concept2seq / trainer_state.json
kevincstowe's picture
updating checkpoint
a84c02e
raw
history blame
3.53 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.884402041269137,
"global_step": 13000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.11,
"learning_rate": 4.8890614599511876e-05,
"loss": 1.2035,
"step": 500
},
{
"epoch": 0.22,
"learning_rate": 4.778122919902374e-05,
"loss": 0.4941,
"step": 1000
},
{
"epoch": 0.33,
"learning_rate": 4.6671843798535615e-05,
"loss": 0.4122,
"step": 1500
},
{
"epoch": 0.44,
"learning_rate": 4.556245839804749e-05,
"loss": 0.3654,
"step": 2000
},
{
"epoch": 0.55,
"learning_rate": 4.4453072997559355e-05,
"loss": 0.3352,
"step": 2500
},
{
"epoch": 0.67,
"learning_rate": 4.334368759707123e-05,
"loss": 0.3101,
"step": 3000
},
{
"epoch": 0.78,
"learning_rate": 4.2234302196583095e-05,
"loss": 0.2922,
"step": 3500
},
{
"epoch": 0.89,
"learning_rate": 4.112491679609496e-05,
"loss": 0.2778,
"step": 4000
},
{
"epoch": 1.0,
"learning_rate": 4.0015531395606834e-05,
"loss": 0.2674,
"step": 4500
},
{
"epoch": 1.11,
"learning_rate": 3.89061459951187e-05,
"loss": 0.2421,
"step": 5000
},
{
"epoch": 1.22,
"learning_rate": 3.7796760594630574e-05,
"loss": 0.2353,
"step": 5500
},
{
"epoch": 1.33,
"learning_rate": 3.668737519414245e-05,
"loss": 0.2299,
"step": 6000
},
{
"epoch": 1.44,
"learning_rate": 3.5577989793654314e-05,
"loss": 0.2231,
"step": 6500
},
{
"epoch": 1.55,
"learning_rate": 3.446860439316619e-05,
"loss": 0.2186,
"step": 7000
},
{
"epoch": 1.66,
"learning_rate": 3.335921899267806e-05,
"loss": 0.2128,
"step": 7500
},
{
"epoch": 1.78,
"learning_rate": 3.224983359218993e-05,
"loss": 0.2068,
"step": 8000
},
{
"epoch": 1.89,
"learning_rate": 3.11404481917018e-05,
"loss": 0.203,
"step": 8500
},
{
"epoch": 2.0,
"learning_rate": 3.003106279121367e-05,
"loss": 0.2002,
"step": 9000
},
{
"epoch": 2.11,
"learning_rate": 2.8921677390725536e-05,
"loss": 0.1852,
"step": 9500
},
{
"epoch": 2.22,
"learning_rate": 2.781229199023741e-05,
"loss": 0.182,
"step": 10000
},
{
"epoch": 2.33,
"learning_rate": 2.6702906589749283e-05,
"loss": 0.1842,
"step": 10500
},
{
"epoch": 2.44,
"learning_rate": 2.559352118926115e-05,
"loss": 0.1801,
"step": 11000
},
{
"epoch": 2.55,
"learning_rate": 2.4484135788773022e-05,
"loss": 0.1764,
"step": 11500
},
{
"epoch": 2.66,
"learning_rate": 2.3374750388284892e-05,
"loss": 0.1772,
"step": 12000
},
{
"epoch": 2.77,
"learning_rate": 2.2265364987796762e-05,
"loss": 0.1731,
"step": 12500
},
{
"epoch": 2.88,
"learning_rate": 2.1155979587308632e-05,
"loss": 0.1711,
"step": 13000
}
],
"max_steps": 22535,
"num_train_epochs": 5,
"total_flos": 3.170301849501696e+16,
"trial_name": null,
"trial_params": null
}