FSI-Edge / logs /cpu_train_20260707_030920.jsonl
FSI Edge
Initial commit: FSI_Edge from-scratch novel architecture coding model
9485e3f
Raw
History Blame Contribute Delete
2.45 kB
{"step": 1166, "loss": 4.16790246963501, "avg_loss": 2.8394746208190917, "best_loss": 1.087227463722229, "lr": 0.0002499017801151383, "elapsed": 51.75848412513733, "steps_per_sec": 0.48301260020593134}
{"step": 1191, "loss": 3.9784233570098877, "avg_loss": 2.9861608076095583, "best_loss": 1.087227463722229, "lr": 0.0002477750587951324, "elapsed": 103.35709762573242, "steps_per_sec": 0.4837597141229292}
{"step": 1216, "loss": 2.4968650341033936, "avg_loss": 2.588305377960205, "best_loss": 1.087227463722229, "lr": 0.00024561359846230407, "elapsed": 155.45915842056274, "steps_per_sec": 0.4824418243478647}
{"step": 1241, "loss": 3.020519495010376, "avg_loss": 2.7912425708770754, "best_loss": 1.087227463722229, "lr": 0.00024304901369648406, "elapsed": 207.3621962070465, "steps_per_sec": 0.48224797879818093}
{"step": 1266, "loss": 1.0227971076965332, "avg_loss": 2.5470275855064393, "best_loss": 0.8561386466026306, "lr": 0.00024081493610715084, "elapsed": 247.06574606895447, "steps_per_sec": 0.5059382046636012}
{"step": 1291, "loss": 2.6970174312591553, "avg_loss": 2.6006040716171266, "best_loss": 0.8561386466026306, "lr": 0.00023854859240344481, "elapsed": 284.1964855194092, "steps_per_sec": 0.5278038527670524}
{"step": 1316, "loss": 4.030348300933838, "avg_loss": 2.7792826890945435, "best_loss": 0.8561386466026306, "lr": 0.00023625078780649243, "elapsed": 321.8028621673584, "steps_per_sec": 0.5438111980153508}
{"step": 1341, "loss": 3.9423696994781494, "avg_loss": 2.4357468128204345, "best_loss": 0.8561386466026306, "lr": 0.00023353134247322882, "elapsed": 358.8600425720215, "steps_per_sec": 0.5573203373843466}
{"step": 1366, "loss": 2.9195241928100586, "avg_loss": 2.4382311058044435, "best_loss": 0.8561386466026306, "lr": 0.00023116818781903197, "elapsed": 395.3430688381195, "steps_per_sec": 0.5691259509399175}
{"step": 1391, "loss": 2.5811784267425537, "avg_loss": 2.7966215467453, "best_loss": 0.8561386466026306, "lr": 0.00022877619449419495, "elapsed": 432.21026062965393, "steps_per_sec": 0.578422177288883}
{"step": 1416, "loss": 2.3694353103637695, "avg_loss": 2.5893052864074706, "best_loss": 0.8561386466026306, "lr": 0.0002263562123625563, "elapsed": 469.646714925766, "steps_per_sec": 0.5855465209491936}
{"step": 1441, "loss": 2.627246856689453, "avg_loss": 2.734176044464111, "best_loss": 0.8561386466026306, "lr": 0.00022349867274663613, "elapsed": 507.05024766921997, "steps_per_sec": 0.5916573384571314}