| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18160651920838183, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004656577415599534, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1999, | |
| "eval_samples_per_second": 21.667, | |
| "eval_steps_per_second": 10.953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023282887077997673, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.046565774155995346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046565774155995346, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2532, | |
| "eval_samples_per_second": 27.973, | |
| "eval_steps_per_second": 14.14, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06984866123399301, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09313154831199069, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09313154831199069, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1891, | |
| "eval_samples_per_second": 28.535, | |
| "eval_steps_per_second": 14.424, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11641443538998836, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13969732246798602, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13969732246798602, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2919, | |
| "eval_samples_per_second": 27.644, | |
| "eval_steps_per_second": 13.974, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1629802095459837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1264763208204288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |