Add SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 768,
+  "word_embedding_dimension": 384,
   "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/paraphrase-mpnet-base-v2
+base_model: sentence-transformers/all-MiniLM-L6-v2
 metrics:
 - accuracy
 widget:
@@ -24,7 +24,7 @@ widget:
 pipeline_tag: text-classification
 inference: true
 model-index:
-- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
+- name: SetFit with sentence-transformers/all-MiniLM-L6-v2
   results:
   - task:
       type: text-classification
@@ -35,13 +35,13 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.9166666666666666
+      value: 0.875
       name: Accuracy
 ---
 
-# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
+# SetFit with sentence-transformers/all-MiniLM-L6-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-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-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:
 
@@ -52,9 +52,9 @@ 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-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-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:** 256 tokens
 - **Number of Classes:** 9 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -84,7 +84,7 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.9167   |
+| **all** | 0.875    |
 
 ## Uses
 
@@ -170,31 +170,31 @@ preds = model("The itinerary meets our requirements, please book as proposed.")
 ### Training Results
 | Epoch   | Step     | Training Loss | Validation Loss |
 |:-------:|:--------:|:-------------:|:---------------:|
-| 0.0009  | 1        | 0.1941        | -               |
-| 0.0434  | 50       | 0.1194        | -               |
-| 0.0868  | 100      | 0.0359        | -               |
-| 0.1302  | 150      | 0.0064        | -               |
-| 0.1736  | 200      | 0.002         | -               |
-| 0.2170  | 250      | 0.0016        | -               |
-| 0.2604  | 300      | 0.0012        | -               |
-| 0.3038  | 350      | 0.0005        | -               |
-| 0.3472  | 400      | 0.0005        | -               |
-| 0.3906  | 450      | 0.0008        | -               |
-| 0.4340  | 500      | 0.0009        | -               |
-| 0.4774  | 550      | 0.0004        | -               |
-| 0.5208  | 600      | 0.0006        | -               |
-| 0.5642  | 650      | 0.0003        | -               |
-| 0.6076  | 700      | 0.0003        | -               |
-| 0.6510  | 750      | 0.0002        | -               |
-| 0.6944  | 800      | 0.0005        | -               |
-| 0.7378  | 850      | 0.0002        | -               |
-| 0.7812  | 900      | 0.0003        | -               |
-| 0.8247  | 950      | 0.0002        | -               |
-| 0.8681  | 1000     | 0.0003        | -               |
-| 0.9115  | 1050     | 0.0003        | -               |
-| 0.9549  | 1100     | 0.0002        | -               |
-| 0.9983  | 1150     | 0.0002        | -               |
-| **1.0** | **1152** | **-**         | **0.0443**      |
+| 0.0009  | 1        | 0.1977        | -               |
+| 0.0434  | 50       | 0.1642        | -               |
+| 0.0868  | 100      | 0.1034        | -               |
+| 0.1302  | 150      | 0.05          | -               |
+| 0.1736  | 200      | 0.0177        | -               |
+| 0.2170  | 250      | 0.0128        | -               |
+| 0.2604  | 300      | 0.0148        | -               |
+| 0.3038  | 350      | 0.0109        | -               |
+| 0.3472  | 400      | 0.0059        | -               |
+| 0.3906  | 450      | 0.004         | -               |
+| 0.4340  | 500      | 0.0036        | -               |
+| 0.4774  | 550      | 0.0064        | -               |
+| 0.5208  | 600      | 0.0042        | -               |
+| 0.5642  | 650      | 0.002         | -               |
+| 0.6076  | 700      | 0.0017        | -               |
+| 0.6510  | 750      | 0.002         | -               |
+| 0.6944  | 800      | 0.0026        | -               |
+| 0.7378  | 850      | 0.0019        | -               |
+| 0.7812  | 900      | 0.0017        | -               |
+| 0.8247  | 950      | 0.0017        | -               |
+| 0.8681  | 1000     | 0.0015        | -               |
+| 0.9115  | 1050     | 0.0009        | -               |
+| 0.9549  | 1100     | 0.002         | -               |
+| 0.9983  | 1150     | 0.0008        | -               |
+| **1.0** | **1152** | **-**         | **0.0732**      |
 
 * The bold row denotes the saved checkpoint.
 ### Framework Versions

config.json

@@ -1,23 +1,24 @@
 {
-  "_name_or_path": "old_models/paraphrase-mpnet-base-v2/0_Transformer",
+  "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
   "architectures": [
-    "MPNetModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "relative_attention_num_buckets": 32,
-  "transformers_version": "4.7.0",
-  "vocab_size": 30527
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
   }
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f38386fe38fb9e27340e3e21b5845aa4ebcf741069a53a910ee1ad6b4171170
-size 56331
+oid sha256:15b6a70cdb3099c1bd608127f07be59a61058c34a5fc6bd783bc68339244294e
+size 28683

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"
   }
 ]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbf26e90285d3f93c1969dcb4309254071e4710e3643a0e80fd90af6576d59e
-size 438014769
+oid sha256:f1deccf1340cb988837e82e9637610686c1dbcb189c17e6e3176393972140ad4
+size 90890353

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 256,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,67 +1,16 @@
 {
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
   "model_max_length": 512,
   "name_or_path": "checkpoints/step_1152/",
   "never_split": null,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "special_tokens_map_file": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/special_tokens_map.json",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "MPNetTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

vocab.txt

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