| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021390374331550803, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.130124777183601e-05, | |
| "eval_loss": 3.975396156311035, | |
| "eval_runtime": 322.0131, | |
| "eval_samples_per_second": 18.341, | |
| "eval_steps_per_second": 9.17, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000213903743315508, | |
| "grad_norm": 1.9560655355453491, | |
| "learning_rate": 3e-05, | |
| "loss": 3.4802, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000427807486631016, | |
| "grad_norm": 1.8377642631530762, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7913, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005704099821746881, | |
| "eval_loss": 3.872006416320801, | |
| "eval_runtime": 322.3184, | |
| "eval_samples_per_second": 18.323, | |
| "eval_steps_per_second": 9.162, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006417112299465241, | |
| "grad_norm": 1.9639679193496704, | |
| "learning_rate": 9e-05, | |
| "loss": 3.6841, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000855614973262032, | |
| "grad_norm": 2.5727527141571045, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.792, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010695187165775401, | |
| "grad_norm": 3.9845669269561768, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7048, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011408199643493761, | |
| "eval_loss": 3.2958037853240967, | |
| "eval_runtime": 321.4005, | |
| "eval_samples_per_second": 18.376, | |
| "eval_steps_per_second": 9.188, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012834224598930481, | |
| "grad_norm": 3.1361684799194336, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.29, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001497326203208556, | |
| "grad_norm": 4.456937313079834, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.9882, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001711229946524064, | |
| "grad_norm": 2.675823211669922, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.06, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001711229946524064, | |
| "eval_loss": 3.014272689819336, | |
| "eval_runtime": 321.7999, | |
| "eval_samples_per_second": 18.353, | |
| "eval_steps_per_second": 9.177, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019251336898395723, | |
| "grad_norm": 2.242222547531128, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 3.0894, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0021390374331550803, | |
| "grad_norm": 2.5812113285064697, | |
| "learning_rate": 0.0, | |
| "loss": 3.036, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801873028546560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |