12/12/2022 17:00:53 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
12/12/2022 17:00:53 - 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/Dec12_17-00-53_129-213-128-6,
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,
)
12/12/2022 17:00:53 - 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/Dec12_17-00-53_129-213-128-6,
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,
)
12/12/2022 17:00:53 - INFO - datasets.info - Loading Dataset Infos from /home/ubuntu/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/12/2022 17:00:53 - INFO - datasets.info - Loading Dataset Infos from /home/ubuntu/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/12/2022 17:00:54 - INFO - datasets.info - Loading Dataset Infos from /home/ubuntu/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/12/2022 17:00:59 - WARNING - huggingface_hub.repository - /home/ubuntu/whisper-small-fy-NL-Transfer-From-English/./ is already a clone of https://huggingface.co/polixonrio/whisper-small-fy-NL-Transfer-From-English. Make sure you pull the latest changes with `repo.git_pull()`.
{'loss': 7.6922, 'learning_rate': 4.0000000000000003e-07, 'epoch': 0.01}
{'loss': 5.8503, 'learning_rate': 9.000000000000001e-07, 'epoch': 0.01}
{'loss': 3.9042, 'learning_rate': 1.4000000000000001e-06, 'epoch': 0.01}
{'loss': 2.7093, 'learning_rate': 1.9000000000000002e-06, 'epoch': 1.0}
{'loss': 1.7436, 'learning_rate': 2.4000000000000003e-06, 'epoch': 1.01}
{'loss': 1.3753, 'learning_rate': 2.9e-06, 'epoch': 1.01}
{'loss': 1.082, 'learning_rate': 3.4000000000000005e-06, 'epoch': 1.02}
{'loss': 0.923, 'learning_rate': 3.900000000000001e-06, 'epoch': 2.0}
{'loss': 0.7541, 'learning_rate': 4.4e-06, 'epoch': 2.01}
{'loss': 0.681, 'learning_rate': 4.9000000000000005e-06, 'epoch': 2.01}
{'loss': 0.5853, 'learning_rate': 5.400000000000001e-06, 'epoch': 2.02}
{'loss': 0.5019, 'learning_rate': 5.9e-06, 'epoch': 3.0}
{'loss': 0.439, 'learning_rate': 6.4000000000000006e-06, 'epoch': 3.01}
{'loss': 0.3904, 'learning_rate': 6.9e-06, 'epoch': 3.01}
{'loss': 0.3482, 'learning_rate': 7.4e-06, 'epoch': 3.02}
{'loss': 0.2813, 'learning_rate': 7.9e-06, 'epoch': 4.0}
{'loss': 0.2462, 'learning_rate': 8.400000000000001e-06, 'epoch': 4.01}
{'loss': 0.2148, 'learning_rate': 8.900000000000001e-06, 'epoch': 4.01}
{'loss': 0.1904, 'learning_rate': 9.4e-06, 'epoch': 4.02}
{'loss': 0.1422, 'learning_rate': 9.9e-06, 'epoch': 5.0}
{'loss': 0.1294, 'learning_rate': 9.955555555555556e-06, 'epoch': 5.01}
{'loss': 0.0987, 'learning_rate': 9.9e-06, 'epoch': 5.01}
{'loss': 0.0965, 'learning_rate': 9.844444444444446e-06, 'epoch': 6.0}
{'loss': 0.0641, 'learning_rate': 9.78888888888889e-06, 'epoch': 6.01}
{'loss': 0.0626, 'learning_rate': 9.733333333333334e-06, 'epoch': 6.01}
{'loss': 0.0461, 'learning_rate': 9.677777777777778e-06, 'epoch': 6.02}
{'loss': 0.0434, 'learning_rate': 9.622222222222222e-06, 'epoch': 7.0}
{'loss': 0.0332, 'learning_rate': 9.566666666666668e-06, 'epoch': 7.01}
{'loss': 0.0307, 'learning_rate': 9.511111111111112e-06, 'epoch': 7.01}
{'loss': 0.0243, 'learning_rate': 9.455555555555557e-06, 'epoch': 7.02}
{'loss': 0.0197, 'learning_rate': 9.4e-06, 'epoch': 8.0}
{'loss': 0.0178, 'learning_rate': 9.344444444444446e-06, 'epoch': 8.01}
{'loss': 0.018, 'learning_rate': 9.28888888888889e-06, 'epoch': 8.01}
{'loss': 0.0158, 'learning_rate': 9.233333333333334e-06, 'epoch': 8.02}
{'loss': 0.0128, 'learning_rate': 9.17777777777778e-06, 'epoch': 9.0}
{'loss': 0.0123, 'learning_rate': 9.122222222222223e-06, 'epoch': 9.01}
{'loss': 0.011, 'learning_rate': 9.066666666666667e-06, 'epoch': 9.01}
{'loss': 0.01, 'learning_rate': 9.011111111111111e-06, 'epoch': 9.02}
{'loss': 0.0086, 'learning_rate': 8.955555555555555e-06, 'epoch': 10.01}
{'loss': 0.0078, 'learning_rate': 8.900000000000001e-06, 'epoch': 10.01}