camelbert-msa-zaebuc-ged-13 / trainer_state.json
balhafni's picture
Uploading model
e83d149
raw
history blame
1.46 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.246376811594203,
"global_step": 4500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.81,
"learning_rate": 4.597423510466989e-05,
"loss": 0.2451,
"step": 500
},
{
"epoch": 1.61,
"learning_rate": 4.194847020933977e-05,
"loss": 0.1689,
"step": 1000
},
{
"epoch": 2.42,
"learning_rate": 3.7922705314009665e-05,
"loss": 0.1414,
"step": 1500
},
{
"epoch": 3.22,
"learning_rate": 3.389694041867955e-05,
"loss": 0.1189,
"step": 2000
},
{
"epoch": 4.03,
"learning_rate": 2.9871175523349438e-05,
"loss": 0.0985,
"step": 2500
},
{
"epoch": 4.83,
"learning_rate": 2.5845410628019323e-05,
"loss": 0.0748,
"step": 3000
},
{
"epoch": 5.64,
"learning_rate": 2.1819645732689212e-05,
"loss": 0.0597,
"step": 3500
},
{
"epoch": 6.44,
"learning_rate": 1.77938808373591e-05,
"loss": 0.0492,
"step": 4000
},
{
"epoch": 7.25,
"learning_rate": 1.3768115942028985e-05,
"loss": 0.0405,
"step": 4500
}
],
"max_steps": 6210,
"num_train_epochs": 10,
"total_flos": 1.1638379847364272e+16,
"trial_name": null,
"trial_params": null
}