| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0037778617302606727, | |
| "eval_steps": 5, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007555723460521345, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4814, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007555723460521345, | |
| "eval_loss": NaN, | |
| "eval_runtime": 332.2255, | |
| "eval_samples_per_second": 6.712, | |
| "eval_steps_per_second": 3.356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001511144692104269, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 355.716, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022667170381564035, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003022289384208538, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0037778617302606727, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 888.046, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037778617302606727, | |
| "eval_loss": NaN, | |
| "eval_runtime": 249.8579, | |
| "eval_samples_per_second": 8.925, | |
| "eval_steps_per_second": 4.463, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "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": 5985653464498176.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |