| { | |
| "best_metric": 0.6115783238201965, | |
| "best_model_checkpoint": "students_scores_model/run-2/checkpoint-846", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 846, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.5280922046056804, | |
| "eval_loss": 1.0346653461456299, | |
| "eval_runtime": 37.6542, | |
| "eval_samples_per_second": 59.754, | |
| "eval_steps_per_second": 7.489, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.773049645390071, | |
| "grad_norm": 15.857311248779297, | |
| "learning_rate": 4.500003283675112e-06, | |
| "loss": 1.0255, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.597013961740708, | |
| "eval_loss": 0.9119309782981873, | |
| "eval_runtime": 37.6531, | |
| "eval_samples_per_second": 59.756, | |
| "eval_steps_per_second": 7.489, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.6115783238201965, | |
| "eval_loss": 0.8967968225479126, | |
| "eval_runtime": 38.7112, | |
| "eval_samples_per_second": 58.123, | |
| "eval_steps_per_second": 7.285, | |
| "step": 846 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 846, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4203350064691200.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.1002898202280765e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 32, | |
| "weight_decay": 0.008293142825111385 | |
| } | |
| } | |