Adel-Elwan commited on
Commit
e908019
1 Parent(s): 70e0eaa

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
Base_Standard_Title_C=150000_Q=105000_R=105000.log ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-06-18 22:04:09 - Load pretrained SentenceTransformer: msmarco-bert-base-dot-v5
2
+ 2023-06-18 22:04:11 - Use pytorch device: cuda
3
+ 2023-06-18 22:04:11 - Train Corpus Size: 150000
4
+ 2023-06-18 22:04:11 - Train Query Size: 105000
5
+ 2023-06-18 22:04:11 - Train qrels Size: 105000
6
+ 2023-06-18 22:04:11 - Information Retrieval Evaluation on Standard_Title dataset:
7
+ 2023-06-18 22:30:00 - Queries: 22500
8
+ 2023-06-18 22:30:00 - Corpus: 150000
9
+
10
+ 2023-06-18 22:30:19 - Score-Function: dot_score
11
+ 2023-06-18 22:30:19 - Accuracy@1: 58.27%
12
+ 2023-06-18 22:30:19 - Accuracy@3: 71.01%
13
+ 2023-06-18 22:30:19 - Accuracy@5: 75.05%
14
+ 2023-06-18 22:30:19 - Accuracy@10: 79.98%
15
+ 2023-06-18 22:30:19 - Accuracy@100: 91.04%
16
+ 2023-06-18 22:30:19 - Precision@1: 58.27%
17
+ 2023-06-18 22:30:19 - Precision@3: 23.67%
18
+ 2023-06-18 22:30:19 - Precision@5: 15.01%
19
+ 2023-06-18 22:30:19 - Precision@10: 8.00%
20
+ 2023-06-18 22:30:19 - Precision@100: 0.91%
21
+ 2023-06-18 22:30:19 - Recall@1: 58.27%
22
+ 2023-06-18 22:30:19 - Recall@3: 71.01%
23
+ 2023-06-18 22:30:19 - Recall@5: 75.05%
24
+ 2023-06-18 22:30:19 - Recall@10: 79.98%
25
+ 2023-06-18 22:30:19 - Recall@100: 91.04%
26
+ 2023-06-18 22:30:19 - MRR@1: 0.5827
27
+ 2023-06-18 22:30:19 - MRR@10: 0.6557
28
+ 2023-06-18 22:30:19 - MRR@100: 0.6604
29
+ 2023-06-18 22:30:19 - NDCG@1: 0.5827
30
+ 2023-06-18 22:30:19 - NDCG@10: 0.6905
31
+ 2023-06-18 22:30:19 - NDCG@100: 0.7139
32
+ 2023-06-18 22:30:19 - MAP@1: 0.5827
33
+ 2023-06-18 22:30:19 - MAP@10: 0.6557
34
+ 2023-06-18 22:30:19 - MAP@100: 0.6604
New_Standard_Title_C=150000_Q=105000_R=105000.log.log ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-06-18 22:30:23 - Load pretrained SentenceTransformer: /kaggle/working/output/msmarco-bert-base-dot-v5-v2-Titles-wiht_150000_samples
2
+ 2023-06-18 22:30:27 - Use pytorch device: cuda
3
+ 2023-06-18 22:30:27 - Information Retrieval Evaluation on msmarco-bert-base-dot-v5 dataset:
4
+ 2023-06-18 22:56:13 - Queries: 22500
5
+ 2023-06-18 22:56:13 - Corpus: 150000
6
+
7
+ 2023-06-18 22:56:32 - Score-Function: dot_score
8
+ 2023-06-18 22:56:32 - Accuracy@1: 65.53%
9
+ 2023-06-18 22:56:32 - Accuracy@3: 79.30%
10
+ 2023-06-18 22:56:32 - Accuracy@5: 83.45%
11
+ 2023-06-18 22:56:32 - Accuracy@10: 87.78%
12
+ 2023-06-18 22:56:32 - Accuracy@100: 96.06%
13
+ 2023-06-18 22:56:32 - Precision@1: 65.53%
14
+ 2023-06-18 22:56:32 - Precision@3: 26.43%
15
+ 2023-06-18 22:56:32 - Precision@5: 16.69%
16
+ 2023-06-18 22:56:32 - Precision@10: 8.78%
17
+ 2023-06-18 22:56:32 - Precision@100: 0.96%
18
+ 2023-06-18 22:56:32 - Recall@1: 65.53%
19
+ 2023-06-18 22:56:32 - Recall@3: 79.30%
20
+ 2023-06-18 22:56:32 - Recall@5: 83.45%
21
+ 2023-06-18 22:56:32 - Recall@10: 87.78%
22
+ 2023-06-18 22:56:32 - Recall@100: 96.06%
23
+ 2023-06-18 22:56:32 - MRR@1: 0.6553
24
+ 2023-06-18 22:56:32 - MRR@10: 0.7327
25
+ 2023-06-18 22:56:32 - MRR@100: 0.7364
26
+ 2023-06-18 22:56:32 - NDCG@1: 0.6553
27
+ 2023-06-18 22:56:32 - NDCG@10: 0.7680
28
+ 2023-06-18 22:56:32 - NDCG@100: 0.7858
29
+ 2023-06-18 22:56:32 - MAP@1: 0.6553
30
+ 2023-06-18 22:56:32 - MAP@10: 0.7327
31
+ 2023-06-18 22:56:32 - MAP@100: 0.7364
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
+
9
+ ---
10
+
11
+ # {MODEL_NAME}
12
+
13
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
+
15
+ <!--- Describe your model here -->
16
+
17
+ ## Usage (Sentence-Transformers)
18
+
19
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
20
+
21
+ ```
22
+ pip install -U sentence-transformers
23
+ ```
24
+
25
+ Then you can use the model like this:
26
+
27
+ ```python
28
+ from sentence_transformers import SentenceTransformer
29
+ sentences = ["This is an example sentence", "Each sentence is converted"]
30
+
31
+ model = SentenceTransformer('{MODEL_NAME}')
32
+ embeddings = model.encode(sentences)
33
+ print(embeddings)
34
+ ```
35
+
36
+
37
+
38
+ ## Usage (HuggingFace Transformers)
39
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
40
+
41
+ ```python
42
+ from transformers import AutoTokenizer, AutoModel
43
+ import torch
44
+
45
+
46
+ #Mean Pooling - Take attention mask into account for correct averaging
47
+ def mean_pooling(model_output, attention_mask):
48
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
49
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
50
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
51
+
52
+
53
+ # Sentences we want sentence embeddings for
54
+ sentences = ['This is an example sentence', 'Each sentence is converted']
55
+
56
+ # Load model from HuggingFace Hub
57
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
58
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
59
+
60
+ # Tokenize sentences
61
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
62
+
63
+ # Compute token embeddings
64
+ with torch.no_grad():
65
+ model_output = model(**encoded_input)
66
+
67
+ # Perform pooling. In this case, mean pooling.
68
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
69
+
70
+ print("Sentence embeddings:")
71
+ print(sentence_embeddings)
72
+ ```
73
+
74
+
75
+
76
+ ## Evaluation Results
77
+
78
+ <!--- Describe how your model was evaluated -->
79
+
80
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
81
+
82
+
83
+ ## Training
84
+ The model was trained with the parameters:
85
+
86
+ **DataLoader**:
87
+
88
+ `torch.utils.data.dataloader.DataLoader` of length 6563 with parameters:
89
+ ```
90
+ {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
91
+ ```
92
+
93
+ **Loss**:
94
+
95
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
96
+ ```
97
+ {'scale': 20.0, 'similarity_fct': 'dot_score'}
98
+ ```
99
+
100
+ Parameters of the fit()-Method:
101
+ ```
102
+ {
103
+ "epochs": 1,
104
+ "evaluation_steps": 5000,
105
+ "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
106
+ "max_grad_norm": 1,
107
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
108
+ "optimizer_params": {
109
+ "correct_bias": false,
110
+ "eps": 1e-06,
111
+ "lr": 2e-05
112
+ },
113
+ "scheduler": "WarmupLinear",
114
+ "steps_per_epoch": null,
115
+ "warmup_steps": 656,
116
+ "weight_decay": 0.01
117
+ }
118
+ ```
119
+
120
+
121
+ ## Full Model Architecture
122
+ ```
123
+ SentenceTransformer(
124
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
125
+ (1): Pooling({'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})
126
+ )
127
+ ```
128
+
129
+ ## Citing & Authors
130
+
131
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_msmarco-bert-base-dot-v5/",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
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-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.28.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.1",
5
+ "pytorch": "1.8.1"
6
+ }
7
+ }
eval/Information-Retrieval_evaluation_eval_results.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
2
+ 0,5000,0.6173333333333333,0.7596444444444445,0.8045777777777777,0.8528888888888889,0.6173333333333333,0.6173333333333333,0.25321481481481484,0.7596444444444445,0.16091555555555556,0.8045777777777777,0.08528888888888889,0.8528888888888889,0.6976215167548637,0.7353112672414058,0.7018455432360402,0.6368444444444444,0.7794666666666666,0.8216,0.8689777777777777,0.6368444444444444,0.6368444444444444,0.25982222222222223,0.7794666666666666,0.16432,0.8216,0.0868977777777778,0.8689777777777777,0.7165995590829068,0.7536350866487502,0.7205145757304534
3
+ 0,-1,0.6252444444444445,0.7662666666666667,0.8103111111111111,0.8591111111111112,0.6252444444444445,0.6252444444444445,0.2554222222222222,0.7662666666666667,0.16206222222222222,0.8103111111111111,0.0859111111111111,0.8591111111111112,0.7052431746031884,0.7425929826318987,0.7092784314670788,0.6585333333333333,0.7963111111111111,0.8389333333333333,0.8808888888888889,0.6585333333333333,0.6585333333333333,0.265437037037037,0.7963111111111111,0.16778666666666667,0.8389333333333333,0.08808888888888888,0.8808888888888889,0.7356587654321133,0.7710220275631976,0.7391586496074568
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f68cd7e58b9c900b812d948aee62741f88b153330818e9eb904ea5f48d1b62
3
+ size 438000173
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff