Training in progress, step 1000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb7e7cdb12c993247dae38eaff7decc384670c9aff9b01b96ce60cb6b4c49c22
+oid sha256:148dc9d8e83df3c44cac9de9435f8e4448aea496e86b272f78ecad49ce3c1541
 size 967102601

run.log

@@ -0,0 +1,277 @@
+12/12/2022 06:37:01 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
+12/12/2022 06:37:01 - 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_06-37-01_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 06:37:01 - 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_06-37-01_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 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/tmpdbxqdsn0
+12/12/2022 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - creating metadata file for /home/ubuntu/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
+12/12/2022 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/tmpooh_q071
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/README.md in cache at /home/ubuntu/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - creating metadata file for /home/ubuntu/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
+12/12/2022 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/tmpiktwf5x7
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/languages.py in cache at /home/ubuntu/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - creating metadata file for /home/ubuntu/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
+12/12/2022 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/tmp68qnwpgl
+12/12/2022 06:37:01 - 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/ubuntu/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
+12/12/2022 06:37:01 - INFO - datasets.utils.file_utils - creating metadata file for /home/ubuntu/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
+12/12/2022 06:37:01 - 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 06:37:02 - 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 06:37:02 - 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 06:37:19 - WARNING - huggingface_hub.repository - /home/ubuntu/whisper-small-fy-NL-Transfer-From-EN/./ is already a clone of https://huggingface.co/polixonrio/whisper-small-fy-NL-Transfer-From-EN. 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}

run.sh

@@ -2,7 +2,7 @@ python run_speech_recognition_seq2seq_streaming.py \
 --model_name_or_path="openai/whisper-small" \
 --dataset_name="mozilla-foundation/common_voice_11_0" \
 --dataset_config_name="fy-NL" \
---train_split_name="train" \
+--train_split_name="train+validation" \
 --eval_split_name="test" \
 --model_index_name="Whisper Small Western Frisian (Netherlands)" \
 --max_steps="5000" \

runs/Dec12_06-37-01_129-213-128-6/1670827042.115391/events.out.tfevents.1670827042.129-213-128-6.68824.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4697accdf86823e13f9e577eeb8c9d365338fba99d43a855d1bc9351ade9c5a5
+size 5869

runs/Dec12_06-37-01_129-213-128-6/events.out.tfevents.1670827042.129-213-128-6.68824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e5f7139ad1b4deb6a380989ba67916db0d79c73efb35a7251b1ea9269321d9
+size 10531

runs/Dec12_11-48-40_129-213-128-6/1670845728.5230641/events.out.tfevents.1670845728.129-213-128-6.2037374.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57920ecca05d876dfa9b6947ebc5001508dc11133c91a890b782a4399d3e2367
+size 5869

runs/Dec12_11-48-40_129-213-128-6/events.out.tfevents.1670845728.129-213-128-6.2037374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4b91195c771cf631a6b5ee2f4629d260d84c4acad916ebdceafdc0fc0f6056
+size 10849

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fed2793182c960f94e65c259eac9262c1bc3500a78583e1ecfcd70232dc5a66
+oid sha256:a5cbd14f154559bd0603874dc5b11605a7ea8764769ccab0dad9e3ca6131e4b0
 size 3579