You can deploy this model and start earning money today!

kanishka/
smolm-autoreg-bpe-babylm-aann-counterfactual-naan-3e-4

Name: smolm-autoreg-bpe-babylm-aann-counterfactual-naan-3e-4
Availability: InStock

Views

No views yet

smolm-autoreg-bpe-babylm-aann-counterfactual-naan-3e-4

This model is a fine-tuned version of models/smolm-autoreg-bpe-babylm-aann-counterfactual-naan-3e-4/config.json on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5639	1.0	18353	3.6707	0.3689
3.2643	2.0	36706	3.3898	0.3954
3.1066	3.0	55059	3.2762	0.4100
3.0219	4.0	73412	3.2161	0.4167
2.9559	5.0	91765	3.1848	0.4207
2.9096	6.0	110118	3.1685	0.4232
2.8687	7.0	128471	3.1490	0.4256
2.8339	8.0	146824	3.1451	0.4271
2.8046	9.0	165177	3.1453	0.4280
2.7762	10.0	183530	3.1355	0.4291
2.7499	11.0	201883	3.1409	0.4296
2.7344	12.0	220236	3.1451	0.4298
2.708	13.0	238589	3.1444	0.4304
2.6808	14.0	256942	3.1492	0.4304
2.6658	15.0	275295	3.1495	0.4307
2.6461	16.0	293648	3.1507	0.4312
2.6243	17.0	312001	3.1567	0.4312
2.6017	18.0	330354	3.1593	0.4312
2.5855	19.0	348707	3.1647	0.4312
2.5643	20.0	367060	3.1689	0.4311