food-Qwen2-VL-2B-Instruct / train_results.json
AdaptLLM's picture
af3bc6eafa6d8706eb37f68b9d06602fe8126449674567ef88ae482732571271
a911571 verified
raw
history blame
207 Bytes
{
"epoch": 1.0,
"total_flos": 1.3956152400113828e+18,
"train_loss": 1.210920991029758,
"train_runtime": 4090.7445,
"train_samples_per_second": 31.964,
"train_steps_per_second": 0.25
}