Mistral-7B-v0.3-Llama-3.1-8B-mix / train_results.json
AmberYifan's picture
Model save
78896d7 verified
raw
history blame contribute delete
217 Bytes
{
"epoch": 3.0,
"total_flos": 0.0,
"train_loss": 0.23421857913081257,
"train_runtime": 6022.7058,
"train_samples": 9987,
"train_samples_per_second": 4.975,
"train_steps_per_second": 0.156
}