End of training

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4414
-- Model Preparation Time: 0.0045
+- Loss: 0.4550
+- Model Preparation Time: 0.0066
 - Accuracy: 0.8313
-- F1 Macro: 0.8354
+- F1 Macro: 0.8378
 
 ## Model description
 
@@ -56,17 +56,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 Macro |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:--------:|:--------:|
-| 0.9162        | 1.0   | 368  | 0.8379          | 0.0045                 | 0.6361   | 0.6334   |
-| 0.5201        | 2.0   | 736  | 0.5242          | 0.0045                 | 0.7782   | 0.7849   |
-| 0.3988        | 3.0   | 1104 | 0.4936          | 0.0045                 | 0.7993   | 0.8024   |
-| 0.3288        | 4.0   | 1472 | 0.4774          | 0.0045                 | 0.8007   | 0.8084   |
-| 0.3602        | 5.0   | 1840 | 0.4858          | 0.0045                 | 0.8034   | 0.8103   |
+| 0.5588        | 1.0   | 368  | 0.5780          | 0.0066                 | 0.7503   | 0.7548   |
+| 0.4576        | 2.0   | 736  | 0.4660          | 0.0066                 | 0.8048   | 0.8131   |
+| 0.2993        | 3.0   | 1104 | 0.4513          | 0.0066                 | 0.8177   | 0.8253   |
+| 0.1717        | 4.0   | 1472 | 0.5759          | 0.0066                 | 0.8020   | 0.8123   |
+| 0.1154        | 5.0   | 1840 | 0.6625          | 0.0066                 | 0.8136   | 0.8214   |
 
 
 ### Framework versions
 
 - PEFT 0.14.0
-- Transformers 4.48.2
+- Transformers 4.49.0
 - Pytorch 2.5.1+cu124
-- Datasets 3.2.0
+- Datasets 3.3.1
 - Tokenizers 0.21.0

adapter_config.json

@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -26,10 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
     "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2aedb4a849cb0cdfe72064eef4e3fd9ac7cc5c4f2212eda363357d9a2d31e8
-size 36779480
+oid sha256:39d49fde721f4ce82ef56835c3a74559bc9cad244bb81df60863a3bf7506474d
+size 97356792