Training in progress, step 500

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 500.0,
-    "eval_loss": 0.6521313190460205,
-    "eval_runtime": 134.0142,
-    "eval_samples": 2609,
-    "eval_samples_per_second": 19.468,
-    "eval_steps_per_second": 0.246,
-    "eval_wer": 0.40601336302895324,
-    "train_loss": 0.11533763631184896,
-    "train_runtime": 176050.2174,
-    "train_samples": 5705,
-    "train_samples_per_second": 16.203,
-    "train_steps_per_second": 0.102
-}

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 500.0,
-    "eval_loss": 0.6521313190460205,
-    "eval_runtime": 134.0142,
-    "eval_samples": 2609,
-    "eval_samples_per_second": 19.468,
-    "eval_steps_per_second": 0.246,
-    "eval_wer": 0.40601336302895324
-}

logs

@@ -1,320 +0,0 @@
-01/26/2022 10:56:56 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
-01/26/2022 10:56:56 - INFO - __main__ - Training/evaluation parameters TrainingArguments(
-_n_gpu=1,
-adafactor=False,
-adam_beta1=0.9,
-adam_beta2=0.999,
-adam_epsilon=1e-08,
-bf16=False,
-bf16_full_eval=False,
-dataloader_drop_last=False,
-dataloader_num_workers=0,
-dataloader_pin_memory=True,
-ddp_bucket_cap_mb=None,
-ddp_find_unused_parameters=None,
-debug=[],
-deepspeed=None,
-disable_tqdm=False,
-do_eval=True,
-do_predict=False,
-do_train=True,
-eval_accumulation_steps=None,
-eval_steps=500,
-evaluation_strategy=IntervalStrategy.STEPS,
-fp16=True,
-fp16_backend=auto,
-fp16_full_eval=False,
-fp16_opt_level=O1,
-gradient_accumulation_steps=2,
-gradient_checkpointing=True,
-greater_is_better=None,
-group_by_length=True,
-half_precision_backend=auto,
-hub_model_id=None,
-hub_strategy=HubStrategy.EVERY_SAVE,
-hub_token=<HUB_TOKEN>,
-ignore_data_skip=False,
-label_names=None,
-label_smoothing_factor=0.0,
-learning_rate=0.0003,
-length_column_name=input_length,
-load_best_model_at_end=False,
-local_rank=-1,
-log_level=-1,
-log_level_replica=-1,
-log_on_each_node=True,
-logging_dir=./runs/Jan26_10-56-56_ganymede.eafit.edu.co,
-logging_first_step=False,
-logging_nan_inf_filter=True,
-logging_steps=100,
-logging_strategy=IntervalStrategy.STEPS,
-lr_scheduler_type=SchedulerType.COSINE,
-max_grad_norm=1.0,
-max_steps=-1,
-metric_for_best_model=None,
-mp_parameters=,
-no_cuda=False,
-num_train_epochs=500.0,
-optim=OptimizerNames.ADAMW_HF,
-output_dir=./,
-overwrite_output_dir=True,
-past_index=-1,
-per_device_eval_batch_size=80,
-per_device_train_batch_size=80,
-prediction_loss_only=False,
-push_to_hub=True,
-push_to_hub_model_id=None,
-push_to_hub_organization=None,
-push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
-remove_unused_columns=True,
-report_to=['wandb'],
-resume_from_checkpoint=None,
-run_name=cosine+drop_proj+low_specaugment-300M,
-save_on_each_node=False,
-save_steps=500,
-save_strategy=IntervalStrategy.STEPS,
-save_total_limit=1,
-seed=42,
-sharded_ddp=[],
-skip_memory_metrics=True,
-tf32=None,
-tpu_metrics_debug=False,
-tpu_num_cores=None,
-use_legacy_prediction_loop=False,
-warmup_ratio=0.0,
-warmup_steps=500,
-weight_decay=0.0,
-xpu_backend=None,
-)
-01/26/2022 10:57:00 - WARNING - datasets.builder - Reusing dataset common_voice (/home/sagrilaft/.cache/huggingface/datasets/mozilla-foundation___common_voice/et/7.0.0/33e08856cfa0d0665e837bcad73ffd920a0bc713ce8c5fffb55dbdf1c084d5ba)
-01/26/2022 10:57:02 - WARNING - datasets.builder - Reusing dataset common_voice (/home/sagrilaft/.cache/huggingface/datasets/mozilla-foundation___common_voice/et/7.0.0/33e08856cfa0d0665e837bcad73ffd920a0bc713ce8c5fffb55dbdf1c084d5ba)
-01/26/2022 10:57:02 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sagrilaft/.cache/huggingface/datasets/mozilla-foundation___common_voice/et/7.0.0/33e08856cfa0d0665e837bcad73ffd920a0bc713ce8c5fffb55dbdf1c084d5ba/cache-f4479ce33e07f5c7.arrow
-01/26/2022 10:57:02 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sagrilaft/.cache/huggingface/datasets/mozilla-foundation___common_voice/et/7.0.0/33e08856cfa0d0665e837bcad73ffd920a0bc713ce8c5fffb55dbdf1c084d5ba/cache-105cefde64f772a9.arrow
-01/26/2022 10:58:44 - WARNING - huggingface_hub.repository - /home/sagrilaft/Project/audio/xls-r-et/./ is already a clone of https://huggingface.co/shpotes/xls-r-et. Make sure you pull the latest changes with `repo.git_pull()`.
-
-{'loss': 4.5903, 'learning_rate': 0.00019800000000000002, 'epoch': 2.78}
-{'loss': 2.9083, 'learning_rate': 0.000398, 'epoch': 5.56}
-{'loss': 1.2823, 'learning_rate': 0.000598, 'epoch': 8.33}
-{'loss': 0.3962, 'learning_rate': 0.0007980000000000001, 'epoch': 11.11}
-{'loss': 0.3034, 'learning_rate': 0.000998, 'epoch': 13.89}
-{'eval_loss': 0.38567885756492615, 'eval_wer': 0.4354438434616608, 'eval_runtime': 133.1769, 'eval_samples_per_second': 19.59, 'eval_steps_per_second': 0.248, 'epoch': 13.89}
-{'loss': 0.2639, 'learning_rate': 0.0009999210371864342, 'epoch': 16.67}
-{'loss': 0.2354, 'learning_rate': 0.0009996809758056298, 'epoch': 19.44}
-{'loss': 0.2158, 'learning_rate': 0.000999279885163942, 'epoch': 22.22}
-{'loss': 0.2063, 'learning_rate': 0.000998717894518502, 'epoch': 25.0}
-{'loss': 0.1926, 'learning_rate': 0.000997995184978743, 'epoch': 27.78}
-{'eval_loss': 0.4142022132873535, 'eval_wer': 0.4174355711104041, 'eval_runtime': 135.7258, 'eval_samples_per_second': 19.223, 'eval_steps_per_second': 0.243, 'epoch': 27.78}
-{'loss': 0.1771, 'learning_rate': 0.0009971119894480345, 'epoch': 30.56}
-{'loss': 0.1709, 'learning_rate': 0.0009960685925486266, 'epoch': 33.33}
-{'loss': 0.1724, 'learning_rate': 0.0009948653305299256, 'epoch': 36.11}
-{'loss': 0.1632, 'learning_rate': 0.0009935025911601335, 'epoch': 38.89}
-{'loss': 0.1609, 'learning_rate': 0.0009919808136012837, 'epoch': 41.67}
-{'eval_loss': 0.4701250195503235, 'eval_wer': 0.42958956411072224, 'eval_runtime': 133.1213, 'eval_samples_per_second': 19.599, 'eval_steps_per_second': 0.248, 'epoch': 41.67}
-01/26/2022 15:02:33 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb']. This may take a bit of time if the files are large.
-{'loss': 0.1521, 'learning_rate': 0.0009903004882677155, 'epoch': 44.44}
-{'loss': 0.1531, 'learning_rate': 0.0009884621566680308, 'epoch': 47.22}
-{'loss': 0.1514, 'learning_rate': 0.0009864664112305846, 'epoch': 50.0}
-{'loss': 0.1468, 'learning_rate': 0.0009843138951125682, 'epoch': 52.78}
-{'loss': 0.1501, 'learning_rate': 0.000982005301992741, 'epoch': 55.56}
-{'eval_loss': 0.45478546619415283, 'eval_wer': 0.43805281578110083, 'eval_runtime': 133.376, 'eval_samples_per_second': 19.561, 'eval_steps_per_second': 0.247, 'epoch': 55.56}
-{'loss': 0.1427, 'learning_rate': 0.0009795413758478834, 'epoch': 58.33}
-{'loss': 0.1441, 'learning_rate': 0.0009769229107130409, 'epoch': 61.11}
-{'loss': 0.1399, 'learning_rate': 0.0009741507504256327, 'epoch': 63.89}
-{'loss': 0.1379, 'learning_rate': 0.0009712257883535152, 'epoch': 66.67}
-{'loss': 0.1382, 'learning_rate': 0.0009681489671070803, 'epoch': 69.44}
-{'eval_loss': 0.523300290107727, 'eval_wer': 0.4544066178810054, 'eval_runtime': 131.9566, 'eval_samples_per_second': 19.772, 'eval_steps_per_second': 0.25, 'epoch': 69.44}
-{'loss': 0.1372, 'learning_rate': 0.0009649212782354872, 'epoch': 72.22}
-{'loss': 0.1345, 'learning_rate': 0.0009615437619071199, 'epoch': 75.0}
-{'loss': 0.1346, 'learning_rate': 0.0009580175065743799, 'epoch': 77.78}
-{'loss': 0.1367, 'learning_rate': 0.0009543436486229162, 'epoch': 80.56}
-{'loss': 0.1287, 'learning_rate': 0.0009505233720054086, 'epoch': 83.33}
-{'eval_loss': 0.48360341787338257, 'eval_wer': 0.43658924594336623, 'eval_runtime': 132.2498, 'eval_samples_per_second': 19.728, 'eval_steps_per_second': 0.25, 'epoch': 83.33}
-{'loss': 0.1226, 'learning_rate': 0.0009465579078600233, 'epoch': 86.11}
-{'loss': 0.1258, 'learning_rate': 0.0009424485341136599, 'epoch': 88.89}
-{'loss': 0.1222, 'learning_rate': 0.0009381965750701229, 'epoch': 91.67}
-{'loss': 0.1182, 'learning_rate': 0.0009338034009833446, 'epoch': 94.44}
-{'loss': 0.1164, 'learning_rate': 0.0009292704276158022, 'epoch': 97.22}
-{'eval_loss': 0.5202445983886719, 'eval_wer': 0.43948456888323256, 'eval_runtime': 132.7793, 'eval_samples_per_second': 19.649, 'eval_steps_per_second': 0.249, 'epoch': 97.22}
-{'loss': 0.1212, 'learning_rate': 0.0009245991157822682, 'epoch': 100.0}
-{'loss': 0.1139, 'learning_rate': 0.000919790970879042, 'epoch': 102.78}
-{'loss': 0.115, 'learning_rate': 0.000914847542398815, 'epoch': 105.56}
-{'loss': 0.1123, 'learning_rate': 0.0009097704234313245, 'epoch': 108.33}
-{'loss': 0.1101, 'learning_rate': 0.0009045612501499573, 'epoch': 111.11}
-{'eval_loss': 0.5120447874069214, 'eval_wer': 0.43827553293032134, 'eval_runtime': 131.3001, 'eval_samples_per_second': 19.871, 'eval_steps_per_second': 0.251, 'epoch': 111.11}
-{'loss': 0.1092, 'learning_rate': 0.0008992217012844713, 'epoch': 113.89}
-{'loss': 0.1104, 'learning_rate': 0.0008937534975799996, 'epoch': 116.67}
-{'loss': 0.1021, 'learning_rate': 0.0008881584012425165, 'epoch': 119.44}
-{'loss': 0.1063, 'learning_rate': 0.0008824382153709421, 'epoch': 122.22}
-{'loss': 0.1107, 'learning_rate': 0.0008765947833760678, 'epoch': 125.0}
-{'eval_loss': 0.5130612850189209, 'eval_wer': 0.4446706967865097, 'eval_runtime': 133.0961, 'eval_samples_per_second': 19.602, 'eval_steps_per_second': 0.248, 'epoch': 125.0}
-{'loss': 0.1054, 'learning_rate': 0.000870629988386491, 'epoch': 127.78}
-{'loss': 0.1037, 'learning_rate': 0.0008645457526417502, 'epoch': 130.56}
-{'loss': 0.1, 'learning_rate': 0.0008583440368728572, 'epoch': 133.33}
-{'loss': 0.0967, 'learning_rate': 0.0008520268396704223, 'epoch': 136.11}
-{'loss': 0.0942, 'learning_rate': 0.0008455961968405809, 'epoch': 138.89}
-{'eval_loss': 0.5256752967834473, 'eval_wer': 0.43748011454024816, 'eval_runtime': 133.1352, 'eval_samples_per_second': 19.597, 'eval_steps_per_second': 0.248, 'epoch': 138.89}
-{'loss': 0.0987, 'learning_rate': 0.0008390541807489265, 'epoch': 141.67}
-{'loss': 0.094, 'learning_rate': 0.0008324028996526611, 'epoch': 144.44}
-{'loss': 0.0935, 'learning_rate': 0.0008256444970211793, 'epoch': 147.22}
-{'loss': 0.0906, 'learning_rate': 0.000818781150845306, 'epoch': 150.0}
-{'loss': 0.0909, 'learning_rate': 0.0008118150729354068, 'epoch': 152.78}
-{'eval_loss': 0.5312919020652771, 'eval_wer': 0.47133312122176263, 'eval_runtime': 133.5185, 'eval_samples_per_second': 19.54, 'eval_steps_per_second': 0.247, 'epoch': 152.78}
-{'loss': 0.0881, 'learning_rate': 0.0008047485082086017, 'epoch': 155.56}
-{'loss': 0.0921, 'learning_rate': 0.0007975837339653084, 'epoch': 158.33}
-{'loss': 0.0838, 'learning_rate': 0.0007903230591553503, 'epoch': 161.11}
-{'loss': 0.0775, 'learning_rate': 0.0007829688236338643, 'epoch': 163.89}
-{'loss': 0.0807, 'learning_rate': 0.0007755233974072504, 'epoch': 166.67}
-{'eval_loss': 0.5847254991531372, 'eval_wer': 0.44708876869233216, 'eval_runtime': 133.1812, 'eval_samples_per_second': 19.59, 'eval_steps_per_second': 0.248, 'epoch': 166.67}
-{'loss': 0.0801, 'learning_rate': 0.0007679891798694021, 'epoch': 169.44}
-{'loss': 0.0952, 'learning_rate': 0.000760368599028469, 'epoch': 172.22}
-{'loss': 0.0813, 'learning_rate': 0.0007526641107243966, 'epoch': 175.0}
-{'loss': 0.0795, 'learning_rate': 0.0007448781978374969, 'epoch': 177.78}
-{'loss': 0.0767, 'learning_rate': 0.0007370133694883051, 'epoch': 180.56}
-{'eval_loss': 0.5318175554275513, 'eval_wer': 0.4534521158129176, 'eval_runtime': 135.804, 'eval_samples_per_second': 19.212, 'eval_steps_per_second': 0.243, 'epoch': 180.56}
-{'loss': 0.0762, 'learning_rate': 0.0007290721602289801, 'epoch': 183.33}
-{'loss': 0.0729, 'learning_rate': 0.0007210571292265096, 'epoch': 186.11}
-{'loss': 0.0751, 'learning_rate': 0.0007129708594379816, 'epoch': 188.89}
-{'loss': 0.0743, 'learning_rate': 0.0007048159567781905, 'epoch': 191.67}
-{'loss': 0.0729, 'learning_rate': 0.0006965950492798443, 'epoch': 194.44}
-{'eval_loss': 0.5796982645988464, 'eval_wer': 0.4584155265669742, 'eval_runtime': 132.2018, 'eval_samples_per_second': 19.735, 'eval_steps_per_second': 0.25, 'epoch': 194.44}
-{'loss': 0.0791, 'learning_rate': 0.0006883107862466433, 'epoch': 197.22}
-{'loss': 0.0737, 'learning_rate': 0.0006799658373995054, 'epoch': 200.0}
-{'loss': 0.0694, 'learning_rate': 0.0006715628920162093, 'epoch': 202.78}
-{'loss': 0.0687, 'learning_rate': 0.0006631046580647384, 'epoch': 205.56}
-{'loss': 0.072, 'learning_rate': 0.0006545938613305993, 'epoch': 208.33}
-{'eval_loss': 0.5266388654708862, 'eval_wer': 0.44339802736239264, 'eval_runtime': 130.3709, 'eval_samples_per_second': 20.012, 'eval_steps_per_second': 0.253, 'epoch': 208.33}
-{'loss': 0.0647, 'learning_rate': 0.000646033244538398, 'epoch': 211.11}
-{'loss': 0.0631, 'learning_rate': 0.000637425566467959, 'epoch': 213.89}
-{'loss': 0.0606, 'learning_rate': 0.0006287736010652693, 'epoch': 216.67}
-{'loss': 0.0645, 'learning_rate': 0.000620080136548535, 'epoch': 219.44}
-{'loss': 0.0593, 'learning_rate': 0.0006113479745096386, 'epoch': 222.22}
-{'eval_loss': 0.579177737236023, 'eval_wer': 0.43888005090677695, 'eval_runtime': 133.0716, 'eval_samples_per_second': 19.606, 'eval_steps_per_second': 0.248, 'epoch': 222.22}
-{'loss': 0.0596, 'learning_rate': 0.0006025799290112865, 'epoch': 225.0}
-{'loss': 0.0606, 'learning_rate': 0.0005937788256801371, 'epoch': 227.78}
-{'loss': 0.0591, 'learning_rate': 0.0005849475007962031, 'epoch': 230.56}
-{'loss': 0.0544, 'learning_rate': 0.0005760888003788196, 'epoch': 233.33}
-{'loss': 0.0524, 'learning_rate': 0.0005672055792694753, 'epoch': 236.11}
-{'eval_loss': 0.5740395784378052, 'eval_wer': 0.43732103086223356, 'eval_runtime': 132.5642, 'eval_samples_per_second': 19.681, 'eval_steps_per_second': 0.249, 'epoch': 236.11}
-{'loss': 0.0504, 'learning_rate': 0.0005583007002117978, 'epoch': 238.89}
-{'loss': 0.0494, 'learning_rate': 0.0005493770329289953, 'epoch': 241.67}
-{'loss': 0.0484, 'learning_rate': 0.0005404374531990474, 'epoch': 244.44}
-{'loss': 0.0489, 'learning_rate': 0.0005314848419279442, 'epoch': 247.22}
-{'loss': 0.0494, 'learning_rate': 0.0005225220842212748, 'epoch': 250.0}
-{'eval_loss': 0.5520852208137512, 'eval_wer': 0.44358892777601017, 'eval_runtime': 133.6258, 'eval_samples_per_second': 19.525, 'eval_steps_per_second': 0.247, 'epoch': 250.0}
-{'loss': 0.0499, 'learning_rate': 0.0005135520684544602, 'epoch': 252.78}
-{'loss': 0.0487, 'learning_rate': 0.0005045776853419344, 'epoch': 255.56}
-{'loss': 0.0523, 'learning_rate': 0.0004956018270055703, 'epoch': 258.33}
-{'loss': 0.0479, 'learning_rate': 0.00048662738604265206, 'epoch': 261.11}
-{'loss': 0.0469, 'learning_rate': 0.0004776572545936954, 'epoch': 263.89}
-{'eval_loss': 0.5630596876144409, 'eval_wer': 0.4345847916003818, 'eval_runtime': 130.7272, 'eval_samples_per_second': 19.958, 'eval_steps_per_second': 0.252, 'epoch': 263.89}
-{'loss': 0.0467, 'learning_rate': 0.0004686943234104146, 'epoch': 266.67}
-{'loss': 0.0438, 'learning_rate': 0.00045974148092413597, 'epoch': 269.44}
-{'loss': 0.0422, 'learning_rate': 0.00045080161231496064, 'epoch': 272.22}
-{'loss': 0.042, 'learning_rate': 0.00044187759858197486, 'epoch': 275.0}
-{'loss': 0.0417, 'learning_rate': 0.0004329723156148063, 'epoch': 277.78}
-{'eval_loss': 0.5777372121810913, 'eval_wer': 0.43057588291441296, 'eval_runtime': 130.7332, 'eval_samples_per_second': 19.957, 'eval_steps_per_second': 0.252, 'epoch': 277.78}
-{'loss': 0.0406, 'learning_rate': 0.0004240886332668285, 'epoch': 280.56}
-{'loss': 0.0385, 'learning_rate': 0.00041522941443031025, 'epoch': 283.33}
-{'loss': 0.0384, 'learning_rate': 0.0004063975141138074, 'epoch': 286.11}
-{'loss': 0.0369, 'learning_rate': 0.00039759577852209704, 'epoch': 288.89}
-{'loss': 0.0379, 'learning_rate': 0.0003888270441389465, 'epoch': 291.67}
-{'eval_loss': 0.5934527516365051, 'eval_wer': 0.42828507795100224, 'eval_runtime': 131.6738, 'eval_samples_per_second': 19.814, 'eval_steps_per_second': 0.251, 'epoch': 291.67}
-{'loss': 0.0399, 'learning_rate': 0.0003800941368130171, 'epoch': 294.44}
-{'loss': 0.0359, 'learning_rate': 0.0003713998708471946, 'epoch': 297.22}
-{'loss': 0.0345, 'learning_rate': 0.0003627470480916394, 'epoch': 300.0}
-{'loss': 0.0346, 'learning_rate': 0.00035413845704085215, 'epoch': 302.78}
-{'loss': 0.0319, 'learning_rate': 0.00034557687193504045, 'epoch': 305.56}
-{'eval_loss': 0.5892442464828491, 'eval_wer': 0.41880369074132995, 'eval_runtime': 130.692, 'eval_samples_per_second': 19.963, 'eval_steps_per_second': 0.253, 'epoch': 305.56}
-{'loss': 0.0318, 'learning_rate': 0.00033706505186608136, 'epoch': 308.33}
-{'loss': 0.0301, 'learning_rate': 0.00032860573988836573, 'epoch': 311.11}
-{'loss': 0.0322, 'learning_rate': 0.0003202016621348088, 'epoch': 313.89}
-{'loss': 0.0331, 'learning_rate': 0.00031185552693831594, 'epoch': 316.67}
-{'loss': 0.0311, 'learning_rate': 0.0003035700239589846, 'epoch': 319.44}
-{'eval_loss': 0.6010639071464539, 'eval_wer': 0.4210626789691378, 'eval_runtime': 132.2371, 'eval_samples_per_second': 19.73, 'eval_steps_per_second': 0.25, 'epoch': 319.44}
-{'loss': 0.0291, 'learning_rate': 0.00029534782331732204, 'epoch': 322.22}
-{'loss': 0.0287, 'learning_rate': 0.00028719157473376303, 'epoch': 325.0}
-{'loss': 0.0279, 'learning_rate': 0.00027918443530500935, 'epoch': 327.78}
-{'loss': 0.0294, 'learning_rate': 0.0002711672294401907, 'epoch': 330.56}
-{'loss': 0.0269, 'learning_rate': 0.00026322376817181157, 'epoch': 333.33}
-{'eval_loss': 0.5972930192947388, 'eval_wer': 0.4232262169901368, 'eval_runtime': 133.0245, 'eval_samples_per_second': 19.613, 'eval_steps_per_second': 0.248, 'epoch': 333.33}
-{'loss': 0.0251, 'learning_rate': 0.0002553566113926006, 'epoch': 336.11}
-{'loss': 0.0261, 'learning_rate': 0.00024756829440508705, 'epoch': 338.89}
-{'loss': 0.025, 'learning_rate': 0.0002398613271045611, 'epoch': 341.67}
-{'loss': 0.0264, 'learning_rate': 0.00023223819317022654, 'epoch': 344.44}
-{'loss': 0.0271, 'learning_rate': 0.00022470134926479935, 'epoch': 347.22}
-{'eval_loss': 0.6094068288803101, 'eval_wer': 0.4428253261215399, 'eval_runtime': 132.9769, 'eval_samples_per_second': 19.62, 'eval_steps_per_second': 0.248, 'epoch': 347.22}
-{'loss': 0.0246, 'learning_rate': 0.00021725322424281286, 'epoch': 350.0}
-{'loss': 0.0245, 'learning_rate': 0.00020989621836788614, 'epoch': 352.78}
-{'loss': 0.0229, 'learning_rate': 0.00020263270253920428, 'epoch': 355.56}
-{'loss': 0.0229, 'learning_rate': 0.00019546501752746288, 'epoch': 358.33}
-{'loss': 0.0236, 'learning_rate': 0.0001883954732205217, 'epoch': 361.11}
-{'eval_loss': 0.611167311668396, 'eval_wer': 0.42373528475978367, 'eval_runtime': 132.3797, 'eval_samples_per_second': 19.708, 'eval_steps_per_second': 0.249, 'epoch': 361.11}
-{'loss': 0.0229, 'learning_rate': 0.00018142634787900996, 'epoch': 363.89}
-{'loss': 0.0221, 'learning_rate': 0.00017455988740212576, 'epoch': 366.67}
-{'loss': 0.0208, 'learning_rate': 0.0001677983046038624, 'epoch': 369.44}
-{'loss': 0.0208, 'learning_rate': 0.00016114377849989813, 'epoch': 372.22}
-{'loss': 0.0202, 'learning_rate': 0.00015459845360537756, 'epoch': 375.0}
-{'eval_loss': 0.605171799659729, 'eval_wer': 0.4233534839325485, 'eval_runtime': 132.1498, 'eval_samples_per_second': 19.743, 'eval_steps_per_second': 0.25, 'epoch': 375.0}
-{'loss': 0.0197, 'learning_rate': 0.0001481644392438113, 'epoch': 377.78}
-{'loss': 0.0195, 'learning_rate': 0.00014184380886731607, 'epoch': 380.56}
-{'loss': 0.0186, 'learning_rate': 0.0001356385993884165, 'epoch': 383.33}
-{'loss': 0.0186, 'learning_rate': 0.00012955081052362072, 'epoch': 386.11}
-{'loss': 0.0175, 'learning_rate': 0.00012358240414898276, 'epoch': 388.89}
-{'eval_loss': 0.631072998046875, 'eval_wer': 0.4188673242125358, 'eval_runtime': 131.5592, 'eval_samples_per_second': 19.831, 'eval_steps_per_second': 0.251, 'epoch': 388.89}
-{'loss': 0.0164, 'learning_rate': 0.00011773530366786184, 'epoch': 391.67}
-{'loss': 0.0166, 'learning_rate': 0.0001120113933910767, 'epoch': 394.44}
-{'loss': 0.0163, 'learning_rate': 0.000106412517929661, 'epoch': 397.22}
-{'loss': 0.0159, 'learning_rate': 0.00010094048160041091, 'epoch': 400.0}
-{'loss': 0.0158, 'learning_rate': 9.559704784441814e-05, 'epoch': 402.78}
-{'eval_loss': 0.618556797504425, 'eval_wer': 0.4137130130448616, 'eval_runtime': 132.4333, 'eval_samples_per_second': 19.7, 'eval_steps_per_second': 0.249, 'epoch': 402.78}
-{'loss': 0.015, 'learning_rate': 9.038393865877726e-05, 'epoch': 405.56}
-{'loss': 0.0156, 'learning_rate': 8.530283404164612e-05, 'epoch': 408.33}
-{'loss': 0.0146, 'learning_rate': 8.03553714508441e-05, 'epoch': 411.11}
-{'loss': 0.0146, 'learning_rate': 7.554314527615763e-05, 'epoch': 413.89}
-{'loss': 0.0141, 'learning_rate': 7.086770632552514e-05, 'epoch': 416.67}
-{'eval_loss': 0.6352781057357788, 'eval_wer': 0.412249443207127, 'eval_runtime': 132.6132, 'eval_samples_per_second': 19.674, 'eval_steps_per_second': 0.249, 'epoch': 416.67}
-{'loss': 0.0138, 'learning_rate': 6.633056132526849e-05, 'epoch': 419.44}
-{'loss': 0.0138, 'learning_rate': 6.193317243452734e-05, 'epoch': 422.22}
-{'loss': 0.0131, 'learning_rate': 5.7676956774059205e-05, 'epoch': 425.0}
-{'loss': 0.0131, 'learning_rate': 5.356328596955179e-05, 'epoch': 427.78}
-{'loss': 0.013, 'learning_rate': 4.963246731369253e-05, 'epoch': 430.56}
-{'eval_loss': 0.6343812942504883, 'eval_wer': 0.40687241489023224, 'eval_runtime': 131.5808, 'eval_samples_per_second': 19.828, 'eval_steps_per_second': 0.251, 'epoch': 430.56}
-{'loss': 0.0127, 'learning_rate': 4.580635924447718e-05, 'epoch': 433.33}
-{'loss': 0.0126, 'learning_rate': 4.212662149914887e-05, 'epoch': 436.11}
-{'loss': 0.0125, 'learning_rate': 3.859443992523443e-05, 'epoch': 438.89}
-{'loss': 0.0127, 'learning_rate': 3.521095281819786e-05, 'epoch': 441.67}
-{'loss': 0.0117, 'learning_rate': 3.1977250554608205e-05, 'epoch': 444.44}
-{'eval_loss': 0.6442536115646362, 'eval_wer': 0.40801781737193765, 'eval_runtime': 132.782, 'eval_samples_per_second': 19.649, 'eval_steps_per_second': 0.249, 'epoch': 444.44}
-{'loss': 0.0122, 'learning_rate': 2.8894375240750613e-05, 'epoch': 447.22}
-{'loss': 0.0127, 'learning_rate': 2.5963320376792666e-05, 'epoch': 450.0}
-{'loss': 0.0125, 'learning_rate': 2.318503053661475e-05, 'epoch': 452.78}
-{'loss': 0.0121, 'learning_rate': 2.056040106340823e-05, 'epoch': 455.56}
-{'loss': 0.0122, 'learning_rate': 1.809027778113803e-05, 'epoch': 458.33}
-{'eval_loss': 0.6512282490730286, 'eval_wer': 0.4069360483614381, 'eval_runtime': 133.1307, 'eval_samples_per_second': 19.597, 'eval_steps_per_second': 0.248, 'epoch': 458.33}
-{'loss': 0.0113, 'learning_rate': 1.5775456721964065e-05, 'epoch': 461.11}
-{'loss': 0.0113, 'learning_rate': 1.3616683869708658e-05, 'epoch': 463.89}
-{'loss': 0.0117, 'learning_rate': 1.1614654919452406e-05, 'epoch': 466.67}
-{'loss': 0.0112, 'learning_rate': 9.770015053337078e-06, 'epoch': 469.44}
-{'loss': 0.0115, 'learning_rate': 8.083358732646206e-06, 'epoch': 472.22}
-{'eval_loss': 0.6556624174118042, 'eval_wer': 0.4069360483614381, 'eval_runtime': 132.4623, 'eval_samples_per_second': 19.696, 'eval_steps_per_second': 0.249, 'epoch': 472.22}
-{'loss': 0.0111, 'learning_rate': 6.555229506231608e-06, 'epoch': 475.0}
-{'loss': 0.0118, 'learning_rate': 5.186119835347169e-06, 'epoch': 477.78}
-{'loss': 0.0112, 'learning_rate': 3.976470934946075e-06, 'epoch': 480.56}
-{'loss': 0.0117, 'learning_rate': 2.92667263149321e-06, 'epoch': 483.33}
-{'loss': 0.0111, 'learning_rate': 2.037063237338044e-06, 'epoch': 486.11}
-{'eval_loss': 0.6513079404830933, 'eval_wer': 0.4059497295577474, 'eval_runtime': 131.4726, 'eval_samples_per_second': 19.844, 'eval_steps_per_second': 0.251, 'epoch': 486.11}
-{'loss': 0.0109, 'learning_rate': 1.3144256109794418e-06, 'epoch': 488.89}
-{'loss': 0.0112, 'learning_rate': 7.44394288673067e-07, 'epoch': 491.67}
-{'loss': 0.0113, 'learning_rate': 3.352551457218578e-07, 'epoch': 494.44}
-{'loss': 0.011, 'learning_rate': 8.714003300058781e-08, 'epoch': 497.22}
-{'loss': 0.0113, 'learning_rate': 1.2890911316176812e-10, 'epoch': 500.0}
-{'eval_loss': 0.6521313190460205, 'eval_wer': 0.40601336302895324, 'eval_runtime': 132.4384, 'eval_samples_per_second': 19.7, 'eval_steps_per_second': 0.249, 'epoch': 500.0}
-{'train_runtime': 176050.2174, 'train_samples_per_second': 16.203, 'train_steps_per_second': 0.102, 'train_loss': 0.11533763631184896, 'epoch': 500.0}
-***** train metrics *****
-  epoch                    =              500.0
-  train_loss               =             0.1153
-  train_runtime            = 2 days, 0:54:10.21
-  train_samples            =               5705
-  train_samples_per_second =             16.203
-  train_steps_per_second   =              0.102
-01/28/2022 11:53:03 - INFO - __main__ - *** Evaluate ***

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a841c1d52b5543205b5280dafe76d3b79f4a8e662faf5145a8f24b4ff311b969
+oid sha256:5f0265c3190d4bad709792f032d753570867b48b4491c9f120d58b7516631525
 size 1262083569

run-300M.sh

@@ -9,7 +9,7 @@ python src/run_speech_recognition_ctc_bnb.py \
        --dataset_config_name="et" \
        --output_dir="./" \
        --overwrite_output_dir \
-       --num_train_epochs=500 \
+       --num_train_epochs=100 \
        --per_device_train_batch_size=80 \
        --per_device_eval_batch_size=80 \
        --gradient_accumulation_steps=2 \

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 500.0,
-    "train_loss": 0.11533763631184896,
-    "train_runtime": 176050.2174,
-    "train_samples": 5705,
-    "train_samples_per_second": 16.203,
-    "train_steps_per_second": 0.102
-}

trainer_state.json

@@ -1,1429 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 500.0,
-  "global_step": 18000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 2.78,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 4.5903,
-      "step": 100
-    },
-    {
-      "epoch": 5.56,
-      "learning_rate": 0.000398,
-      "loss": 2.9083,
-      "step": 200
-    },
-    {
-      "epoch": 8.33,
-      "learning_rate": 0.000598,
-      "loss": 1.2823,
-      "step": 300
-    },
-    {
-      "epoch": 11.11,
-      "learning_rate": 0.0007980000000000001,
-      "loss": 0.3962,
-      "step": 400
-    },
-    {
-      "epoch": 13.89,
-      "learning_rate": 0.000998,
-      "loss": 0.3034,
-      "step": 500
-    },
-    {
-      "epoch": 13.89,
-      "eval_loss": 0.38567885756492615,
-      "eval_runtime": 133.1769,
-      "eval_samples_per_second": 19.59,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.4354438434616608,
-      "step": 500
-    },
-    {
-      "epoch": 16.67,
-      "learning_rate": 0.0009999210371864342,
-      "loss": 0.2639,
-      "step": 600
-    },
-    {
-      "epoch": 19.44,
-      "learning_rate": 0.0009996809758056298,
-      "loss": 0.2354,
-      "step": 700
-    },
-    {
-      "epoch": 22.22,
-      "learning_rate": 0.000999279885163942,
-      "loss": 0.2158,
-      "step": 800
-    },
-    {
-      "epoch": 25.0,
-      "learning_rate": 0.000998717894518502,
-      "loss": 0.2063,
-      "step": 900
-    },
-    {
-      "epoch": 27.78,
-      "learning_rate": 0.000997995184978743,
-      "loss": 0.1926,
-      "step": 1000
-    },
-    {
-      "epoch": 27.78,
-      "eval_loss": 0.4142022132873535,
-      "eval_runtime": 135.7258,
-      "eval_samples_per_second": 19.223,
-      "eval_steps_per_second": 0.243,
-      "eval_wer": 0.4174355711104041,
-      "step": 1000
-    },
-    {
-      "epoch": 30.56,
-      "learning_rate": 0.0009971119894480345,
-      "loss": 0.1771,
-      "step": 1100
-    },
-    {
-      "epoch": 33.33,
-      "learning_rate": 0.0009960685925486266,
-      "loss": 0.1709,
-      "step": 1200
-    },
-    {
-      "epoch": 36.11,
-      "learning_rate": 0.0009948653305299256,
-      "loss": 0.1724,
-      "step": 1300
-    },
-    {
-      "epoch": 38.89,
-      "learning_rate": 0.0009935025911601335,
-      "loss": 0.1632,
-      "step": 1400
-    },
-    {
-      "epoch": 41.67,
-      "learning_rate": 0.0009919808136012837,
-      "loss": 0.1609,
-      "step": 1500
-    },
-    {
-      "epoch": 41.67,
-      "eval_loss": 0.4701250195503235,
-      "eval_runtime": 133.1213,
-      "eval_samples_per_second": 19.599,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.42958956411072224,
-      "step": 1500
-    },
-    {
-      "epoch": 44.44,
-      "learning_rate": 0.0009903004882677155,
-      "loss": 0.1521,
-      "step": 1600
-    },
-    {
-      "epoch": 47.22,
-      "learning_rate": 0.0009884621566680308,
-      "loss": 0.1531,
-      "step": 1700
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 0.0009864664112305846,
-      "loss": 0.1514,
-      "step": 1800
-    },
-    {
-      "epoch": 52.78,
-      "learning_rate": 0.0009843138951125682,
-      "loss": 0.1468,
-      "step": 1900
-    },
-    {
-      "epoch": 55.56,
-      "learning_rate": 0.000982005301992741,
-      "loss": 0.1501,
-      "step": 2000
-    },
-    {
-      "epoch": 55.56,
-      "eval_loss": 0.45478546619415283,
-      "eval_runtime": 133.376,
-      "eval_samples_per_second": 19.561,
-      "eval_steps_per_second": 0.247,
-      "eval_wer": 0.43805281578110083,
-      "step": 2000
-    },
-    {
-      "epoch": 58.33,
-      "learning_rate": 0.0009795413758478834,
-      "loss": 0.1427,
-      "step": 2100
-    },
-    {
-      "epoch": 61.11,
-      "learning_rate": 0.0009769229107130409,
-      "loss": 0.1441,
-      "step": 2200
-    },
-    {
-      "epoch": 63.89,
-      "learning_rate": 0.0009741507504256327,
-      "loss": 0.1399,
-      "step": 2300
-    },
-    {
-      "epoch": 66.67,
-      "learning_rate": 0.0009712257883535152,
-      "loss": 0.1379,
-      "step": 2400
-    },
-    {
-      "epoch": 69.44,
-      "learning_rate": 0.0009681489671070803,
-      "loss": 0.1382,
-      "step": 2500
-    },
-    {
-      "epoch": 69.44,
-      "eval_loss": 0.523300290107727,
-      "eval_runtime": 131.9566,
-      "eval_samples_per_second": 19.772,
-      "eval_steps_per_second": 0.25,
-      "eval_wer": 0.4544066178810054,
-      "step": 2500
-    },
-    {
-      "epoch": 72.22,
-      "learning_rate": 0.0009649212782354872,
-      "loss": 0.1372,
-      "step": 2600
-    },
-    {
-      "epoch": 75.0,
-      "learning_rate": 0.0009615437619071199,
-      "loss": 0.1345,
-      "step": 2700
-    },
-    {
-      "epoch": 77.78,
-      "learning_rate": 0.0009580175065743799,
-      "loss": 0.1346,
-      "step": 2800
-    },
-    {
-      "epoch": 80.56,
-      "learning_rate": 0.0009543436486229162,
-      "loss": 0.1367,
-      "step": 2900
-    },
-    {
-      "epoch": 83.33,
-      "learning_rate": 0.0009505233720054086,
-      "loss": 0.1287,
-      "step": 3000
-    },
-    {
-      "epoch": 83.33,
-      "eval_loss": 0.48360341787338257,
-      "eval_runtime": 132.2498,
-      "eval_samples_per_second": 19.728,
-      "eval_steps_per_second": 0.25,
-      "eval_wer": 0.43658924594336623,
-      "step": 3000
-    },
-    {
-      "epoch": 86.11,
-      "learning_rate": 0.0009465579078600233,
-      "loss": 0.1226,
-      "step": 3100
-    },
-    {
-      "epoch": 88.89,
-      "learning_rate": 0.0009424485341136599,
-      "loss": 0.1258,
-      "step": 3200
-    },
-    {
-      "epoch": 91.67,
-      "learning_rate": 0.0009381965750701229,
-      "loss": 0.1222,
-      "step": 3300
-    },
-    {
-      "epoch": 94.44,
-      "learning_rate": 0.0009338034009833446,
-      "loss": 0.1182,
-      "step": 3400
-    },
-    {
-      "epoch": 97.22,
-      "learning_rate": 0.0009292704276158022,
-      "loss": 0.1164,
-      "step": 3500
-    },
-    {
-      "epoch": 97.22,
-      "eval_loss": 0.5202445983886719,
-      "eval_runtime": 132.7793,
-      "eval_samples_per_second": 19.649,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.43948456888323256,
-      "step": 3500
-    },
-    {
-      "epoch": 100.0,
-      "learning_rate": 0.0009245991157822682,
-      "loss": 0.1212,
-      "step": 3600
-    },
-    {
-      "epoch": 102.78,
-      "learning_rate": 0.000919790970879042,
-      "loss": 0.1139,
-      "step": 3700
-    },
-    {
-      "epoch": 105.56,
-      "learning_rate": 0.000914847542398815,
-      "loss": 0.115,
-      "step": 3800
-    },
-    {
-      "epoch": 108.33,
-      "learning_rate": 0.0009097704234313245,
-      "loss": 0.1123,
-      "step": 3900
-    },
-    {
-      "epoch": 111.11,
-      "learning_rate": 0.0009045612501499573,
-      "loss": 0.1101,
-      "step": 4000
-    },
-    {
-      "epoch": 111.11,
-      "eval_loss": 0.5120447874069214,
-      "eval_runtime": 131.3001,
-      "eval_samples_per_second": 19.871,
-      "eval_steps_per_second": 0.251,
-      "eval_wer": 0.43827553293032134,
-      "step": 4000
-    },
-    {
-      "epoch": 113.89,
-      "learning_rate": 0.0008992217012844713,
-      "loss": 0.1092,
-      "step": 4100
-    },
-    {
-      "epoch": 116.67,
-      "learning_rate": 0.0008937534975799996,
-      "loss": 0.1104,
-      "step": 4200
-    },
-    {
-      "epoch": 119.44,
-      "learning_rate": 0.0008881584012425165,
-      "loss": 0.1021,
-      "step": 4300
-    },
-    {
-      "epoch": 122.22,
-      "learning_rate": 0.0008824382153709421,
-      "loss": 0.1063,
-      "step": 4400
-    },
-    {
-      "epoch": 125.0,
-      "learning_rate": 0.0008765947833760678,
-      "loss": 0.1107,
-      "step": 4500
-    },
-    {
-      "epoch": 125.0,
-      "eval_loss": 0.5130612850189209,
-      "eval_runtime": 133.0961,
-      "eval_samples_per_second": 19.602,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.4446706967865097,
-      "step": 4500
-    },
-    {
-      "epoch": 127.78,
-      "learning_rate": 0.000870629988386491,
-      "loss": 0.1054,
-      "step": 4600
-    },
-    {
-      "epoch": 130.56,
-      "learning_rate": 0.0008645457526417502,
-      "loss": 0.1037,
-      "step": 4700
-    },
-    {
-      "epoch": 133.33,
-      "learning_rate": 0.0008583440368728572,
-      "loss": 0.1,
-      "step": 4800
-    },
-    {
-      "epoch": 136.11,
-      "learning_rate": 0.0008520268396704223,
-      "loss": 0.0967,
-      "step": 4900
-    },
-    {
-      "epoch": 138.89,
-      "learning_rate": 0.0008455961968405809,
-      "loss": 0.0942,
-      "step": 5000
-    },
-    {
-      "epoch": 138.89,
-      "eval_loss": 0.5256752967834473,
-      "eval_runtime": 133.1352,
-      "eval_samples_per_second": 19.597,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.43748011454024816,
-      "step": 5000
-    },
-    {
-      "epoch": 141.67,
-      "learning_rate": 0.0008390541807489265,
-      "loss": 0.0987,
-      "step": 5100
-    },
-    {
-      "epoch": 144.44,
-      "learning_rate": 0.0008324028996526611,
-      "loss": 0.094,
-      "step": 5200
-    },
-    {
-      "epoch": 147.22,
-      "learning_rate": 0.0008256444970211793,
-      "loss": 0.0935,
-      "step": 5300
-    },
-    {
-      "epoch": 150.0,
-      "learning_rate": 0.000818781150845306,
-      "loss": 0.0906,
-      "step": 5400
-    },
-    {
-      "epoch": 152.78,
-      "learning_rate": 0.0008118150729354068,
-      "loss": 0.0909,
-      "step": 5500
-    },
-    {
-      "epoch": 152.78,
-      "eval_loss": 0.5312919020652771,
-      "eval_runtime": 133.5185,
-      "eval_samples_per_second": 19.54,
-      "eval_steps_per_second": 0.247,
-      "eval_wer": 0.47133312122176263,
-      "step": 5500
-    },
-    {
-      "epoch": 155.56,
-      "learning_rate": 0.0008047485082086017,
-      "loss": 0.0881,
-      "step": 5600
-    },
-    {
-      "epoch": 158.33,
-      "learning_rate": 0.0007975837339653084,
-      "loss": 0.0921,
-      "step": 5700
-    },
-    {
-      "epoch": 161.11,
-      "learning_rate": 0.0007903230591553503,
-      "loss": 0.0838,
-      "step": 5800
-    },
-    {
-      "epoch": 163.89,
-      "learning_rate": 0.0007829688236338643,
-      "loss": 0.0775,
-      "step": 5900
-    },
-    {
-      "epoch": 166.67,
-      "learning_rate": 0.0007755233974072504,
-      "loss": 0.0807,
-      "step": 6000
-    },
-    {
-      "epoch": 166.67,
-      "eval_loss": 0.5847254991531372,
-      "eval_runtime": 133.1812,
-      "eval_samples_per_second": 19.59,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.44708876869233216,
-      "step": 6000
-    },
-    {
-      "epoch": 169.44,
-      "learning_rate": 0.0007679891798694021,
-      "loss": 0.0801,
-      "step": 6100
-    },
-    {
-      "epoch": 172.22,
-      "learning_rate": 0.000760368599028469,
-      "loss": 0.0952,
-      "step": 6200
-    },
-    {
-      "epoch": 175.0,
-      "learning_rate": 0.0007526641107243966,
-      "loss": 0.0813,
-      "step": 6300
-    },
-    {
-      "epoch": 177.78,
-      "learning_rate": 0.0007448781978374969,
-      "loss": 0.0795,
-      "step": 6400
-    },
-    {
-      "epoch": 180.56,
-      "learning_rate": 0.0007370133694883051,
-      "loss": 0.0767,
-      "step": 6500
-    },
-    {
-      "epoch": 180.56,
-      "eval_loss": 0.5318175554275513,
-      "eval_runtime": 135.804,
-      "eval_samples_per_second": 19.212,
-      "eval_steps_per_second": 0.243,
-      "eval_wer": 0.4534521158129176,
-      "step": 6500
-    },
-    {
-      "epoch": 183.33,
-      "learning_rate": 0.0007290721602289801,
-      "loss": 0.0762,
-      "step": 6600
-    },
-    {
-      "epoch": 186.11,
-      "learning_rate": 0.0007210571292265096,
-      "loss": 0.0729,
-      "step": 6700
-    },
-    {
-      "epoch": 188.89,
-      "learning_rate": 0.0007129708594379816,
-      "loss": 0.0751,
-      "step": 6800
-    },
-    {
-      "epoch": 191.67,
-      "learning_rate": 0.0007048159567781905,
-      "loss": 0.0743,
-      "step": 6900
-    },
-    {
-      "epoch": 194.44,
-      "learning_rate": 0.0006965950492798443,
-      "loss": 0.0729,
-      "step": 7000
-    },
-    {
-      "epoch": 194.44,
-      "eval_loss": 0.5796982645988464,
-      "eval_runtime": 132.2018,
-      "eval_samples_per_second": 19.735,
-      "eval_steps_per_second": 0.25,
-      "eval_wer": 0.4584155265669742,
-      "step": 7000
-    },
-    {
-      "epoch": 197.22,
-      "learning_rate": 0.0006883107862466433,
-      "loss": 0.0791,
-      "step": 7100
-    },
-    {
-      "epoch": 200.0,
-      "learning_rate": 0.0006799658373995054,
-      "loss": 0.0737,
-      "step": 7200
-    },
-    {
-      "epoch": 202.78,
-      "learning_rate": 0.0006715628920162093,
-      "loss": 0.0694,
-      "step": 7300
-    },
-    {
-      "epoch": 205.56,
-      "learning_rate": 0.0006631046580647384,
-      "loss": 0.0687,
-      "step": 7400
-    },
-    {
-      "epoch": 208.33,
-      "learning_rate": 0.0006545938613305993,
-      "loss": 0.072,
-      "step": 7500
-    },
-    {
-      "epoch": 208.33,
-      "eval_loss": 0.5266388654708862,
-      "eval_runtime": 130.3709,
-      "eval_samples_per_second": 20.012,
-      "eval_steps_per_second": 0.253,
-      "eval_wer": 0.44339802736239264,
-      "step": 7500
-    },
-    {
-      "epoch": 211.11,
-      "learning_rate": 0.000646033244538398,
-      "loss": 0.0647,
-      "step": 7600
-    },
-    {
-      "epoch": 213.89,
-      "learning_rate": 0.000637425566467959,
-      "loss": 0.0631,
-      "step": 7700
-    },
-    {
-      "epoch": 216.67,
-      "learning_rate": 0.0006287736010652693,
-      "loss": 0.0606,
-      "step": 7800
-    },
-    {
-      "epoch": 219.44,
-      "learning_rate": 0.000620080136548535,
-      "loss": 0.0645,
-      "step": 7900
-    },
-    {
-      "epoch": 222.22,
-      "learning_rate": 0.0006113479745096386,
-      "loss": 0.0593,
-      "step": 8000
-    },
-    {
-      "epoch": 222.22,
-      "eval_loss": 0.579177737236023,
-      "eval_runtime": 133.0716,
-      "eval_samples_per_second": 19.606,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.43888005090677695,
-      "step": 8000
-    },
-    {
-      "epoch": 225.0,
-      "learning_rate": 0.0006025799290112865,
-      "loss": 0.0596,
-      "step": 8100
-    },
-    {
-      "epoch": 227.78,
-      "learning_rate": 0.0005937788256801371,
-      "loss": 0.0606,
-      "step": 8200
-    },
-    {
-      "epoch": 230.56,
-      "learning_rate": 0.0005849475007962031,
-      "loss": 0.0591,
-      "step": 8300
-    },
-    {
-      "epoch": 233.33,
-      "learning_rate": 0.0005760888003788196,
-      "loss": 0.0544,
-      "step": 8400
-    },
-    {
-      "epoch": 236.11,
-      "learning_rate": 0.0005672055792694753,
-      "loss": 0.0524,
-      "step": 8500
-    },
-    {
-      "epoch": 236.11,
-      "eval_loss": 0.5740395784378052,
-      "eval_runtime": 132.5642,
-      "eval_samples_per_second": 19.681,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.43732103086223356,
-      "step": 8500
-    },
-    {
-      "epoch": 238.89,
-      "learning_rate": 0.0005583007002117978,
-      "loss": 0.0504,
-      "step": 8600
-    },
-    {
-      "epoch": 241.67,
-      "learning_rate": 0.0005493770329289953,
-      "loss": 0.0494,
-      "step": 8700
-    },
-    {
-      "epoch": 244.44,
-      "learning_rate": 0.0005404374531990474,
-      "loss": 0.0484,
-      "step": 8800
-    },
-    {
-      "epoch": 247.22,
-      "learning_rate": 0.0005314848419279442,
-      "loss": 0.0489,
-      "step": 8900
-    },
-    {
-      "epoch": 250.0,
-      "learning_rate": 0.0005225220842212748,
-      "loss": 0.0494,
-      "step": 9000
-    },
-    {
-      "epoch": 250.0,
-      "eval_loss": 0.5520852208137512,
-      "eval_runtime": 133.6258,
-      "eval_samples_per_second": 19.525,
-      "eval_steps_per_second": 0.247,
-      "eval_wer": 0.44358892777601017,
-      "step": 9000
-    },
-    {
-      "epoch": 252.78,
-      "learning_rate": 0.0005135520684544602,
-      "loss": 0.0499,
-      "step": 9100
-    },
-    {
-      "epoch": 255.56,
-      "learning_rate": 0.0005045776853419344,
-      "loss": 0.0487,
-      "step": 9200
-    },
-    {
-      "epoch": 258.33,
-      "learning_rate": 0.0004956018270055703,
-      "loss": 0.0523,
-      "step": 9300
-    },
-    {
-      "epoch": 261.11,
-      "learning_rate": 0.00048662738604265206,
-      "loss": 0.0479,
-      "step": 9400
-    },
-    {
-      "epoch": 263.89,
-      "learning_rate": 0.0004776572545936954,
-      "loss": 0.0469,
-      "step": 9500
-    },
-    {
-      "epoch": 263.89,
-      "eval_loss": 0.5630596876144409,
-      "eval_runtime": 130.7272,
-      "eval_samples_per_second": 19.958,
-      "eval_steps_per_second": 0.252,
-      "eval_wer": 0.4345847916003818,
-      "step": 9500
-    },
-    {
-      "epoch": 266.67,
-      "learning_rate": 0.0004686943234104146,
-      "loss": 0.0467,
-      "step": 9600
-    },
-    {
-      "epoch": 269.44,
-      "learning_rate": 0.00045974148092413597,
-      "loss": 0.0438,
-      "step": 9700
-    },
-    {
-      "epoch": 272.22,
-      "learning_rate": 0.00045080161231496064,
-      "loss": 0.0422,
-      "step": 9800
-    },
-    {
-      "epoch": 275.0,
-      "learning_rate": 0.00044187759858197486,
-      "loss": 0.042,
-      "step": 9900
-    },
-    {
-      "epoch": 277.78,
-      "learning_rate": 0.0004329723156148063,
-      "loss": 0.0417,
-      "step": 10000
-    },
-    {
-      "epoch": 277.78,
-      "eval_loss": 0.5777372121810913,
-      "eval_runtime": 130.7332,
-      "eval_samples_per_second": 19.957,
-      "eval_steps_per_second": 0.252,
-      "eval_wer": 0.43057588291441296,
-      "step": 10000
-    },
-    {
-      "epoch": 280.56,
-      "learning_rate": 0.0004240886332668285,
-      "loss": 0.0406,
-      "step": 10100
-    },
-    {
-      "epoch": 283.33,
-      "learning_rate": 0.00041522941443031025,
-      "loss": 0.0385,
-      "step": 10200
-    },
-    {
-      "epoch": 286.11,
-      "learning_rate": 0.0004063975141138074,
-      "loss": 0.0384,
-      "step": 10300
-    },
-    {
-      "epoch": 288.89,
-      "learning_rate": 0.00039759577852209704,
-      "loss": 0.0369,
-      "step": 10400
-    },
-    {
-      "epoch": 291.67,
-      "learning_rate": 0.0003888270441389465,
-      "loss": 0.0379,
-      "step": 10500
-    },
-    {
-      "epoch": 291.67,
-      "eval_loss": 0.5934527516365051,
-      "eval_runtime": 131.6738,
-      "eval_samples_per_second": 19.814,
-      "eval_steps_per_second": 0.251,
-      "eval_wer": 0.42828507795100224,
-      "step": 10500
-    },
-    {
-      "epoch": 294.44,
-      "learning_rate": 0.0003800941368130171,
-      "loss": 0.0399,
-      "step": 10600
-    },
-    {
-      "epoch": 297.22,
-      "learning_rate": 0.0003713998708471946,
-      "loss": 0.0359,
-      "step": 10700
-    },
-    {
-      "epoch": 300.0,
-      "learning_rate": 0.0003627470480916394,
-      "loss": 0.0345,
-      "step": 10800
-    },
-    {
-      "epoch": 302.78,
-      "learning_rate": 0.00035413845704085215,
-      "loss": 0.0346,
-      "step": 10900
-    },
-    {
-      "epoch": 305.56,
-      "learning_rate": 0.00034557687193504045,
-      "loss": 0.0319,
-      "step": 11000
-    },
-    {
-      "epoch": 305.56,
-      "eval_loss": 0.5892442464828491,
-      "eval_runtime": 130.692,
-      "eval_samples_per_second": 19.963,
-      "eval_steps_per_second": 0.253,
-      "eval_wer": 0.41880369074132995,
-      "step": 11000
-    },
-    {
-      "epoch": 308.33,
-      "learning_rate": 0.00033706505186608136,
-      "loss": 0.0318,
-      "step": 11100
-    },
-    {
-      "epoch": 311.11,
-      "learning_rate": 0.00032860573988836573,
-      "loss": 0.0301,
-      "step": 11200
-    },
-    {
-      "epoch": 313.89,
-      "learning_rate": 0.0003202016621348088,
-      "loss": 0.0322,
-      "step": 11300
-    },
-    {
-      "epoch": 316.67,
-      "learning_rate": 0.00031185552693831594,
-      "loss": 0.0331,
-      "step": 11400
-    },
-    {
-      "epoch": 319.44,
-      "learning_rate": 0.0003035700239589846,
-      "loss": 0.0311,
-      "step": 11500
-    },
-    {
-      "epoch": 319.44,
-      "eval_loss": 0.6010639071464539,
-      "eval_runtime": 132.2371,
-      "eval_samples_per_second": 19.73,
-      "eval_steps_per_second": 0.25,
-      "eval_wer": 0.4210626789691378,
-      "step": 11500
-    },
-    {
-      "epoch": 322.22,
-      "learning_rate": 0.00029534782331732204,
-      "loss": 0.0291,
-      "step": 11600
-    },
-    {
-      "epoch": 325.0,
-      "learning_rate": 0.00028719157473376303,
-      "loss": 0.0287,
-      "step": 11700
-    },
-    {
-      "epoch": 327.78,
-      "learning_rate": 0.00027918443530500935,
-      "loss": 0.0279,
-      "step": 11800
-    },
-    {
-      "epoch": 330.56,
-      "learning_rate": 0.0002711672294401907,
-      "loss": 0.0294,
-      "step": 11900
-    },
-    {
-      "epoch": 333.33,
-      "learning_rate": 0.00026322376817181157,
-      "loss": 0.0269,
-      "step": 12000
-    },
-    {
-      "epoch": 333.33,
-      "eval_loss": 0.5972930192947388,
-      "eval_runtime": 133.0245,
-      "eval_samples_per_second": 19.613,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.4232262169901368,
-      "step": 12000
-    },
-    {
-      "epoch": 336.11,
-      "learning_rate": 0.0002553566113926006,
-      "loss": 0.0251,
-      "step": 12100
-    },
-    {
-      "epoch": 338.89,
-      "learning_rate": 0.00024756829440508705,
-      "loss": 0.0261,
-      "step": 12200
-    },
-    {
-      "epoch": 341.67,
-      "learning_rate": 0.0002398613271045611,
-      "loss": 0.025,
-      "step": 12300
-    },
-    {
-      "epoch": 344.44,
-      "learning_rate": 0.00023223819317022654,
-      "loss": 0.0264,
-      "step": 12400
-    },
-    {
-      "epoch": 347.22,
-      "learning_rate": 0.00022470134926479935,
-      "loss": 0.0271,
-      "step": 12500
-    },
-    {
-      "epoch": 347.22,
-      "eval_loss": 0.6094068288803101,
-      "eval_runtime": 132.9769,
-      "eval_samples_per_second": 19.62,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.4428253261215399,
-      "step": 12500
-    },
-    {
-      "epoch": 350.0,
-      "learning_rate": 0.00021725322424281286,
-      "loss": 0.0246,
-      "step": 12600
-    },
-    {
-      "epoch": 352.78,
-      "learning_rate": 0.00020989621836788614,
-      "loss": 0.0245,
-      "step": 12700
-    },
-    {
-      "epoch": 355.56,
-      "learning_rate": 0.00020263270253920428,
-      "loss": 0.0229,
-      "step": 12800
-    },
-    {
-      "epoch": 358.33,
-      "learning_rate": 0.00019546501752746288,
-      "loss": 0.0229,
-      "step": 12900
-    },
-    {
-      "epoch": 361.11,
-      "learning_rate": 0.0001883954732205217,
-      "loss": 0.0236,
-      "step": 13000
-    },
-    {
-      "epoch": 361.11,
-      "eval_loss": 0.611167311668396,
-      "eval_runtime": 132.3797,
-      "eval_samples_per_second": 19.708,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.42373528475978367,
-      "step": 13000
-    },
-    {
-      "epoch": 363.89,
-      "learning_rate": 0.00018142634787900996,
-      "loss": 0.0229,
-      "step": 13100
-    },
-    {
-      "epoch": 366.67,
-      "learning_rate": 0.00017455988740212576,
-      "loss": 0.0221,
-      "step": 13200
-    },
-    {
-      "epoch": 369.44,
-      "learning_rate": 0.0001677983046038624,
-      "loss": 0.0208,
-      "step": 13300
-    },
-    {
-      "epoch": 372.22,
-      "learning_rate": 0.00016114377849989813,
-      "loss": 0.0208,
-      "step": 13400
-    },
-    {
-      "epoch": 375.0,
-      "learning_rate": 0.00015459845360537756,
-      "loss": 0.0202,
-      "step": 13500
-    },
-    {
-      "epoch": 375.0,
-      "eval_loss": 0.605171799659729,
-      "eval_runtime": 132.1498,
-      "eval_samples_per_second": 19.743,
-      "eval_steps_per_second": 0.25,
-      "eval_wer": 0.4233534839325485,
-      "step": 13500
-    },
-    {
-      "epoch": 377.78,
-      "learning_rate": 0.0001481644392438113,
-      "loss": 0.0197,
-      "step": 13600
-    },
-    {
-      "epoch": 380.56,
-      "learning_rate": 0.00014184380886731607,
-      "loss": 0.0195,
-      "step": 13700
-    },
-    {
-      "epoch": 383.33,
-      "learning_rate": 0.0001356385993884165,
-      "loss": 0.0186,
-      "step": 13800
-    },
-    {
-      "epoch": 386.11,
-      "learning_rate": 0.00012955081052362072,
-      "loss": 0.0186,
-      "step": 13900
-    },
-    {
-      "epoch": 388.89,
-      "learning_rate": 0.00012358240414898276,
-      "loss": 0.0175,
-      "step": 14000
-    },
-    {
-      "epoch": 388.89,
-      "eval_loss": 0.631072998046875,
-      "eval_runtime": 131.5592,
-      "eval_samples_per_second": 19.831,
-      "eval_steps_per_second": 0.251,
-      "eval_wer": 0.4188673242125358,
-      "step": 14000
-    },
-    {
-      "epoch": 391.67,
-      "learning_rate": 0.00011773530366786184,
-      "loss": 0.0164,
-      "step": 14100
-    },
-    {
-      "epoch": 394.44,
-      "learning_rate": 0.0001120113933910767,
-      "loss": 0.0166,
-      "step": 14200
-    },
-    {
-      "epoch": 397.22,
-      "learning_rate": 0.000106412517929661,
-      "loss": 0.0163,
-      "step": 14300
-    },
-    {
-      "epoch": 400.0,
-      "learning_rate": 0.00010094048160041091,
-      "loss": 0.0159,
-      "step": 14400
-    },
-    {
-      "epoch": 402.78,
-      "learning_rate": 9.559704784441814e-05,
-      "loss": 0.0158,
-      "step": 14500
-    },
-    {
-      "epoch": 402.78,
-      "eval_loss": 0.618556797504425,
-      "eval_runtime": 132.4333,
-      "eval_samples_per_second": 19.7,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.4137130130448616,
-      "step": 14500
-    },
-    {
-      "epoch": 405.56,
-      "learning_rate": 9.038393865877726e-05,
-      "loss": 0.015,
-      "step": 14600
-    },
-    {
-      "epoch": 408.33,
-      "learning_rate": 8.530283404164612e-05,
-      "loss": 0.0156,
-      "step": 14700
-    },
-    {
-      "epoch": 411.11,
-      "learning_rate": 8.03553714508441e-05,
-      "loss": 0.0146,
-      "step": 14800
-    },
-    {
-      "epoch": 413.89,
-      "learning_rate": 7.554314527615763e-05,
-      "loss": 0.0146,
-      "step": 14900
-    },
-    {
-      "epoch": 416.67,
-      "learning_rate": 7.086770632552514e-05,
-      "loss": 0.0141,
-      "step": 15000
-    },
-    {
-      "epoch": 416.67,
-      "eval_loss": 0.6352781057357788,
-      "eval_runtime": 132.6132,
-      "eval_samples_per_second": 19.674,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.412249443207127,
-      "step": 15000
-    },
-    {
-      "epoch": 419.44,
-      "learning_rate": 6.633056132526849e-05,
-      "loss": 0.0138,
-      "step": 15100
-    },
-    {
-      "epoch": 422.22,
-      "learning_rate": 6.193317243452734e-05,
-      "loss": 0.0138,
-      "step": 15200
-    },
-    {
-      "epoch": 425.0,
-      "learning_rate": 5.7676956774059205e-05,
-      "loss": 0.0131,
-      "step": 15300
-    },
-    {
-      "epoch": 427.78,
-      "learning_rate": 5.356328596955179e-05,
-      "loss": 0.0131,
-      "step": 15400
-    },
-    {
-      "epoch": 430.56,
-      "learning_rate": 4.963246731369253e-05,
-      "loss": 0.013,
-      "step": 15500
-    },
-    {
-      "epoch": 430.56,
-      "eval_loss": 0.6343812942504883,
-      "eval_runtime": 131.5808,
-      "eval_samples_per_second": 19.828,
-      "eval_steps_per_second": 0.251,
-      "eval_wer": 0.40687241489023224,
-      "step": 15500
-    },
-    {
-      "epoch": 433.33,
-      "learning_rate": 4.580635924447718e-05,
-      "loss": 0.0127,
-      "step": 15600
-    },
-    {
-      "epoch": 436.11,
-      "learning_rate": 4.212662149914887e-05,
-      "loss": 0.0126,
-      "step": 15700
-    },
-    {
-      "epoch": 438.89,
-      "learning_rate": 3.859443992523443e-05,
-      "loss": 0.0125,
-      "step": 15800
-    },
-    {
-      "epoch": 441.67,
-      "learning_rate": 3.521095281819786e-05,
-      "loss": 0.0127,
-      "step": 15900
-    },
-    {
-      "epoch": 444.44,
-      "learning_rate": 3.1977250554608205e-05,
-      "loss": 0.0117,
-      "step": 16000
-    },
-    {
-      "epoch": 444.44,
-      "eval_loss": 0.6442536115646362,
-      "eval_runtime": 132.782,
-      "eval_samples_per_second": 19.649,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.40801781737193765,
-      "step": 16000
-    },
-    {
-      "epoch": 447.22,
-      "learning_rate": 2.8894375240750613e-05,
-      "loss": 0.0122,
-      "step": 16100
-    },
-    {
-      "epoch": 450.0,
-      "learning_rate": 2.5963320376792666e-05,
-      "loss": 0.0127,
-      "step": 16200
-    },
-    {
-      "epoch": 452.78,
-      "learning_rate": 2.318503053661475e-05,
-      "loss": 0.0125,
-      "step": 16300
-    },
-    {
-      "epoch": 455.56,
-      "learning_rate": 2.056040106340823e-05,
-      "loss": 0.0121,
-      "step": 16400
-    },
-    {
-      "epoch": 458.33,
-      "learning_rate": 1.809027778113803e-05,
-      "loss": 0.0122,
-      "step": 16500
-    },
-    {
-      "epoch": 458.33,
-      "eval_loss": 0.6512282490730286,
-      "eval_runtime": 133.1307,
-      "eval_samples_per_second": 19.597,
-      "eval_steps_per_second": 0.248,
-      "eval_wer": 0.4069360483614381,
-      "step": 16500
-    },
-    {
-      "epoch": 461.11,
-      "learning_rate": 1.5775456721964065e-05,
-      "loss": 0.0113,
-      "step": 16600
-    },
-    {
-      "epoch": 463.89,
-      "learning_rate": 1.3616683869708658e-05,
-      "loss": 0.0113,
-      "step": 16700
-    },
-    {
-      "epoch": 466.67,
-      "learning_rate": 1.1614654919452406e-05,
-      "loss": 0.0117,
-      "step": 16800
-    },
-    {
-      "epoch": 469.44,
-      "learning_rate": 9.770015053337078e-06,
-      "loss": 0.0112,
-      "step": 16900
-    },
-    {
-      "epoch": 472.22,
-      "learning_rate": 8.083358732646206e-06,
-      "loss": 0.0115,
-      "step": 17000
-    },
-    {
-      "epoch": 472.22,
-      "eval_loss": 0.6556624174118042,
-      "eval_runtime": 132.4623,
-      "eval_samples_per_second": 19.696,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.4069360483614381,
-      "step": 17000
-    },
-    {
-      "epoch": 475.0,
-      "learning_rate": 6.555229506231608e-06,
-      "loss": 0.0111,
-      "step": 17100
-    },
-    {
-      "epoch": 477.78,
-      "learning_rate": 5.186119835347169e-06,
-      "loss": 0.0118,
-      "step": 17200
-    },
-    {
-      "epoch": 480.56,
-      "learning_rate": 3.976470934946075e-06,
-      "loss": 0.0112,
-      "step": 17300
-    },
-    {
-      "epoch": 483.33,
-      "learning_rate": 2.92667263149321e-06,
-      "loss": 0.0117,
-      "step": 17400
-    },
-    {
-      "epoch": 486.11,
-      "learning_rate": 2.037063237338044e-06,
-      "loss": 0.0111,
-      "step": 17500
-    },
-    {
-      "epoch": 486.11,
-      "eval_loss": 0.6513079404830933,
-      "eval_runtime": 131.4726,
-      "eval_samples_per_second": 19.844,
-      "eval_steps_per_second": 0.251,
-      "eval_wer": 0.4059497295577474,
-      "step": 17500
-    },
-    {
-      "epoch": 488.89,
-      "learning_rate": 1.3144256109794418e-06,
-      "loss": 0.0109,
-      "step": 17600
-    },
-    {
-      "epoch": 491.67,
-      "learning_rate": 7.44394288673067e-07,
-      "loss": 0.0112,
-      "step": 17700
-    },
-    {
-      "epoch": 494.44,
-      "learning_rate": 3.352551457218578e-07,
-      "loss": 0.0113,
-      "step": 17800
-    },
-    {
-      "epoch": 497.22,
-      "learning_rate": 8.714003300058781e-08,
-      "loss": 0.011,
-      "step": 17900
-    },
-    {
-      "epoch": 500.0,
-      "learning_rate": 1.2890911316176812e-10,
-      "loss": 0.0113,
-      "step": 18000
-    },
-    {
-      "epoch": 500.0,
-      "eval_loss": 0.6521313190460205,
-      "eval_runtime": 132.4384,
-      "eval_samples_per_second": 19.7,
-      "eval_steps_per_second": 0.249,
-      "eval_wer": 0.40601336302895324,
-      "step": 18000
-    },
-    {
-      "epoch": 500.0,
-      "step": 18000,
-      "total_flos": 5.3110650126518e+20,
-      "train_loss": 0.11533763631184896,
-      "train_runtime": 176050.2174,
-      "train_samples_per_second": 16.203,
-      "train_steps_per_second": 0.102
-    }
-  ],
-  "max_steps": 18000,
-  "num_train_epochs": 500,
-  "total_flos": 5.3110650126518e+20,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be3a7c88f8500cf6b3a8b0b089125768d465147886310e4abb4ddc8cf154dd1
+oid sha256:020e62b69669cb5205d10821c92f57fc9ddfd0706b2f7dd41539b83bb4d40ffb
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220126_121554-295enqix/logs/debug-internal.log
+run-20220129_111936-33z1cg4n/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220126_121554-295enqix/logs/debug.log
+run-20220129_111936-33z1cg4n/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220126_121554-295enqix
+run-20220129_111936-33z1cg4n

wandb/run-20220126_105847-1xdiy2kf/files/config.yaml

@@ -4829,7 +4829,13 @@ _wandb:
       - 1
       - 5
       - 11
+      2:
+      - 1
+      - 5
+      - 11
       3:
+      - 1
+      - 7
       - 13
       4: 3.9.6
       5: 0.12.9

wandb/run-20220126_105847-1xdiy2kf/files/output.log

@@ -19602,3 +19602,87 @@ Configuration saved in ./config.json.78s/it]our model on huggingface.co/models =
  97% 32/33 [02:06<00:03,  3.19s/it]tion set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
 Configuration saved in ./config.jsonion set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
 Configuration saved in ./preprocessor_config.jsont have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Configuration saved in ./preprocessor_config.jsont have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+***** eval metrics *****
+  epoch                   =      500.0
+  eval_loss               =     0.6521
+  eval_runtime            = 0:02:14.01
+  eval_samples            =       2609
+  eval_samples_per_second =     19.468
+  eval_steps_per_second   =      0.246
+  eval_wer                =      0.406
+01/28/2022 11:55:40 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+The progress bars may be unreliable.pstream..jsont have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb:   0% 32.0k/119M [00:00<?, ?B/s]C.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:   2% 28.1M/1.18G [00:02<01:18, 15.6MB/s] 8.50M/119M [00:02<00:24, 4.82MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:   5% 57.1M/1.18G [00:04<01:20, 15.0MB/s] 24.0M/119M [00:04<00:14, 6.99MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb:  32% 38.4M/119M [00:06<00:11, 7.24MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:   8% 93.5M/1.18G [00:08<01:51, 10.4MB/s] 51.2M/119M [00:08<00:10, 6.92MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:   9% 113M/1.18G [00:10<01:51, 10.2MB/s]% 65.4M/119M [00:10<00:07, 7.15MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb:  67% 79.8M/119M [00:12<00:05, 7.37MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  12% 147M/1.18G [00:14<01:59, 9.24MB/s]% 93.9M/119M [00:14<00:03, 7.41MB/s]d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb:  92% 109M/119M [00:16<00:01, 7.64MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  15% 183M/1.18G [00:18<01:56, 9.22MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  17% 202M/1.18G [00:20<01:46, 9.81MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  18% 220M/1.18G [00:22<01:46, 9.67MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  20% 241M/1.18G [00:24<01:39, 10.2MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  22% 262M/1.18G [00:26<01:32, 10.6MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  23% 274M/1.18G [00:27<01:28, 11.0MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  24% 295M/1.18G [00:29<01:25, 11.2MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  26% 310M/1.18G [00:31<01:36, 9.67MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  27% 323M/1.18G [00:33<01:52, 8.18MB/s]% 118M/119M [00:17<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb: 100% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  29% 353M/1.18G [00:37<01:55, 7.75MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  31% 369M/1.18G [00:39<01:48, 8.06MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  32% 384M/1.18G [00:41<01:46, 8.03MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  33% 401M/1.18G [00:43<01:38, 8.55MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  35% 423M/1.18G [00:45<01:21, 10.1MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  37% 449M/1.18G [00:47<01:06, 11.9MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  40% 486M/1.18G [00:49<00:47, 16.0MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  44% 536M/1.18G [00:51<00:33, 21.0MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  47% 571M/1.18G [00:53<00:33, 19.5MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  50% 604M/1.18G [00:55<00:33, 18.6MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  53% 634M/1.18G [00:57<00:35, 16.9MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  55% 657M/1.18G [00:59<00:40, 14.1MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  56% 680M/1.18G [01:01<00:41, 13.1MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  58% 703M/1.18G [01:03<00:41, 12.7MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  60% 720M/1.18G [01:05<00:48, 10.6MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  61% 734M/1.18G [01:07<00:53, 9.22MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  62% 750M/1.18G [01:09<00:55, 8.57MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  63% 763M/1.18G [01:11<00:59, 7.72MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  64% 776M/1.18G [01:13<01:01, 7.33MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  66% 791M/1.18G [01:15<00:57, 7.53MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  67% 806M/1.18G [01:17<00:53, 7.79MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  68% 823M/1.18G [01:19<00:49, 8.14MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  70% 839M/1.18G [01:21<00:46, 8.17MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  71% 855M/1.18G [01:23<00:43, 8.46MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  72% 866M/1.18G [01:25<00:50, 7.01MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  73% 876M/1.18G [01:27<00:54, 6.27MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  74% 887M/1.18G [01:29<00:55, 5.99MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  75% 898M/1.18G [01:31<00:54, 5.83MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  76% 910M/1.18G [01:33<00:50, 6.15MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  77% 924M/1.18G [01:35<00:44, 6.65MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  78% 940M/1.18G [01:37<00:36, 7.67MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  79% 956M/1.18G [01:39<00:32, 8.00MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  81% 975M/1.18G [01:41<00:26, 8.90MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  83% 993M/1.18G [01:43<00:23, 9.37MB/s]% 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  84% 0.98G/1.18G [01:45<00:24, 8.35MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  84% 0.99G/1.18G [01:47<00:31, 6.20MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  85% 1.00G/1.18G [01:49<00:32, 5.83MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  86% 1.01G/1.18G [01:51<00:34, 5.21MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  87% 1.02G/1.18G [01:53<00:33, 4.98MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  88% 1.03G/1.18G [01:55<00:28, 5.46MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  89% 1.04G/1.18G [01:57<00:24, 5.87MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  90% 1.06G/1.18G [01:59<00:16, 7.62MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  92% 1.08G/1.18G [02:01<00:09, 10.5MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  95% 1.12G/1.18G [02:03<00:04, 14.5MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  98% 1.15G/1.18G [02:05<00:01, 15.2MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+Upload file pytorch_model.bin:  99% 1.16G/1.18G [02:07<00:00, 12.1MB/s] 119M/119M [00:35<00:00, 8.20MB/s] d` and have been ignored: input_length.orward` and have been ignored: input_length.h..
+error: failed to push some refs to 'https://huggingface.co/shpotes/xls-r-et'e: error: cannot lock ref 'refs/heads/main': is at fa2a9d24f0bae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724
+error: failed to push some refs to 'https://huggingface.co/shpotes/xls-r-et'e: error: cannot lock ref 'refs/heads/main': is at fa2a9d24f0bae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724
+01/28/2022 11:57:53 - WARNING - huggingface_hub.repository - remote: error: cannot lock ref 'refs/heads/main': is at fa2a9d24f0bae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724
+To https://huggingface.co/shpotes/xls-r-et
+ ! [remote rejected]   main -> main (failed to update ref)
+error: failed to push some refs to 'https://huggingface.co/shpotes/xls-r-et'ae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724         but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724
+error: failed to push some refs to 'https://huggingface.co/shpotes/xls-r-et'ae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724         but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724
+error: failed to push some refs to 'https://huggingface.co/shpotes/xls-r-et'ae1b5002fb327d3cfa727ef5b4caf but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724         but expected 47349e7afe3432bdda0b555d40b9efb3c7b25724

wandb/run-20220126_105847-1xdiy2kf/logs/debug-internal.log

@@ -50347,3 +50347,216 @@ requests.exceptions.ReadTimeout: HTTPSConnectionPool(host='api.wandb.ai', port=4
 2022-01-28 11:55:23,950 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
 2022-01-28 11:55:25,861 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
 2022-01-28 11:55:34,430 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:55:39,097 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:55:39,097 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:55:41,869 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:43,870 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:45,871 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:47,872 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:49,873 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:51,874 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:53,875 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:54,268 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:55:54,268 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:55:55,876 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:57,877 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:55:59,878 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:01,879 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:03,880 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:05,447 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:56:05,881 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:07,882 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:09,422 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:56:09,423 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:56:09,883 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:11,884 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:14,885 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:16,886 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:18,887 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:20,889 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:22,889 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:24,576 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:56:24,576 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:56:24,891 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:26,891 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:28,892 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:30,893 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:32,894 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:34,895 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:36,472 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:56:36,896 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:38,897 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:39,736 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:56:39,736 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:56:40,898 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:42,899 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:44,900 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:46,900 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:48,901 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:50,902 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:52,903 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:54,904 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:55,520 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:56:55,520 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:56:56,905 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:56:58,906 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:00,907 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:02,908 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:04,909 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:06,910 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:07,469 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:57:08,911 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:10,670 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:57:10,671 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:57:10,912 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:12,913 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:14,914 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:16,915 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:18,916 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:20,917 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:22,917 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:24,919 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:25,823 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:57:25,823 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:57:26,920 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:28,920 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:30,921 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:32,922 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:34,923 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:36,924 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:38,484 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:57:38,925 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:40,926 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:40,973 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-28 11:57:40,973 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
+2022-01-28 11:57:42,927 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:44,928 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:46,929 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:48,930 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:50,931 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:52,931 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:54,933 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:55,933 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:56,247 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:56,248 DEBUG   SenderThread:2220828 [sender.py:send():234] send: telemetry
+2022-01-28 11:57:56,248 DEBUG   SenderThread:2220828 [sender.py:send():234] send: exit
+2022-01-28 11:57:56,248 INFO    SenderThread:2220828 [sender.py:send_exit():366] handling exit code: 1
+2022-01-28 11:57:56,249 INFO    SenderThread:2220828 [sender.py:send_exit():368] handling runtime: 176347
+2022-01-28 11:57:56,276 INFO    SenderThread:2220828 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-01-28 11:57:56,277 INFO    SenderThread:2220828 [sender.py:send_exit():374] send defer
+2022-01-28 11:57:56,277 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:56,278 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:56,278 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 0
+2022-01-28 11:57:56,278 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:56,278 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 0
+2022-01-28 11:57:56,278 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 1
+2022-01-28 11:57:56,279 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:56,279 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 1
+2022-01-28 11:57:56,432 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:56,432 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:56,432 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 1
+2022-01-28 11:57:56,433 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 2
+2022-01-28 11:57:56,433 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:56,434 DEBUG   SenderThread:2220828 [sender.py:send():234] send: stats
+2022-01-28 11:57:56,435 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:56,435 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 2
+2022-01-28 11:57:56,435 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:56,436 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 2
+2022-01-28 11:57:56,436 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 3
+2022-01-28 11:57:56,436 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:56,436 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 3
+2022-01-28 11:57:56,463 DEBUG   SenderThread:2220828 [sender.py:send():234] send: summary
+2022-01-28 11:57:56,500 INFO    SenderThread:2220828 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-01-28 11:57:56,500 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:56,500 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 3
+2022-01-28 11:57:56,500 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 4
+2022-01-28 11:57:56,500 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:56,501 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 4
+2022-01-28 11:57:56,501 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:56,501 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 4
+2022-01-28 11:57:56,536 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:56,985 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:56,996 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json
+2022-01-28 11:57:57,060 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 5
+2022-01-28 11:57:57,060 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:57,061 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:57,061 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 5
+2022-01-28 11:57:57,061 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:57,061 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 5
+2022-01-28 11:57:57,061 INFO    SenderThread:2220828 [dir_watcher.py:finish():283] shutting down directory watcher
+2022-01-28 11:57:57,162 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:57,986 INFO    Thread-8  :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/config.yaml
+2022-01-28 11:57:57,987 INFO    SenderThread:2220828 [dir_watcher.py:finish():313] scan: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files
+2022-01-28 11:57:57,987 INFO    SenderThread:2220828 [dir_watcher.py:finish():327] scan save: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/config.yaml config.yaml
+2022-01-28 11:57:57,987 INFO    SenderThread:2220828 [dir_watcher.py:finish():327] scan save: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json wandb-summary.json
+2022-01-28 11:57:57,988 INFO    SenderThread:2220828 [dir_watcher.py:finish():327] scan save: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/requirements.txt requirements.txt
+2022-01-28 11:57:57,995 INFO    SenderThread:2220828 [dir_watcher.py:finish():327] scan save: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-metadata.json wandb-metadata.json
+2022-01-28 11:57:58,000 INFO    SenderThread:2220828 [dir_watcher.py:finish():327] scan save: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log output.log
+2022-01-28 11:57:58,000 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 6
+2022-01-28 11:57:58,001 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,008 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:58,014 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 6
+2022-01-28 11:57:58,014 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:58,015 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 6
+2022-01-28 11:57:58,015 INFO    SenderThread:2220828 [file_pusher.py:finish():177] shutting down file pusher
+2022-01-28 11:57:58,104 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,104 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,207 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,207 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,309 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,310 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,412 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,413 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,515 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,515 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,618 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,618 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,630 INFO    Thread-14 :2220828 [upload_job.py:push():137] Uploaded file /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/requirements.txt
+2022-01-28 11:57:58,720 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,721 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,823 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,823 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,926 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:58,926 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:58,959 INFO    Thread-13 :2220828 [upload_job.py:push():137] Uploaded file /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json
+2022-01-28 11:57:59,017 INFO    Thread-12 :2220828 [upload_job.py:push():137] Uploaded file /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/config.yaml
+2022-01-28 11:57:59,029 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:59,029 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:59,131 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:59,132 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:59,170 INFO    Thread-15 :2220828 [upload_job.py:push():137] Uploaded file /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
+2022-01-28 11:57:59,234 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:59,234 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:59,337 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:57:59,337 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:57:59,371 INFO    Thread-7  :2220828 [sender.py:transition_state():387] send defer: 7
+2022-01-28 11:57:59,371 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:57:59,372 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 7
+2022-01-28 11:57:59,372 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:57:59,372 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 7
+2022-01-28 11:57:59,439 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:58:00,216 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 8
+2022-01-28 11:58:00,217 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:58:00,217 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:58:00,218 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 8
+2022-01-28 11:58:00,218 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:58:00,218 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 8
+2022-01-28 11:58:00,218 INFO    SenderThread:2220828 [sender.py:transition_state():387] send defer: 9
+2022-01-28 11:58:00,220 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: defer
+2022-01-28 11:58:00,220 DEBUG   SenderThread:2220828 [sender.py:send():234] send: final
+2022-01-28 11:58:00,221 INFO    HandlerThread:2220828 [handler.py:handle_request_defer():147] handle defer: 9
+2022-01-28 11:58:00,221 DEBUG   SenderThread:2220828 [sender.py:send():234] send: footer
+2022-01-28 11:58:00,222 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: defer
+2022-01-28 11:58:00,222 INFO    SenderThread:2220828 [sender.py:send_request_defer():383] handle sender defer: 9
+2022-01-28 11:58:00,320 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: poll_exit
+2022-01-28 11:58:00,320 DEBUG   SenderThread:2220828 [sender.py:send_request():248] send_request: poll_exit
+2022-01-28 11:58:00,320 INFO    SenderThread:2220828 [file_pusher.py:join():182] waiting for file pusher
+2022-01-28 11:58:00,599 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: get_summary
+2022-01-28 11:58:00,657 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: sampled_history
+2022-01-28 11:58:00,662 DEBUG   HandlerThread:2220828 [handler.py:handle_request():130] handle_request: shutdown
+2022-01-28 11:58:00,663 INFO    HandlerThread:2220828 [handler.py:finish():731] shutting down handler
+2022-01-28 11:58:01,221 INFO    WriterThread:2220828 [datastore.py:close():281] close: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb
+2022-01-28 11:58:01,597 INFO    SenderThread:2220828 [sender.py:finish():1070] shutting down sender
+2022-01-28 11:58:01,597 INFO    SenderThread:2220828 [file_pusher.py:finish():177] shutting down file pusher
+2022-01-28 11:58:01,597 INFO    SenderThread:2220828 [file_pusher.py:join():182] waiting for file pusher
+2022-01-28 11:58:01,606 INFO    MainThread:2220828 [internal.py:handle_exit():77] Internal process exited

wandb/run-20220126_105847-1xdiy2kf/logs/debug.log

@@ -22,3 +22,165 @@ config: {}
 2022-01-26 10:58:48,541 INFO    MainThread:2220463 [wandb_init.py:init():633] run started, returning control to user process
 2022-01-26 10:58:48,562 INFO    MainThread:2220463 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 36, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-xls-r-300m', 'transformers_version': '4.16.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 39, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 80, 'per_device_eval_batch_size': 80, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 500.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jan26_10-56-56_ganymede.eafit.edu.co', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'cosine+drop_proj+low_specaugment-300M', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 80, 'eval_batch_size': 80}
 2022-01-26 10:58:48,565 INFO    MainThread:2220463 [wandb_watch.py:watch():43] Watching
+2022-01-28 11:57:53,891 INFO    MainThread:2220463 [wandb_run.py:_atexit_cleanup():1780] got exitcode: 1
+2022-01-28 11:57:53,896 INFO    MainThread:2220463 [wandb_run.py:_restore():1752] restore
+2022-01-28 11:57:56,278 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 2324
+}
+
+2022-01-28 11:57:56,435 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 2324
+}
+
+2022-01-28 11:57:57,061 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 2324
+}
+
+2022-01-28 11:57:58,002 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,105 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,208 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2324
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,311 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2246495
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,414 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2246495
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,516 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,619 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,722 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,824 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:58,927 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:59,030 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:59,133 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:59,235 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:57:59,338 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:58:00,218 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+
+2022-01-28 11:58:00,597 INFO    MainThread:2220463 [wandb_run.py:_wait_for_finish():1912] got exit ret: done: true
+exit_result {
+}
+file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 3441922
+  total_bytes: 3441922
+}
+local_info {
+}
+
+2022-01-28 11:58:01,703 INFO    MainThread:2220463 [wandb_run.py:_append_history():2130] rendering history
+2022-01-28 11:58:01,705 INFO    MainThread:2220463 [wandb_run.py:_append_summary():2085] rendering summary
+2022-01-28 11:58:01,706 INFO    MainThread:2220463 [wandb_run.py:_append_files():2180] logging synced files

wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e665cf3bd1d21f24efc603dcc4e99707b7439674c0638bb608c504f3187318
-size 124718462
+oid sha256:aee0b40e3c968e6e44cf387e6b28e8eb547361393a2c20aa51d507601ce6dd4f
+size 125379374

wandb/run-20220129_111936-33z1cg4n/files/output.log

@@ -0,0 +1,546 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|█▋                                                            | 99/3600 [15:46<10:30:00, 10.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|███▍                                                         | 200/3600 [31:33<10:03:22, 10.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|█████▏                                                        | 299/3600 [47:03<9:53:18, 10.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 11%|██████▋                                                     | 399/3600 [1:02:40<9:47:13, 11.01s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|████████▎                                                   | 499/3600 [1:18:15<6:47:48,  7.89s/it]
+ 14%|████████▎                                                   | 500/3600 [1:18:20<5:57:31,  6.92s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 2609
+  Batch size = 80
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|███████████████████████████████████████████████████████████████████| 33/33 [02:06<00:00,  2.59s/it]
+
+Configuration saved in ./checkpoint-500/config.json
+Model weights saved in ./checkpoint-500/pytorch_model.bin
+Configuration saved in ./checkpoint-500/preprocessor_config.json

wandb/run-20220129_111936-33z1cg4n/files/requirements.txt

@@ -0,0 +1,87 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+appdirs==1.4.4
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+bitsandbytes-cuda113==0.26.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.10
+click==8.0.3
+clldutils==3.10.1
+colorlog==6.6.0
+configparser==5.2.0
+csvw==1.11.0
+datasets==1.18.1.dev0
+decorator==5.1.1
+dill==0.3.4
+dlinfo==1.2.1
+docker-pycreds==0.4.0
+filelock==3.4.2
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+huggingface-hub==0.4.0
+hypothesis==6.36.0
+idna==3.3
+isodate==0.6.1
+jiwer==2.3.0
+joblib==1.1.0
+librosa==0.8.1
+llvmlite==0.38.0
+multidict==6.0.2
+multiprocess==0.70.12.2
+numba==0.55.0
+numpy==1.21.5
+packaging==21.3
+pandas==1.4.0
+pathtools==0.1.2
+phonemizer==3.0.1
+pip==21.3.1
+pooch==1.6.0
+promise==2.3
+protobuf==3.19.3
+psutil==5.9.0
+pyarrow==6.0.1
+pycparser==2.21
+pyctcdecode==0.3.0
+pygtrie==2.4.2
+pyparsing==3.0.7
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+pytz==2021.3
+pyyaml==6.0
+regex==2022.1.18
+requests==2.27.1
+resampy==0.2.2
+rfc3986==2.0.0
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+sentry-sdk==1.5.4
+setuptools==60.2.0
+shortuuid==1.0.8
+six==1.16.0
+smmap==5.0.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+subprocess32==3.5.4
+tabulate==0.8.9
+termcolor==1.1.0
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+torch==1.10.1
+torchaudio==0.10.1
+tqdm==4.62.3
+transformers==4.16.0.dev0
+typing-extensions==4.0.1
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.9
+wheel==0.37.1
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0

wandb/run-20220129_111936-33z1cg4n/files/wandb-metadata.json

@@ -0,0 +1,76 @@
+{
+    "os": "Linux-4.18.0-305.10.2.el8_4.x86_64-x86_64-with-glibc2.28",
+    "python": "3.9.6",
+    "heartbeatAt": "2022-01-29T16:19:37.625823",
+    "startedAt": "2022-01-29T16:19:36.629047",
+    "docker": null,
+    "gpu": "Tesla V100-PCIE-32GB",
+    "gpu_count": 3,
+    "cpu_count": 64,
+    "cuda": null,
+    "args": [
+        "--dataset_name=mozilla-foundation/common_voice_7_0",
+        "--model_name_or_path=facebook/wav2vec2-xls-r-300m",
+        "--dataset_config_name=et",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=100",
+        "--per_device_train_batch_size=80",
+        "--per_device_eval_batch_size=80",
+        "--gradient_accumulation_steps=2",
+        "--learning_rate=3e-4",
+        "--save_total_limit=1",
+        "--warmup_steps=500",
+        "--evaluation_strategy=steps",
+        "--text_column_name=sentence",
+        "--length_column_name=input_length",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.0",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.1",
+        "--chars_to_ignore",
+        ",",
+        "?",
+        ".",
+        "!",
+        "-",
+        ";",
+        ":",
+        "\"",
+        "\u201c",
+        "%",
+        "\u2018",
+        "\u201d",
+        "\ufffd",
+        "\u2014",
+        "\u2019",
+        "\u2026",
+        "\u2013",
+        "--gradient_checkpointing",
+        "--lr_scheduler_type=cosine",
+        "--fp16",
+        "--group_by_length",
+        "--mask_time_prob=0.1",
+        "--mask_time_length=10",
+        "--report_to=wandb",
+        "--run_name=cosine+drop_proj+low_specaugment-300M",
+        "--do_train",
+        "--do_eval",
+        "--use_auth_token",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "/home/sagrilaft/Project/audio/xls-r-et/src/run_speech_recognition_ctc_bnb.py",
+    "codePath": "src/run_speech_recognition_ctc_bnb.py",
+    "git": {
+        "remote": "https://huggingface.co/shpotes/xls-r-et",
+        "commit": "fa2a9d24f0bae1b5002fb327d3cfa727ef5b4caf"
+    },
+    "email": "shpotes3@gmail.com",
+    "root": "/home/sagrilaft/Project/audio/xls-r-et",
+    "host": "ganymede.eafit.edu.co",
+    "username": "sagrilaft",
+    "executable": "/home/sagrilaft/Project/audio/xls-r-et/.venv/bin/python"
+}

wandb/run-20220129_111936-33z1cg4n/logs/debug.log

@@ -0,0 +1,24 @@
+2022-01-29 11:19:36,632 INFO    MainThread:2523114 [wandb_setup.py:_flush():71] setting env: {'project': 'xls-r-estonian'}
+2022-01-29 11:19:36,632 INFO    MainThread:2523114 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-29 11:19:36,632 INFO    MainThread:2523114 [wandb_init.py:_log_setup():371] Logging user logs to /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220129_111936-33z1cg4n/logs/debug.log
+2022-01-29 11:19:36,632 INFO    MainThread:2523114 [wandb_init.py:_log_setup():372] Logging internal logs to /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220129_111936-33z1cg4n/logs/debug-internal.log
+2022-01-29 11:19:36,633 INFO    MainThread:2523114 [wandb_init.py:init():404] calling init triggers
+2022-01-29 11:19:36,633 INFO    MainThread:2523114 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-01-29 11:19:36,633 INFO    MainThread:2523114 [wandb_init.py:init():460] starting backend
+2022-01-29 11:19:36,633 INFO    MainThread:2523114 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-01-29 11:19:36,666 INFO    MainThread:2523114 [backend.py:ensure_launched():216] starting backend process...
+2022-01-29 11:19:36,693 INFO    MainThread:2523114 [backend.py:ensure_launched():221] started backend process with pid: 2523574
+2022-01-29 11:19:36,694 INFO    MainThread:2523114 [wandb_init.py:init():469] backend started and connected
+2022-01-29 11:19:36,701 INFO    MainThread:2523114 [wandb_init.py:init():533] updated telemetry
+2022-01-29 11:19:36,765 INFO    MainThread:2523114 [wandb_init.py:init():563] communicating current version
+2022-01-29 11:19:37,425 INFO    MainThread:2523114 [wandb_init.py:init():568] got version response 
+2022-01-29 11:19:37,426 INFO    MainThread:2523114 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-01-29 11:19:37,617 INFO    MainThread:2523114 [wandb_init.py:init():606] starting run threads in backend
+2022-01-29 11:19:37,676 INFO    MainThread:2523114 [wandb_run.py:_console_start():1810] atexit reg
+2022-01-29 11:19:37,677 INFO    MainThread:2523114 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-01-29 11:19:37,677 INFO    MainThread:2523114 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-01-29 11:19:37,680 INFO    MainThread:2523114 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-01-29 11:19:37,680 INFO    MainThread:2523114 [wandb_init.py:init():633] run started, returning control to user process
+2022-01-29 11:19:37,694 INFO    MainThread:2523114 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 36, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-xls-r-300m', 'transformers_version': '4.16.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 39, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 80, 'per_device_eval_batch_size': 80, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 100.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jan29_11-17-08_ganymede.eafit.edu.co', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'cosine+drop_proj+low_specaugment-300M', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 80, 'eval_batch_size': 80}
+2022-01-29 11:19:37,697 INFO    MainThread:2523114 [wandb_watch.py:watch():43] Watching