bert-large-sst2 / trainer_state.json
amodaresi's picture
initial model upload
4dd37fb
raw
history blame
2.31 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"global_step": 10525,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9231651376146789,
"eval_loss": 0.21673926711082458,
"eval_runtime": 1.4821,
"eval_samples_per_second": 588.353,
"eval_steps_per_second": 18.892,
"step": 2105
},
{
"epoch": 1.19,
"learning_rate": 2.2874109263657958e-05,
"loss": 0.2049,
"step": 2500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9277522935779816,
"eval_loss": 0.23751771450042725,
"eval_runtime": 1.48,
"eval_samples_per_second": 589.207,
"eval_steps_per_second": 18.919,
"step": 4210
},
{
"epoch": 2.38,
"learning_rate": 1.5748218527315915e-05,
"loss": 0.123,
"step": 5000
},
{
"epoch": 3.0,
"eval_accuracy": 0.9243119266055045,
"eval_loss": 0.2635619044303894,
"eval_runtime": 1.4812,
"eval_samples_per_second": 588.699,
"eval_steps_per_second": 18.903,
"step": 6315
},
{
"epoch": 3.56,
"learning_rate": 8.622327790973872e-06,
"loss": 0.0839,
"step": 7500
},
{
"epoch": 4.0,
"eval_accuracy": 0.9243119266055045,
"eval_loss": 0.28654733300209045,
"eval_runtime": 1.4787,
"eval_samples_per_second": 589.696,
"eval_steps_per_second": 18.935,
"step": 8420
},
{
"epoch": 4.75,
"learning_rate": 1.496437054631829e-06,
"loss": 0.058,
"step": 10000
},
{
"epoch": 5.0,
"eval_accuracy": 0.9254587155963303,
"eval_loss": 0.31086066365242004,
"eval_runtime": 1.4857,
"eval_samples_per_second": 586.933,
"eval_steps_per_second": 18.846,
"step": 10525
},
{
"epoch": 5.0,
"step": 10525,
"total_flos": 8559638497356828.0,
"train_loss": 0.11400984666692955,
"train_runtime": 1175.3679,
"train_samples_per_second": 286.502,
"train_steps_per_second": 8.955
}
],
"max_steps": 10525,
"num_train_epochs": 5,
"total_flos": 8559638497356828.0,
"trial_name": null,
"trial_params": null
}