thomnis/Mistral-7B-Instruct-v0.2-GPTQ-LoRA-shawgpt-ft

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3500
+- Loss: 1.3524
 
 ## Model description
 
@@ -52,15 +52,15 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 4.586         | 0.9231 | 3    | 4.0840          |
-| 4.5009        | 1.8462 | 6    | 3.6764          |
-| 3.4299        | 2.7692 | 9    | 2.6573          |
-| 1.7931        | 4.0    | 13   | 1.7660          |
-| 1.6827        | 4.9231 | 16   | 1.4734          |
-| 1.4268        | 5.8462 | 19   | 1.4157          |
-| 1.3165        | 6.7692 | 22   | 1.3744          |
-| 0.9644        | 8.0    | 26   | 1.3551          |
-| 1.2523        | 8.9231 | 29   | 1.3501          |
-| 0.8941        | 9.2308 | 30   | 1.3500          |
+| 4.5003        | 1.8462 | 6    | 3.6717          |
+| 3.4228        | 2.7692 | 9    | 2.6501          |
+| 1.7833        | 4.0    | 13   | 1.7598          |
+| 1.68          | 4.9231 | 16   | 1.4736          |
+| 1.427         | 5.8462 | 19   | 1.4181          |
+| 1.3196        | 6.7692 | 22   | 1.3783          |
+| 0.9651        | 8.0    | 26   | 1.3563          |
+| 1.245         | 8.9231 | 29   | 1.3527          |
+| 0.8858        | 9.2308 | 30   | 1.3524          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
-    "k_proj"
+    "k_proj",
+    "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 sha256:93e2ef5448ca2d3af24af8e4144167a276e9d0e6e674af5d24ca79ebfbbf4462
-size 37777792
+oid sha256:4b69db1e9bb94fa449f1d23526ce73cc9bcac77c379dcec4de4b0ee30c9f1905
+size 37774528

runs/Oct20_19-09-10_eb53f72e69c6/events.out.tfevents.1729451354.eb53f72e69c6.893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aab0d0680ff719b02e2c83edb554fdc6c4cb06a2472d32846f92a32ad99cf8
+size 10495

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d6ac5e5d3382dcfe169c3f680cefb1aa2acc0b8137ab1dba36c2da5013d76c
+oid sha256:ba0c5bd7e20cb5ad26a95f0d751c5e5215dec8d3f70c5abaf23f1e53b702ad05
 size 5176