Llama-2-7b-Mistral-7B-v0.3-mix / train_results.json
AmberYifan's picture
Model save
0ea740a verified
raw
history blame contribute delete
215 Bytes
{
"epoch": 3.0,
"total_flos": 0.0,
"train_loss": 0.3603214674229566,
"train_runtime": 4632.198,
"train_samples": 9998,
"train_samples_per_second": 6.475,
"train_steps_per_second": 0.203
}