adarsh12x/mistral_7b_samantha_

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 samantha-data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2230
+- Loss: 1.2177
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8132        | 0.01  | 10   | 1.5843          |
-| 1.1784        | 0.02  | 20   | 1.3875          |
-| 1.0916        | 0.02  | 30   | 1.3269          |
-| 1.0672        | 0.03  | 40   | 1.2654          |
-| 0.9785        | 0.04  | 50   | 1.2621          |
-| 1.0143        | 0.05  | 60   | 1.2549          |
-| 0.9283        | 0.05  | 70   | 1.2480          |
-| 1.0852        | 0.06  | 80   | 1.2411          |
-| 0.9801        | 0.07  | 90   | 1.2305          |
-| 1.0415        | 0.08  | 100  | 1.2230          |
+| 1.8256        | 0.01  | 10   | 1.6091          |
+| 1.1803        | 0.02  | 20   | 1.3865          |
+| 1.0851        | 0.02  | 30   | 1.3218          |
+| 1.061         | 0.03  | 40   | 1.2639          |
+| 0.9776        | 0.04  | 50   | 1.2600          |
+| 1.0178        | 0.05  | 60   | 1.2484          |
+| 0.9253        | 0.05  | 70   | 1.2435          |
+| 1.0814        | 0.06  | 80   | 1.2363          |
+| 0.9787        | 0.07  | 90   | 1.2307          |
+| 1.0406        | 0.08  | 100  | 1.2177          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25dac2423cd4dbf28fb4155ebc82b7d7d6e5c65164fdf88473dcb09cb5003816
+oid sha256:5b142edadcebee7cacc9b04888504c24f2ca425544899aefa3ab1aebb0d6d832
 size 4920