microsoft_deberta-large_squad / trainer_state.json
Palak Goenka
add files
1f8912e
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.897018970189702,
"global_step": 14000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07,
"learning_rate": 2.932249322493225e-05,
"loss": 1.2027,
"step": 500
},
{
"epoch": 0.14,
"learning_rate": 2.86449864498645e-05,
"loss": 0.9342,
"step": 1000
},
{
"epoch": 0.2,
"learning_rate": 2.7967479674796748e-05,
"loss": 0.8946,
"step": 1500
},
{
"epoch": 0.27,
"learning_rate": 2.7289972899729e-05,
"loss": 0.8385,
"step": 2000
},
{
"epoch": 0.34,
"learning_rate": 2.6612466124661247e-05,
"loss": 0.8886,
"step": 2500
},
{
"epoch": 0.41,
"learning_rate": 2.59349593495935e-05,
"loss": 0.8402,
"step": 3000
},
{
"epoch": 0.47,
"learning_rate": 2.5257452574525747e-05,
"loss": 0.8194,
"step": 3500
},
{
"epoch": 0.54,
"learning_rate": 2.4579945799457998e-05,
"loss": 0.8212,
"step": 4000
},
{
"epoch": 0.61,
"learning_rate": 2.3902439024390246e-05,
"loss": 0.8091,
"step": 4500
},
{
"epoch": 0.68,
"learning_rate": 2.3224932249322494e-05,
"loss": 0.8132,
"step": 5000
},
{
"epoch": 0.75,
"learning_rate": 2.2547425474254745e-05,
"loss": 0.8147,
"step": 5500
},
{
"epoch": 0.81,
"learning_rate": 2.186991869918699e-05,
"loss": 0.7896,
"step": 6000
},
{
"epoch": 0.88,
"learning_rate": 2.119241192411924e-05,
"loss": 0.789,
"step": 6500
},
{
"epoch": 0.95,
"learning_rate": 2.051490514905149e-05,
"loss": 0.7633,
"step": 7000
},
{
"epoch": 1.02,
"learning_rate": 1.983739837398374e-05,
"loss": 0.7146,
"step": 7500
},
{
"epoch": 1.08,
"learning_rate": 1.915989159891599e-05,
"loss": 0.5437,
"step": 8000
},
{
"epoch": 1.15,
"learning_rate": 1.8482384823848237e-05,
"loss": 0.5602,
"step": 8500
},
{
"epoch": 1.22,
"learning_rate": 1.7804878048780488e-05,
"loss": 0.5229,
"step": 9000
},
{
"epoch": 1.29,
"learning_rate": 1.7127371273712736e-05,
"loss": 0.5459,
"step": 9500
},
{
"epoch": 1.36,
"learning_rate": 1.6449864498644987e-05,
"loss": 0.5575,
"step": 10000
},
{
"epoch": 1.42,
"learning_rate": 1.5772357723577235e-05,
"loss": 0.5722,
"step": 10500
},
{
"epoch": 1.49,
"learning_rate": 1.5094850948509487e-05,
"loss": 0.5476,
"step": 11000
},
{
"epoch": 1.56,
"learning_rate": 1.4417344173441735e-05,
"loss": 0.5541,
"step": 11500
},
{
"epoch": 1.63,
"learning_rate": 1.3739837398373984e-05,
"loss": 0.5298,
"step": 12000
},
{
"epoch": 1.69,
"learning_rate": 1.3062330623306234e-05,
"loss": 0.5409,
"step": 12500
},
{
"epoch": 1.76,
"learning_rate": 1.2384823848238483e-05,
"loss": 0.5411,
"step": 13000
},
{
"epoch": 1.83,
"learning_rate": 1.1707317073170733e-05,
"loss": 0.5214,
"step": 13500
},
{
"epoch": 1.9,
"learning_rate": 1.1029810298102981e-05,
"loss": 0.5251,
"step": 14000
}
],
"max_steps": 22140,
"num_train_epochs": 3,
"total_flos": 1.3649092771917312e+17,
"trial_name": null,
"trial_params": null
}