| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.37991034115948635, |
| "eval_steps": 500, |
| "global_step": 5000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07598206823189728, |
| "grad_norm": 0.30169111490249634, |
| "learning_rate": 0.0004210970464135021, |
| "loss": 1.6575, |
| "mean_token_accuracy": 0.59712015157938, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.15196413646379456, |
| "grad_norm": 0.33283600211143494, |
| "learning_rate": 0.0004994442522809609, |
| "loss": 1.538, |
| "mean_token_accuracy": 0.6154271116852761, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.22794620469569182, |
| "grad_norm": 0.3912029564380646, |
| "learning_rate": 0.0004972403591996743, |
| "loss": 1.4976, |
| "mean_token_accuracy": 0.623363886743784, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.3039282729275891, |
| "grad_norm": 0.3285040557384491, |
| "learning_rate": 0.0004933737298151819, |
| "loss": 1.5005, |
| "mean_token_accuracy": 0.6219179545640945, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.37991034115948635, |
| "grad_norm": 0.3439396619796753, |
| "learning_rate": 0.00048787036791209814, |
| "loss": 1.4646, |
| "mean_token_accuracy": 0.6277292569875718, |
| "step": 5000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 39483, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.577883446244147e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
