End of training

README.md

@@ -1,8 +1,9 @@
 ---
+license: mit
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: cocorooxinnn/eu_based_model
+base_model: facebook/bart-large-mnli
 metrics:
 - f1
 - precision
@@ -18,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eu_adapter01
 
-This model is a fine-tuned version of [cocorooxinnn/eu_based_model](https://huggingface.co/cocorooxinnn/eu_based_model) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6118
-- F1: 0.7786
-- Precision: 0.8226
-- Recall: 0.7391
-- Accuracy: 0.8067
+- Loss: 0.5908
+- F1: 0.8489
+- Precision: 0.8429
+- Recall: 0.8551
+- Accuracy: 0.86
 
 ## Model description
 
@@ -56,9 +57,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Precision | Recall | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:--------:|
-| 0.6221        | 0.625 | 10   | 0.6185          | 0.7972 | 0.7703    | 0.8261 | 0.8067   |
-| 0.5926        | 1.25  | 20   | 0.6078          | 0.8194 | 0.7867    | 0.8551 | 0.8267   |
-| 0.5867        | 1.875 | 30   | 0.6118          | 0.7786 | 0.8226    | 0.7391 | 0.8067   |
+| 0.5685        | 0.625 | 10   | 0.5841          | 0.8397 | 0.8871    | 0.7971 | 0.86     |
+| 0.5716        | 1.25  | 20   | 0.5964          | 0.8493 | 0.8052    | 0.8986 | 0.8533   |
+| 0.5815        | 1.875 | 30   | 0.5908          | 0.8489 | 0.8429    | 0.8551 | 0.86     |
 
 
 ### Framework versions

adapter_config.json

@@ -25,9 +25,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "q_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee987cc504e24b9e989f8dbf7250a97d4665d16e90628406878988f496ef0071
+oid sha256:5cb5f5ddbe1a46bede9d70d692e27b604a6cae34fdd61c5e0dad767d98e797b1
 size 29715788