Upload 13 files

README.md

@@ -9,13 +9,28 @@ base_model: intfloat/multilingual-e5-small
 metrics:
 - accuracy
 widget:
-- text: 'query: Baiklah, kita cakap lagi nanti, Mark. Selamat hari!'
-- text: 'query: Tôi xin lỗi nhưng tôi phải đi'
-- text: 'query: 次回行くときは、私を連れて行ってください。もっと自然の中で活動したいと思っています。'
-- text: 'query: Entschuldigung, ich muss jetzt gehen.'
-- text: 'query: Buenos días, ¿cómo están ustedes?'
+- text: 'query: Interessant. Hast du das schon mal ausprobiert?'
+- text: 'query: はい、持っていますよ。すぐにメールで送りますね。'
+- text: 'query: Va bene ci sentiamo dopo Marco buona giornata'
+- text: 'query: Ζητώ συγγνώμη, πρέπει να αποχωρήσω τώρα.'
+- text: 'query: Guten Morgen, Maria! Hast du die Präsentation für das Meeting heute
+    fertig?'
 pipeline_tag: text-classification
 inference: true
+model-index:
+- name: SetFit with intfloat/multilingual-e5-small
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.9333333333333333
+      name: Accuracy
 ---
 
 # SetFit with intfloat/multilingual-e5-small
@@ -46,10 +61,17 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                                                                         |
-|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 0     | <ul><li>'query: Értem. Mit csinálunk most?'</li><li>'query: Ola Luca, que tal? Rematache o traballo?'</li><li>'query: Lijepo je. Hvala.'</li></ul>               |
-| 1     | <ul><li>'query: Жөнейін, кейін кездесеміз.'</li><li>'query: Така, ќе се видиме повторно.'</li><li>'query: ठीक है बाद में बात करते हैं मार्क अच्छा दिन'</li></ul> |
+| Label | Examples                                                                                                                                                                                            |
+|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>'query: สวัสดีค่ะ วันนี้เป็นอย่างไรบ้าง?'</li><li>'query: Jag förstår. Vad tycker du att vi ska göra nu?'</li><li>'query: Hej, wszystko w porządku. Właśnie dostałam nową pracę.'</li></ul> |
+| 1     | <ul><li>'query: Чудесно, доскоро!'</li><li>'query: Mama mă cheamă, trebuie să mă întorc acasă, pa.'</li><li>'query: Perdó, ja he de marxar.'</li></ul>                                              |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.9333   |
 
 ## Uses
 
@@ -69,7 +91,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("query: Tôi xin lỗi nhưng tôi phải đi")
+preds = model("query: はい、持っていますよ。すぐにメールで送りますね。")
 ```
 
 <!--
@@ -101,65 +123,54 @@ preds = model("query: Tôi xin lỗi nhưng tôi phải đi")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 2   | 7.2168 | 25  |
+| Word count   | 2   | 7.3663 | 21  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| 0     | 346                   |
-| 1     | 346                   |
+| 0     | 286                   |
+| 1     | 290                   |
 
 ### Training Hyperparameters
 - batch_size: (16, 2)
 - num_epochs: (1, 16)
-- max_steps: 1400
+- max_steps: 900
 - sampling_strategy: undersampling
 - body_learning_rate: (1e-05, 1e-05)
 - head_learning_rate: 0.001
 - loss: CosineSimilarityLoss
 - distance_metric: cosine_distance
-- margin: 0.05
+- margin: 0.1
 - end_to_end: False
 - use_amp: False
 - warmup_proportion: 0.1
 - seed: 42
 - run_name: multilingual-e5-small
 - eval_max_steps: -1
-- load_best_model_at_end: True
+- load_best_model_at_end: False
 
 ### Training Results
-| Epoch      | Step     | Training Loss | Validation Loss |
-|:----------:|:--------:|:-------------:|:---------------:|
-| 0.0004     | 1        | 0.3607        | -               |
-| 0.0179     | 50       | 0.3254        | -               |
-| 0.0357     | 100      | 0.2303        | 0.2049          |
-| 0.0536     | 150      | 0.106         | -               |
-| 0.0714     | 200      | 0.1294        | 0.0748          |
-| 0.0893     | 250      | 0.087         | -               |
-| 0.1071     | 300      | 0.0732        | 0.0787          |
-| 0.1250     | 350      | 0.0019        | -               |
-| 0.1428     | 400      | 0.0027        | 0.1072          |
-| 0.1607     | 450      | 0.0015        | -               |
-| 0.1785     | 500      | 0.0008        | 0.0999          |
-| 0.1964     | 550      | 0.0016        | -               |
-| 0.2142     | 600      | 0.0004        | 0.1215          |
-| 0.2321     | 650      | 0.0012        | -               |
-| 0.2499     | 700      | 0.0008        | 0.1267          |
-| 0.2678     | 750      | 0.0005        | -               |
-| 0.2856     | 800      | 0.0003        | 0.1216          |
-| 0.3035     | 850      | 0.0003        | -               |
-| 0.3213     | 900      | 0.0004        | 0.1142          |
-| 0.3392     | 950      | 0.0004        | -               |
-| **0.3570** | **1000** | **0.0004**    | **0.0616**      |
-| 0.3749     | 1050     | 0.0002        | -               |
-| 0.3927     | 1100     | 0.0004        | 0.0946          |
-| 0.4106     | 1150     | 0.0002        | -               |
-| 0.4284     | 1200     | 0.0003        | 0.1091          |
-| 0.4463     | 1250     | 0.0002        | -               |
-| 0.4641     | 1300     | 0.0003        | 0.1141          |
-| 0.4820     | 1350     | 0.0004        | -               |
-| 0.4998     | 1400     | 0.0002        | 0.1209          |
-
-* The bold row denotes the saved checkpoint.
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0006 | 1    | 0.3683        | -               |
+| 0.0278 | 50   | 0.2855        | -               |
+| 0.0555 | 100  | 0.1691        | 0.1598          |
+| 0.0833 | 150  | 0.0339        | -               |
+| 0.1110 | 200  | 0.0134        | 0.0745          |
+| 0.1388 | 250  | 0.0309        | -               |
+| 0.1666 | 300  | 0.0076        | 0.0344          |
+| 0.1943 | 350  | 0.0023        | -               |
+| 0.2221 | 400  | 0.0012        | 0.0849          |
+| 0.2499 | 450  | 0.0007        | -               |
+| 0.2776 | 500  | 0.0008        | 0.0932          |
+| 0.3054 | 550  | 0.0005        | -               |
+| 0.3331 | 600  | 0.0005        | 0.0805          |
+| 0.3609 | 650  | 0.0004        | -               |
+| 0.3887 | 700  | 0.0006        | 0.0951          |
+| 0.4164 | 750  | 0.0006        | -               |
+| 0.4442 | 800  | 0.0016        | 0.0983          |
+| 0.4720 | 850  | 0.0008        | -               |
+| 0.4997 | 900  | 0.0005        | 0.092           |
+
 ### Framework Versions
 - Python: 3.10.11
 - SetFit: 1.0.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "checkpoints/step_1000",
+  "_name_or_path": "intfloat/multilingual-e5-small",
   "architectures": [
     "BertModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c89f801f10bb9afe5e4f308a41a0d7492b8725340318de1847eec8f6b84cf1
+oid sha256:ee129ffbb039e468d217b93891bd4d7fb59fc6cb127dba8a76b3a0c9ca261203
 size 470637416

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b054fef0d715653a0dba9374d17ce2d5fa1a3fb6560f2768740890da80a0321
+oid sha256:df99fc1c0b63c98daf8f7d2ba317bcf6e7a91658fd8942d6f7028ae034ecb4d0
 size 4608

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ce1a4600af70b33f5a7fba12dbb41a504d3c08737c9b26b5e7fd6e437a9a23
-size 17083087
+oid sha256:45b6ee00bc5023ac454b82c372ebe14b27866fa471b6dbb0d24e09b12909a1f4
+size 17083075

tokenizer_config.json

@@ -46,17 +46,10 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }