|
{ |
|
"best_metric": 1.0276169776916504, |
|
"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": 1.0608, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.0753934383392334, |
|
"eval_runtime": 354.351, |
|
"eval_samples_per_second": 5.447, |
|
"eval_steps_per_second": 0.683, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9182, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.05315363407135, |
|
"eval_runtime": 352.7918, |
|
"eval_samples_per_second": 5.471, |
|
"eval_steps_per_second": 0.686, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9037, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.0414820909500122, |
|
"eval_runtime": 353.1451, |
|
"eval_samples_per_second": 5.465, |
|
"eval_steps_per_second": 0.685, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8943, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.0332194566726685, |
|
"eval_runtime": 353.4062, |
|
"eval_samples_per_second": 5.461, |
|
"eval_steps_per_second": 0.685, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8814, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.0276169776916504, |
|
"eval_runtime": 353.0472, |
|
"eval_samples_per_second": 5.467, |
|
"eval_steps_per_second": 0.685, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.4137479027061555e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|