Files
Llama3.2-3B_Paper_Impact_pa…/all_results.json

12 lines
351 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"eval_loss": 0.0693592056632042,
"eval_runtime": 182.6419,
"eval_samples_per_second": 75.388,
"eval_steps_per_second": 2.36,
"total_flos": 2.4545020729727386e+17,
"train_loss": 0.07097241137590674,
"train_runtime": 1113.1898,
"train_samples_per_second": 16.457,
"train_steps_per_second": 0.129
}