12/11/2022 16:15:09 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True 12/11/2022 16:15:09 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( _n_gpu=1, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, bf16=False, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=0, dataloader_pin_memory=True, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, do_eval=True, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_steps=1000, evaluation_strategy=steps, fp16=True, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, generation_max_length=225, generation_num_beams=None, gradient_accumulation_steps=2, gradient_checkpointing=True, greater_is_better=False, group_by_length=False, half_precision_backend=auto, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=1e-05, length_column_name=input_length, load_best_model_at_end=True, local_rank=-1, log_level=passive, log_level_replica=passive, log_on_each_node=True, logging_dir=./runs/Dec11_16-15-08_4b942bf2873e, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=25, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, max_steps=5000, metric_for_best_model=wer, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, optim_args=None, output_dir=./, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=32, per_device_train_batch_size=32, predict_with_generate=True, prediction_loss_only=False, push_to_hub=True, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['tensorboard'], resume_from_checkpoint=None, run_name=./, save_on_each_node=False, save_steps=1000, save_strategy=steps, save_total_limit=None, seed=42, sharded_ddp=[], skip_memory_metrics=True, sortish_sampler=False, tf32=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=500, weight_decay=0.0, xpu_backend=None, ) 12/11/2022 16:15:09 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( _n_gpu=1, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, bf16=False, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=0, dataloader_pin_memory=True, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, do_eval=True, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_steps=1000, evaluation_strategy=steps, fp16=True, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, generation_max_length=225, generation_num_beams=None, gradient_accumulation_steps=2, gradient_checkpointing=True, greater_is_better=False, group_by_length=False, half_precision_backend=auto, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=1e-05, length_column_name=input_length, load_best_model_at_end=True, local_rank=-1, log_level=passive, log_level_replica=passive, log_on_each_node=True, logging_dir=./runs/Dec11_16-15-08_4b942bf2873e, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=25, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, max_steps=5000, metric_for_best_model=wer, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, optim_args=None, output_dir=./, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=32, per_device_train_batch_size=32, predict_with_generate=True, prediction_loss_only=False, push_to_hub=True, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['tensorboard'], resume_from_checkpoint=None, run_name=./, save_on_each_node=False, save_steps=1000, save_strategy=steps, save_total_limit=None, seed=42, sharded_ddp=[], skip_memory_metrics=True, sortish_sampler=False, tf32=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=500, weight_decay=0.0, xpu_backend=None, ) 12/11/2022 16:15:12 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:15:12 - INFO - datasets.builder - Generating dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) Downloading and preparing dataset common_voice_11_0/cs to /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f... 12/11/2022 16:15:12 - INFO - datasets.builder - Dataset not on Hf google storage. Downloading and preparing it from source 12/11/2022 16:15:13 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/n_shards.json not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmp2uu2ip8r 12/11/2022 16:15:13 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/n_shards.json in cache at /root/.cache/huggingface/datasets/downloads/a64fc6ccf85aaef9b75e8612e97f260d2435e8ffe8b7626c5c08499f466674da 12/11/2022 16:15:13 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/a64fc6ccf85aaef9b75e8612e97f260d2435e8ffe8b7626c5c08499f466674da 12/11/2022 16:15:13 - INFO - datasets.download.download_manager - Downloading took 0.0 min 12/11/2022 16:15:13 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min 12/11/2022 16:15:14 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/train/cs_train_0.tar not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpn45dj41t 12/11/2022 16:15:23 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/train/cs_train_0.tar in cache at /root/.cache/huggingface/datasets/downloads/e65067c9e6680c37326687e28407d42076ea8a79d0230ccfa9f1a30beefa496d 12/11/2022 16:15:23 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/e65067c9e6680c37326687e28407d42076ea8a79d0230ccfa9f1a30beefa496d 12/11/2022 16:15:24 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/dev/cs_dev_0.tar not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmp9ynq0ta5 12/11/2022 16:15:29 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/dev/cs_dev_0.tar in cache at /root/.cache/huggingface/datasets/downloads/faef583dccc4451b03508c77f16c823c3e52f080e7d2696c47ef3bc4da88b993 12/11/2022 16:15:29 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/faef583dccc4451b03508c77f16c823c3e52f080e7d2696c47ef3bc4da88b993 12/11/2022 16:15:30 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/test/cs_test_0.tar not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpczbaraay 12/11/2022 16:15:35 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/test/cs_test_0.tar in cache at /root/.cache/huggingface/datasets/downloads/3b199c261a4a515c549e967e06831827866d46648e11b24dc2f4b50880b69664 12/11/2022 16:15:35 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/3b199c261a4a515c549e967e06831827866d46648e11b24dc2f4b50880b69664 12/11/2022 16:15:36 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/other/cs_other_0.tar not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpzpt_v40l 12/11/2022 16:15:41 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/other/cs_other_0.tar in cache at /root/.cache/huggingface/datasets/downloads/e9daf9a9975b7a926609592de3dd2542f6bfa853753253cd36e1ff97a21d5b16 12/11/2022 16:15:41 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/e9daf9a9975b7a926609592de3dd2542f6bfa853753253cd36e1ff97a21d5b16 12/11/2022 16:15:42 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/invalidated/cs_invalidated_0.tar not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpef10rmii 12/11/2022 16:15:43 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/audio/cs/invalidated/cs_invalidated_0.tar in cache at /root/.cache/huggingface/datasets/downloads/8f0074a128edd8f8eb60cf804a3ae6c95ebcea9a743285d0c76e6b2168fd6695 12/11/2022 16:15:43 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/8f0074a128edd8f8eb60cf804a3ae6c95ebcea9a743285d0c76e6b2168fd6695 12/11/2022 16:15:43 - INFO - datasets.download.download_manager - Downloading took 0.0 min 12/11/2022 16:15:48 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min 12/11/2022 16:15:48 - INFO - datasets.utils.py_utils - Spawning 5 processes for 5 objects in slices of [1, 1, 1, 1, 1] 12/11/2022 16:15:53 - INFO - datasets.utils.py_utils - Finished 5 processes 12/11/2022 16:15:53 - INFO - datasets.utils.py_utils - Unpacked 5 objects 12/11/2022 16:15:54 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/train.tsv not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmp2rur8w_5 12/11/2022 16:15:55 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/train.tsv in cache at /root/.cache/huggingface/datasets/downloads/e03f690a1b87aaf6a10df06930bea3ea97524f22df3689d7d4f6de39a04ad6df 12/11/2022 16:15:55 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/e03f690a1b87aaf6a10df06930bea3ea97524f22df3689d7d4f6de39a04ad6df 12/11/2022 16:15:56 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/dev.tsv not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpg21adl1m 12/11/2022 16:15:57 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/dev.tsv in cache at /root/.cache/huggingface/datasets/downloads/5ede6c8121be47f2c2e4cb6be8b87ef855e5e3966ea6288c369f3d760770b29b 12/11/2022 16:15:57 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/5ede6c8121be47f2c2e4cb6be8b87ef855e5e3966ea6288c369f3d760770b29b 12/11/2022 16:15:58 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/test.tsv not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmplvvsd__g 12/11/2022 16:16:02 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/test.tsv in cache at /root/.cache/huggingface/datasets/downloads/af41495b66bafe30b9cd41b7495379553a285ecf658214a8659ed096da46180b 12/11/2022 16:16:02 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/af41495b66bafe30b9cd41b7495379553a285ecf658214a8659ed096da46180b 12/11/2022 16:16:03 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/other.tsv not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmp04ecl_sx 12/11/2022 16:16:03 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/other.tsv in cache at /root/.cache/huggingface/datasets/downloads/0b1cf69c260eb7bfb5a97457676fa623c013d75427595de37d10c03c53b2a184 12/11/2022 16:16:03 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/0b1cf69c260eb7bfb5a97457676fa623c013d75427595de37d10c03c53b2a184 12/11/2022 16:16:04 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/invalidated.tsv not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmphgbsuplm 12/11/2022 16:16:05 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/streaming/transcript/cs/invalidated.tsv in cache at /root/.cache/huggingface/datasets/downloads/678b61c8b7174e01bad8858c770f89625c71e9cbcfe3a7ca7905d4fab962dcbf 12/11/2022 16:16:05 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/678b61c8b7174e01bad8858c770f89625c71e9cbcfe3a7ca7905d4fab962dcbf 12/11/2022 16:16:05 - INFO - datasets.download.download_manager - Downloading took 0.0 min 12/11/2022 16:16:05 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min 12/11/2022 16:16:05 - INFO - datasets.utils.py_utils - Spawning 5 processes for 5 objects in slices of [1, 1, 1, 1, 1] 12/11/2022 16:16:05 - INFO - datasets.utils.py_utils - Finished 5 processes 12/11/2022 16:16:05 - INFO - datasets.utils.py_utils - Unpacked 5 objects 12/11/2022 16:16:05 - INFO - datasets.utils.info_utils - Unable to verify checksums. 12/11/2022 16:16:05 - INFO - datasets.builder - Generating train split 12/11/2022 16:16:13 - INFO - datasets.builder - Generating validation split 12/11/2022 16:16:17 - INFO - datasets.builder - Generating test split 12/11/2022 16:16:21 - INFO - datasets.builder - Generating other split 12/11/2022 16:16:26 - INFO - datasets.builder - Generating invalidated split 12/11/2022 16:16:27 - INFO - datasets.utils.info_utils - Unable to verify splits sizes. Dataset common_voice_11_0 downloaded and prepared to /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f. Subsequent calls will reuse this data. 12/11/2022 16:16:30 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:16:30 - INFO - datasets.builder - Overwrite dataset info from restored data version. 12/11/2022 16:16:30 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:16:30 - WARNING - datasets.builder - Found cached dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) 12/11/2022 16:16:30 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:16:33 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:16:33 - INFO - datasets.builder - Overwrite dataset info from restored data version. 12/11/2022 16:16:33 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:16:33 - WARNING - datasets.builder - Found cached dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) 12/11/2022 16:16:33 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f 12/11/2022 16:17:55 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-a7b69aafcb764d25.arrow 12/11/2022 17:06:52 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-c3bcb0a977898ff3.arrow 12/11/2022 17:34:34 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-1a8c2d6bd9812539.arrow 12/11/2022 18:04:38 - WARNING - huggingface_hub.repository - /usr/src/app/models/whisper-medium-czech-cv11/./ is already a clone of https://huggingface.co/mikr/whisper-medium-czech-cv11. Make sure you pull the latest changes with `repo.git_pull()`. {'loss': 0.9539, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.11} {'loss': 0.6773, 'learning_rate': 9.800000000000001e-07, 'epoch': 0.21} {'loss': 0.3302, 'learning_rate': 1.48e-06, 'epoch': 0.32} {'loss': 0.2437, 'learning_rate': 1.98e-06, 'epoch': 0.42} {'loss': 0.2103, 'learning_rate': 2.4800000000000004e-06, 'epoch': 0.53} {'loss': 0.1938, 'learning_rate': 2.9800000000000003e-06, 'epoch': 0.64} {'loss': 0.1946, 'learning_rate': 3.48e-06, 'epoch': 0.74} {'loss': 0.1788, 'learning_rate': 3.980000000000001e-06, 'epoch': 0.85} {'loss': 0.1669, 'learning_rate': 4.48e-06, 'epoch': 0.95} {'loss': 0.1427, 'learning_rate': 4.980000000000001e-06, 'epoch': 1.06} {'loss': 0.118, 'learning_rate': 5.480000000000001e-06, 'epoch': 1.17} {'loss': 0.1184, 'learning_rate': 5.98e-06, 'epoch': 1.27} {'loss': 0.1103, 'learning_rate': 6.480000000000001e-06, 'epoch': 1.38} {'loss': 0.1143, 'learning_rate': 6.98e-06, 'epoch': 1.48} {'loss': 0.1102, 'learning_rate': 7.48e-06, 'epoch': 1.59} {'loss': 0.116, 'learning_rate': 7.980000000000002e-06, 'epoch': 1.69} {'loss': 0.103, 'learning_rate': 8.48e-06, 'epoch': 1.8} {'loss': 0.1067, 'learning_rate': 8.98e-06, 'epoch': 1.91} {'loss': 0.1014, 'learning_rate': 9.48e-06, 'epoch': 2.01} {'loss': 0.045, 'learning_rate': 9.980000000000001e-06, 'epoch': 2.12} {'loss': 0.0502, 'learning_rate': 9.946666666666667e-06, 'epoch': 2.22} {'loss': 0.051, 'learning_rate': 9.891111111111113e-06, 'epoch': 2.33} {'loss': 0.0467, 'learning_rate': 9.835555555555556e-06, 'epoch': 2.44} {'loss': 0.0495, 'learning_rate': 9.780000000000001e-06, 'epoch': 2.54} {'loss': 0.0465, 'learning_rate': 9.724444444444445e-06, 'epoch': 2.65} {'loss': 0.0489, 'learning_rate': 9.66888888888889e-06, 'epoch': 2.75} {'loss': 0.0525, 'learning_rate': 9.613333333333335e-06, 'epoch': 2.86} {'loss': 0.0506, 'learning_rate': 9.557777777777777e-06, 'epoch': 2.97} {'loss': 0.0278, 'learning_rate': 9.502222222222223e-06, 'epoch': 3.07} {'loss': 0.0201, 'learning_rate': 9.446666666666667e-06, 'epoch': 3.18} {'loss': 0.0201, 'learning_rate': 9.391111111111111e-06, 'epoch': 3.28} {'loss': 0.0203, 'learning_rate': 9.335555555555557e-06, 'epoch': 3.39} {'loss': 0.021, 'learning_rate': 9.280000000000001e-06, 'epoch': 3.5} {'loss': 0.0214, 'learning_rate': 9.224444444444445e-06, 'epoch': 3.6} {'loss': 0.0239, 'learning_rate': 9.168888888888889e-06, 'epoch': 3.71} {'loss': 0.0223, 'learning_rate': 9.113333333333335e-06, 'epoch': 3.81} {'loss': 0.0243, 'learning_rate': 9.057777777777779e-06, 'epoch': 3.92} {'loss': 0.0199, 'learning_rate': 9.002222222222223e-06, 'epoch': 4.03} {'loss': 0.0097, 'learning_rate': 8.946666666666669e-06, 'epoch': 4.13} {'loss': 0.0105, 'learning_rate': 8.891111111111111e-06, 'epoch': 4.24} {'eval_loss': 0.1972593367099762, 'eval_wer': 12.613027384394393, 'eval_runtime': 8895.0887, 'eval_samples_per_second': 0.867, 'eval_steps_per_second': 0.027, 'epoch': 4.24} {'loss': 0.0112, 'learning_rate': 8.835555555555557e-06, 'epoch': 4.34} {'loss': 0.0108, 'learning_rate': 8.78e-06, 'epoch': 4.45} {'loss': 0.0116, 'learning_rate': 8.724444444444445e-06, 'epoch': 4.56} {'loss': 0.0114, 'learning_rate': 8.66888888888889e-06, 'epoch': 4.66} {'loss': 0.011, 'learning_rate': 8.613333333333333e-06, 'epoch': 4.77} {'loss': 0.0096, 'learning_rate': 8.557777777777778e-06, 'epoch': 4.87} {'loss': 0.0126, 'learning_rate': 8.502222222222223e-06, 'epoch': 4.98} {'loss': 0.0078, 'learning_rate': 8.446666666666668e-06, 'epoch': 5.08} {'loss': 0.006, 'learning_rate': 8.391111111111112e-06, 'epoch': 5.19} {'loss': 0.0053, 'learning_rate': 8.335555555555556e-06, 'epoch': 5.3} {'loss': 0.0067, 'learning_rate': 8.28e-06, 'epoch': 5.4} {'loss': 0.0055, 'learning_rate': 8.224444444444444e-06, 'epoch': 5.51} {'loss': 0.0059, 'learning_rate': 8.16888888888889e-06, 'epoch': 5.61} {'loss': 0.0061, 'learning_rate': 8.113333333333334e-06, 'epoch': 5.72} {'loss': 0.0057, 'learning_rate': 8.057777777777778e-06, 'epoch': 5.83} {'loss': 0.0071, 'learning_rate': 8.002222222222222e-06, 'epoch': 5.93} {'loss': 0.0061, 'learning_rate': 7.946666666666666e-06, 'epoch': 6.04} {'loss': 0.0047, 'learning_rate': 7.891111111111112e-06, 'epoch': 6.14} {'loss': 0.004, 'learning_rate': 7.835555555555556e-06, 'epoch': 6.25} {'loss': 0.005, 'learning_rate': 7.78e-06, 'epoch': 6.36} {'loss': 0.0049, 'learning_rate': 7.724444444444446e-06, 'epoch': 6.46} {'loss': 0.0036, 'learning_rate': 7.66888888888889e-06, 'epoch': 6.57} {'loss': 0.0035, 'learning_rate': 7.613333333333334e-06, 'epoch': 6.67} {'loss': 0.0046, 'learning_rate': 7.557777777777779e-06, 'epoch': 6.78} {'loss': 0.0045, 'learning_rate': 7.502222222222223e-06, 'epoch': 6.89} {'loss': 0.0044, 'learning_rate': 7.446666666666668e-06, 'epoch': 6.99} {'loss': 0.0022, 'learning_rate': 7.3911111111111125e-06, 'epoch': 7.1} {'loss': 0.0019, 'learning_rate': 7.335555555555556e-06, 'epoch': 7.2} {'loss': 0.0019, 'learning_rate': 7.280000000000001e-06, 'epoch': 7.31} {'loss': 0.0024, 'learning_rate': 7.224444444444445e-06, 'epoch': 7.42} {'loss': 0.0022, 'learning_rate': 7.1688888888888895e-06, 'epoch': 7.52} {'loss': 0.0029, 'learning_rate': 7.113333333333334e-06, 'epoch': 7.63} {'loss': 0.0026, 'learning_rate': 7.057777777777778e-06, 'epoch': 7.73} {'loss': 0.0033, 'learning_rate': 7.0022222222222225e-06, 'epoch': 7.84} {'loss': 0.0026, 'learning_rate': 6.946666666666667e-06, 'epoch': 7.94} {'loss': 0.0025, 'learning_rate': 6.891111111111111e-06, 'epoch': 8.05} {'loss': 0.0019, 'learning_rate': 6.835555555555556e-06, 'epoch': 8.16} {'loss': 0.0022, 'learning_rate': 6.780000000000001e-06, 'epoch': 8.26} {'loss': 0.0015, 'learning_rate': 6.724444444444444e-06, 'epoch': 8.37} {'loss': 0.0016, 'learning_rate': 6.668888888888889e-06, 'epoch': 8.47} {'eval_loss': 0.2197847217321396, 'eval_wer': 11.898491740483601, 'eval_runtime': 9649.3249, 'eval_samples_per_second': 0.799, 'eval_steps_per_second': 0.025, 'epoch': 8.47} {'loss': 0.0023, 'learning_rate': 6.613333333333334e-06, 'epoch': 8.58} {'loss': 0.0022, 'learning_rate': 6.557777777777778e-06, 'epoch': 8.69} {'loss': 0.002, 'learning_rate': 6.502222222222223e-06, 'epoch': 8.79} {'loss': 0.0019, 'learning_rate': 6.446666666666668e-06, 'epoch': 8.9} {'loss': 0.0019, 'learning_rate': 6.391111111111111e-06, 'epoch': 9.0} {'loss': 0.0014, 'learning_rate': 6.335555555555556e-06, 'epoch': 9.11} {'loss': 0.002, 'learning_rate': 6.280000000000001e-06, 'epoch': 9.22} {'loss': 0.0014, 'learning_rate': 6.224444444444445e-06, 'epoch': 9.32} {'loss': 0.0018, 'learning_rate': 6.16888888888889e-06, 'epoch': 9.43} {'loss': 0.0018, 'learning_rate': 6.113333333333333e-06, 'epoch': 9.53} {'loss': 0.0016, 'learning_rate': 6.057777777777778e-06, 'epoch': 9.64} {'loss': 0.0017, 'learning_rate': 6.002222222222223e-06, 'epoch': 9.75} {'loss': 0.0014, 'learning_rate': 5.946666666666668e-06, 'epoch': 9.85} {'loss': 0.0018, 'learning_rate': 5.891111111111112e-06, 'epoch': 9.96} {'loss': 0.0014, 'learning_rate': 5.8355555555555565e-06, 'epoch': 10.06} {'loss': 0.0011, 'learning_rate': 5.78e-06, 'epoch': 10.17} {'loss': 0.0008, 'learning_rate': 5.724444444444445e-06, 'epoch': 10.28} {'loss': 0.0009, 'learning_rate': 5.6688888888888895e-06, 'epoch': 10.38} {'loss': 0.0008, 'learning_rate': 5.613333333333334e-06, 'epoch': 10.49} {'loss': 0.0008, 'learning_rate': 5.557777777777778e-06, 'epoch': 10.59} {'loss': 0.0008, 'learning_rate': 5.5022222222222224e-06, 'epoch': 10.7} {'loss': 0.0012, 'learning_rate': 5.4466666666666665e-06, 'epoch': 10.81} {'loss': 0.0006, 'learning_rate': 5.391111111111111e-06, 'epoch': 10.91} {'loss': 0.0006, 'learning_rate': 5.335555555555556e-06, 'epoch': 11.02} {'loss': 0.0008, 'learning_rate': 5.28e-06, 'epoch': 11.12} {'loss': 0.0005, 'learning_rate': 5.224444444444445e-06, 'epoch': 11.23} {'loss': 0.0005, 'learning_rate': 5.168888888888889e-06, 'epoch': 11.33} {'loss': 0.0005, 'learning_rate': 5.113333333333333e-06, 'epoch': 11.44} {'loss': 0.0005, 'learning_rate': 5.057777777777778e-06, 'epoch': 11.55} {'loss': 0.0005, 'learning_rate': 5.002222222222223e-06, 'epoch': 11.65} {'loss': 0.0005, 'learning_rate': 4.946666666666667e-06, 'epoch': 11.76} {'loss': 0.0006, 'learning_rate': 4.891111111111111e-06, 'epoch': 11.86} {'loss': 0.0005, 'learning_rate': 4.835555555555556e-06, 'epoch': 11.97} {'loss': 0.0004, 'learning_rate': 4.78e-06, 'epoch': 12.08} {'loss': 0.0004, 'learning_rate': 4.724444444444445e-06, 'epoch': 12.18} {'loss': 0.0004, 'learning_rate': 4.66888888888889e-06, 'epoch': 12.29} {'loss': 0.0004, 'learning_rate': 4.613333333333334e-06, 'epoch': 12.39} {'loss': 0.0004, 'learning_rate': 4.557777777777778e-06, 'epoch': 12.5} {'loss': 0.0004, 'learning_rate': 4.502222222222223e-06, 'epoch': 12.61} {'loss': 0.0004, 'learning_rate': 4.446666666666667e-06, 'epoch': 12.71} {'eval_loss': 0.230974942445755, 'eval_wer': 11.454669343106021, 'eval_runtime': 9689.0706, 'eval_samples_per_second': 0.796, 'eval_steps_per_second': 0.025, 'epoch': 12.71} {'loss': 0.0005, 'learning_rate': 4.391111111111112e-06, 'epoch': 12.82} {'loss': 0.0004, 'learning_rate': 4.3355555555555565e-06, 'epoch': 12.92} {'loss': 0.0004, 'learning_rate': 4.2800000000000005e-06, 'epoch': 13.03} {'loss': 0.0004, 'learning_rate': 4.2244444444444446e-06, 'epoch': 13.14} {'loss': 0.0004, 'learning_rate': 4.168888888888889e-06, 'epoch': 13.24} {'loss': 0.0003, 'learning_rate': 4.1133333333333335e-06, 'epoch': 13.35} {'loss': 0.0003, 'learning_rate': 4.057777777777778e-06, 'epoch': 13.45} {'loss': 0.0004, 'learning_rate': 4.002222222222222e-06, 'epoch': 13.56} {'loss': 0.0003, 'learning_rate': 3.946666666666667e-06, 'epoch': 13.67} {'loss': 0.0003, 'learning_rate': 3.891111111111111e-06, 'epoch': 13.77} {'loss': 0.0003, 'learning_rate': 3.835555555555555e-06, 'epoch': 13.88} {'loss': 0.0003, 'learning_rate': 3.7800000000000002e-06, 'epoch': 13.98} {'loss': 0.0003, 'learning_rate': 3.724444444444445e-06, 'epoch': 14.09} {'loss': 0.0003, 'learning_rate': 3.668888888888889e-06, 'epoch': 14.19} {'loss': 0.0003, 'learning_rate': 3.6133333333333336e-06, 'epoch': 14.3} {'loss': 0.0003, 'learning_rate': 3.5577777777777785e-06, 'epoch': 14.41} {'loss': 0.0003, 'learning_rate': 3.5022222222222225e-06, 'epoch': 14.51} {'loss': 0.0003, 'learning_rate': 3.446666666666667e-06, 'epoch': 14.62} {'loss': 0.0003, 'learning_rate': 3.391111111111111e-06, 'epoch': 14.72} {'loss': 0.0003, 'learning_rate': 3.335555555555556e-06, 'epoch': 14.83} {'loss': 0.0003, 'learning_rate': 3.2800000000000004e-06, 'epoch': 14.94} {'loss': 0.0003, 'learning_rate': 3.2244444444444444e-06, 'epoch': 15.04} {'loss': 0.0003, 'learning_rate': 3.1688888888888893e-06, 'epoch': 15.15} {'loss': 0.0003, 'learning_rate': 3.1133333333333337e-06, 'epoch': 15.25} {'loss': 0.0003, 'learning_rate': 3.0577777777777778e-06, 'epoch': 15.36} {'loss': 0.0003, 'learning_rate': 3.0022222222222227e-06, 'epoch': 15.47} {'loss': 0.0003, 'learning_rate': 2.946666666666667e-06, 'epoch': 15.57} {'loss': 0.0003, 'learning_rate': 2.891111111111111e-06, 'epoch': 15.68} {'loss': 0.0003, 'learning_rate': 2.835555555555556e-06, 'epoch': 15.78} {'loss': 0.0003, 'learning_rate': 2.7800000000000005e-06, 'epoch': 15.89} {'loss': 0.0003, 'learning_rate': 2.7244444444444445e-06, 'epoch': 16.0} {'loss': 0.0003, 'learning_rate': 2.6688888888888894e-06, 'epoch': 16.1} {'loss': 0.0003, 'learning_rate': 2.6133333333333334e-06, 'epoch': 16.21} {'loss': 0.0003, 'learning_rate': 2.557777777777778e-06, 'epoch': 16.31} {'loss': 0.0003, 'learning_rate': 2.5022222222222224e-06, 'epoch': 16.42} {'loss': 0.0003, 'learning_rate': 2.446666666666667e-06, 'epoch': 16.53} {'loss': 0.0002, 'learning_rate': 2.3911111111111113e-06, 'epoch': 16.63} {'loss': 0.0002, 'learning_rate': 2.3355555555555557e-06, 'epoch': 16.74} {'loss': 0.0003, 'learning_rate': 2.28e-06, 'epoch': 16.84} {'loss': 0.0003, 'learning_rate': 2.2244444444444447e-06, 'epoch': 16.95} {'eval_loss': 0.23803874850273132, 'eval_wer': 11.427045542439366, 'eval_runtime': 8967.4245, 'eval_samples_per_second': 0.86, 'eval_steps_per_second': 0.027, 'epoch': 16.95} {'loss': 0.0002, 'learning_rate': 2.168888888888889e-06, 'epoch': 17.06} {'loss': 0.0002, 'learning_rate': 2.1133333333333336e-06, 'epoch': 17.16} {'loss': 0.0002, 'learning_rate': 2.057777777777778e-06, 'epoch': 17.27} {'loss': 0.0002, 'learning_rate': 2.0022222222222225e-06, 'epoch': 17.37} {'loss': 0.0002, 'learning_rate': 1.9466666666666665e-06, 'epoch': 17.48} {'loss': 0.0002, 'learning_rate': 1.8911111111111114e-06, 'epoch': 17.58} {'loss': 0.0002, 'learning_rate': 1.8355555555555557e-06, 'epoch': 17.69} {'loss': 0.0002, 'learning_rate': 1.7800000000000001e-06, 'epoch': 17.8} {'loss': 0.0002, 'learning_rate': 1.7244444444444448e-06, 'epoch': 17.9} {'loss': 0.0002, 'learning_rate': 1.668888888888889e-06, 'epoch': 18.01} {'loss': 0.0002, 'learning_rate': 1.6133333333333335e-06, 'epoch': 18.11} {'loss': 0.0002, 'learning_rate': 1.5577777777777777e-06, 'epoch': 18.22} {'loss': 0.0002, 'learning_rate': 1.5022222222222224e-06, 'epoch': 18.33} {'loss': 0.0002, 'learning_rate': 1.4466666666666669e-06, 'epoch': 18.43} {'loss': 0.0002, 'learning_rate': 1.3911111111111111e-06, 'epoch': 18.54} {'loss': 0.0002, 'learning_rate': 1.3355555555555558e-06, 'epoch': 18.64} {'loss': 0.0002, 'learning_rate': 1.28e-06, 'epoch': 18.75} {'loss': 0.0002, 'learning_rate': 1.2244444444444445e-06, 'epoch': 18.86} {'loss': 0.0002, 'learning_rate': 1.168888888888889e-06, 'epoch': 18.96} {'loss': 0.0002, 'learning_rate': 1.1133333333333334e-06, 'epoch': 19.07} {'loss': 0.0002, 'learning_rate': 1.0577777777777779e-06, 'epoch': 19.17} {'loss': 0.0002, 'learning_rate': 1.0022222222222223e-06, 'epoch': 19.28} {'loss': 0.0002, 'learning_rate': 9.466666666666667e-07, 'epoch': 19.39} {'loss': 0.0002, 'learning_rate': 8.911111111111112e-07, 'epoch': 19.49} {'loss': 0.0002, 'learning_rate': 8.355555555555556e-07, 'epoch': 19.6} {'loss': 0.0002, 'learning_rate': 7.8e-07, 'epoch': 19.7} {'loss': 0.0002, 'learning_rate': 7.244444444444446e-07, 'epoch': 19.81} {'loss': 0.0002, 'learning_rate': 6.68888888888889e-07, 'epoch': 19.92} {'loss': 0.0002, 'learning_rate': 6.133333333333333e-07, 'epoch': 20.02} {'loss': 0.0002, 'learning_rate': 5.577777777777779e-07, 'epoch': 20.13} {'loss': 0.0002, 'learning_rate': 5.022222222222222e-07, 'epoch': 20.23} {'loss': 0.0002, 'learning_rate': 4.466666666666667e-07, 'epoch': 20.34} {'loss': 0.0002, 'learning_rate': 3.9111111111111115e-07, 'epoch': 20.44} {'loss': 0.0002, 'learning_rate': 3.3555555555555556e-07, 'epoch': 20.55} {'loss': 0.0002, 'learning_rate': 2.8e-07, 'epoch': 20.66} {'loss': 0.0002, 'learning_rate': 2.2444444444444445e-07, 'epoch': 20.76} {'loss': 0.0002, 'learning_rate': 1.6888888888888888e-07, 'epoch': 20.87} {'loss': 0.0002, 'learning_rate': 1.1333333333333336e-07, 'epoch': 20.97} {'loss': 0.0002, 'learning_rate': 5.777777777777778e-08, 'epoch': 21.08} {'loss': 0.0002, 'learning_rate': 2.2222222222222225e-09, 'epoch': 21.19} {'eval_loss': 0.24174600839614868, 'eval_wer': 11.408629675328264, 'eval_runtime': 9721.5421, 'eval_samples_per_second': 0.793, 'eval_steps_per_second': 0.025, 'epoch': 21.19} {'train_runtime': 142520.4283, 'train_samples_per_second': 2.245, 'train_steps_per_second': 0.035, 'train_loss': 0.026235109101515264, 'epoch': 21.19} 12/13/2022 09:40:58 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream. 12/13/2022 09:40:58 - WARNING - huggingface_hub.repository - The progress bars may be unreliable. 12/13/2022 09:52:06 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow... remote: LFS file scan complete. To https://huggingface.co/mikr/whisper-medium-czech-cv11 379048f..ae9f79e main -> main 12/13/2022 09:52:13 - WARNING - huggingface_hub.repository - To https://huggingface.co/mikr/whisper-medium-czech-cv11 ae9f79e..faaba36 main -> main ***** train metrics ***** epoch = 21.19 train_loss = 0.0262 train_runtime = 1 day, 15:35:20.42 train_samples_per_second = 2.245 train_steps_per_second = 0.035 12/13/2022 09:52:16 - INFO - __main__ - *** Evaluate *** ***** eval metrics ***** epoch = 21.19 eval_loss = 0.2417 eval_runtime = 2:48:44.26 eval_samples_per_second = 0.762 eval_steps_per_second = 0.024 eval_wer = 11.4086 12/13/2022 12:41:56 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow... remote: LFS file scan complete. To https://huggingface.co/mikr/whisper-medium-czech-cv11 faaba36..24bd50e main -> main