Completed epoch number 4

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.0534
+- Loss: 3.7847
 
 ## Model description
 
@@ -49,12 +49,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 25.8519       | 0.32   | 100  | 4.9088          |
-| 19.0121       | 0.64   | 200  | 4.4574          |
-| 17.7503       | 0.96   | 300  | 4.2383          |
-| 16.7233       | 1.2784 | 400  | 4.1226          |
-| 16.3433       | 1.5984 | 500  | 4.0681          |
-| 16.2588       | 1.9184 | 600  | 4.0534          |
+| 16.2616       | 0.32   | 100  | 4.0377          |
+| 15.8536       | 0.64   | 200  | 3.9617          |
+| 15.5339       | 0.96   | 300  | 3.8805          |
+| 14.7324       | 1.2784 | 400  | 3.8268          |
+| 14.5909       | 1.5984 | 500  | 3.7950          |
+| 14.63         | 1.9184 | 600  | 3.7847          |
 
 
 ### Framework versions

events.out.tfevents.1735415022.59a6f48de76a.402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa8a4966fed5a1caa9d41ffe6f0dc03a7112eba01729f9c286456aca53d94c0
+size 1028603

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03af4ce4295b785f20226ebcf5a250d52d28d0b0c11311605b2b85ed6f09698e
+oid sha256:1da2cc42d895a2a3ad5aead14bdb41b53a0bc3896710e1a7e5f797e0ee53544d
 size 2203703856