mistral-lp2-org_org_a

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2673
-- F1 Micro: 0.4375
-- F1 Macro: 0.4
-- F1 Weighted: 0.5125
+- Loss: 2.9296
+- F1 Micro: 0.1562
+- F1 Macro: 0.1554
+- F1 Weighted: 0.1752
 
 ## Model description
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
-| 2.0749        | 0.0016 | 10   | 2.2673          | 0.4375   | 0.4      | 0.5125      |
+| 3.3046        | 0.0016 | 10   | 2.9296          | 0.1562   | 0.1554   | 0.1752      |
 
 
 ### Framework versions

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10aee89c11acd02e2d287bb18da4ca404e24e3e1f7f2227d7aab3c4c9445bb03
+oid sha256:862e39f78acc0ca3c379d55ec9aba980a8c13a7a04a5219ae504a98bd6ba00c5
 size 578881968