| { | |
| "best_metric": 1.0671894550323486, | |
| "best_model_checkpoint": "Ships/checkpoint-16", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 13.132343292236328, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 10.336759567260742, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4683, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 8.432352066040039, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.3522, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 13.556530952453613, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.7467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3, | |
| "eval_f1_macro": 0.225, | |
| "eval_f1_micro": 0.3, | |
| "eval_f1_weighted": 0.18, | |
| "eval_loss": 1.4493657350540161, | |
| "eval_precision_macro": 0.16666666666666666, | |
| "eval_precision_micro": 0.3, | |
| "eval_precision_weighted": 0.13333333333333333, | |
| "eval_recall_macro": 0.375, | |
| "eval_recall_micro": 0.3, | |
| "eval_recall_weighted": 0.3, | |
| "eval_runtime": 39.4034, | |
| "eval_samples_per_second": 0.254, | |
| "eval_steps_per_second": 0.025, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 10.950541496276855, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 1.2704, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 7.838518142700195, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.1342, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 8.095083236694336, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.0818, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.888486862182617, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.2193, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5916666666666667, | |
| "eval_f1_micro": 0.6, | |
| "eval_f1_weighted": 0.5800000000000001, | |
| "eval_loss": 1.1207724809646606, | |
| "eval_precision_macro": 0.5833333333333333, | |
| "eval_precision_micro": 0.6, | |
| "eval_precision_weighted": 0.5833333333333333, | |
| "eval_recall_macro": 0.625, | |
| "eval_recall_micro": 0.6, | |
| "eval_recall_weighted": 0.6, | |
| "eval_runtime": 32.0397, | |
| "eval_samples_per_second": 0.312, | |
| "eval_steps_per_second": 0.031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 8.940570831298828, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.8535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 7.082061767578125, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.7457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 4.955725193023682, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.4903, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 11.013522148132324, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.9821, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7, | |
| "eval_f1_macro": 0.7, | |
| "eval_f1_micro": 0.7, | |
| "eval_f1_weighted": 0.6933333333333334, | |
| "eval_loss": 1.1053988933563232, | |
| "eval_precision_macro": 0.7499999999999999, | |
| "eval_precision_micro": 0.7, | |
| "eval_precision_weighted": 0.7333333333333333, | |
| "eval_recall_macro": 0.7083333333333333, | |
| "eval_recall_micro": 0.7, | |
| "eval_recall_weighted": 0.7, | |
| "eval_runtime": 44.086, | |
| "eval_samples_per_second": 0.227, | |
| "eval_steps_per_second": 0.023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "grad_norm": 5.3065690994262695, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.6126, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 6.9573259353637695, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.5428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 7.6499199867248535, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.6001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 3.9723899364471436, | |
| "learning_rate": 0.0, | |
| "loss": 0.3854, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7, | |
| "eval_f1_macro": 0.7, | |
| "eval_f1_micro": 0.7, | |
| "eval_f1_weighted": 0.6933333333333334, | |
| "eval_loss": 1.0671894550323486, | |
| "eval_precision_macro": 0.7499999999999999, | |
| "eval_precision_micro": 0.7, | |
| "eval_precision_weighted": 0.7333333333333333, | |
| "eval_recall_macro": 0.7083333333333333, | |
| "eval_recall_micro": 0.7, | |
| "eval_recall_weighted": 0.7, | |
| "eval_runtime": 32.5746, | |
| "eval_samples_per_second": 0.307, | |
| "eval_steps_per_second": 0.031, | |
| "step": 16 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 16, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 1.2897108891795456e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |