| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6040471156750227, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15101177891875567, |
| "grad_norm": 0.6998376846313477, |
| "learning_rate": 8.49290244639082e-05, |
| "loss": 0.9724, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.30202355783751134, |
| "grad_norm": 0.6855610013008118, |
| "learning_rate": 6.982784657203262e-05, |
| "loss": 0.9085, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.453035336756267, |
| "grad_norm": 0.7765684723854065, |
| "learning_rate": 5.472666868015705e-05, |
| "loss": 0.9008, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6040471156750227, |
| "grad_norm": 0.7931118011474609, |
| "learning_rate": 3.962549078828149e-05, |
| "loss": 0.8844, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3311, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.228444112144302e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
