| { | |
| "best_metric": 3.9866342544555664, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-3/checkpoint-129", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 129, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.021621621621621623, | |
| "eval_f1": 0.004198740377886634, | |
| "eval_loss": 4.7169880867004395, | |
| "eval_precision": 0.003367003367003367, | |
| "eval_recall": 0.0055762081784386614, | |
| "eval_runtime": 0.3678, | |
| "eval_samples_per_second": 791.214, | |
| "eval_steps_per_second": 100.601, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.05795795795795796, | |
| "eval_f1": 0.006104328523862375, | |
| "eval_loss": 4.505440711975098, | |
| "eval_precision": 0.005527638190954774, | |
| "eval_recall": 0.006815365551425031, | |
| "eval_runtime": 0.3666, | |
| "eval_samples_per_second": 793.767, | |
| "eval_steps_per_second": 100.926, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.1810810810810811, | |
| "eval_f1": 0.03324099722991689, | |
| "eval_loss": 3.9866342544555664, | |
| "eval_precision": 0.03767660910518053, | |
| "eval_recall": 0.02973977695167286, | |
| "eval_runtime": 0.5428, | |
| "eval_samples_per_second": 536.084, | |
| "eval_steps_per_second": 68.162, | |
| "step": 129 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 559, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "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": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.6487307281599633e-05, | |
| "num_train_epochs": 13, | |
| "per_device_train_batch_size": 32, | |
| "warmup_steps": 215, | |
| "weight_decay": 0.11823639232883996 | |
| } | |
| } | |