|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"global_step": 1196, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 2.874581939799331e-05, |
|
"loss": 1.1476, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 2.7491638795986622e-05, |
|
"loss": 0.9973, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.6237458193979933e-05, |
|
"loss": 1.0316, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 2.4983277591973243e-05, |
|
"loss": 0.9801, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 2.3729096989966557e-05, |
|
"loss": 0.9947, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 2.2474916387959865e-05, |
|
"loss": 0.9882, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 2.122073578595318e-05, |
|
"loss": 0.8896, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 1.996655518394649e-05, |
|
"loss": 0.7913, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 1.87123745819398e-05, |
|
"loss": 0.8249, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 1.745819397993311e-05, |
|
"loss": 0.7808, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 1.620401337792642e-05, |
|
"loss": 0.7632, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 1.4949832775919733e-05, |
|
"loss": 0.7577, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 1.3695652173913042e-05, |
|
"loss": 0.6454, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 1.2441471571906355e-05, |
|
"loss": 0.5908, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 1.1187290969899665e-05, |
|
"loss": 0.6114, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 9.933110367892978e-06, |
|
"loss": 0.6383, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 8.678929765886286e-06, |
|
"loss": 0.6207, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 7.424749163879599e-06, |
|
"loss": 0.5649, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 6.17056856187291e-06, |
|
"loss": 0.4894, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 4.916387959866221e-06, |
|
"loss": 0.4434, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 3.662207357859532e-06, |
|
"loss": 0.3991, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 2.408026755852843e-06, |
|
"loss": 0.4938, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 1.153846153846154e-06, |
|
"loss": 0.3628, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"step": 1196, |
|
"total_flos": 2517491783958528.0, |
|
"train_loss": 0.7212204247414069, |
|
"train_runtime": 362.6132, |
|
"train_samples_per_second": 26.386, |
|
"train_steps_per_second": 3.298 |
|
} |
|
], |
|
"max_steps": 1196, |
|
"num_train_epochs": 4, |
|
"total_flos": 2517491783958528.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|