Training in progress, step 27000

.gitattributes

@@ -39,3 +39,5 @@ community-events/huggan/assets/pix2pix_maps.png filter=lfs diff=lfs merge=lfs -t
 community-events/huggan/assets/wandb.png filter=lfs diff=lfs merge=lfs -text
 wandb/run-20231118_132020-qg88991p/run-qg88991p.wandb filter=lfs diff=lfs merge=lfs -text
 wandb/run-20231119_105908-nwx0xdmm/run-nwx0xdmm.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20231119_105908-nwx0xdmm/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
+wandb/run-20231122_100021-qrxr9o47/run-qrxr9o47.wandb filter=lfs diff=lfs merge=lfs -text

config.json

@@ -34,6 +34,7 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
+  "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74eacfca3ebe20a52f7d30c59c5d75c0590319ade9029e6353b301d09ac8dbfc
+oid sha256:256dbf5bf7dd51701df4c930521269fc6ebc126a8cfdf26df730c1343e52f8fa
 size 3219908024

start_train.sh

@@ -42,4 +42,4 @@ deepspeed run_speech_recognition_seq2seq_streaming.py \
 	--use_auth_token \
 	--push_to_hub \
     --push_to_hub_model_id="WhisperLargeFinnishV3" \
-    --resume_from_checkpoint="./checkpoint-7000"
+    --resume_from_checkpoint="./checkpoint-26000"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5d22c96e3a01c90c6d5a2f12fe2d7c1881cd34751d01b577ea8b353592f589
+oid sha256:15474ac29434544ae625779797f25a48c1f3f4beceb060e4a903486009997382
 size 6456

wandb/debug.log

@@ -1,27 +1,27 @@
-2023-11-19 10:59:09,019 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Current SDK version is 0.16.0
-2023-11-19 10:59:09,020 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Configure stats pid to 605851
-2023-11-19 10:59:09,020 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Loading settings from /home/rasmus/.config/wandb/settings
-2023-11-19 10:59:09,020 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Loading settings from /mnt/e/wandb/settings
-2023-11-19 10:59:09,020 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2023-11-19 10:59:09,020 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2023-11-19 10:59:09,021 INFO    MainThread:605851 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program_abspath': '/mnt/e/run_speech_recognition_seq2seq_streaming.py', 'program': '/mnt/e/run_speech_recognition_seq2seq_streaming.py'}
-2023-11-19 10:59:09,021 INFO    MainThread:605851 [wandb_init.py:_log_setup():524] Logging user logs to /mnt/e/wandb/run-20231119_105908-nwx0xdmm/logs/debug.log
-2023-11-19 10:59:09,022 INFO    MainThread:605851 [wandb_init.py:_log_setup():525] Logging internal logs to /mnt/e/wandb/run-20231119_105908-nwx0xdmm/logs/debug-internal.log
-2023-11-19 10:59:09,022 INFO    MainThread:605851 [wandb_init.py:init():564] calling init triggers
-2023-11-19 10:59:09,022 INFO    MainThread:605851 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+2023-11-22 10:00:21,657 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Current SDK version is 0.16.0
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Configure stats pid to 2217649
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from /home/rasmus/.config/wandb/settings
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from /mnt/e/wandb/settings
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program_abspath': '/mnt/e/run_speech_recognition_seq2seq_streaming.py', 'program': '/mnt/e/run_speech_recognition_seq2seq_streaming.py'}
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:_log_setup():524] Logging user logs to /mnt/e/wandb/run-20231122_100021-qrxr9o47/logs/debug.log
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:_log_setup():525] Logging internal logs to /mnt/e/wandb/run-20231122_100021-qrxr9o47/logs/debug-internal.log
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:init():564] calling init triggers
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
 config: {}
-2023-11-19 10:59:09,023 INFO    MainThread:605851 [wandb_init.py:init():614] starting backend
-2023-11-19 10:59:09,023 INFO    MainThread:605851 [wandb_init.py:init():618] setting up manager
-2023-11-19 10:59:09,029 INFO    MainThread:605851 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2023-11-19 10:59:09,033 INFO    MainThread:605851 [wandb_init.py:init():624] backend started and connected
-2023-11-19 10:59:09,053 INFO    MainThread:605851 [wandb_init.py:init():716] updated telemetry
-2023-11-19 10:59:09,056 INFO    MainThread:605851 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
-2023-11-19 10:59:09,506 INFO    MainThread:605851 [wandb_run.py:_on_init():2254] communicating current version
-2023-11-19 10:59:09,554 INFO    MainThread:605851 [wandb_run.py:_on_init():2263] got version response 
-2023-11-19 10:59:09,554 INFO    MainThread:605851 [wandb_init.py:init():800] starting run threads in backend
-2023-11-19 10:59:14,492 INFO    MainThread:605851 [wandb_run.py:_console_start():2233] atexit reg
-2023-11-19 10:59:14,492 INFO    MainThread:605851 [wandb_run.py:_redirect():2088] redirect: wrap_raw
-2023-11-19 10:59:14,493 INFO    MainThread:605851 [wandb_run.py:_redirect():2153] Wrapping output streams.
-2023-11-19 10:59:14,493 INFO    MainThread:605851 [wandb_run.py:_redirect():2178] Redirects installed.
-2023-11-19 10:59:14,495 INFO    MainThread:605851 [wandb_init.py:init():841] run started, returning control to user process
-2023-11-19 10:59:14,497 INFO    MainThread:605851 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 51866, 'num_mel_bins': 128, 'd_model': 1280, 'encoder_layers': 32, 'encoder_attention_heads': 20, 'decoder_layers': 32, 'decoder_attention_heads': 20, 'decoder_ffn_dim': 5120, 'encoder_ffn_dim': 5120, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': True, 'num_hidden_layers': 32, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50256, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-large-v3', 'transformers_version': '4.36.0.dev0', 'model_type': 'whisper', 'forced_decoder_ids': None, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-06, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Nov19_10-55-41_DESKTOP-59O9VN1', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': 'ds_config.json', 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': './checkpoint-7000', 'hub_model_id': 'RASMUS/WhisperLargeFinnishV3', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'WhisperLargeFinnishV3', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': True, 'torch_compile_backend': 'inductor', 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}
+2023-11-22 10:00:21,661 INFO    MainThread:2217649 [wandb_init.py:init():614] starting backend
+2023-11-22 10:00:21,661 INFO    MainThread:2217649 [wandb_init.py:init():618] setting up manager
+2023-11-22 10:00:21,667 INFO    MainThread:2217649 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2023-11-22 10:00:21,676 INFO    MainThread:2217649 [wandb_init.py:init():624] backend started and connected
+2023-11-22 10:00:21,717 INFO    MainThread:2217649 [wandb_init.py:init():716] updated telemetry
+2023-11-22 10:00:21,722 INFO    MainThread:2217649 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2023-11-22 10:00:22,205 INFO    MainThread:2217649 [wandb_run.py:_on_init():2254] communicating current version
+2023-11-22 10:00:22,253 INFO    MainThread:2217649 [wandb_run.py:_on_init():2263] got version response 
+2023-11-22 10:00:22,253 INFO    MainThread:2217649 [wandb_init.py:init():800] starting run threads in backend
+2023-11-22 10:00:27,927 INFO    MainThread:2217649 [wandb_run.py:_console_start():2233] atexit reg
+2023-11-22 10:00:27,928 INFO    MainThread:2217649 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2023-11-22 10:00:27,929 INFO    MainThread:2217649 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2023-11-22 10:00:27,929 INFO    MainThread:2217649 [wandb_run.py:_redirect():2178] Redirects installed.
+2023-11-22 10:00:27,930 INFO    MainThread:2217649 [wandb_init.py:init():841] run started, returning control to user process
+2023-11-22 10:00:27,933 INFO    MainThread:2217649 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 51866, 'num_mel_bins': 128, 'd_model': 1280, 'encoder_layers': 32, 'encoder_attention_heads': 20, 'decoder_layers': 32, 'decoder_attention_heads': 20, 'decoder_ffn_dim': 5120, 'encoder_ffn_dim': 5120, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': True, 'num_hidden_layers': 32, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50256, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-large-v3', 'transformers_version': '4.36.0.dev0', 'model_type': 'whisper', 'forced_decoder_ids': None, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-06, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Nov22_09-55-44_DESKTOP-59O9VN1', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': 'ds_config.json', 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': './checkpoint-26000', 'hub_model_id': 'RASMUS/WhisperLargeFinnishV3', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'WhisperLargeFinnishV3', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': True, 'torch_compile_backend': 'inductor', 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}

