,  4.54it/s]
 96%|█████████▌| 10587/11066 [38:49<01:45,  4.55it/s]
                                                     

 96%|█████████▌| 10587/11066 [38:49<01:45,  4.55it/s]
 96%|█████████▌| 10588/11066 [38:49<01:44,  4.56it/s]
                                                     

 96%|█████████▌| 10588/11066 [38:49<01:44,  4.56it/s]
 96%|█████████▌| 10589/11066 [38:49<01:45,  4.53it/s]
                                                     

 96%|█████████▌| 10589/11066 [38:49<01:45,  4.53it/s]
 96%|█████████▌| 10590/11066 [38:49<01:44,  4.56it/s]
                                                     

 96%|█████████▌| 10590/11066 [38:49<01:44,  4.56it/s]
 96%|█████████▌| 10591/11066 [38:50<01:43,  4.57it/s]
                                                     

 96%|█████████▌| 10591/11066 [38:50<01:43,  4.57it/s]
 96%|█████████▌| 10592/11066 [38:50<01:43,  4.59it/s]
                                                     

 96%|█████████▌| 10592/11066 [38:50<01:43,  4.59it/s]
 96%|█████████▌| 10593/11066 [38:50<01:42,  4.62it/s]
                                                     

 96%|█████████▌| 10593/11066 [38:50<01:42,  4.62it/s]
 96%|█████████▌| 10594/11066 [38:50<01:43,  4.57it/s]
                                                     

 96%|█████████▌| 10594/11066 [38:50<01:43,  4.57it/s]
 96%|█████████▌| 10595/11066 [38:50<01:42,  4.58it/s]
                                                     

 96%|█████████▌| 10595/11066 [38:50<01:42,  4.58it/s]
 96%|█████████▌| 10596/11066 [38:51<01:43,  4.55it/s]
                                                     

 96%|█████████▌| 10596/11066 [38:51<01:43,  4.55it/s]
 96%|█████████▌| 10597/11066 [38:51<01:42,  4.59it/s]
                                                     
{'loss': 0.9331, 'learning_rate': 1.5778058919212e-06, 'epoch': 1.89}
{'loss': 0.7206, 'learning_rate': 1.5750948852340502e-06, 'epoch': 1.89}
{'loss': 0.5098, 'learning_rate': 1.5723838785469005e-06, 'epoch': 1.9}
{'loss': 0.8802, 'learning_rate': 1.5696728718597507e-06, 'epoch': 1.9}
{'loss': 0.4244, 'learning_rate': 1.5669618651726008e-06, 'epoch': 1.9}
{'loss': 0.4698, 'learning_rate': 1.564250858485451e-06, 'epoch': 1.9}
{'loss': 0.7666, 'learning_rate': 1.561539851798301e-06, 'epoch': 1.9}
{'loss': 0.5374, 'learning_rate': 1.5588288451111514e-06, 'epoch': 1.9}
{'loss': 0.5666, 'learning_rate': 1.5561178384240015e-06, 'epoch': 1.9}
{'loss': 0.9331, 'learning_rate': 1.5534068317368517e-06, 'epoch': 1.9}
{'loss': 1.0123, 'learning_rate': 1.5506958250497018e-06, 'epoch': 1.9}
{'loss': 0.5551, 'learning_rate': 1.547984818362552e-06, 'epoch': 1.9}
{'loss': 1.0967, 'learning_rate': 1.5452738116754023e-06, 'epoch': 1.9}
{'loss': 0.6481, 'learning_rate': 1.5425628049882524e-06, 'epoch': 1.9}
{'loss': 0.479, 'learning_rate': 1.5398517983011026e-06, 'epoch': 1.9}
{'loss': 0.9286, 'learning_rate': 1.5371407916139527e-06, 'epoch': 1.9}
{'loss': 0.6357, 'learning_rate': 1.5344297849268028e-06, 'epoch': 1.9}
{'loss': 1.0608, 'learning_rate': 1.5317187782396532e-06, 'epoch': 1.9}
{'loss': 1.2448, 'learning_rate': 1.5290077715525033e-06, 'epoch': 1.9}
{'loss': 0.2996, 'learning_rate': 1.5262967648653534e-06, 'epoch': 1.9}
{'loss': 0.8536, 'learning_rate': 1.5235857581782036e-06, 'epoch': 1.9}
{'loss': 0.6186, 'learning_rate': 1.5208747514910537e-06, 'epoch': 1.9}
{'loss': 0.8747, 'learning_rate': 1.518163744803904e-06, 'epoch': 1.9}
{'loss': 0.5219, 'learning_rate': 1.5154527381167542e-06, 'epoch': 1.9}
{'loss': 0.8289, 'learning_rate': 1.5127417314296043e-06, 'epoch': 1.9}
{'loss': 0.5836, 'learning_rate': 1.5100307247424545e-06, 'epoch': 1.9}
{'loss': 0.2553, 'learning_rate': 1.5073197180553046e-06, 'epoch': 1.9}
{'loss': 0.544, 'learning_rate': 1.5046087113681547e-06, 'epoch': 1.9}
{'loss': 0.2638, 'learning_rate': 1.501897704681005e-06, 'epoch': 1.9}
{'loss': 0.5012, 'learning_rate': 1.4991866979938552e-06, 'epoch': 1.9}
{'loss': 1.104, 'learning_rate': 1.4964756913067053e-06, 'epoch': 1.9}
{'loss': 0.4988, 'learning_rate': 1.4937646846195555e-06, 'epoch': 1.9}
{'loss': 0.8388, 'learning_rate': 1.4910536779324056e-06, 'epoch': 1.9}
{'loss': 0.9396, 'learning_rate': 1.488342671245256e-06, 'epoch': 1.9}
{'loss': 0.9373, 'learning_rate': 1.485631664558106e-06, 'epoch': 1.9}
{'loss': 0.8816, 'learning_rate': 1.4829206578709562e-06, 'epoch': 1.9}
{'loss': 0.4015, 'learning_rate': 1.4802096511838061e-06, 'epoch': 1.9}
{'loss': 0.6419, 'learning_rate': 1.4774986444966563e-06, 'epoch': 1.9}
{'loss': 0.6144, 'learning_rate': 1.4747876378095066e-06, 'epoch': 1.9}
{'loss': 0.4473, 'learning_rate': 1.4720766311223568e-06, 'epoch': 1.9}
{'loss': 0.7284, 'learning_rate': 1.469365624435207e-06, 'epoch': 1.9}
{'loss': 0.3594, 'learning_rate': 1.466654617748057e-06, 'epoch': 1.9}
{'loss': 0.9663, 'learning_rate': 1.4639436110609072e-06, 'epoch': 1.9}
{'loss': 0.6046, 'learning_rate': 1.4612326043737575e-06, 'epoch': 1.9}
{'loss': 0.7802, 'learning_rate': 1.4585215976866076e-06, 'epoch': 1.9}
{'loss': 0.4117, 'learning_rate': 1.4558105909994578e-06, 'epoch': 1.9}
{'loss': 0.9009, 'learning_rate': 1.453099584312308e-06, 'epoch': 1.9}
{'loss': 0.5827, 'learning_rate': 1.450388577625158e-06, 'epoch': 1.9}
{'loss': 0.8169, 'learning_rate': 1.4476775709380084e-06, 'epoch': 1.9}
{'loss': 0.975, 'learning_rate': 1.4449665642508585e-06, 'epoch': 1.9}
{'loss': 0.3795, 'learning_rate': 1.4422555575637087e-06, 'epoch': 1.9}
{'loss': 0.8887, 'learning_rate': 1.4395445508765588e-06, 'epoch': 1.9}
{'loss': 1.1393, 'learning_rate': 1.436833544189409e-06, 'epoch': 1.9}
{'loss': 0.6201, 'learning_rate': 1.434122537502259e-06, 'epoch': 1.9}
{'loss': 0.8955, 'learning_rate': 1.4314115308151094e-06, 'epoch': 1.9}
{'loss': 0.8106, 'learning_rate': 1.4287005241279595e-06, 'epoch': 1.9}
{'loss': 0.4805, 'learning_rate': 1.4259895174408097e-06, 'epoch': 1.9}
{'loss': 0.5858, 'learning_rate': 1.4232785107536598e-06, 'epoch': 1.91}
{'loss': 0.533, 'learning_rate': 1.42056750406651e-06, 'epoch': 1.91}
{'loss': 0.5374, 'learning_rate': 1.4178564973793603e-06, 'epoch': 1.91}
{'loss': 0.8659, 'learning_rate': 1.4151454906922104e-06, 'epoch': 1.91}
{'loss': 0.302, 'learning_rate': 1.4124344840050606e-06, 'epoch': 1.91}
{'loss': 0.9551, 'learning_rate': 1.4097234773179107e-06, 'epoch': 1.91}
{'loss': 0.5668, 'learning_rate': 1.4070124706307608e-06, 'epoch': 1.91}
{'loss': 0.5539, 'learning_rate': 1.4043014639436112e-06, 'epoch': 1.91}
{'loss': 1.0328, 'learning_rate': 1.4015904572564613e-06, 'epoch': 1.91}
{'loss': 0.5221, 'learning_rate': 1.3988794505693114e-06, 'epoch': 1.91}
{'loss': 1.0415, 'learning_rate': 1.3961684438821616e-06, 'epoch': 1.91}
{'loss': 0.8335, 'learning_rate': 1.3934574371950117e-06, 'epoch': 1.91}
{'loss': 0.6166, 'learning_rate': 1.390746430507862e-06, 'epoch': 1.91}
{'loss': 0.6832, 'learning_rate': 1.3880354238207122e-06, 'epoch': 1.91}
{'loss': 0.5536, 'learning_rate': 1.3853244171335623e-06, 'epoch': 1.91}
{'loss': 1.0655, 'learning_rate': 1.3826134104464125e-06, 'epoch': 1.91}
{'loss': 0.8088, 'learning_rate': 1.3799024037592626e-06, 'epoch': 1.91}
{'loss': 0.9028, 'learning_rate': 1.3771913970721127e-06, 'epoch': 1.91}
{'loss': 0.6991, 'learning_rate': 1.374480390384963e-06, 'epoch': 1.91}
{'loss': 0.8549, 'learning_rate': 1.3717693836978132e-06, 'epoch': 1.91}
{'loss': 0.4908, 'learning_rate': 1.3690583770106633e-06, 'epoch': 1.91}
{'loss': 0.6372, 'learning_rate': 1.3663473703235135e-06, 'epoch': 1.91}
{'loss': 0.797, 'learning_rate': 1.3636363636363636e-06, 'epoch': 1.91}
{'loss': 0.5636, 'learning_rate': 1.360925356949214e-06, 'epoch': 1.91}
{'loss': 0.7699, 'learning_rate': 1.358214350262064e-06, 'epoch': 1.91}
{'loss': 0.6549, 'learning_rate': 1.3555033435749142e-06, 'epoch': 1.91}
{'loss': 0.7668, 'learning_rate': 1.3527923368877644e-06, 'epoch': 1.91}
{'loss': 0.4243, 'learning_rate': 1.3500813302006145e-06, 'epoch': 1.91}
{'loss': 0.3843, 'learning_rate': 1.3473703235134648e-06, 'epoch': 1.91}
{'loss': 0.6633, 'learning_rate': 1.344659316826315e-06, 'epoch': 1.91}
{'loss': 0.4826, 'learning_rate': 1.3419483101391651e-06, 'epoch': 1.91}
{'loss': 0.9356, 'learning_rate': 1.3392373034520152e-06, 'epoch': 1.91}
{'loss': 0.7392, 'learning_rate': 1.3365262967648654e-06, 'epoch': 1.91}
{'loss': 0.4416, 'learning_rate': 1.3338152900777157e-06, 'epoch': 1.91}
{'loss': 0.8884, 'learning_rate': 1.3311042833905659e-06, 'epoch': 1.91}
{'loss': 0.5443, 'learning_rate': 1.328393276703416e-06, 'epoch': 1.91}
{'loss': 0.4771, 'learning_rate': 1.3256822700162661e-06, 'epoch': 1.91}
{'loss': 0.4661, 'learning_rate': 1.3229712633291163e-06, 'epoch': 1.91}
{'loss': 0.623, 'learning_rate': 1.3202602566419666e-06, 'epoch': 1.91}
{'loss': 0.5801, 'learning_rate': 1.3175492499548167e-06, 'epoch': 1.91}
{'loss': 1.3424, 'learning_rate': 1.3148382432676669e-06, 'epoch': 1.91}
{'loss': 0.4303, 'learning_rate': 1.312127236580517e-06, 'epoch': 1.91}
{'loss': 1.2358, 'learning_rate': 1.3094162298933671e-06, 'epoch': 1.91}
{'loss': 1.0214, 'learning_rate': 1.306705223206217e-06, 'epoch': 1.91}
{'loss': 0.7718, 'learning_rate': 1.3039942165190674e-06, 'epoch': 1.91}
{'loss': 1.1999, 'learning_rate': 1.3012832098319175e-06, 'epoch': 1.91}
{'loss': 0.7123, 'learning_rate': 1.2985722031447677e-06, 'epoch': 1.91}
{'loss': 0.7926, 'learning_rate': 1.2958611964576178e-06, 'epoch': 1.91}
{'loss': 1.3456, 'learning_rate': 1.293150189770468e-06, 'epoch': 1.91}
{'loss': 0.2802, 'learning_rate': 1.2904391830833183e-06, 'epoch': 1.91}
{'loss': 1.2769, 'learning_rate': 1.2877281763961684e-06, 'epoch': 1.91}
{'loss': 0.559, 'learning_rate': 1.2850171697090186e-06, 'epoch': 1.91}
{'loss': 0.7939, 'learning_rate': 1.2823061630218687e-06, 'epoch': 1.91}
{'loss': 0.8965, 'learning_rate': 1.2795951563347188e-06, 'epoch': 1.91}
{'loss': 0.3305, 'learning_rate': 1.2768841496475692e-06, 'epoch': 1.91}
{'loss': 1.4532, 'learning_rate': 1.2741731429604193e-06, 'epoch': 1.92}

 96%|█████████▌| 10597/11066 [38:51<01:42,  4.59it/s]
 96%|█████████▌| 10598/11066 [38:51<01:42,  4.54it/s]
                                                     

 96%|█████████▌| 10598/11066 [38:51<01:42,  4.54it/s]
 96%|█████████▌| 10599/11066 [38:51<01:43,  4.53it/s]
                                                     

 96%|█████████▌| 10599/11066 [38:51<01:43,  4.53it/s]
 96%|█████████▌| 10600/11066 [38:52<01:43,  4.51it/s]
                                                     

 96%|█████████▌| 10600/11066 [38:52<01:43,  4.51it/s]
 96%|█████████▌| 10601/11066 [38:52<01:43,  4.51it/s]
                                                     

 96%|█████████▌| 10601/11066 [38:52<01:43,  4.51it/s]
 96%|█████████▌| 10602/11066 [38:52<01:43,  4.50it/s]
                                                     

 96%|█████████▌| 10602/11066 [38:52<01:43,  4.50it/s]
 96%|█████████▌| 10603/11066 [38:52<01:43,  4.45it/s]
                                                     

 96%|█████████▌| 10603/11066 [38:52<01:43,  4.45it/s]
 96%|█████████▌| 10604/11066 [38:52<01:42,  4.49it/s]
                                                     

 96%|█████████▌| 10604/11066 [38:52<01:42,  4.49it/s]
 96%|█████████▌| 10605/11066 [38:53<01:40,  4.57it/s]
                                                     

 96%|█████████▌| 10605/11066 [38:53<01:40,  4.57it/s]
 96%|█████████▌| 10606/11066 [38:53<01:41,  4.55it/s]
                                                     

 96%|█████████▌| 10606/11066 [38:53<01:41,  4.55it/s]
 96%|█████████▌| 10607/11066 [38:53<01:41,  4.54it/s]
                                                     

 96%|█████████▌| 10607/11066 [38:53<01:41,  4.54it/s]
 96%|█████████▌| 10608/11066 [38:53<01:41,  4.53it/s]
                                                     

 96%|█████████▌| 10608/11066 [38:53<01:41,  4.53it/s]
 96%|█████████▌| 10609/11066 [38:54<01:40,  4.55it/s]
                                                     

 96%|█████████▌| 10609/11066 [38:54<01:40,  4.55it/s]
 96%|█████████▌| 10610/11066 [38:54<01:39,  4.58it/s]
                                                     

 96%|█████████▌| 10610/11066 [38:54<01:39,  4.58it/s]
 96%|█████████▌| 10611/11066 [38:54<01:39,  4.58it/s]
                                                     

 96%|█████████▌| 10611/11066 [38:54<01:39,  4.58it/s]
 96%|█████████▌| 10612/11066 [38:54<01:42,  4.43it/s]
                                                     

 96%|█████████▌| 10612/11066 [38:54<01:42,  4.43it/s]
 96%|█████████▌| 10613/11066 [38:54<01:43,  4.39it/s]
                                                     

 96%|█████████▌| 10613/11066 [38:54<01:43,  4.39it/s]
 96%|█████████▌| 10614/11066 [38:55<01:42,  4.40it/s]
                                                     

 96%|█████████▌| 10614/11066 [38:55<01:42,  4.40it/s]
 96%|█████████▌| 10615/11066 [38:55<01:43,  4.37it/s]
                                                     

 96%|█████████▌| 10615/11066 [38:55<01:43,  4.37it/s]
 96%|█████████▌| 10616/11066 [38:55<01:44,  4.30it/s]
                                                     

 96%|█████████▌| 10616/11066 [38:55<01:44,  4.30it/s]
 96%|█████████▌| 10617/11066 [38:55<01:43,  4.33it/s]
                                                     

 96%|█████████▌| 10617/11066 [38:55<01:43,  4.33it/s]
 96%|█████████▌| 10618/11066 [38:56<01:42,  4.38it/s]
                                                     

 96%|█████████▌| 10618/11066 [38:56<01:42,  4.38it/s]
 96%|█████████▌| 10619/11066 [38:56<01:42,  4.36it/s]
                                                     

 96%|█████████▌| 10619/11066 [38:56<01:42,  4.36it/s]
 96%|█████████▌| 10620/11066 [38:56<01:41,  4.39it/s]
                                                     

 96%|█████████▌| 10620/11066 [38:56<01:41,  4.39it/s]
 96%|█████████▌| 10621/11066 [38:56<01:39,  4.48it/s]
                                                     

 96%|█████████▌| 10621/11066 [38:56<01:39,  4.48it/s]
 96%|█████████▌| 10622/11066 [38:57<01:38,  4.52it/s]
                                                     

 96%|█████████▌| 10622/11066 [38:57<01:38,  4.52it/s]
 96%|█████████▌| 10623/11066 [38:57<01:38,  4.49it/s]
                                                     

 96%|█████████▌| 10623/11066 [38:57<01:38,  4.49it/s]
 96%|█████████▌| 10624/11066 [38:57<01:37,  4.52it/s]
                                                     

 96%|█████████▌| 10624/11066 [38:57<01:37,  4.52it/s]
 96%|█████████▌| 10625/11066 [38:57<01:37,  4.54it/s]
                                                     

 96%|█████████▌| 10625/11066 [38:57<01:37,  4.54it/s]
 96%|█████████▌| 10626/11066 [38:57<01:36,  4.56it/s]
                                                     

 96%|█████████▌| 10626/11066 [38:57<01:36,  4.56it/s]
 96%|█████████▌| 10627/11066 [38:58<01:35,  4.60it/s]
                                                     

 96%|█████████▌| 10627/11066 [38:58<01:35,  4.60it/s]
 96%|█████████▌| 10628/11066 [38:58<01:35,  4.59it/s]
                                                     

 96%|█████████▌| 10628/11066 [38:58<01:35,  4.59it/s]
 96%|█████████▌| 10629/11066 [38:58<01:34,  4.60it/s]
                                                     

 96%|█████████▌| 10629/11066 [38:58<01:34,  4.60it/s]
 96%|█████████▌| 10630/11066 [38:58<01:35,  4.55it/s]
                                                     

 96%|█████████▌| 10630/11066 [38:58<01:35,  4.55it/s]
 96%|█████████▌| 10631/11066 [38:58<01:36,  4.53it/s]
                                                     

 96%|█████████▌| 10631/11066 [38:58<01:36,  4.53it/s]
 96%|█████████▌| 10632/11066 [38:59<01:36,  4.52it/s]
                                                     

 96%|█████████▌| 10632/11066 [38:59<01:36,  4.52it/s]
 96%|█████████▌| 10633/11066 [38:59<01:35,  4.51it/s]
                                                     

 96%|█████████▌| 10633/11066 [38:59<01:35,  4.51it/s]
 96%|█████████▌| 10634/11066 [38:59<01:35,  4.51it/s]
                                                     

 96%|█████████▌| 10634/11066 [38:59<01:35,  4.51it/s]
 96%|█████████▌| 10635/11066 [38:59<01:34,  4.54it/s]
                                                     

 96%|█████████▌| 10635/11066 [38:59<01:34,  4.54it/s]
 96%|█████████▌| 10636/11066 [39:00<01:33,  4.58it/s]
                                                     

 96%|█████████▌| 10636/11066 [39:00<01:33,  4.58it/s]
 96%|█████████▌| 10637/11066 [39:00<01:34,  4.54it/s]
                                                     

 96%|█████████▌| 10637/11066 [39:00<01:34,  4.54it/s]
 96%|█████████▌| 10638/11066 [39:00<01:34,  4.52it/s]
                                                     

 96%|█████████▌| 10638/11066 [39:00<01:34,  4.52it/s]
 96%|█████████▌| 10639/11066 [39:00<01:33,  4.57it/s]
                                                     

 96%|█████████▌| 10639/11066 [39:00<01:33,  4.57it/s]
 96%|█████████▌| 10640/11066 [39:00<01:32,  4.58it/s]
                                                     

 96%|█████████▌| 10640/11066 [39:00<01:32,  4.58it/s]
 96%|█████████▌| 10641/11066 [39:01<01:32,  4.57it/s]
                                                     

 96%|█████████▌| 10641/11066 [39:01<01:32,  4.57it/s]
 96%|█████████▌| 10642/11066 [39:01<01:32,  4.59it/s]
                                                     

 96%|█████████▌| 10642/11066 [39:01<01:32,  4.59it/s]
 96%|█████████▌| 10643/11066 [39:01<01:33,  4.54it/s]
                                                     

 96%|█████████▌| 10643/11066 [39:01<01:33,  4.54it/s]
 96%|█████████▌| 10644/11066 [39:01<01:32,  4.58it/s]
                                                     

 96%|█████████▌| 10644/11066 [39:01<01:32,  4.58it/s]
 96%|█████████▌| 10645/11066 [39:02<01:31,  4.59it/s]
                                                     

 96%|█████████▌| 10645/11066 [39:02<01:31,  4.59it/s]
 96%|█████████▌| 10646/11066 [39:02<01:32,  4.55it/s]
                                                     

 96%|█████████▌| 10646/11066 [39:02<01:32,  4.55it/s]
 96%|█████████▌| 10647/11066 [39:02<01:32,  4.52it/s]
                                                     

 96%|█████████▌| 10647/11066 [39:02<01:32,  4.52it/s]
 96%|█████████▌| 10648/11066 [39:02<01:32,  4.52it/s]
                                                     

 96%|█████████▌| 10648/11066 [39:02<01:32,  4.52it/s]
 96%|█████████▌| 10649/11066 [39:02<01:31,  4.54it/s]
                                                     

 96%|█████████▌| 10649/11066 [39:02<01:31,  4.54it/s]
 96%|█████████▌| 10650/11066 [39:03<01:31,  4.54it/s]
                                                     

 96%|█████████▌| 10650/11066 [39:03<01:31,  4.54it/s]
 96%|█████████▌| 10651/11066 [39:03<01:30,  4.58it/s]
                                                     

 96%|█████████▌| 10651/11066 [39:03<01:30,  4.58it/s]
 96%|█████████▋| 10652/11066 [39:03<01:30,  4.57it/s]
                                                     

 96%|█████████▋| 10652/11066 [39:03<01:30,  4.57it/s]
 96%|█████████▋| 10653/11066 [39:03<01:29,  4.63it/s]
                                                     

 96%|█████████▋| 10653/11066 [39:03<01:29,  4.63it/s]
 96%|█████████▋| 10654/11066 [39:04<01:29,  4.62it/s]
                                                     

 96%|█████████▋| 10654/11066 [39:04<01:29,  4.62it/s]
 96%|█████████▋| 10655/11066 [39:04<01:29,  4.61it/s]
                                                     

 96%|█████████▋| 10655/11066 [39:04<01:29,  4.61it/s]
 96%|█████████▋| 10656/11066 [39:04<01:28,  4.62it/s]
                                                     

 96%|█████████▋| 10656/11066 [39:04<01:28,  4.62it/s]
 96%|█████████▋| 10657/11066 [39:04<01:28,  4.62it/s]
                                                     

 96%|█████████▋| 10657/11066 [39:04<01:28,  4.62it/s]
 96%|█████████▋| 10658/11066 [39:04<01:28,  4.61it/s]
                                                     

 96%|█████████▋| 10658/11066 [39:04<01:28,  4.61it/s]
 96%|█████████▋| 10659/11066 [39:05<01:29,  4.55it/s]
                                                     

 96%|█████████▋| 10659/11066 [39:05<01:29,  4.55it/s]
 96%|█████████▋| 10660/11066 [39:05<01:29,  4.53it/s]
                                                     

 96%|█████████▋| 10660/11066 [39:05<01:29,  4.53it/s]
 96%|█████████▋| 10661/11066 [39:05<01:29,  4.52it/s]
                                                     

 96%|█████████▋| 10661/11066 [39:05<01:29,  4.52it/s]
 96%|█████████▋| 10662/11066 [39:05<01:29,  4.51it/s]
                                                     

 96%|█████████▋| 10662/11066 [39:05<01:29,  4.51it/s]
 96%|█████████▋| 10663/11066 [39:06<01:29,  4.51it/s]
                                                     

 96%|█████████▋| 10663/11066 [39:06<01:29,  4.51it/s]
 96%|█████████▋| 10664/11066 [39:06<01:29,  4.51it/s]
                                                     

 96%|█████████▋| 10664/11066 [39:06<01:29,  4.51it/s]
 96%|█████████▋| 10665/11066 [39:06<01:28,  4.51it/s]
                                                     

 96%|█████████▋| 10665/11066 [39:06<01:28,  4.51it/s]
 96%|█████████▋| 10666/11066 [39:06<01:28,  4.50it/s]
                                                     

 96%|█████████▋| 10666/11066 [39:06<01:28,  4.50it/s]
 96%|█████████▋| 10667/11066 [39:06<01:28,  4.50it/s]
                                                     

 96%|█████████▋| 10667/11066 [39:06<01:28,  4.50it/s]
 96%|█████████▋| 10668/11066 [39:07<01:28,  4.49it/s]
                                                     

 96%|█████████▋| 10668/11066 [39:07<01:28,  4.49it/s]
 96%|█████████▋| 10669/11066 [39:07<01:28,  4.49it/s]
                                                     

 96%|█████████▋| 10669/11066 [39:07<01:28,  4.49it/s]
 96%|█████████▋| 10670/11066 [39:07<01:28,  4.49it/s]
                                                     

 96%|█████████▋| 10670/11066 [39:07<01:28,  4.49it/s]
 96%|█████████▋| 10671/11066 [39:07<01:28,  4.48it/s]
                                                     

 96%|█████████▋| 10671/11066 [39:07<01:28,  4.48it/s]
 96%|█████████▋| 10672/11066 [39:08<01:26,  4.55it/s]
                                                     

 96%|█████████▋| 10672/11066 [39:08<01:26,  4.55it/s]
 96%|█████████▋| 10673/11066 [39:08<01:25,  4.59it/s]
                                                     

 96%|█████████▋| 10673/11066 [39:08<01:25,  4.59it/s]
 96%|█████████▋| 10674/11066 [39:08<01:24,  4.63it/s]
                                                     

 96%|█████████▋| 10674/11066 [39:08<01:24,  4.63it/s]
 96%|█████████▋| 10675/11066 [39:08<01:24,  4.63it/s]
                                                     

 96%|█████████▋| 10675/11066 [39:08<01:24,  4.63it/s]
 96%|█████████▋| 10676/11066 [39:08<01:23,  4.67it/s]
                                                     

 96%|█████████▋| 10676/11066 [39:08<01:23,  4.67it/s]
 96%|█████████▋| 10677/11066 [39:09<01:23,  4.65it/s]
                                                     

 96%|█████████▋| 10677/11066 [39:09<01:23,  4.65it/s]
 96%|█████████▋| 10678/11066 [39:09<01:23,  4.64it/s]
                                                     

 96%|█████████▋| 10678/11066 [39:09<01:23,  4.64it/s]
 97%|█████████▋| 10679/11066 [39:09<01:22,  4.67it/s]
                                                     

 97%|█████████▋| 10679/11066 [39:09<01:22,  4.67it/s]
 97%|█████████▋| 10680/11066 [39:09<01:22,  4.66it/s]
                                                     

 97%|█████████▋| 10680/11066 [39:09<01:22,  4.66it/s]
 97%|█████████▋| 10681/11066 [39:09<01:21,  4.70it/s]
                                                     

 97%|█████████▋| 10681/11066 [39:09<01:21,  4.70it/s]
 97%|█████████▋| 10682/11066 [39:10<01:21,  4.69it/s]
                                                     

 97%|█████████▋| 10682/11066 [39:10<01:21,  4.69it/s]
 97%|█████████▋| 10683/11066 [39:10<01:21,  4.70it/s]
                                                     

 97%|█████████▋| 10683/11066 [39:10<01:21,  4.70it/s]
 97%|█████████▋| 10684/11066 [39:10<01:21,  4.67it/s]
                                                     

 97%|█████████▋| 10684/11066 [39:10<01:21,  4.67it/s]
 97%|█████████▋| 10685/11066 [39:10<01:22,  4.60it/s]
                                                     

 97%|█████████▋| 10685/11066 [39:10<01:22,  4.60it/s]
 97%|█████████▋| 10686/11066 [39:11<01:22,  4.62it/s]
                                                     

 97%|█████████▋| 10686/11066 [39:11<01:22,  4.62it/s]
 97%|█████████▋| 10687/11066 [39:11<01:22,  4.58it/s]
                                                     

 97%|█████████▋| 10687/11066 [39:11<01:22,  4.58it/s]
 97%|█████████▋| 10688/11066 [39:11<01:21,  4.61it/s]
                                                     

 97%|█████████▋| 10688/11066 [39:11<01:21,  4.61it/s]
 97%|█████████▋| 10689/11066 [39:11<01:21,  4.61it/s]
                                                     

 97%|█████████▋| 10689/11066 [39:11<01:21,  4.61it/s]
 97%|█████████▋| 10690/11066 [39:11<01:21,  4.64it/s]
                                                     

 97%|█████████▋| 10690/11066 [39:11<01:21,  4.64it/s]
 97%|█████████▋| 10691/11066 [39:12<01:20,  4.66it/s]
                                                     

 97%|█████████▋| 10691/11066 [39:12<01:20,  4.66it/s]
 97%|█████████▋| 10692/11066 [39:12<01:21,  4.60it/s]
                                                     

 97%|█████████▋| 10692/11066 [39:12<01:21,  4.60it/s]
 97%|█████████▋| 10693/11066 [39:12<01:20,  4.64it/s]
                                                     

 97%|█████████▋| 10693/11066 [39:12<01:20,  4.64it/s]
 97%|█████████▋| 10694/11066 [39:12<01:19,  4.67it/s]
                                                     

 97%|█████████▋| 10694/11066 [39:12<01:19,  4.67it/s]
 97%|█████████▋| 10695/11066 [39:12<01:19,  4.68it/s]
                                                     

 97%|█████████▋| 10695/11066 [39:12<01:19,  4.68it/s]
 97%|█████████▋| 10696/11066 [39:13<01:18,  4.69it/s]
                                                     

 97%|█████████▋| 10696/11066 [39:13<01:18,  4.69it/s]
 97%|█████████▋| 10697/11066 [39:13<01:18,  4.70it/s]
                                                     

 97%|█████████▋| 10697/11066 [39:13<01:18,  4.70it/s]
 97%|█████████▋| 10698/11066 [39:13<01:18,  4.70it/s]
                                                     

 97%|█████████▋| 10698/11066 [39:13<01:18,  4.70it/s]
 97%|█████████▋| 10699/11066 [39:13<01:18,  4.70it/s]
                                                     

 97%|█████████▋| 10699/11066 [39:13<01:18,  4.70it/s]
 97%|█████████▋| 10700/11066 [39:14<01:17,  4.70it/s]
                                                     

 97%|█████████▋| 10700/11066 [39:14<01:17,  4.70it/s]
 97%|█████████▋| 10701/11066 [39:14<01:17,  4.70it/s]
                                                     

 97%|█████████▋| 10701/11066 [39:14<01:17,  4.70it/s]
 97%|█████████▋| 10702/11066 [39:14<01:17,  4.71it/s]
                                                     

 97%|█████████▋| 10702/11066 [39:14<01:17,  4.71it/s]
 97%|█████████▋| 10703/11066 [39:14<01:18,  4.65it/s]
                                                     

 97%|█████████▋| 10703/11066 [39:14<01:18,  4.65it/s]
 97%|█████████▋| 10704/11066 [39:14<01:17,  4.67it/s]
                                                     

 97%|█████████▋| 10704/11066 [39:14<01:17,  4.67it/s]
 97%|█████████▋| 10705/11066 [39:15<01:17,  4.69it/s]
                                                     

 97%|█████████▋| 10705/11066 [39:15<01:17,  4.69it/s]
 97%|█████████▋| 10706/11066 [39:15<01:17,  4.63it/s]
                                                     

 97%|█████████▋| 10706/11066 [39:15<01:17,  4.63it/s]
 97%|█████████▋| 10707/11066 [39:15<01:17,  4.65it/s]
                                                     

 97%|█████████▋| 10707/11066 [39:15<01:17,  4.65it/s]
 97%|█████████▋| 10708/11066 [39:15<01:17,  4.60it/s]
                                                     

 97%|█████████▋| 10708/11066 [39:15<01:17,  4.60it/s]
 97%|█████████▋| 10709/11066 [39:15<01:17,  4.62it/s]
                                                     
{'loss': 1.1457, 'learning_rate': 1.2714621362732694e-06, 'epoch': 1.92}
{'loss': 0.6433, 'learning_rate': 1.2687511295861196e-06, 'epoch': 1.92}
{'loss': 0.5456, 'learning_rate': 1.2660401228989697e-06, 'epoch': 1.92}
{'loss': 1.2682, 'learning_rate': 1.26332911621182e-06, 'epoch': 1.92}
{'loss': 0.661, 'learning_rate': 1.2606181095246702e-06, 'epoch': 1.92}
{'loss': 0.8911, 'learning_rate': 1.2579071028375203e-06, 'epoch': 1.92}
{'loss': 0.3676, 'learning_rate': 1.2551960961503705e-06, 'epoch': 1.92}
{'loss': 0.3337, 'learning_rate': 1.2524850894632206e-06, 'epoch': 1.92}
{'loss': 0.9288, 'learning_rate': 1.249774082776071e-06, 'epoch': 1.92}
{'loss': 0.4938, 'learning_rate': 1.247063076088921e-06, 'epoch': 1.92}
{'loss': 0.8888, 'learning_rate': 1.2443520694017712e-06, 'epoch': 1.92}
{'loss': 1.0016, 'learning_rate': 1.2416410627146213e-06, 'epoch': 1.92}
{'loss': 0.91, 'learning_rate': 1.2389300560274715e-06, 'epoch': 1.92}
{'loss': 0.4438, 'learning_rate': 1.2362190493403216e-06, 'epoch': 1.92}
{'loss': 0.5128, 'learning_rate': 1.233508042653172e-06, 'epoch': 1.92}
{'loss': 0.914, 'learning_rate': 1.230797035966022e-06, 'epoch': 1.92}
{'loss': 0.9649, 'learning_rate': 1.2280860292788722e-06, 'epoch': 1.92}
{'loss': 0.612, 'learning_rate': 1.2253750225917224e-06, 'epoch': 1.92}
{'loss': 0.4757, 'learning_rate': 1.2226640159045725e-06, 'epoch': 1.92}
{'loss': 0.6444, 'learning_rate': 1.2199530092174228e-06, 'epoch': 1.92}
{'loss': 0.6658, 'learning_rate': 1.217242002530273e-06, 'epoch': 1.92}
{'loss': 0.3485, 'learning_rate': 1.2145309958431231e-06, 'epoch': 1.92}
{'loss': 0.8744, 'learning_rate': 1.2118199891559733e-06, 'epoch': 1.92}
{'loss': 0.9037, 'learning_rate': 1.2091089824688234e-06, 'epoch': 1.92}
{'loss': 0.9285, 'learning_rate': 1.2063979757816737e-06, 'epoch': 1.92}
{'loss': 0.2973, 'learning_rate': 1.2036869690945239e-06, 'epoch': 1.92}
{'loss': 0.9977, 'learning_rate': 1.200975962407374e-06, 'epoch': 1.92}
{'loss': 0.8466, 'learning_rate': 1.1982649557202241e-06, 'epoch': 1.92}
{'loss': 0.5699, 'learning_rate': 1.1955539490330743e-06, 'epoch': 1.92}
{'loss': 0.3273, 'learning_rate': 1.1928429423459246e-06, 'epoch': 1.92}
{'loss': 0.9475, 'learning_rate': 1.1901319356587747e-06, 'epoch': 1.92}
{'loss': 0.694, 'learning_rate': 1.1874209289716249e-06, 'epoch': 1.92}
{'loss': 1.0804, 'learning_rate': 1.184709922284475e-06, 'epoch': 1.92}
{'loss': 0.5092, 'learning_rate': 1.1819989155973252e-06, 'epoch': 1.92}
{'loss': 1.2004, 'learning_rate': 1.1792879089101755e-06, 'epoch': 1.92}
{'loss': 0.3413, 'learning_rate': 1.1765769022230256e-06, 'epoch': 1.92}
{'loss': 0.6452, 'learning_rate': 1.1738658955358758e-06, 'epoch': 1.92}
{'loss': 0.8279, 'learning_rate': 1.171154888848726e-06, 'epoch': 1.92}
{'loss': 0.3293, 'learning_rate': 1.168443882161576e-06, 'epoch': 1.92}
{'loss': 0.5474, 'learning_rate': 1.1657328754744262e-06, 'epoch': 1.92}
{'loss': 0.1642, 'learning_rate': 1.1630218687872765e-06, 'epoch': 1.92}
{'loss': 0.2176, 'learning_rate': 1.1603108621001266e-06, 'epoch': 1.92}
{'loss': 0.2949, 'learning_rate': 1.1575998554129768e-06, 'epoch': 1.92}
{'loss': 1.0473, 'learning_rate': 1.154888848725827e-06, 'epoch': 1.92}
{'loss': 0.6519, 'learning_rate': 1.152177842038677e-06, 'epoch': 1.92}
{'loss': 0.3889, 'learning_rate': 1.1494668353515274e-06, 'epoch': 1.92}
{'loss': 1.0133, 'learning_rate': 1.1467558286643775e-06, 'epoch': 1.92}
{'loss': 0.8063, 'learning_rate': 1.1440448219772277e-06, 'epoch': 1.92}
{'loss': 0.3005, 'learning_rate': 1.1413338152900778e-06, 'epoch': 1.92}
{'loss': 0.7134, 'learning_rate': 1.138622808602928e-06, 'epoch': 1.92}
{'loss': 0.8426, 'learning_rate': 1.1359118019157783e-06, 'epoch': 1.92}
{'loss': 0.6039, 'learning_rate': 1.1332007952286282e-06, 'epoch': 1.92}
{'loss': 0.939, 'learning_rate': 1.1304897885414783e-06, 'epoch': 1.92}
{'loss': 0.7691, 'learning_rate': 1.1277787818543285e-06, 'epoch': 1.92}
{'loss': 0.8365, 'learning_rate': 1.1250677751671786e-06, 'epoch': 1.92}
{'loss': 0.4931, 'learning_rate': 1.122356768480029e-06, 'epoch': 1.93}
{'loss': 0.4145, 'learning_rate': 1.119645761792879e-06, 'epoch': 1.93}
{'loss': 1.2955, 'learning_rate': 1.1169347551057292e-06, 'epoch': 1.93}
{'loss': 1.2013, 'learning_rate': 1.1142237484185794e-06, 'epoch': 1.93}
{'loss': 0.7726, 'learning_rate': 1.1115127417314295e-06, 'epoch': 1.93}
{'loss': 0.967, 'learning_rate': 1.1088017350442798e-06, 'epoch': 1.93}
{'loss': 0.7377, 'learning_rate': 1.10609072835713e-06, 'epoch': 1.93}
{'loss': 0.4264, 'learning_rate': 1.10337972166998e-06, 'epoch': 1.93}
{'loss': 0.9541, 'learning_rate': 1.1006687149828302e-06, 'epoch': 1.93}
{'loss': 0.5297, 'learning_rate': 1.0979577082956804e-06, 'epoch': 1.93}
{'loss': 0.5817, 'learning_rate': 1.0952467016085305e-06, 'epoch': 1.93}
{'loss': 1.2802, 'learning_rate': 1.0925356949213809e-06, 'epoch': 1.93}
{'loss': 0.6664, 'learning_rate': 1.089824688234231e-06, 'epoch': 1.93}
{'loss': 0.5913, 'learning_rate': 1.0871136815470811e-06, 'epoch': 1.93}
{'loss': 0.444, 'learning_rate': 1.0844026748599313e-06, 'epoch': 1.93}
{'loss': 0.655, 'learning_rate': 1.0816916681727814e-06, 'epoch': 1.93}
{'loss': 0.7119, 'learning_rate': 1.0789806614856317e-06, 'epoch': 1.93}
{'loss': 0.2152, 'learning_rate': 1.0762696547984819e-06, 'epoch': 1.93}
{'loss': 0.5829, 'learning_rate': 1.073558648111332e-06, 'epoch': 1.93}
{'loss': 0.6183, 'learning_rate': 1.0708476414241821e-06, 'epoch': 1.93}
{'loss': 0.8399, 'learning_rate': 1.0681366347370323e-06, 'epoch': 1.93}
{'loss': 1.498, 'learning_rate': 1.0654256280498826e-06, 'epoch': 1.93}
{'loss': 0.5784, 'learning_rate': 1.0627146213627328e-06, 'epoch': 1.93}
{'loss': 0.9685, 'learning_rate': 1.0600036146755829e-06, 'epoch': 1.93}
{'loss': 0.2872, 'learning_rate': 1.057292607988433e-06, 'epoch': 1.93}
{'loss': 0.9061, 'learning_rate': 1.0545816013012832e-06, 'epoch': 1.93}
{'loss': 0.2961, 'learning_rate': 1.0518705946141335e-06, 'epoch': 1.93}
{'loss': 1.3998, 'learning_rate': 1.0491595879269836e-06, 'epoch': 1.93}
{'loss': 0.9921, 'learning_rate': 1.0464485812398338e-06, 'epoch': 1.93}
{'loss': 0.6809, 'learning_rate': 1.043737574552684e-06, 'epoch': 1.93}
{'loss': 0.9405, 'learning_rate': 1.041026567865534e-06, 'epoch': 1.93}
{'loss': 0.4087, 'learning_rate': 1.0383155611783842e-06, 'epoch': 1.93}
{'loss': 0.7111, 'learning_rate': 1.0356045544912345e-06, 'epoch': 1.93}
{'loss': 0.3934, 'learning_rate': 1.0328935478040847e-06, 'epoch': 1.93}
{'loss': 0.4026, 'learning_rate': 1.0301825411169348e-06, 'epoch': 1.93}
{'loss': 0.973, 'learning_rate': 1.027471534429785e-06, 'epoch': 1.93}
{'loss': 0.4613, 'learning_rate': 1.024760527742635e-06, 'epoch': 1.93}
{'loss': 0.7476, 'learning_rate': 1.0220495210554854e-06, 'epoch': 1.93}
{'loss': 0.2904, 'learning_rate': 1.0193385143683355e-06, 'epoch': 1.93}
{'loss': 0.7323, 'learning_rate': 1.0166275076811857e-06, 'epoch': 1.93}
{'loss': 0.6783, 'learning_rate': 1.0139165009940358e-06, 'epoch': 1.93}
{'loss': 0.6938, 'learning_rate': 1.011205494306886e-06, 'epoch': 1.93}
{'loss': 0.7717, 'learning_rate': 1.0084944876197363e-06, 'epoch': 1.93}
{'loss': 0.8241, 'learning_rate': 1.0057834809325864e-06, 'epoch': 1.93}
{'loss': 1.4782, 'learning_rate': 1.0030724742454366e-06, 'epoch': 1.93}
{'loss': 1.1774, 'learning_rate': 1.0003614675582867e-06, 'epoch': 1.93}
{'loss': 0.6376, 'learning_rate': 9.976504608711368e-07, 'epoch': 1.93}
{'loss': 0.4407, 'learning_rate': 9.949394541839872e-07, 'epoch': 1.93}
{'loss': 0.6535, 'learning_rate': 9.922284474968373e-07, 'epoch': 1.93}
{'loss': 1.0971, 'learning_rate': 9.895174408096874e-07, 'epoch': 1.93}
{'loss': 0.3355, 'learning_rate': 9.868064341225376e-07, 'epoch': 1.93}
{'loss': 0.8386, 'learning_rate': 9.840954274353877e-07, 'epoch': 1.93}
{'loss': 1.2594, 'learning_rate': 9.81384420748238e-07, 'epoch': 1.93}
{'loss': 1.3227, 'learning_rate': 9.786734140610882e-07, 'epoch': 1.93}
{'loss': 0.7263, 'learning_rate': 9.759624073739383e-07, 'epoch': 1.93}
{'loss': 0.4048, 'learning_rate': 9.732514006867885e-07, 'epoch': 1.94}
{'loss': 0.5995, 'learning_rate': 9.705403939996386e-07, 'epoch': 1.94}

 97%|█████████▋| 10709/11066 [39:15<01:17,  4.62it/s]
 97%|█████████▋| 10710/11066 [39:16<01:16,  4.65it/s]
                                                     

 97%|█████████▋| 10710/11066 [39:16<01:16,  4.65it/s]
 97%|█████████▋| 10711/11066 [39:16<01:15,  4.67it/s]
                                                     

 97%|█████████▋| 10711/11066 [39:16<01:15,  4.67it/s]
 97%|█████████▋| 10712/11066 [39:16<01:16,  4.65it/s]
                                                     

 97%|█████████▋| 10712/11066 [39:16<01:16,  4.65it/s]
 97%|█████████▋| 10713/11066 [39:16<01:16,  4.59it/s]
                                                     

 97%|█████████▋| 10713/11066 [39:16<01:16,  4.59it/s]
 97%|█████████▋| 10714/11066 [39:17<01:17,  4.55it/s]
                                                     

 97%|█████████▋| 10714/11066 [39:17<01:17,  4.55it/s]
 97%|█████████▋| 10715/11066 [39:17<01:17,  4.52it/s]
                                                     

 97%|█████████▋| 10715/11066 [39:17<01:17,  4.52it/s]
 97%|█████████▋| 10716/11066 [39:17<01:16,  4.58it/s]
                                                     

 97%|█████████▋| 10716/11066 [39:17<01:16,  4.58it/s]
 97%|█████████▋| 10717/11066 [39:17<01:16,  4.55it/s]
                                                     

 97%|█████████▋| 10717/11066 [39:17<01:16,  4.55it/s]
 97%|█████████▋| 10718/11066 [39:17<01:15,  4.60it/s]
                                                     

 97%|█████████▋| 10718/11066 [39:17<01:15,  4.60it/s]
 97%|█████████▋| 10719/11066 [39:18<01:14,  4.63it/s]
                                                     

 97%|█████████▋| 10719/11066 [39:18<01:14,  4.63it/s]
 97%|█████████▋| 10720/11066 [39:18<01:14,  4.66it/s]
                                                     

 97%|█████████▋| 10720/11066 [39:18<01:14,  4.66it/s]
 97%|█████████▋| 10721/11066 [39:18<01:14,  4.65it/s]
                                                     

 97%|█████████▋| 10721/11066 [39:18<01:14,  4.65it/s]
 97%|█████████▋| 10722/11066 [39:18<01:13,  4.69it/s]
                                                     

 97%|█████████▋| 10722/11066 [39:18<01:13,  4.69it/s]
 97%|█████████▋| 10723/11066 [39:18<01:13,  4.69it/s]
                                                     

 97%|█████████▋| 10723/11066 [39:18<01:13,  4.69it/s]
 97%|█████████▋| 10724/11066 [39:19<01:13,  4.66it/s]
                                                     

 97%|█████████▋| 10724/11066 [39:19<01:13,  4.66it/s]
 97%|█████████▋| 10725/11066 [39:19<01:12,  4.69it/s]
                                                     

 97%|█████████▋| 10725/11066 [39:19<01:12,  4.69it/s]
 97%|█████████▋| 10726/11066 [39:19<01:14,  4.55it/s]
                                                     

 97%|█████████▋| 10726/11066 [39:19<01:14,  4.55it/s]
 97%|█████████▋| 10727/11066 [39:19<01:15,  4.50it/s]
                                                     

 97%|█████████▋| 10727/11066 [39:19<01:15,  4.50it/s]
 97%|█████████▋| 10728/11066 [39:20<01:15,  4.50it/s]
                                                     

 97%|█████████▋| 10728/11066 [39:20<01:15,  4.50it/s]
 97%|█████████▋| 10729/11066 [39:20<01:14,  4.50it/s]
                                                     

 97%|█████████▋| 10729/11066 [39:20<01:14,  4.50it/s]
 97%|█████████▋| 10730/11066 [39:20<01:15,  4.45it/s]
                                                     

 97%|█████████▋| 10730/11066 [39:20<01:15,  4.45it/s]
 97%|█████████▋| 10731/11066 [39:20<01:15,  4.46it/s]
                                                     

 97%|█████████▋| 10731/11066 [39:20<01:15,  4.46it/s]
 97%|█████████▋| 10732/11066 [39:20<01:14,  4.47it/s]
                                                     

 97%|█████████▋| 10732/11066 [39:20<01:14,  4.47it/s]
 97%|█████████▋| 10733/11066 [39:21<01:14,  4.48it/s]
                                                     

 97%|█████████▋| 10733/11066 [39:21<01:14,  4.48it/s]
 97%|█████████▋| 10734/11066 [39:21<01:12,  4.55it/s]
                                                     

 97%|█████████▋| 10734/11066 [39:21<01:12,  4.55it/s]
 97%|█████████▋| 10735/11066 [39:21<01:12,  4.57it/s]
                                                     

 97%|█████████▋| 10735/11066 [39:21<01:12,  4.57it/s]
 97%|█████████▋| 10736/11066 [39:21<01:11,  4.63it/s]
                                                     

 97%|█████████▋| 10736/11066 [39:21<01:11,  4.63it/s]
 97%|█████████▋| 10737/11066 [39:22<01:11,  4.63it/s]
                                                     

 97%|█████████▋| 10737/11066 [39:22<01:11,  4.63it/s]
 97%|█████████▋| 10738/11066 [39:22<01:11,  4.57it/s]
                                                     

 97%|█████████▋| 10738/11066 [39:22<01:11,  4.57it/s]
 97%|█████████▋| 10739/11066 [39:22<01:10,  4.61it/s]
                                                     

 97%|█████████▋| 10739/11066 [39:22<01:10,  4.61it/s]
 97%|█████████▋| 10740/11066 [39:22<01:10,  4.61it/s]
                                                     

 97%|█████████▋| 10740/11066 [39:22<01:10,  4.61it/s]
 97%|█████████▋| 10741/11066 [39:22<01:10,  4.63it/s]
                                                     

 97%|█████████▋| 10741/11066 [39:22<01:10,  4.63it/s]
 97%|█████████▋| 10742/11066 [39:23<01:10,  4.60it/s]
                                                     

 97%|█████████▋| 10742/11066 [39:23<01:10,  4.60it/s]
 97%|█████████▋| 10743/11066 [39:23<01:09,  4.63it/s]
                                                     

 97%|█████████▋| 10743/11066 [39:23<01:09,  4.63it/s]
 97%|█████████▋| 10744/11066 [39:23<01:09,  4.64it/s]
                                                     

 97%|█████████▋| 10744/11066 [39:23<01:09,  4.64it/s]
 97%|█████████▋| 10745/11066 [39:23<01:09,  4.62it/s]
                                                     

 97%|█████████▋| 10745/11066 [39:23<01:09,  4.62it/s]
 97%|█████████▋| 10746/11066 [39:24<01:09,  4.61it/s]
                                                     

 97%|█████████▋| 10746/11066 [39:24<01:09,  4.61it/s]
 97%|█████████▋| 10747/11066 [39:24<01:09,  4.57it/s]
                                                     

 97%|█████████▋| 10747/11066 [39:24<01:09,  4.57it/s]
 97%|█████████▋| 10748/11066 [39:24<01:09,  4.58it/s]
                                                     

 97%|█████████▋| 10748/11066 [39:24<01:09,  4.58it/s]
 97%|█████████▋| 10749/11066 [39:24<01:08,  4.61it/s]
                                                     

 97%|█████████▋| 10749/11066 [39:24<01:08,  4.61it/s]
 97%|█████████▋| 10750/11066 [39:24<01:08,  4.61it/s]
                                                     

 97%|█████████▋| 10750/11066 [39:24<01:08,  4.61it/s]
 97%|█████████▋| 10751/11066 [39:25<01:08,  4.58it/s]
                                                     

 97%|█████████▋| 10751/11066 [39:25<01:08,  4.58it/s]
 97%|█████████▋| 10752/11066 [39:25<01:08,  4.59it/s]
                                                     

 97%|█████████▋| 10752/11066 [39:25<01:08,  4.59it/s]
 97%|█████████▋| 10753/11066 [39:25<01:07,  4.62it/s]
                                                     

 97%|█████████▋| 10753/11066 [39:25<01:07,  4.62it/s]
 97%|█████████▋| 10754/11066 [39:25<01:08,  4.58it/s]
                                                     

 97%|█████████▋| 10754/11066 [39:25<01:08,  4.58it/s]
 97%|█████████▋| 10755/11066 [39:25<01:08,  4.54it/s]
                                                     

 97%|█████████▋| 10755/11066 [39:25<01:08,  4.54it/s]
 97%|█████████▋| 10756/11066 [39:26<01:08,  4.53it/s]
                                                     

 97%|█████████▋| 10756/11066 [39:26<01:08,  4.53it/s]
 97%|█████████▋| 10757/11066 [39:26<01:08,  4.51it/s]
                                                     

 97%|█████████▋| 10757/11066 [39:26<01:08,  4.51it/s]
 97%|█████████▋| 10758/11066 [39:26<01:08,  4.51it/s]
                                                     

 97%|█████████▋| 10758/11066 [39:26<01:08,  4.51it/s]
 97%|█████████▋| 10759/11066 [39:26<01:08,  4.51it/s]
                                                     

 97%|█████████▋| 10759/11066 [39:26<01:08,  4.51it/s]
 97%|█████████▋| 10760/11066 [39:27<01:07,  4.50it/s]
                                                     

 97%|█████████▋| 10760/11066 [39:27<01:07,  4.50it/s]
 97%|█████████▋| 10761/11066 [39:27<01:07,  4.50it/s]
                                                     

 97%|█████████▋| 10761/11066 [39:27<01:07,  4.50it/s]
 97%|█████████▋| 10762/11066 [39:27<01:07,  4.50it/s]
                                                     

 97%|█████████▋| 10762/11066 [39:27<01:07,  4.50it/s]
 97%|█████████▋| 10763/11066 [39:27<01:07,  4.49it/s]
                                                     

 97%|█████████▋| 10763/11066 [39:27<01:07,  4.49it/s]
 97%|█████████▋| 10764/11066 [39:27<01:07,  4.50it/s]
                                                     

 97%|█████████▋| 10764/11066 [39:27<01:07,  4.50it/s]
 97%|█████████▋| 10765/11066 [39:28<01:06,  4.50it/s]
                                                     

 97%|█████████▋| 10765/11066 [39:28<01:06,  4.50it/s]
 97%|█████████▋| 10766/11066 [39:28<01:06,  4.50it/s]
                                                     

 97%|█████████▋| 10766/11066 [39:28<01:06,  4.50it/s]
 97%|█████████▋| 10767/11066 [39:28<01:06,  4.50it/s]
                                                     

 97%|█████████▋| 10767/11066 [39:28<01:06,  4.50it/s]
 97%|█████████▋| 10768/11066 [39:28<01:06,  4.50it/s]
                                                     

 97%|█████████▋| 10768/11066 [39:28<01:06,  4.50it/s]
 97%|█████████▋| 10769/11066 [39:29<01:05,  4.50it/s]
                                                     

 97%|█████████▋| 10769/11066 [39:29<01:05,  4.50it/s]
 97%|█████████▋| 10770/11066 [39:29<01:05,  4.51it/s]
                                                     

 97%|█████████▋| 10770/11066 [39:29<01:05,  4.51it/s]
 97%|█████████▋| 10771/11066 [39:29<01:05,  4.50it/s]
                                                     

 97%|█████████▋| 10771/11066 [39:29<01:05,  4.50it/s]
 97%|█████████▋| 10772/11066 [39:29<01:05,  4.50it/s]
                                                     

 97%|█████████▋| 10772/11066 [39:29<01:05,  4.50it/s]
 97%|█████████▋| 10773/11066 [39:29<01:05,  4.50it/s]
                                                     

 97%|█████████▋| 10773/11066 [39:29<01:05,  4.50it/s]
 97%|█████████▋| 10774/11066 [39:30<01:04,  4.50it/s]
                                                     

 97%|█████████▋| 10774/11066 [39:30<01:04,  4.50it/s]
 97%|█████████▋| 10775/11066 [39:30<01:04,  4.50it/s]
                                                     

 97%|█████████▋| 10775/11066 [39:30<01:04,  4.50it/s]
 97%|█████████▋| 10776/11066 [39:30<01:04,  4.50it/s]
                                                     

 97%|█████████▋| 10776/11066 [39:30<01:04,  4.50it/s]
 97%|█████████▋| 10777/11066 [39:30<01:04,  4.50it/s]
                                                     

 97%|█████████▋| 10777/11066 [39:30<01:04,  4.50it/s]
 97%|█████████▋| 10778/11066 [39:31<01:04,  4.50it/s]
                                                     

 97%|█████████▋| 10778/11066 [39:31<01:04,  4.50it/s]
 97%|█████████▋| 10779/11066 [39:31<01:03,  4.50it/s]
                                                     

 97%|█████████▋| 10779/11066 [39:31<01:03,  4.50it/s]
 97%|█████████▋| 10780/11066 [39:31<01:03,  4.49it/s]
                                                     

 97%|█████████▋| 10780/11066 [39:31<01:03,  4.49it/s]
 97%|█████████▋| 10781/11066 [39:31<01:03,  4.49it/s]
                                                     

 97%|█████████▋| 10781/11066 [39:31<01:03,  4.49it/s]
 97%|█████████▋| 10782/11066 [39:31<01:03,  4.49it/s]
                                                     

 97%|█████████▋| 10782/11066 [39:31<01:03,  4.49it/s]
 97%|█████████▋| 10783/11066 [39:32<01:02,  4.50it/s]
                                                     

 97%|█████████▋| 10783/11066 [39:32<01:02,  4.50it/s]
 97%|█████████▋| 10784/11066 [39:32<01:02,  4.51it/s]
                                                     

 97%|█████████▋| 10784/11066 [39:32<01:02,  4.51it/s]
 97%|█████████▋| 10785/11066 [39:32<01:02,  4.51it/s]
                                                     

 97%|█████████▋| 10785/11066 [39:32<01:02,  4.51it/s]
 97%|█████████▋| 10786/11066 [39:32<01:02,  4.50it/s]
                                                     

 97%|█████████▋| 10786/11066 [39:32<01:02,  4.50it/s]
 97%|█████████▋| 10787/11066 [39:33<01:02,  4.49it/s]
                                                     

 97%|█████████▋| 10787/11066 [39:33<01:02,  4.49it/s]
 97%|█████████▋| 10788/11066 [39:33<01:01,  4.51it/s]
                                                     

 97%|█████████▋| 10788/11066 [39:33<01:01,  4.51it/s]
 97%|█████████▋| 10789/11066 [39:33<01:01,  4.51it/s]
                                                     

 97%|█████████▋| 10789/11066 [39:33<01:01,  4.51it/s]
 98%|█████████▊| 10790/11066 [39:33<01:01,  4.51it/s]
                                                     

 98%|█████████▊| 10790/11066 [39:33<01:01,  4.51it/s]
 98%|█████████▊| 10791/11066 [39:33<01:01,  4.50it/s]
                                                     

 98%|█████████▊| 10791/11066 [39:33<01:01,  4.50it/s]
 98%|█████████▊| 10792/11066 [39:34<01:00,  4.51it/s]
                                                     

 98%|█████████▊| 10792/11066 [39:34<01:00,  4.51it/s]
 98%|█████████▊| 10793/11066 [39:34<01:00,  4.50it/s]
                                                     

 98%|█████████▊| 10793/11066 [39:34<01:00,  4.50it/s]
 98%|█████████▊| 10794/11066 [39:34<01:00,  4.50it/s]
                                                     

 98%|█████████▊| 10794/11066 [39:34<01:00,  4.50it/s]
 98%|█████████▊| 10795/11066 [39:34<01:00,  4.50it/s]
                                                     

 98%|█████████▊| 10795/11066 [39:34<01:00,  4.50it/s]
 98%|█████████▊| 10796/11066 [39:35<00:59,  4.50it/s]
                                                     

 98%|█████████▊| 10796/11066 [39:35<00:59,  4.50it/s]
 98%|█████████▊| 10797/11066 [39:35<00:59,  4.50it/s]
                                                     

 98%|█████████▊| 10797/11066 [39:35<00:59,  4.50it/s]
 98%|█████████▊| 10798/11066 [39:35<00:59,  4.50it/s]
                                                     

 98%|█████████▊| 10798/11066 [39:35<00:59,  4.50it/s]
 98%|█████████▊| 10799/11066 [39:35<00:59,  4.50it/s]
                                                     

 98%|█████████▊| 10799/11066 [39:35<00:59,  4.50it/s]
 98%|█████████▊| 10800/11066 [39:35<00:59,  4.49it/s]
                                                     

 98%|█████████▊| 10800/11066 [39:35<00:59,  4.49it/s]
 98%|█████████▊| 10801/11066 [39:36<00:58,  4.49it/s]
                                                     

 98%|█████████▊| 10801/11066 [39:36<00:58,  4.49it/s]
 98%|█████████▊| 10802/11066 [39:36<00:58,  4.49it/s]
                                                     

 98%|█████████▊| 10802/11066 [39:36<00:58,  4.49it/s]
 98%|█████████▊| 10803/11066 [39:36<00:58,  4.49it/s]
                                                     

 98%|█████████▊| 10803/11066 [39:36<00:58,  4.49it/s]
 98%|█████████▊| 10804/11066 [39:36<00:58,  4.49it/s]
                                                     

 98%|█████████▊| 10804/11066 [39:36<00:58,  4.49it/s]
 98%|█████████▊| 10805/11066 [39:37<00:58,  4.49it/s]
                                                     

 98%|█████████▊| 10805/11066 [39:37<00:58,  4.49it/s]
 98%|█████████▊| 10806/11066 [39:37<00:57,  4.50it/s]
                                                     

 98%|█████████▊| 10806/11066 [39:37<00:57,  4.50it/s]
 98%|█████████▊| 10807/11066 [39:37<00:57,  4.50it/s]
                                                     

 98%|█████████▊| 10807/11066 [39:37<00:57,  4.50it/s]
 98%|█████████▊| 10808/11066 [39:37<00:57,  4.48it/s]
                                                     

 98%|█████████▊| 10808/11066 [39:37<00:57,  4.48it/s]
 98%|█████████▊| 10809/11066 [39:37<00:56,  4.52it/s]
                                                     

 98%|█████████▊| 10809/11066 [39:37<00:56,  4.52it/s]
 98%|█████████▊| 10810/11066 [39:38<00:56,  4.54it/s]
                                                     

 98%|█████████▊| 10810/11066 [39:38<00:56,  4.54it/s]
 98%|█████████▊| 10811/11066 [39:38<00:55,  4.58it/s]
                                                     

 98%|█████████▊| 10811/11066 [39:38<00:55,  4.58it/s]
 98%|█████████▊| 10812/11066 [39:38<00:55,  4.56it/s]
                                                     

 98%|█████████▊| 10812/11066 [39:38<00:55,  4.56it/s]
 98%|█████████▊| 10813/11066 [39:38<00:55,  4.56it/s]
                                                     

 98%|█████████▊| 10813/11066 [39:38<00:55,  4.56it/s]
 98%|█████████▊| 10814/11066 [39:39<00:54,  4.62it/s]
                                                     

 98%|█████████▊| 10814/11066 [39:39<00:54,  4.62it/s]
 98%|█████████▊| 10815/11066 [39:39<00:54,  4.59it/s]
                                                     

 98%|█████████▊| 10815/11066 [39:39<00:54,  4.59it/s]
 98%|█████████▊| 10816/11066 [39:39<00:54,  4.60it/s]
                                                     

 98%|█████████▊| 10816/11066 [39:39<00:54,  4.60it/s]
 98%|█████████▊| 10817/11066 [39:39<00:54,  4.55it/s]
                                                     

 98%|█████████▊| 10817/11066 [39:39<00:54,  4.55it/s]
 98%|█████████▊| 10818/11066 [39:39<00:54,  4.56it/s]
                                                     

 98%|█████████▊| 10818/11066 [39:39<00:54,  4.56it/s]
 98%|█████████▊| 10819/11066 [39:40<00:53,  4.60it/s]
                                                     

 98%|█████████▊| 10819/11066 [39:40<00:53,  4.60it/s]
 98%|█████████▊| 10820/11066 [39:40<00:53,  4.60it/s]
                                                     

 98%|█████████▊| 10820/11066 [39:40<00:53,  4.60it/s]
 98%|█████████▊| 10821/11066 [39:40<00:53,  4.60it/s]
                                                     

 98%|█████████▊| 10821/11066 [39:40<00:53,  4.60it/s]
 98%|█████████▊| 10822/11066 [39:40<00:53,  4.55it/s]
                                                     

 98%|█████████▊| 10822/11066 [39:40<00:53,  4.55it/s]
 98%|█████████▊| 10823/11066 [39:41<00:53,  4.52it/s]
                                                     
{'loss': 0.5831, 'learning_rate': 9.678293873124887e-07, 'epoch': 1.94}
{'loss': 0.6266, 'learning_rate': 9.65118380625339e-07, 'epoch': 1.94}
{'loss': 1.2054, 'learning_rate': 9.624073739381892e-07, 'epoch': 1.94}
{'loss': 0.8757, 'learning_rate': 9.596963672510393e-07, 'epoch': 1.94}
{'loss': 0.6794, 'learning_rate': 9.569853605638893e-07, 'epoch': 1.94}
{'loss': 0.5199, 'learning_rate': 9.542743538767394e-07, 'epoch': 1.94}
{'loss': 0.9414, 'learning_rate': 9.515633471895896e-07, 'epoch': 1.94}
{'loss': 1.0303, 'learning_rate': 9.488523405024399e-07, 'epoch': 1.94}
{'loss': 0.7973, 'learning_rate': 9.4614133381529e-07, 'epoch': 1.94}
{'loss': 0.5439, 'learning_rate': 9.434303271281401e-07, 'epoch': 1.94}
{'loss': 0.2546, 'learning_rate': 9.407193204409904e-07, 'epoch': 1.94}
{'loss': 0.3948, 'learning_rate': 9.380083137538405e-07, 'epoch': 1.94}
{'loss': 0.8121, 'learning_rate': 9.352973070666909e-07, 'epoch': 1.94}
{'loss': 0.4386, 'learning_rate': 9.32586300379541e-07, 'epoch': 1.94}
{'loss': 0.5275, 'learning_rate': 9.298752936923911e-07, 'epoch': 1.94}
{'loss': 0.7608, 'learning_rate': 9.271642870052414e-07, 'epoch': 1.94}
{'loss': 1.1615, 'learning_rate': 9.244532803180915e-07, 'epoch': 1.94}
{'loss': 0.5794, 'learning_rate': 9.217422736309416e-07, 'epoch': 1.94}
{'loss': 0.4866, 'learning_rate': 9.190312669437919e-07, 'epoch': 1.94}
{'loss': 0.9027, 'learning_rate': 9.16320260256642e-07, 'epoch': 1.94}
{'loss': 1.0761, 'learning_rate': 9.136092535694921e-07, 'epoch': 1.94}
{'loss': 0.2938, 'learning_rate': 9.108982468823423e-07, 'epoch': 1.94}
{'loss': 0.7183, 'learning_rate': 9.081872401951924e-07, 'epoch': 1.94}
{'loss': 0.9061, 'learning_rate': 9.054762335080427e-07, 'epoch': 1.94}
{'loss': 0.7161, 'learning_rate': 9.027652268208928e-07, 'epoch': 1.94}
{'loss': 0.9015, 'learning_rate': 9.00054220133743e-07, 'epoch': 1.94}
{'loss': 1.1441, 'learning_rate': 8.973432134465932e-07, 'epoch': 1.94}
{'loss': 0.4616, 'learning_rate': 8.946322067594433e-07, 'epoch': 1.94}
{'loss': 0.39, 'learning_rate': 8.919212000722935e-07, 'epoch': 1.94}
{'loss': 0.6444, 'learning_rate': 8.892101933851437e-07, 'epoch': 1.94}
{'loss': 0.6283, 'learning_rate': 8.864991866979938e-07, 'epoch': 1.94}
{'loss': 0.8373, 'learning_rate': 8.83788180010844e-07, 'epoch': 1.94}
{'loss': 0.5074, 'learning_rate': 8.810771733236942e-07, 'epoch': 1.94}
{'loss': 0.9349, 'learning_rate': 8.783661666365444e-07, 'epoch': 1.94}
{'loss': 1.1557, 'learning_rate': 8.756551599493946e-07, 'epoch': 1.94}
{'loss': 0.8553, 'learning_rate': 8.729441532622447e-07, 'epoch': 1.94}
{'loss': 0.9448, 'learning_rate': 8.702331465750949e-07, 'epoch': 1.94}
{'loss': 0.4933, 'learning_rate': 8.675221398879451e-07, 'epoch': 1.94}
{'loss': 0.3823, 'learning_rate': 8.648111332007953e-07, 'epoch': 1.94}
{'loss': 0.7609, 'learning_rate': 8.621001265136454e-07, 'epoch': 1.94}
{'loss': 1.0833, 'learning_rate': 8.593891198264956e-07, 'epoch': 1.94}
{'loss': 0.5999, 'learning_rate': 8.566781131393458e-07, 'epoch': 1.94}
{'loss': 0.7522, 'learning_rate': 8.53967106452196e-07, 'epoch': 1.94}
{'loss': 0.7804, 'learning_rate': 8.512560997650461e-07, 'epoch': 1.94}
{'loss': 0.9872, 'learning_rate': 8.485450930778963e-07, 'epoch': 1.94}
{'loss': 0.7538, 'learning_rate': 8.458340863907465e-07, 'epoch': 1.94}
{'loss': 0.9187, 'learning_rate': 8.431230797035967e-07, 'epoch': 1.94}
{'loss': 0.3302, 'learning_rate': 8.404120730164468e-07, 'epoch': 1.94}
{'loss': 1.022, 'learning_rate': 8.37701066329297e-07, 'epoch': 1.94}
{'loss': 0.425, 'learning_rate': 8.349900596421472e-07, 'epoch': 1.94}
{'loss': 0.3351, 'learning_rate': 8.322790529549973e-07, 'epoch': 1.94}
{'loss': 0.7003, 'learning_rate': 8.295680462678476e-07, 'epoch': 1.94}
{'loss': 0.4509, 'learning_rate': 8.268570395806976e-07, 'epoch': 1.94}
{'loss': 0.4867, 'learning_rate': 8.241460328935477e-07, 'epoch': 1.95}
{'loss': 0.9975, 'learning_rate': 8.21435026206398e-07, 'epoch': 1.95}
{'loss': 0.9777, 'learning_rate': 8.187240195192481e-07, 'epoch': 1.95}
{'loss': 0.2929, 'learning_rate': 8.160130128320983e-07, 'epoch': 1.95}
{'loss': 0.8419, 'learning_rate': 8.133020061449485e-07, 'epoch': 1.95}
{'loss': 0.6973, 'learning_rate': 8.105909994577986e-07, 'epoch': 1.95}
{'loss': 0.5077, 'learning_rate': 8.078799927706489e-07, 'epoch': 1.95}
{'loss': 1.0246, 'learning_rate': 8.05168986083499e-07, 'epoch': 1.95}
{'loss': 0.9928, 'learning_rate': 8.024579793963491e-07, 'epoch': 1.95}
{'loss': 1.2263, 'learning_rate': 7.997469727091994e-07, 'epoch': 1.95}
{'loss': 0.468, 'learning_rate': 7.970359660220495e-07, 'epoch': 1.95}
{'loss': 0.634, 'learning_rate': 7.943249593348998e-07, 'epoch': 1.95}
{'loss': 1.1721, 'learning_rate': 7.916139526477499e-07, 'epoch': 1.95}
{'loss': 0.9969, 'learning_rate': 7.889029459606e-07, 'epoch': 1.95}
{'loss': 0.4106, 'learning_rate': 7.861919392734503e-07, 'epoch': 1.95}
{'loss': 0.7497, 'learning_rate': 7.834809325863004e-07, 'epoch': 1.95}
{'loss': 0.544, 'learning_rate': 7.807699258991505e-07, 'epoch': 1.95}
{'loss': 1.0381, 'learning_rate': 7.780589192120008e-07, 'epoch': 1.95}
{'loss': 0.5169, 'learning_rate': 7.753479125248509e-07, 'epoch': 1.95}
{'loss': 1.0806, 'learning_rate': 7.726369058377011e-07, 'epoch': 1.95}
{'loss': 0.4083, 'learning_rate': 7.699258991505513e-07, 'epoch': 1.95}
{'loss': 0.5238, 'learning_rate': 7.672148924634014e-07, 'epoch': 1.95}
{'loss': 0.7303, 'learning_rate': 7.645038857762517e-07, 'epoch': 1.95}
{'loss': 0.3904, 'learning_rate': 7.617928790891018e-07, 'epoch': 1.95}
{'loss': 0.7974, 'learning_rate': 7.59081872401952e-07, 'epoch': 1.95}
{'loss': 0.3397, 'learning_rate': 7.563708657148022e-07, 'epoch': 1.95}
{'loss': 1.1605, 'learning_rate': 7.536598590276523e-07, 'epoch': 1.95}
{'loss': 1.1229, 'learning_rate': 7.509488523405025e-07, 'epoch': 1.95}
{'loss': 0.2954, 'learning_rate': 7.482378456533527e-07, 'epoch': 1.95}
{'loss': 0.5715, 'learning_rate': 7.455268389662028e-07, 'epoch': 1.95}
{'loss': 0.6336, 'learning_rate': 7.42815832279053e-07, 'epoch': 1.95}
{'loss': 0.3827, 'learning_rate': 7.401048255919031e-07, 'epoch': 1.95}
{'loss': 0.6668, 'learning_rate': 7.373938189047533e-07, 'epoch': 1.95}
{'loss': 0.7688, 'learning_rate': 7.346828122176034e-07, 'epoch': 1.95}
{'loss': 0.6978, 'learning_rate': 7.319718055304536e-07, 'epoch': 1.95}
{'loss': 0.6805, 'learning_rate': 7.292607988433038e-07, 'epoch': 1.95}
{'loss': 0.5377, 'learning_rate': 7.26549792156154e-07, 'epoch': 1.95}
{'loss': 0.5236, 'learning_rate': 7.238387854690042e-07, 'epoch': 1.95}
{'loss': 1.3712, 'learning_rate': 7.211277787818543e-07, 'epoch': 1.95}
{'loss': 1.4037, 'learning_rate': 7.184167720947045e-07, 'epoch': 1.95}
{'loss': 0.4185, 'learning_rate': 7.157057654075547e-07, 'epoch': 1.95}
{'loss': 0.4329, 'learning_rate': 7.129947587204048e-07, 'epoch': 1.95}
{'loss': 0.9129, 'learning_rate': 7.10283752033255e-07, 'epoch': 1.95}
{'loss': 0.8111, 'learning_rate': 7.075727453461052e-07, 'epoch': 1.95}
{'loss': 0.5249, 'learning_rate': 7.048617386589553e-07, 'epoch': 1.95}
{'loss': 0.7029, 'learning_rate': 7.021507319718056e-07, 'epoch': 1.95}
{'loss': 1.2362, 'learning_rate': 6.994397252846557e-07, 'epoch': 1.95}
{'loss': 0.5102, 'learning_rate': 6.967287185975059e-07, 'epoch': 1.95}
{'loss': 0.9694, 'learning_rate': 6.940177119103561e-07, 'epoch': 1.95}
{'loss': 0.3643, 'learning_rate': 6.913067052232062e-07, 'epoch': 1.95}
{'loss': 0.3445, 'learning_rate': 6.885956985360564e-07, 'epoch': 1.95}
{'loss': 1.1187, 'learning_rate': 6.858846918489066e-07, 'epoch': 1.95}
{'loss': 1.2952, 'learning_rate': 6.831736851617567e-07, 'epoch': 1.95}
{'loss': 0.5129, 'learning_rate': 6.80462678474607e-07, 'epoch': 1.95}
{'loss': 1.026, 'learning_rate': 6.777516717874571e-07, 'epoch': 1.95}
{'loss': 0.5381, 'learning_rate': 6.750406651003072e-07, 'epoch': 1.95}
{'loss': 0.7493, 'learning_rate': 6.723296584131575e-07, 'epoch': 1.96}
{'loss': 0.6278, 'learning_rate': 6.696186517260076e-07, 'epoch': 1.96}
{'loss': 0.6154, 'learning_rate': 6.669076450388579e-07, 'epoch': 1.96}
{'loss': 0.481, 'learning_rate': 6.64196638351708e-07, 'epoch': 1.96}
{'loss': 0.4896, 'learning_rate': 6.614856316645581e-07, 'epoch': 1.96}

 98%|█████████▊| 10823/11066 [39:41<00:53,  4.52it/s]
 98%|█████████▊| 10824/11066 [39:41<00:53,  4.50it/s]
                                                     

 98%|█████████▊| 10824/11066 [39:41<00:53,  4.50it/s]
 98%|█████████▊| 10825/11066 [39:41<00:53,  4.50it/s]
                                                     

 98%|█████████▊| 10825/11066 [39:41<00:53,  4.50it/s]
 98%|█████████▊| 10826/11066 [39:41<00:53,  4.50it/s]
                                                     

 98%|█████████▊| 10826/11066 [39:41<00:53,  4.50it/s]
 98%|█████████▊| 10827/11066 [39:41<00:53,  4.49it/s]
                                                     

 98%|█████████▊| 10827/11066 [39:41<00:53,  4.49it/s]
 98%|█████████▊| 10828/11066 [39:42<00:53,  4.42it/s]
                                                     

 98%|█████████▊| 10828/11066 [39:42<00:53,  4.42it/s]
 98%|█████████▊| 10829/11066 [39:42<00:53,  4.44it/s]
                                                     

 98%|█████████▊| 10829/11066 [39:42<00:53,  4.44it/s]
 98%|█████████▊| 10830/11066 [39:42<00:52,  4.50it/s]
                                                     

 98%|█████████▊| 10830/11066 [39:42<00:52,  4.50it/s]
 98%|█████████▊| 10831/11066 [39:42<00:51,  4.54it/s]
                                                     

 98%|█████████▊| 10831/11066 [39:42<00:51,  4.54it/s]
 98%|█████████▊| 10832/11066 [39:43<00:51,  4.56it/s]
                                                     

 98%|█████████▊| 10832/11066 [39:43<00:51,  4.56it/s]
 98%|█████████▊| 10833/11066 [39:43<00:51,  4.53it/s]
                                                     

 98%|█████████▊| 10833/11066 [39:43<00:51,  4.53it/s]
 98%|█████████▊| 10834/11066 [39:43<00:50,  4.58it/s]
                                                     

 98%|█████████▊| 10834/11066 [39:43<00:50,  4.58it/s]
 98%|█████████▊| 10835/11066 [39:43<00:50,  4.54it/s]
                                                     

 98%|█████████▊| 10835/11066 [39:43<00:50,  4.54it/s]
 98%|█████████▊| 10836/11066 [39:43<00:50,  4.52it/s]
                                                     

 98%|█████████▊| 10836/11066 [39:43<00:50,  4.52it/s]
 98%|█████████▊| 10837/11066 [39:44<00:51,  4.43it/s]
                                                     

 98%|█████████▊| 10837/11066 [39:44<00:51,  4.43it/s]
 98%|█████████▊| 10838/11066 [39:44<00:51,  4.45it/s]
                                                     

 98%|█████████▊| 10838/11066 [39:44<00:51,  4.45it/s]
 98%|█████████▊| 10839/11066 [39:44<00:50,  4.47it/s]
                                                     

 98%|█████████▊| 10839/11066 [39:44<00:50,  4.47it/s]
 98%|█████████▊| 10840/11066 [39:44<00:50,  4.49it/s]
                                                     

 98%|█████████▊| 10840/11066 [39:44<00:50,  4.49it/s]
 98%|█████████▊| 10841/11066 [39:45<00:51,  4.40it/s]
                                                     

 98%|█████████▊| 10841/11066 [39:45<00:51,  4.40it/s]
 98%|█████████▊| 10842/11066 [39:45<00:50,  4.42it/s]
                                                     

 98%|█████████▊| 10842/11066 [39:45<00:50,  4.42it/s]
 98%|█████████▊| 10843/11066 [39:45<00:50,  4.44it/s]
                                                     

 98%|█████████▊| 10843/11066 [39:45<00:50,  4.44it/s]
 98%|█████████▊| 10844/11066 [39:45<00:50,  4.41it/s]
                                                     

 98%|█████████▊| 10844/11066 [39:45<00:50,  4.41it/s]
 98%|█████████▊| 10845/11066 [39:45<00:49,  4.43it/s]
                                                     

 98%|█████████▊| 10845/11066 [39:45<00:49,  4.43it/s]
 98%|█████████▊| 10846/11066 [39:46<00:49,  4.48it/s]
                                                     

 98%|█████████▊| 10846/11066 [39:46<00:49,  4.48it/s]
 98%|█████████▊| 10847/11066 [39:46<00:48,  4.50it/s]
                                                     

 98%|█████████▊| 10847/11066 [39:46<00:48,  4.50it/s]
 98%|█████████▊| 10848/11066 [39:46<00:48,  4.54it/s]
                                                     

 98%|█████████▊| 10848/11066 [39:46<00:48,  4.54it/s]
 98%|█████████▊| 10849/11066 [39:46<00:48,  4.51it/s]
                                                     

 98%|█████████▊| 10849/11066 [39:46<00:48,  4.51it/s]
 98%|█████████▊| 10850/11066 [39:47<00:47,  4.54it/s]
                                                     

 98%|█████████▊| 10850/11066 [39:47<00:47,  4.54it/s]
 98%|█████████▊| 10851/11066 [39:47<00:47,  4.51it/s]
                                                     

 98%|█████████▊| 10851/11066 [39:47<00:47,  4.51it/s]
 98%|█████████▊| 10852/11066 [39:47<00:46,  4.56it/s]
                                                     

 98%|█████████▊| 10852/11066 [39:47<00:46,  4.56it/s]
 98%|█████████▊| 10853/11066 [39:47<00:46,  4.54it/s]
                                                     

 98%|█████████▊| 10853/11066 [39:47<00:46,  4.54it/s]
 98%|█████████▊| 10854/11066 [39:47<00:46,  4.53it/s]
                                                     

 98%|█████████▊| 10854/11066 [39:47<00:46,  4.53it/s]
 98%|█████████▊| 10855/11066 [39:48<00:46,  4.55it/s]
                                                     

 98%|█████████▊| 10855/11066 [39:48<00:46,  4.55it/s]
 98%|█████████▊| 10856/11066 [39:48<00:46,  4.52it/s]
                                                     

 98%|█████████▊| 10856/11066 [39:48<00:46,  4.52it/s]
 98%|█████████▊| 10857/11066 [39:48<00:46,  4.51it/s]
                                                     

 98%|█████████▊| 10857/11066 [39:48<00:46,  4.51it/s]
 98%|█████████▊| 10858/11066 [39:48<00:46,  4.50it/s]
                                                     

 98%|█████████▊| 10858/11066 [39:48<00:46,  4.50it/s]
 98%|█████████▊| 10859/11066 [39:49<00:45,  4.50it/s]
                                                     

 98%|█████████▊| 10859/11066 [39:49<00:45,  4.50it/s]
 98%|█████████▊| 10860/11066 [39:49<00:45,  4.50it/s]
                                                     

 98%|█████████▊| 10860/11066 [39:49<00:45,  4.50it/s]
 98%|█████████▊| 10861/11066 [39:49<00:45,  4.50it/s]
                                                     

 98%|█████████▊| 10861/11066 [39:49<00:45,  4.50it/s]
 98%|█████████▊| 10862/11066 [39:49<00:44,  4.59it/s]
                                                     

 98%|█████████▊| 10862/11066 [39:49<00:44,  4.59it/s]
 98%|█████████▊| 10863/11066 [39:49<00:44,  4.58it/s]
                                                     

 98%|█████████▊| 10863/11066 [39:49<00:44,  4.58it/s]
 98%|█████████▊| 10864/11066 [39:50<00:44,  4.56it/s]
                                                     

 98%|█████████▊| 10864/11066 [39:50<00:44,  4.56it/s]
 98%|█████████▊| 10865/11066 [39:50<00:44,  4.57it/s]
                                                     

 98%|█████████▊| 10865/11066 [39:50<00:44,  4.57it/s]
 98%|█████████▊| 10866/11066 [39:50<00:43,  4.61it/s]
                                                     

 98%|█████████▊| 10866/11066 [39:50<00:43,  4.61it/s]
 98%|█████████▊| 10867/11066 [39:50<00:43,  4.57it/s]
                                                     

 98%|█████████▊| 10867/11066 [39:50<00:43,  4.57it/s]
 98%|█████████▊| 10868/11066 [39:51<00:43,  4.55it/s]
                                                     

 98%|█████████▊| 10868/11066 [39:51<00:43,  4.55it/s]
 98%|█████████▊| 10869/11066 [39:51<00:43,  4.54it/s]
                                                     

 98%|█████████▊| 10869/11066 [39:51<00:43,  4.54it/s]
 98%|█████████▊| 10870/11066 [39:51<00:42,  4.56it/s]
                                                     

 98%|█████████▊| 10870/11066 [39:51<00:42,  4.56it/s]
 98%|█████████▊| 10871/11066 [39:51<00:43,  4.53it/s]
                                                     

 98%|█████████▊| 10871/11066 [39:51<00:43,  4.53it/s]
 98%|█████████▊| 10872/11066 [39:51<00:42,  4.54it/s]
                                                     

 98%|█████████▊| 10872/11066 [39:51<00:42,  4.54it/s]
 98%|█████████▊| 10873/11066 [39:52<00:42,  4.58it/s]
                                                     

 98%|█████████▊| 10873/11066 [39:52<00:42,  4.58it/s]
 98%|█████████▊| 10874/11066 [39:52<00:42,  4.53it/s]
                                                     

 98%|█████████▊| 10874/11066 [39:52<00:42,  4.53it/s]
 98%|█████████▊| 10875/11066 [39:52<00:42,  4.50it/s]
                                                     

 98%|█████████▊| 10875/11066 [39:52<00:42,  4.50it/s]
 98%|█████████▊| 10876/11066 [39:52<00:42,  4.51it/s]
                                                     

 98%|█████████▊| 10876/11066 [39:52<00:42,  4.51it/s]
 98%|█████████▊| 10877/11066 [39:53<00:42,  4.49it/s]
                                                     

 98%|█████████▊| 10877/11066 [39:53<00:42,  4.49it/s]
 98%|█████████▊| 10878/11066 [39:53<00:41,  4.48it/s]
                                                     

 98%|█████████▊| 10878/11066 [39:53<00:41,  4.48it/s]
 98%|█████████▊| 10879/11066 [39:53<00:41,  4.45it/s]
                                                     

 98%|█████████▊| 10879/11066 [39:53<00:41,  4.45it/s]
 98%|█████████▊| 10880/11066 [39:53<00:41,  4.43it/s]
                                                     

 98%|█████████▊| 10880/11066 [39:53<00:41,  4.43it/s]
 98%|█████████▊| 10881/11066 [39:53<00:41,  4.45it/s]
                                                     

 98%|█████████▊| 10881/11066 [39:53<00:41,  4.45it/s]
 98%|█████████▊| 10882/11066 [39:54<00:40,  4.53it/s]
                                                     

 98%|█████████▊| 10882/11066 [39:54<00:40,  4.53it/s]
 98%|█████████▊| 10883/11066 [39:54<00:41,  4.46it/s]
                                                     

 98%|█████████▊| 10883/11066 [39:54<00:41,  4.46it/s]
 98%|█████████▊| 10884/11066 [39:54<00:40,  4.46it/s]
                                                     

 98%|█████████▊| 10884/11066 [39:54<00:40,  4.46it/s]
 98%|█████████▊| 10885/11066 [39:54<00:40,  4.49it/s]
                                                     

 98%|█████████▊| 10885/11066 [39:54<00:40,  4.49it/s]
 98%|█████████▊| 10886/11066 [39:55<00:40,  4.49it/s]
                                                     

 98%|█████████▊| 10886/11066 [39:55<00:40,  4.49it/s]
 98%|█████████▊| 10887/11066 [39:55<00:40,  4.47it/s]
                                                     

 98%|█████████▊| 10887/11066 [39:55<00:40,  4.47it/s]
 98%|█████████▊| 10888/11066 [39:55<00:39,  4.50it/s]
                                                     

 98%|█████████▊| 10888/11066 [39:55<00:39,  4.50it/s]
 98%|█████████▊| 10889/11066 [39:55<00:39,  4.49it/s]
                                                     

 98%|█████████▊| 10889/11066 [39:55<00:39,  4.49it/s]
 98%|█████████▊| 10890/11066 [39:55<00:39,  4.47it/s]
                                                     

 98%|█████████▊| 10890/11066 [39:55<00:39,  4.47it/s]
 98%|█████████▊| 10891/11066 [39:56<00:39,  4.48it/s]
                                                     

 98%|█████████▊| 10891/11066 [39:56<00:39,  4.48it/s]
 98%|█████████▊| 10892/11066 [39:56<00:38,  4.48it/s]
                                                     

 98%|█████████▊| 10892/11066 [39:56<00:38,  4.48it/s]
 98%|█████████▊| 10893/11066 [39:56<00:38,  4.48it/s]
                                                     

 98%|█████████▊| 10893/11066 [39:56<00:38,  4.48it/s]
 98%|█████████▊| 10894/11066 [39:56<00:38,  4.51it/s]
                                                     

 98%|█████████▊| 10894/11066 [39:56<00:38,  4.51it/s]
 98%|█████████▊| 10895/11066 [39:57<00:37,  4.51it/s]
                                                     

 98%|█████████▊| 10895/11066 [39:57<00:37,  4.51it/s]
 98%|█████████▊| 10896/11066 [39:57<00:37,  4.54it/s]
                                                     

 98%|█████████▊| 10896/11066 [39:57<00:37,  4.54it/s]
 98%|█████████▊| 10897/11066 [39:57<00:37,  4.54it/s]
                                                     

 98%|█████████▊| 10897/11066 [39:57<00:37,  4.54it/s]
 98%|█████████▊| 10898/11066 [39:57<00:37,  4.50it/s]
                                                     

 98%|█████████▊| 10898/11066 [39:57<00:37,  4.50it/s]
 98%|█████████▊| 10899/11066 [39:57<00:37,  4.49it/s]
                                                     

 98%|█████████▊| 10899/11066 [39:57<00:37,  4.49it/s]
 98%|█████████▊| 10900/11066 [39:58<00:36,  4.49it/s]
                                                     

 98%|█████████▊| 10900/11066 [39:58<00:36,  4.49it/s]
 99%|█████████▊| 10901/11066 [39:58<00:36,  4.49it/s]
                                                     

 99%|█████████▊| 10901/11066 [39:58<00:36,  4.49it/s]
 99%|█████████▊| 10902/11066 [39:58<00:36,  4.50it/s]
                                                     

 99%|█████████▊| 10902/11066 [39:58<00:36,  4.50it/s]
 99%|█████████▊| 10903/11066 [39:58<00:35,  4.56it/s]
                                                     

 99%|█████████▊| 10903/11066 [39:58<00:35,  4.56it/s]
 99%|█████████▊| 10904/11066 [39:59<00:35,  4.54it/s]
                                                     

 99%|█████████▊| 10904/11066 [39:59<00:35,  4.54it/s]
 99%|█████████▊| 10905/11066 [39:59<00:35,  4.53it/s]
                                                     

 99%|█████████▊| 10905/11066 [39:59<00:35,  4.53it/s]
 99%|█████████▊| 10906/11066 [39:59<00:35,  4.52it/s]
                                                     

 99%|█████████▊| 10906/11066 [39:59<00:35,  4.52it/s]
 99%|█████████▊| 10907/11066 [39:59<00:35,  4.51it/s]
                                                     

 99%|█████████▊| 10907/11066 [39:59<00:35,  4.51it/s]
 99%|█████████▊| 10908/11066 [39:59<00:35,  4.51it/s]
                                                     

 99%|█████████▊| 10908/11066 [39:59<00:35,  4.51it/s]
 99%|█████████▊| 10909/11066 [40:00<00:34,  4.54it/s]
                                                     

 99%|█████████▊| 10909/11066 [40:00<00:34,  4.54it/s]
 99%|█████████▊| 10910/11066 [40:00<00:34,  4.51it/s]
                                                     

 99%|█████████▊| 10910/11066 [40:00<00:34,  4.51it/s]
 99%|█████████▊| 10911/11066 [40:00<00:34,  4.50it/s]
                                                     

 99%|█████████▊| 10911/11066 [40:00<00:34,  4.50it/s]
 99%|█████████▊| 10912/11066 [40:00<00:34,  4.50it/s]
                                                     

 99%|█████████▊| 10912/11066 [40:00<00:34,  4.50it/s]
 99%|█████████▊| 10913/11066 [40:01<00:33,  4.53it/s]
                                                     

 99%|█████████▊| 10913/11066 [40:01<00:33,  4.53it/s]
 99%|█████████▊| 10914/11066 [40:01<00:33,  4.51it/s]
                                                     

 99%|█████████▊| 10914/11066 [40:01<00:33,  4.51it/s]
 99%|█████████▊| 10915/11066 [40:01<00:33,  4.53it/s]
                                                     

 99%|█████████▊| 10915/11066 [40:01<00:33,  4.53it/s]
 99%|█████████▊| 10916/11066 [40:01<00:33,  4.51it/s]
                                                     

 99%|█████████▊| 10916/11066 [40:01<00:33,  4.51it/s]
 99%|█████████▊| 10917/11066 [40:01<00:33,  4.49it/s]
                                                     

 99%|█████████▊| 10917/11066 [40:01<00:33,  4.49it/s]
 99%|█████████▊| 10918/11066 [40:02<00:33,  4.48it/s]
                                                     

 99%|█████████▊| 10918/11066 [40:02<00:33,  4.48it/s]
 99%|█████████▊| 10919/11066 [40:02<00:32,  4.49it/s]
                                                     

 99%|█████████▊| 10919/11066 [40:02<00:32,  4.49it/s]
 99%|█████████▊| 10920/11066 [40:02<00:32,  4.49it/s]
                                                     

 99%|█████████▊| 10920/11066 [40:02<00:32,  4.49it/s]
 99%|█████████▊| 10921/11066 [40:02<00:32,  4.49it/s]
                                                     

 99%|█████████▊| 10921/11066 [40:02<00:32,  4.49it/s]
 99%|█████████▊| 10922/11066 [40:03<00:31,  4.52it/s]
                                                     

 99%|█████████▊| 10922/11066 [40:03<00:31,  4.52it/s]
 99%|█████████▊| 10923/11066 [40:03<00:31,  4.51it/s]
                                                     

 99%|█████████▊| 10923/11066 [40:03<00:31,  4.51it/s]
 99%|█████████▊| 10924/11066 [40:03<00:31,  4.50it/s]
                                                     

 99%|█████████▊| 10924/11066 [40:03<00:31,  4.50it/s]
 99%|█████████▊| 10925/11066 [40:03<00:31,  4.50it/s]
                                                     

 99%|█████████▊| 10925/11066 [40:03<00:31,  4.50it/s]
 99%|█████████▊| 10926/11066 [40:03<00:31,  4.50it/s]
                                                     

 99%|█████████▊| 10926/11066 [40:03<00:31,  4.50it/s]
 99%|█████████▊| 10927/11066 [40:04<00:30,  4.50it/s]
                                                     

 99%|█████████▊| 10927/11066 [40:04<00:30,  4.50it/s]
 99%|█████████▉| 10928/11066 [40:04<00:30,  4.50it/s]
                                                     

 99%|█████████▉| 10928/11066 [40:04<00:30,  4.50it/s]
 99%|█████████▉| 10929/11066 [40:04<00:30,  4.50it/s]
                                                     

 99%|█████████▉| 10929/11066 [40:04<00:30,  4.50it/s]
 99%|█████████▉| 10930/11066 [40:04<00:29,  4.57it/s]
                                                     

 99%|█████████▉| 10930/11066 [40:04<00:29,  4.57it/s]
 99%|█████████▉| 10931/11066 [40:05<00:29,  4.53it/s]
                                                     

 99%|█████████▉| 10931/11066 [40:05<00:29,  4.53it/s]
 99%|█████████▉| 10932/11066 [40:05<00:29,  4.52it/s]
                                                     

 99%|█████████▉| 10932/11066 [40:05<00:29,  4.52it/s]
 99%|█████████▉| 10933/11066 [40:05<00:30,  4.42it/s]
                                                     

 99%|█████████▉| 10933/11066 [40:05<00:30,  4.42it/s]
 99%|█████████▉| 10934/11066 [40:05<00:29,  4.43it/s]
                                                     

 99%|█████████▉| 10934/11066 [40:05<00:29,  4.43it/s]
 99%|█████████▉| 10935/11066 [40:05<00:29,  4.44it/s]
                                                     

 99%|█████████▉| 10935/11066 [40:05<00:29,  4.44it/s]
 99%|█████████▉| 10936/11066 [40:06<00:28,  4.49it/s]
                                                     
{'loss': 1.3428, 'learning_rate': 6.587746249774084e-07, 'epoch': 1.96}
{'loss': 1.2545, 'learning_rate': 6.560636182902585e-07, 'epoch': 1.96}
{'loss': 0.8438, 'learning_rate': 6.533526116031085e-07, 'epoch': 1.96}
{'loss': 0.7747, 'learning_rate': 6.506416049159588e-07, 'epoch': 1.96}
{'loss': 0.8123, 'learning_rate': 6.479305982288089e-07, 'epoch': 1.96}
{'loss': 0.6486, 'learning_rate': 6.452195915416591e-07, 'epoch': 1.96}
{'loss': 0.8435, 'learning_rate': 6.425085848545093e-07, 'epoch': 1.96}
{'loss': 0.8698, 'learning_rate': 6.397975781673594e-07, 'epoch': 1.96}
{'loss': 0.4283, 'learning_rate': 6.370865714802097e-07, 'epoch': 1.96}
{'loss': 0.5766, 'learning_rate': 6.343755647930598e-07, 'epoch': 1.96}
{'loss': 0.6586, 'learning_rate': 6.3166455810591e-07, 'epoch': 1.96}
{'loss': 0.4745, 'learning_rate': 6.289535514187602e-07, 'epoch': 1.96}
{'loss': 0.4739, 'learning_rate': 6.262425447316103e-07, 'epoch': 1.96}
{'loss': 0.5451, 'learning_rate': 6.235315380444605e-07, 'epoch': 1.96}
{'loss': 0.6707, 'learning_rate': 6.208205313573107e-07, 'epoch': 1.96}
{'loss': 0.3946, 'learning_rate': 6.181095246701608e-07, 'epoch': 1.96}
{'loss': 0.8898, 'learning_rate': 6.15398517983011e-07, 'epoch': 1.96}
{'loss': 0.7063, 'learning_rate': 6.126875112958612e-07, 'epoch': 1.96}
{'loss': 0.252, 'learning_rate': 6.099765046087114e-07, 'epoch': 1.96}
{'loss': 0.8446, 'learning_rate': 6.072654979215616e-07, 'epoch': 1.96}
{'loss': 0.6551, 'learning_rate': 6.045544912344117e-07, 'epoch': 1.96}
{'loss': 0.6257, 'learning_rate': 6.018434845472619e-07, 'epoch': 1.96}
{'loss': 0.6599, 'learning_rate': 5.991324778601121e-07, 'epoch': 1.96}
{'loss': 1.0033, 'learning_rate': 5.964214711729623e-07, 'epoch': 1.96}
{'loss': 0.748, 'learning_rate': 5.937104644858124e-07, 'epoch': 1.96}
{'loss': 0.4513, 'learning_rate': 5.909994577986626e-07, 'epoch': 1.96}
{'loss': 1.0466, 'learning_rate': 5.882884511115128e-07, 'epoch': 1.96}
{'loss': 0.4233, 'learning_rate': 5.85577444424363e-07, 'epoch': 1.96}
{'loss': 0.3063, 'learning_rate': 5.828664377372131e-07, 'epoch': 1.96}
{'loss': 0.9016, 'learning_rate': 5.801554310500633e-07, 'epoch': 1.96}
{'loss': 0.7211, 'learning_rate': 5.774444243629135e-07, 'epoch': 1.96}
{'loss': 0.7258, 'learning_rate': 5.747334176757637e-07, 'epoch': 1.96}
{'loss': 1.3917, 'learning_rate': 5.720224109886138e-07, 'epoch': 1.96}
{'loss': 0.546, 'learning_rate': 5.69311404301464e-07, 'epoch': 1.96}
{'loss': 1.1886, 'learning_rate': 5.666003976143141e-07, 'epoch': 1.96}
{'loss': 0.6637, 'learning_rate': 5.638893909271642e-07, 'epoch': 1.96}
{'loss': 0.7202, 'learning_rate': 5.611783842400145e-07, 'epoch': 1.96}
{'loss': 0.3564, 'learning_rate': 5.584673775528646e-07, 'epoch': 1.96}
{'loss': 0.5877, 'learning_rate': 5.557563708657147e-07, 'epoch': 1.96}
{'loss': 0.6769, 'learning_rate': 5.53045364178565e-07, 'epoch': 1.96}
{'loss': 0.8955, 'learning_rate': 5.503343574914151e-07, 'epoch': 1.96}
{'loss': 1.0589, 'learning_rate': 5.476233508042653e-07, 'epoch': 1.96}
{'loss': 0.8337, 'learning_rate': 5.449123441171155e-07, 'epoch': 1.96}
{'loss': 0.6903, 'learning_rate': 5.422013374299656e-07, 'epoch': 1.96}
{'loss': 0.3602, 'learning_rate': 5.394903307428159e-07, 'epoch': 1.96}
{'loss': 0.522, 'learning_rate': 5.36779324055666e-07, 'epoch': 1.96}
{'loss': 0.5718, 'learning_rate': 5.340683173685161e-07, 'epoch': 1.96}
{'loss': 0.6319, 'learning_rate': 5.313573106813664e-07, 'epoch': 1.96}
{'loss': 1.0768, 'learning_rate': 5.286463039942165e-07, 'epoch': 1.96}
{'loss': 0.4094, 'learning_rate': 5.259352973070668e-07, 'epoch': 1.96}
{'loss': 1.0955, 'learning_rate': 5.232242906199169e-07, 'epoch': 1.97}
{'loss': 0.4571, 'learning_rate': 5.20513283932767e-07, 'epoch': 1.97}
{'loss': 0.4865, 'learning_rate': 5.178022772456173e-07, 'epoch': 1.97}
{'loss': 0.6409, 'learning_rate': 5.150912705584674e-07, 'epoch': 1.97}
{'loss': 0.8702, 'learning_rate': 5.123802638713175e-07, 'epoch': 1.97}
{'loss': 0.6902, 'learning_rate': 5.096692571841678e-07, 'epoch': 1.97}
{'loss': 0.4931, 'learning_rate': 5.069582504970179e-07, 'epoch': 1.97}
{'loss': 0.3086, 'learning_rate': 5.042472438098681e-07, 'epoch': 1.97}
{'loss': 0.839, 'learning_rate': 5.015362371227183e-07, 'epoch': 1.97}
{'loss': 0.4937, 'learning_rate': 4.988252304355684e-07, 'epoch': 1.97}
{'loss': 0.6506, 'learning_rate': 4.961142237484187e-07, 'epoch': 1.97}
{'loss': 1.1031, 'learning_rate': 4.934032170612688e-07, 'epoch': 1.97}
{'loss': 0.645, 'learning_rate': 4.90692210374119e-07, 'epoch': 1.97}
{'loss': 0.5629, 'learning_rate': 4.879812036869692e-07, 'epoch': 1.97}
{'loss': 0.3914, 'learning_rate': 4.852701969998193e-07, 'epoch': 1.97}
{'loss': 0.7342, 'learning_rate': 4.825591903126695e-07, 'epoch': 1.97}
{'loss': 1.1886, 'learning_rate': 4.798481836255197e-07, 'epoch': 1.97}
{'loss': 0.4077, 'learning_rate': 4.771371769383697e-07, 'epoch': 1.97}
{'loss': 1.1107, 'learning_rate': 4.7442617025121994e-07, 'epoch': 1.97}
{'loss': 0.6388, 'learning_rate': 4.7171516356407007e-07, 'epoch': 1.97}
{'loss': 0.4615, 'learning_rate': 4.6900415687692026e-07, 'epoch': 1.97}
{'loss': 0.4432, 'learning_rate': 4.662931501897705e-07, 'epoch': 1.97}
{'loss': 0.7286, 'learning_rate': 4.635821435026207e-07, 'epoch': 1.97}
{'loss': 0.464, 'learning_rate': 4.608711368154708e-07, 'epoch': 1.97}
{'loss': 0.5851, 'learning_rate': 4.58160130128321e-07, 'epoch': 1.97}
{'loss': 0.6786, 'learning_rate': 4.5544912344117114e-07, 'epoch': 1.97}
{'loss': 0.503, 'learning_rate': 4.5273811675402133e-07, 'epoch': 1.97}
{'loss': 0.5892, 'learning_rate': 4.500271100668715e-07, 'epoch': 1.97}
{'loss': 0.7091, 'learning_rate': 4.4731610337972165e-07, 'epoch': 1.97}
{'loss': 0.7288, 'learning_rate': 4.4460509669257184e-07, 'epoch': 1.97}
{'loss': 1.4084, 'learning_rate': 4.41894090005422e-07, 'epoch': 1.97}
{'loss': 0.4794, 'learning_rate': 4.391830833182722e-07, 'epoch': 1.97}
{'loss': 0.8416, 'learning_rate': 4.3647207663112235e-07, 'epoch': 1.97}
{'loss': 0.9282, 'learning_rate': 4.3376106994397253e-07, 'epoch': 1.97}
{'loss': 0.6303, 'learning_rate': 4.310500632568227e-07, 'epoch': 1.97}
{'loss': 0.5357, 'learning_rate': 4.283390565696729e-07, 'epoch': 1.97}
{'loss': 0.6424, 'learning_rate': 4.2562804988252304e-07, 'epoch': 1.97}
{'loss': 1.3173, 'learning_rate': 4.2291704319537323e-07, 'epoch': 1.97}
{'loss': 0.5124, 'learning_rate': 4.202060365082234e-07, 'epoch': 1.97}
{'loss': 0.5378, 'learning_rate': 4.174950298210736e-07, 'epoch': 1.97}
{'loss': 1.0757, 'learning_rate': 4.147840231339238e-07, 'epoch': 1.97}
{'loss': 0.5583, 'learning_rate': 4.1207301644677387e-07, 'epoch': 1.97}
{'loss': 1.1384, 'learning_rate': 4.0936200975962406e-07, 'epoch': 1.97}
{'loss': 0.5838, 'learning_rate': 4.0665100307247425e-07, 'epoch': 1.97}
{'loss': 0.548, 'learning_rate': 4.0393999638532443e-07, 'epoch': 1.97}
{'loss': 0.7062, 'learning_rate': 4.0122898969817457e-07, 'epoch': 1.97}
{'loss': 0.7535, 'learning_rate': 3.9851798301102476e-07, 'epoch': 1.97}
{'loss': 1.2658, 'learning_rate': 3.9580697632387494e-07, 'epoch': 1.97}
{'loss': 0.4446, 'learning_rate': 3.9309596963672513e-07, 'epoch': 1.97}
{'loss': 0.7511, 'learning_rate': 3.9038496294957526e-07, 'epoch': 1.97}
{'loss': 0.1788, 'learning_rate': 3.8767395626242545e-07, 'epoch': 1.97}
{'loss': 0.4641, 'learning_rate': 3.8496294957527564e-07, 'epoch': 1.97}
{'loss': 0.4811, 'learning_rate': 3.822519428881258e-07, 'epoch': 1.97}
{'loss': 0.647, 'learning_rate': 3.79540936200976e-07, 'epoch': 1.97}
{'loss': 0.3885, 'learning_rate': 3.7682992951382615e-07, 'epoch': 1.97}
{'loss': 0.5655, 'learning_rate': 3.7411892282667633e-07, 'epoch': 1.98}
{'loss': 0.7734, 'learning_rate': 3.714079161395265e-07, 'epoch': 1.98}
{'loss': 0.8253, 'learning_rate': 3.6869690945237666e-07, 'epoch': 1.98}
{'loss': 0.9247, 'learning_rate': 3.659859027652268e-07, 'epoch': 1.98}
{'loss': 1.1011, 'learning_rate': 3.63274896078077e-07, 'epoch': 1.98}
{'loss': 0.6545, 'learning_rate': 3.6056388939092717e-07, 'epoch': 1.98}
{'loss': 0.2961, 'learning_rate': 3.5785288270377735e-07, 'epoch': 1.98}
{'loss': 0.5024, 'learning_rate': 3.551418760166275e-07, 'epoch': 1.98}

 99%|█████████▉| 10936/11066 [40:06<00:28,  4.49it/s]
 99%|█████████▉| 10937/11066 [40:06<00:28,  4.48it/s]
                                                     

 99%|█████████▉| 10937/11066 [40:06<00:28,  4.48it/s]
 99%|█████████▉| 10938/11066 [40:06<00:28,  4.47it/s]
                                                     

 99%|█████████▉| 10938/11066 [40:06<00:28,  4.47it/s]
 99%|█████████▉| 10939/11066 [40:06<00:28,  4.48it/s]
                                                     

 99%|█████████▉| 10939/11066 [40:06<00:28,  4.48it/s]
 99%|█████████▉| 10940/11066 [40:07<00:28,  4.48it/s]
                                                     

 99%|█████████▉| 10940/11066 [40:07<00:28,  4.48it/s]
 99%|█████████▉| 10941/11066 [40:07<00:27,  4.48it/s]
                                                     

 99%|█████████▉| 10941/11066 [40:07<00:27,  4.48it/s]
 99%|█████████▉| 10942/11066 [40:07<00:27,  4.50it/s]
                                                     

 99%|█████████▉| 10942/11066 [40:07<00:27,  4.50it/s]
 99%|█████████▉| 10943/11066 [40:07<00:27,  4.50it/s]
                                                     

 99%|█████████▉| 10943/11066 [40:07<00:27,  4.50it/s]
 99%|█████████▉| 10944/11066 [40:07<00:27,  4.49it/s]
                                                     

 99%|█████████▉| 10944/11066 [40:07<00:27,  4.49it/s]
 99%|█████████▉| 10945/11066 [40:08<00:26,  4.50it/s]
                                                     

 99%|█████████▉| 10945/11066 [40:08<00:26,  4.50it/s]
 99%|█████████▉| 10946/11066 [40:08<00:26,  4.52it/s]
                                                     

 99%|█████████▉| 10946/11066 [40:08<00:26,  4.52it/s]
 99%|█████████▉| 10947/11066 [40:08<00:26,  4.50it/s]
                                                     

 99%|█████████▉| 10947/11066 [40:08<00:26,  4.50it/s]
 99%|█████████▉| 10948/11066 [40:08<00:26,  4.52it/s]
                                                     

 99%|█████████▉| 10948/11066 [40:08<00:26,  4.52it/s]
 99%|█████████▉| 10949/11066 [40:09<00:25,  4.51it/s]
                                                     

 99%|█████████▉| 10949/11066 [40:09<00:25,  4.51it/s]
 99%|█████████▉| 10950/11066 [40:09<00:25,  4.49it/s]
                                                     

 99%|█████████▉| 10950/11066 [40:09<00:25,  4.49it/s]
 99%|█████████▉| 10951/11066 [40:09<00:25,  4.50it/s]
                                                     

 99%|█████████▉| 10951/11066 [40:09<00:25,  4.50it/s]
 99%|█████████▉| 10952/11066 [40:09<00:25,  4.50it/s]
                                                     

 99%|█████████▉| 10952/11066 [40:09<00:25,  4.50it/s]
 99%|█████████▉| 10953/11066 [40:09<00:25,  4.50it/s]
                                                     

 99%|█████████▉| 10953/11066 [40:09<00:25,  4.50it/s]
 99%|█████████▉| 10954/11066 [40:10<00:24,  4.53it/s]
                                                     

 99%|█████████▉| 10954/11066 [40:10<00:24,  4.53it/s]
 99%|█████████▉| 10955/11066 [40:10<00:24,  4.51it/s]
                                                     

 99%|█████████▉| 10955/11066 [40:10<00:24,  4.51it/s]
 99%|█████████▉| 10956/11066 [40:10<00:24,  4.50it/s]
                                                     

 99%|█████████▉| 10956/11066 [40:10<00:24,  4.50it/s]
 99%|█████████▉| 10957/11066 [40:10<00:24,  4.49it/s]
                                                     

 99%|█████████▉| 10957/11066 [40:10<00:24,  4.49it/s]
 99%|█████████▉| 10958/11066 [40:11<00:24,  4.49it/s]
                                                     

 99%|█████████▉| 10958/11066 [40:11<00:24,  4.49it/s]
 99%|█████████▉| 10959/11066 [40:11<00:23,  4.52it/s]
                                                     

 99%|█████████▉| 10959/11066 [40:11<00:23,  4.52it/s]
 99%|█████████▉| 10960/11066 [40:11<00:23,  4.50it/s]
                                                     

 99%|█████████▉| 10960/11066 [40:11<00:23,  4.50it/s]
 99%|█████████▉| 10961/11066 [40:11<00:23,  4.50it/s]
                                                     

 99%|█████████▉| 10961/11066 [40:11<00:23,  4.50it/s]
 99%|█████████▉| 10962/11066 [40:11<00:23,  4.50it/s]
                                                     

 99%|█████████▉| 10962/11066 [40:11<00:23,  4.50it/s]
 99%|█████████▉| 10963/11066 [40:12<00:22,  4.56it/s]
                                                     

 99%|█████████▉| 10963/11066 [40:12<00:22,  4.56it/s]
 99%|█████████▉| 10964/11066 [40:12<00:22,  4.54it/s]
                                                     

 99%|█████████▉| 10964/11066 [40:12<00:22,  4.54it/s]
 99%|█████████▉| 10965/11066 [40:12<00:22,  4.53it/s]
                                                     

 99%|█████████▉| 10965/11066 [40:12<00:22,  4.53it/s]
 99%|█████████▉| 10966/11066 [40:12<00:21,  4.56it/s]
                                                     

 99%|█████████▉| 10966/11066 [40:12<00:21,  4.56it/s]
 99%|█████████▉| 10967/11066 [40:13<00:21,  4.59it/s]
                                                     

 99%|█████████▉| 10967/11066 [40:13<00:21,  4.59it/s]
 99%|█████████▉| 10968/11066 [40:13<00:21,  4.59it/s]
                                                     

 99%|█████████▉| 10968/11066 [40:13<00:21,  4.59it/s]
 99%|█████████▉| 10969/11066 [40:13<00:20,  4.62it/s]
                                                     

 99%|█████████▉| 10969/11066 [40:13<00:20,  4.62it/s]
 99%|█████████▉| 10970/11066 [40:13<00:20,  4.61it/s]
                                                     

 99%|█████████▉| 10970/11066 [40:13<00:20,  4.61it/s]
 99%|█████████▉| 10971/11066 [40:13<00:20,  4.60it/s]
                                                     

 99%|█████████▉| 10971/11066 [40:13<00:20,  4.60it/s]
 99%|█████████▉| 10972/11066 [40:14<00:20,  4.55it/s]
                                                     

 99%|█████████▉| 10972/11066 [40:14<00:20,  4.55it/s]
 99%|█████████▉| 10973/11066 [40:14<00:20,  4.53it/s]
                                                     

 99%|█████████▉| 10973/11066 [40:14<00:20,  4.53it/s]
 99%|█████████▉| 10974/11066 [40:14<00:20,  4.52it/s]
                                                     

 99%|█████████▉| 10974/11066 [40:14<00:20,  4.52it/s]
 99%|█████████▉| 10975/11066 [40:14<00:20,  4.51it/s]
                                                     

 99%|█████████▉| 10975/11066 [40:14<00:20,  4.51it/s]
 99%|█████████▉| 10976/11066 [40:14<00:19,  4.51it/s]
                                                     

 99%|█████████▉| 10976/11066 [40:14<00:19,  4.51it/s]
 99%|█████████▉| 10977/11066 [40:15<00:19,  4.51it/s]
                                                     

 99%|█████████▉| 10977/11066 [40:15<00:19,  4.51it/s]
 99%|█████████▉| 10978/11066 [40:15<00:19,  4.57it/s]
                                                     

 99%|█████████▉| 10978/11066 [40:15<00:19,  4.57it/s]
 99%|█████████▉| 10979/11066 [40:15<00:19,  4.55it/s]
                                                     

 99%|█████████▉| 10979/11066 [40:15<00:19,  4.55it/s]
 99%|█████████▉| 10980/11066 [40:15<00:18,  4.59it/s]
                                                     

 99%|█████████▉| 10980/11066 [40:15<00:18,  4.59it/s]
 99%|█████████▉| 10981/11066 [40:16<00:18,  4.57it/s]
                                                     

