| 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} | |