qwen-test / all_results.json
andregustavo04's picture
Upload folder using huggingface_hub
ef21732 verified
raw
history blame contribute delete
241 Bytes
{
"epoch": 2.88,
"num_input_tokens_seen": 530864,
"total_flos": 4880889936150528.0,
"train_loss": 0.5967088187182391,
"train_runtime": 437.0311,
"train_samples_per_second": 2.059,
"train_steps_per_second": 0.124
}