Files
SmolLM3-DPO-Second-Round/train_results.json

9 lines
221 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.45319234429607314,
"train_runtime": 13193.0651,
"train_samples": 161271,
"train_samples_per_second": 12.224,
"train_steps_per_second": 0.382
}