Llama-3.2-1B-dpo-lora / train_results.json
haizhongzheng's picture
Model save
b96cab0 verified
raw
history blame
218 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.6070349644347967,
"train_runtime": 21926.9285,
"train_samples": 61134,
"train_samples_per_second": 2.788,
"train_steps_per_second": 0.174
}