| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.991869918699187, | |
| "eval_steps": 500, | |
| "global_step": 61, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 44.75566557733456, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 22.155759748420145, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 1.6903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 13.109775732485431, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 1.4186, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 13.52084711445301, | |
| "learning_rate": 1.8936326403234125e-05, | |
| "loss": 1.2585, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 12.039835289226906, | |
| "learning_rate": 1.7273736415730488e-05, | |
| "loss": 1.0465, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4065040650406504, | |
| "grad_norm": 8.6077622745051, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.8583, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 5.273120012817056, | |
| "learning_rate": 1.2306158707424402e-05, | |
| "loss": 0.7416, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5691056910569106, | |
| "grad_norm": 2.4961015181305304, | |
| "learning_rate": 9.418551710895243e-06, | |
| "loss": 0.699, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 1.9961638134484518, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.6797, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 1.6758021856566212, | |
| "learning_rate": 4.028414082972141e-06, | |
| "loss": 0.6653, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 1.466022130424723, | |
| "learning_rate": 1.9787680724495617e-06, | |
| "loss": 0.6514, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8943089430894309, | |
| "grad_norm": 1.2570236883108519, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.6458, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 1.2304481698504517, | |
| "learning_rate": 1.6918417287318245e-08, | |
| "loss": 0.6421, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.991869918699187, | |
| "eval_loss": 2.0331625938415527, | |
| "eval_runtime": 0.7095, | |
| "eval_samples_per_second": 33.828, | |
| "eval_steps_per_second": 1.409, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.991869918699187, | |
| "step": 61, | |
| "total_flos": 25439628165120.0, | |
| "train_loss": 0.9141011159928119, | |
| "train_runtime": 665.6488, | |
| "train_samples_per_second": 47.124, | |
| "train_steps_per_second": 0.092 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 61, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 25439628165120.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |