Add SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 384,
+  "word_embedding_dimension": 768,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

README.md

@@ -5,7 +5,7 @@ tags:
 - sentence-transformers
 - text-classification
 - generated_from_setfit_trainer
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: sentence-transformers/all-mpnet-base-v2
 metrics:
 - accuracy
 widget:
@@ -18,7 +18,7 @@ widget:
 pipeline_tag: text-classification
 inference: false
 model-index:
-- name: SetFit with sentence-transformers/all-MiniLM-L6-v2
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
   results:
   - task:
       type: text-classification
@@ -29,13 +29,13 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.2857142857142857
+      value: 0.42857142857142855
       name: Accuracy
 ---
 
-# SetFit with sentence-transformers/all-MiniLM-L6-v2
+# SetFit with sentence-transformers/all-mpnet-base-v2
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) as the Sentence Transformer embedding model. A MultiOutputClassifier instance is used for classification.
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) as the Sentence Transformer embedding model. A MultiOutputClassifier instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -46,9 +46,9 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
+- **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
 - **Classification head:** a MultiOutputClassifier instance
-- **Maximum Sequence Length:** 256 tokens
+- **Maximum Sequence Length:** 384 tokens
 - **Number of Classes:** 3 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -65,7 +65,7 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.2857   |
+| **all** | 0.4286   |
 
 ## Uses
 
@@ -139,20 +139,20 @@ preds = model("Hats off to the design team.")
 ### Training Results
 | Epoch   | Step   | Training Loss | Validation Loss |
 |:-------:|:------:|:-------------:|:---------------:|
-| 0.0556  | 1      | 0.3535        | -               |
-| **1.0** | **18** | **-**         | **0.1724**      |
-| 2.0     | 36     | -             | 0.1963          |
-| 2.7778  | 50     | 0.1636        | -               |
-| 3.0     | 54     | -             | 0.1957          |
-| 4.0     | 72     | -             | 0.2116          |
-| 5.0     | 90     | -             | 0.2175          |
-| 5.5556  | 100    | 0.053         | -               |
-| 6.0     | 108    | -             | 0.2282          |
-| 7.0     | 126    | -             | 0.2368          |
-| 8.0     | 144    | -             | 0.2413          |
-| 8.3333  | 150    | 0.0167        | -               |
-| 9.0     | 162    | -             | 0.2451          |
-| 10.0    | 180    | -             | 0.2462          |
+| 0.0556  | 1      | 0.323         | -               |
+| 1.0     | 18     | -             | 0.2331          |
+| **2.0** | **36** | **-**         | **0.1994**      |
+| 2.7778  | 50     | 0.0779        | -               |
+| 3.0     | 54     | -             | 0.2288          |
+| 4.0     | 72     | -             | 0.2379          |
+| 5.0     | 90     | -             | 0.2529          |
+| 5.5556  | 100    | 0.0373        | -               |
+| 6.0     | 108    | -             | 0.2569          |
+| 7.0     | 126    | -             | 0.2665          |
+| 8.0     | 144    | -             | 0.2643          |
+| 8.3333  | 150    | 0.0095        | -               |
+| 9.0     | 162    | -             | 0.2639          |
+| 10.0    | 180    | -             | 0.2656          |
 
 * The bold row denotes the saved checkpoint.
 ### Framework Versions

config.json

@@ -1,26 +1,24 @@
 {
-  "_name_or_path": "checkpoints/step_18",
+  "_name_or_path": "checkpoints/step_36",
   "architectures": [
-    "BertModel"
+    "MPNetModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.37.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894e848767bdac3ecbba5b1a640959840698602b7bb511e88f9b538fe4a7f8b7
-size 90864192
+oid sha256:4d4730bc1baf12b18cf4abc3dfe6d5f48c6a5724dffca67414b9ffd36e1b4e96
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013ff19d5a490708f234cd692605bcfc026edc7d95fed9983e281b1af4441543
-size 11105
+oid sha256:6a6487a4a1af3423452d876b957e5ed83ba6e80dc53c1745be84cb4f97946a83
+size 20321

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 384,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,27 +1,41 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,63 +1,71 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "cls_token": "<s>",
   "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "max_length": 128,
   "model_max_length": 512,
-  "never_split": null,
   "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "MPNetTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"

vocab.txt

@@ -1,3 +1,7 @@
+<s>
+<pad>
+</s>
+<unk>
 [PAD]
 [unused0]
 [unused1]
@@ -30520,3 +30524,4 @@ necessitated
 ##：
 ##？
 ##～
+<mask>