Safetensors
English
llama
ProLong-512k-8B-WritingPrompts / train_results.json
chtmp223's picture
Upload folder using huggingface_hub
ba0d393 verified
raw
history blame contribute delete
205 Bytes
{
"epoch": 1.0,
"num_input_tokens_seen": 59375592,
"train_loss": 0.4684678308715094,
"train_runtime": 15557.945,
"train_samples_per_second": 0.233,
"train_steps_per_second": 0.058
}