The following values were not passed to `accelerate launch` and had defaults used instead:
	`--num_processes` was set to a value of `2`
		More than one GPU was found, enabling multi-GPU training.
		If this was unintended please pass in `--num_processes=1`.
	`--num_machines` was set to a value of `1`
	`--mixed_precision` was set to a value of `'no'`
	`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Using RTX 3090 or 4000 series which doesn't support faster communication speedups. Ensuring P2P and IB communications are disabled.
01/18/2024 18:29:34 - WARNING - llmtuner.model.parser - We recommend enable `upcast_layernorm` in quantized training.
01/18/2024 18:29:34 - WARNING - llmtuner.model.parser - We recommend enable mixed precision training.
01/18/2024 18:29:34 - WARNING - llmtuner.model.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
[INFO|training_args.py:1838] 2024-01-18 18:29:34,925 >> PyTorch: setting up devices
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
  warnings.warn(
01/18/2024 18:29:34 - INFO - llmtuner.model.parser - Process rank: 0, device: cuda:0, n_gpu: 1
  distributed training: True, compute dtype: None
01/18/2024 18:29:34 - INFO - llmtuner.model.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=False,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=IntervalStrategy.EPOCH,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=4,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=HubStrategy.EVERY_SAVE,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
length_column_name=length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/runs/Jan18_18-29-34_yhyu13fuwuqi,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=IntervalStrategy.STEPS,
lr_scheduler_kwargs={},
lr_scheduler_type=SchedulerType.COSINE,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=1.0,
optim=OptimizerNames.ADAMW_TORCH,
optim_args=None,
output_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=1,
per_device_train_batch_size=1,
predict_with_generate=False,
prediction_loss_only=True,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=1000,
save_strategy=IntervalStrategy.STEPS,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
01/18/2024 18:29:34 - INFO - llmtuner.data.loader - Loading dataset ./glaive-function-calling-v2-llama-factory-convert/simple-function-calling-v2_converted_2000.json...
01/18/2024 18:29:34 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
01/18/2024 18:29:35 - WARNING - llmtuner.model.parser - We recommend enable `upcast_layernorm` in quantized training.
01/18/2024 18:29:35 - WARNING - llmtuner.model.parser - We recommend enable mixed precision training.
01/18/2024 18:29:35 - WARNING - llmtuner.model.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
  warnings.warn(
01/18/2024 18:29:35 - INFO - llmtuner.model.parser - Process rank: 1, device: cuda:1, n_gpu: 1
  distributed training: True, compute dtype: None
01/18/2024 18:29:35 - INFO - llmtuner.model.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=False,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=IntervalStrategy.EPOCH,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=4,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=HubStrategy.EVERY_SAVE,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
length_column_name=length,
load_best_model_at_end=False,
local_rank=1,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/runs/Jan18_18-29-34_yhyu13fuwuqi,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=IntervalStrategy.STEPS,
lr_scheduler_kwargs={},
lr_scheduler_type=SchedulerType.COSINE,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=1.0,
optim=OptimizerNames.ADAMW_TORCH,
optim_args=None,
output_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=1,
per_device_train_batch_size=1,
predict_with_generate=False,
prediction_loss_only=True,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=1000,
save_strategy=IntervalStrategy.STEPS,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
01/18/2024 18:29:35 - INFO - llmtuner.data.loader - Loading dataset ./glaive-function-calling-v2-llama-factory-convert/simple-function-calling-v2_converted_2000.json...
01/18/2024 18:29:35 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
Using custom data configuration default-cb85ddec01d455d4
Loading Dataset Infos from /home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/datasets/packaged_modules/json
Generating dataset json (/home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
Downloading and preparing dataset json/default to /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96...
Downloading took 0.0 min
Checksum Computation took 0.0 min
Generating train split

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 6640 examples [00:00, 69564.06 examples/s]
Unable to verify splits sizes.
Dataset json downloaded and prepared to /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96. Subsequent calls will reuse this data.
[INFO|tokenization_utils_base.py:2024] 2024-01-18 18:29:36,121 >> loading file tokenizer.model
[INFO|tokenization_utils_base.py:2024] 2024-01-18 18:29:36,121 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2024] 2024-01-18 18:29:36,121 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2024] 2024-01-18 18:29:36,121 >> loading file tokenizerYhyu13/LMCocktail-10.7B-v1
[INFO|tokenization_utils_base.py:2024] 2024-01-18 18:29:36,121 >> loading file tokenizer.json
[INFO|configuration_Yhyu13/LMCocktail-10.7B-v129:36,160 >> loading configuration file ./models/LMCocktail-10.7B-v1/config.json
[INFO|configuration_utils.py:802] 2024-01-18 18:29:36,161 >> Model config LlamaConfig {
  "_name_or_path": "./models/LMCocktail-10.7B-v1",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 32000
}
Yhyu13/LMCocktail-10.7B-v1
01/18/2024 18:29:36 - INFO - llmtuner.model.patcher - Quantizing model to 4 bit.
[INFO|modeling_utils.py:3341] 2024-01-18 18:29:36,179 >> loading weights file ./models/LMCocktail-10.7B-v1/model.safetensors.index.json
[INFO|modeling_utils.py:1341] 2024-01-18 18:29:36,179 >> Instantiating LlamaForCausalLM model under default dtype torch.float16.
[INFO|configuration_utils.py:826] 2024-01-18 18:29:36,179 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 2
}

01/18/2024 18:29:36 - INFO - llmtuner.model.patcher - Quantizing model to 4 bit.
[INFO|modeling_utils.py:3483] 2024-01-18 18:29:37,052 >> Detected 4-bit loading: activating 4-bit loading for this model

Loading checkpoint shards:   0%|          | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/5 [00:00<?, ?it/s]Yhyu13/LMCocktail-10.7B-v1
Loading checkpoint shards:  20%|██        | 1/5 [00:00<00:03,  1.07it/s]
Loading checkpoint shards:  20%|██        | 1/5 [00:00<00:03,  1.02it/s]Yhyu13/LMCocktail-10.7B-v1
Loading checkpoint shards:  40%|████      | 2/5 [00:01<00:02,  1.05it/s]
Loading checkpoint shards:  40%|████      | 2/5 [00:01<00:02,  1.02it/s]
Loading checkpoint shards:  60%|██████    | 3/5 [00:02<00:01,  1.13it/s]
Loading checkpoint shards:  60%|██████    | 3/5 [00:02<00:01,  1.12it/s]
Loading checkpoint shards:  80%|████████  | 4/5 [00:03<00:00,  1.18it/s]
Loading checkpoint shards:  80%|████████  | 4/5 [00:03<00:00,  1.18it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:03<00:00,  1.46it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:03<00:00,  1.29it/s]

Loading checkpoint shards: 100%|██████████| 5/5 [00:03<00:00,  1.49it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:03<00:00,  1.28it/s]
[INFO|modeling_utils.py:4185] 2024-01-18 18:29:41,340 >> All model checkpoint weights were used when initializing LlamaForCausalLM.

[INFO|modeling_utils.py:4193] 2024-01-18 18:29:41,340 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at ./models/LMCocktail-10.7B-v1.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
[INFO|configuration_utils.py:779] 2024-01-18 18:29:41,344 >> loading configuration file ./models/LMCocktail-10.7B-v1/generation_config.json
[INFO|configuration_utils.py:826] 2024-01-18 18:29:41,344 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 2,
  "use_cache": false
}

01/18/2024 18:29:41 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
01/18/2024 18:29:41 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
01/18/2024 18:29:41 - INFO - llmtuner.model.loader - trainable params: 5111808 || all params: 10736635904 || trainable%: 0.0476
01/18/2024 18:29:41 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
01/18/2024 18:29:41 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
01/18/2024 18:29:41 - INFO - llmtuner.model.loader - trainable params: 5111808 || all params: 10736635904 || trainable%: 0.0476

Running tokenizer on dataset:   0%|          | 0/6640 [00:00<?, ? examples/s]Caching processed dataset at /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-29a204c92e15128c.arrow

Running tokenizer on dataset:  15%|█▌        | 1000/6640 [00:02<00:13, 433.18 examples/s]
Running tokenizer on dataset:  30%|███       | 2000/6640 [00:04<00:10, 437.86 examples/s]
Running tokenizer on dataset:  45%|████▌     | 3000/6640 [00:06<00:08, 446.46 examples/s]
Running tokenizer on dataset:  60%|██████    | 4000/6640 [00:09<00:05, 442.18 examples/s]
Running tokenizer on dataset:  75%|███████▌  | 5000/6640 [00:11<00:03, 460.33 examples/s]
Running tokenizer on dataset:  90%|█████████ | 6000/6640 [00:13<00:01, 454.61 examples/s]
Running tokenizer on dataset: 100%|██████████| 6640/6640 [00:14<00:00, 449.05 examples/s]
Running tokenizer on dataset: 100%|██████████| 6640/6640 [00:14<00:00, 447.75 examples/s]
input_ids:
[1, 774, 1247, 28747, 13, 27842, 28747, 995, 460, 264, 10865, 13892, 395, 2735, 298, 272, 2296, 5572, 28723, 5938, 706, 513, 3030, 387, 13, 28751, 13, 2287, 345, 861, 1264, 345, 527, 28730, 720, 4078, 28730, 6036, 548, 13, 2287, 345, 6518, 1264, 345, 1458, 272, 8877, 4338, 1444, 989, 1191, 951, 20023, 548, 13, 2287, 345, 11438, 1264, 371, 13, 5390, 345, 1123, 1264, 345, 2814, 548, 13, 5390, 345, 10723, 1264, 371, 13, 17422, 345, 2893, 28730, 16714, 1264, 371, 13, 1417, 28705, 345, 1123, 1264, 345, 1427, 548, 13, 1417, 28705, 345, 6518, 1264, 345, 1014, 15547, 298, 6603, 477, 28739, 13, 17422, 1630, 13, 17422, 345, 3731, 28730, 16714, 1264, 371, 13, 1417, 28705, 345, 1123, 1264, 345, 1427, 548, 13, 1417, 28705, 345, 6518, 1264, 345, 1014, 15547, 298, 6603, 298, 28739, 13, 17422, 443, 13, 5390, 1630, 13, 5390, 345, 10893, 1264, 733, 13, 17422, 345, 2893, 28730, 16714, 548, 13, 17422, 345, 3731, 28730, 16714, 28739, 13, 5390, 4709, 13, 2287, 443, 13, 28752, 13, 13, 6325, 368, 1820, 264, 9314, 354, 528, 477, 1450, 2726, 298, 4222, 28804, 13, 13, 27332, 21631, 28747, 13, 315, 28742, 28719, 7371, 28725, 562, 315, 949, 28742, 28707, 506, 272, 21368, 298, 1820, 22447, 28723, 1984, 1868, 908, 5976, 528, 298, 625, 272, 8877, 4338, 1444, 989, 1191, 951, 20023, 28723, 1047, 368, 927, 1316, 395, 369, 28725, 1601, 1933, 298, 1460, 28808, 2]
inputs:
<s> ### User:
SYSTEM: You are a helpful assistant with access to the following functions. Use them if required -
{
    "name": "get_exchange_rate",
    "description": "Get the exchange rate between two currencies",
    "parameters": {
        "type": "object",
        "properties": {
            "base_currency": {
                "type": "string",
                "description": "The currency to convert from"
            },
            "target_currency": {
                "type": "string",
                "description": "The currency to convert to"
            }
        },
        "required": [
            "base_currency",
            "target_currency"
        ]
    }
}

Can you book a flight for me from New York to London?

### Assistant:
 I'm sorry, but I don't have the capability to book flights. My current function allows me to get the exchange rate between two currencies. If you need help with that, feel free to ask!</s>
label_ids:
[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 315, 28742, 28719, 7371, 28725, 562, 315, 949, 28742, 28707, 506, 272, 21368, 298, 1820, 22447, 28723, 1984, 1868, 908, 5976, 528, 298, 625, 272, 8877, 4338, 1444, 989, 1191, 951, 20023, 28723, 1047, 368, 927, 1316, 395, 369, 28725, 1601, 1933, 298, 1460, 28808, 2]
labels:
 I'm sorry, but I don't have the capability to book flights. My current function allows me to get the exchange rate between two currencies. If you need help with that, feel free to ask!</s>
[INFO|training_args.py:1838] 2024-01-18 18:29:57,465 >> PyTorch: setting up devices

Running tokenizer on dataset:   0%|          | 0/6640 [00:00<?, ? examples/s]/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
  warnings.warn(
Caching indices mapping at /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-0202cc6fbd77ae6d.arrow
Caching indices mapping at /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-b938353c59a96ce3.arrow
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.

Running tokenizer on dataset:  15%|█▌        | 1000/6640 [00:02<00:13, 430.03 examples/s]
Running tokenizer on dataset:  30%|███       | 2000/6640 [00:04<00:10, 437.41 examples/s]
Running tokenizer on dataset:  45%|████▌     | 3000/6640 [00:06<00:08, 445.02 examples/s]
Running tokenizer on dataset:  60%|██████    | 4000/6640 [00:09<00:06, 439.88 examples/s]
Running tokenizer on dataset:  75%|███████▌  | 5000/6640 [00:11<00:03, 456.98 examples/s]
Running tokenizer on dataset:  90%|█████████ | 6000/6640 [00:13<00:01, 450.87 examples/s]
Running tokenizer on dataset: 100%|██████████| 6640/6640 [00:14<00:00, 445.30 examples/s]
Running tokenizer on dataset: 100%|██████████| 6640/6640 [00:14<00:00, 444.75 examples/s]
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
  warnings.warn(
[INFO|trainer.py:1706] 2024-01-18 18:30:12,809 >> ***** Running training *****
[INFO|trainer.py:1707] 2024-01-18 18:30:12,809 >>   Num examples = 5,975
[INFO|trainer.py:1708] 2024-01-18 18:30:12,809 >>   Num Epochs = 1
[INFO|trainer.py:1709] 2024-01-18 18:30:12,809 >>   Instantaneous batch size per device = 1
[INFO|trainer.py:1712] 2024-01-18 18:30:12,809 >>   Total train batch size (w. parallel, distributed & accumulation) = 8
[INFO|trainer.py:1713] 2024-01-18 18:30:12,809 >>   Gradient Accumulation steps = 4
[INFO|trainer.py:1714] 2024-01-18 18:30:12,809 >>   Total optimization steps = 747
[INFO|trainer.py:1715] 2024-01-18 18:30:12,812 >>   Number of trainable parameters = 5,111,808
01/18/2024 18:30:14 - WARNING - llmtuner.extras.callbacks - Previous log file in this folder will be deleted.

  0%|          | 0/747 [00:00<?, ?it/s]/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
  warnings.warn(
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
  warnings.warn(

  0%|          | 1/747 [00:04<54:33,  4.39s/it]
  0%|          | 2/747 [00:08<49:50,  4.01s/it]
  0%|          | 3/747 [00:11<45:28,  3.67s/it]
  1%|          | 4/747 [00:15<46:47,  3.78s/it]
  1%|          | 5/747 [00:18<45:55,  3.71s/it]
  1%|          | 6/747 [00:22<44:59,  3.64s/it]
  1%|          | 7/747 [00:25<42:55,  3.48s/it]
  1%|          | 8/747 [00:29<43:37,  3.54s/it]
  1%|          | 9/747 [00:32<42:28,  3.45s/it]
  1%|▏         | 10/747 [00:36<43:20,  3.53s/it]
                                                
{'loss': 1.6077, 'learning_rate': 4.997789428625975e-05, 'epoch': 0.01}

  1%|▏         | 10/747 [00:36<43:20,  3.53s/it]
  1%|▏         | 11/747 [00:39<44:03,  3.59s/it]
  2%|▏         | 12/747 [00:44<46:28,  3.79s/it]
  2%|▏         | 13/747 [00:47<44:55,  3.67s/it]
  2%|▏         | 14/747 [00:51<44:30,  3.64s/it]
  2%|▏         | 15/747 [00:54<43:19,  3.55s/it]
  2%|▏         | 16/747 [00:58<44:17,  3.63s/it]
  2%|▏         | 17/747 [01:02<46:13,  3.80s/it]
  2%|▏         | 18/747 [01:05<41:44,  3.44s/it]
  3%|▎         | 19/747 [01:09<46:30,  3.83s/it]
  3%|▎         | 20/747 [01:13<45:20,  3.74s/it]
                                                
{'loss': 0.9415, 'learning_rate': 4.99116162380454e-05, 'epoch': 0.03}

  3%|▎         | 20/747 [01:13<45:20,  3.74s/it]
  3%|▎         | 21/747 [01:17<46:03,  3.81s/it]
  3%|▎         | 22/747 [01:20<44:11,  3.66s/it]
  3%|▎         | 23/747 [01:24<43:54,  3.64s/it]
  3%|▎         | 24/747 [01:28<45:13,  3.75s/it]
  3%|▎         | 25/747 [01:32<45:37,  3.79s/it]
  3%|▎         | 26/747 [01:35<44:49,  3.73s/it]
  4%|▎         | 27/747 [01:38<41:58,  3.50s/it]
  4%|▎         | 28/747 [01:42<41:48,  3.49s/it]
  4%|▍         | 29/747 [01:45<41:09,  3.44s/it]
  4%|▍         | 30/747 [01:48<39:31,  3.31s/it]
                                                
{'loss': 0.6271, 'learning_rate': 4.980128306524183e-05, 'epoch': 0.04}

  4%|▍         | 30/747 [01:48<39:31,  3.31s/it]
  4%|▍         | 31/747 [01:53<44:09,  3.70s/it]
  4%|▍         | 32/747 [01:57<45:09,  3.79s/it]
  4%|▍         | 33/747 [02:01<46:56,  3.95s/it]
  5%|▍         | 34/747 [02:05<47:15,  3.98s/it]
  5%|▍         | 35/747 [02:08<43:38,  3.68s/it]
  5%|▍         | 36/747 [02:12<44:24,  3.75s/it]
  5%|▍         | 37/747 [02:15<42:45,  3.61s/it]
  5%|▌         | 38/747 [02:19<43:40,  3.70s/it]
  5%|▌         | 39/747 [02:23<45:40,  3.87s/it]
  5%|▌         | 40/747 [02:27<43:28,  3.69s/it]
                                                
{'loss': 0.5335, 'learning_rate': 4.964708988733178e-05, 'epoch': 0.05}

  5%|▌         | 40/747 [02:27<43:28,  3.69s/it]
  5%|▌         | 41/747 [02:30<42:05,  3.58s/it]
  6%|▌         | 42/747 [02:33<41:36,  3.54s/it]
  6%|▌         | 43/747 [02:37<40:13,  3.43s/it]
  6%|▌         | 44/747 [02:40<40:06,  3.42s/it]
  6%|▌         | 45/747 [02:44<43:06,  3.68s/it]
  6%|▌         | 46/747 [02:48<41:41,  3.57s/it]
  6%|▋         | 47/747 [02:51<40:40,  3.49s/it]
  6%|▋         | 48/747 [02:54<39:07,  3.36s/it]
  7%|▋         | 49/747 [02:57<39:12,  3.37s/it]
  7%|▋         | 50/747 [03:01<41:17,  3.55s/it]
                                                
{'loss': 0.3693, 'learning_rate': 4.944930938833535e-05, 'epoch': 0.07}

  7%|▋         | 50/747 [03:01<41:17,  3.55s/it]
  7%|▋         | 51/747 [03:05<41:19,  3.56s/it]
  7%|▋         | 52/747 [03:09<42:08,  3.64s/it]
  7%|▋         | 53/747 [03:13<45:41,  3.95s/it]
  7%|▋         | 54/747 [03:18<46:40,  4.04s/it]
  7%|▋         | 55/747 [03:21<45:02,  3.91s/it]
  7%|▋         | 56/747 [03:25<45:59,  3.99s/it]
  8%|▊         | 57/747 [03:29<45:45,  3.98s/it]
  8%|▊         | 58/747 [03:32<41:27,  3.61s/it]
  8%|▊         | 59/747 [03:37<44:19,  3.87s/it]
  8%|▊         | 60/747 [03:39<40:38,  3.55s/it]
                                                
{'loss': 0.47, 'learning_rate': 4.9208291334580104e-05, 'epoch': 0.08}

  8%|▊         | 60/747 [03:39<40:38,  3.55s/it]
  8%|▊         | 61/747 [03:42<38:14,  3.35s/it]
  8%|▊         | 62/747 [03:46<40:18,  3.53s/it]
  8%|▊         | 63/747 [03:50<42:07,  3.69s/it]
  9%|▊         | 64/747 [03:55<44:29,  3.91s/it]
  9%|▊         | 65/747 [03:59<44:23,  3.91s/it]
  9%|▉         | 66/747 [04:01<40:05,  3.53s/it]
  9%|▉         | 67/747 [04:05<39:24,  3.48s/it]
  9%|▉         | 68/747 [04:08<40:36,  3.59s/it]
  9%|▉         | 69/747 [04:12<41:55,  3.71s/it]
  9%|▉         | 70/747 [04:16<40:59,  3.63s/it]
                                                
{'loss': 0.4268, 'learning_rate': 4.892446195615423e-05, 'epoch': 0.09}

  9%|▉         | 70/747 [04:16<40:59,  3.63s/it]
 10%|▉         | 71/747 [04:19<40:31,  3.60s/it]
 10%|▉         | 72/747 [04:23<41:52,  3.72s/it]
 10%|▉         | 73/747 [04:26<39:10,  3.49s/it]
 10%|▉         | 74/747 [04:30<40:53,  3.65s/it]
 10%|█         | 75/747 [04:35<43:08,  3.85s/it]
 10%|█         | 76/747 [04:39<44:06,  3.94s/it]
 10%|█         | 77/747 [04:43<43:46,  3.92s/it]
 10%|█         | 78/747 [04:47<44:10,  3.96s/it]
 11%|█         | 79/747 [04:50<41:48,  3.76s/it]
 11%|█         | 80/747 [04:53<40:12,  3.62s/it]
                                                
{'loss': 0.3653, 'learning_rate': 4.859832319313697e-05, 'epoch': 0.11}

 11%|█         | 80/747 [04:53<40:12,  3.62s/it]
 11%|█         | 81/747 [04:56<38:02,  3.43s/it]
 11%|█         | 82/747 [05:01<42:36,  3.84s/it]
 11%|█         | 83/747 [05:06<44:42,  4.04s/it]
 11%|█         | 84/747 [05:10<44:48,  4.06s/it]
 11%|█▏        | 85/747 [05:13<43:07,  3.91s/it]
 12%|█▏        | 86/747 [05:17<43:07,  3.91s/it]
 12%|█▏        | 87/747 [05:21<42:03,  3.82s/it]
 12%|█▏        | 88/747 [05:24<39:53,  3.63s/it]
 12%|█▏        | 89/747 [05:28<40:23,  3.68s/it]
 12%|█▏        | 90/747 [05:31<39:12,  3.58s/it]
                                                
{'loss': 0.3466, 'learning_rate': 4.8230451807939135e-05, 'epoch': 0.12}

 12%|█▏        | 90/747 [05:31<39:12,  3.58s/it]
 12%|█▏        | 91/747 [05:35<39:19,  3.60s/it]
 12%|█▏        | 92/747 [05:38<39:28,  3.62s/it]
 12%|█▏        | 93/747 [05:41<36:37,  3.36s/it]
 13%|█▎        | 94/747 [05:45<37:12,  3.42s/it]
 13%|█▎        | 95/747 [05:48<37:15,  3.43s/it]
 13%|█▎        | 96/747 [05:52<38:25,  3.54s/it]
 13%|█▎        | 97/747 [05:55<37:57,  3.50s/it]
 13%|█▎        | 98/747 [05:59<36:53,  3.41s/it]
 13%|█▎        | 99/747 [06:03<40:22,  3.74s/it]
 13%|█▎        | 100/747 [06:07<41:25,  3.84s/it]
                                                 
{'loss': 0.3241, 'learning_rate': 4.782149836532345e-05, 'epoch': 0.13}

 13%|█▎        | 100/747 [06:07<41:25,  3.84s/it]
 14%|█▎        | 101/747 [06:12<44:22,  4.12s/it]
 14%|█▎        | 102/747 [06:15<41:30,  3.86s/it]
 14%|█▍        | 103/747 [06:19<41:29,  3.87s/it]
 14%|█▍        | 104/747 [06:22<38:59,  3.64s/it]
 14%|█▍        | 105/747 [06:26<40:53,  3.82s/it]
 14%|█▍        | 106/747 [06:31<42:15,  3.96s/it]
 14%|█▍        | 107/747 [06:37<48:17,  4.53s/it]
 14%|█▍        | 108/747 [06:40<44:45,  4.20s/it]
 15%|█▍        | 109/747 [06:44<43:11,  4.06s/it]
 15%|█▍        | 110/747 [06:47<41:15,  3.89s/it]
                                                 
{'loss': 0.3763, 'learning_rate': 4.737218608190878e-05, 'epoch': 0.15}

 15%|█▍        | 110/747 [06:47<41:15,  3.89s/it]
 15%|█▍        | 111/747 [06:52<43:19,  4.09s/it]
 15%|█▍        | 112/747 [06:54<38:03,  3.60s/it]
 15%|█▌        | 113/747 [06:58<36:59,  3.50s/it]
 15%|█▌        | 114/747 [07:02<40:07,  3.80s/it]
 15%|█▌        | 115/747 [07:06<40:10,  3.81s/it]
 16%|█▌        | 116/747 [07:09<38:19,  3.64s/it]
 16%|█▌        | 117/747 [07:14<42:37,  4.06s/it]
 16%|█▌        | 118/747 [07:19<43:59,  4.20s/it]
 16%|█▌        | 119/747 [07:22<40:29,  3.87s/it]
 16%|█▌        | 120/747 [07:25<39:00,  3.73s/it]
                                                 
{'loss': 0.3333, 'learning_rate': 4.6883309547192476e-05, 'epoch': 0.16}

 16%|█▌        | 120/747 [07:25<39:00,  3.73s/it]
 16%|█▌        | 121/747 [07:28<36:38,  3.51s/it]
 16%|█▋        | 122/747 [07:32<35:52,  3.44s/it]
 16%|█▋        | 123/747 [07:35<37:16,  3.58s/it]
 17%|█▋        | 124/747 [07:38<34:36,  3.33s/it]
 17%|█▋        | 125/747 [07:41<33:52,  3.27s/it]
 17%|█▋        | 126/747 [07:45<35:12,  3.40s/it]
 17%|█▋        | 127/747 [07:49<37:30,  3.63s/it]
 17%|█▋        | 128/747 [07:53<36:49,  3.57s/it]
 17%|█▋        | 129/747 [07:58<40:54,  3.97s/it]
 17%|█▋        | 130/747 [08:01<39:22,  3.83s/it]
                                                 
{'loss': 0.3106, 'learning_rate': 4.635573331835302e-05, 'epoch': 0.17}

 17%|█▋        | 130/747 [08:01<39:22,  3.83s/it]
 18%|█▊        | 131/747 [08:05<38:38,  3.76s/it]
 18%|█▊        | 132/747 [08:08<37:52,  3.69s/it]
 18%|█▊        | 133/747 [08:13<41:27,  4.05s/it]
 18%|█▊        | 134/747 [08:17<41:13,  4.04s/it]
 18%|█▊        | 135/747 [08:21<39:56,  3.92s/it]
 18%|█▊        | 136/747 [08:24<37:38,  3.70s/it]
 18%|█▊        | 137/747 [08:28<37:42,  3.71s/it]
 18%|█▊        | 138/747 [08:32<39:26,  3.89s/it]
 19%|█▊        | 139/747 [08:36<38:49,  3.83s/it]
 19%|█▊        | 140/747 [08:39<37:55,  3.75s/it]
                                                 
{'loss': 0.3241, 'learning_rate': 4.5790390391317675e-05, 'epoch': 0.19}

 19%|█▊        | 140/747 [08:39<37:55,  3.75s/it]
 19%|█▉        | 141/747 [08:44<42:15,  4.18s/it]
 19%|█▉        | 142/747 [08:47<37:44,  3.74s/it]
 19%|█▉        | 143/747 [08:50<34:41,  3.45s/it]
 19%|█▉        | 144/747 [08:53<32:34,  3.24s/it]
 19%|█▉        | 145/747 [08:56<33:42,  3.36s/it]
 20%|█▉        | 146/747 [09:00<34:12,  3.41s/it]
 20%|█▉        | 147/747 [09:04<35:27,  3.55s/it]
 20%|█▉        | 148/747 [09:08<36:34,  3.66s/it]
 20%|█▉        | 149/747 [09:11<35:01,  3.51s/it]
 20%|██        | 150/747 [09:15<36:44,  3.69s/it]
                                                 
{'loss': 0.2781, 'learning_rate': 4.518828055079925e-05, 'epoch': 0.2}

 20%|██        | 150/747 [09:15<36:44,  3.69s/it]
 20%|██        | 151/747 [09:18<36:25,  3.67s/it]
 20%|██        | 152/747 [09:23<38:47,  3.91s/it]
 20%|██        | 153/747 [09:26<36:17,  3.67s/it]
 21%|██        | 154/747 [09:30<37:02,  3.75s/it]
 21%|██        | 155/747 [09:33<36:17,  3.68s/it]
 21%|██        | 156/747 [09:38<38:21,  3.89s/it]
 21%|██        | 157/747 [09:42<39:22,  4.00s/it]
 21%|██        | 158/747 [09:46<38:14,  3.90s/it]
 21%|██▏       | 159/747 [09:49<36:44,  3.75s/it]
 21%|██▏       | 160/747 [09:54<38:24,  3.93s/it]
                                                 
{'loss': 0.3, 'learning_rate': 4.4550468602219716e-05, 'epoch': 0.21}

 21%|██▏       | 160/747 [09:54<38:24,  3.93s/it]
 22%|██▏       | 161/747 [09:57<38:16,  3.92s/it]
 22%|██▏       | 162/747 [10:01<37:12,  3.82s/it]
 22%|██▏       | 163/747 [10:05<37:25,  3.84s/it]
 22%|██▏       | 164/747 [10:09<37:19,  3.84s/it]
 22%|██▏       | 165/747 [10:12<36:11,  3.73s/it]
 22%|██▏       | 166/747 [10:15<33:07,  3.42s/it]
 22%|██▏       | 167/747 [10:19<36:10,  3.74s/it]
 22%|██▏       | 168/747 [10:23<34:50,  3.61s/it]
 23%|██▎       | 169/747 [10:25<32:16,  3.35s/it]
 23%|██▎       | 170/747 [10:29<33:14,  3.46s/it]
                                                 
{'loss': 0.3229, 'learning_rate': 4.387808248864751e-05, 'epoch': 0.23}

 23%|██▎       | 170/747 [10:29<33:14,  3.46s/it]
 23%|██▎       | 171/747 [10:32<32:23,  3.37s/it]
 23%|██▎       | 172/747 [10:36<32:28,  3.39s/it]
 23%|██▎       | 173/747 [10:40<34:55,  3.65s/it]
 23%|██▎       | 174/747 [10:44<36:24,  3.81s/it]
 23%|██▎       | 175/747 [10:48<35:55,  3.77s/it]
 24%|██▎       | 176/747 [10:52<36:41,  3.86s/it]
 24%|██▎       | 177/747 [10:55<33:11,  3.49s/it]
 24%|██▍       | 178/747 [10:58<31:57,  3.37s/it]
 24%|██▍       | 179/747 [11:02<33:24,  3.53s/it]
 24%|██▍       | 180/747 [11:05<33:06,  3.50s/it]
                                                 
{'loss': 0.3347, 'learning_rate': 4.3172311296078595e-05, 'epoch': 0.24}

 24%|██▍       | 180/747 [11:05<33:06,  3.50s/it]
 24%|██▍       | 181/747 [11:08<31:05,  3.30s/it]
 24%|██▍       | 182/747 [11:12<33:42,  3.58s/it]
 24%|██▍       | 183/747 [11:17<36:09,  3.85s/it]
 25%|██▍       | 184/747 [11:19<33:27,  3.57s/it]
 25%|██▍       | 185/747 [11:23<34:03,  3.64s/it]
 25%|██▍       | 186/747 [11:27<34:45,  3.72s/it]
 25%|██▌       | 187/747 [11:30<33:20,  3.57s/it]
 25%|██▌       | 188/747 [11:35<36:27,  3.91s/it]
 25%|██▌       | 189/747 [11:38<34:23,  3.70s/it]
 25%|██▌       | 190/747 [11:42<34:15,  3.69s/it]
                                                 
{'loss': 0.2897, 'learning_rate': 4.2434403150588895e-05, 'epoch': 0.25}

 25%|██▌       | 190/747 [11:42<34:15,  3.69s/it]
 26%|██▌       | 191/747 [11:45<33:34,  3.62s/it]
 26%|██▌       | 192/747 [11:48<31:47,  3.44s/it]
 26%|██▌       | 193/747 [11:51<30:28,  3.30s/it]
 26%|██▌       | 194/747 [11:55<31:25,  3.41s/it]
 26%|██▌       | 195/747 [11:58<29:39,  3.22s/it]
 26%|██▌       | 196/747 [12:02<30:50,  3.36s/it]
 26%|██▋       | 197/747 [12:05<31:53,  3.48s/it]
 27%|██▋       | 198/747 [12:09<33:28,  3.66s/it]
 27%|██▋       | 199/747 [12:15<38:03,  4.17s/it]
 27%|██▋       | 200/747 [12:18<36:06,  3.96s/it]
                                                 
{'loss': 0.2951, 'learning_rate': 4.166566301107687e-05, 'epoch': 0.27}

 27%|██▋       | 200/747 [12:18<36:06,  3.96s/it]
 27%|██▋       | 201/747 [12:22<36:42,  4.03s/it]
 27%|██▋       | 202/747 [12:26<34:31,  3.80s/it]
 27%|██▋       | 203/747 [12:28<31:49,  3.51s/it]
 27%|██▋       | 204/747 [12:32<30:31,  3.37s/it]
 27%|██▋       | 205/747 [12:36<34:19,  3.80s/it]
 28%|██▊       | 206/747 [12:40<34:05,  3.78s/it]
 28%|██▊       | 207/747 [12:43<32:30,  3.61s/it]
 28%|██▊       | 208/747 [12:48<34:48,  3.88s/it]
 28%|██▊       | 209/747 [12:52<35:24,  3.95s/it]
 28%|██▊       | 210/747 [12:56<34:42,  3.88s/it]
                                                 
{'loss': 0.3081, 'learning_rate': 4.08674503614997e-05, 'epoch': 0.28}

 28%|██▊       | 210/747 [12:56<34:42,  3.88s/it]
 28%|██▊       | 211/747 [12:58<31:40,  3.55s/it]
 28%|██▊       | 212/747 [13:02<32:41,  3.67s/it]
 29%|██▊       | 213/747 [13:06<33:28,  3.76s/it]
 29%|██▊       | 214/747 [13:09<31:33,  3.55s/it]
 29%|██▉       | 215/747 [13:12<29:31,  3.33s/it]
 29%|██▉       | 216/747 [13:15<27:28,  3.11s/it]
 29%|██▉       | 217/747 [13:18<27:45,  3.14s/it]
 29%|██▉       | 218/747 [13:22<29:51,  3.39s/it]
 29%|██▉       | 219/747 [13:25<29:47,  3.39s/it]
 29%|██▉       | 220/747 [13:29<30:09,  3.43s/it]
                                                 
{'loss': 0.2889, 'learning_rate': 4.004117680668422e-05, 'epoch': 0.29}

 29%|██▉       | 220/747 [13:29<30:09,  3.43s/it]
 30%|██▉       | 221/747 [13:33<32:02,  3.66s/it]
 30%|██▉       | 222/747 [13:37<32:55,  3.76s/it]
 30%|██▉       | 223/747 [13:40<30:43,  3.52s/it]
 30%|██▉       | 224/747 [13:44<31:34,  3.62s/it]
 30%|███       | 225/747 [13:47<30:05,  3.46s/it]
 30%|███       | 226/747 [13:51<31:34,  3.64s/it]
 30%|███       | 227/747 [13:55<31:12,  3.60s/it]
 31%|███       | 228/747 [13:58<30:46,  3.56s/it]
 31%|███       | 229/747 [14:02<32:10,  3.73s/it]
 31%|███       | 230/747 [14:05<30:22,  3.53s/it]
                                                 
{'loss': 0.3207, 'learning_rate': 3.918830357596434e-05, 'epoch': 0.31}

 31%|███       | 230/747 [14:05<30:22,  3.53s/it]
 31%|███       | 231/747 [14:09<29:49,  3.47s/it]
 31%|███       | 232/747 [14:11<27:52,  3.25s/it]
 31%|███       | 233/747 [14:15<28:27,  3.32s/it]
 31%|███▏      | 234/747 [14:19<31:13,  3.65s/it]
 31%|███▏      | 235/747 [14:23<30:54,  3.62s/it]
 32%|███▏      | 236/747 [14:26<30:58,  3.64s/it]
 32%|███▏      | 237/747 [14:30<30:51,  3.63s/it]
 32%|███▏      | 238/747 [14:33<29:34,  3.49s/it]
 32%|███▏      | 239/747 [14:37<30:50,  3.64s/it]
 32%|███▏      | 240/747 [14:41<31:15,  3.70s/it]
                                                 
{'loss': 0.3238, 'learning_rate': 3.8310338939059644e-05, 'epoch': 0.32}

 32%|███▏      | 240/747 [14:41<31:15,  3.70s/it]
 32%|███▏      | 241/747 [14:44<29:48,  3.54s/it]
 32%|███▏      | 242/747 [14:48<30:35,  3.64s/it]
 33%|███▎      | 243/747 [14:52<30:21,  3.61s/it]
 33%|███▎      | 244/747 [14:55<28:37,  3.41s/it]
 33%|███▎      | 245/747 [14:59<31:20,  3.75s/it]
 33%|███▎      | 246/747 [15:02<29:54,  3.58s/it]
 33%|███▎      | 247/747 [15:07<32:33,  3.91s/it]
 33%|███▎      | 248/747 [15:11<31:53,  3.83s/it]
 33%|███▎      | 249/747 [15:14<31:42,  3.82s/it]
 33%|███▎      | 250/747 [15:19<32:55,  3.97s/it]
                                                 
{'loss': 0.3146, 'learning_rate': 3.740883553876515e-05, 'epoch': 0.33}

 33%|███▎      | 250/747 [15:19<32:55,  3.97s/it]
 34%|███▎      | 251/747 [15:21<29:56,  3.62s/it]
 34%|███▎      | 252/747 [15:25<29:02,  3.52s/it]
 34%|███▍      | 253/747 [15:29<30:12,  3.67s/it]
 34%|███▍      | 254/747 [15:33<31:18,  3.81s/it]
 34%|███▍      | 255/747 [15:36<29:19,  3.58s/it]
 34%|███▍      | 256/747 [15:40<29:38,  3.62s/it]
 34%|███▍      | 257/747 [15:43<28:42,  3.52s/it]
 35%|███▍      | 258/747 [15:46<28:25,  3.49s/it]
 35%|███▍      | 259/747 [15:51<30:08,  3.71s/it]
 35%|███▍      | 260/747 [15:53<27:24,  3.38s/it]
                                                 
{'loss': 0.2973, 'learning_rate': 3.6485387645169064e-05, 'epoch': 0.35}

 35%|███▍      | 260/747 [15:53<27:24,  3.38s/it]
 35%|███▍      | 261/747 [15:56<26:44,  3.30s/it]
 35%|███▌      | 262/747 [16:01<30:54,  3.82s/it]
 35%|███▌      | 263/747 [16:06<31:42,  3.93s/it]
 35%|███▌      | 264/747 [16:10<31:44,  3.94s/it]
 35%|███▌      | 265/747 [16:13<30:03,  3.74s/it]
 36%|███▌      | 266/747 [16:16<29:29,  3.68s/it]
 36%|███▌      | 267/747 [16:19<27:48,  3.48s/it]
 36%|███▌      | 268/747 [16:22<26:56,  3.38s/it]
 36%|███▌      | 269/747 [16:28<31:05,  3.90s/it]
 36%|███▌      | 270/747 [16:31<30:10,  3.80s/it]
                                                 
{'loss': 0.2631, 'learning_rate': 3.55416283362546e-05, 'epoch': 0.36}

 36%|███▌      | 270/747 [16:31<30:10,  3.80s/it]
 36%|███▋      | 271/747 [16:34<28:19,  3.57s/it]
 36%|███▋      | 272/747 [16:38<29:35,  3.74s/it]
 37%|███▋      | 273/747 [16:43<30:40,  3.88s/it]
 37%|███▋      | 274/747 [16:47<31:42,  4.02s/it]
 37%|███▋      | 275/747 [16:50<30:05,  3.82s/it]
 37%|███▋      | 276/747 [16:53<27:42,  3.53s/it]
 37%|███▋      | 277/747 [16:57<28:02,  3.58s/it]
 37%|███▋      | 278/747 [17:01<29:24,  3.76s/it]
 37%|███▋      | 279/747 [17:06<32:38,  4.19s/it]
 37%|███▋      | 280/747 [17:10<31:54,  4.10s/it]
                                                 
{'loss': 0.3323, 'learning_rate': 3.457922660987155e-05, 'epoch': 0.37}

 37%|███▋      | 280/747 [17:10<31:54,  4.10s/it]
 38%|███▊      | 281/747 [17:14<30:23,  3.91s/it]
 38%|███▊      | 282/747 [17:16<28:03,  3.62s/it]
 38%|███▊      | 283/747 [17:19<26:24,  3.41s/it]
 38%|███▊      | 284/747 [17:23<27:14,  3.53s/it]
 38%|███▊      | 285/747 [17:28<30:37,  3.98s/it]
 38%|███▊      | 286/747 [17:31<28:22,  3.69s/it]
 38%|███▊      | 287/747 [17:35<28:54,  3.77s/it]
 39%|███▊      | 288/747 [17:39<29:30,  3.86s/it]
 39%|███▊      | 289/747 [17:44<31:03,  4.07s/it]
 39%|███▉      | 290/747 [17:47<29:35,  3.89s/it]
                                                 
{'loss': 0.2631, 'learning_rate': 3.3599884432185225e-05, 'epoch': 0.39}

 39%|███▉      | 290/747 [17:47<29:35,  3.89s/it]
 39%|███▉      | 291/747 [17:50<27:37,  3.64s/it]
 39%|███▉      | 292/747 [17:54<27:43,  3.66s/it]
 39%|███▉      | 293/747 [17:58<27:38,  3.65s/it]
 39%|███▉      | 294/747 [18:02<28:30,  3.78s/it]
 39%|███▉      | 295/747 [18:05<28:08,  3.74s/it]
 40%|███▉      | 296/747 [18:08<25:59,  3.46s/it]
 40%|███▉      | 297/747 [18:11<25:10,  3.36s/it]
 40%|███▉      | 298/747 [18:15<25:36,  3.42s/it]
 40%|████      | 299/747 [18:18<25:07,  3.37s/it]
 40%|████      | 300/747 [18:22<26:27,  3.55s/it]
                                                 
{'loss': 0.3066, 'learning_rate': 3.260533372782234e-05, 'epoch': 0.4}

 40%|████      | 300/747 [18:22<26:27,  3.55s/it]
 40%|████      | 301/747 [18:26<26:38,  3.58s/it]
 40%|████      | 302/747 [18:29<25:58,  3.50s/it]
 41%|████      | 303/747 [18:33<26:09,  3.53s/it]
 41%|████      | 304/747 [18:37<27:24,  3.71s/it]
 41%|████      | 305/747 [18:41<27:28,  3.73s/it]
 41%|████      | 306/747 [18:44<25:59,  3.54s/it]
 41%|████      | 307/747 [18:47<25:11,  3.44s/it]
 41%|████      | 308/747 [18:50<23:23,  3.20s/it]
 41%|████▏     | 309/747 [18:53<24:38,  3.38s/it]
 41%|████▏     | 310/747 [18:58<27:17,  3.75s/it]
                                                 
{'loss': 0.3131, 'learning_rate': 3.1597333317036545e-05, 'epoch': 0.41}

 41%|████▏     | 310/747 [18:58<27:17,  3.75s/it]
 42%|████▏     | 311/747 [19:02<26:54,  3.70s/it]
 42%|████▏     | 312/747 [19:06<27:53,  3.85s/it]
 42%|████▏     | 313/747 [19:09<27:12,  3.76s/it]
 42%|████▏     | 314/747 [19:14<28:19,  3.92s/it]
 42%|████▏     | 315/747 [19:18<28:29,  3.96s/it]
 42%|████▏     | 316/747 [19:22<28:38,  3.99s/it]
 42%|████▏     | 317/747 [19:25<28:05,  3.92s/it]
 43%|████▎     | 318/747 [19:29<27:32,  3.85s/it]
 43%|████▎     | 319/747 [19:33<27:06,  3.80s/it]
 43%|████▎     | 320/747 [19:36<25:10,  3.54s/it]
                                                 
{'loss': 0.3101, 'learning_rate': 3.057766580531031e-05, 'epoch': 0.43}

 43%|████▎     | 320/747 [19:36<25:10,  3.54s/it]
 43%|████▎     | 321/747 [19:40<26:27,  3.73s/it]
 43%|████▎     | 322/747 [19:44<26:45,  3.78s/it]
 43%|████▎     | 323/747 [19:48<26:43,  3.78s/it]
 43%|████▎     | 324/747 [19:51<26:41,  3.79s/it]
 44%|████▎     | 325/747 [19:56<28:04,  3.99s/it]
 44%|████▎     | 326/747 [19:59<26:53,  3.83s/it]
 44%|████▍     | 327/747 [20:03<26:20,  3.76s/it]
 44%|████▍     | 328/747 [20:07<26:03,  3.73s/it]
 44%|████▍     | 329/747 [20:10<25:26,  3.65s/it]
 44%|████▍     | 330/747 [20:14<25:58,  3.74s/it]
                                                 
{'loss': 0.3022, 'learning_rate': 2.9548134430893604e-05, 'epoch': 0.44}

 44%|████▍     | 330/747 [20:14<25:58,  3.74s/it]
 44%|████▍     | 331/747 [20:16<23:05,  3.33s/it]
 44%|████▍     | 332/747 [20:20<23:44,  3.43s/it]
 45%|████▍     | 333/747 [20:24<25:23,  3.68s/it]
 45%|████▍     | 334/747 [20:28<26:10,  3.80s/it]
 45%|████▍     | 335/747 [20:32<24:53,  3.63s/it]
 45%|████▍     | 336/747 [20:35<24:15,  3.54s/it]
 45%|████▌     | 337/747 [20:39<24:43,  3.62s/it]
 45%|████▌     | 338/747 [20:42<23:51,  3.50s/it]
 45%|████▌     | 339/747 [20:46<24:14,  3.56s/it]
 46%|████▌     | 340/747 [20:49<24:44,  3.65s/it]
                                                 
{'loss': 0.2496, 'learning_rate': 2.8510559875854377e-05, 'epoch': 0.46}

 46%|████▌     | 340/747 [20:49<24:44,  3.65s/it]
 46%|████▌     | 341/747 [20:53<23:45,  3.51s/it]
 46%|████▌     | 342/747 [20:57<25:42,  3.81s/it]
 46%|████▌     | 343/747 [21:01<25:21,  3.77s/it]
 46%|████▌     | 344/747 [21:04<23:59,  3.57s/it]
 46%|████▌     | 345/747 [21:08<24:33,  3.67s/it]
 46%|████▋     | 346/747 [21:12<24:37,  3.68s/it]
 46%|████▋     | 347/747 [21:15<23:11,  3.48s/it]
 47%|████▋     | 348/747 [21:18<22:02,  3.32s/it]
 47%|████▋     | 349/747 [21:21<21:53,  3.30s/it]
 47%|████▋     | 350/747 [21:25<22:54,  3.46s/it]
                                                 
{'loss': 0.3218, 'learning_rate': 2.7466777046280457e-05, 'epoch': 0.47}

 47%|████▋     | 350/747 [21:25<22:54,  3.46s/it]
 47%|████▋     | 351/747 [21:28<22:22,  3.39s/it]
 47%|████▋     | 352/747 [21:32<23:56,  3.64s/it]
 47%|████▋     | 353/747 [21:37<26:17,  4.00s/it]
 47%|████▋     | 354/747 [21:40<23:24,  3.57s/it]
 48%|████▊     | 355/747 [21:43<22:47,  3.49s/it]
 48%|████▊     | 356/747 [21:47<23:38,  3.63s/it]
 48%|████▊     | 357/747 [21:50<22:17,  3.43s/it]
 48%|████▊     | 358/747 [21:53<21:12,  3.27s/it]
 48%|████▊     | 359/747 [21:56<20:35,  3.18s/it]
 48%|████▊     | 360/747 [21:59<21:31,  3.34s/it]
                                                 
{'loss': 0.3064, 'learning_rate': 2.6418631827326857e-05, 'epoch': 0.48}

 48%|████▊     | 360/747 [21:59<21:31,  3.34s/it]
 48%|████▊     | 361/747 [22:04<23:59,  3.73s/it]
 48%|████▊     | 362/747 [22:07<22:55,  3.57s/it]
 49%|████▊     | 363/747 [22:10<21:20,  3.34s/it]
 49%|████▊     | 364/747 [22:14<22:11,  3.48s/it]
 49%|████▉     | 365/747 [22:19<25:17,  3.97s/it]
 49%|████▉     | 366/747 [22:22<23:48,  3.75s/it]
 49%|████▉     | 367/747 [22:26<23:32,  3.72s/it]
 49%|████▉     | 368/747 [22:29<23:10,  3.67s/it]
 49%|████▉     | 369/747 [22:34<24:19,  3.86s/it]
 50%|████▉     | 370/747 [22:38<25:14,  4.02s/it]
                                                 
{'loss': 0.2937, 'learning_rate': 2.5367977818847034e-05, 'epoch': 0.5}

 50%|████▉     | 370/747 [22:38<25:14,  4.02s/it]
 50%|████▉     | 371/747 [22:42<25:24,  4.06s/it]
 50%|████▉     | 372/747 [22:46<24:14,  3.88s/it]
 50%|████▉     | 373/747 [22:49<22:58,  3.69s/it]
 50%|█████     | 374/747 [22:54<24:47,  3.99s/it]
 50%|█████     | 375/747 [22:58<25:13,  4.07s/it]
 50%|█████     | 376/747 [23:03<27:05,  4.38s/it]
 50%|█████     | 377/747 [23:07<27:04,  4.39s/it]
 51%|█████     | 378/747 [23:11<24:52,  4.05s/it]
 51%|█████     | 379/747 [23:14<24:01,  3.92s/it]
 51%|█████     | 380/747 [23:19<26:24,  4.32s/it]
                                                 
{'loss': 0.2708, 'learning_rate': 2.431667305738112e-05, 'epoch': 0.51}

 51%|█████     | 380/747 [23:19<26:24,  4.32s/it]
 51%|█████     | 381/747 [23:24<25:58,  4.26s/it]
 51%|█████     | 382/747 [23:27<25:18,  4.16s/it]
 51%|█████▏    | 383/747 [23:32<26:20,  4.34s/it]
 51%|█████▏    | 384/747 [23:36<24:32,  4.06s/it]
 52%|█████▏    | 385/747 [23:40<24:17,  4.03s/it]
 52%|█████▏    | 386/747 [23:43<23:01,  3.83s/it]
 52%|█████▏    | 387/747 [23:46<21:20,  3.56s/it]
 52%|█████▏    | 388/747 [23:49<19:52,  3.32s/it]
 52%|█████▏    | 389/747 [23:52<20:09,  3.38s/it]
 52%|█████▏    | 390/747 [23:56<20:52,  3.51s/it]
                                                 
{'loss': 0.2838, 'learning_rate': 2.3266576730297956e-05, 'epoch': 0.52}

 52%|█████▏    | 390/747 [23:56<20:52,  3.51s/it]
 52%|█████▏    | 391/747 [24:00<21:32,  3.63s/it]
 52%|█████▏    | 392/747 [24:03<21:05,  3.57s/it]
 53%|█████▎    | 393/747 [24:08<22:32,  3.82s/it]
 53%|█████▎    | 394/747 [24:13<24:35,  4.18s/it]
 53%|█████▎    | 395/747 [24:17<24:04,  4.10s/it]
 53%|█████▎    | 396/747 [24:20<22:05,  3.78s/it]
 53%|█████▎    | 397/747 [24:23<21:01,  3.61s/it]
 53%|█████▎    | 398/747 [24:27<21:52,  3.76s/it]
 53%|█████▎    | 399/747 [24:31<22:11,  3.83s/it]
 54%|█████▎    | 400/747 [24:34<20:53,  3.61s/it]
                                                 
