Safetensors
English
qwen2
Qwen2.5-0.5B-Instruct-R1-Lobotomy / train_results.json
M-o-r-p-h-e-u-s's picture
Initial Upload
ec5dd4c verified
raw
history blame contribute delete
259 Bytes
{
"epoch": 3.0,
"num_input_tokens_seen": 1126151688,
"total_flos": 2.4182853777648783e+18,
"train_loss": 0.9592450147342836,
"train_runtime": 175626.0126,
"train_samples_per_second": 3.612,
"train_steps_per_second": 0.014
}