KrishGoyani/shawgpt-ft-r32-a64

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: 1.7211
+- Loss: 1.3923
 
 ## Model description
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.5898        | 0.9231 | 3    | 3.9563          |
-| 4.0312        | 1.8462 | 6    | 3.4304          |
-| 3.4545        | 2.7692 | 9    | 2.9755          |
-| 2.2386        | 4.0    | 13   | 2.5316          |
-| 2.6251        | 4.9231 | 16   | 2.2757          |
-| 2.2997        | 5.8462 | 19   | 2.0805          |
-| 2.0576        | 6.7692 | 22   | 1.9189          |
-| 1.4258        | 8.0    | 26   | 1.7748          |
-| 1.7945        | 8.9231 | 29   | 1.7268          |
-| 1.2488        | 9.2308 | 30   | 1.7211          |
+| 4.5447        | 0.9231 | 3    | 3.7620          |
+| 3.7057        | 1.8462 | 6    | 3.0314          |
+| 2.9605        | 2.7692 | 9    | 2.5033          |
+| 1.7911        | 4.0    | 13   | 1.9813          |
+| 1.9491        | 4.9231 | 16   | 1.7182          |
+| 1.6483        | 5.8462 | 19   | 1.5669          |
+| 1.459         | 6.7692 | 22   | 1.4547          |
+| 1.0513        | 8.0    | 26   | 1.4034          |
+| 1.3681        | 8.9231 | 29   | 1.3933          |
+| 0.9861        | 9.2308 | 30   | 1.3923          |
 
 
 ### Framework versions
 
 - PEFT 0.13.2
 - Transformers 4.44.2
-- Pytorch 2.5.1+cu121
+- Pytorch 2.5.0+cu121
 - Datasets 3.1.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af0e7d5a20aa0c69bf1e268c0fa814e2efe214fe9a4414098320e1c7ba20b09
-size 8397056
+oid sha256:cc1bbe2a7a27378bc854666df5e83567fd73e3b76894ce42311997acb68c3756
+size 33564136

runs/Nov06_05-41-15_ddda518461ad/events.out.tfevents.1730871692.ddda518461ad.256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f645de2d8a47e2845ad34ef8ad57ef7e578d7b6e2c38462430e389c4e9e42588
+size 10660

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b4168c2ed512bdd5a9b479544710687fb4be177998a2aac758266daf0503b6
+oid sha256:f1726f6ed84eed80d682335133a87354332aab1962ac7e4918fdd7cb004c7ebf
 size 5176