|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.03276774834369272, |
|
"global_step": 400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 1.4445, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 1.4332, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 3e-06, |
|
"loss": 1.4346, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 1.4213, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5e-06, |
|
"loss": 1.4162, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 6e-06, |
|
"loss": 1.4093, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.000000000000001e-06, |
|
"loss": 1.4005, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 1.405, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 9e-06, |
|
"loss": 1.4112, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1e-05, |
|
"loss": 1.4123, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.1000000000000001e-05, |
|
"loss": 1.4037, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.2e-05, |
|
"loss": 1.402, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.3000000000000001e-05, |
|
"loss": 1.3856, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 1.392, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.5e-05, |
|
"loss": 1.3968, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 1.393, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.7000000000000003e-05, |
|
"loss": 1.3897, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.8e-05, |
|
"loss": 1.388, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9e-05, |
|
"loss": 1.3885, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2e-05, |
|
"loss": 1.3883, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.1e-05, |
|
"loss": 1.39, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 1.383, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.3000000000000003e-05, |
|
"loss": 1.3845, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.4e-05, |
|
"loss": 1.3911, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.5e-05, |
|
"loss": 1.3943, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 1.3948, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.7000000000000002e-05, |
|
"loss": 1.3793, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 1.3741, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.9e-05, |
|
"loss": 1.3827, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3e-05, |
|
"loss": 1.3754, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.1e-05, |
|
"loss": 1.3793, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 1.3758, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.3e-05, |
|
"loss": 1.38, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 1.3739, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.5e-05, |
|
"loss": 1.3756, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.6e-05, |
|
"loss": 1.3786, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.7e-05, |
|
"loss": 1.3792, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.8e-05, |
|
"loss": 1.3749, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.9000000000000006e-05, |
|
"loss": 1.3622, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4e-05, |
|
"loss": 1.3694, |
|
"step": 400 |
|
} |
|
], |
|
"max_steps": 24414, |
|
"num_train_epochs": 2, |
|
"total_flos": 5.4042430537728e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|