| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017543859649122806, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "grad_norm": 2.1235438907751814e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.3265, | |
| "eval_samples_per_second": 180.924, | |
| "eval_steps_per_second": 90.462, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035087719298245615, | |
| "grad_norm": 2.284200490976218e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 4.5282857172423974e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.3271, | |
| "eval_samples_per_second": 180.844, | |
| "eval_steps_per_second": 90.422, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 2.3679200239712372e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 1.7480448150308803e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 2.185012272093445e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.4064, | |
| "eval_samples_per_second": 170.648, | |
| "eval_steps_per_second": 85.324, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012280701754385965, | |
| "grad_norm": 3.738150917342864e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 5.03201263200026e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 5.7706041843630373e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.3397, | |
| "eval_samples_per_second": 179.143, | |
| "eval_steps_per_second": 89.572, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 5.83661203563679e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |