12/15/2022 10:25:46 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
12/15/2022 10:25:46 - 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=1,
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=<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/Dec15_10-25-46_129-146-123-136,
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=64,
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=<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,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=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,
)
12/15/2022 10:25:46 - 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=1,
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=<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/Dec15_10-25-46_129-146-123-136,
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=64,
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=<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,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=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,
)
12/15/2022 10:25:47 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/common_voice_11_0.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpk7m0wk0t
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/common_voice_11_0.py in cache at /home/milan/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/README.md not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpndi89gdx
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/README.md in cache at /home/milan/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/languages.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpcpyilpcc
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/languages.py in cache at /home/milan/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/release_stats.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpck8q1rvs
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/release_stats.py in cache at /home/milan/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
12/15/2022 10:25:49 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/15/2022 10:25:52 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/15/2022 10:26:14 - WARNING - huggingface_hub.repository - /home/milan/whisper-small-cs-sk-cv11/./ is already a clone of https://huggingface.co/mikr/whisper-small-cs-sk-cv11. Make sure you pull the latest changes with `repo.git_pull()`.
{'loss': 2.6504, 'learning_rate': 4.2000000000000006e-07, 'epoch': 0.01}
{'loss': 1.9914, 'learning_rate': 9.200000000000001e-07, 'epoch': 1.0}
{'loss': 1.0697, 'learning_rate': 1.42e-06, 'epoch': 1.01}
{'loss': 0.7023, 'learning_rate': 1.9200000000000003e-06, 'epoch': 2.0}
{'loss': 0.5324, 'learning_rate': 2.42e-06, 'epoch': 2.01}
{'loss': 0.45, 'learning_rate': 2.92e-06, 'epoch': 3.0}
12/15/2022 10:50:26 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
{'loss': 0.338, 'learning_rate': 3.4200000000000007e-06, 'epoch': 3.01}
{'loss': 0.2858, 'learning_rate': 3.920000000000001e-06, 'epoch': 4.0}
{'loss': 0.2132, 'learning_rate': 4.42e-06, 'epoch': 4.01}
{'loss': 0.1557, 'learning_rate': 4.92e-06, 'epoch': 5.0}
{'loss': 0.1146, 'learning_rate': 5.420000000000001e-06, 'epoch': 5.01}
{'loss': 0.0738, 'learning_rate': 5.92e-06, 'epoch': 6.0}
{'loss': 0.0512, 'learning_rate': 6.42e-06, 'epoch': 6.01}
{'loss': 0.0324, 'learning_rate': 6.92e-06, 'epoch': 7.0}
{'loss': 0.0261, 'learning_rate': 7.420000000000001e-06, 'epoch': 7.01}
{'loss': 0.0188, 'learning_rate': 7.92e-06, 'epoch': 8.0}
{'loss': 0.0163, 'learning_rate': 8.42e-06, 'epoch': 9.0}
{'loss': 0.0139, 'learning_rate': 8.920000000000001e-06, 'epoch': 9.01}
{'loss': 0.0106, 'learning_rate': 9.42e-06, 'epoch': 10.0}
{'loss': 0.0106, 'learning_rate': 9.920000000000002e-06, 'epoch': 10.01}
{'loss': 0.0105, 'learning_rate': 9.953333333333333e-06, 'epoch': 11.0}
{'loss': 0.0101, 'learning_rate': 9.89777777777778e-06, 'epoch': 11.01}
{'loss': 0.0072, 'learning_rate': 9.842222222222223e-06, 'epoch': 12.0}
{'loss': 0.008, 'learning_rate': 9.786666666666667e-06, 'epoch': 12.01}
{'loss': 0.0057, 'learning_rate': 9.731111111111113e-06, 'epoch': 13.0}
{'loss': 0.0063, 'learning_rate': 9.675555555555555e-06, 'epoch': 13.01}
{'loss': 0.0035, 'learning_rate': 9.620000000000001e-06, 'epoch': 14.0}
{'loss': 0.0038, 'learning_rate': 9.564444444444445e-06, 'epoch': 14.01}
{'loss': 0.0054, 'learning_rate': 9.508888888888889e-06, 'epoch': 15.0}
{'loss': 0.0042, 'learning_rate': 9.453333333333335e-06, 'epoch': 15.01}
{'loss': 0.0035, 'learning_rate': 9.397777777777779e-06, 'epoch': 16.0}
{'loss': 0.0034, 'learning_rate': 9.342222222222223e-06, 'epoch': 17.0}
{'loss': 0.0032, 'learning_rate': 9.286666666666667e-06, 'epoch': 17.01}
{'loss': 0.0027, 'learning_rate': 9.231111111111111e-06, 'epoch': 18.0}
{'loss': 0.0018, 'learning_rate': 9.175555555555557e-06, 'epoch': 18.01}
{'loss': 0.0017, 'learning_rate': 9.12e-06, 'epoch': 19.0}
{'loss': 0.0022, 'learning_rate': 9.064444444444447e-06, 'epoch': 19.01}
{'loss': 0.0018, 'learning_rate': 9.008888888888889e-06, 'epoch': 20.0}
{'loss': 0.0013, 'learning_rate': 8.953333333333335e-06, 'epoch': 20.01}
{'loss': 0.001, 'learning_rate': 8.897777777777779e-06, 'epoch': 21.0}
{'eval_loss': 0.6506679058074951, 'eval_wer': 37.32746311280343, 'eval_runtime': 812.1587, 'eval_samples_per_second': 2.791, 'eval_steps_per_second': 0.087, 'epoch': 21.0}
{'loss': 0.001, 'learning_rate': 8.842222222222223e-06, 'epoch': 21.01}
{'loss': 0.0009, 'learning_rate': 8.786666666666668e-06, 'epoch': 22.0}
{'loss': 0.0008, 'learning_rate': 8.73111111111111e-06, 'epoch': 22.01}
{'loss': 0.0008, 'learning_rate': 8.675555555555556e-06, 'epoch': 23.0}
{'loss': 0.0007, 'learning_rate': 8.62e-06, 'epoch': 23.01}
{'loss': 0.0007, 'learning_rate': 8.564444444444445e-06, 'epoch': 24.0}
{'loss': 0.0006, 'learning_rate': 8.50888888888889e-06, 'epoch': 24.01}
{'loss': 0.0006, 'learning_rate': 8.453333333333334e-06, 'epoch': 25.0}
{'loss': 0.0006, 'learning_rate': 8.397777777777778e-06, 'epoch': 26.0}
{'loss': 0.0006, 'learning_rate': 8.342222222222222e-06, 'epoch': 26.01}
{'loss': 0.0006, 'learning_rate': 8.286666666666668e-06, 'epoch': 27.0}
{'loss': 0.0005, 'learning_rate': 8.231111111111112e-06, 'epoch': 27.01}
{'loss': 0.0005, 'learning_rate': 8.175555555555556e-06, 'epoch': 28.0}
{'loss': 0.0005, 'learning_rate': 8.120000000000002e-06, 'epoch': 28.01}
{'loss': 0.0005, 'learning_rate': 8.064444444444444e-06, 'epoch': 29.0}
{'loss': 0.0005, 'learning_rate': 8.00888888888889e-06, 'epoch': 29.01}
{'loss': 0.0005, 'learning_rate': 7.953333333333334e-06, 'epoch': 30.0}
{'loss': 0.0005, 'learning_rate': 7.897777777777778e-06, 'epoch': 30.01}
{'loss': 0.0004, 'learning_rate': 7.842222222222224e-06, 'epoch': 31.0}
{'loss': 0.0004, 'learning_rate': 7.786666666666666e-06, 'epoch': 31.01}
{'loss': 0.0004, 'learning_rate': 7.731111111111112e-06, 'epoch': 32.0}
{'loss': 0.0004, 'learning_rate': 7.675555555555556e-06, 'epoch': 32.01}
{'loss': 0.0004, 'learning_rate': 7.620000000000001e-06, 'epoch': 33.0}
{'loss': 0.0004, 'learning_rate': 7.564444444444446e-06, 'epoch': 34.0}
{'loss': 0.0004, 'learning_rate': 7.50888888888889e-06, 'epoch': 34.01}
{'loss': 0.0004, 'learning_rate': 7.453333333333334e-06, 'epoch': 35.0}
{'loss': 0.0004, 'learning_rate': 7.3977777777777786e-06, 'epoch': 35.01}
{'loss': 0.0004, 'learning_rate': 7.342222222222223e-06, 'epoch': 36.0}
{'loss': 0.0004, 'learning_rate': 7.2866666666666675e-06, 'epoch': 36.01}
{'loss': 0.0003, 'learning_rate': 7.231111111111112e-06, 'epoch': 37.0}
{'loss': 0.0003, 'learning_rate': 7.1755555555555556e-06, 'epoch': 37.01}
{'loss': 0.0003, 'learning_rate': 7.1200000000000004e-06, 'epoch': 38.0}
{'loss': 0.0003, 'learning_rate': 7.0644444444444445e-06, 'epoch': 38.01}
{'loss': 0.0003, 'learning_rate': 7.008888888888889e-06, 'epoch': 39.0}
{'loss': 0.0003, 'learning_rate': 6.953333333333334e-06, 'epoch': 39.01}
{'loss': 0.0003, 'learning_rate': 6.897777777777779e-06, 'epoch': 40.0}
{'loss': 0.0003, 'learning_rate': 6.842222222222222e-06, 'epoch': 40.01}
{'loss': 0.0003, 'learning_rate': 6.786666666666667e-06, 'epoch': 41.0}
{'loss': 0.0003, 'learning_rate': 6.731111111111111e-06, 'epoch': 42.0}
{'loss': 0.0003, 'learning_rate': 6.675555555555556e-06, 'epoch': 42.01}
{'eval_loss': 0.695440948009491, 'eval_wer': 36.11375535459305, 'eval_runtime': 776.4908, 'eval_samples_per_second': 2.92, 'eval_steps_per_second': 0.091, 'epoch': 42.01}
{'loss': 0.0003, 'learning_rate': 6.620000000000001e-06, 'epoch': 43.0}
{'loss': 0.0003, 'learning_rate': 6.564444444444446e-06, 'epoch': 43.01}
{'loss': 0.0003, 'learning_rate': 6.508888888888889e-06, 'epoch': 44.0}
{'loss': 0.0003, 'learning_rate': 6.453333333333334e-06, 'epoch': 44.01}
{'loss': 0.0003, 'learning_rate': 6.397777777777778e-06, 'epoch': 45.0}
{'loss': 0.0003, 'learning_rate': 6.342222222222223e-06, 'epoch': 45.01}
{'loss': 0.0003, 'learning_rate': 6.286666666666668e-06, 'epoch': 46.0}
{'loss': 0.0002, 'learning_rate': 6.231111111111111e-06, 'epoch': 46.01}
{'loss': 0.0002, 'learning_rate': 6.175555555555556e-06, 'epoch': 47.0}
{'loss': 0.0002, 'learning_rate': 6.120000000000001e-06, 'epoch': 47.01}
{'loss': 0.0002, 'learning_rate': 6.064444444444445e-06, 'epoch': 48.0}
{'loss': 0.0002, 'learning_rate': 6.00888888888889e-06, 'epoch': 48.01}
{'loss': 0.0002, 'learning_rate': 5.9533333333333345e-06, 'epoch': 49.0}
{'loss': 0.0002, 'learning_rate': 5.897777777777778e-06, 'epoch': 49.01}
{'loss': 0.0002, 'learning_rate': 5.8422222222222226e-06, 'epoch': 50.01}
{'loss': 0.0002, 'learning_rate': 5.7866666666666674e-06, 'epoch': 51.0}
{'loss': 0.0002, 'learning_rate': 5.7311111111111115e-06, 'epoch': 51.01}
{'loss': 0.0002, 'learning_rate': 5.675555555555556e-06, 'epoch': 52.0}
{'loss': 0.0002, 'learning_rate': 5.620000000000001e-06, 'epoch': 52.01}
{'loss': 0.0002, 'learning_rate': 5.5644444444444444e-06, 'epoch': 53.0}
{'loss': 0.0002, 'learning_rate': 5.508888888888889e-06, 'epoch': 53.01}
{'loss': 0.0002, 'learning_rate': 5.453333333333334e-06, 'epoch': 54.0}
{'loss': 0.0002, 'learning_rate': 5.397777777777778e-06, 'epoch': 54.01}
{'loss': 0.0002, 'learning_rate': 5.342222222222223e-06, 'epoch': 55.0}
{'loss': 0.0002, 'learning_rate': 5.286666666666666e-06, 'epoch': 55.01}
{'loss': 0.0002, 'learning_rate': 5.231111111111111e-06, 'epoch': 56.0}
{'loss': 0.0002, 'learning_rate': 5.175555555555556e-06, 'epoch': 56.01}
{'loss': 0.0002, 'learning_rate': 5.12e-06, 'epoch': 57.0}
{'loss': 0.0002, 'learning_rate': 5.064444444444445e-06, 'epoch': 57.01}
{'loss': 0.0002, 'learning_rate': 5.00888888888889e-06, 'epoch': 58.0}
{'loss': 0.0002, 'learning_rate': 4.953333333333334e-06, 'epoch': 59.0}
{'loss': 0.0002, 'learning_rate': 4.897777777777778e-06, 'epoch': 59.01}
{'loss': 0.0002, 'learning_rate': 4.842222222222223e-06, 'epoch': 60.0}
{'loss': 0.0002, 'learning_rate': 4.786666666666667e-06, 'epoch': 60.01}
{'loss': 0.0002, 'learning_rate': 4.731111111111112e-06, 'epoch': 61.0}
{'loss': 0.0002, 'learning_rate': 4.675555555555556e-06, 'epoch': 61.01}
{'loss': 0.0002, 'learning_rate': 4.620000000000001e-06, 'epoch': 62.0}
{'loss': 0.0002, 'learning_rate': 4.564444444444445e-06, 'epoch': 62.01}
{'loss': 0.0002, 'learning_rate': 4.50888888888889e-06, 'epoch': 63.0}
{'loss': 0.0002, 'learning_rate': 4.453333333333334e-06, 'epoch': 63.01}
12/15/2022 18:02:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
12/15/2022 18:02:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [2/20]
12/15/2022 18:02:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [3/20]
12/15/2022 18:02:53 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [4/20]
12/15/2022 18:03:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [5/20]
12/15/2022 18:03:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [6/20]
12/15/2022 18:03:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [7/20]
12/15/2022 18:03:53 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [8/20]
12/15/2022 18:04:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [9/20]
12/15/2022 18:04:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [10/20]
12/15/2022 18:04:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [11/20]
12/15/2022 18:04:43 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [12/20]
{'eval_loss': 0.7222780585289001, 'eval_wer': 35.43550690147549, 'eval_runtime': 913.8875, 'eval_samples_per_second': 2.481, 'eval_steps_per_second': 0.078, 'epoch': 63.01}
{'loss': 0.0002, 'learning_rate': 4.397777777777778e-06, 'epoch': 64.0}
{'loss': 0.0002, 'learning_rate': 4.3422222222222225e-06, 'epoch': 64.01}
{'loss': 0.0002, 'learning_rate': 4.2866666666666666e-06, 'epoch': 65.0}
{'loss': 0.0002, 'learning_rate': 4.2311111111111114e-06, 'epoch': 65.01}
{'loss': 0.0002, 'learning_rate': 4.175555555555556e-06, 'epoch': 66.0}
{'loss': 0.0002, 'learning_rate': 4.12e-06, 'epoch': 67.0}
{'loss': 0.0002, 'learning_rate': 4.064444444444444e-06, 'epoch': 67.01}
{'loss': 0.0001, 'learning_rate': 4.008888888888889e-06, 'epoch': 68.0}
{'loss': 0.0001, 'learning_rate': 3.953333333333333e-06, 'epoch': 68.01}
{'loss': 0.0001, 'learning_rate': 3.897777777777778e-06, 'epoch': 69.0}
{'loss': 0.0001, 'learning_rate': 3.842222222222223e-06, 'epoch': 69.01}
{'loss': 0.0001, 'learning_rate': 3.7866666666666667e-06, 'epoch': 70.0}
{'loss': 0.0001, 'learning_rate': 3.7311111111111116e-06, 'epoch': 70.01}
{'loss': 0.0001, 'learning_rate': 3.675555555555556e-06, 'epoch': 71.0}
{'loss': 0.0001, 'learning_rate': 3.62e-06, 'epoch': 71.01}
{'loss': 0.0001, 'learning_rate': 3.564444444444445e-06, 'epoch': 72.0}
{'loss': 0.0001, 'learning_rate': 3.508888888888889e-06, 'epoch': 72.01}
{'loss': 0.0001, 'learning_rate': 3.4533333333333334e-06, 'epoch': 73.0}
{'loss': 0.0001, 'learning_rate': 3.3977777777777783e-06, 'epoch': 73.01}
{'loss': 0.0001, 'learning_rate': 3.3422222222222224e-06, 'epoch': 74.0}
{'loss': 0.0001, 'learning_rate': 3.286666666666667e-06, 'epoch': 74.01}
{'loss': 0.0001, 'learning_rate': 3.2311111111111117e-06, 'epoch': 75.0}
{'loss': 0.0001, 'learning_rate': 3.1755555555555557e-06, 'epoch': 76.0}
{'loss': 0.0001, 'learning_rate': 3.12e-06, 'epoch': 76.01}
{'loss': 0.0001, 'learning_rate': 3.064444444444445e-06, 'epoch': 77.0}
{'loss': 0.0001, 'learning_rate': 3.008888888888889e-06, 'epoch': 77.01}
{'loss': 0.0001, 'learning_rate': 2.9533333333333336e-06, 'epoch': 78.0}
{'loss': 0.0001, 'learning_rate': 2.8977777777777785e-06, 'epoch': 78.01}
{'loss': 0.0001, 'learning_rate': 2.8422222222222225e-06, 'epoch': 79.0}
{'loss': 0.0001, 'learning_rate': 2.786666666666667e-06, 'epoch': 79.01}
{'loss': 0.0001, 'learning_rate': 2.7311111111111114e-06, 'epoch': 80.0}
{'loss': 0.0001, 'learning_rate': 2.675555555555556e-06, 'epoch': 80.01}
{'loss': 0.0001, 'learning_rate': 2.6200000000000003e-06, 'epoch': 81.0}
{'loss': 0.0001, 'learning_rate': 2.5644444444444444e-06, 'epoch': 81.01}
{'loss': 0.0001, 'learning_rate': 2.5088888888888892e-06, 'epoch': 82.0}
{'loss': 0.0001, 'learning_rate': 2.4533333333333333e-06, 'epoch': 82.01}
{'loss': 0.0001, 'learning_rate': 2.397777777777778e-06, 'epoch': 83.0}
{'loss': 0.0001, 'learning_rate': 2.342222222222222e-06, 'epoch': 84.0}
{'loss': 0.0001, 'learning_rate': 2.2866666666666667e-06, 'epoch': 84.01}
{'loss': 0.0001, 'learning_rate': 2.2311111111111115e-06, 'epoch': 85.0}