tmnam20's picture
Training in progress, step 4000, checkpoint
e723904
raw
history blame
2.07 kB
{
"best_metric": 1.1015312671661377,
"best_model_checkpoint": "/kaggle/output/checkpoint-4000",
"epoch": 0.16297262059973924,
"eval_steps": 1000,
"global_step": 4000,
"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": 1.1065,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1586,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.32954091816367265,
"eval_loss": 1.1065887212753296,
"eval_runtime": 54.4372,
"eval_samples_per_second": 92.033,
"eval_steps_per_second": 11.518,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.1259,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.3435129740518962,
"eval_loss": 1.1045255661010742,
"eval_runtime": 54.458,
"eval_samples_per_second": 91.997,
"eval_steps_per_second": 11.513,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 8.327777777777778e-08,
"loss": 1.1229,
"step": 3000
},
{
"epoch": 0.12,
"eval_accuracy": 0.3441117764471058,
"eval_loss": 1.1050777435302734,
"eval_runtime": 54.349,
"eval_samples_per_second": 92.182,
"eval_steps_per_second": 11.537,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 1.1105555555555557e-07,
"loss": 1.1237,
"step": 4000
},
{
"epoch": 0.16,
"eval_accuracy": 0.3411177644710579,
"eval_loss": 1.1015312671661377,
"eval_runtime": 54.4388,
"eval_samples_per_second": 92.03,
"eval_steps_per_second": 11.518,
"step": 4000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 8361420521472000.0,
"trial_name": null,
"trial_params": null
}