harshi321/Mistral-Alpaca-Finetuned

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
 library_name: peft
 license: apache-2.0
 tags:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # shawgpt-ft
 
-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.
+This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8592
+- Loss: 1.8143
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.5954        | 0.9231 | 3    | 3.9711          |
-| 4.0583        | 1.8462 | 6    | 3.4510          |
-| 3.4858        | 2.7692 | 9    | 3.0011          |
-| 2.2701        | 4.0    | 13   | 2.5653          |
-| 2.6726        | 4.9231 | 16   | 2.3082          |
-| 2.3586        | 5.8462 | 19   | 2.1198          |
-| 2.1183        | 6.7692 | 22   | 1.9684          |
-| 1.501         | 8.0    | 26   | 1.9064          |
-| 1.9618        | 8.9231 | 29   | 1.8704          |
-| 1.3647        | 9.2308 | 30   | 1.8592          |
+| 4.0111        | 0.9231 | 3    | 3.4383          |
+| 3.7197        | 1.8462 | 6    | 3.1542          |
+| 3.3433        | 2.7692 | 9    | 2.8819          |
+| 2.2325        | 4.0    | 13   | 2.5118          |
+| 2.6351        | 4.9231 | 16   | 2.2513          |
+| 2.298         | 5.8462 | 19   | 2.0509          |
+| 2.0805        | 6.7692 | 22   | 1.9310          |
+| 1.4903        | 8.0    | 26   | 1.8460          |
+| 1.9251        | 8.9231 | 29   | 1.8175          |
+| 1.3554        | 9.2308 | 30   | 1.8143          |
 
 
 ### Framework versions

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": "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccada718f9b3cc01d8c69735c5a09ada71834fa427fc68d26a936a13a6576ac
+oid sha256:820a2ef47d2562b0b0c45e3ce97a194b3bad64b7686431ceb1119aebf43d2725
 size 8397056

runs/Jul15_15-07-12_9fbad8186d4b/events.out.tfevents.1721056052.9fbad8186d4b.325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36811e516a9e6b276b740cd269b0c088e61fea7145f5904298c7b20314faa92a
+size 10530

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efb011e26ece0445eb0ca05fd02773f685b3c771e741892529f8e136ccdb110
+oid sha256:06dcece5e2eeb3fb00559ac20101f23babf359364ba406783ab3b1e39cbeb0ef
 size 5112