llama3_cpo_best_entropy / train_results.json
yakazimir's picture
Model save
d6a6b27 verified
raw
history blame contribute delete
230 Bytes
{
"epoch": 0.9989071038251366,
"total_flos": 0.0,
"train_loss": 2.585477126766347,
"train_runtime": 5989.402,
"train_samples": 58558,
"train_samples_per_second": 9.777,
"train_steps_per_second": 0.076
}