wandb/run-20231119_105908-nwx0xdmm/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.0712, "train/learning_rate": 2.0324237288135594e-06, "train/epoch": 0.33, "train/global_step": 20060, "_timestamp": 1700533941.1437454, "_runtime": 149592.1096584797, "_step": 665, "eval/loss": 0.1776123046875, "eval/wer": 8.509234828496043, "eval/runtime": 604.4094, "eval/samples_per_second": 2.819, "eval/steps_per_second": 0.705}
+{"train/loss": 0.0556, "train/learning_rate": 1.7094915254237288e-06, "train/epoch": 0.44, "train/global_step": 26420, "_timestamp": 1700600828.0143824, "_runtime": 216478.9802954197, "_step": 989, "eval/loss": 0.197509765625, "eval/wer": 8.301922352054278, "eval/runtime": 649.294, "eval/samples_per_second": 2.624, "eval/steps_per_second": 0.656, "_wandb": {"runtime": 216615}}

wandb/run-20231119_105908-nwx0xdmm/logs/debug.log

@@ -25,3 +25,4 @@ config: {}
 2023-11-19 10:59:14,493 INFO    MainThread:605851 [wandb_run.py:_redirect():2178] Redirects installed.
 2023-11-19 10:59:14,495 INFO    MainThread:605851 [wandb_init.py:init():841] run started, returning control to user process
 2023-11-19 10:59:14,497 INFO    MainThread:605851 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 51866, 'num_mel_bins': 128, 'd_model': 1280, 'encoder_layers': 32, 'encoder_attention_heads': 20, 'decoder_layers': 32, 'decoder_attention_heads': 20, 'decoder_ffn_dim': 5120, 'encoder_ffn_dim': 5120, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': True, 'num_hidden_layers': 32, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50256, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-large-v3', 'transformers_version': '4.36.0.dev0', 'model_type': 'whisper', 'forced_decoder_ids': None, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-06, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Nov19_10-55-41_DESKTOP-59O9VN1', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': 'ds_config.json', 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': './checkpoint-7000', 'hub_model_id': 'RASMUS/WhisperLargeFinnishV3', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'WhisperLargeFinnishV3', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': True, 'torch_compile_backend': 'inductor', 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}
+2023-11-21 23:09:29,646 WARNING MsgRouterThr:605851 [router.py:message_loop():77] message_loop has been closed

wandb/run-20231119_105908-nwx0xdmm/run-nwx0xdmm.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4815856c5203c68d373aea1f58544c4f5864fd2c3cc73cf29d1fde1df0640e7a
-size 9458453
+oid sha256:27a032e58caafe6cf610e02ca71bf9f8041e357ee650fa4ab7879c284a033836
+size 14294891

wandb/run-20231122_100021-qrxr9o47/files/conda-environment.yaml

@@ -0,0 +1,219 @@
+name: WhisperFinetuneEnv
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2023.08.22=h06a4308_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.12=h7f8727e_0
+  - pip=23.3=py310h06a4308_0
+  - python=3.10.13=h955ad1f_0
+  - readline=8.2=h5eee18b_0
+  - setuptools=68.0.0=py310h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - tk=8.6.12=h1ccaba5_0
+  - wheel=0.41.2=py310h06a4308_0
+  - xz=5.4.2=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0
+  - pip:
+      - absl-py==2.0.0
+      - accelerate==0.24.1
+      - aiohttp==3.9.0
+      - aiosignal==1.3.1
+      - annotated-types==0.6.0
+      - anyio==4.0.0
+      - appdirs==1.4.4
+      - argon2-cffi==23.1.0
+      - argon2-cffi-bindings==21.2.0
+      - arrow==1.3.0
+      - asttokens==2.4.1
+      - async-lru==2.0.4
+      - async-timeout==4.0.3
+      - attrs==23.1.0
+      - audioread==3.0.1
+      - babel==2.13.1
+      - beautifulsoup4==4.12.2
+      - bleach==6.1.0
+      - cachetools==5.3.2
+      - certifi==2023.11.17
+      - cffi==1.16.0
+      - charset-normalizer==3.3.2
+      - click==8.1.7
+      - comm==0.2.0
+      - datasets==2.15.1.dev0
+      - debugpy==1.8.0
+      - decorator==5.1.1
+      - deepspeed==0.12.3
+      - defusedxml==0.7.1
+      - dill==0.3.7
+      - docker-pycreds==0.4.0
+      - evaluate==0.4.1
+      - exceptiongroup==1.1.3
+      - executing==2.0.1
+      - fastjsonschema==2.19.0
+      - filelock==3.13.1
+      - fqdn==1.5.1
+      - frozenlist==1.4.0
+      - fsspec==2023.10.0
+      - gitdb==4.0.11
+      - gitpython==3.1.40
+      - google-auth==2.23.4
+      - google-auth-oauthlib==1.1.0
+      - grpcio==1.59.3
+      - hjson==3.1.0
+      - huggingface-hub==0.19.4
+      - idna==3.4
+      - iprogress==0.4
+      - ipykernel==6.26.0
+      - ipython==8.17.2
+      - ipywidgets==8.1.1
+      - isoduration==20.11.0
+      - jedi==0.19.1
+      - jinja2==3.1.2
+      - jiwer==3.0.3
+      - joblib==1.3.2
+      - json5==0.9.14
+      - jsonpointer==2.4
+      - jsonschema==4.20.0
+      - jsonschema-specifications==2023.11.1
+      - jupyter==1.0.0
+      - jupyter-client==8.6.0
+      - jupyter-console==6.6.3
+      - jupyter-core==5.5.0
+      - jupyter-events==0.9.0
+      - jupyter-lsp==2.2.0
+      - jupyter-server==2.10.1
+      - jupyter-server-terminals==0.4.4
+      - jupyterlab==4.0.8
+      - jupyterlab-pygments==0.2.2
+      - jupyterlab-server==2.25.1
+      - jupyterlab-widgets==3.0.9
+      - lazy-loader==0.3
+      - librosa==0.10.1
+      - llvmlite==0.41.1
+      - markdown==3.5.1
+      - markupsafe==2.1.3
+      - matplotlib-inline==0.1.6
+      - mistune==3.0.2
+      - more-itertools==10.1.0
+      - mpmath==1.3.0
+      - msgpack==1.0.7
+      - multidict==6.0.4
+      - multiprocess==0.70.15
+      - nbclient==0.9.0
+      - nbconvert==7.11.0
+      - nbformat==5.9.2
+      - nest-asyncio==1.5.8
+      - networkx==3.2.1
+      - ninja==1.11.1.1
+      - notebook==7.0.6
+      - notebook-shim==0.2.3
+      - numba==0.58.1
+      - numpy==1.26.2
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==8.9.2.26
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-nccl-cu12==2.18.1
+      - nvidia-nvjitlink-cu12==12.3.101
+      - nvidia-nvtx-cu12==12.1.105
+      - oauthlib==3.2.2
+      - overrides==7.4.0
+      - packaging==23.2
+      - pandas==2.1.3
+      - pandocfilters==1.5.0
+      - parso==0.8.3
+      - pexpect==4.8.0
+      - pillow==10.1.0
+      - platformdirs==4.0.0
+      - pooch==1.8.0
+      - prometheus-client==0.18.0
+      - prompt-toolkit==3.0.41
+      - protobuf==4.23.4
+      - psutil==5.9.6
+      - ptyprocess==0.7.0
+      - pure-eval==0.2.2
+      - py-cpuinfo==9.0.0
+      - pyarrow==14.0.1
+      - pyarrow-hotfix==0.5
+      - pyasn1==0.5.0
+      - pyasn1-modules==0.3.0
+      - pycparser==2.21
+      - pydantic==2.5.1
+      - pydantic-core==2.14.3
+      - pygments==2.16.1
+      - pynvml==11.5.0
+      - python-dateutil==2.8.2
+      - python-json-logger==2.0.7
+      - pytz==2023.3.post1
+      - pyyaml==6.0.1
+      - pyzmq==25.1.1
+      - qtconsole==5.5.1
+      - qtpy==2.4.1
+      - rapidfuzz==3.5.2
+      - referencing==0.31.0
+      - regex==2023.10.3
+      - requests==2.31.0
+      - requests-oauthlib==1.3.1
+      - responses==0.18.0
+      - rfc3339-validator==0.1.4
+      - rfc3986-validator==0.1.1
+      - rpds-py==0.13.0
+      - rsa==4.9
+      - safetensors==0.4.0
+      - scikit-learn==1.3.2
+      - scipy==1.11.3
+      - send2trash==1.8.2
+      - sentry-sdk==1.35.0
+      - setproctitle==1.3.3
+      - six==1.16.0
+      - smmap==5.0.1
+      - sniffio==1.3.0
+      - soundfile==0.12.1
+      - soupsieve==2.5
+      - soxr==0.3.7
+      - stack-data==0.6.3
+      - sympy==1.12
+      - tensorboard==2.15.1
+      - tensorboard-data-server==0.7.2
+      - terminado==0.18.0
+      - threadpoolctl==3.2.0
+      - tinycss2==1.2.1
+      - tokenizers==0.15.0
+      - tomli==2.0.1
+      - torch==2.1.1
+      - torchaudio==2.1.1
+      - torchvision==0.16.1
+      - tornado==6.3.3
+      - tqdm==4.66.1
+      - traitlets==5.13.0
+      - transformers==4.36.0.dev0
+      - triton==2.1.0
+      - types-python-dateutil==2.8.19.14
+      - typing-extensions==4.8.0
+      - tzdata==2023.3
+      - uri-template==1.3.0
+      - urllib3==2.1.0
+      - wandb==0.16.0
+      - wcwidth==0.2.10
+      - webcolors==1.13
+      - webencodings==0.5.1
+      - websocket-client==1.6.4
+      - werkzeug==3.0.1
+      - widgetsnbextension==4.0.9
+      - xxhash==3.4.1
+      - yarl==1.9.2
+prefix: /home/rasmus/miniconda3/envs/WhisperFinetuneEnv

wandb/run-20231122_100021-qrxr9o47/files/config.yaml

@@ -0,0 +1,718 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.13
+    cli_version: 0.16.0
+    framework: huggingface
+    huggingface_version: 4.36.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1700640021.677551
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 100
+      2:
+      - 1
+      - 5
+      - 11
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 100
+      3:
+      - 7
+      - 23
+      4: 3.10.13
+      5: 0.16.0
+      6: 4.36.0.dev0
+      8:
+      - 5
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 51866
+num_mel_bins:
+  desc: null
+  value: 128
+d_model:
+  desc: null
+  value: 1280
+encoder_layers:
+  desc: null
+  value: 32
+encoder_attention_heads:
+  desc: null
+  value: 20
+decoder_layers:
+  desc: null
+  value: 32
+decoder_attention_heads:
+  desc: null
+  value: 20
+decoder_ffn_dim:
+  desc: null
+  value: 5120
+encoder_ffn_dim:
+  desc: null
+  value: 5120
+dropout:
+  desc: null
+  value: 0.0
+attention_dropout:
+  desc: null
+  value: 0.0
+activation_dropout:
+  desc: null
+  value: 0.0
+activation_function:
+  desc: null
+  value: gelu
+init_std:
+  desc: null
+  value: 0.02
+encoder_layerdrop:
+  desc: null
+  value: 0.0
+decoder_layerdrop:
+  desc: null
+  value: 0.0
+use_cache:
+  desc: null
+  value: true
+num_hidden_layers:
+  desc: null
+  value: 32
+scale_embedding:
+  desc: null
+  value: false
+max_source_positions:
+  desc: null
+  value: 1500
+max_target_positions:
+  desc: null
+  value: 448
+classifier_proj_size:
+  desc: null
+  value: 256
+use_weighted_layer_sum:
+  desc: null
+  value: false
+apply_spec_augment:
+  desc: null
+  value: false
+mask_time_prob:
+  desc: null
+  value: 0.05
+mask_time_length:
+  desc: null
+  value: 10
+mask_time_min_masks:
+  desc: null
+  value: 2
+mask_feature_prob:
+  desc: null
+  value: 0.0
+mask_feature_length:
+  desc: null
+  value: 10
+mask_feature_min_masks:
+  desc: null
+  value: 0
+median_filter_width:
+  desc: null
+  value: 7
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: float16
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: true
+is_encoder_decoder:
+  desc: null
+  value: true
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 448
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value:
+  - 220
+  - 50257
+architectures:
+  desc: null
+  value:
+  - WhisperForConditionalGeneration
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 50257
+pad_token_id:
+  desc: null
+  value: 50256
+eos_token_id:
+  desc: null
+  value: 50257
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: 50258
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: openai/whisper-large-v3
+transformers_version:
+  desc: null
+  value: 4.36.0.dev0
+model_type:
+  desc: null
+  value: whisper
+forced_decoder_ids:
+  desc: null
+  value: null
+output_dir:
+  desc: null
+  value: ./
+overwrite_output_dir:
+  desc: null
+  value: true
+do_train:
+  desc: null
+  value: true
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+evaluation_strategy:
+  desc: null
+  value: steps
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 8
+per_device_eval_batch_size:
+  desc: null
+  value: 4
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 3.0e-06
+weight_decay:
+  desc: null
+  value: 0.0
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 3.0
+max_steps:
+  desc: null
+  value: 60000
+lr_scheduler_type:
+  desc: null
+  value: linear
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 1000
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/Nov22_09-55-44_DESKTOP-59O9VN1
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 20
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 1000
+save_total_limit:
+  desc: null
+  value: null
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: false
+fp16:
+  desc: null
+  value: true
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: null
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: 1000
+dataloader_num_workers:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: ./
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: true
+metric_for_best_model:
+  desc: null
+  value: wer
+greater_is_better:
+  desc: null
+  value: false
+ignore_data_skip:
+  desc: null
+  value: false
+fsdp:
+  desc: null
+  value: []
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+deepspeed:
+  desc: null
+  value: ds_config.json
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_torch
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: input_length
+report_to:
+  desc: null
+  value:
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: null
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: true
+resume_from_checkpoint:
+  desc: null
+  value: ./checkpoint-26000
+hub_model_id:
+  desc: null
+  value: RASMUS/WhisperLargeFinnishV3
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: true
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+push_to_hub_model_id:
+  desc: null
+  value: WhisperLargeFinnishV3
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: true
+torch_compile_backend:
+  desc: null
+  value: inductor
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: false
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+sortish_sampler:
+  desc: null
+  value: false
+predict_with_generate:
+  desc: null
+  value: true
+generation_max_length:
+  desc: null
+  value: 225
+generation_num_beams:
+  desc: null
+  value: null
+generation_config:
+  desc: null
+  value: null

wandb/run-20231122_100021-qrxr9o47/files/output.log

@@ -0,0 +1,1190 @@
+Reading metadata...: 2165it [00:01, 2091.77it/s]                                                                   | 0/60000 [00:00<?, ?it/s]
+Reading metadata...: 1it [00:01,  1.02s/it]
+
+
+[INFO|trainer_utils.py:759] 2023-11-22 10:02:47,011 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+Reading metadata...: 1650it [00:00, 10770.26it/s]
+Reading metadata...: 1it [00:00,  6.80it/s]
+
+Reading metadata...: 1650it [00:00, 10115.12it/s]
+Reading metadata...: 2165it [00:00, 14042.07it/s]
+Reading metadata...: 1it [00:00,  6.85it/s]
+
+Reading metadata...: 2165it [00:00, 13309.28it/s]
+Reading metadata...: 1650it [00:00, 8448.63it/s]
+Reading metadata...: 1650it [00:00, 10364.40it/s]
+Reading metadata...: 2165it [00:00, 9428.67it/s]
+Reading metadata...: 1650it [00:00, 10640.87it/s]
+Reading metadata...: 2165it [00:00, 12696.95it/s]
+Reading metadata...: 1650it [00:00, 10258.32it/s]
+Reading metadata...: 2165it [00:00, 4710.14it/s]
+Reading metadata...: 1650it [00:00, 10575.18it/s]
+Reading metadata...: 1650it [00:00, 10434.57it/s]
+Reading metadata...: 2165it [00:00, 5422.66it/s]
+Reading metadata...: 1650it [00:00, 9295.20it/s]
+Reading metadata...: 2165it [00:00, 14024.20it/s]
+Reading metadata...: 1650it [00:00, 3584.90it/s]
+Reading metadata...: 2165it [00:00, 10291.07it/s]
+Reading metadata...: 1650it [00:00, 10892.36it/s]
+Reading metadata...: 1it [00:00,  6.91it/s]
+
+Reading metadata...: 2165it [00:00, 10458.57it/s]
+Reading metadata...: 1650it [00:00, 10005.74it/s]
+Reading metadata...: 2165it [00:00, 11594.39it/s]
+Reading metadata...: 1650it [00:00, 10291.47it/s]
+Reading metadata...: 2165it [00:00, 13948.97it/s]
+Reading metadata...: 1650it [00:00, 10099.77it/s]
+Reading metadata...: 1650it [00:00, 6295.95it/s]
+Reading metadata...: 2165it [00:00, 13887.47it/s]
+Reading metadata...: 1650it [00:00, 7971.18it/s]
+Reading metadata...: 2165it [00:00, 9432.98it/s]
+Reading metadata...: 1650it [00:00, 9463.73it/s]
+Reading metadata...: 2165it [00:00, 12577.75it/s]
+Reading metadata...: 1650it [00:00, 10109.37it/s]
+Reading metadata...: 2165it [00:00, 13560.18it/s]
+Reading metadata...: 1it [00:00,  6.62it/s]
+
+Reading metadata...: 1650it [00:00, 9886.86it/s]
+Reading metadata...: 2165it [00:00, 13258.29it/s]
+Reading metadata...: 1650it [00:00, 10246.35it/s]
+Reading metadata...: 2165it [00:00, 9269.32it/s]
+Reading metadata...: 1650it [00:00, 10293.66it/s]
+Reading metadata...: 1it [00:00,  6.56it/s]
+
+Reading metadata...: 1650it [00:00, 10623.23it/s]
+Reading metadata...: 1650it [00:00, 10933.23it/s]
+Reading metadata...: 1it [00:00,  6.92it/s]
+
+
+[WARNING|logging.py:329] 2023-11-22 15:47:28,364 >> `use_cache = True` is incompatible with gradient checkpointing. Setting `use_cache = False`...
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 43%|████████████████████████████████████████▎                                                    | 26020/60000 [5:53:10<16:25:11,  1.74s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 43%|████████████████████████████████████████▎                                                    | 26040/60000 [5:56:33<95:56:28, 10.17s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 43%|████████████████████████████████████████▍                                                    | 26059/60000 [5:59:45<96:59:47, 10.29s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 43%|███████████████████████████████████████▉                                                    | 26080/60000 [6:03:25<110:16:32, 11.70s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▍                                                    | 26100/60000 [6:06:43<94:13:59, 10.01s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▍                                                    | 26120/60000 [6:10:01<94:05:24, 10.00s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▌                                                    | 26140/60000 [6:13:28<95:52:26, 10.19s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▌                                                    | 26160/60000 [6:16:51<93:55:58,  9.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▌                                                    | 26179/60000 [6:20:05<92:57:07,  9.89s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▌                                                    | 26199/60000 [6:23:22<91:17:42,  9.72s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▋                                                    | 26220/60000 [6:26:50<96:34:09, 10.29s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▋                                                    | 26240/60000 [6:30:09<92:51:54,  9.90s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▋                                                    | 26260/60000 [6:33:36<95:21:39, 10.17s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▎                                                   | 26280/60000 [6:37:20<123:53:35, 13.23s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▊                                                    | 26300/60000 [6:41:05<95:25:50, 10.19s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▊                                                    | 26320/60000 [6:44:27<94:57:22, 10.15s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▊                                                    | 26340/60000 [6:47:50<93:05:33,  9.96s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▊                                                    | 26359/60000 [6:51:11<95:25:08, 10.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▉                                                    | 26379/60000 [6:54:33<94:52:34, 10.16s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▉                                                    | 26400/60000 [6:58:09<94:40:27, 10.14s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▉                                                    | 26420/60000 [7:01:33<97:18:13, 10.43s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▌                                                   | 26440/60000 [7:05:30<102:54:30, 11.04s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████                                                    | 26460/60000 [7:08:54<96:05:51, 10.31s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████                                                    | 26480/60000 [7:12:17<95:20:20, 10.24s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████                                                    | 26500/60000 [7:15:42<94:48:09, 10.19s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▋                                                   | 26520/60000 [7:19:08<102:47:39, 11.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▏                                                   | 26540/60000 [7:22:28<95:18:33, 10.25s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████��████████████████████████████▏                                                   | 26560/60000 [7:25:48<92:21:30,  9.94s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▏                                                   | 26580/60000 [7:29:10<92:33:21,  9.97s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▊                                                   | 26600/60000 [7:32:53<132:18:31, 14.26s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▎                                                   | 26620/60000 [7:36:31<95:10:40, 10.26s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▎                                                   | 26632/60000 [7:38:26<81:37:28,  8.81s/it]
+
+ 44%|█████████████████████████████████████████▎                                                   | 26633/60000 [7:38:33<75:28:42,  8.14s/it]
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▎                                                   | 26639/60000 [7:39:31<89:10:50,  9.62s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▎                                                   | 26660/60000 [7:43:02<92:33:09,  9.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|█████████████████████████████████████████▎                                                   | 26680/60000 [7:46:24<92:53:37, 10.04s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 44%|████████████████████████████████████████▉                                                   | 26699/60000 [7:49:42<103:25:53, 11.18s/it]
+
+Reading metadata...: 1650it [00:00, 2640.63it/s]                                                 | 26700/60000 [7:49:53<100:37:44, 10.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|█████████████████████████████████████████▍                                                   | 26719/60000 [7:53:06<91:05:06,  9.85s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|█████████████████████████████████████████▍                                                   | 26739/60000 [7:57:07<96:07:19, 10.40s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌                                                                                                                                                                        | 26759/60000 [8:01:29<103:02:04, 11.16s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏                                                                                                                                                                        | 26779/60000 [8:05:05<99:22:41, 10.77s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏                                                                                                                                                                        | 26799/60000 [8:08:45<97:18:50, 10.55s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎                                                                                                                                                                        | 26819/60000 [8:12:16<98:14:08, 10.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍                                                                                                                                                                        | 26839/60000 [8:15:47<97:32:15, 10.59s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████                                                                                                                                                                        | 26859/60000 [8:19:28<104:49:20, 11.39s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏                                                                                                                                                                       | 26880/60000 [8:23:24<102:15:37, 11.12s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋                                                                                                                                                                        | 26900/60000 [8:27:00<99:42:17, 10.84s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍                                                                                                                                                                       | 26920/60000 [8:30:45<107:01:30, 11.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉                                                                                                                                                                        | 26939/60000 [8:34:11<98:30:06, 10.73s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████��██████████████████████████▌                                                                                                                                                                       | 26960/60000 [8:38:18<101:25:53, 11.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋                                                                                                                                                                       | 26980/60000 [8:42:02<100:28:45, 10.95s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                                                                                                                       | 26999/60000 [8:45:30<100:14:09, 10.93s/it]
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                                                                                                                       | 27000/60000 [8:45:41<100:50:31, 11.00s/it][INFO|trainer.py:3173] 2023-11-22 18:46:09,458 >> ***** Running Evaluation *****
+[INFO|trainer.py:3177] 2023-11-22 18:46:09,461 >>   Num examples: Unknown
+[INFO|trainer.py:3178] 2023-11-22 18:46:09,461 >>   Batch size = 4
+Reading metadata...: 1704it [00:00, 2566.26it/s]
+
+[INFO|trainer_utils.py:759] 2023-11-22 18:46:12,313 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: age, client_id, locale, gender, accent, up_votes, segment, input_length, down_votes, path. If age, client_id, locale, gender, accent, up_votes, segment, input_length, down_votes, path are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                                                                                                                       | 27000/60000 [8:57:11<100:50:31, 11.00s/it]
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                                                                                                                       | 27000/60000 [8:57:11<100:50:31, 11.00s/it][INFO|trainer.py:2896] 2023-11-22 18:57:43,033 >> Saving model checkpoint to ./checkpoint-27000
+[INFO|configuration_utils.py:462] 2023-11-22 18:57:43,068 >> Configuration saved in ./checkpoint-27000/config.json
+[INFO|configuration_utils.py:568] 2023-11-22 18:57:43,077 >> Configuration saved in ./checkpoint-27000/generation_config.json
+[INFO|modeling_utils.py:2194] 2023-11-22 18:58:14,712 >> Model weights saved in ./checkpoint-27000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:425] 2023-11-22 18:58:14,726 >> Feature extractor saved in ./checkpoint-27000/preprocessor_config.json
+[2023-11-22 18:58:17,883] [INFO] [logging.py:96:log_dist] [Rank 0] [Torch] Checkpoint global_step27000 is about to be saved!
+[2023-11-22 18:58:17,952] [INFO] [logging.py:96:log_dist] [Rank 0] Saving model checkpoint: ./checkpoint-27000/global_step27000/mp_rank_00_model_states.pt
+[2023-11-22 18:58:17,952] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving ./checkpoint-27000/global_step27000/mp_rank_00_model_states.pt...
+[2023-11-22 18:58:39,977] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved ./checkpoint-27000/global_step27000/mp_rank_00_model_states.pt.
+[2023-11-22 18:58:40,036] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving ./checkpoint-27000/global_step27000/zero_pp_rank_0_mp_rank_00_optim_states.pt...
+[2023-11-22 18:59:03,183] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved ./checkpoint-27000/global_step27000/zero_pp_rank_0_mp_rank_00_optim_states.pt.
+[2023-11-22 18:59:03,205] [INFO] [engine.py:3417:_save_zero_checkpoint] zero checkpoint saved ./checkpoint-27000/global_step27000/zero_pp_rank_0_mp_rank_00_optim_states.pt
+[2023-11-22 18:59:03,213] [INFO] [torch_checkpoint_engine.py:33:commit] [Torch] Checkpoint global_step27000 is ready now!
+[INFO|feature_extraction_utils.py:425] 2023-11-22 19:00:19,016 >> Feature extractor saved in ./preprocessor_config.json
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉                                                                                                                                                                       | 27019/60000 [9:03:28<105:06:04, 11.47s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 45%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████                                                                                                                                                                       | 27040/60000 [9:07:37<104:50:49, 11.45s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

wandb/run-20231122_100021-qrxr9o47/files/requirements.txt

@@ -0,0 +1,195 @@
+absl-py==2.0.0
+accelerate==0.24.1
+aiohttp==3.9.0
+aiosignal==1.3.1
+annotated-types==0.6.0
+anyio==4.0.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+arrow==1.3.0
+asttokens==2.4.1
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.1.0
+audioread==3.0.1
+babel==2.13.1
+beautifulsoup4==4.12.2
+bleach==6.1.0
+cachetools==5.3.2
+certifi==2023.11.17
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+comm==0.2.0
+datasets==2.15.1.dev0
+debugpy==1.8.0
+decorator==5.1.1
+deepspeed==0.12.3
+defusedxml==0.7.1
+dill==0.3.7
+docker-pycreds==0.4.0
+evaluate==0.4.1
+exceptiongroup==1.1.3
+executing==2.0.1
+fastjsonschema==2.19.0
+filelock==3.13.1
+fqdn==1.5.1
+frozenlist==1.4.0
+fsspec==2023.10.0
+gitdb==4.0.11
+gitpython==3.1.40
+google-auth-oauthlib==1.1.0
+google-auth==2.23.4
+grpcio==1.59.3
+hjson==3.1.0
+huggingface-hub==0.19.4
+idna==3.4
+iprogress==0.4
+ipykernel==6.26.0
+ipython==8.17.2
+ipywidgets==8.1.1
+isoduration==20.11.0
+jedi==0.19.1
+jinja2==3.1.2
+jiwer==3.0.3
+joblib==1.3.2
+json5==0.9.14
+jsonpointer==2.4
+jsonschema-specifications==2023.11.1
+jsonschema==4.20.0
+jupyter-client==8.6.0
+jupyter-console==6.6.3
+jupyter-core==5.5.0
+jupyter-events==0.9.0
+jupyter-lsp==2.2.0
+jupyter-server-terminals==0.4.4
+jupyter-server==2.10.1
+jupyter==1.0.0
+jupyterlab-pygments==0.2.2
+jupyterlab-server==2.25.1
+jupyterlab-widgets==3.0.9
+jupyterlab==4.0.8
+lazy-loader==0.3
+librosa==0.10.1
+llvmlite==0.41.1
+markdown==3.5.1
+markupsafe==2.1.3
+matplotlib-inline==0.1.6
+mistune==3.0.2
+more-itertools==10.1.0
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+multiprocess==0.70.15
+nbclient==0.9.0
+nbconvert==7.11.0
+nbformat==5.9.2
+nest-asyncio==1.5.8
+networkx==3.2.1
+ninja==1.11.1.1
+notebook-shim==0.2.3
+notebook==7.0.6
+numba==0.58.1
+numpy==1.26.2
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+overrides==7.4.0
+packaging==23.2
+pandas==2.1.3
+pandocfilters==1.5.0
+parso==0.8.3
+pexpect==4.8.0
+pillow==10.1.0
+pip==23.3
+platformdirs==4.0.0
+pooch==1.8.0
+prometheus-client==0.18.0
+prompt-toolkit==3.0.41
+protobuf==4.23.4
+psutil==5.9.6
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+pyarrow-hotfix==0.5
+pyarrow==14.0.1
+pyasn1-modules==0.3.0
+pyasn1==0.5.0
+pycparser==2.21
+pydantic-core==2.14.3
+pydantic==2.5.1
+pygments==2.16.1
+pynvml==11.5.0
+python-dateutil==2.8.2
+python-json-logger==2.0.7
+pytz==2023.3.post1
+pyyaml==6.0.1
+pyzmq==25.1.1
+qtconsole==5.5.1
+qtpy==2.4.1
+rapidfuzz==3.5.2
+referencing==0.31.0
+regex==2023.10.3
+requests-oauthlib==1.3.1
+requests==2.31.0
+responses==0.18.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.13.0
+rsa==4.9
+safetensors==0.4.0
+scikit-learn==1.3.2
+scipy==1.11.3
+send2trash==1.8.2
+sentry-sdk==1.35.0
+setproctitle==1.3.3
+setuptools==68.0.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soundfile==0.12.1
+soupsieve==2.5
+soxr==0.3.7
+stack-data==0.6.3
+sympy==1.12
+tensorboard-data-server==0.7.2
+tensorboard==2.15.1
+terminado==0.18.0
+threadpoolctl==3.2.0
+tinycss2==1.2.1
+tokenizers==0.15.0
+tomli==2.0.1
+torch==2.1.1
+torchaudio==2.1.1
+torchvision==0.16.1
+tornado==6.3.3
+tqdm==4.66.1
+traitlets==5.13.0
+transformers==4.36.0.dev0
+triton==2.1.0
+types-python-dateutil==2.8.19.14
+typing-extensions==4.8.0
+tzdata==2023.3
+uri-template==1.3.0
+urllib3==2.1.0
+wandb==0.16.0
+wcwidth==0.2.10
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.6.4
+werkzeug==3.0.1
+wheel==0.41.2
+widgetsnbextension==4.0.9
+xxhash==3.4.1
+yarl==1.9.2

wandb/run-20231122_100021-qrxr9o47/files/wandb-metadata.json

@@ -0,0 +1,168 @@
+{
+    "os": "Linux-5.15.123.1-microsoft-standard-WSL2-x86_64-with-glibc2.35",
+    "python": "3.10.13",
+    "heartbeatAt": "2023-11-22T08:00:22.301922",
+    "startedAt": "2023-11-22T08:00:21.614508",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--local_rank=0",
+        "--deepspeed=ds_config.json",
+        "--model_name_or_path=openai/whisper-large-v3",
+        "--train_dataset_names",
+        "mozilla-foundation/common_voice_11_0",
+        "mozilla-foundation/common_voice_11_0",
+        "google/fleurs",
+        "Finnish-NLP/css10_audio_processed",
+        "Finnish-NLP/youtube_fi_110k_preprocessed",
+        "Finnish-NLP/voxpopuli_fi_audio_processed",
+        "Finnish-NLP/parliament_audio_processed",
+        "Finnish-NLP/aalto_eduskunta_asr_audio_processed",
+        "Finnish-NLP/fbc_dialog_audio_processed",
+        "Finnish-NLP/fbc_monolog_audio_processed",
+        "--train_dataset_config_names",
+        "fi",
+        "fi",
+        "fi_fi",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "--train_dataset_split_name",
+        "train",
+        "validation",
+        "train",
+        "train",
+        "train",
+        "train",
+        "train",
+        "train",
+        "train",
+        "train",
+        "--train_dataset_text_column_names",
+        "sentence",
+        "sentence",
+        "raw_transcription",
+        "sentence",
+        "texts",
+        "sentence",
+        "sentence",
+        "sentence",
+        "sentence",
+        "sentence",
+        "--eval_dataset_name=mozilla-foundation/common_voice_11_0",
+        "--eval_dataset_config_name=fi",
+        "--eval_split_name=test",
+        "--language=finnish",
+        "--model_index_name=WhisperLargeV3Finnish",
+        "--max_steps=60000",
+        "--output_dir=./",
+        "--per_device_train_batch_size=8",
+        "--per_device_eval_batch_size=4",
+        "--gradient_accumulation_steps=2",
+        "--logging_steps=20",
+        "--learning_rate=3e-6",
+        "--warmup_steps=1000",
+        "--evaluation_strategy=steps",
+        "--eval_steps=1000",
+        "--save_strategy=steps",
+        "--save_steps=1000",
+        "--generation_max_length=225",
+        "--length_column_name=input_length",
+        "--max_duration_in_seconds=30",
+        "--text_column_name=sentence",
+        "--freeze_feature_encoder=False",
+        "--report_to=wandb",
+        "--metric_for_best_model=wer",
+        "--greater_is_better=False",
+        "--load_best_model_at_end",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--torch_compile",
+        "--overwrite_output_dir",
+        "--do_train",
+        "--do_eval",
+        "--predict_with_generate",
+        "--do_normalize_eval",
+        "--use_auth_token",
+        "--push_to_hub",
+        "--push_to_hub_model_id=WhisperLargeFinnishV3",
+        "--resume_from_checkpoint=./checkpoint-26000"
+    ],
+    "state": "running",
+    "program": "/mnt/e/run_speech_recognition_seq2seq_streaming.py",
+    "codePathLocal": "run_speech_recognition_seq2seq_streaming.py",
+    "codePath": "run_speech_recognition_seq2seq_streaming.py",
+    "host": "DESKTOP-59O9VN1",
+    "username": "rasmus",
+    "executable": "/home/rasmus/miniconda3/envs/WhisperFinetuneEnv/bin/python",
+    "cpu_count": 4,
+    "cpu_count_logical": 8,
+    "cpu_freq": {
+        "current": 3911.9949999999994,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3911.995,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 1006.853931427002,
+            "used": 37.58251190185547
+        }
+    },
+    "gpu": "NVIDIA GeForce RTX 4080",
+    "gpu_count": 1,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA GeForce RTX 4080",
+            "memory_total": 17171480576
+        }
+    ],
+    "memory": {
+        "total": 54.92573928833008
+    }
+}

wandb/run-20231122_100021-qrxr9o47/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.0592, "train/learning_rate": 1.6780677966101696e-06, "train/epoch": 0.45, "train/global_step": 27040, "_timestamp": 1700672885.8311684, "_runtime": 32864.15361738205, "_step": 52, "eval/loss": 0.19091796875, "eval/wer": 8.95212966453072, "eval/runtime": 689.9912, "eval/samples_per_second": 2.47, "eval/steps_per_second": 0.617}

wandb/run-20231122_100021-qrxr9o47/logs/debug.log

@@ -0,0 +1,27 @@
+2023-11-22 10:00:21,657 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Current SDK version is 0.16.0
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Configure stats pid to 2217649
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from /home/rasmus/.config/wandb/settings
+2023-11-22 10:00:21,658 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from /mnt/e/wandb/settings
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2023-11-22 10:00:21,659 INFO    MainThread:2217649 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq_streaming.py', 'program_abspath': '/mnt/e/run_speech_recognition_seq2seq_streaming.py', 'program': '/mnt/e/run_speech_recognition_seq2seq_streaming.py'}
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:_log_setup():524] Logging user logs to /mnt/e/wandb/run-20231122_100021-qrxr9o47/logs/debug.log
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:_log_setup():525] Logging internal logs to /mnt/e/wandb/run-20231122_100021-qrxr9o47/logs/debug-internal.log
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:init():564] calling init triggers
+2023-11-22 10:00:21,660 INFO    MainThread:2217649 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {}
+2023-11-22 10:00:21,661 INFO    MainThread:2217649 [wandb_init.py:init():614] starting backend
+2023-11-22 10:00:21,661 INFO    MainThread:2217649 [wandb_init.py:init():618] setting up manager
+2023-11-22 10:00:21,667 INFO    MainThread:2217649 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2023-11-22 10:00:21,676 INFO    MainThread:2217649 [wandb_init.py:init():624] backend started and connected
+2023-11-22 10:00:21,717 INFO    MainThread:2217649 [wandb_init.py:init():716] updated telemetry
+2023-11-22 10:00:21,722 INFO    MainThread:2217649 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2023-11-22 10:00:22,205 INFO    MainThread:2217649 [wandb_run.py:_on_init():2254] communicating current version
+2023-11-22 10:00:22,253 INFO    MainThread:2217649 [wandb_run.py:_on_init():2263] got version response 
+2023-11-22 10:00:22,253 INFO    MainThread:2217649 [wandb_init.py:init():800] starting run threads in backend
+2023-11-22 10:00:27,927 INFO    MainThread:2217649 [wandb_run.py:_console_start():2233] atexit reg
+2023-11-22 10:00:27,928 INFO    MainThread:2217649 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2023-11-22 10:00:27,929 INFO    MainThread:2217649 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2023-11-22 10:00:27,929 INFO    MainThread:2217649 [wandb_run.py:_redirect():2178] Redirects installed.
+2023-11-22 10:00:27,930 INFO    MainThread:2217649 [wandb_init.py:init():841] run started, returning control to user process
+2023-11-22 10:00:27,933 INFO    MainThread:2217649 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 51866, 'num_mel_bins': 128, 'd_model': 1280, 'encoder_layers': 32, 'encoder_attention_heads': 20, 'decoder_layers': 32, 'decoder_attention_heads': 20, 'decoder_ffn_dim': 5120, 'encoder_ffn_dim': 5120, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': True, 'num_hidden_layers': 32, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50256, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-large-v3', 'transformers_version': '4.36.0.dev0', 'model_type': 'whisper', 'forced_decoder_ids': None, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-06, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 60000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Nov22_09-55-44_DESKTOP-59O9VN1', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': 'ds_config.json', 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': './checkpoint-26000', 'hub_model_id': 'RASMUS/WhisperLargeFinnishV3', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'WhisperLargeFinnishV3', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': True, 'torch_compile_backend': 'inductor', 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}

wandb/run-20231122_100021-qrxr9o47/run-qrxr9o47.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a0be6c56b94619c3353d0f5558d25aa4eb59dad7a179876f436f10832e5519
+size 1638874