| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00782472613458529, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000782472613458529, | |
| "grad_norm": 45.14743423461914, | |
| "learning_rate": 2e-05, | |
| "loss": 12.1042, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000782472613458529, | |
| "eval_loss": 2.958329439163208, | |
| "eval_runtime": 18.463, | |
| "eval_samples_per_second": 29.194, | |
| "eval_steps_per_second": 14.624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001564945226917058, | |
| "grad_norm": 33.25700378417969, | |
| "learning_rate": 4e-05, | |
| "loss": 11.5379, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002347417840375587, | |
| "grad_norm": 40.21052169799805, | |
| "learning_rate": 6e-05, | |
| "loss": 15.6524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002347417840375587, | |
| "eval_loss": 2.8615334033966064, | |
| "eval_runtime": 18.3838, | |
| "eval_samples_per_second": 29.319, | |
| "eval_steps_per_second": 14.687, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003129890453834116, | |
| "grad_norm": 28.999013900756836, | |
| "learning_rate": 8e-05, | |
| "loss": 10.687, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003912363067292645, | |
| "grad_norm": 36.77431106567383, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4467, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004694835680751174, | |
| "grad_norm": 39.24850082397461, | |
| "learning_rate": 0.00012, | |
| "loss": 9.7763, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004694835680751174, | |
| "eval_loss": 2.4367876052856445, | |
| "eval_runtime": 18.5013, | |
| "eval_samples_per_second": 29.133, | |
| "eval_steps_per_second": 14.594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005477308294209703, | |
| "grad_norm": 29.54821014404297, | |
| "learning_rate": 0.00014, | |
| "loss": 8.2643, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006259780907668232, | |
| "grad_norm": 25.23687171936035, | |
| "learning_rate": 0.00016, | |
| "loss": 9.4489, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007042253521126761, | |
| "grad_norm": 26.87394142150879, | |
| "learning_rate": 0.00018, | |
| "loss": 7.4176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007042253521126761, | |
| "eval_loss": 2.3198800086975098, | |
| "eval_runtime": 18.4501, | |
| "eval_samples_per_second": 29.214, | |
| "eval_steps_per_second": 14.634, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "grad_norm": 30.283151626586914, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7985, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |