End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1114
-- Precision: 0.2802
-- Recall: 0.2684
-- F1: 0.2742
-- Accuracy: 0.9677
+- Loss: 0.1511
+- Precision: 0.4375
+- Recall: 0.4789
+- F1: 0.4573
+- Accuracy: 0.9752
 
 ## Model description
 
@@ -43,26 +43,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0005
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 39   | 0.1589          | 0.0       | 0.0    | 0.0    | 0.9677   |
-| No log        | 2.0   | 78   | 0.1386          | 0.5714    | 0.0421 | 0.0784 | 0.9682   |
-| No log        | 3.0   | 117  | 0.1257          | 0.3784    | 0.0737 | 0.1233 | 0.9678   |
-| No log        | 4.0   | 156  | 0.1107          | 0.2941    | 0.1842 | 0.2265 | 0.9682   |
-| No log        | 5.0   | 195  | 0.1243          | 0.4651    | 0.1053 | 0.1717 | 0.9691   |
-| No log        | 6.0   | 234  | 0.1112          | 0.2775    | 0.2526 | 0.2645 | 0.9679   |
-| No log        | 7.0   | 273  | 0.1093          | 0.2809    | 0.2632 | 0.2717 | 0.9677   |
-| No log        | 8.0   | 312  | 0.1114          | 0.2802    | 0.2684 | 0.2742 | 0.9677   |
+| No log        | 1.0   | 39   | 0.1580          | 0.0       | 0.0    | 0.0    | 0.9677   |
+| No log        | 2.0   | 78   | 0.1313          | 0.2037    | 0.1158 | 0.1477 | 0.9654   |
+| No log        | 3.0   | 117  | 0.0948          | 0.3494    | 0.1526 | 0.2125 | 0.9698   |
+| No log        | 4.0   | 156  | 0.0952          | 0.2252    | 0.3947 | 0.2868 | 0.9676   |
+| No log        | 5.0   | 195  | 0.0850          | 0.3160    | 0.3526 | 0.3333 | 0.9733   |
+| No log        | 6.0   | 234  | 0.1012          | 0.2990    | 0.4895 | 0.3713 | 0.9690   |
+| No log        | 7.0   | 273  | 0.1282          | 0.4476    | 0.4947 | 0.4700 | 0.9739   |
+| No log        | 8.0   | 312  | 0.1400          | 0.4332    | 0.4947 | 0.4619 | 0.9748   |
+| No log        | 9.0   | 351  | 0.1492          | 0.4279    | 0.5    | 0.4612 | 0.9753   |
+| No log        | 10.0  | 390  | 0.1511          | 0.4375    | 0.4789 | 0.4573 | 0.9752   |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e85fb71562e15de881456ac110cc3503fab687ddef21cf9d2be1f822a57b56b
+oid sha256:f6d473daaf5c931f63e0d3c77f9e0198cf03254947ebafb1f9324d0a2bab3a5f
 size 33596518