| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.050473186119873815, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010094637223974764, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010094637223974764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 138.411, | |
| "eval_samples_per_second": 1.207, | |
| "eval_steps_per_second": 0.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02018927444794953, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02018927444794953, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7924, | |
| "eval_samples_per_second": 44.036, | |
| "eval_steps_per_second": 22.15, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03028391167192429, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04037854889589906, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04037854889589906, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7868, | |
| "eval_samples_per_second": 44.101, | |
| "eval_steps_per_second": 22.182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.050473186119873815, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "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": 3703101597941760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |