diff --git a/.gitignore b/.gitignore index 95bb79ae7ea05a653c01203991568b6d9c023405..7a5cff24f2ee6bd67bb6727cf6099f9f34bc1411 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,3 @@ __pycache__ .venv -.vscode -distilhubert-finetuned-cry-detector -distilhubert-finetuned-mixed-data +.vscode \ No newline at end of file diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/config.json b/distilhubert-finetuned-cry-detector/checkpoint-170/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-170/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..970d1de4e0db7e0412c02a6b6a5584ed5de41c1e --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12a1b9a24a4e6c65e2a4cfef5a14bb3968815375ff10b423d324c8475fae74a +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-170/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1aafe6fe9562d9858102affdd59a68cdf99f1683 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:435b96196eb0ed805f14f064a35d0757c0d693014f991ba8af93c9bee59d0dbe +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-170/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..c784825bd6d9050a8ffcfc9c68090bbba06f2528 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8284a213c68ebec7c890dfc113fc2b6a01af65d958e077d0ff89531cb54f031 +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-170/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..018e149aeb62627eb07c8ed04816872335d24bf8 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80195c13720277b88ef44d4298c322ee9ab935ad2c366470453549aba8f696c4 +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-170/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b87c1bac0a7a8804229c7c7cb05873ce5c220062 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/trainer_state.json @@ -0,0 +1,66 @@ +{ + "best_metric": 0.9787545787545787, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170", + "epoch": 1.9912152269399708, + "eval_steps": 500, + "global_step": 170, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9787545787545787, + "eval_f1": 0.9788099592207686, + "eval_loss": 0.07009062170982361, + "eval_precision": 0.9789268917610887, + "eval_recall": 0.9787545787545787, + "eval_runtime": 6.2624, + "eval_samples_per_second": 217.969, + "eval_steps_per_second": 27.306, + "step": 170 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.483401519872e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-170/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-170/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-170/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/config.json b/distilhubert-finetuned-cry-detector/checkpoint-256/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-256/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0ee301fc126db948e09a0cf12ebaf3ee60a4806 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae93606e0068417987c861ef701d781fdc293c56822885b321b538499e3ed9f +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-256/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7c7220d4f3d1e938305a07ebb26321762c3094d --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68055f1bc468b50d717af19d82688b5760436263325799749b5a24328beeda08 +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-256/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..f26d0d5b1cd0d1e829eed9ffc23c5ffee2bf377d --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb65cebf665d8f9d6639246c9118d47b498a1653a2714b80f3ab7cf865354d2 +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-256/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..00dbca0c3768dc3045e541f6c9783677d8e5c351 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9f438092711eef2a53f839a45eb7a09d5325f42278d87a60fc53d358b3a04a +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-256/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b338a264a94251d6094257c4e82da8d9c15142e5 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/trainer_state.json @@ -0,0 +1,78 @@ +{ + "best_metric": 0.9831501831501831, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-256", + "epoch": 2.998535871156662, + "eval_steps": 500, + "global_step": 256, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9787545787545787, + "eval_f1": 0.9788099592207686, + "eval_loss": 0.07009062170982361, + "eval_precision": 0.9789268917610887, + "eval_recall": 0.9787545787545787, + "eval_runtime": 6.2624, + "eval_samples_per_second": 217.969, + "eval_steps_per_second": 27.306, + "step": 170 + }, + { + "epoch": 2.998535871156662, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9831941055888854, + "eval_loss": 0.06720960885286331, + "eval_precision": 0.9832999772248476, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9845, + "eval_samples_per_second": 228.09, + "eval_steps_per_second": 28.574, + "step": 256 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.725102279808e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-256/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-256/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-256/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/config.json b/distilhubert-finetuned-cry-detector/checkpoint-341/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-341/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d6e159665e8a23ddb085470466d985b2cc0c52a --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7944ecc75fe28e156d4c1967e013e12ebf361ba4a1e84d569b5656c10cbbf99f +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-341/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..474ce35709bccc6b4996b98cb75f6ffe0f19b04e --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea12d3536b65dc14e8f5d189dcebc6f55fd60a564653f1c462a9b8fd994950d +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-341/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..85e4aa5265dad48fafb163bbd4eaa03216e0f11e --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536f0fc323ef01dfbff60019f8668ef49478dbb6c4c93f5f8458a58aa887a7ac +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-341/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..da8511260c9636cc7d9bcec0c3392bfbc59ec5d3 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370ad1e402d1e5afefc57f92c683bc92a503cf91bcf53776012b25e1805f62fc +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-341/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a3127f52b9eae5f2310338260bb6159161a41bd4 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/trainer_state.json @@ -0,0 +1,90 @@ +{ + "best_metric": 0.991941391941392, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", + "epoch": 3.994143484626647, + "eval_steps": 500, + "global_step": 341, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9787545787545787, + "eval_f1": 0.9788099592207686, + "eval_loss": 0.07009062170982361, + "eval_precision": 0.9789268917610887, + "eval_recall": 0.9787545787545787, + "eval_runtime": 6.2624, + "eval_samples_per_second": 217.969, + "eval_steps_per_second": 27.306, + "step": 170 + }, + { + "epoch": 2.998535871156662, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9831941055888854, + "eval_loss": 0.06720960885286331, + "eval_precision": 0.9832999772248476, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9845, + "eval_samples_per_second": 228.09, + "eval_steps_per_second": 28.574, + "step": 256 + }, + { + "epoch": 3.994143484626647, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.04145079106092453, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.1222, + "eval_samples_per_second": 222.958, + "eval_steps_per_second": 27.931, + "step": 341 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.966803039744e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-341/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-341/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-341/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/config.json b/distilhubert-finetuned-cry-detector/checkpoint-426/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-426/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40e42894fea84b3487a8e019665920772c7ecfe9 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccd0853b18fcef29f6c50370c40938c3fc157e6d6ab4f5a8cc0ee4de4c2a330 +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-426/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1854f76a3aad589600291c3f40383d77f129cd61 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cf1896c9f8575d9e790921f864e581859c2dd6014460c20f2981f52787a4a4 +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-426/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..7d554835ca9a77da05a3ec4c25e32aa6b68deccb --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67844b2b0357256b4d8649897b9ffa4d435413091b8757335f941cac6b60c370 +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-426/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a89efae5254e3592d2d5203ed5f84b811fc226c9 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77da8d31fe5105cdaffd1de28e960ad7041d43ef167667465d3bd1e966ae27b0 +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-426/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a8266b4c2cb62d48037fc15d11b66a9d6a13eb22 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/trainer_state.json @@ -0,0 +1,102 @@ +{ + "best_metric": 0.991941391941392, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", + "epoch": 4.989751098096632, + "eval_steps": 500, + "global_step": 426, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9787545787545787, + "eval_f1": 0.9788099592207686, + "eval_loss": 0.07009062170982361, + "eval_precision": 0.9789268917610887, + "eval_recall": 0.9787545787545787, + "eval_runtime": 6.2624, + "eval_samples_per_second": 217.969, + "eval_steps_per_second": 27.306, + "step": 170 + }, + { + "epoch": 2.998535871156662, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9831941055888854, + "eval_loss": 0.06720960885286331, + "eval_precision": 0.9832999772248476, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9845, + "eval_samples_per_second": 228.09, + "eval_steps_per_second": 28.574, + "step": 256 + }, + { + "epoch": 3.994143484626647, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.04145079106092453, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.1222, + "eval_samples_per_second": 222.958, + "eval_steps_per_second": 27.931, + "step": 341 + }, + { + "epoch": 4.989751098096632, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.037522196769714355, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.1601, + "eval_samples_per_second": 221.586, + "eval_steps_per_second": 27.759, + "step": 426 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.20850379968e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-426/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-426/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-426/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/config.json b/distilhubert-finetuned-cry-detector/checkpoint-510/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-510/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0592e2befeef017c51faa7a459aa6d66f107408c --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4372169de69c47d33397222523009d2fdeed9d3854c7375e8590a1241949291d +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-510/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b7ba41710c64b4bca9ef581dd42aba975d5b683 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294fd84ccb3eb4e7c39baaa641e3c8f3ea74bdf3b1a46a34208e1257b56d0054 +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-510/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..f65c6fc15ab9db96a45f8de6bb412218a3ab01df --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cc7449d67ace31a2b3ec5d56092754753743418fdab51384b92915bdf832f21 +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-510/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cb84876c4984e93d09b4dce5f9a650573fc8eb4 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10e0f825c3d4b6dffd76325c743990d99721ef8a75e18bb498ded17f46b6918 +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-510/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6da02fe8b087a53d07c71810e47dc4c8778a8ddb --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/trainer_state.json @@ -0,0 +1,121 @@ +{ + "best_metric": 0.991941391941392, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", + "epoch": 5.973645680819912, + "eval_steps": 500, + "global_step": 510, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9787545787545787, + "eval_f1": 0.9788099592207686, + "eval_loss": 0.07009062170982361, + "eval_precision": 0.9789268917610887, + "eval_recall": 0.9787545787545787, + "eval_runtime": 6.2624, + "eval_samples_per_second": 217.969, + "eval_steps_per_second": 27.306, + "step": 170 + }, + { + "epoch": 2.998535871156662, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9831941055888854, + "eval_loss": 0.06720960885286331, + "eval_precision": 0.9832999772248476, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9845, + "eval_samples_per_second": 228.09, + "eval_steps_per_second": 28.574, + "step": 256 + }, + { + "epoch": 3.994143484626647, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.04145079106092453, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.1222, + "eval_samples_per_second": 222.958, + "eval_steps_per_second": 27.931, + "step": 341 + }, + { + "epoch": 4.989751098096632, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.037522196769714355, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.1601, + "eval_samples_per_second": 221.586, + "eval_steps_per_second": 27.759, + "step": 426 + }, + { + "epoch": 5.856515373352855, + "grad_norm": 0.05031043663620949, + "learning_rate": 9.520643773712201e-08, + "loss": 0.056, + "step": 500 + }, + { + "epoch": 5.973645680819912, + "eval_accuracy": 0.991941391941392, + "eval_f1": 0.9919444380146174, + "eval_loss": 0.037607260048389435, + "eval_precision": 0.9919487758943655, + "eval_recall": 0.991941391941392, + "eval_runtime": 6.0461, + "eval_samples_per_second": 225.765, + "eval_steps_per_second": 28.283, + "step": 510 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 7.418366078592e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-510/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-510/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-510/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/config.json b/distilhubert-finetuned-cry-detector/checkpoint-85/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/model.safetensors b/distilhubert-finetuned-cry-detector/checkpoint-85/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da5d08886cd1210822e6660015bef007f2604742 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b5dedf2a772cebe9534bac9b4f4b2cae3c78d018c5e1a5a81305bf2945ebd1 +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/optimizer.pt b/distilhubert-finetuned-cry-detector/checkpoint-85/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f54ec0140987e5134f7d3ce95edde0704c9da569 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71f3df5c54a5867dc09782b6116eb9a8f338591753dc3c3c099a4abc235053a +size 189552570 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/rng_state.pth b/distilhubert-finetuned-cry-detector/checkpoint-85/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cd3048efdf016e5b13f4edbbdcb4f71b66e16f4 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e1c11b94b090a41a3c1ccee3afde4077ab65e935c7dfa8559b5a7860ed3169 +size 14308 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/scheduler.pt b/distilhubert-finetuned-cry-detector/checkpoint-85/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3174b42fc5865b814137cdbed16897499dd21f5 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e2a8e76399fe02fb40c65ecf028aa55e02ca8e63c8cb6c0fbb6115c6f4d731 +size 1064 diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/trainer_state.json b/distilhubert-finetuned-cry-detector/checkpoint-85/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..57ea89271c17b3a1bfc6fd2e37ed223af6058047 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": 0.9597069597069597, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-85", + "epoch": 0.9956076134699854, + "eval_steps": 500, + "global_step": 85, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9597069597069597, + "eval_f1": 0.9599836188656065, + "eval_loss": 0.12706419825553894, + "eval_precision": 0.960694098126733, + "eval_recall": 0.9597069597069597, + "eval_runtime": 6.1839, + "eval_samples_per_second": 220.733, + "eval_steps_per_second": 27.652, + "step": 85 + } + ], + "logging_steps": 500, + "max_steps": 510, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.241700759936e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-cry-detector/checkpoint-85/training_args.bin b/distilhubert-finetuned-cry-detector/checkpoint-85/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/checkpoint-85/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-cry-detector/config.json b/distilhubert-finetuned-cry-detector/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/distilhubert-finetuned-cry-detector/config.json @@ -0,0 +1,81 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "crying", + "1": "no_crying" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "crying": 0, + "no_crying": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-cry-detector/model.safetensors b/distilhubert-finetuned-cry-detector/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d6e159665e8a23ddb085470466d985b2cc0c52a --- /dev/null +++ b/distilhubert-finetuned-cry-detector/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7944ecc75fe28e156d4c1967e013e12ebf361ba4a1e84d569b5656c10cbbf99f +size 94763496 diff --git a/distilhubert-finetuned-cry-detector/runs/Sep06_15-54-59_ubumarcos/events.out.tfevents.1725630900.ubumarcos b/distilhubert-finetuned-cry-detector/runs/Sep06_15-54-59_ubumarcos/events.out.tfevents.1725630900.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..7dd1b1d1ee7dd615261a9e660f1573ed918d12c8 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/runs/Sep06_15-54-59_ubumarcos/events.out.tfevents.1725630900.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1acef9821029fd1212d748efd26c746ef609728916bb04756b301a4027aed9d7 +size 5850 diff --git a/distilhubert-finetuned-cry-detector/runs/Sep06_17-32-26_ubumarcos/events.out.tfevents.1725636747.ubumarcos b/distilhubert-finetuned-cry-detector/runs/Sep06_17-32-26_ubumarcos/events.out.tfevents.1725636747.