| { |
| "best_global_step": 600, |
| "best_metric": 0.9974874371859297, |
| "best_model_checkpoint": "musical_instrument_detection_improved/checkpoint-600", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.25125628140703515, |
| "grad_norm": 0.4818384647369385, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.4941, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5025125628140703, |
| "grad_norm": 4.753159046173096, |
| "learning_rate": 3.266666666666667e-05, |
| "loss": 0.0539, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7537688442211056, |
| "grad_norm": 15.198661804199219, |
| "learning_rate": 4.933333333333334e-05, |
| "loss": 0.1284, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.40100908279418945, |
| "learning_rate": 6.6e-05, |
| "loss": 0.1306, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9748743718592965, |
| "eval_f1_macro": 0.9731342037379646, |
| "eval_loss": 0.07195427268743515, |
| "eval_precision_macro": 0.9712150747238466, |
| "eval_recall_macro": 0.9761503412881977, |
| "eval_runtime": 12.3998, |
| "eval_samples_per_second": 32.097, |
| "eval_steps_per_second": 4.032, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.2512562814070352, |
| "grad_norm": 0.03644077107310295, |
| "learning_rate": 8.266666666666667e-05, |
| "loss": 0.0742, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.5025125628140703, |
| "grad_norm": 0.0054424116387963295, |
| "learning_rate": 9.933333333333334e-05, |
| "loss": 0.0654, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7537688442211055, |
| "grad_norm": 0.05749930813908577, |
| "learning_rate": 9.822222222222223e-05, |
| "loss": 0.0411, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.034677326679229736, |
| "learning_rate": 9.637037037037037e-05, |
| "loss": 0.1626, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9773869346733668, |
| "eval_f1_macro": 0.9760285913720755, |
| "eval_loss": 0.1097569689154625, |
| "eval_precision_macro": 0.9750499571795603, |
| "eval_recall_macro": 0.9784172661870504, |
| "eval_runtime": 12.8602, |
| "eval_samples_per_second": 30.948, |
| "eval_steps_per_second": 3.888, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.251256281407035, |
| "grad_norm": 8.391584396362305, |
| "learning_rate": 9.451851851851853e-05, |
| "loss": 0.0613, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.5025125628140703, |
| "grad_norm": 0.05065636709332466, |
| "learning_rate": 9.266666666666666e-05, |
| "loss": 0.0783, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.7537688442211055, |
| "grad_norm": 4.692741394042969, |
| "learning_rate": 9.081481481481482e-05, |
| "loss": 0.0838, |
| "step": 275 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.001607125741429627, |
| "learning_rate": 8.896296296296297e-05, |
| "loss": 0.0577, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9849246231155779, |
| "eval_f1_macro": 0.9840659199317944, |
| "eval_loss": 0.06375118345022202, |
| "eval_precision_macro": 0.9825340045928281, |
| "eval_recall_macro": 0.9860503753859658, |
| "eval_runtime": 12.6279, |
| "eval_samples_per_second": 31.517, |
| "eval_steps_per_second": 3.959, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.251256281407035, |
| "grad_norm": 0.0066846804693341255, |
| "learning_rate": 8.711111111111112e-05, |
| "loss": 0.0161, |
| "step": 325 |
| }, |
| { |
| "epoch": 3.5025125628140703, |
| "grad_norm": 5.183607578277588, |
| "learning_rate": 8.525925925925926e-05, |
| "loss": 0.0852, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.7537688442211055, |
| "grad_norm": 1.3307738304138184, |
| "learning_rate": 8.340740740740741e-05, |
| "loss": 0.0025, |
| "step": 375 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.0007463983492925763, |
| "learning_rate": 8.155555555555557e-05, |
| "loss": 0.031, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9949748743718593, |
| "eval_f1_macro": 0.9944572643771775, |
| "eval_loss": 0.023198017850518227, |
| "eval_precision_macro": 0.9944572643771775, |
| "eval_recall_macro": 0.9944572643771775, |
| "eval_runtime": 12.4966, |
| "eval_samples_per_second": 31.849, |
| "eval_steps_per_second": 4.001, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.251256281407035, |
| "grad_norm": 0.0033074100501835346, |
| "learning_rate": 7.97037037037037e-05, |
| "loss": 0.0155, |
| "step": 425 |
| }, |
| { |
| "epoch": 4.50251256281407, |
| "grad_norm": 2.0624492168426514, |
| "learning_rate": 7.785185185185186e-05, |
| "loss": 0.0366, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.7537688442211055, |
| "grad_norm": 0.00034747723839245737, |
| "learning_rate": 7.6e-05, |
| "loss": 0.0139, |
| "step": 475 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.0007314584800042212, |
| "learning_rate": 7.414814814814815e-05, |
| "loss": 0.0123, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9874371859296482, |
| "eval_f1_macro": 0.9862145023435346, |
| "eval_loss": 0.05530214682221413, |
| "eval_precision_macro": 0.984984984984985, |
| "eval_recall_macro": 0.9880095923261392, |
| "eval_runtime": 12.5007, |
| "eval_samples_per_second": 31.838, |
| "eval_steps_per_second": 4.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.251256281407035, |
| "grad_norm": 0.0016032257117331028, |
| "learning_rate": 7.22962962962963e-05, |
| "loss": 0.0002, |
| "step": 525 |
| }, |
| { |
| "epoch": 5.50251256281407, |
| "grad_norm": 2.0849623680114746, |
| "learning_rate": 7.044444444444444e-05, |
| "loss": 0.0597, |
| "step": 550 |
| }, |
| { |
| "epoch": 5.7537688442211055, |
| "grad_norm": 0.006351375486701727, |
| "learning_rate": 6.85925925925926e-05, |
| "loss": 0.0191, |
| "step": 575 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.942449152469635, |
| "learning_rate": 6.674074074074075e-05, |
| "loss": 0.0016, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9974874371859297, |
| "eval_f1_macro": 0.9972316853386666, |
| "eval_loss": 0.02638443559408188, |
| "eval_precision_macro": 0.9968847352024922, |
| "eval_recall_macro": 0.9976019184652278, |
| "eval_runtime": 12.501, |
| "eval_samples_per_second": 31.838, |
| "eval_steps_per_second": 4.0, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 15, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.470607627264983e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
