shawgpt-ft-lr2e-05-wd0.01

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3666
+- Loss: 3.8444
 
 ## Model description
 
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 4.1752        | 0.9231  | 3    | 3.7999          |
-| 4.0826        | 1.8462  | 6    | 3.7282          |
-| 4.0096        | 2.7692  | 9    | 3.6622          |
-| 2.9436        | 4.0     | 13   | 3.5842          |
-| 3.8754        | 4.9231  | 16   | 3.5330          |
-| 3.7962        | 5.8462  | 19   | 3.4884          |
-| 3.7544        | 6.7692  | 22   | 3.4507          |
-| 2.7724        | 8.0     | 26   | 3.4109          |
-| 3.6674        | 8.9231  | 29   | 3.3893          |
-| 3.6522        | 9.8462  | 32   | 3.3749          |
-| 3.643         | 10.7692 | 35   | 3.3674          |
-| 0.8397        | 11.0769 | 36   | 3.3666          |
+| 4.6427        | 0.9231  | 3    | 4.2081          |
+| 4.5689        | 1.8462  | 6    | 4.1561          |
+| 4.5192        | 2.7692  | 9    | 4.1061          |
+| 3.3371        | 4.0     | 13   | 4.0411          |
+| 4.4042        | 4.9231  | 16   | 3.9947          |
+| 4.328         | 5.8462  | 19   | 3.9542          |
+| 4.2913        | 6.7692  | 22   | 3.9199          |
+| 3.168         | 8.0     | 26   | 3.8843          |
+| 4.199         | 8.9231  | 29   | 3.8648          |
+| 4.1898        | 9.8462  | 32   | 3.8517          |
+| 4.1757        | 10.7692 | 35   | 3.8450          |
+| 0.9827        | 11.0769 | 36   | 3.8444          |
 
 
 ### Framework versions

runs/Oct22_11-05-18_99867d27916d/events.out.tfevents.1729595119.99867d27916d.882.50

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68395a9b10d18ce04f3c9ddc69de53a79bdec120d4f8eedcbaa51f0a4fe9dbe1
+size 11650

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ef22b8119ccb34b241bf673f09b847800ddcd3a12beda46637754a6f83851e
+oid sha256:26d7e6afbc156d3f61cce15c18c5e41fd91544c8caa094bf7e0c4ec3e22248c5
 size 5240