{'loss': 0.2987, 'learning_rate': 2.221954588790206e-05, 'epoch': 0.54}

 54%|█████▎    | 400/747 [24:34<20:53,  3.61s/it]
 54%|█████▎    | 401/747 [24:38<20:59,  3.64s/it]
 54%|█████▍    | 402/747 [24:42<21:26,  3.73s/it]
 54%|█████▍    | 403/747 [24:46<22:52,  3.99s/it]
 54%|█████▍    | 404/747 [24:50<22:13,  3.89s/it]
 54%|█████▍    | 405/747 [24:54<22:05,  3.88s/it]
 54%|█████▍    | 406/747 [24:57<20:58,  3.69s/it]
 54%|█████▍    | 407/747 [25:00<20:13,  3.57s/it]
 55%|█████▍    | 408/747 [25:04<19:41,  3.49s/it]
 55%|█████▍    | 409/747 [25:08<21:09,  3.75s/it]
 55%|█████▍    | 410/747 [25:11<20:36,  3.67s/it]
                                                 
{'loss': 0.3069, 'learning_rate': 2.1177432159319754e-05, 'epoch': 0.55}

 55%|█████▍    | 410/747 [25:12<20:36,  3.67s/it]
 55%|█████▌    | 411/747 [25:14<19:19,  3.45s/it]
 55%|█████▌    | 412/747 [25:17<17:44,  3.18s/it]
 55%|█████▌    | 413/747 [25:21<19:29,  3.50s/it]
 55%|█████▌    | 414/747 [25:25<20:06,  3.62s/it]
 56%|█████▌    | 415/747 [25:29<19:38,  3.55s/it]
 56%|█████▌    | 416/747 [25:32<19:05,  3.46s/it]
 56%|█████▌    | 417/747 [25:35<19:06,  3.48s/it]
 56%|█████▌    | 418/747 [25:39<19:46,  3.61s/it]
 56%|█████▌    | 419/747 [25:43<20:13,  3.70s/it]
 56%|█████▌    | 420/747 [25:47<21:08,  3.88s/it]
                                                 
{'loss': 0.2709, 'learning_rate': 2.014207847797256e-05, 'epoch': 0.56}

 56%|█████▌    | 420/747 [25:47<21:08,  3.88s/it]
 56%|█████▋    | 421/747 [25:51<20:23,  3.75s/it]
 56%|█████▋    | 422/747 [25:55<21:10,  3.91s/it]
 57%|█████▋    | 423/747 [25:59<21:08,  3.91s/it]
 57%|█████▋    | 424/747 [26:03<20:37,  3.83s/it]
 57%|█████▋    | 425/747 [26:06<19:13,  3.58s/it]
 57%|█████▋    | 426/747 [26:10<20:02,  3.75s/it]
 57%|█████▋    | 427/747 [26:13<19:42,  3.69s/it]
 57%|█████▋    | 428/747 [26:17<18:55,  3.56s/it]
 57%|█████▋    | 429/747 [26:22<20:54,  3.94s/it]
 58%|█████▊    | 430/747 [26:26<21:09,  4.00s/it]
                                                 
{'loss': 0.3159, 'learning_rate': 1.9115315822428437e-05, 'epoch': 0.58}

 58%|█████▊    | 430/747 [26:26<21:09,  4.00s/it]
 58%|█████▊    | 431/747 [26:28<19:09,  3.64s/it]
 58%|█████▊    | 432/747 [26:32<18:38,  3.55s/it]
 58%|█████▊    | 433/747 [26:36<19:33,  3.74s/it]
 58%|█████▊    | 434/747 [26:40<19:43,  3.78s/it]
 58%|█████▊    | 435/747 [26:44<19:32,  3.76s/it]
 58%|█████▊    | 436/747 [26:47<19:08,  3.69s/it]
 59%|█████▊    | 437/747 [26:51<18:55,  3.66s/it]
 59%|█████▊    | 438/747 [26:54<17:42,  3.44s/it]
 59%|█████▉    | 439/747 [26:58<18:24,  3.59s/it]
 59%|█████▉    | 440/747 [27:01<18:23,  3.60s/it]
                                                 
{'loss': 0.2997, 'learning_rate': 1.809895997839482e-05, 'epoch': 0.59}

 59%|█████▉    | 440/747 [27:01<18:23,  3.60s/it]
 59%|█████▉    | 441/747 [27:04<17:57,  3.52s/it]
 59%|█████▉    | 442/747 [27:09<19:10,  3.77s/it]
 59%|█████▉    | 443/747 [27:12<17:48,  3.51s/it]
 59%|█████▉    | 444/747 [27:16<18:22,  3.64s/it]
 60%|█████▉    | 445/747 [27:20<19:12,  3.81s/it]
 60%|█████▉    | 446/747 [27:24<19:19,  3.85s/it]
 60%|█████▉    | 447/747 [27:27<18:54,  3.78s/it]
 60%|█████▉    | 448/747 [27:31<18:21,  3.68s/it]
 60%|██████    | 449/747 [27:33<16:29,  3.32s/it]
 60%|██████    | 450/747 [27:37<17:05,  3.45s/it]
                                                 
{'loss': 0.2347, 'learning_rate': 1.70948083275794e-05, 'epoch': 0.6}

 60%|██████    | 450/747 [27:37<17:05,  3.45s/it]
 60%|██████    | 451/747 [27:40<16:04,  3.26s/it]
 61%|██████    | 452/747 [27:44<16:34,  3.37s/it]
 61%|██████    | 453/747 [27:48<17:38,  3.60s/it]
 61%|██████    | 454/747 [27:52<18:35,  3.81s/it]
 61%|██████    | 455/747 [27:56<18:44,  3.85s/it]
 61%|██████    | 456/747 [27:59<17:37,  3.63s/it]
 61%|██████    | 457/747 [28:02<16:38,  3.44s/it]
 61%|██████▏   | 458/747 [28:06<17:10,  3.56s/it]
 61%|██████▏   | 459/747 [28:08<15:28,  3.23s/it]
 62%|██████▏   | 460/747 [28:12<15:59,  3.34s/it]
                                                 
{'loss': 0.2634, 'learning_rate': 1.6104636669097776e-05, 'epoch': 0.62}

 62%|██████▏   | 460/747 [28:12<15:59,  3.34s/it]
 62%|██████▏   | 461/747 [28:16<17:06,  3.59s/it]
 62%|██████▏   | 462/747 [28:20<17:17,  3.64s/it]
 62%|██████▏   | 463/747 [28:24<17:45,  3.75s/it]
 62%|██████▏   | 464/747 [28:28<17:36,  3.73s/it]
 62%|██████▏   | 465/747 [28:31<17:28,  3.72s/it]
 62%|██████▏   | 466/747 [28:34<16:12,  3.46s/it]
 63%|██████▎   | 467/747 [28:38<16:39,  3.57s/it]
 63%|██████▎   | 468/747 [28:42<17:16,  3.72s/it]
 63%|██████▎   | 469/747 [28:45<16:16,  3.51s/it]
 63%|██████▎   | 470/747 [28:49<16:39,  3.61s/it]
                                                 
{'loss': 0.2438, 'learning_rate': 1.513019607904882e-05, 'epoch': 0.63}

 63%|██████▎   | 470/747 [28:49<16:39,  3.61s/it]
 63%|██████▎   | 471/747 [28:54<18:01,  3.92s/it]
 63%|██████▎   | 472/747 [28:57<17:11,  3.75s/it]
 63%|██████▎   | 473/747 [29:02<18:23,  4.03s/it]
 63%|██████▎   | 474/747 [29:05<17:39,  3.88s/it]
 64%|██████▎   | 475/747 [29:08<16:34,  3.66s/it]
 64%|██████▎   | 476/747 [29:12<17:06,  3.79s/it]
 64%|██████▍   | 477/747 [29:16<16:40,  3.71s/it]
 64%|██████▍   | 478/747 [29:19<15:45,  3.52s/it]
 64%|██████▍   | 479/747 [29:23<16:19,  3.65s/it]
 64%|██████▍   | 480/747 [29:26<16:00,  3.60s/it]
                                                 
{'loss': 0.2289, 'learning_rate': 1.4173209813811788e-05, 'epoch': 0.64}

 64%|██████▍   | 480/747 [29:26<16:00,  3.60s/it]
 64%|██████▍   | 481/747 [29:31<17:03,  3.85s/it]
 65%|██████▍   | 482/747 [29:35<17:08,  3.88s/it]
 65%|██████▍   | 483/747 [29:39<17:46,  4.04s/it]
 65%|██████▍   | 484/747 [29:42<16:22,  3.74s/it]
 65%|██████▍   | 485/747 [29:46<16:31,  3.79s/it]
 65%|██████▌   | 486/747 [29:50<16:11,  3.72s/it]
 65%|██████▌   | 487/747 [29:54<16:30,  3.81s/it]
 65%|██████▌   | 488/747 [29:58<17:24,  4.03s/it]
 65%|██████▌   | 489/747 [30:01<15:37,  3.63s/it]
 66%|██████▌   | 490/747 [30:05<16:41,  3.90s/it]
                                                 
{'loss': 0.2609, 'learning_rate': 1.3235370262541272e-05, 'epoch': 0.66}

 66%|██████▌   | 490/747 [30:05<16:41,  3.90s/it]
 66%|██████▌   | 491/747 [30:10<16:57,  3.97s/it]
 66%|██████▌   | 492/747 [30:13<16:43,  3.94s/it]
 66%|██████▌   | 493/747 [30:18<17:20,  4.09s/it]
 66%|██████▌   | 494/747 [30:21<16:19,  3.87s/it]
 66%|██████▋   | 495/747 [30:24<15:20,  3.65s/it]
 66%|██████▋   | 496/747 [30:27<14:29,  3.46s/it]
 67%|██████▋   | 497/747 [30:31<14:20,  3.44s/it]
 67%|██████▋   | 498/747 [30:36<16:10,  3.90s/it]
 67%|██████▋   | 499/747 [30:40<16:43,  4.05s/it]
 67%|██████▋   | 500/747 [30:43<15:43,  3.82s/it]
                                                 
{'loss': 0.2724, 'learning_rate': 1.2318335954249669e-05, 'epoch': 0.67}

 67%|██████▋   | 500/747 [30:43<15:43,  3.82s/it]
 67%|██████▋   | 501/747 [30:47<15:14,  3.72s/it]
 67%|██████▋   | 502/747 [30:51<15:25,  3.78s/it]
 67%|██████▋   | 503/747 [30:54<15:08,  3.72s/it]
 67%|██████▋   | 504/747 [30:59<15:54,  3.93s/it]
 68%|██████▊   | 505/747 [31:02<14:40,  3.64s/it]
 68%|██████▊   | 506/747 [31:05<14:33,  3.62s/it]
 68%|██████▊   | 507/747 [31:09<13:58,  3.49s/it]
 68%|██████▊   | 508/747 [31:12<13:25,  3.37s/it]
 68%|██████▊   | 509/747 [31:15<13:47,  3.48s/it]
 68%|██████▊   | 510/747 [31:18<13:04,  3.31s/it]
                                                 
{'loss': 0.272, 'learning_rate': 1.1423728624769695e-05, 'epoch': 0.68}

 68%|██████▊   | 510/747 [31:18<13:04,  3.31s/it]
 68%|██████▊   | 511/747 [31:23<14:16,  3.63s/it]
 69%|██████▊   | 512/747 [31:27<15:13,  3.89s/it]
 69%|██████▊   | 513/747 [31:31<14:49,  3.80s/it]
 69%|██████▉   | 514/747 [31:34<14:31,  3.74s/it]
 69%|██████▉   | 515/747 [31:37<13:33,  3.51s/it]
 69%|██████▉   | 516/747 [31:40<12:37,  3.28s/it]
 69%|██████▉   | 517/747 [31:44<13:11,  3.44s/it]
 69%|██████▉   | 518/747 [31:47<13:08,  3.45s/it]
 69%|██████▉   | 519/747 [31:53<15:06,  3.98s/it]
 70%|██████▉   | 520/747 [31:57<15:12,  4.02s/it]
                                                 
{'loss': 0.303, 'learning_rate': 1.0553130348784182e-05, 'epoch': 0.7}

 70%|██████▉   | 520/747 [31:57<15:12,  4.02s/it]
 70%|██████▉   | 521/747 [32:01<15:50,  4.20s/it]
 70%|██████▉   | 522/747 [32:05<15:40,  4.18s/it]
 70%|███████   | 523/747 [32:08<13:53,  3.72s/it]
 70%|███████   | 524/747 [32:12<13:45,  3.70s/it]
 70%|███████   | 525/747 [32:15<13:20,  3.60s/it]
 70%|███████   | 526/747 [32:19<13:54,  3.77s/it]
 71%|███████   | 527/747 [32:23<13:45,  3.75s/it]
 71%|███████   | 528/747 [32:27<14:14,  3.90s/it]
 71%|███████   | 529/747 [32:32<14:50,  4.09s/it]
 71%|███████   | 530/747 [32:35<14:14,  3.94s/it]
                                                 
{'loss': 0.2766, 'learning_rate': 9.708080741994868e-06, 'epoch': 0.71}

 71%|███████   | 530/747 [32:35<14:14,  3.94s/it]
 71%|███████   | 531/747 [32:39<14:07,  3.92s/it]
 71%|███████   | 532/747 [32:44<14:33,  4.06s/it]
 71%|███████▏  | 533/747 [32:47<13:52,  3.89s/it]
 71%|███████▏  | 534/747 [32:51<13:35,  3.83s/it]
 72%|███████▏  | 535/747 [32:55<14:13,  4.02s/it]
 72%|███████▏  | 536/747 [32:59<14:05,  4.01s/it]
 72%|███████▏  | 537/747 [33:04<14:41,  4.20s/it]
 72%|███████▏  | 538/747 [33:07<13:24,  3.85s/it]
 72%|███████▏  | 539/747 [33:09<11:57,  3.45s/it]
 72%|███████▏  | 540/747 [33:13<12:15,  3.55s/it]
                                                 
{'loss': 0.2333, 'learning_rate': 8.890074238378074e-06, 'epoch': 0.72}

 72%|███████▏  | 540/747 [33:13<12:15,  3.55s/it]
 72%|███████▏  | 541/747 [33:18<13:04,  3.81s/it]
 73%|███████▎  | 542/747 [33:21<12:28,  3.65s/it]
 73%|███████▎  | 543/747 [33:25<12:43,  3.74s/it]
 73%|███████▎  | 544/747 [33:29<12:42,  3.76s/it]
 73%|███████▎  | 545/747 [33:32<12:10,  3.61s/it]
 73%|███████▎  | 546/747 [33:36<12:35,  3.76s/it]
 73%|███████▎  | 547/747 [33:41<13:18,  3.99s/it]
 73%|███████▎  | 548/747 [33:44<12:55,  3.90s/it]
 73%|███████▎  | 549/747 [33:48<12:34,  3.81s/it]
 74%|███████▎  | 550/747 [33:51<11:58,  3.65s/it]
                                                 
{'loss': 0.2326, 'learning_rate': 8.100557447342327e-06, 'epoch': 0.74}

 74%|███████▎  | 550/747 [33:51<11:58,  3.65s/it]
 74%|███████▍  | 551/747 [33:54<11:24,  3.49s/it]
 74%|███████▍  | 552/747 [33:58<11:03,  3.40s/it]
 74%|███████▍  | 553/747 [34:01<11:06,  3.44s/it]
 74%|███████▍  | 554/747 [34:05<11:28,  3.56s/it]
 74%|███████▍  | 555/747 [34:08<11:03,  3.45s/it]
 74%|███████▍  | 556/747 [34:12<11:45,  3.70s/it]
 75%|███████▍  | 557/747 [34:16<12:07,  3.83s/it]
 75%|███████▍  | 558/747 [34:20<12:05,  3.84s/it]
 75%|███████▍  | 559/747 [34:23<11:20,  3.62s/it]
 75%|███████▍  | 560/747 [34:28<12:01,  3.86s/it]
                                                 
{'loss': 0.2274, 'learning_rate': 7.340926595461687e-06, 'epoch': 0.75}

 75%|███████▍  | 560/747 [34:28<12:01,  3.86s/it]
 75%|███████▌  | 561/747 [34:31<10:50,  3.50s/it]
 75%|███████▌  | 562/747 [34:34<11:00,  3.57s/it]
 75%|███████▌  | 563/747 [34:39<12:11,  3.98s/it]
 76%|███████▌  | 564/747 [34:42<11:03,  3.63s/it]
 76%|███████▌  | 565/747 [34:46<11:07,  3.67s/it]
 76%|███████▌  | 566/747 [34:50<11:08,  3.69s/it]
 76%|███████▌  | 567/747 [34:53<10:40,  3.56s/it]
 76%|███████▌  | 568/747 [34:57<10:53,  3.65s/it]
 76%|███████▌  | 569/747 [35:01<11:30,  3.88s/it]
 76%|███████▋  | 570/747 [35:05<11:30,  3.90s/it]
                                                 
{'loss': 0.3255, 'learning_rate': 6.612525057308949e-06, 'epoch': 0.76}

 76%|███████▋  | 570/747 [35:05<11:30,  3.90s/it]
 76%|███████▋  | 571/747 [35:08<10:33,  3.60s/it]
 77%|███████▋  | 572/747 [35:12<10:33,  3.62s/it]
 77%|███████▋  | 573/747 [35:14<09:37,  3.32s/it]
 77%|███████▋  | 574/747 [35:18<10:11,  3.53s/it]
 77%|███████▋  | 575/747 [35:22<10:42,  3.73s/it]
 77%|███████▋  | 576/747 [35:27<10:57,  3.85s/it]
 77%|███████▋  | 577/747 [35:30<10:23,  3.67s/it]
 77%|███████▋  | 578/747 [35:33<10:17,  3.65s/it]
 78%|███████▊  | 579/747 [35:37<10:18,  3.68s/it]
 78%|███████▊  | 580/747 [35:41<10:07,  3.64s/it]
                                                 
{'loss': 0.2631, 'learning_rate': 5.9166409797553415e-06, 'epoch': 0.78}

 78%|███████▊  | 580/747 [35:41<10:07,  3.64s/it]
 78%|███████▊  | 581/747 [35:44<09:34,  3.46s/it]
 78%|███████▊  | 582/747 [35:48<10:04,  3.66s/it]
 78%|███████▊  | 583/747 [35:52<10:08,  3.71s/it]
 78%|███████▊  | 584/747 [35:55<09:59,  3.68s/it]
 78%|███████▊  | 585/747 [35:59<09:50,  3.65s/it]
 78%|███████▊  | 586/747 [36:03<09:53,  3.69s/it]
 79%|███████▊  | 587/747 [36:06<09:25,  3.53s/it]
 79%|███████▊  | 588/747 [36:10<09:38,  3.64s/it]
 79%|███████▉  | 589/747 [36:13<09:41,  3.68s/it]
 79%|███████▉  | 590/747 [36:17<09:35,  3.66s/it]
                                                 
{'loss': 0.2938, 'learning_rate': 5.254505003938043e-06, 'epoch': 0.79}

 79%|███████▉  | 590/747 [36:17<09:35,  3.66s/it]
 79%|███████▉  | 591/747 [36:20<08:35,  3.31s/it]
 79%|███████▉  | 592/747 [36:23<08:41,  3.36s/it]
 79%|███████▉  | 593/747 [36:26<08:41,  3.38s/it]
 80%|███████▉  | 594/747 [36:30<08:25,  3.30s/it]
 80%|███████▉  | 595/747 [36:33<08:27,  3.34s/it]
 80%|███████▉  | 596/747 [36:37<08:51,  3.52s/it]
 80%|███████▉  | 597/747 [36:41<08:51,  3.55s/it]
 80%|████████  | 598/747 [36:45<09:22,  3.78s/it]
 80%|████████  | 599/747 [36:49<09:52,  4.01s/it]
 80%|████████  | 600/747 [36:53<09:16,  3.79s/it]
                                                 
{'loss': 0.2807, 'learning_rate': 4.627288088924156e-06, 'epoch': 0.8}

 80%|████████  | 600/747 [36:53<09:16,  3.79s/it]
 80%|████████  | 601/747 [36:57<09:51,  4.05s/it]
 81%|████████  | 602/747 [37:02<09:54,  4.10s/it]
 81%|████████  | 603/747 [37:06<09:43,  4.05s/it]
 81%|████████  | 604/747 [37:10<10:14,  4.30s/it]
 81%|████████  | 605/747 [37:14<09:38,  4.07s/it]
 81%|████████  | 606/747 [37:19<10:18,  4.39s/it]
 81%|████████▏ | 607/747 [37:23<09:34,  4.11s/it]
 81%|████████▏ | 608/747 [37:26<09:03,  3.91s/it]
 82%|████████▏ | 609/747 [37:29<08:36,  3.74s/it]
 82%|████████▏ | 610/747 [37:34<09:09,  4.01s/it]
                                                 
{'loss': 0.2909, 'learning_rate': 4.036099440919763e-06, 'epoch': 0.82}

 82%|████████▏ | 610/747 [37:34<09:09,  4.01s/it]
 82%|████████▏ | 611/747 [37:38<09:06,  4.02s/it]
 82%|████████▏ | 612/747 [37:42<08:48,  3.92s/it]
 82%|████████▏ | 613/747 [37:45<08:14,  3.69s/it]
 82%|████████▏ | 614/747 [37:50<08:54,  4.02s/it]
 82%|████████▏ | 615/747 [37:53<08:34,  3.90s/it]
 82%|████████▏ | 616/747 [37:57<08:19,  3.81s/it]
 83%|████████▎ | 617/747 [38:01<08:29,  3.92s/it]
 83%|████████▎ | 618/747 [38:05<08:18,  3.86s/it]
 83%|████████▎ | 619/747 [38:08<07:49,  3.66s/it]
 83%|████████▎ | 620/747 [38:11<07:25,  3.51s/it]
                                                 
{'loss': 0.2997, 'learning_rate': 3.481984551686429e-06, 'epoch': 0.83}

 83%|████████▎ | 620/747 [38:11<07:25,  3.51s/it]
 83%|████████▎ | 621/747 [38:15<07:33,  3.60s/it]
 83%|████████▎ | 622/747 [38:18<07:20,  3.53s/it]
 83%|████████▎ | 623/747 [38:22<07:25,  3.59s/it]
 84%|████████▎ | 624/747 [38:25<07:13,  3.53s/it]
 84%|████████▎ | 625/747 [38:30<07:46,  3.82s/it]
 84%|████████▍ | 626/747 [38:34<07:41,  3.82s/it]
 84%|████████▍ | 627/747 [38:38<07:38,  3.82s/it]
 84%|████████▍ | 628/747 [38:41<07:38,  3.86s/it]
 84%|████████▍ | 629/747 [38:45<07:34,  3.85s/it]
 84%|████████▍ | 630/747 [38:48<07:01,  3.60s/it]
                                                 
{'loss': 0.2424, 'learning_rate': 2.9659233496337786e-06, 'epoch': 0.84}

 84%|████████▍ | 630/747 [38:48<07:01,  3.60s/it]
 84%|████████▍ | 631/747 [38:53<07:33,  3.91s/it]
 85%|████████▍ | 632/747 [38:56<06:55,  3.62s/it]
 85%|████████▍ | 633/747 [38:59<06:31,  3.44s/it]
 85%|████████▍ | 634/747 [39:02<06:30,  3.45s/it]
 85%|████████▌ | 635/747 [39:06<06:24,  3.43s/it]
 85%|████████▌ | 636/747 [39:11<07:07,  3.85s/it]
 85%|████████▌ | 637/747 [39:15<07:30,  4.10s/it]
 85%|████████▌ | 638/747 [39:19<07:29,  4.12s/it]
 86%|████████▌ | 639/747 [39:23<07:16,  4.05s/it]
 86%|████████▌ | 640/747 [39:27<07:10,  4.03s/it]
                                                 
{'loss': 0.2862, 'learning_rate': 2.4888284668582285e-06, 'epoch': 0.86}

 86%|████████▌ | 640/747 [39:27<07:10,  4.03s/it]
 86%|████████▌ | 641/747 [39:31<06:52,  3.89s/it]
 86%|████████▌ | 642/747 [39:35<06:43,  3.84s/it]
 86%|████████▌ | 643/747 [39:39<06:58,  4.03s/it]
 86%|████████▌ | 644/747 [39:42<06:32,  3.81s/it]
 86%|████████▋ | 645/747 [39:45<06:02,  3.56s/it]
 86%|████████▋ | 646/747 [39:49<06:01,  3.58s/it]
 87%|████████▋ | 647/747 [39:54<06:29,  3.89s/it]
 87%|████████▋ | 648/747 [39:57<06:16,  3.80s/it]
 87%|████████▋ | 649/747 [40:01<06:18,  3.87s/it]
 87%|████████▋ | 650/747 [40:04<05:47,  3.58s/it]
                                                 
{'loss': 0.3124, 'learning_rate': 2.051543625192226e-06, 'epoch': 0.87}

 87%|████████▋ | 650/747 [40:04<05:47,  3.58s/it]
 87%|████████▋ | 651/747 [40:08<05:40,  3.55s/it]
 87%|████████▋ | 652/747 [40:11<05:32,  3.50s/it]
 87%|████████▋ | 653/747 [40:15<05:41,  3.63s/it]
 88%|████████▊ | 654/747 [40:19<05:45,  3.71s/it]
 88%|████████▊ | 655/747 [40:23<05:53,  3.84s/it]
 88%|████████▊ | 656/747 [40:26<05:39,  3.73s/it]
 88%|████████▊ | 657/747 [40:30<05:35,  3.73s/it]
 88%|████████▊ | 658/747 [40:35<05:59,  4.04s/it]
 88%|████████▊ | 659/747 [40:39<05:57,  4.06s/it]
 88%|████████▊ | 660/747 [40:43<05:52,  4.05s/it]
                                                 
{'loss': 0.2644, 'learning_rate': 1.6548421441183875e-06, 'epoch': 0.88}

 88%|████████▊ | 660/747 [40:43<05:52,  4.05s/it]
 88%|████████▊ | 661/747 [40:46<05:19,  3.72s/it]
 89%|████████▊ | 662/747 [40:50<05:34,  3.94s/it]
 89%|████████▉ | 663/747 [40:53<05:06,  3.64s/it]
 89%|████████▉ | 664/747 [40:57<04:52,  3.53s/it]
 89%|████████▉ | 665/747 [41:01<04:57,  3.63s/it]
 89%|████████▉ | 666/747 [41:03<04:36,  3.41s/it]
 89%|████████▉ | 667/747 [41:08<04:57,  3.72s/it]
 89%|████████▉ | 668/747 [41:12<04:56,  3.76s/it]
 90%|████████▉ | 669/747 [41:15<04:43,  3.64s/it]
 90%|████████▉ | 670/747 [41:18<04:31,  3.52s/it]
                                                 
{'loss': 0.2622, 'learning_rate': 1.2994255731871963e-06, 'epoch': 0.9}

 90%|████████▉ | 670/747 [41:18<04:31,  3.52s/it]
 90%|████████▉ | 671/747 [41:21<04:15,  3.36s/it]
 90%|████████▉ | 672/747 [41:24<04:02,  3.23s/it]
 90%|█████████ | 673/747 [41:28<04:02,  3.27s/it]
 90%|█████████ | 674/747 [41:31<04:06,  3.38s/it]
 90%|█████████ | 675/747 [41:35<04:15,  3.55s/it]
 90%|█████████ | 676/747 [41:39<04:20,  3.67s/it]
 91%|█████████ | 677/747 [41:43<04:15,  3.65s/it]
 91%|█████████ | 678/747 [41:46<03:57,  3.44s/it]
 91%|█████████ | 679/747 [41:49<03:57,  3.49s/it]
 91%|█████████ | 680/747 [41:52<03:46,  3.38s/it]
                                                 
{'loss': 0.2234, 'learning_rate': 9.85922451356694e-07, 'epoch': 0.91}

 91%|█████████ | 680/747 [41:52<03:46,  3.38s/it]
 91%|█████████ | 681/747 [41:56<03:50,  3.50s/it]
 91%|█████████▏| 682/747 [42:01<04:13,  3.90s/it]
 91%|█████████▏| 683/747 [42:04<03:55,  3.67s/it]
 92%|█████████▏| 684/747 [42:08<03:56,  3.75s/it]
 92%|█████████▏| 685/747 [42:11<03:32,  3.43s/it]
 92%|█████████▏| 686/747 [42:15<03:51,  3.79s/it]
 92%|█████████▏| 687/747 [42:20<03:55,  3.92s/it]
 92%|█████████▏| 688/747 [42:23<03:43,  3.78s/it]
 92%|█████████▏| 689/747 [42:27<03:33,  3.67s/it]
 92%|█████████▏| 690/747 [42:29<03:15,  3.43s/it]
                                                 
{'loss': 0.334, 'learning_rate': 7.148871954483105e-07, 'epoch': 0.92}

 92%|█████████▏| 690/747 [42:29<03:15,  3.43s/it]
 93%|█████████▎| 691/747 [42:33<03:17,  3.53s/it]
 93%|█████████▎| 692/747 [42:37<03:21,  3.67s/it]
 93%|█████████▎| 693/747 [42:41<03:21,  3.73s/it]
 93%|█████████▎| 694/747 [42:45<03:23,  3.83s/it]
 93%|█████████▎| 695/747 [42:49<03:19,  3.85s/it]
 93%|█████████▎| 696/747 [42:52<03:05,  3.64s/it]
 93%|█████████▎| 697/747 [42:56<03:09,  3.79s/it]
 93%|█████████▎| 698/747 [43:00<03:02,  3.72s/it]
 94%|█████████▎| 699/747 [43:04<02:58,  3.72s/it]
 94%|█████████▎| 700/747 [43:07<02:50,  3.64s/it]
                                                 
{'loss': 0.2915, 'learning_rate': 4.867991196844918e-07, 'epoch': 0.94}

 94%|█████████▎| 700/747 [43:07<02:50,  3.64s/it]
 94%|█████████▍| 701/747 [43:11<02:45,  3.60s/it]
 94%|█████████▍| 702/747 [43:15<02:47,  3.72s/it]
 94%|█████████▍| 703/747 [43:18<02:39,  3.63s/it]
 94%|█████████▍| 704/747 [43:22<02:35,  3.61s/it]
 94%|█████████▍| 705/747 [43:24<02:22,  3.39s/it]
 95%|█████████▍| 706/747 [43:27<02:11,  3.21s/it]
 95%|█████████▍| 707/747 [43:30<02:08,  3.21s/it]
 95%|█████████▍| 708/747 [43:34<02:15,  3.47s/it]
 95%|█████████▍| 709/747 [43:38<02:14,  3.53s/it]
 95%|█████████▌| 710/747 [43:42<02:11,  3.56s/it]
                                                 
{'loss': 0.2802, 'learning_rate': 3.020615880420713e-07, 'epoch': 0.95}

 95%|█████████▌| 710/747 [43:42<02:11,  3.56s/it]
 95%|█████████▌| 711/747 [43:46<02:17,  3.83s/it]
 95%|█████████▌| 712/747 [43:49<02:02,  3.49s/it]
 95%|█████████▌| 713/747 [43:53<02:04,  3.65s/it]
 96%|█████████▌| 714/747 [43:56<01:53,  3.43s/it]
 96%|█████████▌| 715/747 [43:59<01:44,  3.25s/it]
 96%|█████████▌| 716/747 [44:02<01:44,  3.36s/it]
 96%|█████████▌| 717/747 [44:06<01:42,  3.43s/it]
 96%|█████████▌| 718/747 [44:10<01:44,  3.60s/it]
 96%|█████████▋| 719/747 [44:14<01:43,  3.69s/it]
 96%|█████████▋| 720/747 [44:17<01:33,  3.47s/it]
                                                 
{'loss': 0.2975, 'learning_rate': 1.6100130092037703e-07, 'epoch': 0.96}

 96%|█████████▋| 720/747 [44:17<01:33,  3.47s/it]
 97%|█████████▋| 721/747 [44:20<01:27,  3.37s/it]
 97%|█████████▋| 722/747 [44:23<01:23,  3.34s/it]
 97%|█████████▋| 723/747 [44:26<01:18,  3.27s/it]
 97%|█████████▋| 724/747 [44:30<01:19,  3.46s/it]
 97%|█████████▋| 725/747 [44:34<01:20,  3.66s/it]
 97%|█████████▋| 726/747 [44:39<01:23,  3.99s/it]
 97%|█████████▋| 727/747 [44:42<01:14,  3.72s/it]
 97%|█████████▋| 728/747 [44:46<01:09,  3.65s/it]
 98%|█████████▊| 729/747 [44:49<01:05,  3.62s/it]
 98%|█████████▊| 730/747 [44:53<01:01,  3.59s/it]
                                                 
{'loss': 0.2531, 'learning_rate': 6.386771738558506e-08, 'epoch': 0.98}

 98%|█████████▊| 730/747 [44:53<01:01,  3.59s/it]
 98%|█████████▊| 731/747 [44:56<00:58,  3.63s/it]
 98%|█████████▊| 732/747 [45:01<00:57,  3.86s/it]
 98%|█████████▊| 733/747 [45:05<00:56,  4.06s/it]
 98%|█████████▊| 734/747 [45:09<00:50,  3.87s/it]
 98%|█████████▊| 735/747 [45:12<00:43,  3.62s/it]
 99%|█████████▊| 736/747 [45:16<00:40,  3.65s/it]
 99%|█████████▊| 737/747 [45:20<00:38,  3.83s/it]
 99%|█████████▉| 738/747 [45:24<00:34,  3.80s/it]
 99%|█████████▉| 739/747 [45:26<00:27,  3.47s/it]
 99%|█████████▉| 740/747 [45:30<00:25,  3.68s/it]
                                                 
{'loss': 0.2696, 'learning_rate': 1.0832614013073228e-08, 'epoch': 0.99}

 99%|█████████▉| 740/747 [45:30<00:25,  3.68s/it]
 99%|█████████▉| 741/747 [45:34<00:21,  3.62s/it]
 99%|█████████▉| 742/747 [45:37<00:17,  3.46s/it]
 99%|█████████▉| 743/747 [45:41<00:14,  3.51s/it]
100%|█████████▉| 744/747 [45:45<00:11,  3.70s/it]
100%|█████████▉| 745/747 [45:50<00:08,  4.17s/it]
100%|█████████▉| 746/747 [45:53<00:03,  3.86s/it]
100%|██████████| 747/747 [45:56<00:00,  3.69s/it][INFO|trainer.py:3166] 2024-01-18 19:16:11,445 >> ***** Running Evaluation *****
[INFO|trainer.py:3168] 2024-01-18 19:16:11,445 >>   Num examples = 664
[INFO|trainer.py:3171] 2024-01-18 19:16:11,445 >>   Batch size = 1


  0%|          | 0/332 [00:00<?, ?it/s]

  1%|          | 2/332 [00:00<00:42,  7.82it/s]

  1%|          | 3/332 [00:00<00:58,  5.62it/s]

  1%|          | 4/332 [00:00<01:07,  4.85it/s]

  2%|▏         | 5/332 [00:01<01:29,  3.67it/s]

  2%|▏         | 6/332 [00:01<01:46,  3.05it/s]

  2%|▏         | 7/332 [00:01<01:41,  3.19it/s]

  2%|▏         | 8/332 [00:02<01:54,  2.83it/s]

  3%|▎         | 9/332 [00:02<01:38,  3.27it/s]

  3%|▎         | 10/332 [00:02<01:51,  2.88it/s]

  3%|▎         | 11/332 [00:03<01:56,  2.76it/s]

  4%|▎         | 12/332 [00:03<02:05,  2.55it/s]

  4%|▍         | 13/332 [00:04<02:09,  2.47it/s]

  4%|▍         | 14/332 [00:04<01:54,  2.78it/s]

  5%|▍         | 15/332 [00:04<01:54,  2.77it/s]

  5%|▍         | 16/332 [00:05<01:43,  3.06it/s]

  5%|▌         | 17/332 [00:05<01:32,  3.42it/s]

  5%|▌         | 18/332 [00:05<01:27,  3.58it/s]

  6%|▌         | 19/332 [00:05<01:20,  3.88it/s]

  6%|▌         | 20/332 [00:06<01:23,  3.76it/s]

  6%|▋         | 21/332 [00:06<01:29,  3.46it/s]

  7%|▋         | 22/332 [00:06<01:28,  3.49it/s]

  7%|▋         | 23/332 [00:06<01:24,  3.64it/s]

  7%|▋         | 24/332 [00:07<01:19,  3.90it/s]

  8%|▊         | 25/332 [00:07<01:17,  3.94it/s]

  8%|▊         | 26/332 [00:07<01:16,  3.99it/s]

  8%|▊         | 27/332 [00:07<01:12,  4.22it/s]

  8%|▊         | 28/332 [00:08<01:26,  3.51it/s]

  9%|▊         | 29/332 [00:08<01:22,  3.65it/s]

  9%|▉         | 30/332 [00:08<01:15,  4.00it/s]

  9%|▉         | 31/332 [00:08<01:11,  4.18it/s]

 10%|▉         | 32/332 [00:09<01:12,  4.15it/s]

 10%|▉         | 33/332 [00:09<01:16,  3.90it/s]

 10%|█         | 34/332 [00:09<01:29,  3.32it/s]

 11%|█         | 35/332 [00:10<01:39,  2.97it/s]

 11%|█         | 36/332 [00:10<01:31,  3.23it/s]

 11%|█         | 37/332 [00:10<01:35,  3.08it/s]

 11%|█▏        | 38/332 [00:11<01:24,  3.46it/s]

 12%|█▏        | 39/332 [00:11<01:39,  2.94it/s]

 12%|█▏        | 40/332 [00:11<01:39,  2.95it/s]

 12%|█▏        | 41/332 [00:12<01:38,  2.96it/s]

 13%|█▎        | 42/332 [00:12<01:33,  3.10it/s]

 13%|█▎        | 43/332 [00:12<01:32,  3.11it/s]

 13%|█▎        | 44/332 [00:12<01:19,  3.61it/s]

 14%|█▎        | 45/332 [00:13<01:36,  2.97it/s]

 14%|█▍        | 46/332 [00:13<01:33,  3.07it/s]

 14%|█▍        | 47/332 [00:14<01:30,  3.16it/s]

 14%|█▍        | 48/332 [00:14<01:21,  3.48it/s]

 15%|█▍        | 49/332 [00:14<01:18,  3.61it/s]

 15%|█▌        | 50/332 [00:14<01:15,  3.74it/s]

 15%|█▌        | 51/332 [00:15<01:13,  3.84it/s]

 16%|█▌        | 52/332 [00:15<01:04,  4.34it/s]

 16%|█▌        | 53/332 [00:15<01:01,  4.52it/s]

 16%|█▋        | 54/332 [00:15<01:00,  4.56it/s]

 17%|█▋        | 55/332 [00:15<01:10,  3.95it/s]

 17%|█▋        | 56/332 [00:16<01:12,  3.78it/s]

 17%|█▋        | 57/332 [00:16<01:08,  4.04it/s]

 17%|█▋        | 58/332 [00:16<01:00,  4.52it/s]

 18%|█▊        | 59/332 [00:16<01:02,  4.36it/s]

 18%|█▊        | 60/332 [00:17<01:06,  4.08it/s]

 18%|█▊        | 61/332 [00:17<01:06,  4.06it/s]

 19%|█▊        | 62/332 [00:17<01:09,  3.87it/s]

 19%|█▉        | 63/332 [00:18<01:24,  3.20it/s]

 19%|█▉        | 64/332 [00:18<01:34,  2.84it/s]

 20%|█▉        | 65/332 [00:18<01:33,  2.87it/s]

 20%|█▉        | 66/332 [00:19<01:39,  2.66it/s]

 20%|██        | 67/332 [00:19<01:30,  2.94it/s]

 20%|██        | 68/332 [00:19<01:21,  3.23it/s]

 21%|██        | 69/332 [00:20<01:31,  2.87it/s]

 21%|██        | 70/332 [00:20<01:23,  3.14it/s]

 21%|██▏       | 71/332 [00:20<01:20,  3.23it/s]

 22%|██▏       | 72/332 [00:21<01:15,  3.45it/s]

 22%|██▏       | 73/332 [00:21<01:11,  3.60it/s]

 22%|██▏       | 74/332 [00:21<01:24,  3.07it/s]

 23%|██▎       | 75/332 [00:22<01:32,  2.77it/s]

 23%|██▎       | 76/332 [00:22<01:23,  3.07it/s]

 23%|██▎       | 77/332 [00:22<01:16,  3.32it/s]

 23%|██▎       | 78/332 [00:22<01:12,  3.48it/s]

 24%|██▍       | 79/332 [00:23<01:09,  3.62it/s]

 24%|██▍       | 80/332 [00:23<01:22,  3.06it/s]

 24%|██▍       | 81/332 [00:24<01:30,  2.78it/s]

 25%|██▍       | 82/332 [00:24<01:21,  3.06it/s]

 25%|██▌       | 83/332 [00:24<01:30,  2.76it/s]

 25%|██▌       | 84/332 [00:25<01:25,  2.90it/s]

 26%|██▌       | 85/332 [00:25<01:26,  2.85it/s]

 26%|██▌       | 86/332 [00:25<01:18,  3.13it/s]

 26%|██▌       | 87/332 [00:25<01:12,  3.37it/s]

 27%|██▋       | 88/332 [00:26<01:12,  3.38it/s]

 27%|██▋       | 89/332 [00:26<01:08,  3.56it/s]

 27%|██▋       | 90/332 [00:26<01:03,  3.81it/s]

 27%|██▋       | 91/332 [00:26<00:59,  4.07it/s]

 28%|██▊       | 92/332 [00:27<00:59,  4.06it/s]

 28%|██▊       | 93/332 [00:27<01:07,  3.52it/s]

 28%|██▊       | 94/332 [00:27<01:05,  3.64it/s]

 29%|██▊       | 95/332 [00:28<01:12,  3.27it/s]

 29%|██▉       | 96/332 [00:28<01:20,  2.92it/s]

 29%|██▉       | 97/332 [00:28<01:11,  3.27it/s]

 30%|██▉       | 98/332 [00:28<01:05,  3.57it/s]

 30%|██▉       | 99/332 [00:29<01:00,  3.86it/s]

 30%|███       | 100/332 [00:29<01:13,  3.17it/s]

 30%|███       | 101/332 [00:29<01:14,  3.09it/s]

 31%|███       | 102/332 [00:30<01:22,  2.79it/s]

 31%|███       | 103/332 [00:30<01:27,  2.61it/s]

 31%|███▏      | 104/332 [00:31<01:15,  3.01it/s]

 32%|███▏      | 105/332 [00:31<01:03,  3.56it/s]

 32%|███▏      | 106/332 [00:31<01:11,  3.16it/s]

 32%|███▏      | 107/332 [00:31<01:06,  3.37it/s]

 33%|███▎      | 108/332 [00:32<01:09,  3.21it/s]

 33%|███▎      | 109/332 [00:32<01:15,  2.95it/s]

 33%|███▎      | 110/332 [00:33<01:22,  2.70it/s]

 33%|███▎      | 111/332 [00:33<01:19,  2.76it/s]

 34%|███▎      | 112/332 [00:33<01:14,  2.94it/s]

 34%|███▍      | 113/332 [00:34<01:22,  2.64it/s]

 34%|███▍      | 114/332 [00:34<01:17,  2.83it/s]

 35%|███▍      | 115/332 [00:34<01:09,  3.10it/s]

 35%|███▍      | 116/332 [00:34<01:04,  3.33it/s]

 35%|███▌      | 117/332 [00:35<00:55,  3.86it/s]

 36%|███▌      | 118/332 [00:35<00:57,  3.73it/s]

 36%|███▌      | 119/332 [00:35<00:59,  3.61it/s]

 36%|███▌      | 120/332 [00:36<01:08,  3.11it/s]

 36%|███▋      | 121/332 [00:36<01:05,  3.21it/s]

 37%|███▋      | 122/332 [00:36<01:04,  3.28it/s]

 37%|███▋      | 123/332 [00:37<01:02,  3.33it/s]

 37%|███▋      | 124/332 [00:37<00:57,  3.62it/s]

 38%|███▊      | 125/332 [00:37<00:52,  3.96it/s]

 38%|███▊      | 126/332 [00:37<01:03,  3.23it/s]

 38%|███▊      | 127/332 [00:38<01:12,  2.84it/s]

 39%|███▊      | 128/332 [00:38<01:17,  2.64it/s]

 39%|███▉      | 129/332 [00:39<01:14,  2.73it/s]

 39%|███▉      | 130/332 [00:39<01:03,  3.16it/s]

 39%|███▉      | 131/332 [00:39<00:59,  3.38it/s]

 40%|███▉      | 132/332 [00:39<00:54,  3.66it/s]

 40%|████      | 133/332 [00:40<01:06,  3.02it/s]

 40%|████      | 134/332 [00:40<01:00,  3.28it/s]

 41%|████      | 135/332 [00:40<00:56,  3.49it/s]

 41%|████      | 136/332 [00:41<01:06,  2.96it/s]

 41%|████▏     | 137/332 [00:41<01:06,  2.94it/s]

 42%|████▏     | 138/332 [00:41<01:00,  3.19it/s]

 42%|████▏     | 139/332 [00:42<00:59,  3.26it/s]

 42%|████▏     | 140/332 [00:42<01:06,  2.88it/s]

 42%|████▏     | 141/332 [00:42<01:12,  2.62it/s]

 43%|████▎     | 142/332 [00:43<01:06,  2.84it/s]

 43%|████▎     | 143/332 [00:43<01:02,  3.00it/s]

 43%|████▎     | 144/332 [00:43<00:57,  3.27it/s]

 44%|████▎     | 145/332 [00:44<01:04,  2.89it/s]

 44%|████▍     | 146/332 [00:44<01:09,  2.67it/s]

 44%|████▍     | 147/332 [00:44<01:00,  3.05it/s]

 45%|████▍     | 148/332 [00:45<01:01,  3.01it/s]

 45%|████▍     | 149/332 [00:45<00:54,  3.37it/s]

 45%|████▌     | 150/332 [00:45<00:59,  3.06it/s]

 45%|████▌     | 151/332 [00:46<00:57,  3.17it/s]

 46%|████▌     | 152/332 [00:46<00:57,  3.10it/s]

 46%|████▌     | 153/332 [00:46<01:04,  2.78it/s]

 46%|████▋     | 154/332 [00:47<01:08,  2.61it/s]

 47%|████▋     | 155/332 [00:47<01:00,  2.91it/s]

 47%|████▋     | 156/332 [00:47<00:53,  3.26it/s]

 47%|████▋     | 157/332 [00:48<00:52,  3.31it/s]

 48%|████▊     | 158/332 [00:48<00:51,  3.37it/s]

 48%|████▊     | 159/332 [00:48<00:49,  3.53it/s]

 48%|████▊     | 160/332 [00:49<00:55,  3.09it/s]

 48%|████▊     | 161/332 [00:49<00:58,  2.91it/s]

 49%|████▉     | 162/332 [00:49<01:03,  2.68it/s]

 49%|████▉     | 163/332 [00:50<00:56,  2.98it/s]

 49%|████▉     | 164/332 [00:50<00:47,  3.54it/s]

 50%|████▉     | 165/332 [00:50<00:55,  3.03it/s]

 50%|█████     | 166/332 [00:50<00:50,  3.28it/s]

 50%|█████     | 167/332 [00:51<00:46,  3.58it/s]

 51%|█████     | 168/332 [00:51<00:53,  3.04it/s]

 51%|█████     | 169/332 [00:52<00:59,  2.75it/s]

 51%|█████     | 170/332 [00:52<00:53,  3.04it/s]

 52%|█████▏    | 171/332 [00:52<00:47,  3.42it/s]

 52%|█████▏    | 172/332 [00:52<00:42,  3.74it/s]

 52%|█████▏    | 173/332 [00:53<00:41,  3.83it/s]

 52%|█████▏    | 174/332 [00:53<00:44,  3.54it/s]

 53%|█████▎    | 175/332 [00:53<00:46,  3.37it/s]

 53%|█████▎    | 176/332 [00:53<00:43,  3.57it/s]

 53%|█████▎    | 177/332 [00:54<00:49,  3.11it/s]

 54%|█████▎    | 178/332 [00:54<00:46,  3.32it/s]

 54%|█████▍    | 179/332 [00:54<00:45,  3.38it/s]

 54%|█████▍    | 180/332 [00:55<00:42,  3.56it/s]

 55%|█████▍    | 181/332 [00:55<00:42,  3.53it/s]

 55%|█████▍    | 182/332 [00:55<00:36,  4.08it/s]

 55%|█████▌    | 183/332 [00:55<00:34,  4.30it/s]

 55%|█████▌    | 184/332 [00:56<00:37,  3.99it/s]

 56%|█████▌    | 185/332 [00:56<00:40,  3.61it/s]

 56%|█████▌    | 186/332 [00:56<00:48,  2.99it/s]

 56%|█████▋    | 187/332 [00:57<00:46,  3.11it/s]

 57%|█████▋    | 188/332 [00:57<00:41,  3.50it/s]

 57%|█████▋    | 189/332 [00:57<00:43,  3.28it/s]

 57%|█████▋    | 190/332 [00:57<00:39,  3.58it/s]

 58%|█████▊    | 191/332 [00:58<00:45,  3.09it/s]

 58%|█████▊    | 192/332 [00:58<00:46,  3.02it/s]

 58%|█████▊    | 193/332 [00:59<00:44,  3.12it/s]

 58%|█████▊    | 194/332 [00:59<00:43,  3.20it/s]

 59%|█████▊    | 195/332 [00:59<00:39,  3.43it/s]

 59%|█████▉    | 196/332 [00:59<00:37,  3.61it/s]

 59%|█████▉    | 197/332 [00:59<00:34,  3.86it/s]

 60%|█████▉    | 198/332 [01:00<00:42,  3.18it/s]

 60%|█████▉    | 199/332 [01:00<00:40,  3.26it/s]

 60%|██████    | 200/332 [01:00<00:36,  3.57it/s]

 61%|██████    | 201/332 [01:01<00:39,  3.28it/s]

 61%|██████    | 202/332 [01:01<00:44,  2.90it/s]

 61%|██████    | 203/332 [01:01<00:39,  3.29it/s]

 61%|██████▏   | 204/332 [01:02<00:42,  3.00it/s]

 62%|██████▏   | 205/332 [01:02<00:40,  3.13it/s]

 62%|██████▏   | 206/332 [01:02<00:38,  3.25it/s]

 62%|██████▏   | 207/332 [01:03<00:37,  3.30it/s]

 63%|██████▎   | 208/332 [01:03<00:35,  3.50it/s]

 63%|██████▎   | 209/332 [01:03<00:33,  3.64it/s]

 63%|██████▎   | 210/332 [01:03<00:32,  3.76it/s]

 64%|██████▎   | 211/332 [01:04<00:37,  3.23it/s]

 64%|██████▍   | 212/332 [01:04<00:41,  2.86it/s]

 64%|██████▍   | 213/332 [01:05<00:36,  3.22it/s]

 64%|██████▍   | 214/332 [01:05<00:37,  3.11it/s]

 65%|██████▍   | 215/332 [01:05<00:36,  3.19it/s]

 65%|██████▌   | 216/332 [01:05<00:30,  3.76it/s]

 65%|██████▌   | 217/332 [01:06<00:29,  3.84it/s]

 66%|██████▌   | 218/332 [01:06<00:32,  3.51it/s]

 66%|██████▌   | 219/332 [01:06<00:31,  3.63it/s]

 66%|██████▋   | 220/332 [01:06<00:28,  3.89it/s]

 67%|██████▋   | 221/332 [01:07<00:28,  3.94it/s]

 67%|██████▋   | 222/332 [01:07<00:33,  3.33it/s]

 67%|██████▋   | 223/332 [01:07<00:31,  3.48it/s]

 67%|██████▋   | 224/332 [01:08<00:36,  2.99it/s]

 68%|██████▊   | 225/332 [01:08<00:34,  3.14it/s]

 68%|██████▊   | 226/332 [01:08<00:32,  3.22it/s]

 68%|██████▊   | 227/332 [01:09<00:31,  3.29it/s]

 69%|██████▊   | 228/332 [01:09<00:27,  3.83it/s]

 69%|██████▉   | 229/332 [01:09<00:32,  3.18it/s]

 69%|██████▉   | 230/332 [01:10<00:33,  3.09it/s]

 70%|██████▉   | 231/332 [01:10<00:29,  3.46it/s]

 70%|██████▉   | 232/332 [01:10<00:26,  3.78it/s]

 70%|███████   | 233/332 [01:10<00:24,  3.99it/s]

 70%|███████   | 234/332 [01:11<00:30,  3.18it/s]

 71%|███████   | 235/332 [01:11<00:29,  3.28it/s]

 71%|███████   | 236/332 [01:11<00:26,  3.63it/s]

 71%|███████▏  | 237/332 [01:11<00:24,  3.88it/s]

 72%|███████▏  | 238/332 [01:12<00:26,  3.55it/s]

 72%|███████▏  | 239/332 [01:12<00:26,  3.50it/s]

 72%|███████▏  | 240/332 [01:12<00:27,  3.31it/s]

 73%|███████▎  | 241/332 [01:13<00:24,  3.69it/s]

 73%|███████▎  | 242/332 [01:13<00:29,  3.09it/s]

 73%|███████▎  | 243/332 [01:13<00:24,  3.64it/s]

 73%|███████▎  | 244/332 [01:13<00:24,  3.60it/s]

 74%|███████▍  | 245/332 [01:14<00:24,  3.55it/s]

 74%|███████▍  | 246/332 [01:14<00:28,  3.04it/s]

 74%|███████▍  | 247/332 [01:14<00:25,  3.27it/s]

 75%|███████▍  | 248/332 [01:15<00:29,  2.89it/s]

 75%|███████▌  | 249/332 [01:15<00:26,  3.17it/s]

 75%|███████▌  | 250/332 [01:15<00:23,  3.55it/s]

 76%|███████▌  | 251/332 [01:16<00:23,  3.52it/s]

 76%|███████▌  | 252/332 [01:16<00:22,  3.52it/s]

 76%|███████▌  | 253/332 [01:16<00:24,  3.25it/s]

 77%|███████▋  | 254/332 [01:17<00:27,  2.82it/s]

 77%|███████▋  | 255/332 [01:17<00:28,  2.66it/s]

 77%|███████▋  | 256/332 [01:17<00:24,  3.05it/s]

 77%|███████▋  | 257/332 [01:18<00:27,  2.75it/s]

 78%|███████▊  | 258/332 [01:18<00:25,  2.94it/s]

 78%|███████▊  | 259/332 [01:18<00:23,  3.08it/s]

 78%|███████▊  | 260/332 [01:19<00:21,  3.34it/s]

 79%|███████▊  | 261/332 [01:19<00:22,  3.19it/s]

 79%|███████▉  | 262/332 [01:19<00:20,  3.38it/s]

 79%|███████▉  | 263/332 [01:20<00:21,  3.25it/s]

 80%|███████▉  | 264/332 [01:20<00:21,  3.15it/s]

 80%|███████▉  | 265/332 [01:20<00:18,  3.55it/s]

 80%|████████  | 266/332 [01:21<00:21,  3.02it/s]

 80%|████████  | 267/332 [01:21<00:23,  2.78it/s]

 81%|████████  | 268/332 [01:21<00:21,  2.97it/s]

 81%|████████  | 269/332 [01:21<00:19,  3.22it/s]

 81%|████████▏ | 270/332 [01:22<00:18,  3.43it/s]

 82%|████████▏ | 271/332 [01:22<00:20,  3.00it/s]

 82%|████████▏ | 272/332 [01:22<00:17,  3.33it/s]

 82%|████████▏ | 273/332 [01:23<00:19,  3.04it/s]

 83%|████████▎ | 274/332 [01:23<00:18,  3.15it/s]

 83%|████████▎ | 275/332 [01:23<00:16,  3.50it/s]

 83%|████████▎ | 276/332 [01:24<00:15,  3.61it/s]

 83%|████████▎ | 277/332 [01:24<00:16,  3.38it/s]

 84%|████████▎ | 278/332 [01:24<00:15,  3.55it/s]

 84%|████████▍ | 279/332 [01:24<00:13,  3.86it/s]

 84%|████████▍ | 280/332 [01:25<00:13,  3.93it/s]

 85%|████████▍ | 281/332 [01:25<00:15,  3.23it/s]

 85%|████████▍ | 282/332 [01:25<00:16,  3.12it/s]

 85%|████████▌ | 283/332 [01:26<00:15,  3.19it/s]

 86%|████████▌ | 284/332 [01:26<00:15,  3.11it/s]

 86%|████████▌ | 285/332 [01:26<00:14,  3.33it/s]

 86%|████████▌ | 286/332 [01:26<00:12,  3.62it/s]

 86%|████████▋ | 287/332 [01:27<00:14,  3.11it/s]

 87%|████████▋ | 288/332 [01:27<00:12,  3.51it/s]

 87%|████████▋ | 289/332 [01:27<00:11,  3.63it/s]

 87%|████████▋ | 290/332 [01:28<00:10,  3.91it/s]

 88%|████████▊ | 291/332 [01:28<00:10,  3.74it/s]

 88%|████████▊ | 292/332 [01:28<00:12,  3.14it/s]

 88%|████████▊ | 293/332 [01:29<00:11,  3.38it/s]

 89%|████████▊ | 294/332 [01:29<00:12,  3.06it/s]

 89%|████████▉ | 295/332 [01:29<00:11,  3.16it/s]

 89%|████████▉ | 296/332 [01:30<00:11,  3.08it/s]

 89%|████████▉ | 297/332 [01:30<00:10,  3.42it/s]

 90%|████████▉ | 298/332 [01:30<00:09,  3.56it/s]

 90%|█████████ | 299/332 [01:30<00:10,  3.05it/s]

 90%|█████████ | 300/332 [01:31<00:09,  3.27it/s]

 91%|█████████ | 301/332 [01:31<00:09,  3.44it/s]

 91%|█████████ | 302/332 [01:31<00:08,  3.61it/s]

 91%|█████████▏| 303/332 [01:31<00:08,  3.57it/s]

 92%|█████████▏| 304/332 [01:32<00:07,  3.88it/s]

 92%|█████████▏| 305/332 [01:32<00:07,  3.43it/s]

 92%|█████████▏| 306/332 [01:32<00:07,  3.26it/s]

 92%|█████████▏| 307/332 [01:33<00:08,  2.88it/s]

 93%|█████████▎| 308/332 [01:33<00:09,  2.65it/s]

 93%|█████████▎| 309/332 [01:34<00:09,  2.51it/s]

 93%|█████████▎| 310/332 [01:34<00:08,  2.74it/s]

 94%|█████████▎| 311/332 [01:34<00:06,  3.03it/s]

 94%|█████████▍| 312/332 [01:35<00:06,  3.26it/s]

 94%|█████████▍| 313/332 [01:35<00:06,  2.89it/s]

 95%|█████████▍| 314/332 [01:35<00:05,  3.01it/s]

 95%|█████████▍| 315/332 [01:36<00:05,  3.23it/s]

 95%|█████████▌| 316/332 [01:36<00:04,  3.57it/s]

 95%|█████████▌| 317/332 [01:36<00:04,  3.69it/s]

 96%|█████████▌| 318/332 [01:36<00:03,  3.76it/s]

 96%|█████████▌| 319/332 [01:37<00:03,  3.83it/s]

 96%|█████████▋| 320/332 [01:37<00:02,  4.04it/s]

 97%|█████████▋| 321/332 [01:37<00:02,  4.23it/s]

 97%|█████████▋| 322/332 [01:37<00:02,  4.19it/s]

 97%|█████████▋| 323/332 [01:37<00:02,  4.32it/s]

 98%|█████████▊| 324/332 [01:38<00:02,  3.74it/s]

 98%|█████████▊| 325/332 [01:38<00:01,  3.68it/s]

 98%|█████████▊| 326/332 [01:38<00:01,  3.78it/s]

 98%|█████████▊| 327/332 [01:39<00:01,  3.70it/s]

 99%|█████████▉| 328/332 [01:39<00:01,  3.43it/s]

 99%|█████████▉| 329/332 [01:39<00:01,  2.97it/s]

 99%|█████████▉| 330/332 [01:40<00:00,  2.97it/s]

100%|█████████▉| 331/332 [01:40<00:00,  3.54it/s]

100%|██████████| 332/332 [01:40<00:00,  3.03it/s]
                                                 

                                                 
{'eval_loss': 0.27866294980049133, 'eval_runtime': 101.2195, 'eval_samples_per_second': 6.56, 'eval_steps_per_second': 3.28, 'epoch': 1.0}

100%|██████████| 747/747 [47:38<00:00,  3.69s/it]

100%|██████████| 332/332 [01:40<00:00,  3.03it/s]

                                                 [INFO|trainer.py:1947] 2024-01-18 19:17:52,666 >> 

Training completed. Do not forget to share your model on huggingface.co/models =)



                                                 
{'train_runtime': 2859.8545, 'train_samples_per_second': 2.089, 'train_steps_per_second': 0.261, 'train_loss': 0.3299662241814446, 'epoch': 1.0}

100%|██████████| 747/747 [47:38<00:00,  3.69s/it]
100%|██████████| 747/747 [47:38<00:00,  3.83s/it]
[INFO|trainer.py:2889] 2024-01-18 19:17:52,669 >> Saving model checkpoint to ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora
[INFO|tokenization_utils_base.py:2432] 2024-01-18 19:17:52,742 >> tokenizer config file saved in ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/tokenizer_config.json
[INFO|tokenization_utils_base.py:2441] 2024-01-18 19:17:52,742 >> Special tokens file saved in ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/special_tokens_map.json
***** train metrics *****
  epoch                    =        1.0
  train_loss               =       0.33
  train_runtime            = 0:47:39.85
  train_samples_per_second =      2.089
  train_steps_per_second   =      0.261
Figure saved: ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/training_loss.png
Figure saved: ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/training_eval_loss.png
[INFO|trainer.py:3166] 2024-01-18 19:17:55,818 >> ***** Running Evaluation *****
[INFO|trainer.py:3168] 2024-01-18 19:17:55,818 >>   Num examples = 664
[INFO|trainer.py:3171] 2024-01-18 19:17:55,818 >>   Batch size = 1

  0%|          | 0/332 [00:00<?, ?it/s]
  1%|          | 2/332 [00:00<00:41,  7.94it/s]
  1%|          | 3/332 [00:00<00:58,  5.66it/s]
  1%|          | 4/332 [00:00<01:07,  4.85it/s]
  2%|▏         | 5/332 [00:01<01:29,  3.66it/s]
  2%|▏         | 6/332 [00:01<01:46,  3.05it/s]
  2%|▏         | 7/332 [00:01<01:42,  3.19it/s]
  2%|▏         | 8/332 [00:02<01:54,  2.83it/s]
  3%|▎         | 9/332 [00:02<01:38,  3.26it/s]
  3%|▎         | 10/332 [00:02<01:51,  2.88it/s]
  3%|▎         | 11/332 [00:03<01:56,  2.76it/s]
  4%|▎         | 12/332 [00:03<02:05,  2.54it/s]
  4%|▍         | 13/332 [00:04<02:09,  2.46it/s]
  4%|▍         | 14/332 [00:04<01:54,  2.77it/s]
  5%|▍         | 15/332 [00:04<01:55,  2.76it/s]
  5%|▍         | 16/332 [00:05<01:43,  3.04it/s]
  5%|▌         | 17/332 [00:05<01:32,  3.40it/s]
  5%|▌         | 18/332 [00:05<01:28,  3.56it/s]
  6%|▌         | 19/332 [00:05<01:21,  3.84it/s]
  6%|▌         | 20/332 [00:06<01:23,  3.73it/s]
  6%|▋         | 21/332 [00:06<01:30,  3.45it/s]
  7%|▋         | 22/332 [00:06<01:29,  3.48it/s]
  7%|▋         | 23/332 [00:06<01:25,  3.62it/s]
  7%|▋         | 24/332 [00:07<01:19,  3.88it/s]
  8%|▊         | 25/332 [00:07<01:18,  3.93it/s]
  8%|▊         | 26/332 [00:07<01:16,  3.98it/s]
  8%|▊         | 27/332 [00:07<01:12,  4.19it/s]
  8%|▊         | 28/332 [00:08<01:27,  3.49it/s]
  9%|▊         | 29/332 [00:08<01:23,  3.64it/s]
  9%|▉         | 30/332 [00:08<01:15,  3.98it/s]
  9%|▉         | 31/332 [00:08<01:12,  4.17it/s]
 10%|▉         | 32/332 [00:09<01:12,  4.13it/s]
 10%|▉         | 33/332 [00:09<01:16,  3.89it/s]
 10%|█         | 34/332 [00:09<01:29,  3.32it/s]
 11%|█         | 35/332 [00:10<01:39,  2.97it/s]
 11%|█         | 36/332 [00:10<01:31,  3.23it/s]
 11%|█         | 37/332 [00:10<01:35,  3.08it/s]
 11%|█▏        | 38/332 [00:11<01:25,  3.44it/s]
 12%|█▏        | 39/332 [00:11<01:38,  2.97it/s]
 12%|█▏        | 40/332 [00:11<01:38,  2.98it/s]
 12%|█▏        | 41/332 [00:12<01:37,  2.98it/s]
 13%|█▎        | 42/332 [00:12<01:32,  3.13it/s]
 13%|█▎        | 43/332 [00:12<01:29,  3.22it/s]
 13%|█▎        | 44/332 [00:12<01:16,  3.76it/s]
 14%|█▎        | 45/332 [00:13<01:33,  3.05it/s]
 14%|█▍        | 46/332 [00:13<01:30,  3.14it/s]
 14%|█▍        | 47/332 [00:14<01:28,  3.23it/s]
 14%|█▍        | 48/332 [00:14<01:20,  3.53it/s]
 15%|█▍        | 49/332 [00:14<01:17,  3.64it/s]
 15%|█▌        | 50/332 [00:14<01:14,  3.76it/s]
 15%|█▌        | 51/332 [00:14<01:12,  3.85it/s]
 16%|█▌        | 52/332 [00:15<01:04,  4.36it/s]
 16%|█▌        | 53/332 [00:15<01:01,  4.53it/s]
 16%|█▋        | 54/332 [00:15<01:00,  4.56it/s]
 17%|█▋        | 55/332 [00:15<01:10,  3.95it/s]
 17%|█▋        | 56/332 [00:16<01:13,  3.78it/s]
 17%|█▋        | 57/332 [00:16<01:08,  4.04it/s]
 17%|█▋        | 58/332 [00:16<01:00,  4.51it/s]
 18%|█▊        | 59/332 [00:16<01:02,  4.35it/s]
 18%|█▊        | 60/332 [00:17<01:06,  4.07it/s]
 18%|█▊        | 61/332 [00:17<01:06,  4.06it/s]
 19%|█▊        | 62/332 [00:17<01:09,  3.86it/s]
 19%|█▉        | 63/332 [00:18<01:24,  3.19it/s]
 19%|█▉        | 64/332 [00:18<01:34,  2.84it/s]
 20%|█▉        | 65/332 [00:18<01:33,  2.87it/s]
 20%|█▉        | 66/332 [00:19<01:39,  2.66it/s]
 20%|██        | 67/332 [00:19<01:30,  2.94it/s]
 20%|██        | 68/332 [00:19<01:21,  3.23it/s]
 21%|██        | 69/332 [00:20<01:31,  2.87it/s]
 21%|██        | 70/332 [00:20<01:23,  3.14it/s]
 21%|██▏       | 71/332 [00:20<01:20,  3.23it/s]
 22%|██▏       | 72/332 [00:20<01:15,  3.44it/s]
 22%|██▏       | 73/332 [00:21<01:12,  3.59it/s]
 22%|██▏       | 74/332 [00:21<01:24,  3.06it/s]
 23%|██▎       | 75/332 [00:22<01:33,  2.76it/s]
 23%|██▎       | 76/332 [00:22<01:23,  3.06it/s]
 23%|██▎       | 77/332 [00:22<01:17,  3.31it/s]
 23%|██▎       | 78/332 [00:22<01:12,  3.48it/s]
 24%|██▍       | 79/332 [00:23<01:09,  3.62it/s]
 24%|██▍       | 80/332 [00:23<01:22,  3.06it/s]
 24%|██▍       | 81/332 [00:24<01:30,  2.78it/s]
 25%|██▍       | 82/332 [00:24<01:21,  3.05it/s]
 25%|██▌       | 83/332 [00:24<01:30,  2.76it/s]
 25%|██▌       | 84/332 [00:25<01:25,  2.91it/s]
 26%|██▌       | 85/332 [00:25<01:26,  2.85it/s]
 26%|██▌       | 86/332 [00:25<01:18,  3.13it/s]
 26%|██▌       | 87/332 [00:25<01:12,  3.37it/s]
 27%|██▋       | 88/332 [00:26<01:12,  3.38it/s]
 27%|██▋       | 89/332 [00:26<01:08,  3.55it/s]
 27%|██▋       | 90/332 [00:26<01:03,  3.81it/s]
 27%|██▋       | 91/332 [00:26<00:59,  4.07it/s]
 28%|██▊       | 92/332 [00:27<00:59,  4.06it/s]
 28%|██▊       | 93/332 [00:27<01:07,  3.52it/s]
 28%|██▊       | 94/332 [00:27<01:05,  3.64it/s]
 29%|██▊       | 95/332 [00:28<01:12,  3.26it/s]
 29%|██▉       | 96/332 [00:28<01:20,  2.92it/s]
 29%|██▉       | 97/332 [00:28<01:11,  3.27it/s]
 30%|██▉       | 98/332 [00:28<01:05,  3.56it/s]
 30%|██▉       | 99/332 [00:29<01:00,  3.85it/s]
 30%|███       | 100/332 [00:29<01:13,  3.17it/s]
 30%|███       | 101/332 [00:29<01:14,  3.08it/s]
 31%|███       | 102/332 [00:30<01:22,  2.78it/s]
 31%|███       | 103/332 [00:30<01:27,  2.61it/s]
 31%|███▏      | 104/332 [00:31<01:15,  3.00it/s]
 32%|███▏      | 105/332 [00:31<01:04,  3.54it/s]
 32%|███▏      | 106/332 [00:31<01:11,  3.15it/s]
 32%|███▏      | 107/332 [00:31<01:06,  3.36it/s]
 33%|███▎      | 108/332 [00:32<01:09,  3.21it/s]
 33%|███▎      | 109/332 [00:32<01:15,  2.94it/s]
 33%|███▎      | 110/332 [00:33<01:22,  2.69it/s]
 33%|███▎      | 111/332 [00:33<01:20,  2.75it/s]
 34%|███▎      | 112/332 [00:33<01:14,  2.93it/s]
 34%|███▍      | 113/332 [00:34<01:23,  2.64it/s]
 34%|███▍      | 114/332 [00:34<01:17,  2.82it/s]
 35%|███▍      | 115/332 [00:34<01:10,  3.10it/s]
 35%|███▍      | 116/332 [00:34<01:04,  3.33it/s]
 35%|███▌      | 117/332 [00:35<00:55,  3.86it/s]
 36%|███▌      | 118/332 [00:35<00:57,  3.73it/s]
 36%|███▌      | 119/332 [00:35<00:59,  3.60it/s]
 36%|███▌      | 120/332 [00:36<01:08,  3.11it/s]
 36%|███▋      | 121/332 [00:36<01:05,  3.21it/s]
 37%|███▋      | 122/332 [00:36<01:04,  3.27it/s]
 37%|███▋      | 123/332 [00:36<01:02,  3.33it/s]
 37%|███▋      | 124/332 [00:37<00:57,  3.62it/s]
 38%|███▊      | 125/332 [00:37<00:52,  3.96it/s]
 38%|███▊      | 126/332 [00:37<01:03,  3.22it/s]
 38%|███▊      | 127/332 [00:38<01:12,  2.84it/s]
 39%|███▊      | 128/332 [00:38<01:17,  2.64it/s]
 39%|███▉      | 129/332 [00:39<01:14,  2.73it/s]
 39%|███▉      | 130/332 [00:39<01:04,  3.16it/s]
 39%|███▉      | 131/332 [00:39<00:59,  3.38it/s]
 40%|███▉      | 132/332 [00:39<00:54,  3.66it/s]
 40%|████      | 133/332 [00:40<01:05,  3.02it/s]
 40%|████      | 134/332 [00:40<01:00,  3.28it/s]
 41%|████      | 135/332 [00:40<00:56,  3.50it/s]
 41%|████      | 136/332 [00:41<01:06,  2.96it/s]
 41%|████▏     | 137/332 [00:41<01:06,  2.94it/s]
 42%|████▏     | 138/332 [00:41<01:00,  3.19it/s]
 42%|████▏     | 139/332 [00:42<00:59,  3.25it/s]
 42%|████▏     | 140/332 [00:42<01:06,  2.88it/s]
 42%|████▏     | 141/332 [00:42<01:12,  2.62it/s]
 43%|████▎     | 142/332 [00:43<01:07,  2.84it/s]
 43%|████▎     | 143/332 [00:43<01:02,  3.00it/s]
 43%|████▎     | 144/332 [00:43<00:57,  3.26it/s]
 44%|████▎     | 145/332 [00:44<01:04,  2.89it/s]
 44%|████▍     | 146/332 [00:44<01:09,  2.67it/s]
 44%|████▍     | 147/332 [00:44<01:00,  3.04it/s]
 45%|████▍     | 148/332 [00:45<01:01,  3.00it/s]
 45%|████▍     | 149/332 [00:45<00:54,  3.36it/s]
 45%|████▌     | 150/332 [00:45<00:59,  3.05it/s]
 45%|████▌     | 151/332 [00:46<00:57,  3.16it/s]
 46%|████▌     | 152/332 [00:46<00:58,  3.09it/s]
 46%|████▌     | 153/332 [00:46<01:04,  2.78it/s]
 46%|████▋     | 154/332 [00:47<01:08,  2.61it/s]
 47%|████▋     | 155/332 [00:47<01:00,  2.91it/s]
 47%|████▋     | 156/332 [00:47<00:53,  3.26it/s]
 47%|████▋     | 157/332 [00:48<00:52,  3.30it/s]
 48%|████▊     | 158/332 [00:48<00:51,  3.36it/s]
 48%|████▊     | 159/332 [00:48<00:49,  3.52it/s]
 48%|████▊     | 160/332 [00:49<00:55,  3.08it/s]
 48%|████▊     | 161/332 [00:49<00:58,  2.90it/s]
 49%|████▉     | 162/332 [00:49<01:03,  2.67it/s]
 49%|████▉     | 163/332 [00:50<00:56,  2.97it/s]
 49%|████▉     | 164/332 [00:50<00:47,  3.53it/s]
 50%|████▉     | 165/332 [00:50<00:55,  3.03it/s]
 50%|█████     | 166/332 [00:51<00:50,  3.28it/s]
 50%|█████     | 167/332 [00:51<00:46,  3.58it/s]
 51%|█████     | 168/332 [00:51<00:53,  3.04it/s]
 51%|█████     | 169/332 [00:52<00:59,  2.75it/s]
 51%|█████     | 170/332 [00:52<00:53,  3.04it/s]
 52%|█████▏    | 171/332 [00:52<00:47,  3.41it/s]
 52%|█████▏    | 172/332 [00:52<00:42,  3.74it/s]
 52%|█████▏    | 173/332 [00:53<00:41,  3.83it/s]
 52%|█████▏    | 174/332 [00:53<00:44,  3.53it/s]
 53%|█████▎    | 175/332 [00:53<00:46,  3.35it/s]
 53%|█████▎    | 176/332 [00:53<00:43,  3.56it/s]
 53%|█████▎    | 177/332 [00:54<00:50,  3.10it/s]
 54%|█████▎    | 178/332 [00:54<00:46,  3.31it/s]
 54%|█████▍    | 179/332 [00:54<00:45,  3.37it/s]
 54%|█████▍    | 180/332 [00:55<00:42,  3.55it/s]
 55%|█████▍    | 181/332 [00:55<00:42,  3.53it/s]
 55%|█████▍    | 182/332 [00:55<00:36,  4.08it/s]
 55%|█████▌    | 183/332 [00:55<00:34,  4.29it/s]
 55%|█████▌    | 184/332 [00:56<00:37,  3.98it/s]
 56%|█████▌    | 185/332 [00:56<00:40,  3.60it/s]
 56%|█████▌    | 186/332 [00:56<00:48,  2.98it/s]
 56%|█████▋    | 187/332 [00:57<00:46,  3.11it/s]
 57%|█████▋    | 188/332 [00:57<00:41,  3.50it/s]
 57%|█████▋    | 189/332 [00:57<00:43,  3.28it/s]
 57%|█████▋    | 190/332 [00:57<00:39,  3.58it/s]
 58%|█████▊    | 191/332 [00:58<00:45,  3.09it/s]
 58%|█████▊    | 192/332 [00:58<00:46,  3.02it/s]
 58%|█████▊    | 193/332 [00:59<00:44,  3.11it/s]
 58%|█████▊    | 194/332 [00:59<00:43,  3.20it/s]
 59%|█████▊    | 195/332 [00:59<00:39,  3.43it/s]
 59%|█████▉    | 196/332 [00:59<00:37,  3.60it/s]
 59%|█████▉    | 197/332 [01:00<00:34,  3.86it/s]
 60%|█████▉    | 198/332 [01:00<00:42,  3.17it/s]
 60%|█████▉    | 199/332 [01:00<00:40,  3.26it/s]
 60%|██████    | 200/332 [01:00<00:37,  3.56it/s]
 61%|██████    | 201/332 [01:01<00:40,  3.27it/s]
 61%|██████    | 202/332 [01:01<00:44,  2.89it/s]
 61%|██████    | 203/332 [01:01<00:39,  3.29it/s]
 61%|██████▏   | 204/332 [01:02<00:42,  3.00it/s]
 62%|██████▏   | 205/332 [01:02<00:40,  3.13it/s]
 62%|██████▏   | 206/332 [01:02<00:38,  3.25it/s]
 62%|██████▏   | 207/332 [01:03<00:37,  3.30it/s]
 63%|██████▎   | 208/332 [01:03<00:35,  3.50it/s]
 63%|██████▎   | 209/332 [01:03<00:33,  3.64it/s]
 63%|██████▎   | 210/332 [01:03<00:32,  3.76it/s]
 64%|██████▎   | 211/332 [01:04<00:37,  3.23it/s]
 64%|██████▍   | 212/332 [01:04<00:41,  2.86it/s]
 64%|██████▍   | 213/332 [01:05<00:36,  3.22it/s]
 64%|██████▍   | 214/332 [01:05<00:37,  3.12it/s]
 65%|██████▍   | 215/332 [01:05<00:36,  3.19it/s]
 65%|██████▌   | 216/332 [01:05<00:30,  3.76it/s]
 65%|██████▌   | 217/332 [01:06<00:29,  3.84it/s]
 66%|██████▌   | 218/332 [01:06<00:32,  3.51it/s]
 66%|██████▌   | 219/332 [01:06<00:31,  3.63it/s]
 66%|██████▋   | 220/332 [01:06<00:28,  3.89it/s]
 67%|██████▋   | 221/332 [01:07<00:28,  3.93it/s]
 67%|██████▋   | 222/332 [01:07<00:33,  3.33it/s]
 67%|██████▋   | 223/332 [01:07<00:31,  3.47it/s]
 67%|██████▋   | 224/332 [01:08<00:36,  2.99it/s]
 68%|██████▊   | 225/332 [01:08<00:34,  3.14it/s]
 68%|██████▊   | 226/332 [01:08<00:33,  3.21it/s]
 68%|██████▊   | 227/332 [01:09<00:31,  3.28it/s]
 69%|██████▊   | 228/332 [01:09<00:27,  3.83it/s]
 69%|██████▉   | 229/332 [01:09<00:32,  3.18it/s]
 69%|██████▉   | 230/332 [01:10<00:33,  3.09it/s]
 70%|██████▉   | 231/332 [01:10<00:29,  3.46it/s]
 70%|██████▉   | 232/332 [01:10<00:26,  3.78it/s]
 70%|███████   | 233/332 [01:10<00:24,  3.98it/s]
 70%|███████   | 234/332 [01:11<00:30,  3.17it/s]
 71%|███████   | 235/332 [01:11<00:29,  3.27it/s]
 71%|███████   | 236/332 [01:11<00:26,  3.62it/s]
 71%|███████▏  | 237/332 [01:11<00:24,  3.87it/s]
 72%|███████▏  | 238/332 [01:12<00:26,  3.54it/s]
 72%|███████▏  | 239/332 [01:12<00:26,  3.49it/s]
 72%|███████▏  | 240/332 [01:12<00:27,  3.30it/s]
 73%|███████▎  | 241/332 [01:13<00:24,  3.69it/s]
 73%|███████▎  | 242/332 [01:13<00:29,  3.09it/s]
 73%|███████▎  | 243/332 [01:13<00:24,  3.63it/s]
 73%|███████▎  | 244/332 [01:13<00:24,  3.60it/s]
 74%|███████▍  | 245/332 [01:14<00:24,  3.55it/s]
 74%|███████▍  | 246/332 [01:14<00:28,  3.04it/s]
 74%|███████▍  | 247/332 [01:14<00:26,  3.27it/s]
 75%|███████▍  | 248/332 [01:15<00:29,  2.89it/s]
 75%|███████▌  | 249/332 [01:15<00:26,  3.17it/s]
 75%|███████▌  | 250/332 [01:15<00:23,  3.55it/s]
 76%|███████▌  | 251/332 [01:16<00:23,  3.52it/s]
 76%|███████▌  | 252/332 [01:16<00:22,  3.52it/s]
 76%|███████▌  | 253/332 [01:16<00:24,  3.25it/s]
 77%|███████▋  | 254/332 [01:17<00:27,  2.82it/s]
 77%|███████▋  | 255/332 [01:17<00:28,  2.67it/s]
 77%|███████▋  | 256/332 [01:17<00:24,  3.05it/s]
 77%|███████▋  | 257/332 [01:18<00:27,  2.76it/s]
 78%|███████▊  | 258/332 [01:18<00:25,  2.94it/s]
 78%|███████▊  | 259/332 [01:18<00:23,  3.08it/s]
 78%|███████▊  | 260/332 [01:19<00:21,  3.34it/s]
 79%|███████▊  | 261/332 [01:19<00:22,  3.19it/s]
 79%|███████▉  | 262/332 [01:19<00:20,  3.38it/s]
 79%|███████▉  | 263/332 [01:20<00:21,  3.25it/s]
 80%|███████▉  | 264/332 [01:20<00:21,  3.15it/s]
 80%|███████▉  | 265/332 [01:20<00:18,  3.55it/s]
 80%|████████  | 266/332 [01:21<00:21,  3.02it/s]
 80%|████████  | 267/332 [01:21<00:23,  2.78it/s]
 81%|████████  | 268/332 [01:21<00:21,  2.97it/s]
 81%|████████  | 269/332 [01:22<00:19,  3.22it/s]
 81%|████████▏ | 270/332 [01:22<00:18,  3.43it/s]
 82%|████████▏ | 271/332 [01:22<00:20,  3.00it/s]
 82%|████████▏ | 272/332 [01:22<00:17,  3.34it/s]
 82%|████████▏ | 273/332 [01:23<00:19,  3.04it/s]
 83%|████████▎ | 274/332 [01:23<00:18,  3.16it/s]
 83%|████████▎ | 275/332 [01:23<00:16,  3.50it/s]
 83%|████████▎ | 276/332 [01:24<00:15,  3.61it/s]
 83%|████████▎ | 277/332 [01:24<00:16,  3.37it/s]
 84%|████████▎ | 278/332 [01:24<00:15,  3.55it/s]
 84%|████████▍ | 279/332 [01:24<00:13,  3.86it/s]
 84%|████████▍ | 280/332 [01:25<00:13,  3.93it/s]
 85%|████████▍ | 281/332 [01:25<00:15,  3.23it/s]
 85%|████████▍ | 282/332 [01:25<00:16,  3.12it/s]
 85%|████████▌ | 283/332 [01:26<00:15,  3.19it/s]
 86%|████████▌ | 284/332 [01:26<00:15,  3.11it/s]
 86%|████████▌ | 285/332 [01:26<00:14,  3.33it/s]
 86%|████████▌ | 286/332 [01:26<00:12,  3.61it/s]
 86%|████████▋ | 287/332 [01:27<00:14,  3.11it/s]
 87%|████████▋ | 288/332 [01:27<00:12,  3.50it/s]
 87%|████████▋ | 289/332 [01:27<00:11,  3.63it/s]
 87%|████████▋ | 290/332 [01:28<00:10,  3.90it/s]
 88%|████████▊ | 291/332 [01:28<00:10,  3.74it/s]
 88%|████████▊ | 292/332 [01:28<00:12,  3.14it/s]
 88%|████████▊ | 293/332 [01:29<00:11,  3.38it/s]
 89%|████████▊ | 294/332 [01:29<00:12,  3.06it/s]
 89%|████████▉ | 295/332 [01:29<00:11,  3.16it/s]
 89%|████████▉ | 296/332 [01:30<00:11,  3.08it/s]
 89%|████████▉ | 297/332 [01:30<00:10,  3.43it/s]
 90%|████████▉ | 298/332 [01:30<00:09,  3.56it/s]
 90%|█████████ | 299/332 [01:30<00:10,  3.05it/s]
 90%|█████████ | 300/332 [01:31<00:09,  3.27it/s]
 91%|█████████ | 301/332 [01:31<00:08,  3.45it/s]
 91%|█████████ | 302/332 [01:31<00:08,  3.61it/s]
 91%|█████████▏| 303/332 [01:32<00:08,  3.57it/s]
 92%|█████████▏| 304/332 [01:32<00:07,  3.89it/s]
 92%|█████████▏| 305/332 [01:32<00:07,  3.44it/s]
 92%|█████████▏| 306/332 [01:32<00:07,  3.27it/s]
 92%|█████████▏| 307/332 [01:33<00:08,  2.88it/s]
 93%|█████████▎| 308/332 [01:33<00:09,  2.65it/s]
 93%|█████████▎| 309/332 [01:34<00:09,  2.51it/s]
 93%|█████████▎| 310/332 [01:34<00:08,  2.74it/s]
 94%|█████████▎| 311/332 [01:34<00:06,  3.04it/s]
 94%|█████████▍| 312/332 [01:35<00:06,  3.26it/s]
 94%|█████████▍| 313/332 [01:35<00:06,  2.89it/s]
 95%|█████████▍| 314/332 [01:35<00:05,  3.01it/s]
 95%|█████████▍| 315/332 [01:36<00:05,  3.23it/s]
 95%|█████████▌| 316/332 [01:36<00:04,  3.56it/s]
 95%|█████████▌| 317/332 [01:36<00:04,  3.69it/s]
 96%|█████████▌| 318/332 [01:36<00:03,  3.76it/s]
 96%|█████████▌| 319/332 [01:37<00:03,  3.83it/s]
 96%|█████████▋| 320/332 [01:37<00:02,  4.04it/s]
 97%|█████████▋| 321/332 [01:37<00:02,  4.23it/s]
 97%|█████████▋| 322/332 [01:37<00:02,  4.19it/s]
 97%|█████████▋| 323/332 [01:37<00:02,  4.33it/s]
 98%|█████████▊| 324/332 [01:38<00:02,  3.74it/s]
 98%|█████████▊| 325/332 [01:38<00:01,  3.68it/s]
 98%|█████████▊| 326/332 [01:38<00:01,  3.78it/s]
 98%|█████████▊| 327/332 [01:39<00:01,  3.71it/s]
 99%|█████████▉| 328/332 [01:39<00:01,  3.43it/s]
 99%|█████████▉| 329/332 [01:39<00:01,  2.97it/s]
 99%|█████████▉| 330/332 [01:40<00:00,  2.98it/s]
100%|█████████▉| 331/332 [01:40<00:00,  3.54it/s]
100%|██████████| 332/332 [01:40<00:00,  3.03it/s]
100%|██████████| 332/332 [01:40<00:00,  3.29it/s]
***** eval metrics *****
  epoch                   =        1.0
  eval_loss               =     0.2787
  eval_runtime            = 0:01:41.25
  eval_samples_per_second =      6.558
  eval_steps_per_second   =      3.279
[INFO|modelcard.py:452] 2024-01-18 19:19:37,075 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}