Add SetFit model

README.md

@@ -43,6 +43,20 @@ widget:
 pipeline_tag: text-classification
 inference: true
 base_model: ibaucells/RoBERTa-ca-CaWikiTC
+model-index:
+- name: SetFit with ibaucells/RoBERTa-ca-CaWikiTC
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.4
+      name: Accuracy
 ---
 
 # SetFit with ibaucells/RoBERTa-ca-CaWikiTC
@@ -93,6 +107,13 @@ The model has been trained using an efficient few-shot learning technique that i
 | 15    | <ul><li>'Aquest article tracta sobre Tramitacions'</li><li>'Aquest article tracta sobre Tramitacions'</li><li>'Aquest article tracta sobre Tramitacions'</li></ul>             |
 | 16    | <ul><li>'Aquest article tracta sobre Urbanisme'</li><li>'Aquest article tracta sobre Urbanisme'</li><li>'Aquest article tracta sobre Urbanisme'</li></ul>                      |
 
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.4      |
+
 ## Uses
 
 ### Direct Use for Inference
@@ -166,7 +187,7 @@ preds = model("Mateicula estiu de petits : Bona tarda, Un cop adjudicada la pla
 | 16    | 8                     |
 
 ### Training Hyperparameters
-- batch_size: (30, 30)
+- batch_size: (8, 8)
 - num_epochs: (1, 1)
 - max_steps: -1
 - sampling_strategy: oversampling
@@ -183,21 +204,55 @@ preds = model("Mateicula estiu de petits : Bona tarda, Un cop adjudicada la pla
 - load_best_model_at_end: True
 
 ### Training Results
-| Epoch  | Step | Training Loss | Validation Loss |
-|:------:|:----:|:-------------:|:---------------:|
-| 0.0017 | 1    | 0.3501        | -               |
-| 0.0861 | 50   | 0.2833        | -               |
-| 0.1721 | 100  | 0.0906        | -               |
-| 0.2582 | 150  | 0.0673        | -               |
-| 0.3442 | 200  | 0.0084        | -               |
-| 0.4303 | 250  | 0.0025        | -               |
-| 0.5164 | 300  | 0.0016        | -               |
-| 0.6024 | 350  | 0.0013        | -               |
-| 0.6885 | 400  | 0.0014        | -               |
-| 0.7745 | 450  | 0.0015        | -               |
-| 0.8606 | 500  | 0.0013        | -               |
-| 0.9466 | 550  | 0.001         | -               |
-
+| Epoch   | Step     | Training Loss | Validation Loss |
+|:-------:|:--------:|:-------------:|:---------------:|
+| 0.0005  | 1        | 0.4258        | -               |
+| 0.0230  | 50       | 0.201         | -               |
+| 0.0460  | 100      | 0.194         | -               |
+| 0.0689  | 150      | 0.237         | -               |
+| 0.0919  | 200      | 0.1165        | -               |
+| 0.1149  | 250      | 0.0622        | -               |
+| 0.1379  | 300      | 0.0904        | -               |
+| 0.1608  | 350      | 0.0045        | -               |
+| 0.1838  | 400      | 0.0188        | -               |
+| 0.2068  | 450      | 0.0025        | -               |
+| 0.2298  | 500      | 0.0017        | -               |
+| 0.2528  | 550      | 0.0014        | -               |
+| 0.2757  | 600      | 0.0013        | -               |
+| 0.2987  | 650      | 0.0014        | -               |
+| 0.3217  | 700      | 0.0027        | -               |
+| 0.3447  | 750      | 0.0014        | -               |
+| 0.3676  | 800      | 0.0007        | -               |
+| 0.3906  | 850      | 0.0014        | -               |
+| 0.4136  | 900      | 0.0011        | -               |
+| 0.4366  | 950      | 0.0011        | -               |
+| 0.4596  | 1000     | 0.0017        | -               |
+| 0.4825  | 1050     | 0.0007        | -               |
+| 0.5055  | 1100     | 0.001         | -               |
+| 0.5285  | 1150     | 0.0008        | -               |
+| 0.5515  | 1200     | 0.0005        | -               |
+| 0.5744  | 1250     | 0.0009        | -               |
+| 0.5974  | 1300     | 0.0008        | -               |
+| 0.6204  | 1350     | 0.0013        | -               |
+| 0.6434  | 1400     | 0.0008        | -               |
+| 0.6664  | 1450     | 0.001         | -               |
+| 0.6893  | 1500     | 0.0006        | -               |
+| 0.7123  | 1550     | 0.0008        | -               |
+| 0.7353  | 1600     | 0.0006        | -               |
+| 0.7583  | 1650     | 0.0005        | -               |
+| 0.7812  | 1700     | 0.0006        | -               |
+| 0.8042  | 1750     | 0.0006        | -               |
+| 0.8272  | 1800     | 0.001         | -               |
+| 0.8502  | 1850     | 0.0005        | -               |
+| 0.8732  | 1900     | 0.0007        | -               |
+| 0.8961  | 1950     | 0.0009        | -               |
+| 0.9191  | 2000     | 0.0005        | -               |
+| 0.9421  | 2050     | 0.0005        | -               |
+| 0.9651  | 2100     | 0.0005        | -               |
+| 0.9881  | 2150     | 0.0005        | -               |
+| **1.0** | **2176** | **-**         | **0.2021**      |
+
+* The bold row denotes the saved checkpoint.
 ### Framework Versions
 - Python: 3.10.12
 - SetFit: 1.0.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ibaucells/RoBERTa-ca-CaWikiTC",
+  "_name_or_path": "checkpoints/step_2176",
   "architectures": [
     "RobertaModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bbffd44a7df2a8ee4d00f4e36559e636750008b731e5dbc67ff2a3e9d09d40
+oid sha256:0705118e8450af3950ee9f0192935809108aaf086055201096c95de80f39e029
 size 498595688

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a2349eb3f96eb70d9185b2f02af4ffabe28566b0bbeda0ad56312e9e6879cb
-size 324
+oid sha256:475fb90c532ccaaa01aed0d52af3a6f806107706ac1aebd375915940a35af9be
+size 105567