|
12/14/2022 23:13:58 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True |
|
12/14/2022 23:13:58 - 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/Dec14_23-13-58_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, |
|
) |
|
12/14/2022 23:13:58 - 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/Dec14_23-13-58_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, |
|
) |
|
12/14/2022 23:13:59 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 |
|
12/14/2022 23:14:01 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 |
|
12/14/2022 23:14:02 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 |
|
12/14/2022 23:14:09 - WARNING - huggingface_hub.repository - /home/milan/whisper-small-hr-vox/./ is already a clone of https://huggingface.co/mikr/whisper-small-hr-vox. Make sure you pull the latest changes with `repo.git_pull()`. |
|
{'loss': 1.4901, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.01} |
|
{'loss': 1.2499, 'learning_rate': 9.800000000000001e-07, 'epoch': 1.0} |
|
{'loss': 1.0153, 'learning_rate': 1.48e-06, 'epoch': 1.01} |
|
{'loss': 0.8027, 'learning_rate': 1.98e-06, 'epoch': 2.0} |
|
{'loss': 0.6815, 'learning_rate': 2.4800000000000004e-06, 'epoch': 3.0} |
|
{'loss': 0.5597, 'learning_rate': 2.9800000000000003e-06, 'epoch': 3.01} |
|
{'loss': 0.4858, 'learning_rate': 3.48e-06, 'epoch': 4.0} |
|
{'loss': 0.4395, 'learning_rate': 3.980000000000001e-06, 'epoch': 4.01} |
|
{'loss': 0.37, 'learning_rate': 4.48e-06, 'epoch': 5.0} |
|
{'loss': 0.3308, 'learning_rate': 4.980000000000001e-06, 'epoch': 6.0} |
|
{'loss': 0.2814, 'learning_rate': 5.480000000000001e-06, 'epoch': 6.01} |
|
{'loss': 0.2378, 'learning_rate': 5.98e-06, 'epoch': 7.0} |
|
{'loss': 0.2064, 'learning_rate': 6.480000000000001e-06, 'epoch': 8.0} |
|
{'loss': 0.1689, 'learning_rate': 6.98e-06, 'epoch': 8.01} |
|
{'loss': 0.1391, 'learning_rate': 7.48e-06, 'epoch': 9.0} |
|
{'loss': 0.1139, 'learning_rate': 7.980000000000002e-06, 'epoch': 9.01} |
|
{'loss': 0.0882, 'learning_rate': 8.48e-06, 'epoch': 10.01} |
|
{'loss': 0.0764, 'learning_rate': 8.98e-06, 'epoch': 11.0} |
|
{'loss': 0.0609, 'learning_rate': 9.48e-06, 'epoch': 11.01} |
|
{'loss': 0.0437, 'learning_rate': 9.980000000000001e-06, 'epoch': 12.0} |
|
{'loss': 0.0433, 'learning_rate': 9.946666666666667e-06, 'epoch': 13.0} |
|
{'loss': 0.0334, 'learning_rate': 9.891111111111113e-06, 'epoch': 13.01} |
|
{'loss': 0.0249, 'learning_rate': 9.835555555555556e-06, 'epoch': 14.0} |
|
{'loss': 0.0228, 'learning_rate': 9.780000000000001e-06, 'epoch': 14.01} |
|
{'loss': 0.0153, 'learning_rate': 9.724444444444445e-06, 'epoch': 15.01} |
|
{'loss': 0.0147, 'learning_rate': 9.66888888888889e-06, 'epoch': 16.0} |
|
{'loss': 0.013, 'learning_rate': 9.613333333333335e-06, 'epoch': 16.01} |
|
{'loss': 0.0109, 'learning_rate': 9.557777777777777e-06, 'epoch': 17.0} |
|
{'loss': 0.0081, 'learning_rate': 9.502222222222223e-06, 'epoch': 18.0} |
|
{'loss': 0.0082, 'learning_rate': 9.446666666666667e-06, 'epoch': 18.01} |
|
{'loss': 0.006, 'learning_rate': 9.391111111111111e-06, 'epoch': 19.0} |
|
{'loss': 0.0056, 'learning_rate': 9.335555555555557e-06, 'epoch': 19.01} |
|
{'loss': 0.0049, 'learning_rate': 9.280000000000001e-06, 'epoch': 20.0} |
|
{'loss': 0.0043, 'learning_rate': 9.224444444444445e-06, 'epoch': 21.0} |
|
{'loss': 0.0038, 'learning_rate': 9.168888888888889e-06, 'epoch': 21.01} |
|
{'loss': 0.004, 'learning_rate': 9.113333333333335e-06, 'epoch': 22.0} |
|
{'loss': 0.0041, 'learning_rate': 9.057777777777779e-06, 'epoch': 23.0} |
|
{'loss': 0.004, 'learning_rate': 9.002222222222223e-06, 'epoch': 23.01} |
|
{'loss': 0.003, 'learning_rate': 8.946666666666669e-06, 'epoch': 24.0} |
|
{'loss': 0.0028, 'learning_rate': 8.891111111111111e-06, 'epoch': 24.01} |
|
{'eval_loss': 0.5302625894546509, 'eval_wer': 26.17524963536407, 'eval_runtime': 722.0594, 'eval_samples_per_second': 0.922, 'eval_steps_per_second': 0.029, 'epoch': 24.01} |
|
{'loss': 0.0025, 'learning_rate': 8.835555555555557e-06, 'epoch': 25.0} |
|
{'loss': 0.0022, 'learning_rate': 8.78e-06, 'epoch': 26.0} |
|
{'loss': 0.002, 'learning_rate': 8.724444444444445e-06, 'epoch': 26.01} |
|
{'loss': 0.0021, 'learning_rate': 8.66888888888889e-06, 'epoch': 27.0} |
|
{'loss': 0.0018, 'learning_rate': 8.613333333333333e-06, 'epoch': 28.0} |
|
{'loss': 0.0017, 'learning_rate': 8.557777777777778e-06, 'epoch': 28.01} |
|
{'loss': 0.0016, 'learning_rate': 8.502222222222223e-06, 'epoch': 29.0} |
|
{'loss': 0.0015, 'learning_rate': 8.446666666666668e-06, 'epoch': 29.01} |
|
{'loss': 0.0014, 'learning_rate': 8.391111111111112e-06, 'epoch': 30.0} |
|
{'loss': 0.0014, 'learning_rate': 8.335555555555556e-06, 'epoch': 31.0} |
|
{'loss': 0.0013, 'learning_rate': 8.28e-06, 'epoch': 31.01} |
|
{'loss': 0.0013, 'learning_rate': 8.224444444444444e-06, 'epoch': 32.0} |
|
{'loss': 0.0012, 'learning_rate': 8.16888888888889e-06, 'epoch': 33.0} |
|
{'loss': 0.0012, 'learning_rate': 8.113333333333334e-06, 'epoch': 33.01} |
|
{'loss': 0.0011, 'learning_rate': 8.057777777777778e-06, 'epoch': 34.0} |
|
{'loss': 0.0011, 'learning_rate': 8.002222222222222e-06, 'epoch': 34.01} |
|
{'loss': 0.0011, 'learning_rate': 7.946666666666666e-06, 'epoch': 35.01} |
|
{'loss': 0.001, 'learning_rate': 7.891111111111112e-06, 'epoch': 36.0} |
|
{'loss': 0.001, 'learning_rate': 7.835555555555556e-06, 'epoch': 36.01} |
|
{'loss': 0.001, 'learning_rate': 7.78e-06, 'epoch': 37.0} |
|
{'loss': 0.0009, 'learning_rate': 7.724444444444446e-06, 'epoch': 38.0} |
|
{'loss': 0.0009, 'learning_rate': 7.66888888888889e-06, 'epoch': 38.01} |
|
{'loss': 0.0009, 'learning_rate': 7.613333333333334e-06, 'epoch': 39.0} |
|
{'loss': 0.0009, 'learning_rate': 7.557777777777779e-06, 'epoch': 39.01} |
|
{'loss': 0.0008, 'learning_rate': 7.502222222222223e-06, 'epoch': 40.01} |
|
{'loss': 0.0008, 'learning_rate': 7.446666666666668e-06, 'epoch': 41.0} |
|
{'loss': 0.0008, 'learning_rate': 7.3911111111111125e-06, 'epoch': 41.01} |
|
{'loss': 0.0008, 'learning_rate': 7.335555555555556e-06, 'epoch': 42.0} |
|
{'loss': 0.0008, 'learning_rate': 7.280000000000001e-06, 'epoch': 43.0} |
|
{'loss': 0.0007, 'learning_rate': 7.224444444444445e-06, 'epoch': 43.01} |
|
{'loss': 0.0007, 'learning_rate': 7.1688888888888895e-06, 'epoch': 44.0} |
|
{'loss': 0.0007, 'learning_rate': 7.113333333333334e-06, 'epoch': 44.01} |
|
{'loss': 0.0007, 'learning_rate': 7.057777777777778e-06, 'epoch': 45.01} |
|
{'loss': 0.0007, 'learning_rate': 7.0022222222222225e-06, 'epoch': 46.0} |
|
{'loss': 0.0007, 'learning_rate': 6.946666666666667e-06, 'epoch': 46.01} |
|
{'loss': 0.0007, 'learning_rate': 6.891111111111111e-06, 'epoch': 47.0} |
|
{'loss': 0.0006, 'learning_rate': 6.835555555555556e-06, 'epoch': 48.0} |
|
{'loss': 0.0006, 'learning_rate': 6.780000000000001e-06, 'epoch': 48.01} |
|
{'loss': 0.0006, 'learning_rate': 6.724444444444444e-06, 'epoch': 49.0} |
|
{'loss': 0.0006, 'learning_rate': 6.668888888888889e-06, 'epoch': 49.01} |
|
{'eval_loss': 0.5848765969276428, 'eval_wer': 25.412319084483336, 'eval_runtime': 674.6923, 'eval_samples_per_second': 0.987, 'eval_steps_per_second': 0.031, 'epoch': 49.01} |
|
{'loss': 0.0006, 'learning_rate': 6.613333333333334e-06, 'epoch': 50.01} |
|
{'loss': 0.0006, 'learning_rate': 6.557777777777778e-06, 'epoch': 51.0} |
|
{'loss': 0.0006, 'learning_rate': 6.502222222222223e-06, 'epoch': 51.01} |
|
{'loss': 0.0005, 'learning_rate': 6.446666666666668e-06, 'epoch': 52.0} |
|
{'loss': 0.0005, 'learning_rate': 6.391111111111111e-06, 'epoch': 53.0} |
|
{'loss': 0.0005, 'learning_rate': 6.335555555555556e-06, 'epoch': 53.01} |
|
{'loss': 0.0005, 'learning_rate': 6.280000000000001e-06, 'epoch': 54.0} |
|
{'loss': 0.0005, 'learning_rate': 6.224444444444445e-06, 'epoch': 54.01} |
|
{'loss': 0.0005, 'learning_rate': 6.16888888888889e-06, 'epoch': 55.01} |
|
{'loss': 0.0005, 'learning_rate': 6.113333333333333e-06, 'epoch': 56.0} |
|
{'loss': 0.0005, 'learning_rate': 6.057777777777778e-06, 'epoch': 56.01} |
|
{'loss': 0.0005, 'learning_rate': 6.002222222222223e-06, 'epoch': 57.0} |
|
{'loss': 0.0005, 'learning_rate': 5.946666666666668e-06, 'epoch': 58.0} |
|
{'loss': 0.0005, 'learning_rate': 5.891111111111112e-06, 'epoch': 58.01} |
|
{'loss': 0.0004, 'learning_rate': 5.8355555555555565e-06, 'epoch': 59.0} |
|
{'loss': 0.0004, 'learning_rate': 5.78e-06, 'epoch': 59.01} |
|
{'loss': 0.0004, 'learning_rate': 5.724444444444445e-06, 'epoch': 60.01} |
|
{'loss': 0.0004, 'learning_rate': 5.6688888888888895e-06, 'epoch': 61.0} |
|
{'loss': 0.0004, 'learning_rate': 5.613333333333334e-06, 'epoch': 61.01} |
|
{'loss': 0.0004, 'learning_rate': 5.557777777777778e-06, 'epoch': 62.0} |
|
{'loss': 0.0004, 'learning_rate': 5.5022222222222224e-06, 'epoch': 63.0} |
|
{'loss': 0.0004, 'learning_rate': 5.4466666666666665e-06, 'epoch': 63.01} |
|
{'loss': 0.0004, 'learning_rate': 5.391111111111111e-06, 'epoch': 64.0} |
|
{'loss': 0.0004, 'learning_rate': 5.335555555555556e-06, 'epoch': 64.01} |
|
{'loss': 0.0004, 'learning_rate': 5.28e-06, 'epoch': 65.0} |
|
{'loss': 0.0004, 'learning_rate': 5.224444444444445e-06, 'epoch': 66.0} |
|
{'loss': 0.0004, 'learning_rate': 5.168888888888889e-06, 'epoch': 66.01} |
|
{'loss': 0.0004, 'learning_rate': 5.113333333333333e-06, 'epoch': 67.0} |
|
{'loss': 0.0004, 'learning_rate': 5.057777777777778e-06, 'epoch': 68.0} |
|
{'loss': 0.0004, 'learning_rate': 5.002222222222223e-06, 'epoch': 68.01} |
|
{'loss': 0.0003, 'learning_rate': 4.946666666666667e-06, 'epoch': 69.0} |
|
{'loss': 0.0003, 'learning_rate': 4.891111111111111e-06, 'epoch': 69.01} |
|
{'loss': 0.0003, 'learning_rate': 4.835555555555556e-06, 'epoch': 70.0} |
|
{'loss': 0.0003, 'learning_rate': 4.78e-06, 'epoch': 71.0} |
|
{'loss': 0.0003, 'learning_rate': 4.724444444444445e-06, 'epoch': 71.01} |
|
{'loss': 0.0003, 'learning_rate': 4.66888888888889e-06, 'epoch': 72.0} |
|
{'loss': 0.0003, 'learning_rate': 4.613333333333334e-06, 'epoch': 73.0} |
|
{'loss': 0.0003, 'learning_rate': 4.557777777777778e-06, 'epoch': 73.01} |
|
{'loss': 0.0003, 'learning_rate': 4.502222222222223e-06, 'epoch': 74.0} |
|
{'loss': 0.0003, 'learning_rate': 4.446666666666667e-06, 'epoch': 74.01} |
|
{'eval_loss': 0.6140743494033813, 'eval_wer': 25.631100639515314, 'eval_runtime': 663.2632, 'eval_samples_per_second': 1.004, 'eval_steps_per_second': 0.032, 'epoch': 74.01} |
|
{'loss': 0.0003, 'learning_rate': 4.391111111111112e-06, 'epoch': 75.0} |
|
{'loss': 0.0003, 'learning_rate': 4.3355555555555565e-06, 'epoch': 76.0} |
|
{'loss': 0.0003, 'learning_rate': 4.2800000000000005e-06, 'epoch': 76.01} |
|
{'loss': 0.0003, 'learning_rate': 4.2244444444444446e-06, 'epoch': 77.0} |
|
{'loss': 0.0003, 'learning_rate': 4.168888888888889e-06, 'epoch': 78.0} |
|
{'loss': 0.0003, 'learning_rate': 4.1133333333333335e-06, 'epoch': 78.01} |
|
{'loss': 0.0003, 'learning_rate': 4.057777777777778e-06, 'epoch': 79.0} |
|
{'loss': 0.0003, 'learning_rate': 4.002222222222222e-06, 'epoch': 79.01} |
|
{'loss': 0.0003, 'learning_rate': 3.946666666666667e-06, 'epoch': 80.0} |
|
{'loss': 0.0003, 'learning_rate': 3.891111111111111e-06, 'epoch': 81.0} |
|
{'loss': 0.0003, 'learning_rate': 3.835555555555555e-06, 'epoch': 81.01} |
|
{'loss': 0.0003, 'learning_rate': 3.7800000000000002e-06, 'epoch': 82.0} |
|
{'loss': 0.0003, 'learning_rate': 3.724444444444445e-06, 'epoch': 83.0} |
|
{'loss': 0.0003, 'learning_rate': 3.668888888888889e-06, 'epoch': 83.01} |
|
{'loss': 0.0003, 'learning_rate': 3.6133333333333336e-06, 'epoch': 84.0} |
|
{'loss': 0.0003, 'learning_rate': 3.5577777777777785e-06, 'epoch': 84.01} |
|
12/15/2022 06:41:03 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20] |
|
{'loss': 0.0003, 'learning_rate': 3.5022222222222225e-06, 'epoch': 85.0} |
|
{'loss': 0.0002, 'learning_rate': 3.446666666666667e-06, 'epoch': 86.0} |
|
{'loss': 0.0003, 'learning_rate': 3.391111111111111e-06, 'epoch': 86.01} |
|
{'loss': 0.0002, 'learning_rate': 3.335555555555556e-06, 'epoch': 87.0} |
|
{'loss': 0.0003, 'learning_rate': 3.2800000000000004e-06, 'epoch': 88.0} |
|
{'loss': 0.0002, 'learning_rate': 3.2244444444444444e-06, 'epoch': 88.01} |
|
{'loss': 0.0002, 'learning_rate': 3.1688888888888893e-06, 'epoch': 89.0} |
|
{'loss': 0.0002, 'learning_rate': 3.1133333333333337e-06, 'epoch': 89.01} |
|
{'loss': 0.0002, 'learning_rate': 3.0577777777777778e-06, 'epoch': 90.0} |
|
{'loss': 0.0002, 'learning_rate': 3.0022222222222227e-06, 'epoch': 91.0} |
|
{'loss': 0.0002, 'learning_rate': 2.946666666666667e-06, 'epoch': 91.01} |
|
{'loss': 0.0002, 'learning_rate': 2.891111111111111e-06, 'epoch': 92.0} |
|
{'loss': 0.0002, 'learning_rate': 2.835555555555556e-06, 'epoch': 93.0} |
|
{'loss': 0.0002, 'learning_rate': 2.7800000000000005e-06, 'epoch': 93.01} |
|
{'loss': 0.0002, 'learning_rate': 2.7244444444444445e-06, 'epoch': 94.0} |
|
{'loss': 0.0002, 'learning_rate': 2.6688888888888894e-06, 'epoch': 94.01} |
|
{'loss': 0.0002, 'learning_rate': 2.6133333333333334e-06, 'epoch': 95.0} |
|
{'loss': 0.0002, 'learning_rate': 2.557777777777778e-06, 'epoch': 96.0} |
|
{'loss': 0.0002, 'learning_rate': 2.5022222222222224e-06, 'epoch': 96.01} |
|
{'loss': 0.0002, 'learning_rate': 2.446666666666667e-06, 'epoch': 97.0} |
|
{'loss': 0.0002, 'learning_rate': 2.3911111111111113e-06, 'epoch': 98.0} |
|
{'loss': 0.0002, 'learning_rate': 2.3355555555555557e-06, 'epoch': 98.01} |
|
{'loss': 0.0002, 'learning_rate': 2.28e-06, 'epoch': 99.0} |
|
{'loss': 0.0002, 'learning_rate': 2.2244444444444447e-06, 'epoch': 99.01} |
|
{'eval_loss': 0.6324931383132935, 'eval_wer': 25.37305060024683, 'eval_runtime': 650.4597, 'eval_samples_per_second': 1.024, 'eval_steps_per_second': 0.032, 'epoch': 99.01} |
|
{'loss': 0.0002, 'learning_rate': 2.168888888888889e-06, 'epoch': 100.0} |
|
{'loss': 0.0002, 'learning_rate': 2.1133333333333336e-06, 'epoch': 101.0} |
|
{'loss': 0.0002, 'learning_rate': 2.057777777777778e-06, 'epoch': 101.01} |
|
{'loss': 0.0002, 'learning_rate': 2.0022222222222225e-06, 'epoch': 102.0} |
|
{'loss': 0.0002, 'learning_rate': 1.9466666666666665e-06, 'epoch': 103.0} |
|
{'loss': 0.0002, 'learning_rate': 1.8911111111111114e-06, 'epoch': 103.01} |
|
{'loss': 0.0002, 'learning_rate': 1.8355555555555557e-06, 'epoch': 104.0} |
|
{'loss': 0.0002, 'learning_rate': 1.7800000000000001e-06, 'epoch': 104.01} |
|
{'loss': 0.0002, 'learning_rate': 1.7244444444444448e-06, 'epoch': 105.0} |
|
{'loss': 0.0002, 'learning_rate': 1.668888888888889e-06, 'epoch': 106.0} |
|
{'loss': 0.0002, 'learning_rate': 1.6133333333333335e-06, 'epoch': 106.01} |
|
{'loss': 0.0002, 'learning_rate': 1.5577777777777777e-06, 'epoch': 107.0} |
|
{'loss': 0.0002, 'learning_rate': 1.5022222222222224e-06, 'epoch': 108.0} |
|
{'loss': 0.0002, 'learning_rate': 1.4466666666666669e-06, 'epoch': 108.01} |
|
{'loss': 0.0002, 'learning_rate': 1.3911111111111111e-06, 'epoch': 109.0} |
|
{'loss': 0.0002, 'learning_rate': 1.3355555555555558e-06, 'epoch': 109.01} |
|
{'loss': 0.0002, 'learning_rate': 1.28e-06, 'epoch': 110.0} |
|
{'loss': 0.0002, 'learning_rate': 1.2244444444444445e-06, 'epoch': 111.0} |
|
{'loss': 0.0002, 'learning_rate': 1.168888888888889e-06, 'epoch': 111.01} |
|
{'loss': 0.0002, 'learning_rate': 1.1133333333333334e-06, 'epoch': 112.0} |
|
{'loss': 0.0002, 'learning_rate': 1.0577777777777779e-06, 'epoch': 113.0} |
|
{'loss': 0.0002, 'learning_rate': 1.0022222222222223e-06, 'epoch': 113.01} |
|
{'loss': 0.0002, 'learning_rate': 9.466666666666667e-07, 'epoch': 114.0} |
|
{'loss': 0.0002, 'learning_rate': 8.911111111111112e-07, 'epoch': 114.01} |
|
{'loss': 0.0002, 'learning_rate': 8.355555555555556e-07, 'epoch': 115.0} |
|
{'loss': 0.0002, 'learning_rate': 7.8e-07, 'epoch': 116.0} |
|
{'loss': 0.0002, 'learning_rate': 7.244444444444446e-07, 'epoch': 116.01} |
|
{'loss': 0.0002, 'learning_rate': 6.68888888888889e-07, 'epoch': 117.0} |
|
{'loss': 0.0002, 'learning_rate': 6.133333333333333e-07, 'epoch': 118.0} |
|
{'loss': 0.0002, 'learning_rate': 5.577777777777779e-07, 'epoch': 118.01} |
|
{'loss': 0.0002, 'learning_rate': 5.022222222222222e-07, 'epoch': 119.0} |
|
{'loss': 0.0002, 'learning_rate': 4.466666666666667e-07, 'epoch': 119.01} |
|
{'loss': 0.0002, 'learning_rate': 3.9111111111111115e-07, 'epoch': 120.0} |
|
{'loss': 0.0002, 'learning_rate': 3.3555555555555556e-07, 'epoch': 121.0} |
|
{'loss': 0.0002, 'learning_rate': 2.8e-07, 'epoch': 121.01} |
|
{'loss': 0.0002, 'learning_rate': 2.2444444444444445e-07, 'epoch': 122.0} |
|
{'loss': 0.0002, 'learning_rate': 1.6888888888888888e-07, 'epoch': 123.0} |
|
{'loss': 0.0002, 'learning_rate': 1.1333333333333336e-07, 'epoch': 123.01} |
|
{'loss': 0.0002, 'learning_rate': 5.777777777777778e-08, 'epoch': 124.0} |
|
{'loss': 0.0002, 'learning_rate': 2.2222222222222225e-09, 'epoch': 124.01} |
|
{'eval_loss': 0.6405040621757507, 'eval_wer': 25.43475821833277, 'eval_runtime': 648.4677, 'eval_samples_per_second': 1.027, 'eval_steps_per_second': 0.032, 'epoch': 124.01} |
|
{'train_runtime': 39423.3866, 'train_samples_per_second': 8.117, 'train_steps_per_second': 0.127, 'train_loss': 0.04578730283072218, 'epoch': 124.01} |
|
12/15/2022 10:11:51 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream. |
|
12/15/2022 10:11:51 - WARNING - huggingface_hub.repository - The progress bars may be unreliable. |
|
12/15/2022 10:11:57 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow... |
|
remote: LFS file scan complete. |
|
To https://huggingface.co/mikr/whisper-small-hr-vox |
|
ddcf8d0..1dba846 main -> main |
|
|
|
12/15/2022 10:12:11 - WARNING - huggingface_hub.repository - To https://huggingface.co/mikr/whisper-small-hr-vox |
|
1dba846..c404c89 main -> main |
|
|
|
***** train metrics ***** |
|
epoch = 124.01 |
|
train_loss = 0.0458 |
|
train_runtime = 10:57:03.38 |
|
train_samples_per_second = 8.117 |
|
train_steps_per_second = 0.127 |
|
12/15/2022 10:12:14 - INFO - __main__ - *** Evaluate *** |
|
***** eval metrics ***** |
|
epoch = 124.01 |
|
eval_loss = 0.6325 |
|
eval_runtime = 0:10:46.41 |
|
eval_samples_per_second = 1.03 |
|
eval_steps_per_second = 0.032 |
|
eval_wer = 25.3731 |
|
12/15/2022 10:23:21 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow... |
|
remote: LFS file scan complete. |
|
To https://huggingface.co/mikr/whisper-small-hr-vox |
|
c404c89..bb31423 main -> main |
|
|
|
|