End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8379
+- Loss: 0.5643
 
 ## Model description
 
@@ -46,7 +46,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.8605        | 0.51  | 500  | 0.8379          |
+| No log        | 0.2   | 200  | 1.2924          |
+| No log        | 0.41  | 400  | 0.8516          |
+| 3.3931        | 0.61  | 600  | 0.6926          |
+| 3.3931        | 0.82  | 800  | 0.5643          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c40082f5d67a353d28810470ab95159ad723fafcf090313b4603197df2a4c4b
+oid sha256:839a86442169a1caf2c558e16f48ea8597db84d5060fb67d7921f6bfdfc52a65
 size 281715176