| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010894729674519951, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00217894593490399, | |
| "grad_norm": 2.2648794651031494, | |
| "learning_rate": 1e-05, | |
| "loss": 29.1832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00217894593490399, | |
| "eval_loss": NaN, | |
| "eval_runtime": 258.107, | |
| "eval_samples_per_second": 2.995, | |
| "eval_steps_per_second": 1.499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00435789186980798, | |
| "grad_norm": 1.9293023347854614, | |
| "learning_rate": 2e-05, | |
| "loss": 28.361, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00435789186980798, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.926, | |
| "eval_samples_per_second": 18.437, | |
| "eval_steps_per_second": 9.231, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006536837804711971, | |
| "grad_norm": 2.23138165473938, | |
| "learning_rate": 3e-05, | |
| "loss": 32.707, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00871578373961596, | |
| "grad_norm": 2.1601669788360596, | |
| "learning_rate": 4e-05, | |
| "loss": 29.649, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00871578373961596, | |
| "eval_loss": NaN, | |
| "eval_runtime": 42.1418, | |
| "eval_samples_per_second": 18.343, | |
| "eval_steps_per_second": 9.183, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010894729674519951, | |
| "grad_norm": 3.325908899307251, | |
| "learning_rate": 5e-05, | |
| "loss": 28.3075, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8707116839731200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |