Mistral-7B-v0.3-gen-dpo-2k-hhrlhf / train_results.json
AmberYifan's picture
Model save
4cbee17 verified
raw
history blame
217 Bytes
{
"epoch": 0.992,
"total_flos": 0.0,
"train_loss": 0.7342928696063257,
"train_runtime": 746.6525,
"train_samples": 1999,
"train_samples_per_second": 2.677,
"train_steps_per_second": 0.083
}