| { | |
| "best_metric": 0.14910581707954407, | |
| "best_model_checkpoint": "speech-multiclassifier-run-2/checkpoint-3192", | |
| "epoch": 5.0, | |
| "global_step": 15960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9373433583959903e-05, | |
| "loss": 0.2984, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.87468671679198e-05, | |
| "loss": 0.2101, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.81203007518797e-05, | |
| "loss": 0.2104, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.74937343358396e-05, | |
| "loss": 0.1926, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.68671679197995e-05, | |
| "loss": 0.1981, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.62406015037594e-05, | |
| "loss": 0.1808, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.14910581707954407, | |
| "eval_overall-accuracy": 0.9499647639182522, | |
| "eval_overall-f1": 0.9499647639182522, | |
| "eval_overall-precision": 0.9499647639182522, | |
| "eval_overall-recall": 0.9499647639182522, | |
| "eval_runtime": 79.4483, | |
| "eval_samples_per_second": 35.721, | |
| "eval_steps_per_second": 2.24, | |
| "step": 3192 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.56140350877193e-05, | |
| "loss": 0.1611, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.49874686716792e-05, | |
| "loss": 0.1598, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.43609022556391e-05, | |
| "loss": 0.1544, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.3734335839598997e-05, | |
| "loss": 0.1536, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.3107769423558898e-05, | |
| "loss": 0.1518, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.2481203007518798e-05, | |
| "loss": 0.1567, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.1555911898612976, | |
| "eval_overall-accuracy": 0.9513742071881607, | |
| "eval_overall-f1": 0.9513742071881607, | |
| "eval_overall-precision": 0.9513742071881607, | |
| "eval_overall-recall": 0.9513742071881607, | |
| "eval_runtime": 78.9404, | |
| "eval_samples_per_second": 35.951, | |
| "eval_steps_per_second": 2.255, | |
| "step": 6384 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.18546365914787e-05, | |
| "loss": 0.1468, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.1228070175438597e-05, | |
| "loss": 0.1265, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0601503759398497e-05, | |
| "loss": 0.1211, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.974937343358396e-06, | |
| "loss": 0.1232, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 9.348370927318296e-06, | |
| "loss": 0.1215, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.721804511278195e-06, | |
| "loss": 0.114, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 8.095238095238097e-06, | |
| "loss": 0.1328, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.17720717191696167, | |
| "eval_overall-accuracy": 0.952431289640592, | |
| "eval_overall-f1": 0.952431289640592, | |
| "eval_overall-precision": 0.952431289640592, | |
| "eval_overall-recall": 0.952431289640592, | |
| "eval_runtime": 78.7543, | |
| "eval_samples_per_second": 36.036, | |
| "eval_steps_per_second": 2.26, | |
| "step": 9576 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.468671679197995e-06, | |
| "loss": 0.1011, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.842105263157896e-06, | |
| "loss": 0.0942, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.215538847117794e-06, | |
| "loss": 0.0994, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 5.588972431077695e-06, | |
| "loss": 0.1042, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.962406015037594e-06, | |
| "loss": 0.0993, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.335839598997494e-06, | |
| "loss": 0.0954, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.1867782473564148, | |
| "eval_overall-accuracy": 0.95630725863284, | |
| "eval_overall-f1": 0.95630725863284, | |
| "eval_overall-precision": 0.95630725863284, | |
| "eval_overall-recall": 0.95630725863284, | |
| "eval_runtime": 79.4309, | |
| "eval_samples_per_second": 35.729, | |
| "eval_steps_per_second": 2.241, | |
| "step": 12768 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 3.7092731829573934e-06, | |
| "loss": 0.0798, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.0827067669172934e-06, | |
| "loss": 0.0773, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 2.456140350877193e-06, | |
| "loss": 0.0827, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.8295739348370927e-06, | |
| "loss": 0.0857, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.2030075187969925e-06, | |
| "loss": 0.0758, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.764411027568922e-07, | |
| "loss": 0.0756, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.20741401612758636, | |
| "eval_overall-accuracy": 0.9570119802677942, | |
| "eval_overall-f1": 0.9570119802677942, | |
| "eval_overall-precision": 0.9570119802677942, | |
| "eval_overall-recall": 0.9570119802677942, | |
| "eval_runtime": 80.2735, | |
| "eval_samples_per_second": 35.354, | |
| "eval_steps_per_second": 2.217, | |
| "step": 15960 | |
| } | |
| ], | |
| "max_steps": 15960, | |
| "num_train_epochs": 5, | |
| "total_flos": 4401666409805172.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |