End of training

README.md

@@ -12,19 +12,23 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Mistral Sentimental Analysis
+# mistral_retrained
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the IMDb dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1688
 
-This fine-tuned model can classify a piece of text as a positive or negative review. 
-It achieves an accuracy of 96.4% for 2500 test cases. This test cases were inside IMDb dataset. 
+## Model description
 
-## Training and evaluation data
+More information needed
+
+## Intended uses & limitations
 
-The dataset used for training only had 900 cases from the training part of the original dataset, so that the training phase did not take too much time. 
-It is important to mention that the data for train is totally balanced (450 positive reviews, 450 negative reviews).
+More information needed
+
+## Training and evaluation data
 
-The evaluation data is just 100 different cases from the training part of the original dataset.
+More information needed
 
 ## Training procedure
 
@@ -47,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.0486        | 1.0   | 225  | 2.0695          |
-| 1.9664        | 2.0   | 450  | 2.0785          |
-| 1.8297        | 3.0   | 675  | 2.1041          |
-| 1.7339        | 4.0   | 900  | 2.1275          |
+| 2.0202        | 1.0   | 70   | 2.1164          |
+| 1.9788        | 2.0   | 140  | 2.1238          |
+| 1.8819        | 3.0   | 210  | 2.1551          |
+| 1.8268        | 4.0   | 280  | 2.1688          |
 
 
 ### 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"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e299129d926d9b10bad064cca01381b33a8e89b52bd056a54b3bb52e44dc63
+oid sha256:ae8a8a6c29f771d7d58d1673e2136a59c9e69a7b28fc2d3de452892297fa25c4
 size 109069176

runs/May14_15-18-56_089a828f3b46/events.out.tfevents.1715699938.089a828f3b46.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8e6713bed17a779948fe96c4cb5757c944eca4e6d27eeec3a60e307a67b264
+size 7923

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1983b11b062438a8760645fe8c49fd7b2f07a64593145a95d076d7f37041da
+oid sha256:a56b63cbcad85f36657bee5b1ffe7251b38d0ccc69203d3436679ad5f7deda3d
 size 4283