|
{ |
|
"best_metric": 1.0277502536773682, |
|
"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": 1.0007, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.0926419496536255, |
|
"eval_runtime": 890.2071, |
|
"eval_samples_per_second": 2.168, |
|
"eval_steps_per_second": 0.272, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.897, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.0682977437973022, |
|
"eval_runtime": 890.4733, |
|
"eval_samples_per_second": 2.167, |
|
"eval_steps_per_second": 0.272, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8814, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.0527396202087402, |
|
"eval_runtime": 888.2495, |
|
"eval_samples_per_second": 2.173, |
|
"eval_steps_per_second": 0.272, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8697, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.039888620376587, |
|
"eval_runtime": 883.1791, |
|
"eval_samples_per_second": 2.185, |
|
"eval_steps_per_second": 0.274, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8552, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.0277502536773682, |
|
"eval_runtime": 724.238, |
|
"eval_samples_per_second": 2.665, |
|
"eval_steps_per_second": 0.334, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.2948397906255872e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|