|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 18984, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.868573535608934e-05, |
|
"loss": 3.0005, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.736883691529709e-05, |
|
"loss": 2.2882, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.6051938474504844e-05, |
|
"loss": 2.0436, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.473767383059418e-05, |
|
"loss": 1.8905, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.342077538980194e-05, |
|
"loss": 1.7659, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.210387694900969e-05, |
|
"loss": 1.7129, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.078697850821745e-05, |
|
"loss": 1.6088, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 3.9470080067425204e-05, |
|
"loss": 1.5347, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 3.8153181626632956e-05, |
|
"loss": 1.5119, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 3.683628318584071e-05, |
|
"loss": 1.4421, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 3.551938474504846e-05, |
|
"loss": 1.4284, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 3.420248630425621e-05, |
|
"loss": 1.3803, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 3.2888221660345556e-05, |
|
"loss": 1.3363, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 3.1573957016434894e-05, |
|
"loss": 1.1398, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 3.025705857564265e-05, |
|
"loss": 1.1177, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 2.89401601348504e-05, |
|
"loss": 1.1345, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 2.7623261694058157e-05, |
|
"loss": 1.0919, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 2.630636325326591e-05, |
|
"loss": 1.0813, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 2.498946481247366e-05, |
|
"loss": 1.0593, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 2.3672566371681416e-05, |
|
"loss": 1.0509, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 2.235566793088917e-05, |
|
"loss": 1.0613, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 2.1038769490096924e-05, |
|
"loss": 1.0285, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 1.972187104930468e-05, |
|
"loss": 1.0115, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 1.8404972608512434e-05, |
|
"loss": 0.9924, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 1.7090707964601772e-05, |
|
"loss": 0.9593, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 1.5773809523809524e-05, |
|
"loss": 0.8149, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 1.4456911083017278e-05, |
|
"loss": 0.7528, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 1.3142646439106617e-05, |
|
"loss": 0.7545, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 1.1825747998314371e-05, |
|
"loss": 0.7447, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 1.0511483354403709e-05, |
|
"loss": 0.73, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 9.194584913611463e-06, |
|
"loss": 0.7448, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 7.877686472819216e-06, |
|
"loss": 0.733, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 6.560788032026971e-06, |
|
"loss": 0.731, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 5.243889591234724e-06, |
|
"loss": 0.7339, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 3.926991150442478e-06, |
|
"loss": 0.7282, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 2.6100927096502315e-06, |
|
"loss": 0.7143, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 1.2931942688579856e-06, |
|
"loss": 0.6983, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 18984, |
|
"total_flos": 8111946579836928.0, |
|
"train_loss": 1.1911298154629186, |
|
"train_runtime": 9696.9033, |
|
"train_samples_per_second": 15.66, |
|
"train_steps_per_second": 1.958 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 18984, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 8111946579836928.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|