|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 2500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 8.0806, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.8060000000000004e-05, |
|
"loss": 1.2685, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.606e-05, |
|
"loss": 0.7447, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.4080000000000005e-05, |
|
"loss": 0.6506, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.2080000000000004e-05, |
|
"loss": 0.7171, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.008e-05, |
|
"loss": 0.5667, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 3.808e-05, |
|
"loss": 0.5265, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.608e-05, |
|
"loss": 0.4884, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.408e-05, |
|
"loss": 0.4605, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.208e-05, |
|
"loss": 0.3832, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.01e-05, |
|
"loss": 0.385, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 2.8100000000000005e-05, |
|
"loss": 0.3362, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.61e-05, |
|
"loss": 0.2882, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.41e-05, |
|
"loss": 0.2704, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.2100000000000002e-05, |
|
"loss": 0.2177, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.01e-05, |
|
"loss": 0.2197, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 1.81e-05, |
|
"loss": 0.1808, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1.6100000000000002e-05, |
|
"loss": 0.1755, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.4099999999999999e-05, |
|
"loss": 0.1549, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 1.2100000000000001e-05, |
|
"loss": 0.1254, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.0100000000000002e-05, |
|
"loss": 0.1057, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.1e-06, |
|
"loss": 0.1035, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 6.1e-06, |
|
"loss": 0.0938, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 4.1000000000000006e-06, |
|
"loss": 0.0882, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 2.1000000000000002e-06, |
|
"loss": 0.0721, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.0000000000000001e-07, |
|
"loss": 0.0627, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 2500, |
|
"total_flos": 1.496570381991936e+19, |
|
"train_loss": 0.3501619976043701, |
|
"train_runtime": 17883.0624, |
|
"train_samples_per_second": 1.118, |
|
"train_steps_per_second": 0.14 |
|
} |
|
], |
|
"max_steps": 2500, |
|
"num_train_epochs": 1, |
|
"total_flos": 1.496570381991936e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|