llama3-dpo-llm-judge / training_history.json
pyamy's picture
Upload DPO LLM Judge fine-tuned model
f582c27 verified
raw
history blame contribute delete
219 Bytes
[
{
"train_runtime": 2.0172,
"train_samples_per_second": 3.966,
"train_steps_per_second": 0.496,
"total_flos": 0.0,
"train_loss": 0.6931471824645996,
"epoch": 1.0,
"step": 1
}
]