diff --git a/README.md b/README.md index a1d9efbaaae185144bc52dfcb54293c92f15be7c..c7ae91830d058c78a9d1fde965ac759ff057f20a 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,11 @@ license: apache-2.0 base_model: ntu-spml/distilhubert tags: - generated_from_trainer +metrics: +- accuracy +- precision +- recall +- f1 model-index: - name: distilhubert-finetuned-cry-detector results: [] @@ -15,6 +20,12 @@ should probably proofread and complete it, then remove this comment. --> # distilhubert-finetuned-cry-detector 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: 0.0878 +- Accuracy: 0.9861 +- Precision: 0.9861 +- Recall: 0.9861 +- F1: 0.9861 ## Model description @@ -42,13 +53,20 @@ The following hyperparameters were used during training: - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.001 -- num_epochs: 1 +- num_epochs: 8 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| -| No log | 0.9956 | 85 | 0.1412 | 0.9480 | 0.9478 | 0.9480 | 0.9476 | +| No log | 0.9956 | 85 | 0.1204 | 0.9641 | 0.9641 | 0.9641 | 0.9638 | +| No log | 1.9912 | 170 | 0.0847 | 0.9773 | 0.9772 | 0.9773 | 0.9773 | +| No log | 2.9985 | 256 | 0.1025 | 0.9766 | 0.9769 | 0.9766 | 0.9766 | +| No log | 3.9941 | 341 | 0.0869 | 0.9832 | 0.9835 | 0.9832 | 0.9832 | +| No log | 4.9898 | 426 | 0.0746 | 0.9832 | 0.9834 | 0.9832 | 0.9832 | +| 0.0538 | 5.9971 | 512 | 0.0870 | 0.9861 | 0.9861 | 0.9861 | 0.9861 | +| 0.0538 | 6.9927 | 597 | 0.0890 | 0.9861 | 0.9861 | 0.9861 | 0.9861 | +| 0.0538 | 7.9649 | 680 | 0.0878 | 0.9861 | 0.9861 | 0.9861 | 0.9861 | ### Framework versions diff --git a/checkpoint-170/config.json b/checkpoint-170/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-170/config.json +++ b/checkpoint-170/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-170/model.safetensors b/checkpoint-170/model.safetensors index 4dda87edb0e7ca2086b861aa309031d6ab7720c5..029c9551db378142e03a8a4f643e1cfa69067638 100644 --- a/checkpoint-170/model.safetensors +++ b/checkpoint-170/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:234766c4455d275002665fd833b44efa39e41bc2661c4bb2462491e9b235265b +oid sha256:ddc4c9cb0876910fe2ac6089e9622d2ec25163c90268babf3b3a68cc1955bbc3 size 94763496 diff --git a/checkpoint-170/optimizer.pt b/checkpoint-170/optimizer.pt index 05020f0ccc3bef504995b3ff62ffe5b2ef42f213..1ae9b92d7b172201b4c0272522dcb9015b14f6e6 100644 --- a/checkpoint-170/optimizer.pt +++ b/checkpoint-170/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:54168c775d69b037d7dd954b39f148a62b5d5230761ef39bcb3fc60c2c2b65be +oid sha256:f284ad3b43a12e7fdbaf43673ca92e158c1ab9cbea63e0352b6085f5564ff555 size 189552570 diff --git a/checkpoint-170/scheduler.pt b/checkpoint-170/scheduler.pt index 8586668d4d3aa9bbd15cdb7b42394d4c7997054b..68b63252632e88961f463e916419c0bcc60eed4e 100644 --- a/checkpoint-170/scheduler.pt +++ b/checkpoint-170/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e2034409269304d3556c2ec17a8e8112c21629214e514ea105efbb26052b23cf +oid sha256:28ead2442e291cf84a44bd5f670a529388e7aee7f31ec31fec65f8af5dd527ac size 1064 diff --git a/checkpoint-170/trainer_state.json b/checkpoint-170/trainer_state.json index a3c31b77660242213d3b79764705f1c23a1344e7..4af90f58e465a196effbfd6c98b0156a169637f4 100644 --- a/checkpoint-170/trainer_state.json +++ b/checkpoint-170/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9860805860805861, + "best_metric": 0.9772893772893773, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170", "epoch": 1.9912152269399708, "eval_steps": 500, @@ -10,27 +10,33 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-170/training_args.bin b/checkpoint-170/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-170/training_args.bin +++ b/checkpoint-170/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-256/config.json b/checkpoint-256/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-256/config.json +++ b/checkpoint-256/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-256/model.safetensors b/checkpoint-256/model.safetensors index 0355d2d714e77d35759dbf462bb4644229635b6c..a3f584b51c67efed2549a44016d80c5ee51ebea3 100644 --- a/checkpoint-256/model.safetensors +++ b/checkpoint-256/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:74664b03f722ebd6f388e4906fa982d1ec05522a8b62f38b65182ae0f78dd659 +oid sha256:1e8fcce3d6821b09907a57bf2280fdb73fc79c008d23670c77bd0350d6249146 size 94763496 diff --git a/checkpoint-256/optimizer.pt b/checkpoint-256/optimizer.pt index bf230ea74fcbc155e80cad9f60d5fe4484050430..20186f2b66e074cdb14ef5cdeb7b773d31e09668 100644 --- a/checkpoint-256/optimizer.pt +++ b/checkpoint-256/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c93c7b3a43b80636a934d1782de63f8303fd44e61f41d41d41caa10a9639ffc1 +oid sha256:eb370b3600823d6c126a14d977da564c51a816566b23701954070eb23a1ecf47 size 189552570 diff --git a/checkpoint-256/scheduler.pt b/checkpoint-256/scheduler.pt index 9bf65f88975f1f8f262c36f2f436a418f294d554..862d31ba10ad45931e67f050616990185c0ba31d 100644 --- a/checkpoint-256/scheduler.pt +++ b/checkpoint-256/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c1daa6dfbc632505773869a612096b9f14303a596de4d72e49c6d934621e4204 +oid sha256:b1ef84753a69d0410f7f7d925e2fedd5694b09472e6721f4fe864ef701cb0dd7 size 1064 diff --git a/checkpoint-256/trainer_state.json b/checkpoint-256/trainer_state.json index de39269cd014a907b0f4e269a291880f38448fe6..6aee8a4046ef5e46f318d65debdade0e0177b5b3 100644 --- a/checkpoint-256/trainer_state.json +++ b/checkpoint-256/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9860805860805861, + "best_metric": 0.9772893772893773, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170", "epoch": 2.998535871156662, "eval_steps": 500, @@ -10,36 +10,45 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 }, { "epoch": 2.998535871156662, - "eval_accuracy": 0.9853479853479854, - "eval_loss": 0.04894961416721344, - "eval_runtime": 15.5622, - "eval_samples_per_second": 87.713, - "eval_steps_per_second": 10.988, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, "step": 256 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-256/training_args.bin b/checkpoint-256/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-256/training_args.bin +++ b/checkpoint-256/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-341/config.json b/checkpoint-341/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-341/config.json +++ b/checkpoint-341/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-341/model.safetensors b/checkpoint-341/model.safetensors index bfc0e5bd107954cb2a0aedced68af33505cff094..6487b6ae8b87a3a3ba1da9a2f16f9ce63bc66f43 100644 --- a/checkpoint-341/model.safetensors +++ b/checkpoint-341/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4c4695016088987cb75a8381886d078dee5da33d439dfa3472cbded298196975 +oid sha256:083f40b77a3962067064a68eb072696b4bf2222ce7f9bdab915843b0aab6cf86 size 94763496 diff --git a/checkpoint-341/optimizer.pt b/checkpoint-341/optimizer.pt index 0f0552d9a6a696ef63eed17d5d6cc698788b7a6c..31081e447efda4c71db020f7f658257c66054127 100644 --- a/checkpoint-341/optimizer.pt +++ b/checkpoint-341/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:88625b2c249303af96915509b84fbe0fd810785b84d32d68e936f83e44e0c710 +oid sha256:f581f41271d1b7b3e94ec5316e0b37c75a3ad264185a441b84016451887b8ec4 size 189552570 diff --git a/checkpoint-341/scheduler.pt b/checkpoint-341/scheduler.pt index 906be069a04584b0206917bdc3bda9acbe78311f..60b9d8df3b96033550d6d80e5dbb8b70e456a3e7 100644 --- a/checkpoint-341/scheduler.pt +++ b/checkpoint-341/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0d0e5f3394e1cb08f5e6ec9d7e11dc43d76ef8c66bf2eaa7a0f848f815b1d4cc +oid sha256:d5073b7c775ebf0fc889f5dba154fdfe2dbb913e0f115f2091d61c7aad83715e size 1064 diff --git a/checkpoint-341/trainer_state.json b/checkpoint-341/trainer_state.json index 33db5e91f41d03b76714b47e31b37c4e2ab828f4..c262d71e9d7fdc4b4520d4176b9770fe728c2fa6 100644 --- a/checkpoint-341/trainer_state.json +++ b/checkpoint-341/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9897435897435898, + "best_metric": 0.9831501831501831, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", "epoch": 3.994143484626647, "eval_steps": 500, @@ -10,45 +10,57 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 }, { "epoch": 2.998535871156662, - "eval_accuracy": 0.9853479853479854, - "eval_loss": 0.04894961416721344, - "eval_runtime": 15.5622, - "eval_samples_per_second": 87.713, - "eval_steps_per_second": 10.988, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, "step": 256 }, { "epoch": 3.994143484626647, - "eval_accuracy": 0.9897435897435898, - "eval_loss": 0.04228556528687477, - "eval_runtime": 15.6217, - "eval_samples_per_second": 87.378, - "eval_steps_per_second": 10.946, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9832333934847322, + "eval_loss": 0.08685966581106186, + "eval_precision": 0.9835305336122597, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9568, + "eval_samples_per_second": 229.152, + "eval_steps_per_second": 28.707, "step": 341 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-341/training_args.bin b/checkpoint-341/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-341/training_args.bin +++ b/checkpoint-341/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-426/config.json b/checkpoint-426/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-426/config.json +++ b/checkpoint-426/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-426/model.safetensors b/checkpoint-426/model.safetensors index 17ed7020b5b38c3749565bca9cf64e211c3f97e0..ab5e06f4c072a373cb17798bc0d42c15036a4905 100644 --- a/checkpoint-426/model.safetensors +++ b/checkpoint-426/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d14ac9c4fea572b7ef6e0e3502f94a78d1c0c3fef295cf4a6f6746aeac8feaf9 +oid sha256:1a9d6d392a4f841e92110c90f40ef7219881d17b11f11a64bad39c27cbe0178e size 94763496 diff --git a/checkpoint-426/optimizer.pt b/checkpoint-426/optimizer.pt index 75a972ebf308ffdfd700bc307c48efc75cf07994..418bbc58e2ba2a00bd766e7d59dcf59af09b46e3 100644 --- a/checkpoint-426/optimizer.pt +++ b/checkpoint-426/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2bfbb9842afd0e0e7c548c18e2442c293c57767268f19e3c10c10c38c6745a66 +oid sha256:fcfe6fb7847bde58aeb36b9a7bc45200d4352f754fb3595c33126144f17addf2 size 189552570 diff --git a/checkpoint-426/scheduler.pt b/checkpoint-426/scheduler.pt index f519d549a8b824e4f456fcc93b124db502c580e0..c6796b38f784299e3bfefd486d42c7b3921b23f1 100644 --- a/checkpoint-426/scheduler.pt +++ b/checkpoint-426/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4d495ecbbc4c3121c1feab1c93a2d37084137f7007f1d94685663700a6993c70 +oid sha256:d56f52cf1fd1013d5989e211cbbbf97096f52d89af5defd532d0d8a25d4724f7 size 1064 diff --git a/checkpoint-426/trainer_state.json b/checkpoint-426/trainer_state.json index e91532d3175048ecc032dfff6dc1b826e46f8030..1bb15713c46d5b8a6821f07ee7630f248c62177d 100644 --- a/checkpoint-426/trainer_state.json +++ b/checkpoint-426/trainer_state.json @@ -1,6 +1,6 @@ { - "best_metric": 0.991941391941392, - "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-426", + "best_metric": 0.9831501831501831, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341", "epoch": 4.989751098096632, "eval_steps": 500, "global_step": 426, @@ -10,54 +10,69 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 }, { "epoch": 2.998535871156662, - "eval_accuracy": 0.9853479853479854, - "eval_loss": 0.04894961416721344, - "eval_runtime": 15.5622, - "eval_samples_per_second": 87.713, - "eval_steps_per_second": 10.988, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, "step": 256 }, { "epoch": 3.994143484626647, - "eval_accuracy": 0.9897435897435898, - "eval_loss": 0.04228556528687477, - "eval_runtime": 15.6217, - "eval_samples_per_second": 87.378, - "eval_steps_per_second": 10.946, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9832333934847322, + "eval_loss": 0.08685966581106186, + "eval_precision": 0.9835305336122597, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9568, + "eval_samples_per_second": 229.152, + "eval_steps_per_second": 28.707, "step": 341 }, { "epoch": 4.989751098096632, - "eval_accuracy": 0.991941391941392, - "eval_loss": 0.044283464550971985, - "eval_runtime": 15.0667, - "eval_samples_per_second": 90.597, - "eval_steps_per_second": 11.35, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.983208365019189, + "eval_loss": 0.07458490133285522, + "eval_precision": 0.9833696765629429, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9419, + "eval_samples_per_second": 229.726, + "eval_steps_per_second": 28.779, "step": 426 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-426/training_args.bin b/checkpoint-426/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-426/training_args.bin +++ b/checkpoint-426/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-512/config.json b/checkpoint-512/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-512/config.json +++ b/checkpoint-512/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-512/model.safetensors b/checkpoint-512/model.safetensors index 6adabfcc62349df6737e9d27b1eea1db6a28242e..1c80cb983e1544b5c3ec32aaa1b41cb104b19955 100644 --- a/checkpoint-512/model.safetensors +++ b/checkpoint-512/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3dc7074a340619ed7e6d2c55347500f679c4e5f5a30b51392562feb760a9f1c7 +oid sha256:dbc5b2463f7b10d6accd90a38663b1fe5924ce417d20bd4c4b022491ab407a53 size 94763496 diff --git a/checkpoint-512/optimizer.pt b/checkpoint-512/optimizer.pt index e1679b4725d4c67c1b97ee50a0435eac1ef26c67..09ca234771791f6d85130f6302521f534489154d 100644 --- a/checkpoint-512/optimizer.pt +++ b/checkpoint-512/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:02b1c42643e3e59059b3734bb2a70cedcdb1a3f2b1cfd13f8b4f6444d7bb6e94 +oid sha256:00ec41f63df75118d702c2384056a8cc4b5a13080b78a48bdd542ffc79dc1c02 size 189552570 diff --git a/checkpoint-512/scheduler.pt b/checkpoint-512/scheduler.pt index 703c196fad30c816082cf754526114a4cef79d68..e664475626928694397d9c77a90e3bbe8924ca93 100644 --- a/checkpoint-512/scheduler.pt +++ b/checkpoint-512/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:11fe4216d2ecf2b0e2a833d51c97781e3fccf9e2a48a3b58142f2cf031047fa3 +oid sha256:bcc97a747eb11a8dc86d1d122f7b8fac6f5b54e0a4e11d9bd187896e44dca8fe size 1064 diff --git a/checkpoint-512/trainer_state.json b/checkpoint-512/trainer_state.json index 152ffae386a905ff5efcd3423b3162bbe389c3a0..bd6435809a76b12f438a2bfbb9bbd82c46ca0060 100644 --- a/checkpoint-512/trainer_state.json +++ b/checkpoint-512/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9926739926739927, + "best_metric": 0.9860805860805861, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512", "epoch": 5.997071742313324, "eval_steps": 500, @@ -10,70 +10,88 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 }, { "epoch": 2.998535871156662, - "eval_accuracy": 0.9853479853479854, - "eval_loss": 0.04894961416721344, - "eval_runtime": 15.5622, - "eval_samples_per_second": 87.713, - "eval_steps_per_second": 10.988, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, "step": 256 }, { "epoch": 3.994143484626647, - "eval_accuracy": 0.9897435897435898, - "eval_loss": 0.04228556528687477, - "eval_runtime": 15.6217, - "eval_samples_per_second": 87.378, - "eval_steps_per_second": 10.946, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9832333934847322, + "eval_loss": 0.08685966581106186, + "eval_precision": 0.9835305336122597, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9568, + "eval_samples_per_second": 229.152, + "eval_steps_per_second": 28.707, "step": 341 }, { "epoch": 4.989751098096632, - "eval_accuracy": 0.991941391941392, - "eval_loss": 0.044283464550971985, - "eval_runtime": 15.0667, - "eval_samples_per_second": 90.597, - "eval_steps_per_second": 11.35, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.983208365019189, + "eval_loss": 0.07458490133285522, + "eval_precision": 0.9833696765629429, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9419, + "eval_samples_per_second": 229.726, + "eval_steps_per_second": 28.779, "step": 426 }, { "epoch": 5.856515373352855, - "grad_norm": 0.008579956367611885, - "learning_rate": 3.639014166001028e-05, - "loss": 0.055, + "grad_norm": 0.01886621303856373, + "learning_rate": 1.6360497736760383e-05, + "loss": 0.0538, "step": 500 }, { "epoch": 5.997071742313324, - "eval_accuracy": 0.9926739926739927, - "eval_loss": 0.04338795691728592, - "eval_runtime": 14.898, - "eval_samples_per_second": 91.623, - "eval_steps_per_second": 11.478, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08699370175600052, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9399, + "eval_samples_per_second": 229.803, + "eval_steps_per_second": 28.789, "step": 512 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-512/training_args.bin b/checkpoint-512/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-512/training_args.bin +++ b/checkpoint-512/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-597/config.json b/checkpoint-597/config.json index 4550a22abfa803293b5dc6b2633d0201ac2ff44d..a8097f6a414b056b727b26aa15ffac67f0897e4b 100644 --- a/checkpoint-597/config.json +++ b/checkpoint-597/config.json @@ -45,6 +45,7 @@ "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, @@ -55,8 +56,8 @@ "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { - "crying": "0", - "no_crying": "1" + "crying": 0, + "no_crying": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, diff --git a/checkpoint-597/model.safetensors b/checkpoint-597/model.safetensors index 058d139f47aebef271e9f2f7538eaca7a1396a92..25b31c518467e2391d91ee0dd4cd3a262c859fcf 100644 --- a/checkpoint-597/model.safetensors +++ b/checkpoint-597/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:15156ce7496feffe08a94b0b76ed04e2398b912b56dfe3d329336cae4f32b8ab +oid sha256:a064606432f81dfcabef436b3a7746c96408c18ddc57930d2e91972b830e997f size 94763496 diff --git a/checkpoint-597/optimizer.pt b/checkpoint-597/optimizer.pt index 412b6d13c76b0137daf9a72e04b32a00949ba384..946201474d0386c9629e3a7390ca0fb1054fba39 100644 --- a/checkpoint-597/optimizer.pt +++ b/checkpoint-597/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:14a1d6ff155620819b854ea259f85accf2532818e85d714ea4a614a3b91d42cb +oid sha256:84091c5d2d0db5e72458d1db7aef4f39da72483fa57f4cd28ecc4085a3dfd425 size 189552570 diff --git a/checkpoint-597/scheduler.pt b/checkpoint-597/scheduler.pt index d8edf894f8452030b3eeeb62759bc959cb2bf4bb..b3c66fe4c8efd23e69ea1095bff5b035907ce704 100644 --- a/checkpoint-597/scheduler.pt +++ b/checkpoint-597/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:08eb49f7720b737aa4a97dd1c15d069bd20c33dc2f3de8105e499906c629b0bb +oid sha256:fbae7c9f313f104f989b156afed3a79758bf4cf1949ca702f760fa941bede2bf size 1064 diff --git a/checkpoint-597/trainer_state.json b/checkpoint-597/trainer_state.json index 37c0856c108edd95f8cd3842c60b0033e712a533..41592baeb8b5b489a557fd45cf082af0457a3d7d 100644 --- a/checkpoint-597/trainer_state.json +++ b/checkpoint-597/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9926739926739927, + "best_metric": 0.9860805860805861, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512", "epoch": 6.992679355783309, "eval_steps": 500, @@ -10,79 +10,100 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9772893772893773, - "eval_loss": 0.06922276318073273, - "eval_runtime": 15.5305, - "eval_samples_per_second": 87.892, - "eval_steps_per_second": 11.011, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 }, { "epoch": 1.9912152269399708, - "eval_accuracy": 0.9860805860805861, - "eval_loss": 0.04661192744970322, - "eval_runtime": 15.4605, - "eval_samples_per_second": 88.29, - "eval_steps_per_second": 11.06, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, "step": 170 }, { "epoch": 2.998535871156662, - "eval_accuracy": 0.9853479853479854, - "eval_loss": 0.04894961416721344, - "eval_runtime": 15.5622, - "eval_samples_per_second": 87.713, - "eval_steps_per_second": 10.988, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, "step": 256 }, { "epoch": 3.994143484626647, - "eval_accuracy": 0.9897435897435898, - "eval_loss": 0.04228556528687477, - "eval_runtime": 15.6217, - "eval_samples_per_second": 87.378, - "eval_steps_per_second": 10.946, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9832333934847322, + "eval_loss": 0.08685966581106186, + "eval_precision": 0.9835305336122597, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9568, + "eval_samples_per_second": 229.152, + "eval_steps_per_second": 28.707, "step": 341 }, { "epoch": 4.989751098096632, - "eval_accuracy": 0.991941391941392, - "eval_loss": 0.044283464550971985, - "eval_runtime": 15.0667, - "eval_samples_per_second": 90.597, - "eval_steps_per_second": 11.35, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.983208365019189, + "eval_loss": 0.07458490133285522, + "eval_precision": 0.9833696765629429, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9419, + "eval_samples_per_second": 229.726, + "eval_steps_per_second": 28.779, "step": 426 }, { "epoch": 5.856515373352855, - "grad_norm": 0.008579956367611885, - "learning_rate": 3.639014166001028e-05, - "loss": 0.055, + "grad_norm": 0.01886621303856373, + "learning_rate": 1.6360497736760383e-05, + "loss": 0.0538, "step": 500 }, { "epoch": 5.997071742313324, - "eval_accuracy": 0.9926739926739927, - "eval_loss": 0.04338795691728592, - "eval_runtime": 14.898, - "eval_samples_per_second": 91.623, - "eval_steps_per_second": 11.478, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08699370175600052, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9399, + "eval_samples_per_second": 229.803, + "eval_steps_per_second": 28.789, "step": 512 }, { "epoch": 6.992679355783309, - "eval_accuracy": 0.9926739926739927, - "eval_loss": 0.04399614781141281, - "eval_runtime": 15.2426, - "eval_samples_per_second": 89.552, - "eval_steps_per_second": 11.219, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08903729915618896, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9207, + "eval_samples_per_second": 230.546, + "eval_steps_per_second": 28.882, "step": 597 } ], "logging_steps": 500, - "max_steps": 850, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 10, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { diff --git a/checkpoint-597/training_args.bin b/checkpoint-597/training_args.bin index ba89ffbbb5f921e8486f25ee9c3f0a763e7c1271..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-597/training_args.bin +++ b/checkpoint-597/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84d763bc52a548d7900e672478766167dea5015bedfc4ad077e5cffda9256cc8 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/checkpoint-680/config.json b/checkpoint-680/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8097f6a414b056b727b26aa15ffac67f0897e4b --- /dev/null +++ b/checkpoint-680/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/checkpoint-680/model.safetensors b/checkpoint-680/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a080c63d9ecc785f11478a11b503d3b6394e1fb --- /dev/null +++ b/checkpoint-680/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44cc698d409540f6e674563ba636b09a358b51b95c971805d7140c78f749221d +size 94763496 diff --git a/checkpoint-680/optimizer.pt b/checkpoint-680/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..282ffead933dafdfc41c9704da2092252478d1b2 --- /dev/null +++ b/checkpoint-680/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ee67cfbe8e68b976d9e8b9d28361fe29aabb080922e8ca1dfc46687eee0bf5 +size 189552570 diff --git a/checkpoint-680/rng_state.pth b/checkpoint-680/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a16d2d5a5c8c4c2cf0cbd5e44b11c8f613fb105 --- /dev/null +++ b/checkpoint-680/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fd3252e5fe944df77172e7776b58570ce1e9687a28e4844bb5682e98356731 +size 14308 diff --git a/checkpoint-680/scheduler.pt b/checkpoint-680/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..dad5b9f283c7f4a850facd23602d37188473ac06 --- /dev/null +++ b/checkpoint-680/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3c5930117a39fdd2c8cd1183dafd9e8a9fe0628798a35edc18e6f58251dd0e +size 1064 diff --git a/checkpoint-680/trainer_state.json b/checkpoint-680/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c20a8ae4e36ba9dd06e180d5e721ec5359c6c812 --- /dev/null +++ b/checkpoint-680/trainer_state.json @@ -0,0 +1,145 @@ +{ + "best_metric": 0.9860805860805861, + "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512", + "epoch": 7.964860907759883, + "eval_steps": 500, + "global_step": 680, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.9956076134699854, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, + "step": 85 + }, + { + "epoch": 1.9912152269399708, + "eval_accuracy": 0.9772893772893773, + "eval_f1": 0.9772624500008753, + "eval_loss": 0.08473604917526245, + "eval_precision": 0.9772470873644479, + "eval_recall": 0.9772893772893773, + "eval_runtime": 5.9068, + "eval_samples_per_second": 231.09, + "eval_steps_per_second": 28.95, + "step": 170 + }, + { + "epoch": 2.998535871156662, + "eval_accuracy": 0.9765567765567765, + "eval_f1": 0.9766464967450174, + "eval_loss": 0.10245847702026367, + "eval_precision": 0.9768621127754256, + "eval_recall": 0.9765567765567765, + "eval_runtime": 5.8911, + "eval_samples_per_second": 231.706, + "eval_steps_per_second": 29.027, + "step": 256 + }, + { + "epoch": 3.994143484626647, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.9832333934847322, + "eval_loss": 0.08685966581106186, + "eval_precision": 0.9835305336122597, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9568, + "eval_samples_per_second": 229.152, + "eval_steps_per_second": 28.707, + "step": 341 + }, + { + "epoch": 4.989751098096632, + "eval_accuracy": 0.9831501831501831, + "eval_f1": 0.983208365019189, + "eval_loss": 0.07458490133285522, + "eval_precision": 0.9833696765629429, + "eval_recall": 0.9831501831501831, + "eval_runtime": 5.9419, + "eval_samples_per_second": 229.726, + "eval_steps_per_second": 28.779, + "step": 426 + }, + { + "epoch": 5.856515373352855, + "grad_norm": 0.01886621303856373, + "learning_rate": 1.6360497736760383e-05, + "loss": 0.0538, + "step": 500 + }, + { + "epoch": 5.997071742313324, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08699370175600052, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9399, + "eval_samples_per_second": 229.803, + "eval_steps_per_second": 28.789, + "step": 512 + }, + { + "epoch": 6.992679355783309, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08903729915618896, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9207, + "eval_samples_per_second": 230.546, + "eval_steps_per_second": 28.882, + "step": 597 + }, + { + "epoch": 7.964860907759883, + "eval_accuracy": 0.9860805860805861, + "eval_f1": 0.9860860332682386, + "eval_loss": 0.08778514713048935, + "eval_precision": 0.9860927746075414, + "eval_recall": 0.9860805860805861, + "eval_runtime": 5.9724, + "eval_samples_per_second": 228.552, + "eval_steps_per_second": 28.632, + "step": 680 + } + ], + "logging_steps": 500, + "max_steps": 680, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "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": 9.8908515478272e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-680/training_args.bin b/checkpoint-680/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c --- /dev/null +++ b/checkpoint-680/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a +size 5240 diff --git a/checkpoint-85/model.safetensors b/checkpoint-85/model.safetensors index e8883c56033a417e2f243fe418911b2d2790d0a2..3eae5fcd03daf5a5487aa4730e86c4b0645c9058 100644 --- a/checkpoint-85/model.safetensors +++ b/checkpoint-85/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:df8b4bbb885f9e08a2aba87cc03e2b8f1567fabb50c07badd97e951e719a31ac +oid sha256:a15277aa4797964b12aaedf5acf9218acf9f11597a299deaf3a64bad8d89176e size 94763496 diff --git a/checkpoint-85/optimizer.pt b/checkpoint-85/optimizer.pt index 1c53a8641f8d9f7a68758777cdec32654b160faf..99eb9a53faecf6366fcea8b97c1887c6b97da4d7 100644 --- a/checkpoint-85/optimizer.pt +++ b/checkpoint-85/optimizer.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb53a5b91f0cc0ec8e866f1a0a30bed26aa135a28c7a35daf2f9f91b6d1b05c9 +oid sha256:f9c4d0328f867e3a4371326367364a334fc34c6ecaba4f27c44bae6d943a3f5e size 189552570 diff --git a/checkpoint-85/rng_state.pth b/checkpoint-85/rng_state.pth index 5a526e8c7bacf2298b1d8a9aae7df27b006b54a4..2cd3048efdf016e5b13f4edbbdcb4f71b66e16f4 100644 --- a/checkpoint-85/rng_state.pth +++ b/checkpoint-85/rng_state.pth @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3db364763fd75b720e1e92ab8fcebb6dd7848ca54daab21f7eb8f5ba3936503a +oid sha256:74e1c11b94b090a41a3c1ccee3afde4077ab65e935c7dfa8559b5a7860ed3169 size 14308 diff --git a/checkpoint-85/scheduler.pt b/checkpoint-85/scheduler.pt index 674bd61dda0a039ccb554193e5a8b68c1508ba37..64070b82cd705945274cddf9bb4f5e9effabd7ea 100644 --- a/checkpoint-85/scheduler.pt +++ b/checkpoint-85/scheduler.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:08ad4dbf82e07518bfba3f03afe8b5f7b88773a00971103527317aa28f4df577 +oid sha256:1a3200599f03a01d89a474fcdd8a567058cd33b2f50dde928b44d422ff5012f0 size 1064 diff --git a/checkpoint-85/trainer_state.json b/checkpoint-85/trainer_state.json index 2ade1cb7d01ff9740d18613dd0b1057b83e58fcb..e03524cc7b4d9a6094f8eda580344b97ded58445 100644 --- a/checkpoint-85/trainer_state.json +++ b/checkpoint-85/trainer_state.json @@ -1,5 +1,5 @@ { - "best_metric": 0.9560439560439561, + "best_metric": 0.9641025641025641, "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-85", "epoch": 0.9956076134699854, "eval_steps": 500, @@ -10,21 +10,21 @@ "log_history": [ { "epoch": 0.9956076134699854, - "eval_accuracy": 0.9560439560439561, - "eval_f1": 0.956078786784062, - "eval_loss": 0.12699252367019653, - "eval_precision": 0.9561185753022488, - "eval_recall": 0.9560439560439561, - "eval_runtime": 5.8872, - "eval_samples_per_second": 231.858, - "eval_steps_per_second": 29.046, + "eval_accuracy": 0.9641025641025641, + "eval_f1": 0.9637911305761953, + "eval_loss": 0.12035853415727615, + "eval_precision": 0.9640509308043554, + "eval_recall": 0.9641025641025641, + "eval_runtime": 6.052, + "eval_samples_per_second": 225.545, + "eval_steps_per_second": 28.255, "step": 85 } ], "logging_steps": 500, - "max_steps": 85, + "max_steps": 680, "num_input_tokens_seen": 0, - "num_train_epochs": 1, + "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { @@ -42,12 +42,12 @@ "should_evaluate": false, "should_log": false, "should_save": true, - "should_training_stop": true + "should_training_stop": false }, "attributes": {} } }, - "total_flos": 1.237152405504e+16, + "total_flos": 1.241700759936e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null diff --git a/checkpoint-85/training_args.bin b/checkpoint-85/training_args.bin index 3edc4b9d87a39197e34724b6964a1412ad507f7c..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/checkpoint-85/training_args.bin +++ b/checkpoint-85/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d5b268a75d8603f488ccdf5a9c773941c717339e58b25823758027bd2a38cac6 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240 diff --git a/model.safetensors b/model.safetensors index caa5f600e6e05c65f940e23a16e7c9c7552d2405..1c80cb983e1544b5c3ec32aaa1b41cb104b19955 100644 --- a/model.safetensors +++ b/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cc34463948a1090e862c3f562483f73d9b8575c62d53f2695ead5ce878d0cb51 +oid sha256:dbc5b2463f7b10d6accd90a38663b1fe5924ce417d20bd4c4b022491ab407a53 size 94763496 diff --git a/runs/Sep08_19-57-45_ubumarcos/events.out.tfevents.1725818266.ubumarcos b/runs/Sep08_19-57-45_ubumarcos/events.out.tfevents.1725818266.ubumarcos new file mode 100644 index 0000000000000000000000000000000000000000..16b068d14ad477e5f65ddf9bf654cb342651b37c --- /dev/null +++ b/runs/Sep08_19-57-45_ubumarcos/events.out.tfevents.1725818266.ubumarcos @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baff4a5ec9071f4919cc3c8fb3eb07f523c18644538fec4decc9a9a9cc8b0691 +size 10183 diff --git a/training_args.bin b/training_args.bin index d81db1486814b17531760b8eaf1083f2793980a5..c8c5ee2f5a98e481c3fe2eaa5d0cb0485c79a08c 100644 --- a/training_args.bin +++ b/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e03a8d2517098878f32d3d0862d22bbbeeb4ecf145573639f810ef31e34b5336 +oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a size 5240