GRS-Grammar-Checker-DeBerta / trainer_state.json
imohammad12's picture
model files added
3da2248
raw
history blame
1.87 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 716,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.28,
"learning_rate": 5e-06,
"loss": 0.6789,
"step": 50
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 0.5907,
"step": 100
},
{
"epoch": 0.84,
"learning_rate": 1.5e-05,
"loss": 0.4927,
"step": 150
},
{
"epoch": 1.12,
"learning_rate": 2e-05,
"loss": 0.4183,
"step": 200
},
{
"epoch": 1.4,
"learning_rate": 2.5e-05,
"loss": 0.3848,
"step": 250
},
{
"epoch": 1.68,
"learning_rate": 3e-05,
"loss": 0.3815,
"step": 300
},
{
"epoch": 1.96,
"learning_rate": 3.5e-05,
"loss": 0.3652,
"step": 350
},
{
"epoch": 2.23,
"learning_rate": 4e-05,
"loss": 0.2917,
"step": 400
},
{
"epoch": 2.51,
"learning_rate": 4.5e-05,
"loss": 0.2744,
"step": 450
},
{
"epoch": 2.79,
"learning_rate": 5e-05,
"loss": 0.2875,
"step": 500
},
{
"epoch": 3.07,
"learning_rate": 4.367088607594937e-05,
"loss": 0.2423,
"step": 550
},
{
"epoch": 3.35,
"learning_rate": 3.7341772151898736e-05,
"loss": 0.1756,
"step": 600
},
{
"epoch": 3.63,
"learning_rate": 3.10126582278481e-05,
"loss": 0.1606,
"step": 650
},
{
"epoch": 3.91,
"learning_rate": 2.468354430379747e-05,
"loss": 0.1644,
"step": 700
}
],
"max_steps": 895,
"num_train_epochs": 5,
"total_flos": 1342598254767024.0,
"trial_name": null,
"trial_params": null
}