|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.984, |
|
"global_step": 62, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 2.5e-05, |
|
"loss": 2.4811, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 5e-05, |
|
"loss": 2.7677, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 2.8184, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001, |
|
"loss": 2.7164, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.992667069255619e-05, |
|
"loss": 2.6905, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 9.970689785771798e-05, |
|
"loss": 2.4758, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 9.934132612707632e-05, |
|
"loss": 2.1961, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 9.883102778550434e-05, |
|
"loss": 2.1084, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 9.817749962596115e-05, |
|
"loss": 1.9172, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 9.738265855914013e-05, |
|
"loss": 1.7626, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.644883599083958e-05, |
|
"loss": 1.6495, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.537877098354786e-05, |
|
"loss": 1.3566, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 9.417560222230115e-05, |
|
"loss": 1.2721, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_loss": 1.381595492362976, |
|
"eval_runtime": 1.4441, |
|
"eval_samples_per_second": 34.623, |
|
"eval_steps_per_second": 4.847, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.284285880837946e-05, |
|
"loss": 1.1247, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 9.138444990784453e-05, |
|
"loss": 1.3827, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 8.980465328528219e-05, |
|
"loss": 1.4877, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 8.810810275638183e-05, |
|
"loss": 1.4821, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.629977459615655e-05, |
|
"loss": 1.3786, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 8.438497294267117e-05, |
|
"loss": 1.2494, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 8.236931423909138e-05, |
|
"loss": 1.1829, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 8.025871075968828e-05, |
|
"loss": 1.0193, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 7.805935326811912e-05, |
|
"loss": 1.4785, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 7.577769285885109e-05, |
|
"loss": 1.4004, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 7.342042203498951e-05, |
|
"loss": 1.3328, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 7.099445507801323e-05, |
|
"loss": 1.2686, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 6.850690776699573e-05, |
|
"loss": 1.0142, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 1.1247260570526123, |
|
"eval_runtime": 1.4412, |
|
"eval_samples_per_second": 34.693, |
|
"eval_steps_per_second": 4.857, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 6.5965076506799e-05, |
|
"loss": 0.9446, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 6.337641692646106e-05, |
|
"loss": 0.8311, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 6.0748522010551215e-05, |
|
"loss": 1.3538, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 5.808909982763825e-05, |
|
"loss": 1.1263, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 5.540595092119709e-05, |
|
"loss": 0.9153, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 5.270694542927088e-05, |
|
"loss": 0.9691, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 5e-05, |
|
"loss": 1.377, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.729305457072913e-05, |
|
"loss": 1.242, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.4594049078802925e-05, |
|
"loss": 1.2525, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 4.1910900172361764e-05, |
|
"loss": 1.0716, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 3.92514779894488e-05, |
|
"loss": 0.9491, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 3.6623583073538966e-05, |
|
"loss": 0.7949, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 3.403492349320101e-05, |
|
"loss": 1.1087, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 1.0872222185134888, |
|
"eval_runtime": 1.4388, |
|
"eval_samples_per_second": 34.752, |
|
"eval_steps_per_second": 4.865, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.149309223300428e-05, |
|
"loss": 1.3412, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 2.900554492198677e-05, |
|
"loss": 1.1742, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 2.65795779650105e-05, |
|
"loss": 1.0373, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 2.422230714114891e-05, |
|
"loss": 1.0752, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 2.194064673188089e-05, |
|
"loss": 0.8705, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.9741289240311755e-05, |
|
"loss": 0.8475, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.7630685760908622e-05, |
|
"loss": 1.2784, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 1.561502705732883e-05, |
|
"loss": 1.4262, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 1.3700225403843469e-05, |
|
"loss": 1.1989, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 1.1891897243618182e-05, |
|
"loss": 1.0853, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.0195346714717813e-05, |
|
"loss": 0.8383, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 8.615550092155478e-06, |
|
"loss": 0.9405, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 7.157141191620548e-06, |
|
"loss": 0.837, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"eval_loss": 1.077386736869812, |
|
"eval_runtime": 1.4402, |
|
"eval_samples_per_second": 34.716, |
|
"eval_steps_per_second": 4.86, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 5.824397777698859e-06, |
|
"loss": 1.1777, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.621229016452156e-06, |
|
"loss": 1.2908, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 3.551164009160429e-06, |
|
"loss": 1.2032, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 2.6173414408598827e-06, |
|
"loss": 1.0568, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 1.8225003740388547e-06, |
|
"loss": 1.029, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 1.1689722144956671e-06, |
|
"loss": 1.0957, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 6.58673872923693e-07, |
|
"loss": 0.7948, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 2.9310214228202013e-07, |
|
"loss": 1.1412, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 7.332930744380906e-08, |
|
"loss": 1.3215, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.0, |
|
"loss": 1.0566, |
|
"step": 62 |
|
} |
|
], |
|
"max_steps": 62, |
|
"num_train_epochs": 2, |
|
"total_flos": 1589370366787584.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|