tmnam20's picture
Training in progress, step 9000, checkpoint
b03067f
raw
history blame
3.91 kB
{
"best_metric": 1.094658613204956,
"best_model_checkpoint": "/kaggle/output/checkpoint-8000",
"epoch": 0.3666883963494133,
"eval_steps": 1000,
"global_step": 9000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.7777777777777777e-11,
"loss": 1.1383,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1424,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.32375249500998005,
"eval_loss": 1.1077626943588257,
"eval_runtime": 54.8633,
"eval_samples_per_second": 91.318,
"eval_steps_per_second": 11.428,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.1244,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.33652694610778444,
"eval_loss": 1.1080161333084106,
"eval_runtime": 54.7384,
"eval_samples_per_second": 91.526,
"eval_steps_per_second": 11.454,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 8.327777777777778e-08,
"loss": 1.1228,
"step": 3000
},
{
"epoch": 0.12,
"eval_accuracy": 0.34331337325349304,
"eval_loss": 1.1084064245224,
"eval_runtime": 54.7948,
"eval_samples_per_second": 91.432,
"eval_steps_per_second": 11.443,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 1.1105555555555557e-07,
"loss": 1.1216,
"step": 4000
},
{
"epoch": 0.16,
"eval_accuracy": 0.3385229540918164,
"eval_loss": 1.1014840602874756,
"eval_runtime": 54.8508,
"eval_samples_per_second": 91.339,
"eval_steps_per_second": 11.431,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 1.3880555555555558e-07,
"loss": 1.1181,
"step": 5000
},
{
"epoch": 0.2,
"eval_accuracy": 0.33073852295409184,
"eval_loss": 1.1008135080337524,
"eval_runtime": 54.8304,
"eval_samples_per_second": 91.373,
"eval_steps_per_second": 11.435,
"step": 5000
},
{
"epoch": 0.24,
"learning_rate": 1.6658333333333335e-07,
"loss": 1.1132,
"step": 6000
},
{
"epoch": 0.24,
"eval_accuracy": 0.3520958083832335,
"eval_loss": 1.0993762016296387,
"eval_runtime": 54.8804,
"eval_samples_per_second": 91.289,
"eval_steps_per_second": 11.425,
"step": 6000
},
{
"epoch": 0.29,
"learning_rate": 1.9433333333333334e-07,
"loss": 1.1113,
"step": 7000
},
{
"epoch": 0.29,
"eval_accuracy": 0.3530938123752495,
"eval_loss": 1.0965770483016968,
"eval_runtime": 54.8881,
"eval_samples_per_second": 91.277,
"eval_steps_per_second": 11.423,
"step": 7000
},
{
"epoch": 0.33,
"learning_rate": 2.2211111111111114e-07,
"loss": 1.1111,
"step": 8000
},
{
"epoch": 0.33,
"eval_accuracy": 0.35708582834331337,
"eval_loss": 1.094658613204956,
"eval_runtime": 54.8233,
"eval_samples_per_second": 91.384,
"eval_steps_per_second": 11.437,
"step": 8000
},
{
"epoch": 0.37,
"learning_rate": 2.4986111111111113e-07,
"loss": 1.109,
"step": 9000
},
{
"epoch": 0.37,
"eval_accuracy": 0.34191616766467064,
"eval_loss": 1.106990933418274,
"eval_runtime": 54.9095,
"eval_samples_per_second": 91.241,
"eval_steps_per_second": 11.419,
"step": 9000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 1.8813196173312e+16,
"trial_name": null,
"trial_params": null
}