End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4297
+- Loss: 2.1425
 
 ## Model description
 
@@ -33,7 +33,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.6075        | 0.2   | 13   | 2.5622          |
-| 2.5296        | 0.4   | 26   | 2.4880          |
-| 2.4669        | 0.6   | 39   | 2.4456          |
-| 2.4483        | 0.8   | 52   | 2.4297          |
+| 2.2348        | 0.2   | 13   | 2.3243          |
+| 2.1848        | 0.4   | 26   | 2.2166          |
+| 2.2501        | 0.6   | 39   | 2.1606          |
+| 2.2727        | 0.8   | 52   | 2.1425          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2552ec9e722d62a6b0d234fe424d5b32123c62258320f555537ead8da188d149
+oid sha256:90d90d672ab33e4fd5ed637a5545318d655334def584db4f73be6d14f45129a6
 size 16794200

runs/Dec01_12-59-24_7f9337b2413a/events.out.tfevents.1701435570.7f9337b2413a.183.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f46426601ec1f2f536c9d88f334b8958eb6102026837d2ed7efc669c3f198e4
+size 15905

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb3c082338556ea9eb14f80d3b2b8e77f38617f3d4cb04da15dbf94f833d32b
+oid sha256:deb1b020e419fe2bfe59babcdcecc69adff48514ea87307d37ed763d8a2e2d9e
 size 4600