clause_model
Browse files- README.md +71 -0
- config.json +128 -0
- model.safetensors +3 -0
- runs/Aug22_11-13-21_978f4495e191/events.out.tfevents.1724325208.978f4495e191.379.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
base_model: nlpaueb/bert-base-uncased-contracts
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: clause_model
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# clause_model
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [nlpaueb/bert-base-uncased-contracts](https://huggingface.co/nlpaueb/bert-base-uncased-contracts) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5961
|
21 |
+
- Accuracy: 0.8955
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 500
|
47 |
+
- num_epochs: 10
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 3.0237 | 1.0 | 883 | 0.9479 | 0.7783 |
|
55 |
+
| 0.6024 | 2.0 | 1766 | 0.5360 | 0.8713 |
|
56 |
+
| 0.2674 | 3.0 | 2649 | 0.5095 | 0.8866 |
|
57 |
+
| 0.1629 | 4.0 | 3532 | 0.5706 | 0.8904 |
|
58 |
+
| 0.1027 | 5.0 | 4415 | 0.5767 | 0.8866 |
|
59 |
+
| 0.0724 | 6.0 | 5298 | 0.5502 | 0.8955 |
|
60 |
+
| 0.0646 | 7.0 | 6181 | 0.5825 | 0.8917 |
|
61 |
+
| 0.0458 | 8.0 | 7064 | 0.6150 | 0.8981 |
|
62 |
+
| 0.0359 | 9.0 | 7947 | 0.5936 | 0.8955 |
|
63 |
+
| 0.0268 | 10.0 | 8830 | 0.5961 | 0.8955 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.42.4
|
69 |
+
- Pytorch 2.3.1+cu121
|
70 |
+
- Datasets 2.21.0
|
71 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nlpaueb/bert-base-uncased-contracts",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_ids": null,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Governing Law",
|
14 |
+
"1": "Competitive Restriction Exception",
|
15 |
+
"2": "Non-Compete",
|
16 |
+
"3": "Exclusivity",
|
17 |
+
"4": "No-Solicit Of Customers",
|
18 |
+
"5": "No-Solicit Of Employees",
|
19 |
+
"6": "Non-Disparagement",
|
20 |
+
"7": "Rofr/Rofo/Rofn",
|
21 |
+
"8": "Change Of Control",
|
22 |
+
"9": "Revenue/Profit Sharing",
|
23 |
+
"10": "Price Restrictions",
|
24 |
+
"11": "Minimum Commitment",
|
25 |
+
"12": "Ip Ownership Assignment",
|
26 |
+
"13": "Joint Ip Ownership",
|
27 |
+
"14": "License Grant",
|
28 |
+
"15": "Irrevocable Or Perpetual License",
|
29 |
+
"16": "Source Code Escrow",
|
30 |
+
"17": "Post-Termination Services",
|
31 |
+
"18": "Uncapped Liability",
|
32 |
+
"19": "Cap On Liability",
|
33 |
+
"20": "Liquidated Damages",
|
34 |
+
"21": "Warranty Duration",
|
35 |
+
"22": "Insurance",
|
36 |
+
"23": "Covenant Not To Sue",
|
37 |
+
"24": "Severability",
|
38 |
+
"25": "Indemnification",
|
39 |
+
"26": "Waiver",
|
40 |
+
"27": "Compensation",
|
41 |
+
"28": "Confidentiality",
|
42 |
+
"29": "Termination",
|
43 |
+
"30": "Arbitration",
|
44 |
+
"31": "Force Majeure",
|
45 |
+
"32": "Definition",
|
46 |
+
"33": "Survival",
|
47 |
+
"34": "Assignment",
|
48 |
+
"35": "Dispute Resolution",
|
49 |
+
"36": "Audits",
|
50 |
+
"37": "Security Deposit",
|
51 |
+
"38": "Breach",
|
52 |
+
"39": "Intellectual Property Rights",
|
53 |
+
"40": "Obligations",
|
54 |
+
"41": "Exclusion from Confidentiality",
|
55 |
+
"42": "Ownership of Confidential Information",
|
56 |
+
"43": "Legal Obligation to Disclose",
|
57 |
+
"44": "No Binding",
|
58 |
+
"45": "Return of Information",
|
59 |
+
"46": "Permitted Use of Information",
|
60 |
+
"47": "Others"
|
61 |
+
},
|
62 |
+
"initializer_range": 0.02,
|
63 |
+
"intermediate_size": 3072,
|
64 |
+
"label2id": {
|
65 |
+
"Arbitration": 30,
|
66 |
+
"Assignment": 34,
|
67 |
+
"Audits": 36,
|
68 |
+
"Breach": 38,
|
69 |
+
"Cap On Liability": 19,
|
70 |
+
"Change Of Control": 8,
|
71 |
+
"Compensation": 27,
|
72 |
+
"Competitive Restriction Exception": 1,
|
73 |
+
"Confidentiality": 28,
|
74 |
+
"Covenant Not To Sue": 23,
|
75 |
+
"Definition": 32,
|
76 |
+
"Dispute Resolution": 35,
|
77 |
+
"Exclusion from Confidentiality": 41,
|
78 |
+
"Exclusivity": 3,
|
79 |
+
"Force Majeure": 31,
|
80 |
+
"Governing Law": 0,
|
81 |
+
"Indemnification": 25,
|
82 |
+
"Insurance": 22,
|
83 |
+
"Intellectual Property Rights": 39,
|
84 |
+
"Ip Ownership Assignment": 12,
|
85 |
+
"Irrevocable Or Perpetual License": 15,
|
86 |
+
"Joint Ip Ownership": 13,
|
87 |
+
"Legal Obligation to Disclose": 43,
|
88 |
+
"License Grant": 14,
|
89 |
+
"Liquidated Damages": 20,
|
90 |
+
"Minimum Commitment": 11,
|
91 |
+
"No Binding": 44,
|
92 |
+
"No-Solicit Of Customers": 4,
|
93 |
+
"No-Solicit Of Employees": 5,
|
94 |
+
"Non-Compete": 2,
|
95 |
+
"Non-Disparagement": 6,
|
96 |
+
"Obligations": 40,
|
97 |
+
"Others": 47,
|
98 |
+
"Ownership of Confidential Information": 42,
|
99 |
+
"Permitted Use of Information": 46,
|
100 |
+
"Post-Termination Services": 17,
|
101 |
+
"Price Restrictions": 10,
|
102 |
+
"Return of Information": 45,
|
103 |
+
"Revenue/Profit Sharing": 9,
|
104 |
+
"Rofr/Rofo/Rofn": 7,
|
105 |
+
"Security Deposit": 37,
|
106 |
+
"Severability": 24,
|
107 |
+
"Source Code Escrow": 16,
|
108 |
+
"Survival": 33,
|
109 |
+
"Termination": 29,
|
110 |
+
"Uncapped Liability": 18,
|
111 |
+
"Waiver": 26,
|
112 |
+
"Warranty Duration": 21
|
113 |
+
},
|
114 |
+
"layer_norm_eps": 1e-12,
|
115 |
+
"max_position_embeddings": 512,
|
116 |
+
"model_type": "bert",
|
117 |
+
"num_attention_heads": 12,
|
118 |
+
"num_hidden_layers": 12,
|
119 |
+
"output_past": true,
|
120 |
+
"pad_token_id": null,
|
121 |
+
"position_embedding_type": "absolute",
|
122 |
+
"problem_type": "single_label_classification",
|
123 |
+
"torch_dtype": "float32",
|
124 |
+
"transformers_version": "4.42.4",
|
125 |
+
"type_vocab_size": 2,
|
126 |
+
"use_cache": true,
|
127 |
+
"vocab_size": 30522
|
128 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43849f87c40991651f9e1b3d6d4877538ec8f35e5ecab50f2e92ce37c4ea8c2d
|
3 |
+
size 438100144
|
runs/Aug22_11-13-21_978f4495e191/events.out.tfevents.1724325208.978f4495e191.379.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12b3b5b56e87fab89362f329f740f7299f5043f11192818cfe3c952920de8168
|
3 |
+
size 14895
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:182a5f1499c0fdd349a826342f7140f0442743da1657ba369e5a1672f8ee3484
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|