|
{ |
|
"best_metric": 1.2735565900802612, |
|
"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": 1.2694, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.3544635772705078, |
|
"eval_runtime": 457.1536, |
|
"eval_samples_per_second": 4.222, |
|
"eval_steps_per_second": 0.529, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 1.105, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.319144368171692, |
|
"eval_runtime": 457.9804, |
|
"eval_samples_per_second": 4.214, |
|
"eval_steps_per_second": 0.528, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0849, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.299824833869934, |
|
"eval_runtime": 460.2328, |
|
"eval_samples_per_second": 4.194, |
|
"eval_steps_per_second": 0.526, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0697, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.2875007390975952, |
|
"eval_runtime": 456.2021, |
|
"eval_samples_per_second": 4.231, |
|
"eval_steps_per_second": 0.53, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0562, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.2735565900802612, |
|
"eval_runtime": 461.3936, |
|
"eval_samples_per_second": 4.183, |
|
"eval_steps_per_second": 0.524, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.6636259895410688e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|