| { | |
| "best_metric": 4.5262579917907715, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-9/checkpoint-66", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 66, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.012012012012012012, | |
| "eval_f1": 0.0031978072179077205, | |
| "eval_loss": 4.749619007110596, | |
| "eval_precision": 0.002532561505065123, | |
| "eval_recall": 0.004337050805452293, | |
| "eval_runtime": 0.3642, | |
| "eval_samples_per_second": 799.034, | |
| "eval_steps_per_second": 101.595, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.03333333333333333, | |
| "eval_f1": 0.003970223325062034, | |
| "eval_loss": 4.679495334625244, | |
| "eval_precision": 0.0033112582781456954, | |
| "eval_recall": 0.004956629491945477, | |
| "eval_runtime": 0.8425, | |
| "eval_samples_per_second": 345.396, | |
| "eval_steps_per_second": 43.916, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.05795795795795796, | |
| "eval_f1": 0.0071546505228398454, | |
| "eval_loss": 4.5262579917907715, | |
| "eval_precision": 0.006435643564356435, | |
| "eval_recall": 0.0080545229244114, | |
| "eval_runtime": 0.361, | |
| "eval_samples_per_second": 806.114, | |
| "eval_steps_per_second": 102.496, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 264, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "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": 0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.901404269366272e-05, | |
| "num_train_epochs": 12, | |
| "per_device_train_batch_size": 64, | |
| "warmup_steps": 368, | |
| "weight_decay": 0.16924253041207893 | |
| } | |
| } | |