yaniseuranova
commited on
Commit
•
1e9ec87
1
Parent(s):
77e267e
Add SetFit model
Browse files- 1_Pooling/config.json +3 -3
- README.md +41 -41
- config.json +10 -14
- config_sentence_transformers.json +3 -3
- config_setfit.json +2 -2
- model.safetensors +2 -2
- model_head.pkl +2 -2
- sentence_bert_config.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +16 -6
1_Pooling/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
-
"pooling_mode_cls_token":
|
4 |
-
"pooling_mode_mean_tokens":
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
"pooling_mode_weightedmean_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
"pooling_mode_weightedmean_tokens": false,
|
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- sentence-transformers
|
6 |
- text-classification
|
7 |
- generated_from_setfit_trainer
|
8 |
-
base_model:
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
widget:
|
@@ -22,7 +22,7 @@ widget:
|
|
22 |
pipeline_tag: text-classification
|
23 |
inference: true
|
24 |
model-index:
|
25 |
-
- name: SetFit with
|
26 |
results:
|
27 |
- task:
|
28 |
type: text-classification
|
@@ -37,9 +37,9 @@ model-index:
|
|
37 |
name: Accuracy
|
38 |
---
|
39 |
|
40 |
-
# SetFit with
|
41 |
|
42 |
-
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [
|
43 |
|
44 |
The model has been trained using an efficient few-shot learning technique that involves:
|
45 |
|
@@ -50,9 +50,9 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
50 |
|
51 |
### Model Description
|
52 |
- **Model Type:** SetFit
|
53 |
-
- **Sentence Transformer body:** [
|
54 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
55 |
-
- **Maximum Sequence Length:**
|
56 |
- **Number of Classes:** 2 classes
|
57 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
58 |
<!-- - **Language:** Unknown -->
|
@@ -152,41 +152,41 @@ preds = model("What distinguishes a transforming industry from one that merely i
|
|
152 |
- load_best_model_at_end: True
|
153 |
|
154 |
### Training Results
|
155 |
-
| Epoch | Step
|
156 |
-
|
157 |
-
| 0.0021 | 1
|
158 |
-
| 0.1033 | 50
|
159 |
-
| 0.2066 | 100
|
160 |
-
| 0.3099 | 150
|
161 |
-
| 0.4132 | 200
|
162 |
-
| 0.5165 | 250
|
163 |
-
| 0.6198 | 300
|
164 |
-
| 0.7231 | 350
|
165 |
-
| 0.8264 | 400
|
166 |
-
| 0.9298 | 450
|
167 |
-
|
|
168 |
-
| 1.0331 | 500
|
169 |
-
| 1.1364 | 550
|
170 |
-
| 1.2397 | 600
|
171 |
-
| 1.3430 | 650
|
172 |
-
| 1.4463 | 700
|
173 |
-
| 1.5496 | 750
|
174 |
-
| 1.6529 | 800
|
175 |
-
| 1.7562 | 850
|
176 |
-
| 1.8595 | 900
|
177 |
-
| 1.9628 | 950
|
178 |
-
| 2.0 | 968
|
179 |
-
| 2.0661 | 1000
|
180 |
-
| 2.1694 | 1050
|
181 |
-
| 2.2727 | 1100
|
182 |
-
| 2.3760 | 1150
|
183 |
-
| 2.4793 | 1200
|
184 |
-
| 2.5826 | 1250
|
185 |
-
| 2.6860 | 1300
|
186 |
-
| 2.7893 | 1350
|
187 |
-
| 2.8926 | 1400
|
188 |
-
| 2.9959 | 1450
|
189 |
-
| 3.0
|
190 |
|
191 |
* The bold row denotes the saved checkpoint.
|
192 |
### Framework Versions
|
|
|
5 |
- sentence-transformers
|
6 |
- text-classification
|
7 |
- generated_from_setfit_trainer
|
8 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
widget:
|
|
|
22 |
pipeline_tag: text-classification
|
23 |
inference: true
|
24 |
model-index:
|
25 |
+
- name: SetFit with sentence-transformers/all-mpnet-base-v2
|
26 |
results:
|
27 |
- task:
|
28 |
type: text-classification
|
|
|
37 |
name: Accuracy
|
38 |
---
|
39 |
|
40 |
+
# SetFit with sentence-transformers/all-mpnet-base-v2
|
41 |
|
42 |
+
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.
|
43 |
|
44 |
The model has been trained using an efficient few-shot learning technique that involves:
|
45 |
|
|
|
50 |
|
51 |
### Model Description
|
52 |
- **Model Type:** SetFit
|
53 |
+
- **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
|
54 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
55 |
+
- **Maximum Sequence Length:** 384 tokens
|
56 |
- **Number of Classes:** 2 classes
|
57 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
58 |
<!-- - **Language:** Unknown -->
|
|
|
152 |
- load_best_model_at_end: True
|
153 |
|
154 |
### Training Results
|
155 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
156 |
+
|:-------:|:--------:|:-------------:|:---------------:|
|
157 |
+
| 0.0021 | 1 | 0.301 | - |
|
158 |
+
| 0.1033 | 50 | 0.1244 | - |
|
159 |
+
| 0.2066 | 100 | 0.0021 | - |
|
160 |
+
| 0.3099 | 150 | 0.0006 | - |
|
161 |
+
| 0.4132 | 200 | 0.0002 | - |
|
162 |
+
| 0.5165 | 250 | 0.0002 | - |
|
163 |
+
| 0.6198 | 300 | 0.0001 | - |
|
164 |
+
| 0.7231 | 350 | 0.0001 | - |
|
165 |
+
| 0.8264 | 400 | 0.0001 | - |
|
166 |
+
| 0.9298 | 450 | 0.0001 | - |
|
167 |
+
| 1.0 | 484 | - | 0.0001 |
|
168 |
+
| 1.0331 | 500 | 0.0001 | - |
|
169 |
+
| 1.1364 | 550 | 0.0001 | - |
|
170 |
+
| 1.2397 | 600 | 0.0001 | - |
|
171 |
+
| 1.3430 | 650 | 0.0 | - |
|
172 |
+
| 1.4463 | 700 | 0.0001 | - |
|
173 |
+
| 1.5496 | 750 | 0.0001 | - |
|
174 |
+
| 1.6529 | 800 | 0.0001 | - |
|
175 |
+
| 1.7562 | 850 | 0.0001 | - |
|
176 |
+
| 1.8595 | 900 | 0.0 | - |
|
177 |
+
| 1.9628 | 950 | 0.0 | - |
|
178 |
+
| 2.0 | 968 | - | 0.0001 |
|
179 |
+
| 2.0661 | 1000 | 0.0001 | - |
|
180 |
+
| 2.1694 | 1050 | 0.0001 | - |
|
181 |
+
| 2.2727 | 1100 | 0.0 | - |
|
182 |
+
| 2.3760 | 1150 | 0.0 | - |
|
183 |
+
| 2.4793 | 1200 | 0.0 | - |
|
184 |
+
| 2.5826 | 1250 | 0.0 | - |
|
185 |
+
| 2.6860 | 1300 | 0.0001 | - |
|
186 |
+
| 2.7893 | 1350 | 0.0 | - |
|
187 |
+
| 2.8926 | 1400 | 0.0001 | - |
|
188 |
+
| 2.9959 | 1450 | 0.0 | - |
|
189 |
+
| **3.0** | **1452** | **-** | **0.0001** |
|
190 |
|
191 |
* The bold row denotes the saved checkpoint.
|
192 |
### Framework Versions
|
config.json
CHANGED
@@ -1,28 +1,24 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "checkpoints/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"initializer_range": 0.02,
|
14 |
-
"intermediate_size":
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
-
"max_position_embeddings":
|
17 |
-
"model_type": "
|
18 |
-
"num_attention_heads":
|
19 |
-
"num_hidden_layers":
|
20 |
-
"output_past": true,
|
21 |
"pad_token_id": 1,
|
22 |
-
"
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.39.0",
|
25 |
-
"
|
26 |
-
"use_cache": true,
|
27 |
-
"vocab_size": 250002
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "checkpoints/step_1452",
|
3 |
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
|
|
19 |
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.39.0",
|
23 |
+
"vocab_size": 30527
|
|
|
|
|
24 |
}
|
config_sentence_transformers.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
-
"sentence_transformers": "2.
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.6.1",
|
5 |
+
"pytorch": "1.8.1"
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
config_setfit.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"normalize_embeddings": false,
|
3 |
"labels": [
|
4 |
"lexical",
|
5 |
"semantic"
|
6 |
-
]
|
|
|
7 |
}
|
|
|
1 |
{
|
|
|
2 |
"labels": [
|
3 |
"lexical",
|
4 |
"semantic"
|
5 |
+
],
|
6 |
+
"normalize_embeddings": false
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3aecb73df1f4899ecef5a4732119cf7319250902ae704c7a28e0ffc99a99eda
|
3 |
+
size 437967672
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03051f677d184f53e2f1ee6703c4aba2d3bf9688700c5baa2bcd55b8790363d4
|
3 |
+
size 7039
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 384,
|
3 |
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -42,7 +42,7 @@
|
|
42 |
"single_word": false
|
43 |
},
|
44 |
"unk_token": {
|
45 |
-
"content": "
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
|
|
42 |
"single_word": false
|
43 |
},
|
44 |
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46fb1f735006f52c1f9744bb05f7bc1544ec8475955af30396212c7737558d1e
|
3 |
+
size 710932
|
tokenizer_config.json
CHANGED
@@ -27,12 +27,20 @@
|
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "<mask>",
|
37 |
"lstrip": true,
|
38 |
"normalized": false,
|
@@ -44,19 +52,21 @@
|
|
44 |
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|
|
|
47 |
"eos_token": "</s>",
|
48 |
"mask_token": "<mask>",
|
49 |
-
"max_length":
|
50 |
-
"model_max_length":
|
51 |
"pad_to_multiple_of": null,
|
52 |
"pad_token": "<pad>",
|
53 |
"pad_token_type_id": 0,
|
54 |
"padding_side": "right",
|
55 |
"sep_token": "</s>",
|
56 |
-
"sp_model_kwargs": {},
|
57 |
"stride": 0,
|
58 |
-
"
|
|
|
|
|
59 |
"truncation_side": "right",
|
60 |
"truncation_strategy": "longest_first",
|
61 |
-
"unk_token": "
|
62 |
}
|
|
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[UNK]",
|
37 |
+
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
+
"30526": {
|
44 |
"content": "<mask>",
|
45 |
"lstrip": true,
|
46 |
"normalized": false,
|
|
|
52 |
"bos_token": "<s>",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
"cls_token": "<s>",
|
55 |
+
"do_lower_case": true,
|
56 |
"eos_token": "</s>",
|
57 |
"mask_token": "<mask>",
|
58 |
+
"max_length": 128,
|
59 |
+
"model_max_length": 512,
|
60 |
"pad_to_multiple_of": null,
|
61 |
"pad_token": "<pad>",
|
62 |
"pad_token_type_id": 0,
|
63 |
"padding_side": "right",
|
64 |
"sep_token": "</s>",
|
|
|
65 |
"stride": 0,
|
66 |
+
"strip_accents": null,
|
67 |
+
"tokenize_chinese_chars": true,
|
68 |
+
"tokenizer_class": "MPNetTokenizer",
|
69 |
"truncation_side": "right",
|
70 |
"truncation_strategy": "longest_first",
|
71 |
+
"unk_token": "[UNK]"
|
72 |
}
|