| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001180307031149513, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0264282849987515e-05, | |
| "eval_loss": 5.79030179977417, | |
| "eval_runtime": 940.4939, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 7.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015132141424993757, | |
| "grad_norm": 12.141045570373535, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9707, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030264282849987514, | |
| "grad_norm": 9.119531631469727, | |
| "learning_rate": 0.0001, | |
| "loss": 4.826, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030264282849987514, | |
| "eval_loss": 2.8944547176361084, | |
| "eval_runtime": 940.3469, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 7.398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004539642427498127, | |
| "grad_norm": 6.808655738830566, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1243, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006052856569997503, | |
| "grad_norm": 4.205870151519775, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006052856569997503, | |
| "eval_loss": 0.8383878469467163, | |
| "eval_runtime": 946.9426, | |
| "eval_samples_per_second": 14.693, | |
| "eval_steps_per_second": 7.347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007566070712496879, | |
| "grad_norm": 3.0068631172180176, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4534, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009079284854996254, | |
| "grad_norm": 5.501338958740234, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6805, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009079284854996254, | |
| "eval_loss": 0.759836733341217, | |
| "eval_runtime": 939.4983, | |
| "eval_samples_per_second": 14.809, | |
| "eval_steps_per_second": 7.405, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001059249899749563, | |
| "grad_norm": 3.4861016273498535, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6598, | |
| "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": 7213300567769088.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |