Vasanth/openhermes-mistral-dpo-gptq

README.md

@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0134
-- Rewards/chosen: 7.8160
-- Rewards/rejected: 8.7194
-- Rewards/accuracies: 0.375
-- Rewards/margins: -0.9034
-- Logps/rejected: -146.7816
-- Logps/chosen: -235.0709
-- Logits/rejected: -2.1916
-- Logits/chosen: -2.6628
+- Loss: 0.6557
+- Rewards/chosen: -0.0382
+- Rewards/rejected: -0.1408
+- Rewards/accuracies: 0.75
+- Rewards/margins: 0.1027
+- Logps/rejected: -129.7875
+- Logps/chosen: -131.0592
+- Logits/rejected: -2.0563
+- Logits/chosen: -2.3077
 
 ## Model description
 
@@ -59,11 +59,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.6763        | 0.005 | 10   | 0.7302          | 0.0677         | 0.1589           | 0.1875             | -0.0912         | -232.3873      | -312.5545    | -2.1541         | -2.6006       |
-| 0.7076        | 0.01  | 20   | 0.7628          | 0.0161         | 0.1965           | 0.25               | -0.1804         | -232.0109      | -313.0701    | -2.1614         | -2.6040       |
-| 0.6925        | 0.015 | 30   | 0.7999          | 0.1974         | 0.5152           | 0.25               | -0.3179         | -228.8234      | -311.2576    | -2.1717         | -2.6192       |
-| 0.6966        | 0.02  | 40   | 0.8630          | 0.7996         | 1.2680           | 0.3125             | -0.4684         | -221.2960      | -305.2355    | -2.1636         | -2.6203       |
-| 0.6764        | 0.025 | 50   | 1.0134          | 7.8160         | 8.7194           | 0.375              | -0.9034         | -146.7816      | -235.0709    | -2.1916         | -2.6628       |
+| 0.6769        | 0.005 | 10   | 0.6888          | -0.0796        | -0.0900          | 0.4375             | 0.0104          | -129.2791      | -131.4733    | -2.0870         | -2.3346       |
+| 0.713         | 0.01  | 20   | 0.7072          | -0.1185        | -0.0997          | 0.4375             | -0.0188         | -129.3760      | -131.8626    | -2.0821         | -2.3307       |
+| 0.7127        | 0.015 | 30   | 0.6886          | 0.0301         | 0.0180           | 0.5                | 0.0121          | -128.1994      | -130.3766    | -2.0743         | -2.3175       |
+| 0.6974        | 0.02  | 40   | 0.6637          | 0.0450         | -0.0273          | 0.5                | 0.0722          | -128.6517      | -130.2277    | -2.0686         | -2.3128       |
+| 0.6725        | 0.025 | 50   | 0.6557          | -0.0382        | -0.1408          | 0.75               | 0.1027          | -129.7875      | -131.0592    | -2.0563         | -2.3077       |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70dcac79ca16462c76212dd70441264c78fe397b2ab3ac49f7641c622a0f58a6
+oid sha256:c3bae9155c2d0d65d1239a10c829c15d6333e2ce877e07fc43d4a4c6f2ae214e
 size 13648432

runs/Jun10_14-42-31_e842a6e3edf7/events.out.tfevents.1718030584.e842a6e3edf7.217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a954393f86c23e7c023fda2b5d4e7a06dc3b50576055a6ace3585d820e68edcc
+size 14251

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad7570d800cf828b868d05977fbe7797c9f977bc019be609815d44c37d27427
+oid sha256:2bdeac99f439d4313c7dc854de7c9b45af15b8eac9cc37e4a7c7fb81f1f5bbc5
 size 5307