| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006843455945252353, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.843455945252352e-05, | |
| "grad_norm": 22.180809020996094, | |
| "learning_rate": 2e-05, | |
| "loss": 18.4493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.843455945252352e-05, | |
| "eval_loss": 4.43656063079834, | |
| "eval_runtime": 70.5079, | |
| "eval_samples_per_second": 87.267, | |
| "eval_steps_per_second": 43.64, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013686911890504704, | |
| "grad_norm": 20.325641632080078, | |
| "learning_rate": 4e-05, | |
| "loss": 18.4389, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020530367835757058, | |
| "grad_norm": 28.384052276611328, | |
| "learning_rate": 6e-05, | |
| "loss": 23.389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020530367835757058, | |
| "eval_loss": 4.37176513671875, | |
| "eval_runtime": 70.5766, | |
| "eval_samples_per_second": 87.182, | |
| "eval_steps_per_second": 43.598, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002737382378100941, | |
| "grad_norm": 16.388090133666992, | |
| "learning_rate": 8e-05, | |
| "loss": 14.8767, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00034217279726261765, | |
| "grad_norm": 22.81606101989746, | |
| "learning_rate": 0.0001, | |
| "loss": 19.229, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00041060735671514116, | |
| "grad_norm": 20.989870071411133, | |
| "learning_rate": 0.00012, | |
| "loss": 16.6525, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00041060735671514116, | |
| "eval_loss": 3.6957924365997314, | |
| "eval_runtime": 71.1839, | |
| "eval_samples_per_second": 86.438, | |
| "eval_steps_per_second": 43.226, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00047904191616766467, | |
| "grad_norm": 21.524320602416992, | |
| "learning_rate": 0.00014, | |
| "loss": 15.0557, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005474764756201882, | |
| "grad_norm": 16.7387638092041, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3882, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006159110350727117, | |
| "grad_norm": 16.268218994140625, | |
| "learning_rate": 0.00018, | |
| "loss": 9.0993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006159110350727117, | |
| "eval_loss": 2.402513265609741, | |
| "eval_runtime": 70.9504, | |
| "eval_samples_per_second": 86.723, | |
| "eval_steps_per_second": 43.368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006843455945252353, | |
| "grad_norm": 18.078418731689453, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0813, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 75069652992000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |