Training in progress, step 1000

.gitattributes

@@ -33,4 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240327_141031-aoxf8fxn/run-aoxf8fxn.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fadd9d0fda5b60e26d882d14f7f3b21183f6d681c79958372fb20f11f5e9c022
+oid sha256:9462752283f48808e567cfa9b61a780fca95285fcf13c52272085cb1fce9a0b8
 size 3025686376

run.sh

@@ -16,6 +16,7 @@ python run_speech_recognition_seq2seq.py \
 	--eval_steps="1000" \
 	--save_strategy="steps" \
 	--save_steps="1000" \
+	--save_total_limit="1" \
 	--generation_max_length="225" \
 	--preprocessing_num_workers="1" \
 	--dataloader_num_workers="4" \

runs/Mar27_19-04-06_hf-dgx-01/events.out.tfevents.1711562657.hf-dgx-01.1893386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a09f8a71f8134c693f79ce3983c1f5e7aeb209e0c4d1d3e01b33d4f51e8fd2
+size 14123

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8fef62a116fd373aed4cbee49637759d2e8da863586704c7abd35aeea4042a0
+oid sha256:69039d984d087c8af1175b297d7c95f99b4285dbb1d726c14590ca1ccf214e41
 size 5048

wandb/debug.log

@@ -1,28 +1,28 @@
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Current SDK version is 0.16.2
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Configure stats pid to 1482719
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/.config/wandb/settings
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/distil-large-v3-hi-ft/wandb/settings
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program_abspath': '/home/sanchit/distil-large-v3-hi-ft/run_speech_recognition_seq2seq.py', 'program': 'run_speech_recognition_seq2seq.py'}
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_init.py:_log_setup():526] Logging user logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_141031-aoxf8fxn/logs/debug.log
-2024-03-27 14:10:31,568 INFO    MainThread:1482719 [wandb_init.py:_log_setup():527] Logging internal logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_141031-aoxf8fxn/logs/debug-internal.log
-2024-03-27 14:10:31,569 INFO    MainThread:1482719 [wandb_init.py:init():566] calling init triggers
-2024-03-27 14:10:31,569 INFO    MainThread:1482719 [wandb_init.py:init():573] wandb.init called with sweep_config: {}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Current SDK version is 0.16.2
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Configure stats pid to 1893386
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/.config/wandb/settings
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/distil-large-v3-hi-ft/wandb/settings
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program_abspath': '/home/sanchit/distil-large-v3-hi-ft/run_speech_recognition_seq2seq.py', 'program': 'run_speech_recognition_seq2seq.py'}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:_log_setup():526] Logging user logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/logs/debug.log
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:_log_setup():527] Logging internal logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/logs/debug-internal.log
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():566] calling init triggers
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():573] wandb.init called with sweep_config: {}
 config: {}
-2024-03-27 14:10:31,569 INFO    MainThread:1482719 [wandb_init.py:init():616] starting backend
-2024-03-27 14:10:31,569 INFO    MainThread:1482719 [wandb_init.py:init():620] setting up manager
-2024-03-27 14:10:31,569 INFO    MainThread:1482719 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2024-03-27 14:10:31,570 INFO    MainThread:1482719 [wandb_init.py:init():628] backend started and connected
-2024-03-27 14:10:31,574 INFO    MainThread:1482719 [wandb_init.py:init():720] updated telemetry
-2024-03-27 14:10:31,631 INFO    MainThread:1482719 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
-2024-03-27 14:10:31,976 INFO    MainThread:1482719 [wandb_run.py:_on_init():2254] communicating current version
-2024-03-27 14:10:32,002 INFO    MainThread:1482719 [wandb_run.py:_on_init():2263] got version response upgrade_message: "wandb version 0.16.5 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():616] starting backend
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():620] setting up manager
+2024-03-27 19:04:18,563 INFO    MainThread:1893386 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-03-27 19:04:18,564 INFO    MainThread:1893386 [wandb_init.py:init():628] backend started and connected
+2024-03-27 19:04:18,568 INFO    MainThread:1893386 [wandb_init.py:init():720] updated telemetry
+2024-03-27 19:04:18,639 INFO    MainThread:1893386 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
+2024-03-27 19:04:18,995 INFO    MainThread:1893386 [wandb_run.py:_on_init():2254] communicating current version
+2024-03-27 19:04:19,034 INFO    MainThread:1893386 [wandb_run.py:_on_init():2263] got version response upgrade_message: "wandb version 0.16.5 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
 
-2024-03-27 14:10:32,002 INFO    MainThread:1482719 [wandb_init.py:init():804] starting run threads in backend
-2024-03-27 14:10:32,531 INFO    MainThread:1482719 [wandb_run.py:_console_start():2233] atexit reg
-2024-03-27 14:10:32,531 INFO    MainThread:1482719 [wandb_run.py:_redirect():2088] redirect: wrap_raw
-2024-03-27 14:10:32,531 INFO    MainThread:1482719 [wandb_run.py:_redirect():2153] Wrapping output streams.
-2024-03-27 14:10:32,531 INFO    MainThread:1482719 [wandb_run.py:_redirect():2178] Redirects installed.
-2024-03-27 14:10:32,532 INFO    MainThread:1482719 [wandb_init.py:init():847] run started, returning control to user process
-2024-03-27 14:10:32,534 INFO    MainThread:1482719 [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': 2, '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, 'chunk_size_feed_forward': 0, '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, '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': 'distil-whisper/distil-large-v3', 'transformers_version': '4.40.0.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': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, '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': 5000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Mar27_14-10-21_hf-dgx-01', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': 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': 4, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, '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': None, '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': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}
+2024-03-27 19:04:19,034 INFO    MainThread:1893386 [wandb_init.py:init():804] starting run threads in backend
+2024-03-27 19:04:19,118 INFO    MainThread:1893386 [wandb_run.py:_console_start():2233] atexit reg
+2024-03-27 19:04:19,118 INFO    MainThread:1893386 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_init.py:init():847] run started, returning control to user process
+2024-03-27 19:04:19,121 INFO    MainThread:1893386 [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': 2, '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, 'chunk_size_feed_forward': 0, '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, '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': 'distil-whisper/distil-large-v3', 'transformers_version': '4.40.0.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': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, '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': 5000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Mar27_19-04-06_hf-dgx-01', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': 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': 4, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, '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': None, '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': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}

wandb/run-20240327_190418-lwtbcr8s/files/config.yaml

@@ -0,0 +1,751 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.8.10
+    cli_version: 0.16.2
+    framework: huggingface
+    huggingface_version: 4.40.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1711562658.56459
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 98
+      - 100
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 98
+      - 100
+      3:
+      - 7
+      - 23
+      4: 3.8.10
+      5: 0.16.2
+      6: 4.40.0.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/grad_norm
+      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: 2
+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
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+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
+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: distil-whisper/distil-large-v3
+transformers_version:
+  desc: null
+  value: 4.40.0.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: 32
+per_device_eval_batch_size:
+  desc: null
+  value: 32
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 1
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 0.0001
+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: 5000
+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: 500
+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/Mar27_19-04-06_hf-dgx-01
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 25
+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: 1
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  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: 4
+dataloader_prefetch_factor:
+  desc: null
+  value: null
+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: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+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_v2: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+accelerator_config:
+  desc: null
+  value:
+    split_batches: false
+    dispatch_batches: null
+    even_batches: true
+    use_seedable_sampler: true
+deepspeed:
+  desc: null
+  value: null
+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:
+  - tensorboard
+  - 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
+dataloader_persistent_workers:
+  desc: null
+  value: false
+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: null
+hub_model_id:
+  desc: null
+  value: null
+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: null
+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: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: null
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+optim_target_modules:
+  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-20240327_190418-lwtbcr8s/files/output.log

@@ -0,0 +1,1168 @@
+
+  0%|                                                                                          | 0/5000 [00:00<?, ?it/s]/home/sanchit/hf/lib/python3.8/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+[WARNING|logging.py:329] 2024-03-27 19:04:32,560 >> `use_cache = True` is incompatible with gradient checkpointing. Setting `use_cache = False`...
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  0%|▍                                                                              | 25/5000 [01:42<7:34:43,  5.48s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|▊                                                                              | 49/5000 [04:07<8:22:42,  6.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|█▏                                                                             | 74/5000 [06:39<8:19:38,  6.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|█▌                                                                             | 99/5000 [08:56<8:16:05,  6.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|█▉                                                                            | 125/5000 [11:34<8:14:25,  6.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|██▎                                                                           | 149/5000 [13:49<5:08:20,  3.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|██▋                                                                           | 174/5000 [16:16<8:07:28,  6.06s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|███                                                                           | 199/5000 [18:48<8:06:00,  6.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  4%|███▍                                                                          | 224/5000 [21:12<9:32:38,  7.19s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|███▉                                                                          | 249/5000 [23:42<8:02:12,  6.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|████▎                                                                         | 275/5000 [26:19<7:56:48,  6.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|████▋                                                                         | 299/5000 [28:30<7:54:23,  6.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  6%|█████                                                                         | 324/5000 [30:40<6:38:21,  5.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|█████▍                                                                        | 349/5000 [32:57<7:12:34,  5.58s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|█████▊                                                                        | 374/5000 [35:15<7:05:59,  5.53s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|██████▏                                                                       | 399/5000 [37:31<6:58:32,  5.46s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  8%|██████▌                                                                       | 424/5000 [39:49<6:53:43,  5.42s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  9%|███████                                                                       | 449/5000 [42:16<7:51:23,  6.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|███████▍                                                                      | 475/5000 [44:39<6:45:52,  5.38s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|███████▊                                                                      | 499/5000 [46:53<7:02:26,  5.63s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|████████▏                                                                     | 524/5000 [49:11<6:54:40,  5.56s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 11%|████████▌                                                                     | 549/5000 [51:29<6:56:18,  5.61s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|████████▉                                                                     | 575/5000 [53:37<7:16:11,  5.91s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█████████▎                                                                    | 600/5000 [55:56<4:32:00,  3.71s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|█████████▋                                                                    | 624/5000 [58:19<7:22:51,  6.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 13%|█████████▊                                                                  | 649/5000 [1:00:51<7:22:34,  6.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|██████████▎                                                                 | 675/5000 [1:03:27<7:24:53,  6.17s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|██████████▋                                                                 | 700/5000 [1:05:59<7:16:57,  6.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 14%|███████████                                                                 | 724/5000 [1:08:26<7:15:14,  6.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 15%|███████████▍                                                                | 750/5000 [1:10:50<7:11:55,  6.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|███████████▊                                                                | 775/5000 [1:13:23<7:10:59,  6.12s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|████████████▏                                                               | 799/5000 [1:15:35<6:23:31,  5.48s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 16%|████████████▌                                                               | 825/5000 [1:18:13<7:05:11,  6.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 17%|████████████▉                                                               | 849/5000 [1:20:41<7:03:09,  6.12s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 17%|█████████████▎                                                              | 874/5000 [1:22:41<6:21:02,  5.54s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|█████████████▋                                                              | 900/5000 [1:25:15<6:29:20,  5.70s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 18%|██████████████                                                              | 925/5000 [1:27:33<6:20:58,  5.61s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 19%|██████████████▍                                                             | 949/5000 [1:29:44<6:00:38,  5.34s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|██████████████▊                                                             | 975/5000 [1:32:06<5:56:54,  5.32s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|███████████████                                                            | 1000/5000 [1:34:23<6:09:03,  5.54s/it][INFO|trainer.py:768] 2024-03-27 20:38:42,868 >> The following columns in the evaluation 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.
+[INFO|trainer.py:3544] 2024-03-27 20:38:42,871 >> ***** Running Evaluation *****
+[INFO|trainer.py:3546] 2024-03-27 20:38:42,871 >>   Num examples = 3123
+[INFO|trainer.py:3549] 2024-03-27 20:38:42,871 >>   Batch size = 32
+{'loss': 0.125, 'grad_norm': 1.3431593179702759, 'learning_rate': 8.900000000000001e-05, 'epoch': 4.5}
+[INFO|generation_whisper.py:1111] 2024-03-27 20:38:54,363 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+                                                                                                                        [INFO|generation_whisper.py:1111] 2024-03-27 20:39:08,530 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  0%|                                                                                            | 0/98 [00:00<?, ?it/s][INFO|generation_whisper.py:1111] 2024-03-27 20:39:20,731 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  2%|█▋                                                                                  | 2/98 [00:12<09:45,  6.10s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:39:33,353 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  3%|██▌                                                                                 | 3/98 [00:24<13:57,  8.82s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:39:45,719 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  4%|███▍                                                                                | 4/98 [00:37<15:53, 10.14s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:39:58,186 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  5%|████▎                                                                               | 5/98 [00:49<16:58, 10.95s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:40:10,256 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  6%|█████▏                                                                              | 6/98 [01:01<17:21, 11.32s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:40:22,756 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  7%|██████                                                                              | 7/98 [01:14<17:44, 11.70s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:40:35,815 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  8%|██████▊                                                                             | 8/98 [01:27<18:11, 12.13s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:40:48,410 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  9%|███████▋                                                                            | 9/98 [01:39<18:12, 12.27s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:41:00,725 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 10%|████████▍                                                                          | 10/98 [01:52<18:01, 12.29s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:41:13,064 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 11%|█████████▎                                                                         | 11/98 [02:04<17:50, 12.30s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:41:25,221 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 12%|██████████▏                                                                        | 12/98 [02:16<17:34, 12.26s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:41:37,320 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 13%|███████████                                                                        | 13/98 [02:28<17:17, 12.21s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:41:49,529 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 14%|███████████▊                                                                       | 14/98 [02:40<17:05, 12.21s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:42:02,322 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 15%|████████████▋                                                                      | 15/98 [02:53<17:07, 12.39s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:42:14,865 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 16%|█████████████▌                                                                     | 16/98 [03:06<16:59, 12.43s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:42:26,915 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 17%|██████████████▍                                                                    | 17/98 [03:18<16:37, 12.32s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:42:39,306 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 18%|███████████████▏                                                                   | 18/98 [03:30<16:27, 12.34s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:42:51,947 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 19%|████████████████                                                                   | 19/98 [03:43<16:21, 12.43s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:43:04,435 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 20%|████████████████▉                                                                  | 20/98 [03:55<16:10, 12.45s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:43:17,092 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 21%|█████████████████▊                                                                 | 21/98 [04:08<16:03, 12.51s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:43:29,623 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 22%|██████████████████▋                                                                | 22/98 [04:21<15:51, 12.52s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:43:41,880 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 23%|███████████████████▍                                                               | 23/98 [04:33<15:32, 12.44s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:43:54,170 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 24%|████████████████████▎                                                              | 24/98 [04:45<15:17, 12.39s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:44:06,407 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 26%|█████████████████████▏                                                             | 25/98 [04:57<15:01, 12.35s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:44:18,895 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 27%|██████████████████████                                                             | 26/98 [05:10<14:52, 12.39s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:44:31,076 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 28%|██████████████████████▊                                                            | 27/98 [05:22<14:35, 12.33s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:44:43,369 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 29%|███████████████████████▋                                                           | 28/98 [05:34<14:22, 12.32s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:44:55,737 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 30%|████████████████████████▌                                                          | 29/98 [05:47<14:10, 12.33s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:45:08,272 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 31%|█████████████████████████▍                                                         | 30/98 [05:59<14:02, 12.39s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:45:20,453 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 32%|██████████████████████████▎                                                        | 31/98 [06:11<13:46, 12.33s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:45:32,520 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 33%|███████████████████████████                                                        | 32/98 [06:23<13:28, 12.25s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:45:44,789 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 34%|███████████████████████████▉                                                       | 33/98 [06:36<13:16, 12.26s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:45:56,701 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 35%|████████████████████████████▊                                                      | 34/98 [06:48<12:57, 12.15s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:46:09,446 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 36%|█████████████████████████████▋                                                     | 35/98 [07:00<12:56, 12.33s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:46:21,603 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 37%|██████████████████████████████▍                                                    | 36/98 [07:13<12:41, 12.28s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:46:34,264 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 38%|███████████████████████████████▎                                                   | 37/98 [07:25<12:35, 12.39s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:46:46,595 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 39%|████████████████████████████████▏                                                  | 38/98 [07:38<12:22, 12.37s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:46:59,053 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 40%|█████████████████████████████████                                                  | 39/98 [07:50<12:11, 12.40s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:10,902 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 41%|█████████████████████████████████▉                                                 | 40/98 [08:02<11:49, 12.24s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:20,081 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 42%|██████████████████████████████████▋                                                | 41/98 [08:11<10:45, 11.32s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:25,687 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 43%|███████████████████████████████████▌                                               | 42/98 [08:17<08:57,  9.60s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:31,276 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 44%|████████████████████████████████████▍                                              | 43/98 [08:22<07:42,  8.40s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:36,866 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 45%|█████████████████████████████████████▎                                             | 44/98 [08:28<06:48,  7.56s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:49,750 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 46%|██████████████████████████████████████                                             | 45/98 [08:41<08:05,  9.15s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:47:59,779 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 47%|██████████████████████████████████████▉                                            | 46/98 [08:51<08:09,  9.42s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:48:11,034 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 48%|███████████████████████████████████████▊                                           | 47/98 [09:02<08:28,  9.97s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:48:19,962 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 49%|████████████████████████████████████████▋                                          | 48/98 [09:11<08:02,  9.66s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:48:27,683 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 50%|█████████████████████████████████████████▌                                         | 49/98 [09:19<07:24,  9.07s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:48:41,338 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 51%|██████████████████████████████████████████▎                                        | 50/98 [09:32<08:21, 10.45s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:48:51,077 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 52%|███████████████████████████████████████████▏                                       | 51/98 [09:42<08:01, 10.24s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:02,926 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 53%|████████████████████████████████████████████                                       | 52/98 [09:54<08:13, 10.72s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:12,936 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 54%|████████████████████████████████████████████▉                                      | 53/98 [10:04<07:52, 10.51s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:26,952 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 55%|█████████████████████████████████████████████▋                                     | 54/98 [10:18<08:28, 11.56s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:35,958 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 56%|██████████████████████████████████████████████▌                                    | 55/98 [10:27<07:44, 10.79s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:43,258 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 57%|███████████████████████████████████████████████▍                                   | 56/98 [10:34<06:49,  9.75s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:49:57,125 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 58%|████████████████████████████████████████████████▎                                  | 57/98 [10:48<07:30, 10.98s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:50:07,215 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 59%|█████████████████████████████████████████████████                                  | 58/98 [10:58<07:08, 10.72s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:50:20,553 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 60%|█████████████████████████████████████████████████▉                                 | 59/98 [11:12<07:28, 11.50s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:50:29,864 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 61%|██████████████████████████████████████████████████▊                                | 60/98 [11:21<06:52, 10.85s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:50:42,112 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 62%|███████████████████████████████████████████████████▋                               | 61/98 [11:33<06:56, 11.26s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:50:55,720 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 63%|████████████████████████████████████████████████████▌                              | 62/98 [11:47<07:10, 11.97s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:51:04,551 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 64%|█████████████████████████████████████████████████████▎                             | 63/98 [11:56<06:25, 11.03s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:51:17,578 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 65%|██████████████████████████████████████████████████████▏                            | 64/98 [12:09<06:35, 11.63s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:51:26,598 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 66%|███████████████████████████████████████████████████████                            | 65/98 [12:18<05:57, 10.85s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:51:39,417 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 67%|███████████████████████████████████████████████████████▉                           | 66/98 [12:30<06:05, 11.44s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:51:48,597 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 68%|████████████████████████████████████████████████████████▋                          | 67/98 [12:40<05:33, 10.76s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:01,301 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 69%|█████████████████████████████████████████████████████████▌                         | 68/98 [12:52<05:40, 11.34s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:10,667 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 70%|██████████████████████████████████████████████████████████▍                        | 69/98 [13:02<05:11, 10.75s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:23,355 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 71%|███████████████████████████████████████████████████████████▎                       | 70/98 [13:14<05:17, 11.33s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:32,654 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 72%|████████████████████████████████████████████████████████████▏                      | 71/98 [13:24<04:49, 10.72s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:44,957 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 73%|████████████████████████████████████████████████████████████▉                      | 72/98 [13:36<04:51, 11.20s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:52:54,552 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 74%|█████████████████████████████████████████████████████████████▊                     | 73/98 [13:46<04:27, 10.72s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:53:04,284 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 76%|██████████████████████████████████████████████████████████████▋                    | 74/98 [13:55<04:10, 10.42s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:53:14,743 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 77%|███████████████████████████████████████████████████████████████▌                   | 75/98 [14:06<03:59, 10.43s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:53:27,643 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 78%|████████████████████████████████████████████████████████████████▎                  | 76/98 [14:19<04:05, 11.17s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:53:37,693 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 79%|█████████████████████████████████████████████████████████████████▏                 | 77/98 [14:29<03:47, 10.84s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:53:51,003 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 80%|██████████████████████████████████████████████████████████████████                 | 78/98 [14:42<03:51, 11.58s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:04,626 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 81%|██████████████████████████████████████████████████████████████████▉                | 79/98 [14:56<03:51, 12.19s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:16,550 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 82%|███████████████████████████████████████████████████████████████████▊               | 80/98 [15:08<03:38, 12.11s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:22,154 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 83%|████████████████████████████████████████████████████████████████████▌              | 81/98 [15:13<02:52, 10.16s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:29,173 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 84%|█████████████████████████████████████████████████████████████████████▍             | 82/98 [15:20<02:27,  9.22s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:41,896 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 85%|████████████████████████████████���█████████████████████████████████████▎            | 83/98 [15:33<02:34, 10.27s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:54:51,984 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 86%|███████████████████████████████████████████████████████████████████████▏           | 84/98 [15:43<02:23, 10.21s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:55:05,787 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 87%|███████████████████████████████████████████████████████████████████████▉           | 85/98 [15:57<02:26, 11.29s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:55:18,825 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 88%|████████████████████████████████████████████████████████████████████████▊          | 86/98 [16:10<02:21, 11.81s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:55:28,223 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 89%|█████████████████████████████████████████████████████████████████████████▋         | 87/98 [16:19<02:02, 11.09s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:55:40,560 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 90%|██████████████████████████████████████████████████████████████████████████▌        | 88/98 [16:32<01:54, 11.46s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:55:50,658 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 91%|███████████████████████████████████████████████████████████████████████████▍       | 89/98 [16:42<01:39, 11.05s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:56:04,429 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 92%|████████████████████████████████████████████████████████████████████████████▏      | 90/98 [16:55<01:34, 11.87s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:56:15,135 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 93%|█████████████████████████████████████████████████████████████████████████████      | 91/98 [17:06<01:20, 11.52s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:56:28,795 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 95%|██████████████████████████████████████████████████████████████████████████████▊    | 93/98 [17:30<00:57, 11.57s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:56:38,973 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 96%|███████████████████████████████████████████████████████████████████████████████▌   | 94/98 [17:44<00:48, 12.17s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:56:52,561 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 97%|████████████████████████████████████████████████████████████████████████████████▍  | 95/98 [17:54<00:34, 11.54s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:57:02,626 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 98%|█████████████████████████████████████████████████████████████████████████████████▎ | 96/98 [18:07<00:24, 12.23s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:57:16,451 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 99%|██████████████████████████████████████████████████████████████████████████████████▏| 97/98 [18:18<00:11, 11.61s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:57:26,758 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 99%|██████████████████████████████████████████████████████████████████████████████████▏| 97/98 [18:18<00:11, 11.61s/it][INFO|generation_whisper.py:1111] 2024-03-27 20:57:26,758 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+[WARNING|configuration_utils.py:447] 2024-03-27 20:57:36,255 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.of task=transcribe.
+[WARNING|configuration_utils.py:447] 2024-03-27 20:57:36,255 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.of task=transcribe.
+Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]}
+[INFO|configuration_utils.py:471] 2024-03-27 20:57:36,256 >> Configuration saved in ./checkpoint-1000/config.json
+[INFO|configuration_utils.py:697] 2024-03-27 20:57:36,257 >> Configuration saved in ./checkpoint-1000/generation_config.json
+[INFO|modeling_utils.py:2475] 2024-03-27 20:57:44,189 >> Model weights saved in ./checkpoint-1000/model.safetensors
+[INFO|feature_extraction_utils.py:424] 2024-03-27 20:57:44,190 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:424] 2024-03-27 20:58:06,811 >> Feature extractor saved in ./preprocessor_config.json
+/home/sanchit/hf/lib/python3.8/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+
+
+
+
+
+
+
+
+
+
+
+

wandb/run-20240327_190418-lwtbcr8s/files/requirements.txt

@@ -0,0 +1,246 @@
+absl-py==2.1.0
+accelerate==0.27.2
+aiohttp==3.9.3
+aiosignal==1.3.1
+anyio==4.2.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+arrow==1.3.0
+asttokens==2.4.1
+astunparse==1.6.3
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.2.0
+audioread==3.0.1
+av==11.0.0
+babel==2.14.0
+backcall==0.2.0
+beautifulsoup4==4.12.3
+bitsandbytes==0.42.0
+bleach==6.1.0
+cached-property==1.5.2
+cachetools==5.3.2
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+chex==0.1.7
+click==8.1.7
+coloredlogs==15.0.1
+comm==0.2.1
+contourpy==1.1.1
+ctranslate2==4.1.0
+cycler==0.12.1
+datasets==2.18.0
+debugpy==1.8.0
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.7
+dm-tree==0.1.8
+docker-pycreds==0.4.0
+docstring-parser==0.15
+einops==0.7.0
+etils==1.3.0
+evaluate==0.4.1
+exceptiongroup==1.2.0
+executing==2.0.1
+fastjsonschema==2.19.1
+filelock==3.13.1
+flash-attn==2.5.3
+flatbuffers==23.5.26
+flax==0.7.2
+fonttools==4.48.1
+fqdn==1.5.1
+frozenlist==1.4.1
+fsspec==2024.2.0
+gast==0.4.0
+gitdb==4.0.11
+gitpython==3.1.41
+google-auth-oauthlib==1.0.0
+google-auth==2.27.0
+google-pasta==0.2.0
+grpcio==1.60.1
+h11==0.14.0
+h5py==3.10.0
+httpcore==1.0.2
+httpx==0.26.0
+huggingface-hub==0.21.4
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+iniconfig==2.0.0
+ipdb==0.13.13
+ipykernel==6.29.2
+ipython==8.12.3
+isoduration==20.11.0
+jax==0.4.13
+jaxlib==0.4.13
+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==2023.12.1
+jsonschema==4.21.1
+jupyter-client==8.6.0
+jupyter-core==5.7.1
+jupyter-events==0.9.0
+jupyter-lsp==2.2.2
+jupyter-server-terminals==0.5.2
+jupyter-server==2.12.5
+jupyterlab-pygments==0.3.0
+jupyterlab-server==2.25.2
+jupyterlab==4.1.0
+keras==2.13.1
+kiwisolver==1.4.5
+lazy-loader==0.3
+libclang==16.0.6
+librosa==0.10.1
+llvmlite==0.41.1
+markdown-it-py==3.0.0
+markdown==3.5.2
+markupsafe==2.1.3
+matplotlib-inline==0.1.6
+matplotlib==3.7.4
+mdurl==0.1.2
+mistune==3.0.2
+ml-dtypes==0.2.0
+more-itertools==10.2.0
+mpmath==1.2.1
+msclap==1.3.3
+msgpack==1.0.7
+multidict==6.0.5
+multiprocess==0.70.15
+nbclient==0.9.0
+nbconvert==7.16.0
+nbformat==5.9.2
+nest-asyncio==1.6.0
+networkx==3.0rc1
+ninja==1.11.1.1
+notebook-shim==0.2.3
+numba==0.58.1
+numpy==1.24.3
+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==2.19.3
+nvidia-nvjitlink-cu12==12.1.105
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.17.1
+openai-whisper==20231117
+opt-einsum==3.3.0
+optax==0.1.8
+orbax-checkpoint==0.2.3
+overrides==7.7.0
+packaging==23.2
+pandas==2.0.3
+pandocfilters==1.5.1
+parameterized==0.9.0
+parso==0.8.3
+peft==0.8.2
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==9.3.0
+pip==24.0
+pkg-resources==0.0.0
+pkgutil-resolve-name==1.3.10
+platformdirs==4.2.0
+pluggy==1.4.0
+pooch==1.8.0
+prometheus-client==0.19.0
+prompt-toolkit==3.0.43
+protobuf==4.25.2
+psutil==5.9.8
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow-hotfix==0.6
+pyarrow==15.0.0
+pyasn1-modules==0.3.0
+pyasn1==0.5.1
+pycparser==2.21
+pygments==2.17.2
+pyparsing==3.1.1
+pytest==7.4.4
+python-dateutil==2.8.2
+python-json-logger==2.0.7
+pytorch-triton==3.0.0+901819d2b6
+pytz==2024.1
+pyyaml==6.0.1
+pyzmq==25.1.2
+rapidfuzz==3.6.1
+referencing==0.33.0
+regex==2023.12.25
+requests-oauthlib==1.3.1
+requests==2.31.0
+responses==0.18.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.7.0
+rpds-py==0.17.1
+rsa==4.9
+safetensors==0.4.2
+scikit-learn==1.3.2
+scipy==1.10.1
+send2trash==1.8.2
+sentry-sdk==1.40.0
+setproctitle==1.3.3
+setuptools==44.0.0
+shtab==1.7.0
+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==1.11.1
+tensorboard-data-server==0.7.2
+tensorboard==2.13.0
+tensorflow-cpu==2.13.1
+tensorflow-estimator==2.13.0
+tensorflow-io-gcs-filesystem==0.34.0
+tensorstore==0.1.45
+termcolor==2.4.0
+terminado==0.18.0
+threadpoolctl==3.2.0
+tiktoken==0.6.0
+tinycss2==1.2.1
+tokenizers==0.15.1
+tomli==2.0.1
+toolz==0.12.1
+torch==2.2.1
+torchaudio==2.2.1
+torchlibrosa==0.1.0
+torchvision==0.17.1
+tornado==6.4
+tqdm==4.66.1
+traitlets==5.14.1
+transformers==4.39.0.dev0
+triton==2.2.0
+trl==0.7.11
+types-python-dateutil==2.8.19.20240106
+typing-extensions==4.9.0
+tyro==0.7.3
+tzdata==2023.4
+uri-template==1.3.0
+urllib3==2.2.0
+wandb==0.16.2
+wcwidth==0.2.13
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.7.0
+werkzeug==3.0.1
+wheel==0.42.0
+wrapt==1.16.0
+xxhash==3.4.1
+yarl==1.9.4
+zipp==3.17.0

