simple-llm-python-124m-5b / qualification.json
jfrick's picture
python-124m-muon-5b-20261021-v1: 50065393 training targets
4719692 verified
Raw History Blame Contribute Delete
1.3 kB
{
"passed": true,
"parameters": 124389632,
"initial_loss": 10.464919090270996,
"final_loss": 0.0014346196549013257,
"updates": 21,
"losses": [
10.461538314819336,
7.20192289352417,
4.79567289352417,
2.724158763885498,
1.326021671295166,
0.6623347401618958,
0.11782602220773697,
0.10554386675357819,
0.023414025083184242,
0.010023850947618484,
0.0060213529504835606,
0.004254854749888182,
0.003371018683537841,
0.002859849249944091,
0.0025118314661085606,
0.0022271962370723486,
0.002055828459560871,
0.0018862211145460606,
0.0017189612844958901,
0.0016150841256603599,
0.0014346196549013257
],
"completion": {
"prompt": "def add(a, b):\n ",
"completion": " return a + b\n",
"token_ids": [
262,
401,
277,
361,
305,
202
],
"temperature": 0.0,
"top_k": 0,
"seed": 42,
"new_tokens": 6,
"stop_reason": "eos",
"syntax_valid": true,
"repeated_token_4gram_fraction": 0.0,
"longest_tandem_repeat_tokens": 0,
"long_loop": false
},
"logit_alignment": "passed",
"causality": "passed",
"cached_rope": "passed",
"optimizer_partition": "passed",
"note": "Separate diagnostic model; its weights are discarded"
}