Mahesh9 commited on
Commit
271a097
1 Parent(s): 2251be3

Upload 54 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/README.md +67 -0
  3. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/config.json +63 -0
  4. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/model.safetensors +3 -0
  5. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/optimizer.pt +3 -0
  6. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/rng_state.pth +3 -0
  7. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/scheduler.pt +3 -0
  8. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/special_tokens_map.json +7 -0
  9. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/tokenizer.json +0 -0
  10. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/tokenizer_config.json +55 -0
  11. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/trainer_state.json +171 -0
  12. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/training_args.bin +3 -0
  13. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/vocab.txt +0 -0
  14. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/config.json +63 -0
  15. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/model.safetensors +3 -0
  16. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/optimizer.pt +3 -0
  17. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/rng_state.pth +3 -0
  18. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/scheduler.pt +3 -0
  19. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/special_tokens_map.json +7 -0
  20. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/tokenizer.json +0 -0
  21. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/tokenizer_config.json +55 -0
  22. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/trainer_state.json +321 -0
  23. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/training_args.bin +3 -0
  24. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/vocab.txt +0 -0
  25. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/config.json +63 -0
  26. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/model.safetensors +3 -0
  27. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/runs/Mar31_00-10-44_d1026/events.out.tfevents.1711858247.d1026 +3 -0
  28. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/runs/Mar31_01-35-36_d1026/events.out.tfevents.1711863338.d1026 +3 -0
  29. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/special_tokens_map.json +7 -0
  30. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/tokenizer.json +0 -0
  31. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/tokenizer_config.json +55 -0
  32. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/training_args.bin +3 -0
  33. finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/vocab.txt +0 -0
  34. finetuned-models/finetuned_on_issue/finetuning_on_issues.ipynb +0 -0
  35. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/README.md +66 -0
  36. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/config.json +39 -0
  37. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/model.safetensors +3 -0
  38. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/optimizer.pt +3 -0
  39. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/rng_state.pth +3 -0
  40. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/scheduler.pt +3 -0
  41. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/special_tokens_map.json +7 -0
  42. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/tokenizer.json +0 -0
  43. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/tokenizer_config.json +55 -0
  44. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/trainer_state.json +171 -0
  45. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/training_args.bin +3 -0
  46. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/vocab.txt +0 -0
  47. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/config.json +39 -0
  48. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/model.safetensors +3 -0
  49. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/saved_results/model_predictions_and_labels.csv +3 -0
  50. finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/special_tokens_map.json +7 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/saved_results/model_predictions_and_labels.csv filter=lfs diff=lfs merge=lfs -text
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: distil-bert-fintuned-issues-cfpb-complaints
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # distil-bert-fintuned-issues-cfpb-complaints
20
+
21
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6711
24
+ - Accuracy: 0.7652
25
+ - Precision: 0.5935
26
+ - Recall: 0.5577
27
+ - F1: 0.5702
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 2
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.7269 | 1.0 | 11603 | 0.7187 | 0.7438 | 0.5853 | 0.5327 | 0.5491 |
59
+ | 0.612 | 2.0 | 23206 | 0.6711 | 0.7652 | 0.5935 | 0.5577 | 0.5702 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.37.2
65
+ - Pytorch 2.2.0
66
+ - Datasets 2.17.1
67
+ - Tokenizers 0.15.2
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Account Operations and Unauthorized Transaction Issues",
13
+ "1": "Attempts to collect debt not owed",
14
+ "2": "Closing an account",
15
+ "3": "Closing your account",
16
+ "4": "Credit Report and Monitoring Issues",
17
+ "5": "Dealing with your lender or servicer",
18
+ "6": "Disputes and Misrepresentations",
19
+ "7": "Improper use of your report",
20
+ "8": "Incorrect information on your report",
21
+ "9": "Legal and Threat Actions",
22
+ "10": "Managing an account",
23
+ "11": "Payment and Funds Management",
24
+ "12": "Problem with a company's investigation into an existing issue",
25
+ "13": "Problem with a company's investigation into an existing problem",
26
+ "14": "Problem with a credit reporting company's investigation into an existing problem",
27
+ "15": "Problem with a purchase shown on your statement",
28
+ "16": "Written notification about debt"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "label2id": {
32
