| { | |
| "best_metric": 0.802, | |
| "best_model_checkpoint": "Bert_tinybert-distilled/run-26/checkpoint-516", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 516, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.019540548324585, | |
| "learning_rate": 0.00010368996748543682, | |
| "loss": 0.5941, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AUC": 0.819072, | |
| "eval_BAC": 0.7366666666666667, | |
| "eval_MCC": 0.47336741701441504, | |
| "eval_PR_AUC": 0.7723271954821734, | |
| "eval_accuracy": 0.7366666666666667, | |
| "eval_loss": 0.5035012364387512, | |
| "eval_runtime": 6.3714, | |
| "eval_samples_per_second": 235.425, | |
| "eval_steps_per_second": 7.377, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.5166783332824707, | |
| "learning_rate": 9.072872154975722e-05, | |
| "loss": 0.5442, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AUC": 0.8454275555555554, | |
| "eval_BAC": 0.7753333333333333, | |
| "eval_MCC": 0.5820649492328364, | |
| "eval_PR_AUC": 0.790134879283048, | |
| "eval_accuracy": 0.7753333333333333, | |
| "eval_loss": 0.4930420219898224, | |
| "eval_runtime": 6.2243, | |
| "eval_samples_per_second": 240.99, | |
| "eval_steps_per_second": 7.551, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.6264541149139404, | |
| "learning_rate": 7.776747561407761e-05, | |
| "loss": 0.5232, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AUC": 0.8629688888888889, | |
| "eval_BAC": 0.802, | |
| "eval_MCC": 0.6107257017486105, | |
| "eval_PR_AUC": 0.823189737884114, | |
| "eval_accuracy": 0.802, | |
| "eval_loss": 0.4630783796310425, | |
| "eval_runtime": 6.2126, | |
| "eval_samples_per_second": 241.445, | |
| "eval_steps_per_second": 7.565, | |
| "step": 516 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9, | |
| "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": 1351133190000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9196094567227121, | |
| "learning_rate": 0.00011665121342111642, | |
| "num_train_epochs": 9, | |
| "temperature": 22 | |
| } | |
| } | |