| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 2046, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8351485729217529, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.4848, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.31648269295692444, | |
| "eval_runtime": 3.2931, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 4.251, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.2281255722045898, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.2556, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.2928766906261444, | |
| "eval_runtime": 3.0078, | |
| "eval_samples_per_second": 4.655, | |
| "eval_steps_per_second": 4.655, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9520564675331116, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1603, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.3044079840183258, | |
| "eval_runtime": 3.4408, | |
| "eval_samples_per_second": 4.069, | |
| "eval_steps_per_second": 4.069, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.4696643352508545, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 0.0987, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.30785349011421204, | |
| "eval_runtime": 3.5553, | |
| "eval_samples_per_second": 3.938, | |
| "eval_steps_per_second": 3.938, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.1521769762039185, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.068, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.3232688903808594, | |
| "eval_runtime": 3.0456, | |
| "eval_samples_per_second": 4.597, | |
| "eval_steps_per_second": 4.597, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.5258505940437317, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0491, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.33182573318481445, | |
| "eval_runtime": 2.9002, | |
| "eval_samples_per_second": 4.827, | |
| "eval_steps_per_second": 4.827, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.3425712287425995, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0392, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.34946054220199585, | |
| "eval_runtime": 3.1735, | |
| "eval_samples_per_second": 4.412, | |
| "eval_steps_per_second": 4.412, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.3734869360923767, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0345, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.3462740480899811, | |
| "eval_runtime": 2.8648, | |
| "eval_samples_per_second": 4.887, | |
| "eval_steps_per_second": 4.887, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.43035927414894104, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0313, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.35318323969841003, | |
| "eval_runtime": 3.6767, | |
| "eval_samples_per_second": 3.808, | |
| "eval_steps_per_second": 3.808, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.2107960730791092, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0292, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.36506205797195435, | |
| "eval_runtime": 2.9324, | |
| "eval_samples_per_second": 4.774, | |
| "eval_steps_per_second": 4.774, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.2807460129261017, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0275, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.37569472193717957, | |
| "eval_runtime": 3.1107, | |
| "eval_samples_per_second": 4.501, | |
| "eval_steps_per_second": 4.501, | |
| "step": 2046 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2790, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8580253388636160.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |