73 lines
1.7 KiB
JSON
73 lines
1.7 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.004,
|
|
"eval_steps": 500,
|
|
"global_step": 3,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"completion_length": 120.6875,
|
|
"epoch": 0.0013333333333333333,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 3.75e-07,
|
|
"loss": 0.0,
|
|
"reward": 0.0,
|
|
"reward_std": 0.0,
|
|
"rewards/equation_reward_func": 0.0,
|
|
"rewards/format_reward_func": 0.0,
|
|
"step": 1
|
|
},
|
|
{
|
|
"completion_length": 129.5625,
|
|
"epoch": 0.0026666666666666666,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 1.2500000000000005e-07,
|
|
"loss": 0.0,
|
|
"reward": 0.0,
|
|
"reward_std": 0.0,
|
|
"rewards/equation_reward_func": 0.0,
|
|
"rewards/format_reward_func": 0.0,
|
|
"step": 2
|
|
},
|
|
{
|
|
"completion_length": 123.875,
|
|
"epoch": 0.004,
|
|
"grad_norm": 0.0,
|
|
"kl": 0.0,
|
|
"learning_rate": 0.0,
|
|
"loss": 0.0,
|
|
"reward": 0.0,
|
|
"reward_std": 0.0,
|
|
"rewards/equation_reward_func": 0.0,
|
|
"rewards/format_reward_func": 0.0,
|
|
"step": 3
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 3,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 250,
|
|
"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": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|