Llama-3.1-8B-Llama-2-7b-mix / all_results.json
AmberYifan's picture
Model save
aa1497f verified
raw
history blame contribute delete
216 Bytes
{
"epoch": 3.0,
"total_flos": 0.0,
"train_loss": 0.37425009308023827,
"train_runtime": 4934.2684,
"train_samples": 9985,
"train_samples_per_second": 6.071,
"train_steps_per_second": 0.19
}