TERRYYYZHANG/test-Llama-3.1-8B-Instruct-GPTQ-ytbcomment

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+base_model: hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4
 library_name: peft
-license: apache-2.0
+license: llama3.1
 tags:
 - generated_from_trainer
 model-index:
@@ -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 [hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7321
+- Loss: 2.0354
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.593         | 0.9231 | 3    | 3.9700          |
-| 4.0535        | 1.8462 | 6    | 3.4530          |
-| 3.4744        | 2.7692 | 9    | 2.9876          |
-| 2.2452        | 4.0    | 13   | 2.5414          |
-| 2.6304        | 4.9231 | 16   | 2.2687          |
-| 2.2902        | 5.8462 | 19   | 2.0619          |
-| 2.0316        | 6.7692 | 22   | 1.8933          |
-| 1.4235        | 8.0    | 26   | 1.7775          |
-| 1.8098        | 8.9231 | 29   | 1.7367          |
-| 1.261         | 9.2308 | 30   | 1.7321          |
+| 3.8384        | 0.9231 | 3    | 3.2747          |
+| 3.666         | 1.8462 | 6    | 3.1189          |
+| 3.4422        | 2.7692 | 9    | 2.9378          |
+| 2.3978        | 4.0    | 13   | 2.6971          |
+| 2.9756        | 4.9231 | 16   | 2.5165          |
+| 2.7288        | 5.8462 | 19   | 2.3571          |
+| 2.5339        | 6.7692 | 22   | 2.2220          |
+| 1.796         | 8.0    | 26   | 2.0908          |
+| 2.2918        | 8.9231 | 29   | 2.0411          |
+| 1.6171        | 9.2308 | 30   | 2.0354          |
 
 
 ### 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": "hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4",
   "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 sha256:8deff009cbdd5a4a3fdff767ae716b82d00499f20ac72f022b83841af006ee89
+oid sha256:e0ec4d06686828b4f1b7c8f525e1af4f23a8284ba8b444b0c67615a6578e03eb
 size 8397056

runs/Jul27_19-43-53_9d50e49a61e9/events.out.tfevents.1722109440.9d50e49a61e9.1846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528c747ad6a263ce7fa78b64624802c87ec6aea4459f04f3381dac6bcb8f15a8
+size 10636

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ee2993eebba283dbcd4d1d2259ba016be62933963f90859e54aab1d4ae3a31
+oid sha256:527132337a28f0a9c1f3aba2f66c2daa030503c08322ea957c9f616efdfe89f8
 size 5112