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: 0.1281
-- Precision: 0.4369
-- Recall: 0.4737
-- F1: 0.4545
-- Accuracy: 0.9738
+- Loss: 0.1266
+- Precision: 0.5172
+- Recall: 0.5526
+- F1: 0.5344
+- Accuracy: 0.9776
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.0008
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 39   | 0.1497          | 0.2759    | 0.0421 | 0.0731 | 0.9670   |
-| No log        | 2.0   | 78   | 0.1247          | 0.4167    | 0.0789 | 0.1327 | 0.9679   |
-| No log        | 3.0   | 117  | 0.1009          | 0.5111    | 0.1211 | 0.1957 | 0.9697   |
-| No log        | 4.0   | 156  | 0.0875          | 0.3209    | 0.3158 | 0.3183 | 0.9711   |
-| No log        | 5.0   | 195  | 0.0863          | 0.472     | 0.3105 | 0.3746 | 0.9730   |
-| No log        | 6.0   | 234  | 0.0915          | 0.3770    | 0.5    | 0.4299 | 0.9719   |
-| No log        | 7.0   | 273  | 0.1292          | 0.4847    | 0.4158 | 0.4476 | 0.9749   |
-| No log        | 8.0   | 312  | 0.1281          | 0.4369    | 0.4737 | 0.4545 | 0.9738   |
+| No log        | 1.0   | 39   | 0.1253          | 0.5862    | 0.0895 | 0.1553 | 0.9683   |
+| No log        | 2.0   | 78   | 0.1157          | 0.2233    | 0.3632 | 0.2766 | 0.9618   |
+| No log        | 3.0   | 117  | 0.0949          | 0.45      | 0.2368 | 0.3103 | 0.9730   |
+| No log        | 4.0   | 156  | 0.0716          | 0.4618    | 0.6053 | 0.5239 | 0.9764   |
+| No log        | 5.0   | 195  | 0.1050          | 0.584     | 0.3842 | 0.4635 | 0.9760   |
+| No log        | 6.0   | 234  | 0.1071          | 0.4798    | 0.5632 | 0.5182 | 0.9775   |
+| No log        | 7.0   | 273  | 0.1220          | 0.5049    | 0.5474 | 0.5253 | 0.9777   |
+| No log        | 8.0   | 312  | 0.1266          | 0.5172    | 0.5526 | 0.5344 | 0.9776   |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09419d5dd9dd304c1d55086b5f3b003f03e69c09c36ab291ef80e91b128075a3
+oid sha256:ed0e552b32bd0011126a47e036e7b35bdc4bb457a6b684440331091489ab3560
 size 33596518