diff --git a/README.md b/README.md index be579bc95277f8c0ff84913be5c67b1b4c186407..bd6eec152fe2ad3281aa09a39749dde7ea53f58e 100644 --- a/README.md +++ b/README.md @@ -6,9 +6,9 @@ tags: - generated_from_trainer metrics: - accuracy +- f1 - precision - recall -- f1 model-index: - name: distilhubert-finetuned-cry-detector results: [] @@ -21,11 +21,12 @@ should probably proofread and complete it, then remove this comment. --> This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset. It achieves the following results on the evaluation set: -- Loss: 0.0338 -- Accuracy: 0.9912 -- Precision: 0.9912 -- Recall: 0.9912 -- F1: 0.9912 +- Loss: 0.2255 +- Accuracy: 0.9883 +- F1: 0.9883 +- Precision: 0.9883 +- Recall: 0.9883 +- Confusion Matrix: [[960, 10], [6, 389]] ## Model description @@ -45,30 +46,29 @@ More information needed The following hyperparameters were used during training: - learning_rate: 3e-05 -- train_batch_size: 8 -- eval_batch_size: 8 +- train_batch_size: 64 +- eval_batch_size: 64 - seed: 123 -- gradient_accumulation_steps: 8 -- total_train_batch_size: 64 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 -- lr_scheduler_type: cosine -- lr_scheduler_warmup_ratio: 0.001 -- num_epochs: 10 +- lr_scheduler_type: cosine_with_restarts +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 20 +- label_smoothing_factor: 0.1 ### Training results -| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | -|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| -| No log | 0.9956 | 85 | 0.1197 | 0.9538 | 0.9535 | 0.9538 | 0.9536 | -| No log | 1.9912 | 170 | 0.0601 | 0.9832 | 0.9831 | 0.9832 | 0.9831 | -| No log | 2.9985 | 256 | 0.0506 | 0.9868 | 0.9868 | 0.9868 | 0.9868 | -| No log | 3.9941 | 341 | 0.0461 | 0.9861 | 0.9864 | 0.9861 | 0.9862 | -| No log | 4.9898 | 426 | 0.0439 | 0.9890 | 0.9891 | 0.9890 | 0.9890 | -| 0.0779 | 5.9971 | 512 | 0.0396 | 0.9905 | 0.9905 | 0.9905 | 0.9905 | -| 0.0779 | 6.9927 | 597 | 0.0350 | 0.9919 | 0.9919 | 0.9919 | 0.9919 | -| 0.0779 | 8.0 | 683 | 0.0335 | 0.9912 | 0.9912 | 0.9912 | 0.9912 | -| 0.0779 | 8.9956 | 768 | 0.0337 | 0.9912 | 0.9912 | 0.9912 | 0.9912 | -| 0.0779 | 9.9561 | 850 | 0.0338 | 0.9912 | 0.9912 | 0.9912 | 0.9912 | +| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Confusion Matrix | +|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:----------------------:| +| 0.3124 | 2.3256 | 100 | 0.2739 | 0.9641 | 0.9640 | 0.9640 | 0.9641 | [[948, 22], [27, 368]] | +| 0.2337 | 4.6512 | 200 | 0.2385 | 0.9736 | 0.9737 | 0.9737 | 0.9736 | [[950, 20], [16, 379]] | +| 0.2064 | 6.9767 | 300 | 0.2295 | 0.9832 | 0.9832 | 0.9832 | 0.9832 | [[958, 12], [11, 384]] | +| 0.2023 | 9.3023 | 400 | 0.2277 | 0.9868 | 0.9869 | 0.9870 | 0.9868 | [[957, 13], [5, 390]] | +| 0.2003 | 11.6279 | 500 | 0.2254 | 0.9875 | 0.9876 | 0.9876 | 0.9875 | [[960, 10], [7, 388]] | +| 0.2002 | 13.9535 | 600 | 0.2259 | 0.9875 | 0.9876 | 0.9876 | 0.9875 | [[959, 11], [6, 389]] | +| 0.1994 | 16.2791 | 700 | 0.2255 | 0.9883 | 0.9883 | 0.9883 | 0.9883 | [[960, 10], [6, 389]] | +| 0.1997 | 18.6047 | 800 | 0.2254 | 0.9883 | 0.9883 | 0.9883 | 0.9883 | [[960, 10], [6, 389]] | ### Framework versions diff --git a/checkpoint-500/config.json b/checkpoint-500/config.json new file mode 100644 index 0000000000000000000000000000000000000000..23cd00c8f7806f9961fb35e24a24f5d256693560 --- /dev/null +++ b/checkpoint-500/config.json @@ -0,0 +1,77 @@ +{ + "_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, + "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/checkpoint-500/model.safetensors b/checkpoint-500/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71d49746b07b61ac8a62ae90f21aaf040a270b98 --- /dev/null +++ b/checkpoint-500/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2041eca5fb53efe367a7173ea2f8134639376a8725d1d5e4b703cc5c51091e4d +size 94763496 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..db8553d9fd2aa6a42cc58d98519fe8eef90d6336 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2841bddb32715286bfd37dc809b01547440737cf55fe0e6e2a35570191638266 +size 189552570 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..59ce8dc9759ee1785d910b3ea3dcf7891079d3c4 --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf8e41f94dcf5fdfbe835965b81bc88cbb914f7ffde871d0d81b52f38954873 +size 14308 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b62a101c35a57b97a31a3c813a95ba47714a5472 --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3642500630a8e812e7a47cae4b5478d99e83284cbb8a78eda0b69e2f157e5321 +size 1064 diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..16b569fbd15cdf2710cab75892b0f4669ad4f5b3 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,222 @@ +{ + "best_metric": 0.9875597008648797, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-500", + "epoch": 11.627906976744185, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.1627906976744187, + "grad_norm": 0.9607858657836914, + "learning_rate": 1.744186046511628e-05, + "loss": 0.6124, + "step": 50 + }, + { + "epoch": 2.3255813953488373, + "grad_norm": 2.0142862796783447, + "learning_rate": 2.997578868976474e-05, + "loss": 0.3124, + "step": 100 + }, + { + "epoch": 2.3255813953488373, + "eval_accuracy": 0.9641025641025641, + "eval_confusion_matrix": [ + [ + 948, + 22 + ], + [ + 27, + 368 + ] + ], + "eval_f1": 0.9640343817214121, + "eval_loss": 0.2739163041114807, + "eval_precision": 0.9639973701512163, + "eval_recall": 0.9641025641025641, + "eval_runtime": 3.48, + "eval_samples_per_second": 392.238, + "eval_steps_per_second": 6.322, + "step": 100 + }, + { + "epoch": 3.488372093023256, + "grad_norm": 1.6254416704177856, + "learning_rate": 2.9496736466239833e-05, + "loss": 0.2509, + "step": 150 + }, + { + "epoch": 4.651162790697675, + "grad_norm": 1.0478523969650269, + "learning_rate": 2.8422656841613377e-05, + "loss": 0.2337, + "step": 200 + }, + { + "epoch": 4.651162790697675, + "eval_accuracy": 0.9736263736263736, + "eval_confusion_matrix": [ + [ + 950, + 20 + ], + [ + 16, + 379 + ] + ], + "eval_f1": 0.9736655604528286, + "eval_loss": 0.23845618963241577, + "eval_precision": 0.9737247242968067, + "eval_recall": 0.9736263736263736, + "eval_runtime": 3.3782, + "eval_samples_per_second": 404.066, + "eval_steps_per_second": 6.512, + "step": 200 + }, + { + "epoch": 5.813953488372093, + "grad_norm": 0.19202682375907898, + "learning_rate": 2.679763606999547e-05, + "loss": 0.213, + "step": 250 + }, + { + "epoch": 6.976744186046512, + "grad_norm": 3.5125396251678467, + "learning_rate": 2.4688374121322346e-05, + "loss": 0.2064, + "step": 300 + }, + { + "epoch": 6.976744186046512, + "eval_accuracy": 0.9831501831501831, + "eval_confusion_matrix": [ + [ + 958, + 12 + ], + [ + 11, + 384 + ] + ], + "eval_f1": 0.9831564891330211, + "eval_loss": 0.2294875830411911, + "eval_precision": 0.983164066755398, + "eval_recall": 0.9831501831501831, + "eval_runtime": 3.421, + "eval_samples_per_second": 399.01, + "eval_steps_per_second": 6.431, + "step": 300 + }, + { + "epoch": 8.13953488372093, + "grad_norm": 0.06433115154504776, + "learning_rate": 2.218144694035814e-05, + "loss": 0.2044, + "step": 350 + }, + { + "epoch": 9.30232558139535, + "grad_norm": 0.1391066163778305, + "learning_rate": 1.9379752884171956e-05, + "loss": 0.2023, + "step": 400 + }, + { + "epoch": 9.30232558139535, + "eval_accuracy": 0.9868131868131869, + "eval_confusion_matrix": [ + [ + 957, + 13 + ], + [ + 5, + 390 + ] + ], + "eval_f1": 0.9868519842367506, + "eval_loss": 0.22771421074867249, + "eval_precision": 0.986971783497838, + "eval_recall": 0.9868131868131869, + "eval_runtime": 3.414, + "eval_samples_per_second": 399.822, + "eval_steps_per_second": 6.444, + "step": 400 + }, + { + "epoch": 10.465116279069768, + "grad_norm": 0.03317234292626381, + "learning_rate": 1.6398289196234188e-05, + "loss": 0.201, + "step": 450 + }, + { + "epoch": 11.627906976744185, + "grad_norm": 0.0141974575817585, + "learning_rate": 1.3359431874331888e-05, + "loss": 0.2003, + "step": 500 + }, + { + "epoch": 11.627906976744185, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 7, + 388 + ] + ], + "eval_f1": 0.9875597008648797, + "eval_loss": 0.22541972994804382, + "eval_precision": 0.9875850990732533, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.4267, + "eval_samples_per_second": 398.347, + "eval_steps_per_second": 6.42, + "step": 500 + } + ], + "logging_steps": 50, + "max_steps": 860, + "num_input_tokens_seen": 0, + "num_train_epochs": 20, + "save_steps": 100, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 5, + "early_stopping_threshold": 0.001 + }, + "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": 1.44446640051456e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a50d231c01a45b8b6c28c0d26e003afaece81e --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c +size 5240 diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json new file mode 100644 index 0000000000000000000000000000000000000000..23cd00c8f7806f9961fb35e24a24f5d256693560 --- /dev/null +++ b/checkpoint-600/config.json @@ -0,0 +1,77 @@ +{ + "_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, + "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/checkpoint-600/model.safetensors b/checkpoint-600/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa2584c651dc2b0fbadcf9a5391e16a828558313 --- /dev/null +++ b/checkpoint-600/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c21555c55a0eb1aec9860b56c83a094ef848ce0579ddca6d5a2738b99a6f806 +size 94763496 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb2e4b796f6941a869ff8fb706ba3526f2b80acb --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7548a3259806672f97717e12300878518dfc2ef8dabff02eac23f755b765bc77 +size 189552570 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac60b9bbc51d9896c817c21e65711eb286288a17 --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651bc52340f775bf5ca0ad060e768c602fb2b8b78ae4dc9f9e330238fb6e4131 +size 14308 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b3e1a757534566d85a9834cd0b949c882a8bc04 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb0226b5a39dda6cf123353e8e8fb3f8a8e30903e4332b33f1dd1a021acd14c +size 1064 diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a60ba4f38caad820d24a9f6d9232259c2bf8e86a --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,258 @@ +{ + "best_metric": 0.9875688610221299, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-600", + "epoch": 13.953488372093023, + "eval_steps": 100, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.1627906976744187, + "grad_norm": 0.9607858657836914, + "learning_rate": 1.744186046511628e-05, + "loss": 0.6124, + "step": 50 + }, + { + "epoch": 2.3255813953488373, + "grad_norm": 2.0142862796783447, + "learning_rate": 2.997578868976474e-05, + "loss": 0.3124, + "step": 100 + }, + { + "epoch": 2.3255813953488373, + "eval_accuracy": 0.9641025641025641, + "eval_confusion_matrix": [ + [ + 948, + 22 + ], + [ + 27, + 368 + ] + ], + "eval_f1": 0.9640343817214121, + "eval_loss": 0.2739163041114807, + "eval_precision": 0.9639973701512163, + "eval_recall": 0.9641025641025641, + "eval_runtime": 3.48, + "eval_samples_per_second": 392.238, + "eval_steps_per_second": 6.322, + "step": 100 + }, + { + "epoch": 3.488372093023256, + "grad_norm": 1.6254416704177856, + "learning_rate": 2.9496736466239833e-05, + "loss": 0.2509, + "step": 150 + }, + { + "epoch": 4.651162790697675, + "grad_norm": 1.0478523969650269, + "learning_rate": 2.8422656841613377e-05, + "loss": 0.2337, + "step": 200 + }, + { + "epoch": 4.651162790697675, + "eval_accuracy": 0.9736263736263736, + "eval_confusion_matrix": [ + [ + 950, + 20 + ], + [ + 16, + 379 + ] + ], + "eval_f1": 0.9736655604528286, + "eval_loss": 0.23845618963241577, + "eval_precision": 0.9737247242968067, + "eval_recall": 0.9736263736263736, + "eval_runtime": 3.3782, + "eval_samples_per_second": 404.066, + "eval_steps_per_second": 6.512, + "step": 200 + }, + { + "epoch": 5.813953488372093, + "grad_norm": 0.19202682375907898, + "learning_rate": 2.679763606999547e-05, + "loss": 0.213, + "step": 250 + }, + { + "epoch": 6.976744186046512, + "grad_norm": 3.5125396251678467, + "learning_rate": 2.4688374121322346e-05, + "loss": 0.2064, + "step": 300 + }, + { + "epoch": 6.976744186046512, + "eval_accuracy": 0.9831501831501831, + "eval_confusion_matrix": [ + [ + 958, + 12 + ], + [ + 11, + 384 + ] + ], + "eval_f1": 0.9831564891330211, + "eval_loss": 0.2294875830411911, + "eval_precision": 0.983164066755398, + "eval_recall": 0.9831501831501831, + "eval_runtime": 3.421, + "eval_samples_per_second": 399.01, + "eval_steps_per_second": 6.431, + "step": 300 + }, + { + "epoch": 8.13953488372093, + "grad_norm": 0.06433115154504776, + "learning_rate": 2.218144694035814e-05, + "loss": 0.2044, + "step": 350 + }, + { + "epoch": 9.30232558139535, + "grad_norm": 0.1391066163778305, + "learning_rate": 1.9379752884171956e-05, + "loss": 0.2023, + "step": 400 + }, + { + "epoch": 9.30232558139535, + "eval_accuracy": 0.9868131868131869, + "eval_confusion_matrix": [ + [ + 957, + 13 + ], + [ + 5, + 390 + ] + ], + "eval_f1": 0.9868519842367506, + "eval_loss": 0.22771421074867249, + "eval_precision": 0.986971783497838, + "eval_recall": 0.9868131868131869, + "eval_runtime": 3.414, + "eval_samples_per_second": 399.822, + "eval_steps_per_second": 6.444, + "step": 400 + }, + { + "epoch": 10.465116279069768, + "grad_norm": 0.03317234292626381, + "learning_rate": 1.6398289196234188e-05, + "loss": 0.201, + "step": 450 + }, + { + "epoch": 11.627906976744185, + "grad_norm": 0.0141974575817585, + "learning_rate": 1.3359431874331888e-05, + "loss": 0.2003, + "step": 500 + }, + { + "epoch": 11.627906976744185, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 7, + 388 + ] + ], + "eval_f1": 0.9875597008648797, + "eval_loss": 0.22541972994804382, + "eval_precision": 0.9875850990732533, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.4267, + "eval_samples_per_second": 398.347, + "eval_steps_per_second": 6.42, + "step": 500 + }, + { + "epoch": 12.790697674418604, + "grad_norm": 0.020028484985232353, + "learning_rate": 1.0387912673007252e-05, + "loss": 0.2005, + "step": 550 + }, + { + "epoch": 13.953488372093023, + "grad_norm": 0.013127407990396023, + "learning_rate": 7.605699412521431e-06, + "loss": 0.2002, + "step": 600 + }, + { + "epoch": 13.953488372093023, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 959, + 11 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9875688610221299, + "eval_loss": 0.2259330302476883, + "eval_precision": 0.9876237449942113, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.3216, + "eval_samples_per_second": 410.95, + "eval_steps_per_second": 6.623, + "step": 600 + } + ], + "logging_steps": 50, + "max_steps": 860, + "num_input_tokens_seen": 0, + "num_train_epochs": 20, + "save_steps": 100, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 5, + "early_stopping_threshold": 0.001 + }, + "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": 1.73355980821248e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a50d231c01a45b8b6c28c0d26e003afaece81e --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c +size 5240 diff --git a/checkpoint-700/config.json b/checkpoint-700/config.json new file mode 100644 index 0000000000000000000000000000000000000000..23cd00c8f7806f9961fb35e24a24f5d256693560 --- /dev/null +++ b/checkpoint-700/config.json @@ -0,0 +1,77 @@ +{ + "_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, + "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/checkpoint-700/model.safetensors b/checkpoint-700/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95ee785f1b799b40629a4dd83e97e714215aa1c1 --- /dev/null +++ b/checkpoint-700/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9d6a3efaa15139c296f80cc6ffb6fb613e832c8d723e4e3b6b9262917a4d3c +size 94763496 diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8c2fb6faa533d8c0cb93c0a3c196bafa7f5b60a --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e2c90128a1e2ea359948ddde461ddbd528fd38eb7b3d98c943f471de53b0fd +size 189552570 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..c03374ed36d68a6bb4c19416576b06eb62086790 --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58dca5fb1b7169134a579fbefe18f63835f88838b2ef059378fcdd3c9cecd5f +size 14308 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e47fe9ed8fd955f9b4c9aa6fa9e59d1af7683fe5 --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9763cc72a9be84b93ee3f8307b04709caa68b45aea1c765c4087e9b0f2cec06b +size 1064 diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..11721a0a38364e88b227ac3785d20300c31ce1e3 --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,294 @@ +{ + "best_metric": 0.9882958046457017, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700", + "epoch": 16.27906976744186, + "eval_steps": 100, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.1627906976744187, + "grad_norm": 0.9607858657836914, + "learning_rate": 1.744186046511628e-05, + "loss": 0.6124, + "step": 50 + }, + { + "epoch": 2.3255813953488373, + "grad_norm": 2.0142862796783447, + "learning_rate": 2.997578868976474e-05, + "loss": 0.3124, + "step": 100 + }, + { + "epoch": 2.3255813953488373, + "eval_accuracy": 0.9641025641025641, + "eval_confusion_matrix": [ + [ + 948, + 22 + ], + [ + 27, + 368 + ] + ], + "eval_f1": 0.9640343817214121, + "eval_loss": 0.2739163041114807, + "eval_precision": 0.9639973701512163, + "eval_recall": 0.9641025641025641, + "eval_runtime": 3.48, + "eval_samples_per_second": 392.238, + "eval_steps_per_second": 6.322, + "step": 100 + }, + { + "epoch": 3.488372093023256, + "grad_norm": 1.6254416704177856, + "learning_rate": 2.9496736466239833e-05, + "loss": 0.2509, + "step": 150 + }, + { + "epoch": 4.651162790697675, + "grad_norm": 1.0478523969650269, + "learning_rate": 2.8422656841613377e-05, + "loss": 0.2337, + "step": 200 + }, + { + "epoch": 4.651162790697675, + "eval_accuracy": 0.9736263736263736, + "eval_confusion_matrix": [ + [ + 950, + 20 + ], + [ + 16, + 379 + ] + ], + "eval_f1": 0.9736655604528286, + "eval_loss": 0.23845618963241577, + "eval_precision": 0.9737247242968067, + "eval_recall": 0.9736263736263736, + "eval_runtime": 3.3782, + "eval_samples_per_second": 404.066, + "eval_steps_per_second": 6.512, + "step": 200 + }, + { + "epoch": 5.813953488372093, + "grad_norm": 0.19202682375907898, + "learning_rate": 2.679763606999547e-05, + "loss": 0.213, + "step": 250 + }, + { + "epoch": 6.976744186046512, + "grad_norm": 3.5125396251678467, + "learning_rate": 2.4688374121322346e-05, + "loss": 0.2064, + "step": 300 + }, + { + "epoch": 6.976744186046512, + "eval_accuracy": 0.9831501831501831, + "eval_confusion_matrix": [ + [ + 958, + 12 + ], + [ + 11, + 384 + ] + ], + "eval_f1": 0.9831564891330211, + "eval_loss": 0.2294875830411911, + "eval_precision": 0.983164066755398, + "eval_recall": 0.9831501831501831, + "eval_runtime": 3.421, + "eval_samples_per_second": 399.01, + "eval_steps_per_second": 6.431, + "step": 300 + }, + { + "epoch": 8.13953488372093, + "grad_norm": 0.06433115154504776, + "learning_rate": 2.218144694035814e-05, + "loss": 0.2044, + "step": 350 + }, + { + "epoch": 9.30232558139535, + "grad_norm": 0.1391066163778305, + "learning_rate": 1.9379752884171956e-05, + "loss": 0.2023, + "step": 400 + }, + { + "epoch": 9.30232558139535, + "eval_accuracy": 0.9868131868131869, + "eval_confusion_matrix": [ + [ + 957, + 13 + ], + [ + 5, + 390 + ] + ], + "eval_f1": 0.9868519842367506, + "eval_loss": 0.22771421074867249, + "eval_precision": 0.986971783497838, + "eval_recall": 0.9868131868131869, + "eval_runtime": 3.414, + "eval_samples_per_second": 399.822, + "eval_steps_per_second": 6.444, + "step": 400 + }, + { + "epoch": 10.465116279069768, + "grad_norm": 0.03317234292626381, + "learning_rate": 1.6398289196234188e-05, + "loss": 0.201, + "step": 450 + }, + { + "epoch": 11.627906976744185, + "grad_norm": 0.0141974575817585, + "learning_rate": 1.3359431874331888e-05, + "loss": 0.2003, + "step": 500 + }, + { + "epoch": 11.627906976744185, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 7, + 388 + ] + ], + "eval_f1": 0.9875597008648797, + "eval_loss": 0.22541972994804382, + "eval_precision": 0.9875850990732533, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.4267, + "eval_samples_per_second": 398.347, + "eval_steps_per_second": 6.42, + "step": 500 + }, + { + "epoch": 12.790697674418604, + "grad_norm": 0.020028484985232353, + "learning_rate": 1.0387912673007252e-05, + "loss": 0.2005, + "step": 550 + }, + { + "epoch": 13.953488372093023, + "grad_norm": 0.013127407990396023, + "learning_rate": 7.605699412521431e-06, + "loss": 0.2002, + "step": 600 + }, + { + "epoch": 13.953488372093023, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 959, + 11 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9875688610221299, + "eval_loss": 0.2259330302476883, + "eval_precision": 0.9876237449942113, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.3216, + "eval_samples_per_second": 410.95, + "eval_steps_per_second": 6.623, + "step": 600 + }, + { + "epoch": 15.116279069767442, + "grad_norm": 0.016032038256525993, + "learning_rate": 5.126989735188782e-06, + "loss": 0.2012, + "step": 650 + }, + { + "epoch": 16.27906976744186, + "grad_norm": 0.012081542983651161, + "learning_rate": 3.0535237934100274e-06, + "loss": 0.1994, + "step": 700 + }, + { + "epoch": 16.27906976744186, + "eval_accuracy": 0.9882783882783883, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9882958046457017, + "eval_loss": 0.22554340958595276, + "eval_precision": 0.9883336307004172, + "eval_recall": 0.9882783882783883, + "eval_runtime": 3.3839, + "eval_samples_per_second": 403.383, + "eval_steps_per_second": 6.501, + "step": 700 + } + ], + "logging_steps": 50, + "max_steps": 860, + "num_input_tokens_seen": 0, + "num_train_epochs": 20, + "save_steps": 100, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 5, + "early_stopping_threshold": 0.001 + }, + "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": 2.02165257793536e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a50d231c01a45b8b6c28c0d26e003afaece81e --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c +size 5240 diff --git a/checkpoint-800/config.json b/checkpoint-800/config.json new file mode 100644 index 0000000000000000000000000000000000000000..23cd00c8f7806f9961fb35e24a24f5d256693560 --- /dev/null +++ b/checkpoint-800/config.json @@ -0,0 +1,77 @@ +{ + "_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, + "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/checkpoint-800/model.safetensors b/checkpoint-800/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d386ee54c3996a46e74b7422ff74d42c37242957 --- /dev/null +++ b/checkpoint-800/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca2c8b3045e83eee0dd3997a0d466b85f518369f3117e39e4afe419a6cab06b +size 94763496 diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0efa745a43ad49cc064bae7252c7c0f466306a1 --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fe4b3c8426713ecb377f192fbe2278ecf2710151ea3b3a8d8e5710d4c0dd32 +size 189552570 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e9e4a916e03eefe62f8c1bf40385b084dde6995 --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b21d10b3ec1e745fe106985b1f76b00d319efb8e992b1ee18f7aa51bf01b984 +size 14308 diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e79a91ff041e2e8b7b8b26bce4b2feb76aae583 --- /dev/null +++ b/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e085557df30c0fd508f88a56be4593075bb2341a5f76662bf774b850aa237abb +size 1064 diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e8f5fb4433ba4ea5d8bd3bd71580d634e3bd09e8 --- /dev/null +++ b/checkpoint-800/trainer_state.json @@ -0,0 +1,330 @@ +{ + "best_metric": 0.9882958046457017, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700", + "epoch": 18.6046511627907, + "eval_steps": 100, + "global_step": 800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.1627906976744187, + "grad_norm": 0.9607858657836914, + "learning_rate": 1.744186046511628e-05, + "loss": 0.6124, + "step": 50 + }, + { + "epoch": 2.3255813953488373, + "grad_norm": 2.0142862796783447, + "learning_rate": 2.997578868976474e-05, + "loss": 0.3124, + "step": 100 + }, + { + "epoch": 2.3255813953488373, + "eval_accuracy": 0.9641025641025641, + "eval_confusion_matrix": [ + [ + 948, + 22 + ], + [ + 27, + 368 + ] + ], + "eval_f1": 0.9640343817214121, + "eval_loss": 0.2739163041114807, + "eval_precision": 0.9639973701512163, + "eval_recall": 0.9641025641025641, + "eval_runtime": 3.48, + "eval_samples_per_second": 392.238, + "eval_steps_per_second": 6.322, + "step": 100 + }, + { + "epoch": 3.488372093023256, + "grad_norm": 1.6254416704177856, + "learning_rate": 2.9496736466239833e-05, + "loss": 0.2509, + "step": 150 + }, + { + "epoch": 4.651162790697675, + "grad_norm": 1.0478523969650269, + "learning_rate": 2.8422656841613377e-05, + "loss": 0.2337, + "step": 200 + }, + { + "epoch": 4.651162790697675, + "eval_accuracy": 0.9736263736263736, + "eval_confusion_matrix": [ + [ + 950, + 20 + ], + [ + 16, + 379 + ] + ], + "eval_f1": 0.9736655604528286, + "eval_loss": 0.23845618963241577, + "eval_precision": 0.9737247242968067, + "eval_recall": 0.9736263736263736, + "eval_runtime": 3.3782, + "eval_samples_per_second": 404.066, + "eval_steps_per_second": 6.512, + "step": 200 + }, + { + "epoch": 5.813953488372093, + "grad_norm": 0.19202682375907898, + "learning_rate": 2.679763606999547e-05, + "loss": 0.213, + "step": 250 + }, + { + "epoch": 6.976744186046512, + "grad_norm": 3.5125396251678467, + "learning_rate": 2.4688374121322346e-05, + "loss": 0.2064, + "step": 300 + }, + { + "epoch": 6.976744186046512, + "eval_accuracy": 0.9831501831501831, + "eval_confusion_matrix": [ + [ + 958, + 12 + ], + [ + 11, + 384 + ] + ], + "eval_f1": 0.9831564891330211, + "eval_loss": 0.2294875830411911, + "eval_precision": 0.983164066755398, + "eval_recall": 0.9831501831501831, + "eval_runtime": 3.421, + "eval_samples_per_second": 399.01, + "eval_steps_per_second": 6.431, + "step": 300 + }, + { + "epoch": 8.13953488372093, + "grad_norm": 0.06433115154504776, + "learning_rate": 2.218144694035814e-05, + "loss": 0.2044, + "step": 350 + }, + { + "epoch": 9.30232558139535, + "grad_norm": 0.1391066163778305, + "learning_rate": 1.9379752884171956e-05, + "loss": 0.2023, + "step": 400 + }, + { + "epoch": 9.30232558139535, + "eval_accuracy": 0.9868131868131869, + "eval_confusion_matrix": [ + [ + 957, + 13 + ], + [ + 5, + 390 + ] + ], + "eval_f1": 0.9868519842367506, + "eval_loss": 0.22771421074867249, + "eval_precision": 0.986971783497838, + "eval_recall": 0.9868131868131869, + "eval_runtime": 3.414, + "eval_samples_per_second": 399.822, + "eval_steps_per_second": 6.444, + "step": 400 + }, + { + "epoch": 10.465116279069768, + "grad_norm": 0.03317234292626381, + "learning_rate": 1.6398289196234188e-05, + "loss": 0.201, + "step": 450 + }, + { + "epoch": 11.627906976744185, + "grad_norm": 0.0141974575817585, + "learning_rate": 1.3359431874331888e-05, + "loss": 0.2003, + "step": 500 + }, + { + "epoch": 11.627906976744185, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 7, + 388 + ] + ], + "eval_f1": 0.9875597008648797, + "eval_loss": 0.22541972994804382, + "eval_precision": 0.9875850990732533, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.4267, + "eval_samples_per_second": 398.347, + "eval_steps_per_second": 6.42, + "step": 500 + }, + { + "epoch": 12.790697674418604, + "grad_norm": 0.020028484985232353, + "learning_rate": 1.0387912673007252e-05, + "loss": 0.2005, + "step": 550 + }, + { + "epoch": 13.953488372093023, + "grad_norm": 0.013127407990396023, + "learning_rate": 7.605699412521431e-06, + "loss": 0.2002, + "step": 600 + }, + { + "epoch": 13.953488372093023, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 959, + 11 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9875688610221299, + "eval_loss": 0.2259330302476883, + "eval_precision": 0.9876237449942113, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.3216, + "eval_samples_per_second": 410.95, + "eval_steps_per_second": 6.623, + "step": 600 + }, + { + "epoch": 15.116279069767442, + "grad_norm": 0.016032038256525993, + "learning_rate": 5.126989735188782e-06, + "loss": 0.2012, + "step": 650 + }, + { + "epoch": 16.27906976744186, + "grad_norm": 0.012081542983651161, + "learning_rate": 3.0535237934100274e-06, + "loss": 0.1994, + "step": 700 + }, + { + "epoch": 16.27906976744186, + "eval_accuracy": 0.9882783882783883, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9882958046457017, + "eval_loss": 0.22554340958595276, + "eval_precision": 0.9883336307004172, + "eval_recall": 0.9882783882783883, + "eval_runtime": 3.3839, + "eval_samples_per_second": 403.383, + "eval_steps_per_second": 6.501, + "step": 700 + }, + { + "epoch": 17.441860465116278, + "grad_norm": 0.015530905686318874, + "learning_rate": 1.470408262986479e-06, + "loss": 0.2008, + "step": 750 + }, + { + "epoch": 18.6046511627907, + "grad_norm": 0.03649911284446716, + "learning_rate": 4.4262308763892087e-07, + "loss": 0.1997, + "step": 800 + }, + { + "epoch": 18.6046511627907, + "eval_accuracy": 0.9882783882783883, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9882958046457017, + "eval_loss": 0.22540099918842316, + "eval_precision": 0.9883336307004172, + "eval_recall": 0.9882783882783883, + "eval_runtime": 3.38, + "eval_samples_per_second": 403.852, + "eval_steps_per_second": 6.509, + "step": 800 + } + ], + "logging_steps": 50, + "max_steps": 860, + "num_input_tokens_seen": 0, + "num_train_epochs": 20, + "save_steps": 100, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 5, + "early_stopping_threshold": 0.001 + }, + "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": 2.31074598563328e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a50d231c01a45b8b6c28c0d26e003afaece81e --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c +size 5240 diff --git a/checkpoint-860/config.json b/checkpoint-860/config.json new file mode 100644 index 0000000000000000000000000000000000000000..23cd00c8f7806f9961fb35e24a24f5d256693560 --- /dev/null +++ b/checkpoint-860/config.json @@ -0,0 +1,77 @@ +{ + "_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, + "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/checkpoint-860/model.safetensors b/checkpoint-860/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c9ab3d15718a3270918ddc5f1720b1d74c06d8b --- /dev/null +++ b/checkpoint-860/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d7ea4d47fbee3393f5e749620e0b4a578cea2449907bfe0372d868b5f4b30a +size 94763496 diff --git a/checkpoint-860/optimizer.pt b/checkpoint-860/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..27f1bc0badaf883aacf076fe2895e07c490ea9c3 --- /dev/null +++ b/checkpoint-860/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfa4331625c52dd28223fd3b2cba322b7836ef0875a75d29701a3fd08df747a +size 189552570 diff --git a/checkpoint-860/rng_state.pth b/checkpoint-860/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfd466f53c8825facc5ee7207d8b584dbcd8089c --- /dev/null +++ b/checkpoint-860/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8e1549744101389fee1cb4923c7729bf266144965aa751df09dad62532a0fd +size 14308 diff --git a/checkpoint-860/scheduler.pt b/checkpoint-860/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdef5baa6a57b6aa49bd226cceb0955a8f1a8317 --- /dev/null +++ b/checkpoint-860/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3305b0d94ed5c5807ba878e31359e591ea9ddd9f01e4c81eb836abb2e249bfab +size 1064 diff --git a/checkpoint-860/trainer_state.json b/checkpoint-860/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..62706aae155a6a20d9eac9b28f41aadffe0dbc09 --- /dev/null +++ b/checkpoint-860/trainer_state.json @@ -0,0 +1,337 @@ +{ + "best_metric": 0.9882958046457017, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700", + "epoch": 20.0, + "eval_steps": 100, + "global_step": 860, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.1627906976744187, + "grad_norm": 0.9607858657836914, + "learning_rate": 1.744186046511628e-05, + "loss": 0.6124, + "step": 50 + }, + { + "epoch": 2.3255813953488373, + "grad_norm": 2.0142862796783447, + "learning_rate": 2.997578868976474e-05, + "loss": 0.3124, + "step": 100 + }, + { + "epoch": 2.3255813953488373, + "eval_accuracy": 0.9641025641025641, + "eval_confusion_matrix": [ + [ + 948, + 22 + ], + [ + 27, + 368 + ] + ], + "eval_f1": 0.9640343817214121, + "eval_loss": 0.2739163041114807, + "eval_precision": 0.9639973701512163, + "eval_recall": 0.9641025641025641, + "eval_runtime": 3.48, + "eval_samples_per_second": 392.238, + "eval_steps_per_second": 6.322, + "step": 100 + }, + { + "epoch": 3.488372093023256, + "grad_norm": 1.6254416704177856, + "learning_rate": 2.9496736466239833e-05, + "loss": 0.2509, + "step": 150 + }, + { + "epoch": 4.651162790697675, + "grad_norm": 1.0478523969650269, + "learning_rate": 2.8422656841613377e-05, + "loss": 0.2337, + "step": 200 + }, + { + "epoch": 4.651162790697675, + "eval_accuracy": 0.9736263736263736, + "eval_confusion_matrix": [ + [ + 950, + 20 + ], + [ + 16, + 379 + ] + ], + "eval_f1": 0.9736655604528286, + "eval_loss": 0.23845618963241577, + "eval_precision": 0.9737247242968067, + "eval_recall": 0.9736263736263736, + "eval_runtime": 3.3782, + "eval_samples_per_second": 404.066, + "eval_steps_per_second": 6.512, + "step": 200 + }, + { + "epoch": 5.813953488372093, + "grad_norm": 0.19202682375907898, + "learning_rate": 2.679763606999547e-05, + "loss": 0.213, + "step": 250 + }, + { + "epoch": 6.976744186046512, + "grad_norm": 3.5125396251678467, + "learning_rate": 2.4688374121322346e-05, + "loss": 0.2064, + "step": 300 + }, + { + "epoch": 6.976744186046512, + "eval_accuracy": 0.9831501831501831, + "eval_confusion_matrix": [ + [ + 958, + 12 + ], + [ + 11, + 384 + ] + ], + "eval_f1": 0.9831564891330211, + "eval_loss": 0.2294875830411911, + "eval_precision": 0.983164066755398, + "eval_recall": 0.9831501831501831, + "eval_runtime": 3.421, + "eval_samples_per_second": 399.01, + "eval_steps_per_second": 6.431, + "step": 300 + }, + { + "epoch": 8.13953488372093, + "grad_norm": 0.06433115154504776, + "learning_rate": 2.218144694035814e-05, + "loss": 0.2044, + "step": 350 + }, + { + "epoch": 9.30232558139535, + "grad_norm": 0.1391066163778305, + "learning_rate": 1.9379752884171956e-05, + "loss": 0.2023, + "step": 400 + }, + { + "epoch": 9.30232558139535, + "eval_accuracy": 0.9868131868131869, + "eval_confusion_matrix": [ + [ + 957, + 13 + ], + [ + 5, + 390 + ] + ], + "eval_f1": 0.9868519842367506, + "eval_loss": 0.22771421074867249, + "eval_precision": 0.986971783497838, + "eval_recall": 0.9868131868131869, + "eval_runtime": 3.414, + "eval_samples_per_second": 399.822, + "eval_steps_per_second": 6.444, + "step": 400 + }, + { + "epoch": 10.465116279069768, + "grad_norm": 0.03317234292626381, + "learning_rate": 1.6398289196234188e-05, + "loss": 0.201, + "step": 450 + }, + { + "epoch": 11.627906976744185, + "grad_norm": 0.0141974575817585, + "learning_rate": 1.3359431874331888e-05, + "loss": 0.2003, + "step": 500 + }, + { + "epoch": 11.627906976744185, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 7, + 388 + ] + ], + "eval_f1": 0.9875597008648797, + "eval_loss": 0.22541972994804382, + "eval_precision": 0.9875850990732533, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.4267, + "eval_samples_per_second": 398.347, + "eval_steps_per_second": 6.42, + "step": 500 + }, + { + "epoch": 12.790697674418604, + "grad_norm": 0.020028484985232353, + "learning_rate": 1.0387912673007252e-05, + "loss": 0.2005, + "step": 550 + }, + { + "epoch": 13.953488372093023, + "grad_norm": 0.013127407990396023, + "learning_rate": 7.605699412521431e-06, + "loss": 0.2002, + "step": 600 + }, + { + "epoch": 13.953488372093023, + "eval_accuracy": 0.9875457875457876, + "eval_confusion_matrix": [ + [ + 959, + 11 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9875688610221299, + "eval_loss": 0.2259330302476883, + "eval_precision": 0.9876237449942113, + "eval_recall": 0.9875457875457876, + "eval_runtime": 3.3216, + "eval_samples_per_second": 410.95, + "eval_steps_per_second": 6.623, + "step": 600 + }, + { + "epoch": 15.116279069767442, + "grad_norm": 0.016032038256525993, + "learning_rate": 5.126989735188782e-06, + "loss": 0.2012, + "step": 650 + }, + { + "epoch": 16.27906976744186, + "grad_norm": 0.012081542983651161, + "learning_rate": 3.0535237934100274e-06, + "loss": 0.1994, + "step": 700 + }, + { + "epoch": 16.27906976744186, + "eval_accuracy": 0.9882783882783883, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9882958046457017, + "eval_loss": 0.22554340958595276, + "eval_precision": 0.9883336307004172, + "eval_recall": 0.9882783882783883, + "eval_runtime": 3.3839, + "eval_samples_per_second": 403.383, + "eval_steps_per_second": 6.501, + "step": 700 + }, + { + "epoch": 17.441860465116278, + "grad_norm": 0.015530905686318874, + "learning_rate": 1.470408262986479e-06, + "loss": 0.2008, + "step": 750 + }, + { + "epoch": 18.6046511627907, + "grad_norm": 0.03649911284446716, + "learning_rate": 4.4262308763892087e-07, + "loss": 0.1997, + "step": 800 + }, + { + "epoch": 18.6046511627907, + "eval_accuracy": 0.9882783882783883, + "eval_confusion_matrix": [ + [ + 960, + 10 + ], + [ + 6, + 389 + ] + ], + "eval_f1": 0.9882958046457017, + "eval_loss": 0.22540099918842316, + "eval_precision": 0.9883336307004172, + "eval_recall": 0.9882783882783883, + "eval_runtime": 3.38, + "eval_samples_per_second": 403.852, + "eval_steps_per_second": 6.509, + "step": 800 + }, + { + "epoch": 19.767441860465116, + "grad_norm": 0.17561723291873932, + "learning_rate": 1.2354337535766536e-08, + "loss": 0.2008, + "step": 850 + } + ], + "logging_steps": 50, + "max_steps": 860, + "num_input_tokens_seen": 0, + "num_train_epochs": 20, + "save_steps": 100, + "stateful_callbacks": { + "EarlyStoppingCallback": { + "args": { + "early_stopping_patience": 5, + "early_stopping_threshold": 0.001 + }, + "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": 2.483401519872e+17, + "train_batch_size": 64, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-860/training_args.bin b/checkpoint-860/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a50d231c01a45b8b6c28c0d26e003afaece81e --- /dev/null +++ b/checkpoint-860/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c +size 5240 diff --git a/model.safetensors b/model.safetensors index e8250db40335ef01374cc2551da82b034b606100..95ee785f1b799b40629a4dd83e97e714215aa1c1 100644 --- a/model.safetensors +++ b/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3fefc9fc9e0c6f521d52f6944550be09ad08cf2a406465b2bad96d43e8e656a9 +oid sha256:dc9d6a3efaa15139c296f80cc6ffb6fb613e832c8d723e4e3b6b9262917a4d3c size 94763496 diff --git a/runs/Sep11_15-20-39_ubumarcos/events.out.tfevents.1726060840.ubumarcos b/runs/Sep11_15-20-39_ubumarcos/events.out.tfevents.1726060840.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..3e85dcb8ae40961cff149e8ff7fc6777129030fd --- /dev/null +++ b/runs/Sep11_15-20-39_ubumarcos/events.out.tfevents.1726060840.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3457d6d32eee966361cd1a5e55bfc41aea0b8448b79e8dc0419ad9f56364d56 +size 5795 diff --git a/runs/Sep11_15-21-14_ubumarcos/events.out.tfevents.1726060876.ubumarcos b/runs/Sep11_15-21-14_ubumarcos/events.out.tfevents.1726060876.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..a377b37b9f10e3e67286419f03651d13765c0cd0 --- /dev/null +++ b/runs/Sep11_15-21-14_ubumarcos/events.out.tfevents.1726060876.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2677a6a2bf7d8a64d0c79c173ee4f873dd3a521604a432950bae62def6d8e06e +size 7184 diff --git a/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061160.ubumarcos b/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061160.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..888da31cc8ca39bc4040cc32a6514b9ec5573055 --- /dev/null +++ b/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061160.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dbe9a7696e2700e9ae245d9bd2b3e8f9ce8e4c4724beed7069fcf4b8827c826 +size 10773 diff --git a/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061977.ubumarcos b/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061977.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..92afc522b670679c87c9ef235ef4285a36b1de02 --- /dev/null +++ b/runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061977.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea600bf545d3d4626fd88b275f082cd15a4449c22b38bdc432c40f465a710247 +size 503 diff --git a/runs/Sep11_15-42-12_ubumarcos/events.out.tfevents.1726062133.ubumarcos b/runs/Sep11_15-42-12_ubumarcos/events.out.tfevents.1726062133.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..eb4080a85ae6ba9295783d07e0952458cedd2055 --- /dev/null +++ b/runs/Sep11_15-42-12_ubumarcos/events.out.tfevents.1726062133.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4204743a7822eb72e21292b34c8728a7257c7e6624882cef2790dc8e48c7dee0 +size 7647 diff --git a/runs/Sep11_15-50-04_ubumarcos/events.out.tfevents.1726062605.ubumarcos b/runs/Sep11_15-50-04_ubumarcos/events.out.tfevents.1726062605.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..ef95e03a6833f6a8ada1a9aba56fe49add553d78 --- /dev/null +++ b/runs/Sep11_15-50-04_ubumarcos/events.out.tfevents.1726062605.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae11e51efaad3daa9c0afdc2f11dbd3f7305426132549ec41a4a4a274c18c988 +size 5806 diff --git a/runs/Sep11_15-50-31_ubumarcos/events.out.tfevents.1726062632.ubumarcos b/runs/Sep11_15-50-31_ubumarcos/events.out.tfevents.1726062632.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..f4b69764ae5d9654ec83f9bff01c3fc0f20e9a5b --- /dev/null +++ b/runs/Sep11_15-50-31_ubumarcos/events.out.tfevents.1726062632.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9e10b14d9386a106cfe9f147897a38340fa2232ba11190681651623aa3eb1a +size 5804 diff --git a/runs/Sep11_15-50-57_ubumarcos/events.out.tfevents.1726062658.ubumarcos b/runs/Sep11_15-50-57_ubumarcos/events.out.tfevents.1726062658.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..451c689b1906e7fea5827d0685e18d7d6b16498f --- /dev/null +++ b/runs/Sep11_15-50-57_ubumarcos/events.out.tfevents.1726062658.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e350751289634829a9fd460749053434acd1af6a93ed53f32d40ba013fa2170 +size 5806 diff --git a/runs/Sep11_15-51-52_ubumarcos/events.out.tfevents.1726062713.ubumarcos b/runs/Sep11_15-51-52_ubumarcos/events.out.tfevents.1726062713.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..b92ab5f7bfd32c9ef3f98c3649fd337131df467c --- /dev/null +++ b/runs/Sep11_15-51-52_ubumarcos/events.out.tfevents.1726062713.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d152b790394ef1654f41e83eee46f69ad24e2c6949b44a7d10b165f8445e42a7 +size 5807 diff --git a/runs/Sep11_15-52-20_ubumarcos/events.out.tfevents.1726062741.ubumarcos b/runs/Sep11_15-52-20_ubumarcos/events.out.tfevents.1726062741.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..520d50ff983c955de6ca36f1ae1280f86dfcbcf5 --- /dev/null +++ b/runs/Sep11_15-52-20_ubumarcos/events.out.tfevents.1726062741.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b53922a640a17f8f76424c75f29092341a456c1ab191c88af0a378c2b04c97 +size 5806 diff --git a/runs/Sep11_15-52-43_ubumarcos/events.out.tfevents.1726062764.ubumarcos b/runs/Sep11_15-52-43_ubumarcos/events.out.tfevents.1726062764.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..257338889de9a88a464f141f53cc617dbc732863 --- /dev/null +++ b/runs/Sep11_15-52-43_ubumarcos/events.out.tfevents.1726062764.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948a1e01a387f8ee74909d6ff171610a41577bf81caef495d41daecdf546b406 +size 5807 diff --git a/runs/Sep11_15-54-06_ubumarcos/events.out.tfevents.1726062847.ubumarcos b/runs/Sep11_15-54-06_ubumarcos/events.out.tfevents.1726062847.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..6eda1be053cde99edab022fe0a280a1f36190bda --- /dev/null +++ b/runs/Sep11_15-54-06_ubumarcos/events.out.tfevents.1726062847.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012e4be1fb2dcb0201aad7f28222fcb79340b9cf0fc188a95c1eb9d0e43a8b33 +size 5807 diff --git a/runs/Sep11_15-54-19_ubumarcos/events.out.tfevents.1726062860.ubumarcos b/runs/Sep11_15-54-19_ubumarcos/events.out.tfevents.1726062860.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..cae8f026d0ed5035d4853eb15e608ccb6b53e2de --- /dev/null +++ b/runs/Sep11_15-54-19_ubumarcos/events.out.tfevents.1726062860.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d408531ac1a90d9d340e9886c50d5d601dc05adbeb15f7553e3e20fbb324ee +size 5806 diff --git a/runs/Sep11_15-54-49_ubumarcos/events.out.tfevents.1726062890.ubumarcos b/runs/Sep11_15-54-49_ubumarcos/events.out.tfevents.1726062890.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..8ae84ca3dd356f629b2db178de218ff3fa0d1ee8 --- /dev/null +++ b/runs/Sep11_15-54-49_ubumarcos/events.out.tfevents.1726062890.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37410bad9c5f52d5f945a23e56ef80288c95b91fb305eb5050a3a4566e056c13 +size 5807 diff --git a/runs/Sep11_15-55-24_ubumarcos/events.out.tfevents.1726062925.ubumarcos b/runs/Sep11_15-55-24_ubumarcos/events.out.tfevents.1726062925.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..ded7441da08d830fef359d7e076ada141665f6d7 --- /dev/null +++ b/runs/Sep11_15-55-24_ubumarcos/events.out.tfevents.1726062925.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e405ae019edbcb8fce075fe4830883ef48e6517064b4cf16915ba48def858a72 +size 9719 diff --git a/runs/Sep11_16-34-29_ubumarcos/events.out.tfevents.1726065271.ubumarcos b/runs/Sep11_16-34-29_ubumarcos/events.out.tfevents.1726065271.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..fb757645deac9eae8e0835320a7a7acf9be4c7ac --- /dev/null +++ b/runs/Sep11_16-34-29_ubumarcos/events.out.tfevents.1726065271.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4608309372d5956f5ea438a8ea9ed76acd59be95b5ad221aeb1897ed3feffa56 +size 5806 diff --git a/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726065295.ubumarcos b/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726065295.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..5f55d83337da36064e6a456cc2f51fad5a516fe3 --- /dev/null +++ b/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726065295.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66d864acb48b3eb2d4716615d72005bb726e5014c270ce6ea7db7daa3882765f +size 13506 diff --git a/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726066840.ubumarcos b/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726066840.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..50891b780980912ff3170d58a1c97c965167660b --- /dev/null +++ b/runs/Sep11_16-34-54_ubumarcos/events.out.tfevents.1726066840.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ebf7c7ff3eeb7859af09453dcab6960e86ed978029feab37d64f9a3913eae0 +size 40 diff --git a/training_args.bin b/training_args.bin index 5d762b1cb8eeee08ab8703debb3a686abe8615eb..f1a50d231c01a45b8b6c28c0d26e003afaece81e 100644 --- a/training_args.bin +++ b/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:39b105bc8a63684c00e408cee2101863b9ae4fed57fb146361599a16b19b549b +oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c size 5240