| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.19997818023128955, |
| "eval_steps": 500, |
| "global_step": 3666, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.027274710888064588, |
| "grad_norm": 8.132363319396973, |
| "learning_rate": 1.976e-05, |
| "loss": 3.5991, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.054549421776129176, |
| "grad_norm": 7.099025249481201, |
| "learning_rate": 1.9818702290076336e-05, |
| "loss": 2.8754, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.08182413266419376, |
| "grad_norm": 7.820577621459961, |
| "learning_rate": 1.963520258367587e-05, |
| "loss": 2.6895, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.10909884355225835, |
| "grad_norm": 5.448477268218994, |
| "learning_rate": 1.94517028772754e-05, |
| "loss": 2.6494, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.13637355444032292, |
| "grad_norm": 6.391147613525391, |
| "learning_rate": 1.926820317087493e-05, |
| "loss": 2.5544, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.16364826532838753, |
| "grad_norm": 5.117228031158447, |
| "learning_rate": 1.908470346447446e-05, |
| "loss": 2.5431, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.1909229762164521, |
| "grad_norm": 4.08992338180542, |
| "learning_rate": 1.890120375807399e-05, |
| "loss": 2.5359, |
| "step": 3500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 54996, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1833, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 957896589312000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
