| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3071895424836601, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 6.301905632019043, | |
| "learning_rate": 2.20959595959596e-05, | |
| "loss": 2.8043, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 3.043227434158325, | |
| "learning_rate": 1.893939393939394e-05, | |
| "loss": 0.7822, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 3.3406591415405273, | |
| "learning_rate": 1.5782828282828283e-05, | |
| "loss": 0.7175, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 12.487229347229004, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.5927, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "eval_loss": 0.663481593132019, | |
| "eval_runtime": 57.2108, | |
| "eval_samples_per_second": 5.349, | |
| "eval_steps_per_second": 0.682, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8169934640522876, | |
| "grad_norm": 1.7172660827636719, | |
| "learning_rate": 9.46969696969697e-06, | |
| "loss": 0.7212, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 2.2951853275299072, | |
| "learning_rate": 6.313131313131314e-06, | |
| "loss": 0.7329, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1437908496732025, | |
| "grad_norm": 1.7792625427246094, | |
| "learning_rate": 3.156565656565657e-06, | |
| "loss": 0.6664, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3071895424836601, | |
| "grad_norm": 2.2873575687408447, | |
| "learning_rate": 0.0, | |
| "loss": 0.697, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3071895424836601, | |
| "eval_loss": 0.6353954672813416, | |
| "eval_runtime": 58.4084, | |
| "eval_samples_per_second": 5.239, | |
| "eval_steps_per_second": 0.668, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 467417274777600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |