| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 93, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16260162601626016, |
| "grad_norm": 8.03538990020752, |
| "learning_rate": 9.99695413509548e-06, |
| "loss": 0.7373, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3252032520325203, |
| "grad_norm": 5.579499244689941, |
| "learning_rate": 9.890738003669029e-06, |
| "loss": 0.6633, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "grad_norm": 6.246809482574463, |
| "learning_rate": 9.635919272833938e-06, |
| "loss": 0.6976, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6504065040650406, |
| "grad_norm": 5.933238506317139, |
| "learning_rate": 9.24024048078213e-06, |
| "loss": 0.6842, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8130081300813008, |
| "grad_norm": 5.804722785949707, |
| "learning_rate": 8.715724127386971e-06, |
| "loss": 0.691, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 6.376720905303955, |
| "learning_rate": 8.078307376628292e-06, |
| "loss": 0.7457, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1300813008130082, |
| "grad_norm": 4.015146255493164, |
| "learning_rate": 7.347357813929455e-06, |
| "loss": 0.4042, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.2926829268292683, |
| "grad_norm": 3.916799545288086, |
| "learning_rate": 6.545084971874738e-06, |
| "loss": 0.333, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.4552845528455285, |
| "grad_norm": 4.416755199432373, |
| "learning_rate": 5.695865504800328e-06, |
| "loss": 0.3379, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.6178861788617886, |
| "grad_norm": 5.097067832946777, |
| "learning_rate": 4.825502516487497e-06, |
| "loss": 0.3403, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.7804878048780488, |
| "grad_norm": 5.069389820098877, |
| "learning_rate": 3.960441545911205e-06, |
| "loss": 0.2831, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.943089430894309, |
| "grad_norm": 4.832127094268799, |
| "learning_rate": 3.12696703292044e-06, |
| "loss": 0.3053, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.097560975609756, |
| "grad_norm": 2.930651903152466, |
| "learning_rate": 2.3504036788339763e-06, |
| "loss": 0.2135, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.2601626016260163, |
| "grad_norm": 2.997800827026367, |
| "learning_rate": 1.6543469682057105e-06, |
| "loss": 0.1665, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.4227642276422765, |
| "grad_norm": 3.1228225231170654, |
| "learning_rate": 1.0599462319663906e-06, |
| "loss": 0.1545, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.5853658536585367, |
| "grad_norm": 3.1767897605895996, |
| "learning_rate": 5.852620357053651e-07, |
| "loss": 0.1774, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.747967479674797, |
| "grad_norm": 3.0374221801757812, |
| "learning_rate": 2.447174185242324e-07, |
| "loss": 0.1657, |
| "step": 85 |
| }, |
| { |
| "epoch": 2.910569105691057, |
| "grad_norm": 2.8217225074768066, |
| "learning_rate": 4.865965629214819e-08, |
| "loss": 0.1569, |
| "step": 90 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 93, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2533230053045043e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
