math_llama3_reset_dpo_100_0_0.5 / train_results.json
lzc0525's picture
Upload folder using huggingface_hub
b4cbb59 verified
raw
history blame contribute delete
230 Bytes
{
"epoch": 0.9221902017291066,
"total_flos": 0.0,
"train_loss": 0.5759013295173645,
"train_runtime": 619.8336,
"train_samples": 1387,
"train_samples_per_second": 2.238,
"train_steps_per_second": 0.016
}