|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 16851, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.955492255652484e-05, |
|
"loss": 2.8362, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9109845113049673e-05, |
|
"loss": 1.6844, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.8664767669574508e-05, |
|
"loss": 1.5, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.8219690226099342e-05, |
|
"loss": 1.3599, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.777461278262418e-05, |
|
"loss": 1.2865, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.7329535339149014e-05, |
|
"loss": 1.2309, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1.6884457895673848e-05, |
|
"loss": 1.219, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.6439380452198682e-05, |
|
"loss": 1.1917, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.599430300872352e-05, |
|
"loss": 1.1278, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.5549225565248354e-05, |
|
"loss": 1.1211, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.510414812177319e-05, |
|
"loss": 1.098, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_exact_match": 77.43614001892148, |
|
"eval_f1": 85.27628850491176, |
|
"step": 5617 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.4659070678298024e-05, |
|
"loss": 0.9305, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 1.421399323482286e-05, |
|
"loss": 0.8982, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.3768915791347694e-05, |
|
"loss": 0.8622, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.332383834787253e-05, |
|
"loss": 0.8733, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.2878760904397368e-05, |
|
"loss": 0.858, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 1.2433683460922202e-05, |
|
"loss": 0.8723, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.1988606017447038e-05, |
|
"loss": 0.8781, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 1.1543528573971872e-05, |
|
"loss": 0.8645, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 1.1098451130496708e-05, |
|
"loss": 0.8643, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 1.0653373687021542e-05, |
|
"loss": 0.8594, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.0208296243546378e-05, |
|
"loss": 0.8501, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_exact_match": 79.43235572374645, |
|
"eval_f1": 86.5587922621179, |
|
"step": 11234 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 9.763218800071214e-06, |
|
"loss": 0.7317, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 9.318141356596048e-06, |
|
"loss": 0.6347, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 8.873063913120884e-06, |
|
"loss": 0.6572, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 8.42798646964572e-06, |
|
"loss": 0.6525, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 7.982909026170554e-06, |
|
"loss": 0.6543, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 7.53783158269539e-06, |
|
"loss": 0.6496, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 7.092754139220225e-06, |
|
"loss": 0.6533, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 6.64767669574506e-06, |
|
"loss": 0.652, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 6.202599252269895e-06, |
|
"loss": 0.6363, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 5.75752180879473e-06, |
|
"loss": 0.6802, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 5.312444365319565e-06, |
|
"loss": 0.6562, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_exact_match": 79.61210974456007, |
|
"eval_f1": 87.30118518584376, |
|
"step": 16851 |
|
} |
|
], |
|
"max_steps": 22468, |
|
"num_train_epochs": 4, |
|
"total_flos": 5.28373385307095e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|