| { | |
| "best_metric": 0.6128642398583826, | |
| "best_model_checkpoint": "students_scores_model/run-3/checkpoint-1126", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1126, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8880994671403197, | |
| "grad_norm": 21.45689582824707, | |
| "learning_rate": 9.694484049714234e-06, | |
| "loss": 1.0844, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.5742027809107039, | |
| "eval_loss": 0.9514040946960449, | |
| "eval_runtime": 37.3512, | |
| "eval_samples_per_second": 60.239, | |
| "eval_steps_per_second": 7.55, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 28.843307495117188, | |
| "learning_rate": 5.617745593148113e-06, | |
| "loss": 0.8934, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.6128642398583826, | |
| "eval_loss": 0.8889710307121277, | |
| "eval_runtime": 37.662, | |
| "eval_samples_per_second": 59.742, | |
| "eval_steps_per_second": 7.488, | |
| "step": 1126 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1689, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4207559992768512.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.3771222506280354e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 16, | |
| "weight_decay": 0.0002914894301194684 | |
| } | |
| } | |