80 lines
2.0 KiB
JSON
80 lines
2.0 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 500,
|
|
"global_step": 3,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 30.078697204589844,
|
|
"learning_rate": 0.0,
|
|
"logits/chosen": -3.45875883102417,
|
|
"logits/rejected": -3.423557996749878,
|
|
"logps/chosen": -848.84765625,
|
|
"logps/rejected": -816.5891723632812,
|
|
"loss": 0.6931,
|
|
"rewards/accuracies": 0.0,
|
|
"rewards/chosen": 0.0,
|
|
"rewards/margins": 0.0,
|
|
"rewards/rejected": 0.0,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 30.074949264526367,
|
|
"learning_rate": 2e-05,
|
|
"logits/chosen": -3.5248451232910156,
|
|
"logits/rejected": -3.506687879562378,
|
|
"logps/chosen": -848.84765625,
|
|
"logps/rejected": -816.5891723632812,
|
|
"loss": 0.6931,
|
|
"rewards/accuracies": 0.0,
|
|
"rewards/chosen": 0.0,
|
|
"rewards/margins": 0.0,
|
|
"rewards/rejected": 0.0,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"grad_norm": 18.459684371948242,
|
|
"learning_rate": 4e-05,
|
|
"logits/chosen": -3.505913257598877,
|
|
"logits/rejected": -3.469709873199463,
|
|
"logps/chosen": -845.7001953125,
|
|
"logps/rejected": -820.7750854492188,
|
|
"loss": 0.415,
|
|
"rewards/accuracies": 1.0,
|
|
"rewards/chosen": 0.3147410452365875,
|
|
"rewards/margins": 0.7333309650421143,
|
|
"rewards/rejected": -0.41858991980552673,
|
|
"step": 3
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 3,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 5000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 0.0,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|