| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1119664100769768, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11196641007697691, |
| "grad_norm": 33.81226137131406, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.7358, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22393282015395383, |
| "grad_norm": 3.126971357941473, |
| "learning_rate": 8.444444444444446e-06, |
| "loss": 0.527, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3358992302309307, |
| "grad_norm": 1.6515920436614058, |
| "learning_rate": 1.288888888888889e-05, |
| "loss": 0.3884, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.44786564030790765, |
| "grad_norm": 0.9474838344715308, |
| "learning_rate": 1.7333333333333336e-05, |
| "loss": 0.3406, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5598320503848845, |
| "grad_norm": 5.128129734480829, |
| "learning_rate": 1.9995186678809513e-05, |
| "loss": 0.311, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6717984604618614, |
| "grad_norm": 1.6245368590343587, |
| "learning_rate": 1.9941090015469614e-05, |
| "loss": 0.2988, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7837648705388384, |
| "grad_norm": 1.611763809071587, |
| "learning_rate": 1.9827206467064133e-05, |
| "loss": 0.2809, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8957312806158153, |
| "grad_norm": 1.668412741711298, |
| "learning_rate": 1.9654220942653223e-05, |
| "loss": 0.2657, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.1431570423104263, |
| "learning_rate": 1.9423173797534924e-05, |
| "loss": 0.2516, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.1119664100769768, |
| "grad_norm": 1.484525869599161, |
| "learning_rate": 1.913545457642601e-05, |
| "loss": 0.2454, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1119664100769768, |
| "eval_loss": 0.22891120612621307, |
| "eval_runtime": 286.3307, |
| "eval_samples_per_second": 12.611, |
| "eval_steps_per_second": 3.154, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 450, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 264469242445824.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
