|
{ |
|
"best_metric": 1.699326515197754, |
|
"best_model_checkpoint": "output/pharaoh/checkpoint-200", |
|
"epoch": 1.0, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001369885290940926, |
|
"loss": 2.5312, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00013635542016482644, |
|
"loss": 2.1558, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0001353045765392806, |
|
"loss": 2.1677, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00013384247701784754, |
|
"loss": 2.0874, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00013197813593027427, |
|
"loss": 2.0224, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00012972304755932203, |
|
"loss": 1.9402, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00012709111527469072, |
|
"loss": 2.113, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001240985658141214, |
|
"loss": 2.0482, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00012076384924016213, |
|
"loss": 1.843, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00011710752518939715, |
|
"loss": 2.0109, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00011315213611545058, |
|
"loss": 1.9608, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00010892206830726365, |
|
"loss": 2.053, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00010444340153951408, |
|
"loss": 1.9682, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.974374828213291e-05, |
|
"loss": 1.9954, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.485208346024516e-05, |
|
"loss": 1.9485, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 8.97985658141214e-05, |
|
"loss": 1.8621, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 8.461435196051512e-05, |
|
"loss": 1.9375, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 7.933140430175984e-05, |
|
"loss": 1.8682, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 7.398229396693017e-05, |
|
"loss": 1.9141, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 6.86e-05, |
|
"loss": 1.8811, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 6.321770603306985e-05, |
|
"loss": 1.9623, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 5.786859569824015e-05, |
|
"loss": 1.8849, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 5.258564803948491e-05, |
|
"loss": 1.891, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.740143418587861e-05, |
|
"loss": 1.7659, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.2347916539754844e-05, |
|
"loss": 1.8337, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 3.745625171786709e-05, |
|
"loss": 1.8855, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 3.275659846048591e-05, |
|
"loss": 1.8395, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 2.8277931692736352e-05, |
|
"loss": 1.8782, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 2.4047863884549408e-05, |
|
"loss": 1.8944, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 2.0092474810602843e-05, |
|
"loss": 1.913, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.6436150759837878e-05, |
|
"loss": 1.7538, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.3101434185878613e-05, |
|
"loss": 1.9117, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.0108884725309277e-05, |
|
"loss": 1.8817, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 7.476952440677969e-06, |
|
"loss": 1.8265, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 5.22186406972573e-06, |
|
"loss": 1.7538, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 3.357522982152468e-06, |
|
"loss": 1.7725, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.8954234607193881e-06, |
|
"loss": 1.8434, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 8.445798351735566e-07, |
|
"loss": 1.7535, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 2.1147090590742169e-07, |
|
"loss": 1.8311, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.862, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.699326515197754, |
|
"eval_runtime": 10.3078, |
|
"eval_samples_per_second": 22.992, |
|
"eval_steps_per_second": 2.91, |
|
"step": 200 |
|
} |
|
], |
|
"max_steps": 200, |
|
"num_train_epochs": 1, |
|
"total_flos": 208772333568000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|