|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9707112970711297, |
|
"eval_steps": 500, |
|
"global_step": 29, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.6666666666666665e-07, |
|
"logits/chosen": -2.787102699279785, |
|
"logits/rejected": -2.7550511360168457, |
|
"logps/chosen": -276.68115234375, |
|
"logps/rejected": -251.47610473632812, |
|
"loss": 0.6931, |
|
"rewards/accuracies": 0.0, |
|
"rewards/chosen": 0.0, |
|
"rewards/margins": 0.0, |
|
"rewards/rejected": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.157806645601988e-07, |
|
"logits/chosen": -2.7923507690429688, |
|
"logits/rejected": -2.788248062133789, |
|
"logps/chosen": -273.4093017578125, |
|
"logps/rejected": -256.6051330566406, |
|
"loss": 0.6892, |
|
"rewards/accuracies": 0.53125, |
|
"rewards/chosen": 0.009637600742280483, |
|
"rewards/margins": 0.007923546247184277, |
|
"rewards/rejected": 0.0017140543786808848, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.3381920698905784e-07, |
|
"logits/chosen": -2.801476001739502, |
|
"logits/rejected": -2.796142101287842, |
|
"logps/chosen": -271.7885437011719, |
|
"logps/rejected": -238.5182647705078, |
|
"loss": 0.669, |
|
"rewards/accuracies": 0.6796875, |
|
"rewards/chosen": 0.03407515212893486, |
|
"rewards/margins": 0.058315712958574295, |
|
"rewards/rejected": -0.024240557104349136, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"step": 29, |
|
"total_flos": 0.0, |
|
"train_loss": 0.6742583143300024, |
|
"train_runtime": 1883.6921, |
|
"train_samples_per_second": 8.113, |
|
"train_steps_per_second": 0.015 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 29, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 0.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|