alexbrun commited on
Commit
1018861
·
1 Parent(s): e1b45d6

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. README.md +54 -0
  2. config.json +83 -0
  3. special_tokens_map.json +7 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +13 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: alexbrun/contract_classifier
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # alexbrun/contract_classifier
14
+
15
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.0996
18
+ - Validation Loss: 1.2174
19
+ - Train Accuracy: 0.7820
20
+ - Epoch: 0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 672, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
+ |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 2.0996 | 1.2174 | 0.7820 | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.30.2
52
+ - TensorFlow 2.13.0
53
+ - Datasets 2.13.1
54
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Label Report - Anti-assignment, CIC (Group 3)",
13
+ "1": "Label Report - ROFR-ROFO-ROFN",
14
+ "2": "Label Report - Joint IP Ownership",
15
+ "3": "Label Report - Document Name",
16
+ "4": "Label Report - Minimum Commitment",
17
+ "5": "Label Report - Revenue-Profit Sharing",
18
+ "6": "Label Report - Uncapped Liability (Group 5)",
19
+ "7": "Label Report - No-Solicit of Employees",
20
+ "8": "Label Report - Source Code Escrow",
21
+ "9": "Label Report - Non-Disparagement",
22
+ "10": "Label Report - Audit Rights",
23
+ "11": "Label Report - Post-Termination Services",
24
+ "12": "Label Report - Covenant not to Sue_ Release of Claims",
25
+ "13": "Label Report - Liquidated Damages",
26
+ "14": "Label Report - Non-Compete, Exclusivity, No-Solicit of Customers (Group 2)",
27
+ "15": "Label Report - Insurance",
28
+ "16": "Label Report - Most Favored Nation",
29
+ "17": "Label Report - Parties",
30
+ "18": "Label Report - IP Ownership Assignment",
31
+ "19": "Label Report - Dates (Group 1)",
32
+ "20": "Label Report - Licenses (Group 4)",
33
+ "21": "Label Report - Volume Restriction",
34
+ "22": "Label Report - Price Restrictions",
35
+ "23": "Label Report - Governing Law",
36
+ "24": "Label Report - Termination for Convenience",
37
+ "25": "Label Report - Unlimited-All-You-Can-Eat License",
38
+ "26": "Label Report - Warranty Duration",
39
+ "27": "Label Report - Third Party Beneficiary"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "label2id": {
43
+ "Label Report - Anti-assignment, CIC (Group 3)": 0,
44
+ "Label Report - Audit Rights": 10,
45
+ "Label Report - Covenant not to Sue_ Release of Claims": 12,
46
+ "Label Report - Dates (Group 1)": 19,
47
+ "Label Report - Document Name": 3,
48
+ "Label Report - Governing Law": 23,
49
+ "Label Report - IP Ownership Assignment": 18,
50
+ "Label Report - Insurance": 15,
51
+ "Label Report - Joint IP Ownership": 2,
52
+ "Label Report - Licenses (Group 4)": 20,
53
+ "Label Report - Liquidated Damages": 13,
54
+ "Label Report - Minimum Commitment": 4,
55
+ "Label Report - Most Favored Nation": 16,
56
+ "Label Report - No-Solicit of Employees": 7,
57
+ "Label Report - Non-Compete, Exclusivity, No-Solicit of Customers (Group 2)": 14,
58
+ "Label Report - Non-Disparagement": 9,
59
+ "Label Report - Parties": 17,
60
+ "Label Report - Post-Termination Services": 11,
61
+ "Label Report - Price Restrictions": 22,
62
+ "Label Report - ROFR-ROFO-ROFN": 1,
63
+ "Label Report - Revenue-Profit Sharing": 5,
64
+ "Label Report - Source Code Escrow": 8,
65
+ "Label Report - Termination for Convenience": 24,
66
+ "Label Report - Third Party Beneficiary": 27,
67
+ "Label Report - Uncapped Liability (Group 5)": 6,
68
+ "Label Report - Unlimited-All-You-Can-Eat License": 25,
69
+ "Label Report - Volume Restriction": 21,
70
+ "Label Report - Warranty Duration": 26
71
+ },
72
+ "max_position_embeddings": 512,
73
+ "model_type": "distilbert",
74
+ "n_heads": 12,
75
+ "n_layers": 6,
76
+ "pad_token_id": 0,
77
+ "qa_dropout": 0.1,
78
+ "seq_classif_dropout": 0.2,
79
+ "sinusoidal_pos_embds": false,
80
+ "tie_weights_": true,
81
+ "transformers_version": "4.30.2",
82
+ "vocab_size": 30522
83
+ }
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
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df295e771486b1baea08a36fda3f967b7b7f95250d28f3965eb1e4984e9894c2
3
+ size 268035016
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff