Model save

README.md

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # NeoLLM
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6379
 
 ## Model description
 
@@ -42,6 +44,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 5.3596        | 0.1067 | 5000  | 5.2775          |
+| 5.0526        | 0.2133 | 10000 | 4.9718          |
+| 4.9395        | 0.32   | 15000 | 4.8671          |
+| 4.9021        | 0.4267 | 20000 | 4.8195          |
+| 4.8792        | 0.5333 | 25000 | 4.7910          |
+| 4.8616        | 0.64   | 30000 | 4.7811          |
+| 4.8573        | 0.7467 | 35000 | 4.7679          |
+| 4.7668        | 0.8533 | 40000 | 4.6924          |
+| 4.7173        | 0.96   | 45000 | 4.6379          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3410b39971f342b50c863ec3c437a6622b933766ecd2c03c90225920c1fe89
+oid sha256:3816f1b0cef7d58039649547cc3d8cc1600719bdec9083ceda293dc37dea4224
 size 303438024

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b88075aa320014734dd32de989c729a2a69a687121a48e424824b7a76e3c5b1
+oid sha256:b9994cdff0ede5029eb82c391045f726eb7dbf0b0ad0a40f7965c97a8ca54d8e
 size 6033