| { | |
| "best_metric": 0.3246058225631714, | |
| "best_model_checkpoint": "autotrain-bky4n-9127r/checkpoint-18", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 25.276142120361328, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.977174758911133, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.9326001405715942, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.0896, | |
| "eval_samples_per_second": 22.314, | |
| "eval_steps_per_second": 11.157, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 25.151567459106445, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.1028, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.748934745788574, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.552675724029541, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0767, | |
| "eval_samples_per_second": 26.086, | |
| "eval_steps_per_second": 13.043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 18.061382293701172, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.7341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 16.173526763916016, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.6532, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.748201310634613, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.0922, | |
| "eval_samples_per_second": 21.696, | |
| "eval_steps_per_second": 10.848, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 12.271732330322266, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.3989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 17.591384887695312, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8427, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.7152054309844971, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.0814, | |
| "eval_samples_per_second": 24.557, | |
| "eval_steps_per_second": 12.279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 14.792201042175293, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.5565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 16.458282470703125, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.5198105573654175, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.085, | |
| "eval_samples_per_second": 23.523, | |
| "eval_steps_per_second": 11.762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 15.189569473266602, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5917, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 14.650206565856934, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.4799, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.49704572558403015, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.0754, | |
| "eval_samples_per_second": 26.511, | |
| "eval_steps_per_second": 13.256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 18.180917739868164, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.6923, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 9.605114936828613, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2899, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.4110625088214874, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0745, | |
| "eval_samples_per_second": 26.848, | |
| "eval_steps_per_second": 13.424, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 12.864969253540039, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 12.070390701293945, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4061, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.5760210752487183, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0825, | |
| "eval_samples_per_second": 24.243, | |
| "eval_steps_per_second": 12.122, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 11.683992385864258, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.4051, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 12.339411735534668, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.3246058225631714, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0879, | |
| "eval_samples_per_second": 22.753, | |
| "eval_steps_per_second": 11.377, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 189101405896704.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |