qwen-1.8B-test-function-calling / train_results.json
NIEChaojun's picture
Upload folder using huggingface_hub
e9d0ee1 verified
raw
history blame contribute delete
266 Bytes
{
"epoch": 2.986666666666667,
"num_input_tokens_seen": 1596080,
"total_flos": 1.467473931042816e+16,
"train_loss": 0.5455739086582547,
"train_runtime": 1063.0707,
"train_samples_per_second": 2.54,
"train_steps_per_second": 0.158
}