mpnet-metric / checkpoint-1600 /trainer_state.json
cbrew475's picture
Training in progress, step 1600
adc3913
raw
history blame
6.14 kB
{
"best_metric": 0.925,
"best_model_checkpoint": "mpnet-metric/checkpoint-1400",
"epoch": 36.36363636363637,
"global_step": 1600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.27,
"eval_accuracy": 0.8418831168831169,
"eval_f1": 0.8027962745185904,
"eval_loss": 1.4791860580444336,
"eval_matthews_correlation": 0.8403536839300481,
"eval_runtime": 2.0893,
"eval_samples_per_second": 1474.144,
"eval_steps_per_second": 9.572,
"step": 100
},
{
"epoch": 4.55,
"eval_accuracy": 0.9042207792207793,
"eval_f1": 0.9047628877989691,
"eval_loss": 1.487802267074585,
"eval_matthews_correlation": 0.9030870359405524,
"eval_runtime": 2.1548,
"eval_samples_per_second": 1429.39,
"eval_steps_per_second": 9.282,
"step": 200
},
{
"epoch": 6.82,
"eval_accuracy": 0.9172077922077922,
"eval_f1": 0.9169016425995938,
"eval_loss": 1.6755403280258179,
"eval_matthews_correlation": 0.9161647270846853,
"eval_runtime": 2.1745,
"eval_samples_per_second": 1416.389,
"eval_steps_per_second": 9.197,
"step": 300
},
{
"epoch": 9.09,
"eval_accuracy": 0.9123376623376623,
"eval_f1": 0.9128534869153119,
"eval_loss": 1.6229037046432495,
"eval_matthews_correlation": 0.9111753584333115,
"eval_runtime": 2.0543,
"eval_samples_per_second": 1499.327,
"eval_steps_per_second": 9.736,
"step": 400
},
{
"epoch": 11.36,
"learning_rate": 5.2705340156346366e-05,
"loss": 1.1094,
"step": 500
},
{
"epoch": 11.36,
"eval_accuracy": 0.9172077922077922,
"eval_f1": 0.9150003521466267,
"eval_loss": 1.6902168989181519,
"eval_matthews_correlation": 0.916107308697779,
"eval_runtime": 2.1005,
"eval_samples_per_second": 1466.292,
"eval_steps_per_second": 9.521,
"step": 500
},
{
"epoch": 13.64,
"eval_accuracy": 0.9211038961038961,
"eval_f1": 0.9217190641997036,
"eval_loss": 1.809704065322876,
"eval_matthews_correlation": 0.9200266092875187,
"eval_runtime": 2.1893,
"eval_samples_per_second": 1406.863,
"eval_steps_per_second": 9.135,
"step": 600
},
{
"epoch": 15.91,
"eval_accuracy": 0.9256493506493506,
"eval_f1": 0.9258906800234634,
"eval_loss": 1.767533779144287,
"eval_matthews_correlation": 0.9246460003797943,
"eval_runtime": 2.1499,
"eval_samples_per_second": 1432.599,
"eval_steps_per_second": 9.303,
"step": 700
},
{
"epoch": 18.18,
"eval_accuracy": 0.9188311688311688,
"eval_f1": 0.9200483431183891,
"eval_loss": 1.8722023963928223,
"eval_matthews_correlation": 0.917724204986671,
"eval_runtime": 2.0585,
"eval_samples_per_second": 1496.224,
"eval_steps_per_second": 9.716,
"step": 800
},
{
"epoch": 20.45,
"eval_accuracy": 0.9243506493506494,
"eval_f1": 0.9260936300814407,
"eval_loss": 1.8695343732833862,
"eval_matthews_correlation": 0.9233259198964885,
"eval_runtime": 2.2261,
"eval_samples_per_second": 1383.609,
"eval_steps_per_second": 8.984,
"step": 900
},
{
"epoch": 22.73,
"learning_rate": 3.17905226339867e-05,
"loss": 0.3393,
"step": 1000
},
{
"epoch": 22.73,
"eval_accuracy": 0.9207792207792208,
"eval_f1": 0.922710960511792,
"eval_loss": 1.8605962991714478,
"eval_matthews_correlation": 0.9197088857351889,
"eval_runtime": 2.2172,
"eval_samples_per_second": 1389.151,
"eval_steps_per_second": 9.02,
"step": 1000
},
{
"epoch": 25.0,
"eval_accuracy": 0.9233766233766234,
"eval_f1": 0.9254235342983648,
"eval_loss": 1.953273057937622,
"eval_matthews_correlation": 0.9223384276331019,
"eval_runtime": 2.1419,
"eval_samples_per_second": 1437.981,
"eval_steps_per_second": 9.338,
"step": 1100
},
{
"epoch": 27.27,
"eval_accuracy": 0.9214285714285714,
"eval_f1": 0.9231886111183961,
"eval_loss": 1.9357961416244507,
"eval_matthews_correlation": 0.9203654618815811,
"eval_runtime": 2.0224,
"eval_samples_per_second": 1522.94,
"eval_steps_per_second": 9.889,
"step": 1200
},
{
"epoch": 29.55,
"eval_accuracy": 0.924025974025974,
"eval_f1": 0.9255922212692556,
"eval_loss": 1.9956995248794556,
"eval_matthews_correlation": 0.922995468010013,
"eval_runtime": 2.3012,
"eval_samples_per_second": 1338.415,
"eval_steps_per_second": 8.691,
"step": 1300
},
{
"epoch": 31.82,
"eval_accuracy": 0.925,
"eval_f1": 0.9265277453816252,
"eval_loss": 1.9824904203414917,
"eval_matthews_correlation": 0.923978861394841,
"eval_runtime": 2.0192,
"eval_samples_per_second": 1525.369,
"eval_steps_per_second": 9.905,
"step": 1400
},
{
"epoch": 34.09,
"learning_rate": 1.0875705111627028e-05,
"loss": 0.0269,
"step": 1500
},
{
"epoch": 34.09,
"eval_accuracy": 0.9243506493506494,
"eval_f1": 0.9259389201090135,
"eval_loss": 1.9924736022949219,
"eval_matthews_correlation": 0.9233194822300343,
"eval_runtime": 2.0795,
"eval_samples_per_second": 1481.122,
"eval_steps_per_second": 9.618,
"step": 1500
},
{
"epoch": 36.36,
"eval_accuracy": 0.924025974025974,
"eval_f1": 0.9255203853603882,
"eval_loss": 2.019881248474121,
"eval_matthews_correlation": 0.9229923674514793,
"eval_runtime": 2.0765,
"eval_samples_per_second": 1483.253,
"eval_steps_per_second": 9.632,
"step": 1600
}
],
"max_steps": 1760,
"num_train_epochs": 40,
"total_flos": 8360620865327346.0,
"trial_name": null,
"trial_params": null
}