| { | |
| "model": "Agron", | |
| "run": "wikitext-103-subset-50k", | |
| "steps": [ | |
| {"step": 50, "loss": 7.461}, | |
| {"step": 100, "loss": 7.509}, | |
| {"step": 150, "loss": 7.461}, | |
| {"step": 200, "loss": 7.831}, | |
| {"step": 250, "loss": 8.117}, | |
| {"step": 300, "loss": 8.594} | |
| ], | |
| "notes": "Larger run: 8 layers, hidden 512, 1000 steps with 50k lines; early training artifacts retained" | |
| } | |