mpnet-metric / checkpoint-1600 /trainer_state.json
cbrew475's picture
Training in progress, step 200
d06a44e
raw
history blame
6.17 kB
{
"best_metric": 0.9282467532467532,
"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": 0.8194805194805195,
"eval_f1": 0.7656701166780793,
"eval_loss": 1.9282063245773315,
"eval_matthews_correlation": 0.8177401806097793,
"eval_runtime": 2.1248,
"eval_samples_per_second": 1449.542,
"eval_steps_per_second": 9.413,
"step": 100
},
{
"epoch": 4.55,
"eval_accuracy": 0.8603896103896104,
"eval_f1": 0.8221385737164676,
"eval_loss": 1.785994529724121,
"eval_matthews_correlation": 0.8588446795045349,
"eval_runtime": 2.1571,
"eval_samples_per_second": 1427.834,
"eval_steps_per_second": 9.272,
"step": 200
},
{
"epoch": 6.82,
"eval_accuracy": 0.8831168831168831,
"eval_f1": 0.8503152420049573,
"eval_loss": 1.703816533088684,
"eval_matthews_correlation": 0.8817033568232515,
"eval_runtime": 2.2955,
"eval_samples_per_second": 1341.777,
"eval_steps_per_second": 8.713,
"step": 300
},
{
"epoch": 9.09,
"eval_accuracy": 0.8948051948051948,
"eval_f1": 0.8658511061420076,
"eval_loss": 1.5578949451446533,
"eval_matthews_correlation": 0.893469940479661,
"eval_runtime": 2.1159,
"eval_samples_per_second": 1455.648,
"eval_steps_per_second": 9.452,
"step": 400
},
{
"epoch": 11.36,
"learning_rate": 2.91576008814464e-05,
"loss": 1.3674,
"step": 500
},
{
"epoch": 11.36,
"eval_accuracy": 0.9084415584415585,
"eval_f1": 0.8884952022189863,
"eval_loss": 1.6358195543289185,
"eval_matthews_correlation": 0.9072261203467101,
"eval_runtime": 2.0369,
"eval_samples_per_second": 1512.102,
"eval_steps_per_second": 9.819,
"step": 500
},
{
"epoch": 13.64,
"eval_accuracy": 0.9191558441558442,
"eval_f1": 0.9087017801267994,
"eval_loss": 1.6092149019241333,
"eval_matthews_correlation": 0.9180607280357055,
"eval_runtime": 2.2317,
"eval_samples_per_second": 1380.116,
"eval_steps_per_second": 8.962,
"step": 600
},
{
"epoch": 15.91,
"eval_accuracy": 0.9237012987012987,
"eval_f1": 0.9173470137032593,
"eval_loss": 1.6759223937988281,
"eval_matthews_correlation": 0.92267900847975,
"eval_runtime": 2.1403,
"eval_samples_per_second": 1439.027,
"eval_steps_per_second": 9.344,
"step": 700
},
{
"epoch": 18.18,
"eval_accuracy": 0.922077922077922,
"eval_f1": 0.9224956919233739,
"eval_loss": 1.7042781114578247,
"eval_matthews_correlation": 0.9210156723561079,
"eval_runtime": 2.1182,
"eval_samples_per_second": 1454.06,
"eval_steps_per_second": 9.442,
"step": 800
},
{
"epoch": 20.45,
"eval_accuracy": 0.9256493506493506,
"eval_f1": 0.9250031430609338,
"eval_loss": 1.618914246559143,
"eval_matthews_correlation": 0.9246330543218574,
"eval_runtime": 2.1102,
"eval_samples_per_second": 1459.597,
"eval_steps_per_second": 9.478,
"step": 900
},
{
"epoch": 22.73,
"learning_rate": 1.758712434118989e-05,
"loss": 0.4113,
"step": 1000
},
{
"epoch": 22.73,
"eval_accuracy": 0.9272727272727272,
"eval_f1": 0.9262478178442993,
"eval_loss": 1.6726940870285034,
"eval_matthews_correlation": 0.9262802775880362,
"eval_runtime": 2.3947,
"eval_samples_per_second": 1286.193,
"eval_steps_per_second": 8.352,
"step": 1000
},
{
"epoch": 25.0,
"eval_accuracy": 0.9282467532467532,
"eval_f1": 0.9285902214751346,
"eval_loss": 1.7208188772201538,
"eval_matthews_correlation": 0.9272760959410294,
"eval_runtime": 2.0547,
"eval_samples_per_second": 1498.986,
"eval_steps_per_second": 9.734,
"step": 1100
},
{
"epoch": 27.27,
"eval_accuracy": 0.9272727272727272,
"eval_f1": 0.9269182576494233,
"eval_loss": 1.7480313777923584,
"eval_matthews_correlation": 0.9262735351894748,
"eval_runtime": 2.0774,
"eval_samples_per_second": 1482.597,
"eval_steps_per_second": 9.627,
"step": 1200
},
{
"epoch": 29.55,
"eval_accuracy": 0.9262987012987013,
"eval_f1": 0.9262601189689171,
"eval_loss": 1.7753738164901733,
"eval_matthews_correlation": 0.9252925536787239,
"eval_runtime": 2.1885,
"eval_samples_per_second": 1407.348,
"eval_steps_per_second": 9.139,
"step": 1300
},
{
"epoch": 31.82,
"eval_accuracy": 0.9282467532467532,
"eval_f1": 0.9278794105174281,
"eval_loss": 1.790648341178894,
"eval_matthews_correlation": 0.9272619193360061,
"eval_runtime": 2.0054,
"eval_samples_per_second": 1535.842,
"eval_steps_per_second": 9.973,
"step": 1400
},
{
"epoch": 34.09,
"learning_rate": 6.0166478009333844e-06,
"loss": 0.0733,
"step": 1500
},
{
"epoch": 34.09,
"eval_accuracy": 0.9262987012987013,
"eval_f1": 0.9263368444227621,
"eval_loss": 1.805496335029602,
"eval_matthews_correlation": 0.9252900896996127,
"eval_runtime": 2.1349,
"eval_samples_per_second": 1442.709,
"eval_steps_per_second": 9.368,
"step": 1500
},
{
"epoch": 36.36,
"eval_accuracy": 0.9282467532467532,
"eval_f1": 0.9281799745185059,
"eval_loss": 1.7787483930587769,
"eval_matthews_correlation": 0.9272691959664779,
"eval_runtime": 2.095,
"eval_samples_per_second": 1470.152,
"eval_steps_per_second": 9.546,
"step": 1600
}
],
"max_steps": 1760,
"num_train_epochs": 40,
"total_flos": 8360620865327346.0,
"trial_name": null,
"trial_params": null
}