GPT2_instruct_tuned / trainer_state.json
RaushanTurganbay's picture
Upload folder using huggingface_hub
ee39bd9
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 12.038221352795125,
"eval_steps": 500,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.24,
"learning_rate": 1.2e-05,
"loss": 1.7974,
"step": 200
},
{
"epoch": 0.48,
"learning_rate": 2.4e-05,
"loss": 1.78,
"step": 400
},
{
"epoch": 0.72,
"learning_rate": 2.968421052631579e-05,
"loss": 1.7735,
"step": 600
},
{
"epoch": 0.96,
"learning_rate": 2.905263157894737e-05,
"loss": 1.7659,
"step": 800
},
{
"epoch": 1.2,
"learning_rate": 2.8421052631578946e-05,
"loss": 1.7449,
"step": 1000
},
{
"epoch": 1.44,
"learning_rate": 2.7789473684210526e-05,
"loss": 1.7377,
"step": 1200
},
{
"epoch": 1.69,
"learning_rate": 2.7157894736842106e-05,
"loss": 1.7293,
"step": 1400
},
{
"epoch": 1.93,
"learning_rate": 2.6526315789473685e-05,
"loss": 1.7259,
"step": 1600
},
{
"epoch": 2.17,
"learning_rate": 2.5894736842105265e-05,
"loss": 1.705,
"step": 1800
},
{
"epoch": 2.41,
"learning_rate": 2.526315789473684e-05,
"loss": 1.6861,
"step": 2000
},
{
"epoch": 2.65,
"learning_rate": 2.463157894736842e-05,
"loss": 1.6913,
"step": 2200
},
{
"epoch": 2.89,
"learning_rate": 2.4e-05,
"loss": 1.6857,
"step": 2400
},
{
"epoch": 3.13,
"learning_rate": 2.336842105263158e-05,
"loss": 1.6676,
"step": 2600
},
{
"epoch": 3.37,
"learning_rate": 2.273684210526316e-05,
"loss": 1.6573,
"step": 2800
},
{
"epoch": 3.61,
"learning_rate": 2.2105263157894736e-05,
"loss": 1.6504,
"step": 3000
},
{
"epoch": 3.85,
"learning_rate": 2.1473684210526316e-05,
"loss": 1.6465,
"step": 3200
},
{
"epoch": 4.09,
"learning_rate": 2.0842105263157895e-05,
"loss": 1.6333,
"step": 3400
},
{
"epoch": 4.33,
"learning_rate": 2.0210526315789475e-05,
"loss": 1.6197,
"step": 3600
},
{
"epoch": 4.57,
"learning_rate": 1.9578947368421055e-05,
"loss": 1.6201,
"step": 3800
},
{
"epoch": 4.82,
"learning_rate": 1.894736842105263e-05,
"loss": 1.6179,
"step": 4000
},
{
"epoch": 5.06,
"learning_rate": 1.831578947368421e-05,
"loss": 1.6134,
"step": 4200
},
{
"epoch": 5.3,
"learning_rate": 1.7684210526315787e-05,
"loss": 1.5945,
"step": 4400
},
{
"epoch": 5.54,
"learning_rate": 1.705263157894737e-05,
"loss": 1.588,
"step": 4600
},
{
"epoch": 5.78,
"learning_rate": 1.642105263157895e-05,
"loss": 1.5949,
"step": 4800
},
{
"epoch": 6.02,
"learning_rate": 1.5789473684210526e-05,
"loss": 1.585,
"step": 5000
},
{
"epoch": 6.26,
"learning_rate": 1.5157894736842105e-05,
"loss": 1.5695,
"step": 5200
},
{
"epoch": 6.5,
"learning_rate": 1.4526315789473685e-05,
"loss": 1.5656,
"step": 5400
},
{
"epoch": 6.74,
"learning_rate": 1.3894736842105263e-05,
"loss": 1.5687,
"step": 5600
},
{
"epoch": 6.98,
"learning_rate": 1.3263157894736843e-05,
"loss": 1.5669,
"step": 5800
},
{
"epoch": 7.22,
"learning_rate": 1.263157894736842e-05,
"loss": 1.5511,
"step": 6000
},
{
"epoch": 7.46,
"learning_rate": 1.2e-05,
"loss": 1.5488,
"step": 6200
},
{
"epoch": 7.7,
"learning_rate": 1.136842105263158e-05,
"loss": 1.5462,
"step": 6400
},
{
"epoch": 7.95,
"learning_rate": 1.0736842105263158e-05,
"loss": 1.5507,
"step": 6600
},
{
"epoch": 8.19,
"learning_rate": 1.0105263157894738e-05,
"loss": 1.5364,
"step": 6800
},
{
"epoch": 8.43,
"learning_rate": 9.473684210526315e-06,
"loss": 1.5352,
"step": 7000
},
{
"epoch": 8.67,
"learning_rate": 8.842105263157893e-06,
"loss": 1.533,
"step": 7200
},
{
"epoch": 8.91,
"learning_rate": 8.210526315789475e-06,
"loss": 1.5292,
"step": 7400
},
{
"epoch": 9.15,
"learning_rate": 7.578947368421053e-06,
"loss": 1.5258,
"step": 7600
},
{
"epoch": 9.39,
"learning_rate": 6.9473684210526315e-06,
"loss": 1.5194,
"step": 7800
},
{
"epoch": 9.63,
"learning_rate": 6.31578947368421e-06,
"loss": 1.5205,
"step": 8000
},
{
"epoch": 9.87,
"learning_rate": 5.68421052631579e-06,
"loss": 1.5163,
"step": 8200
},
{
"epoch": 10.11,
"learning_rate": 5.052631578947369e-06,
"loss": 1.5182,
"step": 8400
},
{
"epoch": 10.35,
"learning_rate": 4.421052631578947e-06,
"loss": 1.5126,
"step": 8600
},
{
"epoch": 10.59,
"learning_rate": 3.7894736842105264e-06,
"loss": 1.5102,
"step": 8800
},
{
"epoch": 10.83,
"learning_rate": 3.157894736842105e-06,
"loss": 1.5073,
"step": 9000
},
{
"epoch": 11.08,
"learning_rate": 2.5263157894736844e-06,
"loss": 1.5104,
"step": 9200
},
{
"epoch": 11.32,
"learning_rate": 1.8947368421052632e-06,
"loss": 1.5033,
"step": 9400
},
{
"epoch": 11.56,
"learning_rate": 1.2631578947368422e-06,
"loss": 1.5055,
"step": 9600
},
{
"epoch": 11.8,
"learning_rate": 6.315789473684211e-07,
"loss": 1.5047,
"step": 9800
},
{
"epoch": 12.04,
"learning_rate": 0.0,
"loss": 1.5057,
"step": 10000
}
],
"logging_steps": 200,
"max_steps": 10000,
"num_train_epochs": 13,
"save_steps": 500,
"total_flos": 1.1107602523509228e+18,
"trial_name": null,
"trial_params": null
}