Model save

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hivaze/ParaLex-Llama-3-8B-SFT](https://huggingface.co/hivaze/ParaLex-Llama-3-8B-SFT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3215
+- Loss: 1.8083
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 2e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
@@ -48,12 +48,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4022        | 1.25  | 5    | 0.3324          |
-| 0.3492        | 2.5   | 10   | 0.3161          |
-| 0.3181        | 3.75  | 15   | 0.3138          |
-| 0.2808        | 5.0   | 20   | 0.3177          |
-| 0.2571        | 6.25  | 25   | 0.3206          |
-| 0.2424        | 7.5   | 30   | 0.3215          |
+| 7.3306        | 1.25  | 5    | 5.9428          |
+| 5.4669        | 2.5   | 10   | 4.3334          |
+| 4.0282        | 3.75  | 15   | 3.1156          |
+| 2.9271        | 5.0   | 20   | 2.3114          |
+| 2.3074        | 6.25  | 25   | 1.9202          |
+| 1.9795        | 7.5   | 30   | 1.8083          |
 
 
 ### Framework versions