wandb/run-20240327_190418-lwtbcr8s/files/wandb-metadata.json

@@ -0,0 +1,738 @@
+{
+    "os": "Linux-5.4.0-166-generic-x86_64-with-glibc2.29",
+    "python": "3.8.10",
+    "heartbeatAt": "2024-03-27T18:04:19.090782",
+    "startedAt": "2024-03-27T18:04:18.560848",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "--model_name_or_path=distil-whisper/distil-large-v3",
+        "--dataset_name=mozilla-foundation/common_voice_16_1",
+        "--dataset_config_name=hi",
+        "--language=hindi",
+        "--train_split_name=train+validation",
+        "--eval_split_name=test",
+        "--max_steps=5000",
+        "--output_dir=./",
+        "--per_device_train_batch_size=32",
+        "--per_device_eval_batch_size=32",
+        "--logging_steps=25",
+        "--learning_rate=1e-4",
+        "--warmup_steps=500",
+        "--evaluation_strategy=steps",
+        "--eval_steps=1000",
+        "--save_strategy=steps",
+        "--save_steps=1000",
+        "--save_total_limit=1",
+        "--generation_max_length=225",
+        "--preprocessing_num_workers=1",
+        "--dataloader_num_workers=4",
+        "--length_column_name=input_length",
+        "--max_duration_in_seconds=30",
+        "--text_column_name=sentence",
+        "--freeze_feature_encoder=False",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--overwrite_output_dir",
+        "--do_train",
+        "--do_eval",
+        "--predict_with_generate",
+        "--use_auth_token",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "run_speech_recognition_seq2seq.py",
+    "codePathLocal": "run_speech_recognition_seq2seq.py",
+    "codePath": "run_speech_recognition_seq2seq.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/distil-large-v3-hi-ft",
+        "commit": "40c686df113c0e98e7363c1bd523f58d11848fc0"
+    },
+    "email": "sanchit@huggingface.co",
+    "root": "/home/sanchit/distil-large-v3-hi-ft",
+    "host": "hf-dgx-01",
+    "username": "sanchit",
+    "executable": "/home/sanchit/hf/bin/python",
+    "cpu_count": 64,
+    "cpu_count_logical": 128,
+    "cpu_freq": {
+        "current": 2290.4996484375006,
+        "min": 1500.0,
+        "max": 2250.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2186.729,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1795.542,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1792.045,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1791.339,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1791.496,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1742.02,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1692.095,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1658.911,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1606.212,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1606.808,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1606.448,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2094.446,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1734.944,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1736.215,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2489.415,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1737.217,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1695.232,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2416.542,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1737.614,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1599.452,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1772.758,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1738.087,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2311.378,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1735.599,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1620.967,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1864.863,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1729.177,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1728.804,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1788.133,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1795.255,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1794.306,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1794.529,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1733.742,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2473.813,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1932.309,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1727.805,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1730.935,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1729.65,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1730.989,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2002.554,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2089.927,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1727.843,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1728.434,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2271.01,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3370.134,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1687.104,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1688.345,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1694.029,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3295.66,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1684.621,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1686.668,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1687.585,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1727.907,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1728.023,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1727.835,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2090.043,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2245.903,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2202.881,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2284.838,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1598.829,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1656.082,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1661.638,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1649.714,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1655.626,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3027.152,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2017.291,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2012.466,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1990.236,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2114.394,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2095.433,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2096.911,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1840.403,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2203.59,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2185.592,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2201.94,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2018.775,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2200.874,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1873.351,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3369.243,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2235.133,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3367.352,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3364.254,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2202.453,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2038.768,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2233.914,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2182.285,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2302.527,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2185.247,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2132.843,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2971.398,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2055.752,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1567.353,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1609.825,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1606.242,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1610.589,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1617.499,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2398.668,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3020.272,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2053.074,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2141.083,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2182.762,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2190.047,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2209.589,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2072.985,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2427.726,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2205.137,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2197.942,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2208.468,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3307.897,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2210.539,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2580.208,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2487.416,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 3360.967,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2409.573,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2399.184,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2400.551,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2453.642,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1814.426,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2440.557,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2422.632,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1919.862,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 2519.195,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1666.938,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1669.157,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1794.328,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1797.233,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1793.218,
+            "min": 1500.0,
+            "max": 2250.0
+        },
+        {
+            "current": 1790.531,
+            "min": 1500.0,
+            "max": 2250.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 1757.8785285949707,
+            "used": 1614.0720481872559
+        }
+    },
+    "gpu": "NVIDIA A100-SXM4-80GB",
+    "gpu_count": 5,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA DGX Display",
+            "memory_total": 4294967296
+        },
+        {
+            "name": "NVIDIA A100-SXM4-80GB",
+            "memory_total": 85899345920
+        }
+    ],
+    "memory": {
+        "total": 503.5396919250488
+    }
+}

wandb/run-20240327_190418-lwtbcr8s/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 0.125, "train/grad_norm": 1.3431593179702759, "train/learning_rate": 8.900000000000001e-05, "train/epoch": 4.5, "train/global_step": 1000, "_timestamp": 1711569456.2541177, "_runtime": 6797.689527750015, "_step": 40, "eval/loss": 0.4658036530017853, "eval/wer": 0.43003940353859227, "eval/runtime": 1133.3821, "eval/samples_per_second": 2.755, "eval/steps_per_second": 0.086}

wandb/run-20240327_190418-lwtbcr8s/logs/debug.log

@@ -0,0 +1,28 @@
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Current SDK version is 0.16.2
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Configure stats pid to 1893386
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/.config/wandb/settings
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from /home/sanchit/distil-large-v3-hi-ft/wandb/settings
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program_abspath': '/home/sanchit/distil-large-v3-hi-ft/run_speech_recognition_seq2seq.py', 'program': 'run_speech_recognition_seq2seq.py'}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:_log_setup():526] Logging user logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/logs/debug.log
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:_log_setup():527] Logging internal logs to /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/logs/debug-internal.log
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():566] calling init triggers
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():573] wandb.init called with sweep_config: {}
+config: {}
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():616] starting backend
+2024-03-27 19:04:18,562 INFO    MainThread:1893386 [wandb_init.py:init():620] setting up manager
+2024-03-27 19:04:18,563 INFO    MainThread:1893386 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-03-27 19:04:18,564 INFO    MainThread:1893386 [wandb_init.py:init():628] backend started and connected
+2024-03-27 19:04:18,568 INFO    MainThread:1893386 [wandb_init.py:init():720] updated telemetry
+2024-03-27 19:04:18,639 INFO    MainThread:1893386 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
+2024-03-27 19:04:18,995 INFO    MainThread:1893386 [wandb_run.py:_on_init():2254] communicating current version
+2024-03-27 19:04:19,034 INFO    MainThread:1893386 [wandb_run.py:_on_init():2263] got version response upgrade_message: "wandb version 0.16.5 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-03-27 19:04:19,034 INFO    MainThread:1893386 [wandb_init.py:init():804] starting run threads in backend
+2024-03-27 19:04:19,118 INFO    MainThread:1893386 [wandb_run.py:_console_start():2233] atexit reg
+2024-03-27 19:04:19,118 INFO    MainThread:1893386 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-03-27 19:04:19,119 INFO    MainThread:1893386 [wandb_init.py:init():847] run started, returning control to user process
+2024-03-27 19:04:19,121 INFO    MainThread:1893386 [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': 2, '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, 'chunk_size_feed_forward': 0, '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, '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': 'distil-whisper/distil-large-v3', 'transformers_version': '4.40.0.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': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, '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': 5000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Mar27_19-04-06_hf-dgx-01', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': 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': 4, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, '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': None, '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': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}

wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ba05f1e017ca342d3b2973674cb98788723f936678e1306d0f19a09b282999
+size 1430398