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..778a9eb6b39e0cbe23f35fd7e98f228ae50d55c7 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/runs/Sep06_17-32-26_ubumarcos/events.out.tfevents.1725636747.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89395943d8de67b3553472ad01aa836188c676359cc9b10e225dd488dbb1d7ac +size 9238 diff --git a/distilhubert-finetuned-cry-detector/training_args.bin b/distilhubert-finetuned-cry-detector/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..bff11f0a04d7786ba1f282509a88be97e3ad2b24 --- /dev/null +++ b/distilhubert-finetuned-cry-detector/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f29e363429f3041b65000237638d975c16df70ba592fd3c2ce610392338bd3 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/config.json b/distilhubert-finetuned-mixed-data/checkpoint-121/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-121/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2cdb8a0e31fb735f47862b027ec36ac666afbb1 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812ef836989997aee1750c6a31d13aded72b6dae0ab04fd01133347e51bda632 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-121/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..52f2aafed2a1b44838f93be9a7ec52eace2f9cc3 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b91c228c28ab83396ebeb72f916cb49ca20c381b7dfed4afee579a8270e4469 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-121/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..45ecf54a6054c26572dbc5197b72382acf2bb107 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d192864925cf93da2109df89709998e97445c2f0e2cb3b0965d9757c92c461fb +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-121/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcf6a5e28d8e6ecf76343f883a769bcbd2c01648 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffbebf6c867de7592a335cbf1d413aa003dc4d34f2b64687b903aabde1a8765c +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-121/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..da61dc72c3b00fca16736e4841c71d79415de3c0 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/trainer_state.json @@ -0,0 +1,102 @@ +{ + "best_metric": 0.8475452196382429, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121", + "epoch": 4.989690721649485, + "eval_steps": 500, + "global_step": 121, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.7568400176e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-121/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-121/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-121/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/config.json b/distilhubert-finetuned-mixed-data/checkpoint-145/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-145/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..888b065a5500942406faed616cd8dde29010f766 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b504655a65a38520d0d800a1931a7f35b792c02532530da059066aa4e8a54a06 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-145/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd2c6382e2bb3d5f02fe1474e7083227ccb502bc --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04c1f3ec1916ec289cb211cbae2db133f656c3034323cacf312b109b1e43c41 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-145/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e6f910234c1c71dfa337286bd802c3271b6b027 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0867bb3588983088e1ae19ae31c54b18cd181442273a375c356a0362c53a9a5 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-145/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ff4981b5aef05572c4c8e53c6d9ac129ca600df --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c96f63d225b344458caccba583518a8d54c069124a93e668862e1fe8af48062 +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-145/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f3c356aefdf30127f89e043c1bf90b334751fd91 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/trainer_state.json @@ -0,0 +1,114 @@ +{ + "best_metric": 0.8604651162790697, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-145", + "epoch": 5.979381443298969, + "eval_steps": 500, + "global_step": 145, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + }, + { + "epoch": 5.979381443298969, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.8544807697335172, + "eval_loss": 0.3910721242427826, + "eval_precision": 0.8630186766891821, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.746, + "eval_samples_per_second": 221.647, + "eval_steps_per_second": 28.064, + "step": 145 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.10820802112e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-145/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-145/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-145/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/config.json b/distilhubert-finetuned-mixed-data/checkpoint-169/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-169/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4264f5f47fe1a124c016e72d6c579e432b20a714 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc5d06305a8a9b42b9f3fda9d6daff1c45d3ccbb5f7dc3ba486ba85018609c8 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-169/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1a771f16222e1dff0a5936e1aebddf745459066 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9cd0f1f6795d3c8d4fcb226d2fca891f414573b127d3acca2ceee650822b26 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-169/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..227ad56e63341ddcfd2891326574cc0c15e6b468 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d85d4b435d4ac4552bb46f32d5f63a55dbc65baaa5af6a14b6b39e968f4b8e +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-169/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4a8be15100edadd22bb2dd06facb8c1d41d02f7 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c06141f493a3ac959d15469bdae5b577f3da9e55aced3d27f611c36184c1ab +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-169/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..356a49fb34c6d8145e8a5947c4ea4ef959a5a468 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/trainer_state.json @@ -0,0 +1,126 @@ +{ + "best_metric": 0.8656330749354005, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-169", + "epoch": 6.969072164948454, + "eval_steps": 500, + "global_step": 169, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + }, + { + "epoch": 5.979381443298969, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.8544807697335172, + "eval_loss": 0.3910721242427826, + "eval_precision": 0.8630186766891821, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.746, + "eval_samples_per_second": 221.647, + "eval_steps_per_second": 28.064, + "step": 145 + }, + { + "epoch": 6.969072164948454, + "eval_accuracy": 0.8656330749354005, + "eval_f1": 0.8624793288389035, + "eval_loss": 0.384008526802063, + "eval_precision": 0.8694521764574283, + "eval_recall": 0.8656330749354005, + "eval_runtime": 1.7429, + "eval_samples_per_second": 222.045, + "eval_steps_per_second": 28.114, + "step": 169 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.45957602464e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-169/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-169/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-169/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/config.json b/distilhubert-finetuned-mixed-data/checkpoint-194/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-194/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e333c2a756ace291400811950ad84a9f0b44e72 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d3c8ab6464feca528dbd779fffa178fa8c54e1aa626c7b6af82b51d350034a +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-194/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..208b0664c9836703e9cea964bd81e6dfa0498380 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396ad1b328739c1e91b3b93f1475a85ada29934d91ca3d2a2f931b5dcf6f2011 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-194/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8dfee6203431b1c5ac7be87a3e7e223f86001ab --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a98371a8e546887d8a0cf63952365049758fe889acd42fc72eb734ef3af0332 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-194/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e78e2767c398f7d56c324fa19b8357dc561f15a7 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f844180816496e4a1cc8acf4e080448617f948dad646f622c1569a848338e2f +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-194/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2488ac38732a7de9d5086b68f8baea7e1730bd68 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/trainer_state.json @@ -0,0 +1,138 @@ +{ + "best_metric": 0.8708010335917312, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-194", + "epoch": 8.0, + "eval_steps": 500, + "global_step": 194, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + }, + { + "epoch": 5.979381443298969, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.8544807697335172, + "eval_loss": 0.3910721242427826, + "eval_precision": 0.8630186766891821, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.746, + "eval_samples_per_second": 221.647, + "eval_steps_per_second": 28.064, + "step": 145 + }, + { + "epoch": 6.969072164948454, + "eval_accuracy": 0.8656330749354005, + "eval_f1": 0.8624793288389035, + "eval_loss": 0.384008526802063, + "eval_precision": 0.8694521764574283, + "eval_recall": 0.8656330749354005, + "eval_runtime": 1.7429, + "eval_samples_per_second": 222.045, + "eval_steps_per_second": 28.114, + "step": 169 + }, + { + "epoch": 8.0, + "eval_accuracy": 0.8708010335917312, + "eval_f1": 0.8684113678605722, + "eval_loss": 0.36738282442092896, + "eval_precision": 0.8707162397260695, + "eval_recall": 0.8708010335917312, + "eval_runtime": 1.7081, + "eval_samples_per_second": 226.563, + "eval_steps_per_second": 28.686, + "step": 194 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.81094402816e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-194/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-194/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-194/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/config.json b/distilhubert-finetuned-mixed-data/checkpoint-218/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-218/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bc7f57644910e10442b9d59502826830afc9d66 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e481e77f89d46235cd616c6da58c443db661f69c2466cf503a200365fa4e77a2 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-218/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd5f7772f4d2570b69232a87dc2fc5f29f896b90 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8f1918c3aac31b0172992d1deb009c2ade6459beef8b26a934ae549fc6c065 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-218/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..d430fc02ebee6a20553d790dd1badb8940dbf287 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87f5981b8629d20da8d7bb452f1f8e311534ac9a1fbf9cf6ca9f99f281c14bfa +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-218/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc9d8bcc631cbb5818105b6e334a593886c0618d --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3883f947b72cb03bc5e119879f5b2b2d83cbbec4ebf4270eda5103d63206321e +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-218/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a45659ef624a3f95c2b110e4892ce6b45bdc80bd --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/trainer_state.json @@ -0,0 +1,150 @@ +{ + "best_metric": 0.8708010335917312, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-194", + "epoch": 8.989690721649485, + "eval_steps": 500, + "global_step": 218, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + }, + { + "epoch": 5.979381443298969, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.8544807697335172, + "eval_loss": 0.3910721242427826, + "eval_precision": 0.8630186766891821, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.746, + "eval_samples_per_second": 221.647, + "eval_steps_per_second": 28.064, + "step": 145 + }, + { + "epoch": 6.969072164948454, + "eval_accuracy": 0.8656330749354005, + "eval_f1": 0.8624793288389035, + "eval_loss": 0.384008526802063, + "eval_precision": 0.8694521764574283, + "eval_recall": 0.8656330749354005, + "eval_runtime": 1.7429, + "eval_samples_per_second": 222.045, + "eval_steps_per_second": 28.114, + "step": 169 + }, + { + "epoch": 8.0, + "eval_accuracy": 0.8708010335917312, + "eval_f1": 0.8684113678605722, + "eval_loss": 0.36738282442092896, + "eval_precision": 0.8707162397260695, + "eval_recall": 0.8708010335917312, + "eval_runtime": 1.7081, + "eval_samples_per_second": 226.563, + "eval_steps_per_second": 28.686, + "step": 194 + }, + { + "epoch": 8.989690721649485, + "eval_accuracy": 0.8630490956072352, + "eval_f1": 0.8592830012203397, + "eval_loss": 0.3704662024974823, + "eval_precision": 0.8623599751505485, + "eval_recall": 0.8630490956072352, + "eval_runtime": 1.7284, + "eval_samples_per_second": 223.903, + "eval_steps_per_second": 28.349, + "step": 218 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.16231203168e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-218/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-218/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-218/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/config.json b/distilhubert-finetuned-mixed-data/checkpoint-24/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-24/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e9e8c007f36a78c711695a584976e37ef31551e --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40031b71d7dd3e7a94060e464453d1b72931895f1679cb27f4c2cfc56253f2cf +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-24/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3032d12bddd329293f5043cb4cf3a9c6e48128fc --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e28890b1508529b3102a609a70cef4a07840dec28102fd82dd79685fed2268 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-24/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f4c7eea6d1ab45f43fd742de99363e16c650680 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202bb63ca18cd0b022bafcf6cf19faa822d2e1dbc2cdaf6b5a9bdcbe21ca7562 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-24/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ee53e956118ac9f720a0e14603d760615d18c97 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493f7d829970a517c374f92a4ecf91a5fa4999ea96aaffd4f6176aab38dca974 +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-24/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6e46fec44f2e1a67f279a73463b0ef8d5e54488e --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/trainer_state.json @@ -0,0 +1,54 @@ +{ + "best_metric": 0.6330749354005168, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-24", + "epoch": 0.9896907216494846, + "eval_steps": 500, + "global_step": 24, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3513680035200000.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-24/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-24/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-24/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/config.json b/distilhubert-finetuned-mixed-data/checkpoint-240/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-240/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5869d2d57867718f1259cb281db749836414e267 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c8f6e4fc9100f4d71122912bb94edac220c70b21797f95d3fd43a259c18007 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-240/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d82f7a6703f04d9421c39f4dcaf2206534259b32 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7753185d05213d7c63e37954ef51607daff76f5320cebcc1a63a5d4b1e7a5bf0 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-240/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..f57e4d76994d4bd3bfbf12e11715065eb279d996 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa08735989c33a0829468f970a7eea2caca2871ec3d3c1f5b6fd56289f75077f +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-240/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d2d67065a3f1f7808e213b383fc1a758a9ba63d --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:017cd29b99a3062420550f8b286fdfd5821ab72a9ad7a19ba06fce7ecd44b7bb +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-240/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1b9d99a8498f807f979653fd975cb4e947ce7188 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/trainer_state.json @@ -0,0 +1,162 @@ +{ + "best_metric": 0.8708010335917312, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-194", + "epoch": 9.896907216494846, + "eval_steps": 500, + "global_step": 240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + }, + { + "epoch": 4.989690721649485, + "eval_accuracy": 0.8475452196382429, + "eval_f1": 0.8448866153449188, + "eval_loss": 0.4369746148586273, + "eval_precision": 0.8463304077554821, + "eval_recall": 0.8475452196382429, + "eval_runtime": 1.74, + "eval_samples_per_second": 222.416, + "eval_steps_per_second": 28.161, + "step": 121 + }, + { + "epoch": 5.979381443298969, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.8544807697335172, + "eval_loss": 0.3910721242427826, + "eval_precision": 0.8630186766891821, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.746, + "eval_samples_per_second": 221.647, + "eval_steps_per_second": 28.064, + "step": 145 + }, + { + "epoch": 6.969072164948454, + "eval_accuracy": 0.8656330749354005, + "eval_f1": 0.8624793288389035, + "eval_loss": 0.384008526802063, + "eval_precision": 0.8694521764574283, + "eval_recall": 0.8656330749354005, + "eval_runtime": 1.7429, + "eval_samples_per_second": 222.045, + "eval_steps_per_second": 28.114, + "step": 169 + }, + { + "epoch": 8.0, + "eval_accuracy": 0.8708010335917312, + "eval_f1": 0.8684113678605722, + "eval_loss": 0.36738282442092896, + "eval_precision": 0.8707162397260695, + "eval_recall": 0.8708010335917312, + "eval_runtime": 1.7081, + "eval_samples_per_second": 226.563, + "eval_steps_per_second": 28.686, + "step": 