heruberuto's picture
models done
f829f49
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.478566858605246,
"global_step": 7000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.32,
"learning_rate": 1.872040946896993e-05,
"loss": 0.3165,
"step": 500
},
{
"epoch": 0.64,
"learning_rate": 1.744081893793986e-05,
"loss": 0.2508,
"step": 1000
},
{
"epoch": 0.96,
"learning_rate": 1.616122840690979e-05,
"loss": 0.2268,
"step": 1500
},
{
"epoch": 1.28,
"learning_rate": 1.488163787587972e-05,
"loss": 0.1718,
"step": 2000
},
{
"epoch": 1.6,
"learning_rate": 1.3602047344849649e-05,
"loss": 0.1513,
"step": 2500
},
{
"epoch": 1.92,
"learning_rate": 1.2322456813819578e-05,
"loss": 0.156,
"step": 3000
},
{
"epoch": 2.24,
"learning_rate": 1.1042866282789508e-05,
"loss": 0.0976,
"step": 3500
},
{
"epoch": 2.56,
"learning_rate": 9.763275751759437e-06,
"loss": 0.0879,
"step": 4000
},
{
"epoch": 2.88,
"learning_rate": 8.483685220729368e-06,
"loss": 0.0924,
"step": 4500
},
{
"epoch": 3.2,
"learning_rate": 7.204094689699297e-06,
"loss": 0.065,
"step": 5000
},
{
"epoch": 3.52,
"learning_rate": 5.924504158669226e-06,
"loss": 0.0453,
"step": 5500
},
{
"epoch": 3.84,
"learning_rate": 4.644913627639156e-06,
"loss": 0.0432,
"step": 6000
},
{
"epoch": 4.16,
"learning_rate": 3.3653230966090854e-06,
"loss": 0.031,
"step": 6500
},
{
"epoch": 4.48,
"learning_rate": 2.085732565579015e-06,
"loss": 0.0297,
"step": 7000
}
],
"max_steps": 7815,
"num_train_epochs": 5,
"total_flos": 1.46890304135448e+16,
"trial_name": null,
"trial_params": null
}