| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 25.0, |
| "eval_steps": 20, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.6262099742889404, |
| "learning_rate": 2.297979797979798e-05, |
| "loss": 2.8063, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.6399787068367004, |
| "learning_rate": 2.0454545454545457e-05, |
| "loss": 2.7403, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 2.703382968902588, |
| "eval_runtime": 0.7983, |
| "eval_samples_per_second": 2.505, |
| "eval_steps_per_second": 1.253, |
| "step": 20 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.6646024584770203, |
| "learning_rate": 1.7929292929292927e-05, |
| "loss": 2.6502, |
| "step": 30 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.751811683177948, |
| "learning_rate": 1.5404040404040404e-05, |
| "loss": 2.5553, |
| "step": 40 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.528615951538086, |
| "eval_runtime": 0.7939, |
| "eval_samples_per_second": 2.519, |
| "eval_steps_per_second": 1.26, |
| "step": 40 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 0.7830923199653625, |
| "learning_rate": 1.287878787878788e-05, |
| "loss": 2.4616, |
| "step": 50 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.6407041549682617, |
| "learning_rate": 1.0353535353535354e-05, |
| "loss": 2.3847, |
| "step": 60 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 2.367687463760376, |
| "eval_runtime": 0.7918, |
| "eval_samples_per_second": 2.526, |
| "eval_steps_per_second": 1.263, |
| "step": 60 |
| }, |
| { |
| "epoch": 17.5, |
| "grad_norm": 0.8876730799674988, |
| "learning_rate": 7.82828282828283e-06, |
| "loss": 2.3101, |
| "step": 70 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.857641339302063, |
| "learning_rate": 5.303030303030304e-06, |
| "loss": 2.2454, |
| "step": 80 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 2.2565157413482666, |
| "eval_runtime": 0.7857, |
| "eval_samples_per_second": 2.545, |
| "eval_steps_per_second": 1.273, |
| "step": 80 |
| }, |
| { |
| "epoch": 22.5, |
| "grad_norm": 0.6596696376800537, |
| "learning_rate": 2.777777777777778e-06, |
| "loss": 2.208, |
| "step": 90 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 0.9338703751564026, |
| "learning_rate": 2.525252525252526e-07, |
| "loss": 2.1862, |
| "step": 100 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_loss": 2.216174364089966, |
| "eval_runtime": 0.7813, |
| "eval_samples_per_second": 2.56, |
| "eval_steps_per_second": 1.28, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 25, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 212382892032000.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
