| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024451372333272204, | |
| "eval_steps": 34, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "grad_norm": 0.34075865149497986, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "eval_loss": 1.4345602989196777, | |
| "eval_runtime": 756.5177, | |
| "eval_samples_per_second": 3.414, | |
| "eval_steps_per_second": 1.138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009780548933308881, | |
| "grad_norm": 0.4255630671977997, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.4716, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014670823399963323, | |
| "grad_norm": 0.3547780513763428, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019561097866617762, | |
| "grad_norm": 0.31101933121681213, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.3129, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024451372333272204, | |
| "grad_norm": 0.3006742596626282, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2779, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8348676548198400.0, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |