Add SetFit model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-  "word_embedding_dimension": 384,
-  "pooling_mode_cls_token": true,
-  "pooling_mode_mean_tokens": false,
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,
   "pooling_mode_mean_sqrt_len_tokens": false,
   "pooling_mode_weightedmean_tokens": false,

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: avsolatorio/GIST-small-Embedding-v0
+base_model: sentence-transformers/paraphrase-mpnet-base-v2
 library_name: setfit
 metrics:
 - accuracy
@@ -164,11 +164,25 @@ widget:
 
     '
 inference: false
+model-index:
+- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.0
+      name: Accuracy
 ---
 
-# SetFit with avsolatorio/GIST-small-Embedding-v0
+# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [avsolatorio/GIST-small-Embedding-v0](https://huggingface.co/avsolatorio/GIST-small-Embedding-v0) as the Sentence Transformer embedding model. A OneVsRestClassifier 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/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -179,7 +193,7 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [avsolatorio/GIST-small-Embedding-v0](https://huggingface.co/avsolatorio/GIST-small-Embedding-v0)
+- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
 - **Classification head:** a OneVsRestClassifier instance
 - **Maximum Sequence Length:** 512 tokens
 - **Number of Classes:** 13 classes
@@ -193,6 +207,13 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.0      |
+
 ## Uses
 
 ### Direct Use for Inference
@@ -251,8 +272,8 @@ Add water and seasonings.  Bring to a boil.  Cover and simmer on low for 20 minu
 | Word count   | 4   | 4.2308 | 5   |
 
 ### Training Hyperparameters
-- batch_size: (32, 32)
-- num_epochs: (1, 1)
+- batch_size: (16, 2)
+- num_epochs: (1, 16)
 - max_steps: -1
 - sampling_strategy: oversampling
 - body_learning_rate: (2e-05, 1e-05)
@@ -265,15 +286,14 @@ Add water and seasonings.  Bring to a boil.  Cover and simmer on low for 20 minu
 - warmup_proportion: 0.1
 - seed: 42
 - eval_max_steps: -1
-- load_best_model_at_end: True
+- load_best_model_at_end: False
 
 ### Training Results
-| Epoch   | Step   | Training Loss | Validation Loss |
-|:-------:|:------:|:-------------:|:---------------:|
-| 0.05    | 1      | 0.3162        | -               |
-| **1.0** | **20** | **-**         | **0.2636**      |
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0256 | 1    | 0.1572        | -               |
+| 1.0    | 39   | 0.0152        | 0.2304          |
 
-* The bold row denotes the saved checkpoint.
 ### Framework Versions
 - Python: 3.10.12
 - SetFit: 1.0.3

config.json

@@ -1,31 +1,24 @@
 {
-  "_name_or_path": "checkpoints/step_20",
+  "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
   "architectures": [
-    "BertModel"
+    "MPNetModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "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": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.42.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

config_setfit.json

@@ -1,4 +1,5 @@
 {
+  "normalize_embeddings": false,
   "labels": [
     "Baking",
     "Grilling",
@@ -13,6 +14,5 @@
     "Saut\u00e9ing",
     "Sous vide",
     "Stir-frying"
-  ],
-  "normalize_embeddings": false
+  ]
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab8af3296eb8871c79e07f139646e86938dd7e81eec6b8a54fada4db3b4d909
-size 133462128
+oid sha256:0c459619a48663c3e77b088e66e942b68a15128aae191f8f0aec44d930d28c54
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53bcc40c8e1e047e7d2e334879f57555a428fff6e22cb405cd9b3ec44032b09f
-size 45316
+oid sha256:fadf9efa1bf6b64e594a679094b02e3ab341007efaeb88e8bca7ed5499a49a0e
+size 85252

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
   "max_seq_length": 512,
-  "do_lower_case": true
+  "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

@@ -1,64 +1,59 @@
 {
   "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]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "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]",
+  "cls_token": "<s>",
   "do_basic_tokenize": true,
   "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "max_length": 512,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 512,
   "never_split": null,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "[SEP]",
-  "stride": 0,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "MPNetTokenizer",
   "unk_token": "[UNK]"
 }

vocab.txt

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