tiny-gpt2-instruct-polish / trainer_state.json
s3nh's picture
Upload folder using huggingface_hub
5a6372e
raw
history blame
3.55 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.943714821763603,
"global_step": 26500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.38,
"learning_rate": 9.628378378378378e-07,
"loss": 10.819,
"step": 1000
},
{
"epoch": 0.75,
"learning_rate": 9.253003003003003e-07,
"loss": 10.816,
"step": 2000
},
{
"epoch": 1.13,
"learning_rate": 8.877627627627627e-07,
"loss": 10.8125,
"step": 3000
},
{
"epoch": 1.5,
"learning_rate": 8.502252252252253e-07,
"loss": 10.8092,
"step": 4000
},
{
"epoch": 1.88,
"learning_rate": 8.126876876876877e-07,
"loss": 10.8057,
"step": 5000
},
{
"epoch": 2.25,
"learning_rate": 7.751501501501501e-07,
"loss": 10.8023,
"step": 6000
},
{
"epoch": 2.63,
"learning_rate": 7.376126126126125e-07,
"loss": 10.7993,
"step": 7000
},
{
"epoch": 3.0,
"learning_rate": 7.00075075075075e-07,
"loss": 10.7962,
"step": 8000
},
{
"epoch": 3.38,
"learning_rate": 6.625375375375375e-07,
"loss": 10.7936,
"step": 9000
},
{
"epoch": 3.75,
"learning_rate": 6.249999999999999e-07,
"loss": 10.7913,
"step": 10000
},
{
"epoch": 4.13,
"learning_rate": 5.874624624624625e-07,
"loss": 10.7887,
"step": 11000
},
{
"epoch": 4.5,
"learning_rate": 5.499249249249249e-07,
"loss": 10.7866,
"step": 12000
},
{
"epoch": 4.88,
"learning_rate": 5.123873873873874e-07,
"loss": 10.7845,
"step": 13000
},
{
"epoch": 5.25,
"learning_rate": 4.7484984984984984e-07,
"loss": 10.7826,
"step": 14000
},
{
"epoch": 5.63,
"learning_rate": 4.373123123123123e-07,
"loss": 10.7809,
"step": 15000
},
{
"epoch": 6.0,
"learning_rate": 3.997747747747748e-07,
"loss": 10.7793,
"step": 16000
},
{
"epoch": 6.38,
"learning_rate": 3.6223723723723723e-07,
"loss": 10.7777,
"step": 17000
},
{
"epoch": 6.75,
"learning_rate": 3.246996996996997e-07,
"loss": 10.7764,
"step": 18000
},
{
"epoch": 7.13,
"learning_rate": 2.871621621621622e-07,
"loss": 10.7754,
"step": 19000
},
{
"epoch": 7.5,
"learning_rate": 2.496246246246246e-07,
"loss": 10.7741,
"step": 20000
},
{
"epoch": 7.88,
"learning_rate": 2.120870870870871e-07,
"loss": 10.7732,
"step": 21000
},
{
"epoch": 8.26,
"learning_rate": 1.7454954954954954e-07,
"loss": 10.7725,
"step": 22000
},
{
"epoch": 8.63,
"learning_rate": 1.37012012012012e-07,
"loss": 10.7719,
"step": 23000
},
{
"epoch": 9.01,
"learning_rate": 9.947447447447447e-08,
"loss": 10.7713,
"step": 24000
},
{
"epoch": 9.38,
"learning_rate": 6.193693693693693e-08,
"loss": 10.7709,
"step": 25000
},
{
"epoch": 9.76,
"learning_rate": 2.4399399399399398e-08,
"loss": 10.7708,
"step": 26000
}
],
"max_steps": 26650,
"num_train_epochs": 10,
"total_flos": 98983723008.0,
"trial_name": null,
"trial_params": null
}