your-username/mistral_finetuned

README.md

@@ -18,7 +18,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3764
+- Loss: 0.3806
 
 ## Model description
 
@@ -44,19 +44,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4035        | 1.0   | 1915 | 0.3892          |
-| 0.3797        | 2.0   | 3830 | 0.3764          |
+| 0.3872        | 1.0   | 4174 | 0.3806          |
 
 
 ### Framework versions
 
-- PEFT 0.10.1.dev0
+- PEFT 0.11.1.dev0
 - Transformers 4.40.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1

adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "up_proj",
-    "k_proj",
+    "v_proj",
+    "q_proj",
     "lm_head",
+    "gate_proj",
     "down_proj",
-    "v_proj",
-    "gate_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215e942ac19cefaf6701ceab7ba55d24d996aaee9ea33d573e9b0bfcfdb70f54
+oid sha256:e3191c437b593a85b2422e00b5cd458c8a06e0ba0ca9d7b0c56fed5935956783
 size 694431312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b778b3ecd8a3450648bd496eb386d5f4fc0b3c5738e9c589eae6a7595f643565
+oid sha256:213abb780a160958fe966296f84c0c08b32c4a88dbbd320063c02f2f9d92106f
 size 4984