chchen
/

Llama-3.1-8B-Instruct-PsyCourse-doc-fold1

Generated from Trainer

Model card Files Files and versions Community

chchen commited on Feb 5

Commit

87c9c94

·

verified ·

1 Parent(s): 6af4e93

Model save

Files changed (2) hide show

README.md +14 -14
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # Llama-3.1-8B-Instruct-PsyCourse-doc-fold1
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the course-doc-train-fold1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0762
 ## Model description
@@ -52,18 +52,18 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.1808        | 0.3951 | 10   | 0.1560          |
-| 0.0381        | 0.7901 | 20   | 0.1022          |
-| 0.0724        | 1.1852 | 30   | 0.0880          |
-| 0.0846        | 1.5802 | 40   | 0.0821          |
-| 0.1173        | 1.9753 | 50   | 0.0794          |
-| 0.0746        | 2.3704 | 60   | 0.0781          |
-| 0.0663        | 2.7654 | 70   | 0.0775          |
-| 0.0749        | 3.1605 | 80   | 0.0765          |
-| 0.0336        | 3.5556 | 90   | 0.0765          |
-| 0.0701        | 3.9506 | 100  | 0.0762          |
-| 0.0415        | 4.3457 | 110  | 0.0763          |
-| 0.0748        | 4.7407 | 120  | 0.0763          |
 ### Framework versions

 # Llama-3.1-8B-Instruct-PsyCourse-doc-fold1
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0187
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.0868        | 0.3951 | 10   | 0.0878          |
+| 0.0371        | 0.7901 | 20   | 0.0388          |
+| 0.0205        | 1.1852 | 30   | 0.0277          |
+| 0.0215        | 1.5802 | 40   | 0.0236          |
+| 0.0153        | 1.9753 | 50   | 0.0214          |
+| 0.0168        | 2.3704 | 60   | 0.0207          |
+| 0.0153        | 2.7654 | 70   | 0.0198          |
+| 0.0123        | 3.1605 | 80   | 0.0193          |
+| 0.011         | 3.5556 | 90   | 0.0192          |
+| 0.0117        | 3.9506 | 100  | 0.0187          |
+| 0.011         | 4.3457 | 110  | 0.0188          |
+| 0.0153        | 4.7407 | 120  | 0.0187          |
 ### Framework versions

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6b114c15e24b4641427dc1a8cfd2d9bbaae0416ae44c2bcfe20fe3ef403c78
 size 83945296

 version https://git-lfs.github.com/spec/v1
+oid sha256:9f8c3b498a3a590826dda97ff0acbdce7cf0cbe348a43c5aae4d81bbafb15243
 size 83945296