 99%|█████████▉| 10981/11066 [40:16<00:18,  4.57it/s]
 99%|█████████▉| 10982/11066 [40:16<00:18,  4.61it/s]
                                                     

 99%|█████████▉| 10982/11066 [40:16<00:18,  4.61it/s]
 99%|█████████▉| 10983/11066 [40:16<00:18,  4.58it/s]
                                                     

 99%|█████████▉| 10983/11066 [40:16<00:18,  4.58it/s]
 99%|█████████▉| 10984/11066 [40:16<00:17,  4.57it/s]
                                                     

 99%|█████████▉| 10984/11066 [40:16<00:17,  4.57it/s]
 99%|█████████▉| 10985/11066 [40:16<00:17,  4.54it/s]
                                                     

 99%|█████████▉| 10985/11066 [40:16<00:17,  4.54it/s]
 99%|█████████▉| 10986/11066 [40:17<00:18,  4.44it/s]
                                                     

 99%|█████████▉| 10986/11066 [40:17<00:18,  4.44it/s]
 99%|█████████▉| 10987/11066 [40:17<00:17,  4.43it/s]
                                                     

 99%|█████████▉| 10987/11066 [40:17<00:17,  4.43it/s]
 99%|█████████▉| 10988/11066 [40:17<00:17,  4.44it/s]
                                                     

 99%|█████████▉| 10988/11066 [40:17<00:17,  4.44it/s]
 99%|█████████▉| 10989/11066 [40:17<00:17,  4.46it/s]
                                                     

 99%|█████████▉| 10989/11066 [40:17<00:17,  4.46it/s]
 99%|█████████▉| 10990/11066 [40:18<00:16,  4.47it/s]
                                                     

 99%|█████████▉| 10990/11066 [40:18<00:16,  4.47it/s]
 99%|█████████▉| 10991/11066 [40:18<00:16,  4.48it/s]
                                                     

 99%|█████████▉| 10991/11066 [40:18<00:16,  4.48it/s]
 99%|█████████▉| 10992/11066 [40:18<00:16,  4.52it/s]
                                                     

 99%|█████████▉| 10992/11066 [40:18<00:16,  4.52it/s]
 99%|█████████▉| 10993/11066 [40:18<00:16,  4.49it/s]
                                                     

 99%|█████████▉| 10993/11066 [40:18<00:16,  4.49it/s]
 99%|█████████▉| 10994/11066 [40:18<00:15,  4.52it/s]
                                                     

 99%|█████████▉| 10994/11066 [40:18<00:15,  4.52it/s]
 99%|█████████▉| 10995/11066 [40:19<00:15,  4.49it/s]
                                                     

 99%|█████████▉| 10995/11066 [40:19<00:15,  4.49it/s]
 99%|█████████▉| 10996/11066 [40:19<00:15,  4.49it/s]
                                                     

 99%|█████████▉| 10996/11066 [40:19<00:15,  4.49it/s]
 99%|█████████▉| 10997/11066 [40:19<00:15,  4.49it/s]
                                                     

 99%|█████████▉| 10997/11066 [40:19<00:15,  4.49it/s]
 99%|█████████▉| 10998/11066 [40:19<00:15,  4.48it/s]
                                                     

 99%|█████████▉| 10998/11066 [40:19<00:15,  4.48it/s]
 99%|█████████▉| 10999/11066 [40:20<00:14,  4.47it/s]
                                                     

 99%|█████████▉| 10999/11066 [40:20<00:14,  4.47it/s]
 99%|█████████▉| 11000/11066 [40:20<00:14,  4.46it/s]
                                                     

 99%|█████████▉| 11000/11066 [40:20<00:14,  4.46it/s]
 99%|█████████▉| 11001/11066 [40:20<00:14,  4.47it/s]
                                                     

 99%|█████████▉| 11001/11066 [40:20<00:14,  4.47it/s]
 99%|█████████▉| 11002/11066 [40:20<00:14,  4.47it/s]
                                                     

 99%|█████████▉| 11002/11066 [40:20<00:14,  4.47it/s]
 99%|█████████▉| 11003/11066 [40:20<00:13,  4.52it/s]
                                                     

 99%|█████████▉| 11003/11066 [40:20<00:13,  4.52it/s]
 99%|█████████▉| 11004/11066 [40:21<00:13,  4.52it/s]
                                                     

 99%|█████████▉| 11004/11066 [40:21<00:13,  4.52it/s]
 99%|█████████▉| 11005/11066 [40:21<00:13,  4.57it/s]
                                                     

 99%|█████████▉| 11005/11066 [40:21<00:13,  4.57it/s]
 99%|█████████▉| 11006/11066 [40:21<00:13,  4.56it/s]
                                                     

 99%|█████████▉| 11006/11066 [40:21<00:13,  4.56it/s]
 99%|█████████▉| 11007/11066 [40:21<00:12,  4.59it/s]
                                                     

 99%|█████████▉| 11007/11066 [40:21<00:12,  4.59it/s]
 99%|█████████▉| 11008/11066 [40:22<00:12,  4.62it/s]
                                                     

 99%|█████████▉| 11008/11066 [40:22<00:12,  4.62it/s]
 99%|█████████▉| 11009/11066 [40:22<00:12,  4.61it/s]
                                                     

 99%|█████████▉| 11009/11066 [40:22<00:12,  4.61it/s]
 99%|█████████▉| 11010/11066 [40:22<00:12,  4.63it/s]
                                                     

 99%|█████████▉| 11010/11066 [40:22<00:12,  4.63it/s]
100%|█████████▉| 11011/11066 [40:22<00:11,  4.60it/s]
                                                     

100%|█████████▉| 11011/11066 [40:22<00:11,  4.60it/s]
100%|█████████▉| 11012/11066 [40:22<00:12,  4.49it/s]
                                                     

100%|█████████▉| 11012/11066 [40:22<00:12,  4.49it/s]
100%|█████████▉| 11013/11066 [40:23<00:11,  4.50it/s]
                                                     

100%|█████████▉| 11013/11066 [40:23<00:11,  4.50it/s]
100%|█████████▉| 11014/11066 [40:23<00:11,  4.58it/s]
                                                     

100%|█████████▉| 11014/11066 [40:23<00:11,  4.58it/s]
100%|█████████▉| 11015/11066 [40:23<00:10,  4.64it/s]
                                                     

100%|█████████▉| 11015/11066 [40:23<00:10,  4.64it/s]
100%|█████████▉| 11016/11066 [40:23<00:10,  4.59it/s]
                                                     

100%|█████████▉| 11016/11066 [40:23<00:10,  4.59it/s]
100%|█████████▉| 11017/11066 [40:24<00:10,  4.59it/s]
                                                     

100%|█████████▉| 11017/11066 [40:24<00:10,  4.59it/s]
100%|█████████▉| 11018/11066 [40:24<00:10,  4.64it/s]
                                                     

100%|█████████▉| 11018/11066 [40:24<00:10,  4.64it/s]
100%|█████████▉| 11019/11066 [40:24<00:10,  4.67it/s]
                                                     

100%|█████████▉| 11019/11066 [40:24<00:10,  4.67it/s]
100%|█████████▉| 11020/11066 [40:24<00:09,  4.69it/s]
                                                     

100%|█████████▉| 11020/11066 [40:24<00:09,  4.69it/s]
100%|█████████▉| 11021/11066 [40:24<00:09,  4.70it/s]
                                                     

100%|█████████▉| 11021/11066 [40:24<00:09,  4.70it/s]
100%|█████████▉| 11022/11066 [40:25<00:09,  4.63it/s]
                                                     

100%|█████████▉| 11022/11066 [40:25<00:09,  4.63it/s]
100%|█████████▉| 11023/11066 [40:25<00:09,  4.66it/s]
                                                     

100%|█████████▉| 11023/11066 [40:25<00:09,  4.66it/s]
100%|█████████▉| 11024/11066 [40:25<00:08,  4.67it/s]
                                                     

100%|█████████▉| 11024/11066 [40:25<00:08,  4.67it/s]
100%|█████████▉| 11025/11066 [40:25<00:08,  4.62it/s]
                                                     

100%|█████████▉| 11025/11066 [40:25<00:08,  4.62it/s]
100%|█████████▉| 11026/11066 [40:25<00:08,  4.57it/s]
                                                     

100%|█████████▉| 11026/11066 [40:25<00:08,  4.57it/s]
100%|█████████▉| 11027/11066 [40:26<00:08,  4.61it/s]
                                                     

100%|█████████▉| 11027/11066 [40:26<00:08,  4.61it/s]
100%|█████████▉| 11028/11066 [40:26<00:08,  4.64it/s]
                                                     

100%|█████████▉| 11028/11066 [40:26<00:08,  4.64it/s]
100%|█████████▉| 11029/11066 [40:26<00:07,  4.66it/s]
                                                     

100%|█████████▉| 11029/11066 [40:26<00:07,  4.66it/s]
100%|█████████▉| 11030/11066 [40:26<00:07,  4.65it/s]
                                                     

100%|█████████▉| 11030/11066 [40:26<00:07,  4.65it/s]
100%|█████████▉| 11031/11066 [40:27<00:07,  4.68it/s]
                                                     

100%|█████████▉| 11031/11066 [40:27<00:07,  4.68it/s]
100%|█████████▉| 11032/11066 [40:27<00:07,  4.63it/s]
                                                     

100%|█████████▉| 11032/11066 [40:27<00:07,  4.63it/s]
100%|█████████▉| 11033/11066 [40:27<00:07,  4.63it/s]
                                                     

100%|█████████▉| 11033/11066 [40:27<00:07,  4.63it/s]
100%|█████████▉| 11034/11066 [40:27<00:06,  4.62it/s]
                                                     

100%|█████████▉| 11034/11066 [40:27<00:06,  4.62it/s]
100%|█████████▉| 11035/11066 [40:27<00:06,  4.65it/s]
                                                     

100%|█████████▉| 11035/11066 [40:27<00:06,  4.65it/s]
100%|█████████▉| 11036/11066 [40:28<00:06,  4.67it/s]
                                                     

100%|█████████▉| 11036/11066 [40:28<00:06,  4.67it/s]
100%|█████████▉| 11037/11066 [40:28<00:06,  4.69it/s]
                                                     

100%|█████████▉| 11037/11066 [40:28<00:06,  4.69it/s]
100%|█████████▉| 11038/11066 [40:28<00:05,  4.69it/s]
                                                     

100%|█████████▉| 11038/11066 [40:28<00:05,  4.69it/s]
100%|█████████▉| 11039/11066 [40:28<00:05,  4.67it/s]
                                                     

100%|█████████▉| 11039/11066 [40:28<00:05,  4.67it/s]
100%|█████████▉| 11040/11066 [40:28<00:05,  4.67it/s]
                                                     

100%|█████████▉| 11040/11066 [40:28<00:05,  4.67it/s]
100%|█████████▉| 11041/11066 [40:29<00:05,  4.64it/s]
                                                     

100%|█████████▉| 11041/11066 [40:29<00:05,  4.64it/s]
100%|█████████▉| 11042/11066 [40:29<00:05,  4.68it/s]
                                                     

100%|█████████▉| 11042/11066 [40:29<00:05,  4.68it/s]
100%|█████████▉| 11043/11066 [40:29<00:04,  4.68it/s]
                                                     

100%|█████████▉| 11043/11066 [40:29<00:04,  4.68it/s]
100%|█████████▉| 11044/11066 [40:29<00:04,  4.67it/s]
                                                     

100%|█████████▉| 11044/11066 [40:29<00:04,  4.67it/s]
100%|█████████▉| 11045/11066 [40:30<00:04,  4.70it/s]
                                                     

100%|█████████▉| 11045/11066 [40:30<00:04,  4.70it/s]
100%|█████████▉| 11046/11066 [40:30<00:04,  4.72it/s]
                                                     

100%|█████████▉| 11046/11066 [40:30<00:04,  4.72it/s]
100%|█████████▉| 11047/11066 [40:30<00:04,  4.72it/s]
                                                     

100%|█████████▉| 11047/11066 [40:30<00:04,  4.72it/s]
100%|█████████▉| 11048/11066 [40:30<00:03,  4.72it/s]
                                                     

100%|█████████▉| 11048/11066 [40:30<00:03,  4.72it/s]
100%|█████████▉| 11049/11066 [40:30<00:03,  4.71it/s]
                                                     
{'loss': 1.1048, 'learning_rate': 3.524308693294777e-07, 'epoch': 1.98}
{'loss': 0.6476, 'learning_rate': 3.4971986264232786e-07, 'epoch': 1.98}
{'loss': 0.2974, 'learning_rate': 3.4700885595517805e-07, 'epoch': 1.98}
{'loss': 0.7423, 'learning_rate': 3.442978492680282e-07, 'epoch': 1.98}
{'loss': 0.7019, 'learning_rate': 3.4158684258087837e-07, 'epoch': 1.98}
{'loss': 0.654, 'learning_rate': 3.3887583589372856e-07, 'epoch': 1.98}
{'loss': 1.0116, 'learning_rate': 3.3616482920657874e-07, 'epoch': 1.98}
{'loss': 0.8012, 'learning_rate': 3.3345382251942893e-07, 'epoch': 1.98}
{'loss': 0.6982, 'learning_rate': 3.3074281583227907e-07, 'epoch': 1.98}
{'loss': 0.8199, 'learning_rate': 3.2803180914512925e-07, 'epoch': 1.98}
{'loss': 0.7294, 'learning_rate': 3.253208024579794e-07, 'epoch': 1.98}
{'loss': 0.3557, 'learning_rate': 3.226097957708296e-07, 'epoch': 1.98}
{'loss': 0.413, 'learning_rate': 3.198987890836797e-07, 'epoch': 1.98}
{'loss': 0.3363, 'learning_rate': 3.171877823965299e-07, 'epoch': 1.98}
{'loss': 0.6272, 'learning_rate': 3.144767757093801e-07, 'epoch': 1.98}
{'loss': 0.8527, 'learning_rate': 3.1176576902223027e-07, 'epoch': 1.98}
{'loss': 0.235, 'learning_rate': 3.090547623350804e-07, 'epoch': 1.98}
{'loss': 0.5767, 'learning_rate': 3.063437556479306e-07, 'epoch': 1.98}
{'loss': 0.5585, 'learning_rate': 3.036327489607808e-07, 'epoch': 1.98}
{'loss': 0.4596, 'learning_rate': 3.0092174227363097e-07, 'epoch': 1.98}
{'loss': 0.9205, 'learning_rate': 2.9821073558648115e-07, 'epoch': 1.98}
{'loss': 0.9336, 'learning_rate': 2.954997288993313e-07, 'epoch': 1.98}
{'loss': 0.8773, 'learning_rate': 2.927887222121815e-07, 'epoch': 1.98}
{'loss': 0.3223, 'learning_rate': 2.9007771552503166e-07, 'epoch': 1.98}
{'loss': 0.719, 'learning_rate': 2.8736670883788185e-07, 'epoch': 1.98}
{'loss': 0.7092, 'learning_rate': 2.84655702150732e-07, 'epoch': 1.98}
{'loss': 0.8337, 'learning_rate': 2.819446954635821e-07, 'epoch': 1.98}
{'loss': 0.6949, 'learning_rate': 2.792336887764323e-07, 'epoch': 1.98}
{'loss': 0.851, 'learning_rate': 2.765226820892825e-07, 'epoch': 1.98}
{'loss': 0.8821, 'learning_rate': 2.7381167540213263e-07, 'epoch': 1.98}
{'loss': 0.9523, 'learning_rate': 2.711006687149828e-07, 'epoch': 1.98}
{'loss': 0.7278, 'learning_rate': 2.68389662027833e-07, 'epoch': 1.98}
{'loss': 0.6208, 'learning_rate': 2.656786553406832e-07, 'epoch': 1.98}
{'loss': 0.5151, 'learning_rate': 2.629676486535334e-07, 'epoch': 1.98}
{'loss': 1.0197, 'learning_rate': 2.602566419663835e-07, 'epoch': 1.98}
{'loss': 0.6817, 'learning_rate': 2.575456352792337e-07, 'epoch': 1.98}
{'loss': 0.6522, 'learning_rate': 2.548346285920839e-07, 'epoch': 1.98}
{'loss': 0.5543, 'learning_rate': 2.5212362190493407e-07, 'epoch': 1.98}
{'loss': 0.6465, 'learning_rate': 2.494126152177842e-07, 'epoch': 1.98}
{'loss': 0.7342, 'learning_rate': 2.467016085306344e-07, 'epoch': 1.98}
{'loss': 0.9579, 'learning_rate': 2.439906018434846e-07, 'epoch': 1.98}
{'loss': 0.5579, 'learning_rate': 2.4127959515633477e-07, 'epoch': 1.98}
{'loss': 1.0729, 'learning_rate': 2.3856858846918485e-07, 'epoch': 1.98}
{'loss': 1.0067, 'learning_rate': 2.3585758178203504e-07, 'epoch': 1.98}
{'loss': 0.795, 'learning_rate': 2.3314657509488525e-07, 'epoch': 1.98}
{'loss': 0.8886, 'learning_rate': 2.304355684077354e-07, 'epoch': 1.98}
{'loss': 0.7426, 'learning_rate': 2.2772456172058557e-07, 'epoch': 1.98}
{'loss': 0.6107, 'learning_rate': 2.2501355503343576e-07, 'epoch': 1.98}
{'loss': 0.5422, 'learning_rate': 2.2230254834628592e-07, 'epoch': 1.99}
{'loss': 0.6236, 'learning_rate': 2.195915416591361e-07, 'epoch': 1.99}
{'loss': 0.6775, 'learning_rate': 2.1688053497198627e-07, 'epoch': 1.99}
{'loss': 0.3561, 'learning_rate': 2.1416952828483645e-07, 'epoch': 1.99}
{'loss': 0.3834, 'learning_rate': 2.1145852159768661e-07, 'epoch': 1.99}
{'loss': 0.5268, 'learning_rate': 2.087475149105368e-07, 'epoch': 1.99}
{'loss': 0.4498, 'learning_rate': 2.0603650822338694e-07, 'epoch': 1.99}
{'loss': 1.0319, 'learning_rate': 2.0332550153623712e-07, 'epoch': 1.99}
{'loss': 0.4949, 'learning_rate': 2.0061449484908728e-07, 'epoch': 1.99}
{'loss': 0.7002, 'learning_rate': 1.9790348816193747e-07, 'epoch': 1.99}
{'loss': 0.3424, 'learning_rate': 1.9519248147478763e-07, 'epoch': 1.99}
{'loss': 0.4705, 'learning_rate': 1.9248147478763782e-07, 'epoch': 1.99}
{'loss': 0.256, 'learning_rate': 1.89770468100488e-07, 'epoch': 1.99}
{'loss': 0.5019, 'learning_rate': 1.8705946141333817e-07, 'epoch': 1.99}
{'loss': 1.2005, 'learning_rate': 1.8434845472618833e-07, 'epoch': 1.99}
{'loss': 0.9312, 'learning_rate': 1.816374480390385e-07, 'epoch': 1.99}
{'loss': 0.731, 'learning_rate': 1.7892644135188868e-07, 'epoch': 1.99}
{'loss': 1.029, 'learning_rate': 1.7621543466473884e-07, 'epoch': 1.99}
{'loss': 0.6349, 'learning_rate': 1.7350442797758902e-07, 'epoch': 1.99}
{'loss': 0.5103, 'learning_rate': 1.7079342129043918e-07, 'epoch': 1.99}
{'loss': 0.9348, 'learning_rate': 1.6808241460328937e-07, 'epoch': 1.99}
{'loss': 0.7165, 'learning_rate': 1.6537140791613953e-07, 'epoch': 1.99}
{'loss': 0.7424, 'learning_rate': 1.626604012289897e-07, 'epoch': 1.99}
{'loss': 0.3513, 'learning_rate': 1.5994939454183985e-07, 'epoch': 1.99}
{'loss': 0.8015, 'learning_rate': 1.5723838785469004e-07, 'epoch': 1.99}
{'loss': 0.905, 'learning_rate': 1.545273811675402e-07, 'epoch': 1.99}
{'loss': 1.167, 'learning_rate': 1.518163744803904e-07, 'epoch': 1.99}
{'loss': 0.6511, 'learning_rate': 1.4910536779324058e-07, 'epoch': 1.99}
{'loss': 0.5468, 'learning_rate': 1.4639436110609074e-07, 'epoch': 1.99}
{'loss': 0.4404, 'learning_rate': 1.4368335441894092e-07, 'epoch': 1.99}
{'loss': 0.9051, 'learning_rate': 1.4097234773179106e-07, 'epoch': 1.99}
{'loss': 0.5647, 'learning_rate': 1.3826134104464125e-07, 'epoch': 1.99}
{'loss': 0.6354, 'learning_rate': 1.355503343574914e-07, 'epoch': 1.99}
{'loss': 0.6661, 'learning_rate': 1.328393276703416e-07, 'epoch': 1.99}
{'loss': 1.0375, 'learning_rate': 1.3012832098319175e-07, 'epoch': 1.99}
{'loss': 0.6944, 'learning_rate': 1.2741731429604194e-07, 'epoch': 1.99}
{'loss': 0.38, 'learning_rate': 1.247063076088921e-07, 'epoch': 1.99}
{'loss': 0.6036, 'learning_rate': 1.219953009217423e-07, 'epoch': 1.99}
{'loss': 1.2028, 'learning_rate': 1.1928429423459242e-07, 'epoch': 1.99}
{'loss': 1.0183, 'learning_rate': 1.1657328754744262e-07, 'epoch': 1.99}
{'loss': 0.6078, 'learning_rate': 1.1386228086029279e-07, 'epoch': 1.99}
{'loss': 0.474, 'learning_rate': 1.1115127417314296e-07, 'epoch': 1.99}
{'loss': 0.9146, 'learning_rate': 1.0844026748599313e-07, 'epoch': 1.99}
{'loss': 0.9846, 'learning_rate': 1.0572926079884331e-07, 'epoch': 1.99}
{'loss': 0.5561, 'learning_rate': 1.0301825411169347e-07, 'epoch': 1.99}
{'loss': 0.7157, 'learning_rate': 1.0030724742454364e-07, 'epoch': 1.99}
{'loss': 0.7976, 'learning_rate': 9.759624073739382e-08, 'epoch': 1.99}
{'loss': 0.6179, 'learning_rate': 9.4885234050244e-08, 'epoch': 1.99}
{'loss': 0.7891, 'learning_rate': 9.217422736309416e-08, 'epoch': 1.99}
{'loss': 0.5762, 'learning_rate': 8.946322067594434e-08, 'epoch': 1.99}
{'loss': 0.471, 'learning_rate': 8.675221398879451e-08, 'epoch': 1.99}
{'loss': 0.4826, 'learning_rate': 8.404120730164469e-08, 'epoch': 1.99}
{'loss': 0.7229, 'learning_rate': 8.133020061449485e-08, 'epoch': 1.99}
{'loss': 0.3919, 'learning_rate': 7.861919392734502e-08, 'epoch': 1.99}
{'loss': 0.2105, 'learning_rate': 7.59081872401952e-08, 'epoch': 1.99}
{'loss': 0.6759, 'learning_rate': 7.319718055304537e-08, 'epoch': 2.0}
{'loss': 0.5047, 'learning_rate': 7.048617386589553e-08, 'epoch': 2.0}
{'loss': 0.8142, 'learning_rate': 6.77751671787457e-08, 'epoch': 2.0}
{'loss': 0.4116, 'learning_rate': 6.506416049159588e-08, 'epoch': 2.0}
{'loss': 0.9319, 'learning_rate': 6.235315380444605e-08, 'epoch': 2.0}
{'loss': 0.5246, 'learning_rate': 5.964214711729621e-08, 'epoch': 2.0}
{'loss': 0.9541, 'learning_rate': 5.693114043014639e-08, 'epoch': 2.0}
{'loss': 0.8759, 'learning_rate': 5.422013374299657e-08, 'epoch': 2.0}
{'loss': 0.6786, 'learning_rate': 5.1509127055846734e-08, 'epoch': 2.0}
{'loss': 0.7232, 'learning_rate': 4.879812036869691e-08, 'epoch': 2.0}

100%|█████████▉| 11049/11066 [40:30<00:03,  4.71it/s]
100%|█████████▉| 11050/11066 [40:31<00:03,  4.68it/s]
                                                     

100%|█████████▉| 11050/11066 [40:31<00:03,  4.68it/s]
100%|█████████▉| 11051/11066 [40:31<00:03,  4.64it/s]
                                                     

100%|█████████▉| 11051/11066 [40:31<00:03,  4.64it/s]
100%|█████████▉| 11052/11066 [40:31<00:02,  4.69it/s]
                                                     

100%|█████████▉| 11052/11066 [40:31<00:02,  4.69it/s]
100%|█████████▉| 11053/11066 [40:31<00:02,  4.66it/s]
                                                     

100%|█████████▉| 11053/11066 [40:31<00:02,  4.66it/s]
100%|█████████▉| 11054/11066 [40:31<00:02,  4.69it/s]
                                                     

100%|█████████▉| 11054/11066 [40:31<00:02,  4.69it/s]
100%|█████████▉| 11055/11066 [40:32<00:02,  4.71it/s]
                                                     

100%|█████████▉| 11055/11066 [40:32<00:02,  4.71it/s]
100%|█████████▉| 11056/11066 [40:32<00:02,  4.64it/s]
                                                     

100%|█████████▉| 11056/11066 [40:32<00:02,  4.64it/s]
100%|█████████▉| 11057/11066 [40:32<00:01,  4.66it/s]
                                                     

100%|█████████▉| 11057/11066 [40:32<00:01,  4.66it/s]
100%|█████████▉| 11058/11066 [40:32<00:01,  4.65it/s]
                                                     

100%|█████████▉| 11058/11066 [40:32<00:01,  4.65it/s]
100%|█████████▉| 11059/11066 [40:33<00:01,  4.63it/s]
                                                     

100%|█████████▉| 11059/11066 [40:33<00:01,  4.63it/s]
100%|█████████▉| 11060/11066 [40:33<00:01,  4.59it/s]
                                                     

100%|█████████▉| 11060/11066 [40:33<00:01,  4.59it/s]
100%|█████████▉| 11061/11066 [40:33<00:01,  4.63it/s]
                                                     

100%|█████████▉| 11061/11066 [40:33<00:01,  4.63it/s]
100%|█████████▉| 11062/11066 [40:33<00:00,  4.65it/s]
                                                     

100%|█████████▉| 11062/11066 [40:33<00:00,  4.65it/s]
100%|█████████▉| 11063/11066 [40:33<00:00,  4.64it/s]
                                                     

100%|█████████▉| 11063/11066 [40:33<00:00,  4.64it/s]
100%|█████████▉| 11064/11066 [40:34<00:00,  4.65it/s]
                                                     

100%|█████████▉| 11064/11066 [40:34<00:00,  4.65it/s]
100%|█████████▉| 11065/11066 [40:34<00:00,  4.63it/s]
                                                     

100%|█████████▉| 11065/11066 [40:34<00:00,  4.63it/s]
100%|██████████| 11066/11066 [40:34<00:00,  4.94it/s]
                                                     

100%|██████████| 11066/11066 [40:34<00:00,  4.94it/s][INFO|trainer.py:1366] 2021-10-20 22:28:50,423 >> 

Training completed. Do not forget to share your model on huggingface.co/models =)



                                                     

100%|██████████| 11066/11066 [40:34<00:00,  4.94it/s]
100%|██████████| 11066/11066 [40:34<00:00,  4.55it/s]
[INFO|trainer.py:1935] 2021-10-20 22:28:50,424 >> Saving model checkpoint to bert-based-uncased-squad
[INFO|configuration_utils.py:391] 2021-10-20 22:28:50,425 >> Configuration saved in bert-based-uncased-squad/config.json
[INFO|modeling_utils.py:1001] 2021-10-20 22:28:50,902 >> Model weights saved in bert-based-uncased-squad/pytorch_model.bin
[INFO|tokenization_utils_base.py:2020] 2021-10-20 22:28:50,902 >> tokenizer config file saved in bert-based-uncased-squad/tokenizer_config.json
[INFO|tokenization_utils_base.py:2026] 2021-10-20 22:28:50,902 >> Special tokens file saved in bert-based-uncased-squad/special_tokens_map.json
{'loss': 0.1013, 'learning_rate': 4.608711368154708e-08, 'epoch': 2.0}
{'loss': 1.202, 'learning_rate': 4.3376106994397256e-08, 'epoch': 2.0}
{'loss': 0.686, 'learning_rate': 4.0665100307247423e-08, 'epoch': 2.0}
{'loss': 1.0953, 'learning_rate': 3.79540936200976e-08, 'epoch': 2.0}
{'loss': 0.4561, 'learning_rate': 3.5243086932947765e-08, 'epoch': 2.0}
{'loss': 0.4277, 'learning_rate': 3.253208024579794e-08, 'epoch': 2.0}
{'loss': 0.1749, 'learning_rate': 2.9821073558648106e-08, 'epoch': 2.0}
{'loss': 0.6099, 'learning_rate': 2.7110066871498283e-08, 'epoch': 2.0}
{'loss': 0.5117, 'learning_rate': 2.4399060184348454e-08, 'epoch': 2.0}
{'loss': 0.5277, 'learning_rate': 2.1688053497198628e-08, 'epoch': 2.0}
{'loss': 1.204, 'learning_rate': 1.89770468100488e-08, 'epoch': 2.0}
{'loss': 0.4059, 'learning_rate': 1.626604012289897e-08, 'epoch': 2.0}
{'loss': 0.8129, 'learning_rate': 1.3555033435749142e-08, 'epoch': 2.0}
{'loss': 0.474, 'learning_rate': 1.0844026748599314e-08, 'epoch': 2.0}
{'loss': 0.7607, 'learning_rate': 8.133020061449485e-09, 'epoch': 2.0}
{'loss': 0.5483, 'learning_rate': 5.422013374299657e-09, 'epoch': 2.0}
{'loss': 0.3523, 'learning_rate': 2.7110066871498285e-09, 'epoch': 2.0}
{'loss': 0.6686, 'learning_rate': 0.0, 'epoch': 2.0}
{'train_runtime': 2434.5113, 'train_samples_per_second': 72.724, 'train_steps_per_second': 4.545, 'train_loss': 1.0129275434533833, 'epoch': 2.0}
***** train metrics *****
  epoch                    =        2.0
  train_loss               =     1.0129
  train_runtime            = 0:40:34.51
  train_samples            =      88524
  train_samples_per_second =     72.724
  train_steps_per_second   =      4.545
10/20/2021 22:28:51 - INFO - __main__ - *** Evaluate ***
[INFO|trainer.py:520] 2021-10-20 22:28:51,066 >> The following columns in the evaluation set  don't have a corresponding argument in `BertForQuestionAnswering.forward` and have been ignored: example_id, offset_mapping.
[INFO|trainer.py:2181] 2021-10-20 22:28:51,068 >> ***** Running Evaluation *****
[INFO|trainer.py:2183] 2021-10-20 22:28:51,068 >>   Num examples = 10784
[INFO|trainer.py:2186] 2021-10-20 22:28:51,068 >>   Batch size = 16

  0%|          | 0/674 [00:00<?, ?it/s]
  0%|          | 3/674 [00:00<00:32, 20.86it/s]
  1%|          | 6/674 [00:00<00:40, 16.67it/s]
  1%|          | 8/674 [00:00<00:41, 15.87it/s]
  1%|▏         | 10/674 [00:00<00:43, 15.40it/s]
  2%|▏         | 12/674 [00:00<00:43, 15.12it/s]
  2%|▏         | 14/674 [00:00<00:44, 14.94it/s]
  2%|▏         | 16/674 [00:01<00:44, 14.80it/s]
  3%|▎         | 18/674 [00:01<00:44, 14.71it/s]
  3%|▎         | 20/674 [00:01<00:44, 14.66it/s]
  3%|▎         | 22/674 [00:01<00:44, 14.63it/s]
  4%|▎         | 24/674 [00:01<00:44, 14.61it/s]
  4%|▍         | 26/674 [00:01<00:44, 14.59it/s]
  4%|▍         | 28/674 [00:01<00:44, 14.58it/s]
  4%|▍         | 30/674 [00:01<00:44, 14.55it/s]
  5%|▍         | 32/674 [00:02<00:44, 14.55it/s]
  5%|▌         | 34/674 [00:02<00:43, 14.55it/s]
  5%|▌         | 36/674 [00:02<00:43, 14.56it/s]
  6%|▌         | 38/674 [00:02<00:43, 14.57it/s]
  6%|▌         | 40/674 [00:02<00:43, 14.54it/s]
  6%|▌         | 42/674 [00:02<00:43, 14.52it/s]
  7%|▋         | 44/674 [00:02<00:43, 14.54it/s]
  7%|▋         | 46/674 [00:03<00:43, 14.54it/s]
  7%|▋         | 48/674 [00:03<00:43, 14.54it/s]
  7%|▋         | 50/674 [00:03<00:42, 14.55it/s]
  8%|▊         | 52/674 [00:03<00:42, 14.54it/s]
  8%|▊         | 54/674 [00:03<00:42, 14.54it/s]
  8%|▊         | 56/674 [00:03<00:42, 14.54it/s]
  9%|▊         | 58/674 [00:03<00:42, 14.54it/s]
  9%|▉         | 60/674 [00:04<00:42, 14.54it/s]
  9%|▉         | 62/674 [00:04<00:42, 14.54it/s]
  9%|▉         | 64/674 [00:04<00:41, 14.54it/s]
 10%|▉         | 66/674 [00:04<00:41, 14.54it/s]
 10%|█         | 68/674 [00:04<00:41, 14.54it/s]
 10%|█         | 70/674 [00:04<00:41, 14.53it/s]
 11%|█         | 72/674 [00:04<00:41, 14.54it/s]
 11%|█         | 74/674 [00:05<00:41, 14.55it/s]
 11%|█▏        | 76/674 [00:05<00:41, 14.55it/s]
 12%|█▏        | 78/674 [00:05<00:40, 14.55it/s]
 12%|█▏        | 80/674 [00:05<00:40, 14.56it/s]
 12%|█▏        | 82/674 [00:05<00:40, 14.54it/s]
 12%|█▏        | 84/674 [00:05<00:40, 14.51it/s]
 13%|█▎        | 86/674 [00:05<00:40, 14.51it/s]
 13%|█▎        | 88/674 [00:05<00:40, 14.52it/s]
 13%|█▎        | 90/674 [00:06<00:40, 14.53it/s]
 14%|█▎        | 92/674 [00:06<00:40, 14.54it/s]
 14%|█▍        | 94/674 [00:06<00:39, 14.54it/s]
 14%|█▍        | 96/674 [00:06<00:39, 14.54it/s]
 15%|█▍        | 98/674 [00:06<00:39, 14.55it/s]
 15%|█▍        | 100/674 [00:06<00:39, 14.54it/s]
 15%|█▌        | 102/674 [00:06<00:39, 14.56it/s]
 15%|█▌        | 104/674 [00:07<00:39, 14.56it/s]
 16%|█▌        | 106/674 [00:07<00:39, 14.55it/s]
 16%|█▌        | 108/674 [00:07<00:38, 14.55it/s]
 16%|█▋        | 110/674 [00:07<00:38, 14.55it/s]
 17%|█▋        | 112/674 [00:07<00:38, 14.55it/s]
 17%|█▋        | 114/674 [00:07<00:38, 14.54it/s]
 17%|█▋        | 116/674 [00:07<00:38, 14.54it/s]
 18%|█▊        | 118/674 [00:08<00:38, 14.54it/s]
 18%|█▊        | 120/674 [00:08<00:38, 14.54it/s]
 18%|█▊        | 122/674 [00:08<00:37, 14.55it/s]
 18%|█▊        | 124/674 [00:08<00:37, 14.54it/s]
 19%|█▊        | 126/674 [00:08<00:37, 14.53it/s]
 19%|█▉        | 128/674 [00:08<00:37, 14.50it/s]
 19%|█▉        | 130/674 [00:08<00:37, 14.51it/s]
 20%|█▉        | 132/674 [00:09<00:37, 14.51it/s]
 20%|█▉        | 134/674 [00:09<00:37, 14.52it/s]
 20%|██        | 136/674 [00:09<00:37, 14.52it/s]
 20%|██        | 138/674 [00:09<00:36, 14.53it/s]
 21%|██        | 140/674 [00:09<00:36, 14.53it/s]
 21%|██        | 142/674 [00:09<00:36, 14.54it/s]
 21%|██▏       | 144/674 [00:09<00:36, 14.54it/s]
 22%|██▏       | 146/674 [00:09<00:36, 14.55it/s]
 22%|██▏       | 148/674 [00:10<00:36, 14.55it/s]
 22%|██▏       | 150/674 [00:10<00:36, 14.54it/s]
 23%|██▎       | 152/674 [00:10<00:35, 14.55it/s]
 23%|██▎       | 154/674 [00:10<00:35, 14.55it/s]
 23%|██▎       | 156/674 [00:10<00:35, 14.55it/s]
 23%|██▎       | 158/674 [00:10<00:35, 14.55it/s]
 24%|██▎       | 160/674 [00:10<00:35, 14.54it/s]
 24%|██▍       | 162/674 [00:11<00:35, 14.54it/s]
 24%|██▍       | 164/674 [00:11<00:35, 14.54it/s]
 25%|██▍       | 166/674 [00:11<00:34, 14.54it/s]
 25%|██▍       | 168/674 [00:11<00:34, 14.54it/s]
 25%|██▌       | 170/674 [00:11<00:34, 14.54it/s]
 26%|██▌       | 172/674 [00:11<00:34, 14.52it/s]
 26%|██▌       | 174/674 [00:11<00:34, 14.53it/s]
 26%|██▌       | 176/674 [00:12<00:34, 14.54it/s]
 26%|██▋       | 178/674 [00:12<00:34, 14.53it/s]
 27%|██▋       | 180/674 [00:12<00:33, 14.54it/s]
 27%|██▋       | 182/674 [00:12<00:33, 14.53it/s]
 27%|██▋       | 184/674 [00:12<00:33, 14.54it/s]
 28%|██▊       | 186/674 [00:12<00:33, 14.54it/s]
 28%|██▊       | 188/674 [00:12<00:33, 14.55it/s]
 28%|██▊       | 190/674 [00:13<00:33, 14.54it/s]
 28%|██▊       | 192/674 [00:13<00:33, 14.54it/s]
 29%|██▉       | 194/674 [00:13<00:33, 14.54it/s]
 29%|██▉       | 196/674 [00:13<00:32, 14.55it/s]
 29%|██▉       | 198/674 [00:13<00:32, 14.54it/s]
 30%|██▉       | 200/674 [00:13<00:32, 14.54it/s]
 30%|██▉       | 202/674 [00:13<00:32, 14.54it/s]
 30%|███       | 204/674 [00:13<00:32, 14.54it/s]
 31%|███       | 206/674 [00:14<00:32, 14.54it/s]
 31%|███       | 208/674 [00:14<00:32, 14.54it/s]
 31%|███       | 210/674 [00:14<00:31, 14.55it/s]
 31%|███▏      | 212/674 [00:14<00:31, 14.55it/s]
 32%|███▏      | 214/674 [00:14<00:31, 14.53it/s]
 32%|███▏      | 216/674 [00:14<00:31, 14.51it/s]
 32%|███▏      | 218/674 [00:14<00:31, 14.52it/s]
 33%|███▎      | 220/674 [00:15<00:31, 14.52it/s]
 33%|███▎      | 222/674 [00:15<00:31, 14.52it/s]
 33%|███▎      | 224/674 [00:15<00:30, 14.54it/s]
 34%|███▎      | 226/674 [00:15<00:30, 14.55it/s]
 34%|███▍      | 228/674 [00:15<00:30, 14.54it/s]
 34%|███▍      | 230/674 [00:15<00:30, 14.54it/s]
 34%|███▍      | 232/674 [00:15<00:30, 14.56it/s]
 35%|███▍      | 234/674 [00:16<00:30, 14.55it/s]
 35%|███▌      | 236/674 [00:16<00:30, 14.55it/s]
 35%|███▌      | 238/674 [00:16<00:29, 14.54it/s]
 36%|███▌      | 240/674 [00:16<00:29, 14.55it/s]
 36%|███▌      | 242/674 [00:16<00:29, 14.55it/s]
 36%|███▌      | 244/674 [00:16<00:29, 14.54it/s]
 36%|███▋      | 246/674 [00:16<00:29, 14.55it/s]
 37%|███▋      | 248/674 [00:16<00:29, 14.55it/s]
 37%|███▋      | 250/674 [00:17<00:29, 14.54it/s]
 37%|███▋      | 252/674 [00:17<00:29, 14.54it/s]
 38%|███▊      | 254/674 [00:17<00:28, 14.55it/s]
 38%|███▊      | 256/674 [00:17<00:28, 14.54it/s]
 38%|███▊      | 258/674 [00:17<00:28, 14.53it/s]
 39%|███▊      | 260/674 [00:17<00:28, 14.49it/s]
 39%|███▉      | 262/674 [00:17<00:28, 14.49it/s]
 39%|███▉      | 264/674 [00:18<00:28, 14.50it/s]
 39%|███▉      | 266/674 [00:18<00:28, 14.51it/s]
 40%|███▉      | 268/674 [00:18<00:27, 14.53it/s]
 40%|████      | 270/674 [00:18<00:27, 14.53it/s]
 40%|████      | 272/674 [00:18<00:27, 14.53it/s]
 41%|████      | 274/674 [00:18<00:27, 14.53it/s]
 41%|████      | 276/674 [00:18<00:27, 14.53it/s]
 41%|████      | 278/674 [00:19<00:27, 14.54it/s]
 42%|████▏     | 280/674 [00:19<00:27, 14.54it/s]
 42%|████▏     | 282/674 [00:19<00:26, 14.54it/s]
 42%|████▏     | 284/674 [00:19<00:26, 14.54it/s]
 42%|████▏     | 286/674 [00:19<00:26, 14.53it/s]
 43%|████▎     | 288/674 [00:19<00:26, 14.54it/s]
 43%|████▎     | 290/674 [00:19<00:26, 14.54it/s]
 43%|████▎     | 292/674 [00:20<00:26, 14.54it/s]
 44%|████▎     | 294/674 [00:20<00:26, 14.54it/s]
 44%|████▍     | 296/674 [00:20<00:25, 14.54it/s]
 44%|████▍     | 298/674 [00:20<00:25, 14.54it/s]
 45%|████▍     | 300/674 [00:20<00:25, 14.54it/s]
 45%|████▍     | 302/674 [00:20<00:25, 14.52it/s]
 45%|████▌     | 304/674 [00:20<00:25, 14.50it/s]
 45%|████▌     | 306/674 [00:20<00:25, 14.50it/s]
 46%|████▌     | 308/674 [00:21<00:25, 14.50it/s]
 46%|████▌     | 310/674 [00:21<00:25, 14.52it/s]
 46%|████▋     | 312/674 [00:21<00:24, 14.52it/s]
 47%|████▋     | 314/674 [00:21<00:24, 14.52it/s]
 47%|████▋     | 316/674 [00:21<00:24, 14.53it/s]
 47%|████▋     | 318/674 [00:21<00:24, 14.54it/s]
 47%|████▋     | 320/674 [00:21<00:24, 14.54it/s]
 48%|████▊     | 322/674 [00:22<00:24, 14.54it/s]
 48%|████▊     | 324/674 [00:22<00:24, 14.54it/s]
 48%|████▊     | 326/674 [00:22<00:23, 14.54it/s]
 49%|████▊     | 328/674 [00:22<00:23, 14.54it/s]
 49%|████▉     | 330/674 [00:22<00:23, 14.54it/s]
 49%|████▉     | 332/674 [00:22<00:23, 14.55it/s]
 50%|████▉     | 334/674 [00:22<00:23, 14.55it/s]
 50%|████▉     | 336/674 [00:23<00:23, 14.54it/s]
 50%|█████     | 338/674 [00:23<00:23, 14.54it/s]
 50%|█████     | 340/674 [00:23<00:22, 14.54it/s]
 51%|█████     | 342/674 [00:23<00:22, 14.54it/s]
 51%|█████     | 344/674 [00:23<00:22, 14.54it/s]
 51%|█████▏    | 346/674 [00:23<00:22, 14.53it/s]
 52%|█████▏    | 348/674 [00:23<00:22, 14.49it/s]
 52%|█████▏    | 350/674 [00:24<00:22, 14.49it/s]
 52%|█████▏    | 352/674 [00:24<00:22, 14.50it/s]
 53%|█████▎    | 354/674 [00:24<00:22, 14.51it/s]
 53%|█████▎    | 356/674 [00:24<00:21, 14.51it/s]
 53%|█████▎    | 358/674 [00:24<00:21, 14.52it/s]
 53%|█████▎    | 360/674 [00:24<00:21, 14.53it/s]
 54%|█████▎    | 362/674 [00:24<00:21, 14.52it/s]
 54%|█████▍    | 364/674 [00:24<00:21, 14.52it/s]
 54%|█████▍    | 366/674 [00:25<00:21, 14.52it/s]
 55%|█████▍    | 368/674 [00:25<00:21, 14.52it/s]
 55%|█████▍    | 370/674 [00:25<00:20, 14.52it/s]
 55%|█████▌    | 372/674 [00:25<00:20, 14.52it/s]
 55%|█████▌    | 374/674 [00:25<00:20, 14.53it/s]
 56%|█████▌    | 376/674 [00:25<00:20, 14.53it/s]
 56%|█████▌    | 378/674 [00:25<00:20, 14.53it/s]
 56%|█████▋    | 380/674 [00:26<00:20, 14.53it/s]
 57%|█████▋    | 382/674 [00:26<00:20, 14.53it/s]
 57%|█████▋    | 384/674 [00:26<00:19, 14.53it/s]
 57%|█████▋    | 386/674 [00:26<00:19, 14.53it/s]
 58%|█████▊    | 388/674 [00:26<00:19, 14.52it/s]
 58%|█████▊    | 390/674 [00:26<00:19, 14.51it/s]
 58%|█████▊    | 392/674 [00:26<00:19, 14.50it/s]
 58%|█████▊    | 394/674 [00:27<00:19, 14.50it/s]
 59%|█████▉    | 396/674 [00:27<00:19, 14.52it/s]
 59%|█████▉    | 398/674 [00:27<00:19, 14.52it/s]
 59%|█████▉    | 400/674 [00:27<00:18, 14.52it/s]
 60%|█████▉    | 402/674 [00:27<00:18, 14.52it/s]
 60%|█████▉    | 404/674 [00:27<00:18, 14.52it/s]
 60%|██████    | 406/674 [00:27<00:18, 14.52it/s]
 61%|██████    | 408/674 [00:28<00:18, 14.52it/s]
 61%|██████    | 410/674 [00:28<00:18, 14.53it/s]
 61%|██████    | 412/674 [00:28<00:18, 14.53it/s]
 61%|██████▏   | 414/674 [00:28<00:17, 14.53it/s]
 62%|██████▏   | 416/674 [00:28<00:17, 14.54it/s]
 62%|██████▏   | 418/674 [00:28<00:17, 14.54it/s]
 62%|██████▏   | 420/674 [00:28<00:17, 14.53it/s]
 63%|██████▎   | 422/674 [00:28<00:17, 14.53it/s]
 63%|██████▎   | 424/674 [00:29<00:17, 14.55it/s]
 63%|██████▎   | 426/674 [00:29<00:17, 14.55it/s]
 64%|██████▎   | 428/674 [00:29<00:16, 14.53it/s]
 64%|██████▍   | 430/674 [00:29<00:16, 14.53it/s]
 64%|██████▍   | 432/674 [00:29<00:16, 14.53it/s]
 64%|██████▍   | 434/674 [00:29<00:16, 14.50it/s]
 65%|██████▍   | 436/674 [00:29<00:16, 14.49it/s]
 65%|██████▍   | 438/674 [00:30<00:16, 14.51it/s]
 65%|██████▌   | 440/674 [00:30<00:16, 14.51it/s]
 66%|██████▌   | 442/674 [00:30<00:15, 14.51it/s]
 66%|██████▌   | 444/674 [00:30<00:15, 14.51it/s]
 66%|██████▌   | 446/674 [00:30<00:15, 14.51it/s]
 66%|██████▋   | 448/674 [00:30<00:15, 14.51it/s]
 67%|██████▋   | 450/674 [00:30<00:15, 14.52it/s]
 67%|██████▋   | 452/674 [00:31<00:15, 14.53it/s]
 67%|██████▋   | 454/674 [00:31<00:15, 14.52it/s]
 68%|██████▊   | 456/674 [00:31<00:15, 14.52it/s]
 68%|██████▊   | 458/674 [00:31<00:14, 14.52it/s]
 68%|██████▊   | 460/674 [00:31<00:14, 14.52it/s]
 69%|██████▊   | 462/674 [00:31<00:14, 14.52it/s]
 69%|██████▉   | 464/674 [00:31<00:14, 14.51it/s]
 69%|██████▉   | 466/674 [00:32<00:14, 14.52it/s]
 69%|██████▉   | 468/674 [00:32<00:14, 14.51it/s]
 70%|██████▉   | 470/674 [00:32<00:14, 14.52it/s]
 70%|███████   | 472/674 [00:32<00:13, 14.52it/s]
 70%|███████   | 474/674 [00:32<00:13, 14.53it/s]
 71%|███████   | 476/674 [00:32<00:13, 14.53it/s]
 71%|███████   | 478/674 [00:32<00:13, 14.50it/s]
 71%|███████   | 480/674 [00:32<00:13, 14.50it/s]
 72%|███████▏  | 482/674 [00:33<00:13, 14.50it/s]
 72%|███████▏  | 484/674 [00:33<00:13, 14.51it/s]
 72%|███████▏  | 486/674 [00:33<00:12, 14.53it/s]
 72%|███████▏  | 488/674 [00:33<00:12, 14.54it/s]
 73%|███████▎  | 490/674 [00:33<00:12, 14.53it/s]
 73%|███████▎  | 492/674 [00:33<00:12, 14.53it/s]
 73%|███████▎  | 494/674 [00:33<00:12, 14.54it/s]
 74%|███████▎  | 496/674 [00:34<00:12, 14.54it/s]
 74%|███████▍  | 498/674 [00:34<00:12, 14.53it/s]
 74%|███████▍  | 500/674 [00:34<00:11, 14.53it/s]
 74%|███████▍  | 502/674 [00:34<00:11, 14.53it/s]
 75%|███████▍  | 504/674 [00:34<00:11, 14.52it/s]
 75%|███████▌  | 506/674 [00:34<00:11, 14.52it/s]
 75%|███████▌  | 508/674 [00:34<00:11, 14.52it/s]
 76%|███████▌  | 510/674 [00:35<00:11, 14.52it/s]
 76%|███████▌  | 512/674 [00:35<00:11, 14.52it/s]
 76%|███████▋  | 514/674 [00:35<00:11, 14.52it/s]
 77%|███████▋  | 516/674 [00:35<00:10, 14.53it/s]
 77%|███████▋  | 518/674 [00:35<00:10, 14.52it/s]
 77%|███████▋  | 520/674 [00:35<00:10, 14.52it/s]
 77%|███████▋  | 522/674 [00:35<00:10, 14.50it/s]
 78%|███████▊  | 524/674 [00:35<00:10, 14.49it/s]
 78%|███████▊  | 526/674 [00:36<00:10, 14.49it/s]
 78%|███████▊  | 528/674 [00:36<00:10, 14.50it/s]
 79%|███████▊  | 530/674 [00:36<00:09, 14.52it/s]
 79%|███████▉  | 532/674 [00:36<00:09, 14.52it/s]
 79%|███████▉  | 534/674 [00:36<00:09, 14.52it/s]
 80%|███████▉  | 536/674 [00:36<00:09, 14.53it/s]
 80%|███████▉  | 538/674 [00:36<00:09, 14.53it/s]
 80%|████████  | 540/674 [00:37<00:09, 14.53it/s]
 80%|████████  | 542/674 [00:37<00:09, 14.53it/s]
 81%|████████  | 544/674 [00:37<00:08, 14.54it/s]
 81%|████████  | 546/674 [00:37<00:08, 14.54it/s]
 81%|████████▏ | 548/674 [00:37<00:08, 14.53it/s]
 82%|████████▏ | 550/674 [00:37<00:08, 14.53it/s]
 82%|████████▏ | 552/674 [00:37<00:08, 14.54it/s]
 82%|████████▏ | 554/674 [00:38<00:08, 14.53it/s]
 82%|████████▏ | 556/674 [00:38<00:08, 14.53it/s]
 83%|████████▎ | 558/674 [00:38<00:07, 14.53it/s]
 83%|████████▎ | 560/674 [00:38<00:07, 14.52it/s]
 83%|████████▎ | 562/674 [00:38<00:07, 14.53it/s]
 84%|████████▎ | 564/674 [00:38<00:07, 14.51it/s]
 84%|████████▍ | 566/674 [00:38<00:07, 14.50it/s]
 84%|████████▍ | 568/674 [00:39<00:07, 14.51it/s]
 85%|████████▍ | 570/674 [00:39<00:07, 14.51it/s]
 85%|████████▍ | 572/674 [00:39<00:07, 14.52it/s]
 85%|████████▌ | 574/674 [00:39<00:06, 14.52it/s]
 85%|████████▌ | 576/674 [00:39<00:06, 14.52it/s]
 86%|████████▌ | 578/674 [00:39<00:06, 14.52it/s]
 86%|████████▌ | 580/674 [00:39<00:06, 14.52it/s]
 86%|████████▋ | 582/674 [00:39<00:06, 14.52it/s]
 87%|████████▋ | 584/674 [00:40<00:06, 14.52it/s]
 87%|████████▋ | 586/674 [00:40<00:06, 14.52it/s]
 87%|████████▋ | 588/674 [00:40<00:05, 14.52it/s]
 88%|████████▊ | 590/674 [00:40<00:05, 14.52it/s]
 88%|████████▊ | 592/674 [00:40<00:05, 14.52it/s]
 88%|████████▊ | 594/674 [00:40<00:05, 14.53it/s]
 88%|████████▊ | 596/674 [00:40<00:05, 14.53it/s]
 89%|████████▊ | 598/674 [00:41<00:05, 14.53it/s]
 89%|████████▉ | 600/674 [00:41<00:05, 14.52it/s]
 89%|████████▉ | 602/674 [00:41<00:04, 14.50it/s]
 90%|████████▉ | 604/674 [00:41<00:04, 14.50it/s]
 90%|████████▉ | 606/674 [00:41<00:04, 14.51it/s]
 90%|█████████ | 608/674 [00:41<00:04, 14.50it/s]
 91%|█████████ | 610/674 [00:41<00:04, 14.49it/s]
 91%|█████████ | 612/674 [00:42<00:04, 14.50it/s]
 91%|█████████ | 614/674 [00:42<00:04, 14.53it/s]
 91%|█████████▏| 616/674 [00:42<00:03, 14.53it/s]
 92%|█████████▏| 618/674 [00:42<00:03, 14.53it/s]
 92%|█████████▏| 620/674 [00:42<00:03, 14.53it/s]
 92%|█████████▏| 622/674 [00:42<00:03, 14.53it/s]
 93%|█████████▎| 624/674 [00:42<00:03, 14.53it/s]
 93%|█████████▎| 626/674 [00:43<00:03, 14.54it/s]
 93%|█████████▎| 628/674 [00:43<00:03, 14.54it/s]
 93%|█████████▎| 630/674 [00:43<00:03, 14.53it/s]
 94%|█████████▍| 632/674 [00:43<00:02, 14.54it/s]
 94%|█████████▍| 634/674 [00:43<00:02, 14.54it/s]
 94%|█████████▍| 636/674 [00:43<00:02, 14.55it/s]
 95%|█████████▍| 638/674 [00:43<00:02, 14.54it/s]
 95%|█████████▍| 640/674 [00:43<00:02, 14.54it/s]
 95%|█████████▌| 642/674 [00:44<00:02, 14.54it/s]
 96%|█████████▌| 644/674 [00:44<00:02, 14.55it/s]
 96%|█████████▌| 646/674 [00:44<00:01, 14.54it/s]
 96%|█████████▌| 648/674 [00:44<00:01, 14.55it/s]
 96%|█████████▋| 650/674 [00:44<00:01, 14.55it/s]
 97%|█████████▋| 652/674 [00:44<00:01, 14.51it/s]
 97%|█████████▋| 654/674 [00:44<00:01, 14.48it/s]
 97%|█████████▋| 656/674 [00:45<00:01, 14.49it/s]
 98%|█████████▊| 658/674 [00:45<00:01, 14.51it/s]
 98%|█████████▊| 660/674 [00:45<00:00, 14.52it/s]
 98%|█████████▊| 662/674 [00:45<00:00, 14.52it/s]
 99%|█████████▊| 664/674 [00:45<00:00, 14.53it/s]
 99%|█████████▉| 666/674 [00:45<00:00, 14.54it/s]
 99%|█████████▉| 668/674 [00:45<00:00, 14.53it/s]
 99%|█████████▉| 670/674 [00:46<00:00, 14.53it/s]
100%|█████████▉| 672/674 [00:46<00:00, 14.54it/s]
100%|██████████| 674/674 [00:46<00:00, 14.54it/s]10/20/2021 22:29:43 - INFO - utils_qa - Post-processing 10570 example predictions split into 10784 features.


  0%|          | 0/10570 [00:00<?, ?it/s]

  1%|          | 68/10570 [00:00<00:15, 674.26it/s]

  1%|▏         | 142/10570 [00:00<00:14, 711.72it/s]

  2%|▏         | 214/10570 [00:00<00:14, 697.22it/s]

  3%|▎         | 284/10570 [00:00<00:17, 579.90it/s]

  3%|▎         | 355/10570 [00:00<00:16, 620.30it/s]

  4%|▍         | 423/10570 [00:00<00:15, 638.35it/s]

  5%|▍         | 493/10570 [00:00<00:15, 655.28it/s]

  5%|▌         | 564/10570 [00:00<00:14, 669.32it/s]

  6%|▌         | 634/10570 [00:00<00:14, 678.34it/s]

  7%|▋         | 704/10570 [00:01<00:14, 683.70it/s]

  7%|▋         | 773/10570 [00:01<00:14, 672.69it/s]

  8%|▊         | 841/10570 [00:01<00:15, 646.85it/s]

  9%|▊         | 908/10570 [00:01<00:14, 650.30it/s]

  9%|▉         | 974/10570 [00:01<00:14, 645.75it/s]

 10%|▉         | 1039/10570 [00:01<00:14, 638.94it/s]

 10%|█         | 1104/10570 [00:01<00:15, 628.65it/s]

 11%|█         | 1170/10570 [00:01<00:14, 636.67it/s]

 12%|█▏        | 1240/10570 [00:01<00:14, 652.64it/s]

 12%|█▏        | 1308/10570 [00:02<00:14, 659.23it/s]

 13%|█▎        | 1376/10570 [00:02<00:13, 664.61it/s]

 14%|█▎        | 1443/10570 [00:02<00:13, 661.90it/s]

 14%|█▍        | 1513/10570 [00:02<00:13, 670.61it/s]

 15%|█▍        | 1583/10570 [00:02<00:13, 677.04it/s]

 16%|█▌        | 1653/10570 [00:02<00:13, 681.58it/s]

 16%|█▋        | 1725/10570 [00:02<00:12, 690.81it/s]

 17%|█▋        | 1795/10570 [00:02<00:12, 688.89it/s]

 18%|█▊        | 1864/10570 [00:02<00:12, 686.60it/s]

 18%|█▊        | 1936/10570 [00:02<00:12, 693.83it/s]

 19%|█▉        | 2007/10570 [00:03<00:12, 696.88it/s]

 20%|█▉        | 2078/10570 [00:03<00:12, 699.07it/s]

 20%|██        | 2148/10570 [00:03<00:12, 660.02it/s]

 21%|██        | 2216/10570 [00:03<00:12, 664.63it/s]

 22%|██▏       | 2285/10570 [00:03<00:12, 669.90it/s]

 22%|██▏       | 2353/10570 [00:03<00:12, 671.95it/s]

 23%|██▎       | 2421/10570 [00:03<00:12, 662.84it/s]

 24%|██▎       | 2488/10570 [00:03<00:12, 657.65it/s]

 24%|██▍       | 2554/10570 [00:03<00:12, 629.21it/s]

 25%|██▍       | 2620/10570 [00:03<00:12, 636.00it/s]

 25%|██▌       | 2690/10570 [00:04<00:12, 651.97it/s]

 26%|██▌       | 2761/10570 [00:04<00:11, 666.63it/s]

 27%|██▋       | 2832/10570 [00:04<00:11, 677.53it/s]

 27%|██▋       | 2900/10570 [00:04<00:11, 667.80it/s]

 28%|██▊       | 2967/10570 [00:04<00:11, 665.89it/s]

 29%|██▊       | 3035/10570 [00:04<00:11, 667.74it/s]

 29%|██▉       | 3102/10570 [00:04<00:11, 660.26it/s]

 30%|██▉       | 3169/10570 [00:04<00:11, 643.63it/s]

 31%|███       | 3234/10570 [00:04<00:11, 637.95it/s]

 31%|███       | 3299/10570 [00:04<00:11, 639.42it/s]

 32%|███▏      | 3365/10570 [00:05<00:11, 645.23it/s]

 32%|███▏      | 3431/10570 [00:05<00:11, 648.33it/s]

 33%|███▎      | 3496/10570 [00:05<00:10, 647.44it/s]

 34%|███▎      | 3563/10570 [00:05<00:10, 651.31it/s]

 34%|███▍      | 3629/10570 [00:05<00:10, 650.33it/s]

 35%|███▍      | 3695/10570 [00:05<00:10, 650.70it/s]

 36%|███▌      | 3761/10570 [00:05<00:10, 652.75it/s]

 36%|███▌      | 3827/10570 [00:05<00:10, 653.06it/s]

 37%|███▋      | 3893/10570 [00:05<00:10, 654.89it/s]

 37%|███▋      | 3959/10570 [00:06<00:10, 655.29it/s]

 38%|███▊      | 4025/10570 [00:06<00:09, 655.75it/s]

 39%|███▊      | 4092/10570 [00:06<00:09, 659.06it/s]

 39%|███▉      | 4158/10570 [00:06<00:11, 574.61it/s]

 40%|███▉      | 4218/10570 [00:06<00:12, 518.13it/s]

 40%|████      | 4272/10570 [00:06<00:13, 480.50it/s]

 41%|████      | 4322/10570 [00:06<00:14, 433.02it/s]

 42%|████▏     | 4388/10570 [00:06<00:12, 487.48it/s]

 42%|████▏     | 4454/10570 [00:06<00:11, 530.75it/s]

 43%|████▎     | 4517/10570 [00:07<00:10, 555.60it/s]

 43%|████▎     | 4579/10570 [00:07<00:10, 571.13it/s]

 44%|████▍     | 4638/10570 [00:07<00:10, 575.11it/s]

 44%|████▍     | 4697/10570 [00:07<00:10, 573.92it/s]

 45%|████▌     | 4758/10570 [00:07<00:10, 580.38it/s]

 46%|████▌     | 4820/10570 [00:07<00:09, 590.26it/s]

 46%|████▌     | 4880/10570 [00:07<00:09, 582.34it/s]

 47%|████▋     | 4943/10570 [00:07<00:09, 594.88it/s]

 47%|████▋     | 5003/10570 [00:07<00:09, 595.80it/s]

 48%|████▊     | 5068/10570 [00:08<00:09, 609.68it/s]

 49%|████▊     | 5133/10570 [00:08<00:08, 619.49it/s]

 49%|████▉     | 5198/10570 [00:08<00:08, 626.06it/s]

 50%|████▉     | 5262/10570 [00:08<00:08, 629.09it/s]

 50%|█████     | 5330/10570 [00:08<00:08, 642.05it/s]

 51%|█████     | 5395/10570 [00:08<00:08, 641.99it/s]

 52%|█████▏    | 5460/10570 [00:08<00:08, 618.68it/s]

 52%|█████▏    | 5523/10570 [00:08<00:08, 595.15it/s]

 53%|█████▎    | 5585/10570 [00:08<00:08, 601.85it/s]

 53%|█████▎    | 5646/10570 [00:08<00:08, 603.70it/s]

 54%|█████▍    | 5707/10570 [00:09<00:08, 602.60it/s]

 55%|█████▍    | 5770/10570 [00:09<00:07, 608.43it/s]

 55%|█████▌    | 5833/10570 [00:09<00:07, 614.40it/s]

 56%|█████▌    | 5897/10570 [00:09<00:07, 619.09it/s]

 56%|█████▋    | 5961/10570 [00:09<00:07, 624.21it/s]

 57%|█████▋    | 6025/10570 [00:09<00:07, 625.97it/s]

 58%|█████▊    | 6088/10570 [00:09<00:07, 616.12it/s]

 58%|█████▊    | 6153/10570 [00:09<00:07, 624.04it/s]

 59%|█████▉    | 6217/10570 [00:09<00:06, 627.72it/s]

 59%|█████▉    | 6280/10570 [00:09<00:06, 612.96it/s]

 60%|██████    | 6345/10570 [00:10<00:06, 621.28it/s]

 61%|██████    | 6408/10570 [00:10<00:06, 611.41it/s]

 61%|██████    | 6474/10570 [00:10<00:06, 624.89it/s]

 62%|██████▏   | 6539/10570 [00:10<00:06, 629.65it/s]

 62%|██████▏   | 6603/10570 [00:10<00:06, 625.67it/s]

 63%|██████▎   | 6669/10570 [00:10<00:06, 635.65it/s]

 64%|██████▎   | 6733/10570 [00:10<00:06, 626.41it/s]

 64%|██████▍   | 6796/10570 [00:10<00:06, 625.14it/s]

 65%|██████▍   | 6859/10570 [00:10<00:06, 615.55it/s]

 65%|██████▌   | 6921/10570 [00:10<00:05, 615.86it/s]

 66%|██████▌   | 6988/10570 [00:11<00:05, 629.66it/s]

 67%|██████▋   | 7054/10570 [00:11<00:05, 637.58it/s]

 67%|██████▋   | 7120/10570 [00:11<00:05, 642.05it/s]

 68%|██████▊   | 7186/10570 [00:11<00:05, 645.69it/s]

 69%|██████▊   | 7251/10570 [00:11<00:05, 639.29it/s]

 69%|██████▉   | 7315/10570 [00:11<00:05, 639.05it/s]
100%|██████████| 674/674 [01:03<00:00, 14.54it/s]

 70%|██████▉   | 7379/10570 [00:11<00:05, 555.39it/s]

 70%|███████   | 7443/10570 [00:11<00:05, 576.91it/s]

 71%|███████   | 7508/10570 [00:11<00:05, 595.00it/s]

 72%|███████▏  | 7573/10570 [00:12<00:04, 610.26it/s]

 72%|███████▏  | 7639/10570 [00:12<00:04, 622.96it/s]

 73%|███████▎  | 7703/10570 [00:12<00:04, 618.92it/s]

 73%|███████▎  | 7766/10570 [00:12<00:04, 609.00it/s]

 74%|███████▍  | 7828/10570 [00:12<00:04, 611.61it/s]

 75%|███████▍  | 7893/10570 [00:12<00:04, 620.50it/s]

 75%|███████▌  | 7959/10570 [00:12<00:04, 630.76it/s]

 76%|███████▌  | 8023/10570 [00:12<00:04, 629.63it/s]

 77%|███████▋  | 8087/10570 [00:12<00:03, 627.59it/s]

 77%|███████▋  | 8150/10570 [00:12<00:03, 626.28it/s]

 78%|███████▊  | 8213/10570 [00:13<00:03, 615.92it/s]

 78%|███████▊  | 8275/10570 [00:13<00:03, 604.17it/s]

 79%|███████▉  | 8336/10570 [00:13<00:03, 598.58it/s]

 79%|███████▉  | 8402/10570 [00:13<00:03, 614.72it/s]

 80%|████████  | 8470/10570 [00:13<00:03, 631.19it/s]

 81%|████████  | 8535/10570 [00:13<00:03, 634.73it/s]

 81%|████████▏ | 8599/10570 [00:13<00:03, 634.21it/s]

 82%|████████▏ | 8663/10570 [00:13<00:03, 626.24it/s]

 83%|████████▎ | 8726/10570 [00:13<00:02, 624.24it/s]

 83%|████████▎ | 8789/10570 [00:14<00:02, 619.66it/s]

 84%|████████▎ | 8852/10570 [00:14<00:02, 622.44it/s]

 84%|████████▍ | 8916/10570 [00:14<00:02, 626.59it/s]

 85%|████████▍ | 8980/10570 [00:14<00:02, 630.49it/s]

 86%|████████▌ | 9044/10570 [00:14<00:02, 631.22it/s]

 86%|████████▌ | 9108/10570 [00:14<00:02, 630.76it/s]

 87%|████████▋ | 9172/10570 [00:14<00:02, 632.85it/s]

 87%|████████▋ | 9237/10570 [00:14<00:02, 637.48it/s]

 88%|████████▊ | 9303/10570 [00:14<00:01, 641.60it/s]

 89%|████████▊ | 9368/10570 [00:14<00:01, 639.33it/s]

 89%|████████▉ | 9432/10570 [00:15<00:01, 638.59it/s]

 90%|████████▉ | 9496/10570 [00:15<00:01, 638.89it/s]

 90%|█████████ | 9560/10570 [00:15<00:01, 536.50it/s]

 91%|█████████ | 9625/10570 [00:15<00:01, 565.00it/s]

 92%|█████████▏| 9691/10570 [00:15<00:01, 590.80it/s]

 92%|█████████▏| 9759/10570 [00:15<00:01, 613.77it/s]

 93%|█████████▎| 9824/10570 [00:15<00:01, 621.82it/s]

 94%|█████████▎| 9888/10570 [00:15<00:01, 622.82it/s]

 94%|█████████▍| 9953/10570 [00:15<00:00, 628.86it/s]

 95%|█████████▍| 10017/10570 [00:15<00:00, 628.57it/s]

 95%|█████████▌| 10083/10570 [00:16<00:00, 635.40it/s]

 96%|█████████▌| 10149/10570 [00:16<00:00, 640.29it/s]

 97%|█████████▋| 10214/10570 [00:16<00:00, 632.05it/s]

 97%|█████████▋| 10279/10570 [00:16<00:00, 635.05it/s]

 98%|█████████▊| 10344/10570 [00:16<00:00, 639.22it/s]

 98%|█████████▊| 10409/10570 [00:16<00:00, 633.64it/s]

 99%|█████████▉| 10473/10570 [00:16<00:00, 625.53it/s]

100%|█████████▉| 10536/10570 [00:16<00:00, 624.96it/s]
100%|██████████| 10570/10570 [00:16<00:00, 626.91it/s]10/20/2021 22:30:00 - INFO - utils_qa - Saving predictions to bert-based-uncased-squad/eval_predictions.json.
10/20/2021 22:30:00 - INFO - utils_qa - Saving nbest_preds to bert-based-uncased-squad/eval_nbest_predictions.json.
10/20/2021 22:30:03 - INFO - datasets.metric - Removing /home/vchua/.cache/huggingface/metrics/squad/default/default_experiment-1-0.arrow


100%|██████████| 674/674 [01:11<00:00,  9.37it/s]
***** eval metrics *****
  epoch            =     2.0
  eval_exact_match = 81.4853
  eval_f1          = 88.7405
  eval_samples     =   10784