|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.6206896551724138, |
|
"eval_steps": 500, |
|
"global_step": 126, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.9998802517966852e-05, |
|
"loss": 2.4397, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.997007728639956e-05, |
|
"loss": 2.4187, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9880488219356086e-05, |
|
"loss": 2.4229, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.973176894846855e-05, |
|
"loss": 2.3977, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.9524809490566878e-05, |
|
"loss": 2.3913, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.926084840336821e-05, |
|
"loss": 2.3677, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1.894146537327533e-05, |
|
"loss": 2.3463, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.8568571761675893e-05, |
|
"loss": 2.3193, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.814439916631857e-05, |
|
"loss": 2.3087, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.7671486066220965e-05, |
|
"loss": 2.2779, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.7152662630033506e-05, |
|
"loss": 2.2744, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 1.659103377877423e-05, |
|
"loss": 2.24, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.598996060429634e-05, |
|
"loss": 2.2244, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.5353040254690396e-05, |
|
"loss": 2.2106, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.4684084406997903e-05, |
|
"loss": 2.1877, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.3987096456067236e-05, |
|
"loss": 2.1695, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.3266247556066122e-05, |
|
"loss": 2.1692, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.252585165803135e-05, |
|
"loss": 2.1628, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.1770339692844484e-05, |
|
"loss": 2.1589, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.1004233054136726e-05, |
|
"loss": 2.1428, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.0232116539815558e-05, |
|
"loss": 2.1529, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.458610914145826e-06, |
|
"loss": 2.1368, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 8.688345254588579e-06, |
|
"loss": 2.1302, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 7.92592924888925e-06, |
|
"loss": 2.1387, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 7.175925608204428e-06, |
|
"loss": 2.126, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 6.442822761362015e-06, |
|
"loss": 2.1248, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"eval_loss": 2.0764729976654053, |
|
"eval_runtime": 586.1695, |
|
"eval_samples_per_second": 39.425, |
|
"eval_steps_per_second": 2.465, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"step": 126, |
|
"total_flos": 4.961968235772641e+17, |
|
"train_loss": 2.2405008626362632, |
|
"train_runtime": 21947.0981, |
|
"train_samples_per_second": 9.471, |
|
"train_steps_per_second": 0.009 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 203, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 4.961968235772641e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|