lambda-qwen2.5-14b-dpo-test / train_results.json
tanliboy's picture
Model save
5d863b5 verified
raw
history blame
231 Bytes
{
"epoch": 0.998691442030882,
"total_flos": 0.0,
"train_loss": 0.5192520058629898,
"train_runtime": 13862.6582,
"train_samples": 61134,
"train_samples_per_second": 4.41,
"train_steps_per_second": 0.034
}