| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.9664, | |
| "eval_steps": 500, | |
| "global_step": 936, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.056663136929273605, | |
| "learning_rate": 0.0001, | |
| "loss": 1.074, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.05507315695285797, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9146, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07707152515649796, | |
| "learning_rate": 0.00018803827751196172, | |
| "loss": 0.8534, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2752, | |
| "grad_norm": 0.0732378214597702, | |
| "learning_rate": 0.00017607655502392347, | |
| "loss": 0.8235, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5952, | |
| "grad_norm": 0.07976480573415756, | |
| "learning_rate": 0.00016411483253588518, | |
| "loss": 0.826, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9152, | |
| "grad_norm": 0.06750624626874924, | |
| "learning_rate": 0.0001521531100478469, | |
| "loss": 0.831, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.2304, | |
| "grad_norm": 0.07449544221162796, | |
| "learning_rate": 0.00014019138755980864, | |
| "loss": 0.811, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5504, | |
| "grad_norm": 0.079868845641613, | |
| "learning_rate": 0.00012822966507177036, | |
| "loss": 0.8053, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.8704, | |
| "grad_norm": 0.07078613340854645, | |
| "learning_rate": 0.00011626794258373206, | |
| "loss": 0.8033, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.1856, | |
| "grad_norm": 0.07061311602592468, | |
| "learning_rate": 0.00010430622009569377, | |
| "loss": 0.7903, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.5056000000000003, | |
| "grad_norm": 0.06763527542352676, | |
| "learning_rate": 9.234449760765552e-05, | |
| "loss": 0.7832, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.8256, | |
| "grad_norm": 0.07528316229581833, | |
| "learning_rate": 8.038277511961723e-05, | |
| "loss": 0.7846, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.1408, | |
| "grad_norm": 0.07467867434024811, | |
| "learning_rate": 6.842105263157895e-05, | |
| "loss": 0.784, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.4608, | |
| "grad_norm": 0.07377243041992188, | |
| "learning_rate": 5.645933014354067e-05, | |
| "loss": 0.7711, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.7808, | |
| "grad_norm": 0.07530038803815842, | |
| "learning_rate": 4.449760765550239e-05, | |
| "loss": 0.7678, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.096, | |
| "grad_norm": 0.08314452320337296, | |
| "learning_rate": 3.253588516746411e-05, | |
| "loss": 0.773, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.416, | |
| "grad_norm": 0.0708891972899437, | |
| "learning_rate": 2.057416267942584e-05, | |
| "loss": 0.768, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.736, | |
| "grad_norm": 0.07850036770105362, | |
| "learning_rate": 8.61244019138756e-06, | |
| "loss": 0.7569, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6924141879311565e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |