lesso
/

2282480b-ef3b-4136-8e90-4dd3c99bfab5

Generated from Trainer

Model card Files Files and versions Community

lesso commited on 19 days ago

Commit

386280e

•

1 Parent(s): 69ffba8

End of training

Files changed (2) hide show

README.md +2 -2
adapter_model.bin +1 -1

README.md CHANGED Viewed

@@ -104,7 +104,7 @@ xformers_attention: null
 This model is a fine-tuned version of [fxmarty/tiny-llama-fast-tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.3852
 ## Model description
@@ -142,7 +142,7 @@ The following hyperparameters were used during training:
 | 10.3888       | 0.0001 | 1    | 10.3863         |
 | 10.3902       | 0.0002 | 3    | 10.3862         |
 | 10.3935       | 0.0004 | 6    | 10.3859         |
-| 10.3808       | 0.0006 | 9    | 10.3852         |
 ### Framework versions

 This model is a fine-tuned version of [fxmarty/tiny-llama-fast-tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 10.3853
 ## Model description
 | 10.3888       | 0.0001 | 1    | 10.3863         |
 | 10.3902       | 0.0002 | 3    | 10.3862         |
 | 10.3935       | 0.0004 | 6    | 10.3859         |
+| 10.3808       | 0.0006 | 9    | 10.3853         |
 ### Framework versions

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329878b0df5e22c754242bc6f8b1a61964d1b3e57caeb639a85000724d444a7a
 size 33666

 version https://git-lfs.github.com/spec/v1
+oid sha256:64975a076984ab9a23d2750f0aa36bc8e439616eca743d20cfe66a16f1a486e5
 size 33666