anacondia-70m / trainer_state.json
UncleanCode's picture
Upload folder using huggingface_hub
fecf5d8
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.218769043266301,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 5e-06,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 5e-06,
"loss": 1085325.8,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 5e-06,
"loss": 27.3891,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 5e-06,
"loss": 0.0,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 9.7985347985348e-06,
"loss": 43973696.0,
"step": 200
},
{
"epoch": 0.29,
"learning_rate": 9.554334554334555e-06,
"loss": 308.4559,
"step": 240
},
{
"epoch": 0.34,
"learning_rate": 9.31013431013431e-06,
"loss": 0.0,
"step": 280
},
{
"epoch": 0.39,
"learning_rate": 9.065934065934067e-06,
"loss": 54291310182.4,
"step": 320
},
{
"epoch": 0.44,
"learning_rate": 8.821733821733822e-06,
"loss": 201.0815,
"step": 360
},
{
"epoch": 0.49,
"learning_rate": 8.577533577533578e-06,
"loss": 49.0666,
"step": 400
},
{
"epoch": 0.54,
"learning_rate": 8.333333333333334e-06,
"loss": 13360362.4,
"step": 440
},
{
"epoch": 0.59,
"learning_rate": 8.08913308913309e-06,
"loss": 41888.1875,
"step": 480
},
{
"epoch": 0.63,
"learning_rate": 7.844932844932845e-06,
"loss": 1587181676134.4,
"step": 520
},
{
"epoch": 0.68,
"learning_rate": 7.600732600732601e-06,
"loss": 0.0,
"step": 560
},
{
"epoch": 0.73,
"learning_rate": 7.3565323565323575e-06,
"loss": 19445940.8,
"step": 600
},
{
"epoch": 0.78,
"learning_rate": 7.112332112332113e-06,
"loss": 364.8462,
"step": 640
},
{
"epoch": 0.83,
"learning_rate": 6.868131868131869e-06,
"loss": 8510298521.6,
"step": 680
},
{
"epoch": 0.88,
"learning_rate": 6.623931623931624e-06,
"loss": 2695.5557,
"step": 720
},
{
"epoch": 0.93,
"learning_rate": 6.37973137973138e-06,
"loss": 49141020.8,
"step": 760
},
{
"epoch": 0.98,
"learning_rate": 6.135531135531136e-06,
"loss": 8376225792.0,
"step": 800
},
{
"epoch": 1.02,
"learning_rate": 5.891330891330892e-06,
"loss": 10.4181,
"step": 840
},
{
"epoch": 1.07,
"learning_rate": 5.647130647130648e-06,
"loss": 89069.3438,
"step": 880
},
{
"epoch": 1.12,
"learning_rate": 5.402930402930403e-06,
"loss": 3576579469659341.0,
"step": 920
},
{
"epoch": 1.17,
"learning_rate": 5.15873015873016e-06,
"loss": 15996842252697.6,
"step": 960
},
{
"epoch": 1.22,
"learning_rate": 4.914529914529915e-06,
"loss": 13413.2859,
"step": 1000
}
],
"max_steps": 1640,
"num_train_epochs": 2,
"total_flos": 1119188941897728.0,
"trial_name": null,
"trial_params": null
}