Hiranmai49/judicial-summarization-llama-3-finetuned_FL

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4012
+- Loss: 1.7191
 
 ## Model description
 
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2255        | 1.0   | 726  | 1.1015          |
-| 1.2532        | 2.0   | 1452 | 1.0946          |
-| 0.8203        | 3.0   | 2178 | 1.1221          |
-| 0.7731        | 4.0   | 2904 | 1.1810          |
-| 0.6434        | 5.0   | 3630 | 1.2805          |
-| 0.5579        | 6.0   | 4356 | 1.4012          |
+| 1.357         | 1.0   | 726  | 1.4384          |
+| 1.449         | 2.0   | 1452 | 1.4221          |
+| 1.1707        | 3.0   | 2178 | 1.4453          |
+| 1.0099        | 4.0   | 2904 | 1.5047          |
+| 0.9094        | 5.0   | 3630 | 1.5998          |
+| 0.7842        | 6.0   | 4356 | 1.7191          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe2f8457de2e09d81842065f4565936ca632e7e21380d75d4c3420f3d683c9b
+oid sha256:39b6c3f71767b85c3b28f63a440ec3b6e4052884ef30f234a9242e3cf1b1c4a1
 size 167832240