mistralai/mistral-instruct-generation

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4969
+- Loss: 1.4958
 
 ## Model description
 
@@ -53,17 +53,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.6666        | 0.0260 | 20   | 1.5570          |
-| 1.5509        | 0.0521 | 40   | 1.5239          |
-| 1.5707        | 0.0781 | 60   | 1.5093          |
-| 1.5722        | 0.1042 | 80   | 1.5024          |
-| 1.5602        | 0.1302 | 100  | 1.4969          |
+| 1.6146        | 0.0260 | 20   | 1.5552          |
+| 1.5344        | 0.0521 | 40   | 1.5207          |
+| 1.5492        | 0.0781 | 60   | 1.5117          |
+| 1.5122        | 0.1042 | 80   | 1.5025          |
+| 1.5222        | 0.1302 | 100  | 1.4958          |
 
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.40.2
+- PEFT 0.11.1
+- Transformers 4.41.1
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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 sha256:5da2600a0dcc2d5a7b2838b49cb83a0c02dadda5a3e7e652007661ae36b8ed1c
+oid sha256:5c135165f24e4872595fd851b199995519eb32fd2ff9a80d599dadfb0d618763
 size 27280152

runs/May23_10-21-36_adfafe14d5e3/events.out.tfevents.1716459740.adfafe14d5e3.927.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01eb2c6517cdc18143d7ea2a33090651776339b4297f91cdce8a4c8211738c30
+size 9088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413bc6e1d67a088848afdf175ac749c9f4d0ff09768e00b393021aabec09c5d4
-size 5048
+oid sha256:3b5c2f842e1e4cfebb26b3bf2db1186a93b0408b6f2d74b015075f3642dda696
+size 5112