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: 0.1763
-- Precision: 0.5149
-- Recall: 0.5474
-- F1: 0.5306
-- Accuracy: 0.9771
+- Loss: 0.1250
+- Precision: 0.5365
+- Recall: 0.5421
+- F1: 0.5393
+- Accuracy: 0.9778
 
 ## Model description
 
@@ -43,33 +43,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.0009
 - 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: 15
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 39   | 0.1373          | 0.3704    | 0.1053 | 0.1639 | 0.9658   |
-| No log        | 2.0   | 78   | 0.1236          | 0.2123    | 0.3632 | 0.2680 | 0.9638   |
-| No log        | 3.0   | 117  | 0.0959          | 0.5333    | 0.1263 | 0.2043 | 0.9701   |
-| No log        | 4.0   | 156  | 0.0803          | 0.3480    | 0.5    | 0.4104 | 0.9715   |
-| No log        | 5.0   | 195  | 0.1118          | 0.4684    | 0.3895 | 0.4253 | 0.9758   |
-| No log        | 6.0   | 234  | 0.0944          | 0.4421    | 0.4421 | 0.4421 | 0.9752   |
-| No log        | 7.0   | 273  | 0.1037          | 0.4976    | 0.5368 | 0.5165 | 0.9772   |
-| No log        | 8.0   | 312  | 0.1405          | 0.4798    | 0.5632 | 0.5182 | 0.9770   |
-| No log        | 9.0   | 351  | 0.1623          | 0.52      | 0.5474 | 0.5333 | 0.9766   |
-| No log        | 10.0  | 390  | 0.1656          | 0.4906    | 0.5474 | 0.5174 | 0.9766   |
-| No log        | 11.0  | 429  | 0.1729          | 0.5098    | 0.5474 | 0.5279 | 0.9770   |
-| No log        | 12.0  | 468  | 0.1751          | 0.5073    | 0.5474 | 0.5266 | 0.9770   |
-| 0.0487        | 13.0  | 507  | 0.1758          | 0.5099    | 0.5421 | 0.5255 | 0.9770   |
-| 0.0487        | 14.0  | 546  | 0.1762          | 0.5073    | 0.5474 | 0.5266 | 0.9770   |
-| 0.0487        | 15.0  | 585  | 0.1763          | 0.5149    | 0.5474 | 0.5306 | 0.9771   |
+| No log        | 1.0   | 39   | 0.1314          | 0.3137    | 0.0842 | 0.1328 | 0.9676   |
+| No log        | 2.0   | 78   | 0.1068          | 0.2567    | 0.3526 | 0.2971 | 0.9669   |
+| No log        | 3.0   | 117  | 0.0806          | 0.3886    | 0.3579 | 0.3726 | 0.9736   |
+| No log        | 4.0   | 156  | 0.0710          | 0.4455    | 0.5158 | 0.4780 | 0.9757   |
+| No log        | 5.0   | 195  | 0.0852          | 0.5217    | 0.4421 | 0.4786 | 0.9758   |
+| No log        | 6.0   | 234  | 0.1035          | 0.5179    | 0.5316 | 0.5247 | 0.9773   |
+| No log        | 7.0   | 273  | 0.1237          | 0.5344    | 0.5316 | 0.5330 | 0.9773   |
+| No log        | 8.0   | 312  | 0.1250          | 0.5365    | 0.5421 | 0.5393 | 0.9778   |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cffa21bdc4910e4ee22bb0268d0f6af647040b823dc47d4cac3ff973f2ad801
+oid sha256:8e294f01e88217270f298d89371b0d1c01dc5f03b8438907213deda48d2c38eb
 size 33596518