|
{ |
|
"best_metric": 1.2884504795074463, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.6666666666666666, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 1.4919, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.361365795135498, |
|
"eval_runtime": 127.054, |
|
"eval_samples_per_second": 15.19, |
|
"eval_steps_per_second": 1.905, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1628, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.319554328918457, |
|
"eval_runtime": 126.2625, |
|
"eval_samples_per_second": 15.286, |
|
"eval_steps_per_second": 1.917, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1376, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.3056749105453491, |
|
"eval_runtime": 126.1549, |
|
"eval_samples_per_second": 15.299, |
|
"eval_steps_per_second": 1.918, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1257, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.2944581508636475, |
|
"eval_runtime": 126.2031, |
|
"eval_samples_per_second": 15.293, |
|
"eval_steps_per_second": 1.918, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1123, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.2884504795074463, |
|
"eval_runtime": 126.384, |
|
"eval_samples_per_second": 15.271, |
|
"eval_steps_per_second": 1.915, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.7727133699817472e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|