vignesh2404/vignesh-gpt

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: openai-community/gpt2
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
 library_name: peft
-license: mit
+license: apache-2.0
 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 [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+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: 4.0598
+- Loss: 0.5838
 
 ## Model description
 
@@ -49,18 +49,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 5.1312        | 0.9231 | 3    | 4.3328          |
-| 5.0633        | 1.8462 | 6    | 4.2915          |
-| 4.9802        | 2.7692 | 9    | 4.2487          |
-| 3.7123        | 4.0    | 13   | 4.1952          |
-| 4.8599        | 4.9231 | 16   | 4.1598          |
-| 4.8022        | 5.8462 | 19   | 4.1289          |
-| 4.7692        | 6.7692 | 22   | 4.1004          |
-| 3.5131        | 8.0    | 26   | 4.0711          |
-| 4.6584        | 8.9231 | 29   | 4.0618          |
-| 3.1781        | 9.2308 | 30   | 4.0598          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3788        | 1.0   | 134  | 1.1852          |
+| 1.1719        | 2.0   | 268  | 1.0125          |
+| 1.0327        | 3.0   | 402  | 0.8912          |
+| 0.9163        | 4.0   | 536  | 0.8010          |
+| 0.8256        | 5.0   | 670  | 0.7345          |
+| 0.7605        | 6.0   | 804  | 0.6839          |
+| 0.7048        | 7.0   | 938  | 0.6426          |
+| 0.6641        | 8.0   | 1072 | 0.6137          |
+| 0.636         | 9.0   | 1206 | 0.5929          |
+| 0.6089        | 10.0  | 1340 | 0.5838          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "openai-community/gpt2",
+  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,7 +20,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "attn.c_attn"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590fa2da4719180f2de16cda5402359a2a8ec3ff3a139f2b2f032f35c5979e63
-size 1182680
+oid sha256:3e8d09e37fdeb2c2b9f4db2f0643a1036047a6ee27f9574b050c9a7c6994f903
+size 8397056

runs/Dec03_18-09-26_decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC/events.out.tfevents.1733229566.decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC.242060.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276157a165ccf026d86163463c8b7a37b464a41ecb7c0fcefd8bb7b0cad59e96
+size 6098

runs/Dec03_18-36-24_decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC/events.out.tfevents.1733231184.decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC.242060.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbebf2f3b40202618f6e67169efeb49bf78eaf61f95c461e2b92bc219ef8258
+size 6098

runs/Dec03_18-59-17_decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC/events.out.tfevents.1733232557.decoders-HP-Z2-Tower-G9-Workstation-Desktop-PC.242060.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bb36c1fb4f20f7a12d3d2af8c7cc0ada4817ab25b881678f3625eba9b8749d
+size 10790

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2256458ad5ec8e24d39ae9f039a77d8aa55c4c5215004282c6a65db2f7c5f006
+oid sha256:6ef38971a5fc9931b2a8b9b8cf9b3388cf9820d5320ad94a817549f75d39f1f8
 size 5240