|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.3333333333333333, |
|
"eval_steps": 500, |
|
"global_step": 150, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08888888888888889, |
|
"grad_norm": 29.641796112060547, |
|
"learning_rate": 2.9411764705882354e-05, |
|
"loss": 1.3387, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.17777777777777778, |
|
"grad_norm": 2.8391942977905273, |
|
"learning_rate": 5.882352941176471e-05, |
|
"loss": 1.4468, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.26666666666666666, |
|
"grad_norm": 2.4493441581726074, |
|
"learning_rate": 8.823529411764706e-05, |
|
"loss": 1.0612, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.35555555555555557, |
|
"grad_norm": 2.3891420364379883, |
|
"learning_rate": 9.990263847374976e-05, |
|
"loss": 1.0064, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4444444444444444, |
|
"grad_norm": 1.1571154594421387, |
|
"learning_rate": 9.930902394260747e-05, |
|
"loss": 0.9215, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5333333333333333, |
|
"grad_norm": 1.3602615594863892, |
|
"learning_rate": 9.818229479678158e-05, |
|
"loss": 1.2268, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.6222222222222222, |
|
"grad_norm": 1.3397140502929688, |
|
"learning_rate": 9.653463289927411e-05, |
|
"loss": 0.8976, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.7111111111111111, |
|
"grad_norm": 1.1149853467941284, |
|
"learning_rate": 9.438385228425938e-05, |
|
"loss": 0.8541, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.9571573734283447, |
|
"learning_rate": 9.175320655700406e-05, |
|
"loss": 0.8365, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 0.8198672533035278, |
|
"learning_rate": 8.86711374827494e-05, |
|
"loss": 0.8059, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9777777777777777, |
|
"grad_norm": 1.072033166885376, |
|
"learning_rate": 8.517096748273951e-05, |
|
"loss": 0.8329, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0666666666666667, |
|
"grad_norm": 0.9767541885375977, |
|
"learning_rate": 8.129053936203687e-05, |
|
"loss": 0.835, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.1555555555555554, |
|
"grad_norm": 1.8347275257110596, |
|
"learning_rate": 7.707180716428237e-05, |
|
"loss": 0.8222, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.2444444444444445, |
|
"grad_norm": 1.700829267501831, |
|
"learning_rate": 7.256038257695687e-05, |
|
"loss": 0.7214, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.3333333333333333, |
|
"grad_norm": 0.6811372637748718, |
|
"learning_rate": 6.780504179127734e-05, |
|
"loss": 0.7347, |
|
"step": 150 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 336, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4465855572830208.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|