percival-a / checkpoint-350 /trainer_state.json
ashwinpreyan's picture
Upload folder using huggingface_hub
d61b6a3
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 69.0909090909091,
"eval_steps": 500,
"global_step": 350,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.02,
"learning_rate": 5.194805194805195e-06,
"loss": 1.8662,
"step": 11
},
{
"epoch": 4.04,
"learning_rate": 1.0909090909090909e-05,
"loss": 1.5883,
"step": 22
},
{
"epoch": 6.05,
"learning_rate": 1.6623376623376623e-05,
"loss": 1.0967,
"step": 33
},
{
"epoch": 8.07,
"learning_rate": 2.2337662337662336e-05,
"loss": 0.7579,
"step": 44
},
{
"epoch": 10.09,
"learning_rate": 2.8051948051948052e-05,
"loss": 0.5478,
"step": 55
},
{
"epoch": 13.02,
"learning_rate": 3.324675324675325e-05,
"loss": 0.4326,
"step": 66
},
{
"epoch": 15.04,
"learning_rate": 3.8441558441558445e-05,
"loss": 0.3292,
"step": 77
},
{
"epoch": 17.05,
"learning_rate": 4.415584415584416e-05,
"loss": 0.2404,
"step": 88
},
{
"epoch": 19.07,
"learning_rate": 4.987012987012987e-05,
"loss": 0.1739,
"step": 99
},
{
"epoch": 21.09,
"learning_rate": 5.558441558441558e-05,
"loss": 0.1312,
"step": 110
},
{
"epoch": 24.02,
"learning_rate": 6.12987012987013e-05,
"loss": 0.0961,
"step": 121
},
{
"epoch": 26.04,
"learning_rate": 6.701298701298702e-05,
"loss": 0.0595,
"step": 132
},
{
"epoch": 28.05,
"learning_rate": 7.16883116883117e-05,
"loss": 0.1897,
"step": 143
},
{
"epoch": 30.07,
"learning_rate": 7.74025974025974e-05,
"loss": 0.0537,
"step": 154
},
{
"epoch": 32.09,
"learning_rate": 8.311688311688312e-05,
"loss": 0.0264,
"step": 165
},
{
"epoch": 35.02,
"learning_rate": 8.883116883116883e-05,
"loss": 0.0199,
"step": 176
},
{
"epoch": 37.04,
"learning_rate": 9.454545454545455e-05,
"loss": 0.0176,
"step": 187
},
{
"epoch": 39.05,
"learning_rate": 0.00010025974025974026,
"loss": 0.015,
"step": 198
},
{
"epoch": 41.07,
"learning_rate": 0.00010597402597402598,
"loss": 0.0134,
"step": 209
},
{
"epoch": 43.09,
"learning_rate": 0.00011168831168831168,
"loss": 0.0094,
"step": 220
},
{
"epoch": 46.02,
"learning_rate": 0.0001174025974025974,
"loss": 0.0064,
"step": 231
},
{
"epoch": 48.04,
"learning_rate": 0.0001231168831168831,
"loss": 0.0084,
"step": 242
},
{
"epoch": 50.05,
"learning_rate": 0.00012883116883116884,
"loss": 0.0077,
"step": 253
},
{
"epoch": 52.07,
"learning_rate": 0.00013454545454545455,
"loss": 0.0082,
"step": 264
},
{
"epoch": 54.09,
"learning_rate": 0.00014025974025974028,
"loss": 0.0058,
"step": 275
},
{
"epoch": 57.02,
"learning_rate": 0.00014597402597402599,
"loss": 0.006,
"step": 286
},
{
"epoch": 59.04,
"learning_rate": 0.0001516883116883117,
"loss": 0.0095,
"step": 297
},
{
"epoch": 61.05,
"learning_rate": 0.00015740259740259742,
"loss": 0.006,
"step": 308
},
{
"epoch": 63.07,
"learning_rate": 0.00016311688311688313,
"loss": 0.0068,
"step": 319
},
{
"epoch": 65.09,
"learning_rate": 0.00016883116883116884,
"loss": 0.0086,
"step": 330
},
{
"epoch": 68.02,
"learning_rate": 0.00017454545454545454,
"loss": 0.0036,
"step": 341
}
],
"logging_steps": 11,
"max_steps": 3850,
"num_train_epochs": 70,
"save_steps": 500,
"total_flos": 6.12217506496512e+16,
"trial_name": null,
"trial_params": null
}