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 [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2299
+- Loss: 1.6080
 
 ## Model description
 
@@ -42,13 +42,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3358        | 1.0   | 446  | 1.2299          |
+| 1.3521        | 1.0   | 446  | 1.2259          |
+| 1.4185        | 2.0   | 892  | 1.2080          |
+| 1.1195        | 3.0   | 1338 | 1.2291          |
+| 0.9606        | 4.0   | 1784 | 1.2634          |
+| 0.7691        | 5.0   | 2230 | 1.3193          |
+| 0.8449        | 6.0   | 2676 | 1.3843          |
+| 0.6701        | 7.0   | 3122 | 1.4593          |
+| 0.5451        | 8.0   | 3568 | 1.5175          |
+| 0.5712        | 9.0   | 4014 | 1.5782          |
+| 0.6186        | 10.0  | 4460 | 1.6080          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01facc0013b2b4e3b992afa648fb1ffda25e79d7be876c916b622868abfe781
+oid sha256:38d4c7e4976530645c3d96d4739e738b02537be8a868e692bd44a4659554ee1c
 size 658572432