Add SetFit model

README.md

@@ -5,7 +5,7 @@ tags:
 - sentence-transformers
 - text-classification
 - generated_from_setfit_trainer
-base_model: sentence-transformers/paraphrase-mpnet-base-v2
+base_model: sentence-transformers/all-mpnet-base-v2
 metrics:
 - accuracy
 widget:
@@ -17,7 +17,7 @@ widget:
 pipeline_tag: text-classification
 inference: true
 model-index:
-- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
+- name: SetFit with sentence-transformers/all-mpnet-base-v2
   results:
   - task:
       type: text-classification
@@ -32,9 +32,9 @@ model-index:
       name: Accuracy
 ---
 
-# SetFit with sentence-transformers/paraphrase-mpnet-base-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/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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 [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -45,9 +45,9 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
+- **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
-- **Maximum Sequence Length:** 512 tokens
+- **Maximum Sequence Length:** 384 tokens
 - **Number of Classes:** 4 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -153,24 +153,24 @@ preds = model("Comment rédiger un bon CV?")
 ### Training Results
 | Epoch   | Step    | Training Loss | Validation Loss |
 |:-------:|:-------:|:-------------:|:---------------:|
-| 0.0060  | 1       | 0.3581        | -               |
-| 0.3012  | 50      | 0.2063        | -               |
-| 0.6024  | 100     | 0.1283        | -               |
-| 0.9036  | 150     | 0.0083        | -               |
-| 1.0     | 166     | -             | 0.003           |
-| 1.2048  | 200     | 0.0014        | -               |
-| 1.5060  | 250     | 0.0008        | -               |
-| 1.8072  | 300     | 0.0006        | -               |
-| 2.0     | 332     | -             | 0.0006          |
-| 2.1084  | 350     | 0.0004        | -               |
-| 2.4096  | 400     | 0.0003        | -               |
-| 2.7108  | 450     | 0.0005        | -               |
-| 3.0     | 498     | -             | 0.0004          |
-| 3.0120  | 500     | 0.0003        | -               |
-| 3.3133  | 550     | 0.0005        | -               |
+| 0.0060  | 1       | 0.3577        | -               |
+| 0.3012  | 50      | 0.2222        | -               |
+| 0.6024  | 100     | 0.1178        | -               |
+| 0.9036  | 150     | 0.0031        | -               |
+| 1.0     | 166     | -             | 0.0009          |
+| 1.2048  | 200     | 0.0008        | -               |
+| 1.5060  | 250     | 0.0006        | -               |
+| 1.8072  | 300     | 0.0005        | -               |
+| 2.0     | 332     | -             | 0.0003          |
+| 2.1084  | 350     | 0.0005        | -               |
+| 2.4096  | 400     | 0.0004        | -               |
+| 2.7108  | 450     | 0.0004        | -               |
+| 3.0     | 498     | -             | 0.0002          |
+| 3.0120  | 500     | 0.0004        | -               |
+| 3.3133  | 550     | 0.0004        | -               |
 | 3.6145  | 600     | 0.0003        | -               |
 | 3.9157  | 650     | 0.0003        | -               |
-| **4.0** | **664** | **-**         | **0.0003**      |
+| **4.0** | **664** | **-**         | **0.0002**      |
 
 * The bold row denotes the saved checkpoint.
 ### Framework Versions

config_sentence_transformers.json

@@ -1,8 +1,8 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
   },
   "prompts": {},
   "default_prompt_name": null

config_setfit.json

@@ -1,9 +1,9 @@
 {
+  "normalize_embeddings": false,
   "labels": [
     "very_semantic",
     "semantic",
     "lexical",
     "very_lexical"
-  ],
-  "normalize_embeddings": false
+  ]
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b53398a5e1768704556a85ff27c1d05e5391646db87372f075a3bc0d2145a0b
+oid sha256:4ecaf937ec012e0ca789426506a82ac68a73094b315e1a34b0825dd45ea29b8b
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8319b40498ce63d8e5868820a4e5de714d7af5a0e73cb8705a3d00f2c7f6ee4
+oid sha256:b6401ba0eccde015d202256f9d2a28bb798e26a65bab62b6d00e056d2ac48706
 size 25655

modules.json

@@ -10,5 +10,11 @@
     "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,
+  "max_seq_length": 384,
   "do_lower_case": false
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 384,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -42,6 +42,15 @@
       "normalized": false,
       "special": true
     },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    },
     {
       "id": 104,
       "content": "[UNK]",
@@ -72,85 +81,17 @@
     "type": "BertPreTokenizer"
   },
   "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      }
+    "type": "RobertaProcessing",
+    "sep": [
+      "</s>",
+      2
     ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
-      }
+    "cls": [
+      "<s>",
+      0
     ],
-    "special_tokens": {
-      "</s>": {
-        "id": "</s>",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "</s>"
-        ]
-      },
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          0
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "trim_offsets": true,
+    "add_prefix_space": false
   },
   "decoder": {
     "type": "WordPiece",

tokenizer_config.json

@@ -24,6 +24,14 @@
       "single_word": false,
       "special": true
     },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "104": {
       "content": "[UNK]",
       "lstrip": false,
@@ -44,13 +52,11 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 512,
+  "max_length": 128,
   "model_max_length": 512,
-  "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_type_id": 0,