shawgpt-ft-model2

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: 1.3751
+- Loss: 1.3191
 
 ## Model description
 
@@ -51,25 +51,24 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 4.6182        | 0.9231  | 3    | 4.0877          |
-| 4.2686        | 1.8462  | 6    | 3.7161          |
-| 3.8186        | 2.7692  | 9    | 3.3369          |
-| 2.5439        | 4.0     | 13   | 2.8860          |
-| 3.0323        | 4.9231  | 16   | 2.6111          |
-| 2.6988        | 5.8462  | 19   | 2.3843          |
-| 2.4082        | 6.7692  | 22   | 2.1636          |
-| 1.6101        | 8.0     | 26   | 1.9022          |
-| 1.9075        | 8.9231  | 29   | 1.7570          |
-| 1.7273        | 9.8462  | 32   | 1.6473          |
-| 1.6278        | 10.7692 | 35   | 1.5542          |
-| 1.1086        | 12.0    | 39   | 1.4598          |
-| 1.4381        | 12.9231 | 42   | 1.4263          |
-| 1.3783        | 13.8462 | 45   | 1.4075          |
-| 1.3758        | 14.7692 | 48   | 1.3950          |
-| 1.0266        | 16.0    | 52   | 1.3837          |
-| 1.339         | 16.9231 | 55   | 1.3786          |
-| 1.3216        | 17.8462 | 58   | 1.3758          |
-| 0.9319        | 18.4615 | 60   | 1.3751          |
+| 4.5905        | 0.9231  | 3    | 3.9593          |
+| 4.025         | 1.8462  | 6    | 3.4099          |
+| 3.4125        | 2.7692  | 9    | 2.9152          |
+| 2.1722        | 4.0     | 13   | 2.4169          |
+| 2.4691        | 4.9231  | 16   | 2.1005          |
+| 2.0548        | 5.8462  | 19   | 1.8257          |
+| 1.7281        | 6.7692  | 22   | 1.6290          |
+| 1.1606        | 8.0     | 26   | 1.4558          |
+| 1.4189        | 8.9231  | 29   | 1.4021          |
+| 1.3437        | 9.8462  | 32   | 1.3720          |
+| 1.3363        | 10.7692 | 35   | 1.3524          |
+| 0.9514        | 12.0    | 39   | 1.3344          |
+| 1.2724        | 12.9231 | 42   | 1.3275          |
+| 1.2308        | 13.8462 | 45   | 1.3237          |
+| 1.2342        | 14.7692 | 48   | 1.3222          |
+| 0.9248        | 16.0    | 52   | 1.3202          |
+| 1.2053        | 16.9231 | 55   | 1.3195          |
+| 1.1905        | 17.8462 | 58   | 1.3191          |
 
 
 ### Framework versions

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b636e3b1a288144cd16ddbadaea21976117058d914f12ce8a2812628da32ce96
-size 8397056
+oid sha256:4ce7c80b125b589e4b493b7277684e473d00b2d470730d6f9a42dcd489efc579
+size 16785792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187af95ae00ce9034fdc3235e8329911535283d1f6626d292c351356fe9ed5be
+oid sha256:d271edaaa7af6f36ea4328fc6305c1187a8960a2f15ac75f1f084647a6c86472
 size 5176