| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11204481792717087, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003734827264239029, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.076, | |
| "eval_samples_per_second": 36.736, | |
| "eval_steps_per_second": 18.531, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011204481792717087, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018674136321195144, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2667, | |
| "eval_samples_per_second": 49.853, | |
| "eval_steps_per_second": 25.147, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022408963585434174, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03361344537815126, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03734827264239029, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2315, | |
| "eval_samples_per_second": 50.637, | |
| "eval_steps_per_second": 25.543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04481792717086835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.056022408963585436, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.056022408963585436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.307, | |
| "eval_samples_per_second": 48.982, | |
| "eval_steps_per_second": 24.708, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06722689075630252, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07469654528478058, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2177, | |
| "eval_samples_per_second": 50.954, | |
| "eval_steps_per_second": 25.703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0896358543417367, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09337068160597572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2259, | |
| "eval_samples_per_second": 50.767, | |
| "eval_steps_per_second": 25.608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10084033613445378, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11204481792717087, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11204481792717087, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2114, | |
| "eval_samples_per_second": 51.1, | |
| "eval_steps_per_second": 25.776, | |
| "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": 180186409598976.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |