| { | |
| "best_metric": 0.804, | |
| "best_model_checkpoint": "Bert_tinybert-distilled/run-38/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": 2.369624614715576, | |
| "learning_rate": 0.00010150235987388685, | |
| "loss": 0.641, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AUC": 0.8192835555555557, | |
| "eval_BAC": 0.7393333333333334, | |
| "eval_MCC": 0.478738589243997, | |
| "eval_PR_AUC": 0.7668773893377483, | |
| "eval_accuracy": 0.7393333333333333, | |
| "eval_loss": 0.5342645645141602, | |
| "eval_runtime": 6.2413, | |
| "eval_samples_per_second": 240.333, | |
| "eval_steps_per_second": 7.53, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.409252643585205, | |
| "learning_rate": 9.022431988789944e-05, | |
| "loss": 0.5812, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AUC": 0.8472373333333332, | |
| "eval_BAC": 0.7773333333333333, | |
| "eval_MCC": 0.5854511255434387, | |
| "eval_PR_AUC": 0.7929492844718843, | |
| "eval_accuracy": 0.7773333333333333, | |
| "eval_loss": 0.508563756942749, | |
| "eval_runtime": 6.2422, | |
| "eval_samples_per_second": 240.301, | |
| "eval_steps_per_second": 7.529, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.4908885955810547, | |
| "learning_rate": 7.894627990191199e-05, | |
| "loss": 0.5572, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AUC": 0.8623342222222222, | |
| "eval_BAC": 0.804, | |
| "eval_MCC": 0.6144035052075252, | |
| "eval_PR_AUC": 0.821901299271215, | |
| "eval_accuracy": 0.804, | |
| "eval_loss": 0.4822913408279419, | |
| "eval_runtime": 6.2667, | |
| "eval_samples_per_second": 239.362, | |
| "eval_steps_per_second": 7.5, | |
| "step": 516 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1720, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 0.9992013304702073, | |
| "learning_rate": 0.00011278039985987428, | |
| "num_train_epochs": 10, | |
| "temperature": 16 | |
| } | |
| } | |