Token-Level-Stereotype-Detector / trainer_state.json
wu981526092's picture
update
c1456bb
raw
history blame
2.15 kB
{
"best_metric": 0.06264707446098328,
"best_model_checkpoint": "token_level_model/best_model/checkpoint-1264",
"epoch": 4.0,
"global_step": 1264,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_balanced accuracy": 0.6290652713011048,
"eval_f1": 0.5903625610241477,
"eval_loss": 0.08535531163215637,
"eval_precision": 0.6673952462175068,
"eval_recall": 0.6290652713011048,
"eval_runtime": 1.1616,
"eval_samples_per_second": 1088.145,
"eval_steps_per_second": 68.009,
"step": 316
},
{
"epoch": 1.58,
"learning_rate": 1.7362869198312237e-05,
"loss": 0.1826,
"step": 500
},
{
"epoch": 2.0,
"eval_balanced accuracy": 0.7368620541402373,
"eval_f1": 0.7319179038298047,
"eval_loss": 0.0663721114397049,
"eval_precision": 0.7513664045814622,
"eval_recall": 0.7368620541402373,
"eval_runtime": 1.1399,
"eval_samples_per_second": 1108.902,
"eval_steps_per_second": 69.306,
"step": 632
},
{
"epoch": 3.0,
"eval_balanced accuracy": 0.7154153135735104,
"eval_f1": 0.7058619488659976,
"eval_loss": 0.0662752017378807,
"eval_precision": 0.7270224611135597,
"eval_recall": 0.7154153135735104,
"eval_runtime": 1.1286,
"eval_samples_per_second": 1119.927,
"eval_steps_per_second": 69.995,
"step": 948
},
{
"epoch": 3.16,
"learning_rate": 1.4725738396624474e-05,
"loss": 0.0568,
"step": 1000
},
{
"epoch": 4.0,
"eval_balanced accuracy": 0.73742506900579,
"eval_f1": 0.7367887044772851,
"eval_loss": 0.06264707446098328,
"eval_precision": 0.7489761641718176,
"eval_recall": 0.73742506900579,
"eval_runtime": 1.1361,
"eval_samples_per_second": 1112.55,
"eval_steps_per_second": 69.534,
"step": 1264
}
],
"max_steps": 3792,
"num_train_epochs": 12,
"total_flos": 100660027447476.0,
"trial_name": null,
"trial_params": null
}