Slayer149-balanced / reports /run /validation.jsonl
kacperwikiel's picture
Update tokenizer, configuration and training reports
a3929e0 verified
Raw History Blame Contribute Delete
4.89 kB
{"step": 1000, "source_validation_loss": {"fineweb_edu": 3.6357946395874023, "dclm_edu": 3.6318132877349854, "cosmopedia": 2.9174532890319824, "finemath": 2.940213680267334}}
{"step": 2000, "source_validation_loss": {"fineweb_edu": 3.3628950119018555, "dclm_edu": 3.3812646865844727, "cosmopedia": 2.551811456680298, "finemath": 2.6517066955566406}}
{"step": 3000, "source_validation_loss": {"fineweb_edu": 3.2158007621765137, "dclm_edu": 3.24115252494812, "cosmopedia": 2.362274169921875, "finemath": 2.494218349456787}}
{"step": 4000, "source_validation_loss": {"fineweb_edu": 3.1462671756744385, "dclm_edu": 3.168818950653076, "cosmopedia": 2.2698538303375244, "finemath": 2.4097580909729004}}
{"step": 5000, "source_validation_loss": {"fineweb_edu": 3.097052812576294, "dclm_edu": 3.1254994869232178, "cosmopedia": 2.2071025371551514, "finemath": 2.3563427925109863}}
{"step": 6000, "source_validation_loss": {"fineweb_edu": 3.0642285346984863, "dclm_edu": 3.0997276306152344, "cosmopedia": 2.1647276878356934, "finemath": 2.31894588470459}}
{"step": 7000, "source_validation_loss": {"fineweb_edu": 3.0427091121673584, "dclm_edu": 3.072791576385498, "cosmopedia": 2.1341612339019775, "finemath": 2.284400701522827}}
{"step": 8000, "source_validation_loss": {"fineweb_edu": 3.022184133529663, "dclm_edu": 3.0521011352539062, "cosmopedia": 2.1067497730255127, "finemath": 2.2722864151000977}}
{"step": 9000, "source_validation_loss": {"fineweb_edu": 3.0031962394714355, "dclm_edu": 3.0357918739318848, "cosmopedia": 2.0862884521484375, "finemath": 2.2452752590179443}}
{"step": 10000, "source_validation_loss": {"fineweb_edu": 2.9892542362213135, "dclm_edu": 3.0245914459228516, "cosmopedia": 2.067286968231201, "finemath": 2.238250970840454}}
{"step": 11000, "source_validation_loss": {"fineweb_edu": 2.9761719703674316, "dclm_edu": 3.0146288871765137, "cosmopedia": 2.05277943611145, "finemath": 2.2114815711975098}}
{"step": 12000, "source_validation_loss": {"fineweb_edu": 2.9684195518493652, "dclm_edu": 3.0029680728912354, "cosmopedia": 2.0343093872070312, "finemath": 2.201632261276245}}
{"step": 13000, "source_validation_loss": {"fineweb_edu": 2.9597086906433105, "dclm_edu": 2.994127035140991, "cosmopedia": 2.02358341217041, "finemath": 2.192626714706421}}
{"step": 14000, "source_validation_loss": {"fineweb_edu": 2.948702096939087, "dclm_edu": 2.9865922927856445, "cosmopedia": 2.0160582065582275, "finemath": 2.18440580368042}}
{"step": 15000, "source_validation_loss": {"fineweb_edu": 2.9435317516326904, "dclm_edu": 2.9802112579345703, "cosmopedia": 2.0042612552642822, "finemath": 2.18125581741333}}
{"step": 16000, "source_validation_loss": {"fineweb_edu": 2.9361798763275146, "dclm_edu": 2.9739556312561035, "cosmopedia": 1.9942559003829956, "finemath": 2.171142578125}}
{"step": 17000, "source_validation_loss": {"fineweb_edu": 2.931060791015625, "dclm_edu": 2.966684341430664, "cosmopedia": 1.9891211986541748, "finemath": 2.1641457080841064}}
{"step": 18000, "source_validation_loss": {"fineweb_edu": 2.923886775970459, "dclm_edu": 2.9643118381500244, "cosmopedia": 1.983628511428833, "finemath": 2.1608521938323975}}
{"step": 19000, "source_validation_loss": {"fineweb_edu": 2.920513153076172, "dclm_edu": 2.958641767501831, "cosmopedia": 1.972259521484375, "finemath": 2.146366834640503}}
{"step": 20000, "source_validation_loss": {"fineweb_edu": 2.914907693862915, "dclm_edu": 2.9553182125091553, "cosmopedia": 1.9704746007919312, "finemath": 2.1503968238830566}}
{"step": 21000, "source_validation_loss": {"fineweb_edu": 2.9123802185058594, "dclm_edu": 2.9512526988983154, "cosmopedia": 1.9636504650115967, "finemath": 2.145289421081543}}
{"step": 22000, "source_validation_loss": {"fineweb_edu": 2.906125783920288, "dclm_edu": 2.946148633956909, "cosmopedia": 1.962751865386963, "finemath": 2.1453704833984375}}
{"step": 23000, "source_validation_loss": {"fineweb_edu": 2.9029648303985596, "dclm_edu": 2.9421579837799072, "cosmopedia": 1.955125093460083, "finemath": 2.1363375186920166}}
{"step": 24000, "source_validation_loss": {"fineweb_edu": 2.9004201889038086, "dclm_edu": 2.94045090675354, "cosmopedia": 1.9505376815795898, "finemath": 2.12982439994812}}
{"step": 25000, "source_validation_loss": {"fineweb_edu": 2.8956382274627686, "dclm_edu": 2.936393976211548, "cosmopedia": 1.9424511194229126, "finemath": 2.1288459300994873}}
{"step": 26000, "source_validation_loss": {"fineweb_edu": 2.893357038497925, "dclm_edu": 2.934877634048462, "cosmopedia": 1.9365743398666382, "finemath": 2.1286120414733887}}
{"step": 27000, "source_validation_loss": {"fineweb_edu": 2.890822649002075, "dclm_edu": 2.9303057193756104, "cosmopedia": 1.936927318572998, "finemath": 2.1255106925964355}}
{"step": 28000, "source_validation_loss": {"fineweb_edu": 2.887849807739258, "dclm_edu": 2.930004119873047, "cosmopedia": 1.933445692062378, "finemath": 2.1189560890197754}}