lesso
/

c0ea47d1-26f2-4180-8f45-7bddb8dea95d

Generated from Trainer

8-bit precision

Model card Files Files and versions Community

lesso commited on 25 days ago

Commit

be695c2

•

1 Parent(s): 3720ebd

End of training

Files changed (2) hide show

README.md +4 -4
adapter_model.bin +1 -1

README.md CHANGED Viewed

@@ -105,7 +105,7 @@ xformers_attention: null
 This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 23.4227
 ## Model description
@@ -140,9 +140,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 95.6979       | 0.0000 | 1    | 23.5341         |
-| 94.7096       | 0.0000 | 3    | 23.5243         |
-| 94.5627       | 0.0001 | 6    | 23.4904         |
-| 94.9168       | 0.0001 | 9    | 23.4227         |
 ### Framework versions

 This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 23.4692
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 95.6979       | 0.0000 | 1    | 23.5341         |
+| 95.2096       | 0.0000 | 3    | 23.5267         |
+| 94.1798       | 0.0001 | 6    | 23.5058         |
+| 94.8532       | 0.0001 | 9    | 23.4692         |
 ### Framework versions

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c1fc223fed071fa0e67996d8dcd977d7abf853f6d99a5b2b40619ced5de530
 size 3163390

 version https://git-lfs.github.com/spec/v1
+oid sha256:ae7f1540e4341bd52485060d1e0d37f5b095dc39369c3074dabe4c77ea32eb89
 size 3163390