194 + }, + { + "epoch": 8.989690721649485, + "eval_accuracy": 0.8630490956072352, + "eval_f1": 0.8592830012203397, + "eval_loss": 0.3704662024974823, + "eval_precision": 0.8623599751505485, + "eval_recall": 0.8630490956072352, + "eval_runtime": 1.7284, + "eval_samples_per_second": 223.903, + "eval_steps_per_second": 28.349, + "step": 218 + }, + { + "epoch": 9.896907216494846, + "eval_accuracy": 0.8604651162790697, + "eval_f1": 0.85550218853575, + "eval_loss": 0.37302064895629883, + "eval_precision": 0.8601366936250657, + "eval_recall": 0.8604651162790697, + "eval_runtime": 1.7164, + "eval_samples_per_second": 225.471, + "eval_steps_per_second": 28.548, + "step": 240 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.478884368832e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-240/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-240/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-240/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/config.json b/distilhubert-finetuned-mixed-data/checkpoint-48/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-48/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac2452a79347a9f4538642c34e4dbff46c76d2b8 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85d8324e2cc0662626b451c83f10af38e4710c030fa65047970f4c116d42c82 +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-48/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e1d28f88e1a5fcc4cf7f4220db13b5f39dd5bdb --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139d7018f70cda75f3decd600c1c3767f8cd6c615da07ee4e7337012ca1c3f67 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-48/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e08d33cbd45ccaf4be57defb1be8d18eeb838fd --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9cbdb2c6d711d4b07d5c44fbe2571bdf0b92fd58e29512676ddee90a5f1c70 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-48/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..62841262e150c6b876130d7e545529c600343fa1 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e2c0c04f0a5c0b5768f3f6177e83d61c948b88a99a4442db2a8a0b5298d525 +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-48/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..475c9a4356a468a7a170c4e4d2fa5b2d29a9ccdc --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/trainer_state.json @@ -0,0 +1,66 @@ +{ + "best_metric": 0.648578811369509, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-48", + "epoch": 1.9793814432989691, + "eval_steps": 500, + "global_step": 48, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7027360070400000.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-48/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-48/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-48/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/config.json b/distilhubert-finetuned-mixed-data/checkpoint-72/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-72/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af7cd477d6a51cd761be393863ba9344b17b89c3 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da980738e5e3f5b3c8be20886ede2ac8d9cbc79ea1f44669d29aa54a89fdd5ec +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-72/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..021f819960ca5592e511d1fcfda6be12d4a7fea5 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:030f832f0c965e9c74b6a8c8d3ad26251e1015f557b8b8fa4703c904e7bcc961 +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-72/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..b93e09e14fe55e82da3283abf076091c6113915c --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3522560e565218b6663eeab3b8d9ab4726c5760eb23fe1339f732fa6c6f00a0 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-72/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..404d6738ae6f15618ab17cf291f948828349bac2 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5ad3684d25c11edf8fc44e63cf6ba00ef086b3af08ecb73f9b1b28fc71a5f3 +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-72/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..688031bb2246d45474ff9304e839bbf1a4a93206 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/trainer_state.json @@ -0,0 +1,78 @@ +{ + "best_metric": 0.7622739018087855, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-72", + "epoch": 2.9690721649484537, + "eval_steps": 500, + "global_step": 72, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.05410401056e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-72/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-72/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-72/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/config.json b/distilhubert-finetuned-mixed-data/checkpoint-97/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/model.safetensors b/distilhubert-finetuned-mixed-data/checkpoint-97/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..31a219fa48a80d5425deb4cb00c1531bf70517da --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f1c034f8ce547ab7352770538770acf5885097bb9c4e33c986d0a1f7d3871c +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/optimizer.pt b/distilhubert-finetuned-mixed-data/checkpoint-97/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bd7a4d0baf7a2c073fe4ff36d489c3ab8f5fb1a --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea85a4d63af7f0e636b4d63ef8f0ab5182a7f33d9b6140be2c0ac779d7bf669d +size 189556666 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/rng_state.pth b/distilhubert-finetuned-mixed-data/checkpoint-97/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff0227323d54cad4887c264819256f17b8157c46 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d439ef21ecde4890958d6f1346e10eacaa9ba5ddeb4801bf0e15758a657d4e8 +size 14308 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/scheduler.pt b/distilhubert-finetuned-mixed-data/checkpoint-97/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..033ba96452e68e63b02c39ede67fe7c5b4f5eec3 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651c880f99ea02b04c16ff3f62505280950a22d917ee50923064872dfb2c8703 +size 1064 diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/trainer_state.json b/distilhubert-finetuned-mixed-data/checkpoint-97/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..7a20ec41433307cdc5f35d155b9afd64f417a1dc --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/trainer_state.json @@ -0,0 +1,90 @@ +{ + "best_metric": 0.8165374677002584, + "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-97", + "epoch": 4.0, + "eval_steps": 500, + "global_step": 97, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9896907216494846, + "eval_accuracy": 0.6330749354005168, + "eval_f1": 0.5595352399182605, + "eval_loss": 0.9406359791755676, + "eval_precision": 0.5371302620976882, + "eval_recall": 0.6330749354005168, + "eval_runtime": 1.7053, + "eval_samples_per_second": 226.94, + "eval_steps_per_second": 28.734, + "step": 24 + }, + { + "epoch": 1.9793814432989691, + "eval_accuracy": 0.648578811369509, + "eval_f1": 0.6477021416649994, + "eval_loss": 0.780166745185852, + "eval_precision": 0.6774262760064707, + "eval_recall": 0.648578811369509, + "eval_runtime": 1.7536, + "eval_samples_per_second": 220.692, + "eval_steps_per_second": 27.943, + "step": 48 + }, + { + "epoch": 2.9690721649484537, + "eval_accuracy": 0.7622739018087855, + "eval_f1": 0.7570575757476992, + "eval_loss": 0.6011457443237305, + "eval_precision": 0.7764632789142593, + "eval_recall": 0.7622739018087855, + "eval_runtime": 1.7377, + "eval_samples_per_second": 222.71, + "eval_steps_per_second": 28.198, + "step": 72 + }, + { + "epoch": 4.0, + "eval_accuracy": 0.8165374677002584, + "eval_f1": 0.8076125604953357, + "eval_loss": 0.5131179690361023, + "eval_precision": 0.8269359136036004, + "eval_recall": 0.8165374677002584, + "eval_runtime": 1.7268, + "eval_samples_per_second": 224.11, + "eval_steps_per_second": 28.376, + "step": 97 + } + ], + "logging_steps": 500, + "max_steps": 240, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 3, + "early_stopping_threshold": 0.0 + }, + "attributes": { + "early_stopping_patience_counter": 0 + } + }, + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.40547201408e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/distilhubert-finetuned-mixed-data/checkpoint-97/training_args.bin b/distilhubert-finetuned-mixed-data/checkpoint-97/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/checkpoint-97/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/distilhubert-finetuned-mixed-data/config.json b/distilhubert-finetuned-mixed-data/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d08a8bd80e93984973b2e4be199a10eccbe7cae --- /dev/null +++ b/distilhubert-finetuned-mixed-data/config.json @@ -0,0 +1,85 @@ +{ + "_name_or_path": "ntu-spml/distilhubert", + "activation_dropout": 0.1, + "apply_spec_augment": false, + "architectures": [ + "HubertForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": false, + "final_dropout": 0.0, + "finetuning_task": "audio-classification", + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "id2label": { + "0": "1s_normal", + "1": "1s_pain", + "2": "1s_hunger", + "3": "1s_asphyxia" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "1s_asphyxia": 3, + "1s_hunger": 2, + "1s_normal": 0, + "1s_pain": 1 + }, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 2, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/distilhubert-finetuned-mixed-data/model.safetensors b/distilhubert-finetuned-mixed-data/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e333c2a756ace291400811950ad84a9f0b44e72 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d3c8ab6464feca528dbd779fffa178fa8c54e1aa626c7b6af82b51d350034a +size 94765560 diff --git a/distilhubert-finetuned-mixed-data/runs/Sep06_15-59-37_ubumarcos/events.out.tfevents.1725631178.ubumarcos b/distilhubert-finetuned-mixed-data/runs/Sep06_15-59-37_ubumarcos/events.out.tfevents.1725631178.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..f39cc658f8b2fd3d7a15826899d3c3e7cce16242 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/runs/Sep06_15-59-37_ubumarcos/events.out.tfevents.1725631178.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d121a4efcbc718574c904f0abd8573c1e6d337153c47941f49050657e1125b8 +size 5934 diff --git a/distilhubert-finetuned-mixed-data/runs/Sep06_17-26-28_ubumarcos/events.out.tfevents.1725636389.ubumarcos b/distilhubert-finetuned-mixed-data/runs/Sep06_17-26-28_ubumarcos/events.out.tfevents.1725636389.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..5ff11d50fe590bbfdf729be0c5dd503b9ba494bd --- /dev/null +++ b/distilhubert-finetuned-mixed-data/runs/Sep06_17-26-28_ubumarcos/events.out.tfevents.1725636389.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8429b4ed9e2f512ac3ca2da7fd904b71edac89d0e5119ab9398ce3c28752138 +size 10964 diff --git a/distilhubert-finetuned-mixed-data/training_args.bin b/distilhubert-finetuned-mixed-data/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..704bec313412b5bc2af349d9bad62b729d831aa9 --- /dev/null +++ b/distilhubert-finetuned-mixed-data/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d54561089e0dfe6a74c774cae0dc42a2bf49a8e6a8a96acd883461ec0d33a1 +size 5240 diff --git a/model.py b/model.py index 6f906e6d7a885dff9fabbcbeb4d901630d9c62e3..5baf625fb974c9293e0ce762b46614b8fde703f8 100644 --- a/model.py +++ b/model.py @@ -175,8 +175,8 @@ def load_config(model_name): return model_config if __name__ == "__main__": - config = load_config(clasificador) # PARA MONITOR - # config = load_config(monitor) # PARA CLASIFICADOR + config = load_config(clasificador) # PARA CAMBIAR MODELOS + # config = load_config(monitor) # PARA CAMBIAR MODELOS training_args = config["training_args"] output_dir = config["output_dir"] dataset_path = config["dataset_path"] diff --git a/models_config.json b/models_config.json index cfa143bc1694434e5b11928a213e297c6944e719..29b31470b28ba52689a452c6a8f57ebe31edc70a 100644 --- a/models_config.json +++ b/models_config.json @@ -30,7 +30,7 @@ "dataset_path": "data/mixed_data", "output_dir": "distilhubert-finetuned-mixed-data", "training_args": { - "num_train_epochs": 2, + "num_train_epochs": 10, "learning_rate": 0.0001, "warmup_ratio": 0.001, "output_dir": "distilhubert-finetuned-mixed-data",