selfimprov-llama3.2-3b-code-ig / train_results.json
SidhaarthMurali's picture
Upload adapter model
dbcfdcb verified
raw
history blame contribute delete
217 Bytes
{
"epoch": 2.972136222910217,
"total_flos": 1389000190033920.0,
"train_loss": 0.5450925727685293,
"train_runtime": 1139.6636,
"train_samples_per_second": 0.85,
"train_steps_per_second": 0.105
}