llama3-3b-closedqa-gpt4o-100k / train_results.json
chansung's picture
Model save
13bda72 verified
raw
history blame contribute delete
236 Bytes
{
"epoch": 10.0,
"total_flos": 2.846679860191953e+18,
"train_loss": 1.3252380434423685,
"train_runtime": 3360.483,
"train_samples": 111440,
"train_samples_per_second": 48.669,
"train_steps_per_second": 0.19
}