+ "Account Operations and Unauthorized Transaction Issues": 0,
33
+ "Attempts to collect debt not owed": 1,
34
+ "Closing an account": 2,
35
+ "Closing your account": 3,
36
+ "Credit Report and Monitoring Issues": 4,
37
+ "Dealing with your lender or servicer": 5,
38
+ "Disputes and Misrepresentations": 6,
39
+ "Improper use of your report": 7,
40
+ "Incorrect information on your report": 8,
41
+ "Legal and Threat Actions": 9,
42
+ "Managing an account": 10,
43
+ "Payment and Funds Management": 11,
44
+ "Problem with a company's investigation into an existing issue": 12,
45
+ "Problem with a company's investigation into an existing problem": 13,
46
+ "Problem with a credit reporting company's investigation into an existing problem": 14,
47
+ "Problem with a purchase shown on your statement": 15,
48
+ "Written notification about debt": 16
49
+ },
50
+ "max_position_embeddings": 512,
51
+ "model_type": "distilbert",
52
+ "n_heads": 12,
53
+ "n_layers": 6,
54
+ "pad_token_id": 0,
55
+ "problem_type": "single_label_classification",
56
+ "qa_dropout": 0.1,
57
+ "seq_classif_dropout": 0.2,
58
+ "sinusoidal_pos_embds": false,
59
+ "tie_weights_": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.37.2",
62
+ "vocab_size": 30522
63
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c1858294df47b24072c932b6341cb0791a566421a29df04dbe0ea77b14bb80
3
+ size 267878708
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90484ceb2bb914e92101ded6201c2ce256cb808b24facfcf6c081d7c492e94c
3
+ size 535819578
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba522fa4fab6b54194f62d63a0eba799c9eaf28d6ccf12f605086cbcb7ad248
3
+ size 14244
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300063f4cba8d12b93f40cd5990c0daa3b4fad457e1b796be7745e07b88219f2
3
+ size 1064
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/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
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7186761498451233,
3
+ "best_model_checkpoint": "distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11603,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1.9569076962854436e-05,
14
+ "loss": 1.4292,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 1.9138153925708868e-05,
20
+ "loss": 1.1124,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 1.8707230888563303e-05,
26
+ "loss": 1.0067,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.17,
31
+ "learning_rate": 1.8276307851417738e-05,
32
+ "loss": 0.9522,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 1.7845384814272172e-05,
38
+ "loss": 0.8931,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 1.7414461777126604e-05,
44
+ "loss": 0.8832,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.3,
49
+ "learning_rate": 1.698353873998104e-05,
50
+ "loss": 0.8627,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.34,
55
+ "learning_rate": 1.6552615702835474e-05,
56
+ "loss": 0.8511,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.39,
61
+ "learning_rate": 1.612169266568991e-05,
62
+ "loss": 0.835,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.43,
67
+ "learning_rate": 1.5690769628544343e-05,
68
+ "loss": 0.8137,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.47,
73
+ "learning_rate": 1.5259846591398778e-05,
74
+ "loss": 0.8188,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.52,
79
+ "learning_rate": 1.4828923554253211e-05,
80
+ "loss": 0.8164,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.56,
85
+ "learning_rate": 1.4398000517107646e-05,
86
+ "loss": 0.7985,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.6,
91
+ "learning_rate": 1.396707747996208e-05,
92
+ "loss": 0.7913,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.65,
97
+ "learning_rate": 1.3536154442816514e-05,
98
+ "loss": 0.7857,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.69,
103
+ "learning_rate": 1.3105231405670949e-05,
104
+ "loss": 0.7922,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.73,
109
+ "learning_rate": 1.2674308368525384e-05,
110
+ "loss": 0.7649,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.78,
115
+ "learning_rate": 1.2243385331379815e-05,
116
+ "loss": 0.7679,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.82,
121
+ "learning_rate": 1.181246229423425e-05,
122
+ "loss": 0.7558,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.86,
127
+ "learning_rate": 1.1381539257088685e-05,
128
+ "loss": 0.7499,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.9,
133
+ "learning_rate": 1.095061621994312e-05,
134
+ "loss": 0.7278,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.95,
139
+ "learning_rate": 1.0519693182797553e-05,
140
+ "loss": 0.7288,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.99,
145
+ "learning_rate": 1.0088770145651988e-05,
146
+ "loss": 0.7269,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 1.0,
151
+ "eval_accuracy": 0.7437621202327085,
152
+ "eval_f1": 0.5490839527402266,
153
+ "eval_loss": 0.7186761498451233,
154
+ "eval_precision": 0.5852853204976994,
155
+ "eval_recall": 0.532749286993408,
156
+ "eval_runtime": 244.2988,
157
+ "eval_samples_per_second": 253.296,
158
+ "eval_steps_per_second": 15.833,
159
+ "step": 11603
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 23206,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 2,
166
+ "save_steps": 500,
167
+ "total_flos": 2.459742862793011e+16,
168
+ "train_batch_size": 16,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab92b4eaa43f951a436c810b0973f0b78ad0ba2ba68a6ceb8353b7c912ccc9b6
3
+ size 4728
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Account Operations and Unauthorized Transaction Issues",
13
+ "1": "Attempts to collect debt not owed",
14
+ "2": "Closing an account",
15
+ "3": "Closing your account",
16
+ "4": "Credit Report and Monitoring Issues",
17
+ "5": "Dealing with your lender or servicer",
18
+ "6": "Disputes and Misrepresentations",
19
+ "7": "Improper use of your report",
20
+ "8": "Incorrect information on your report",
21
+ "9": "Legal and Threat Actions",
22
+ "10": "Managing an account",
23
+ "11": "Payment and Funds Management",
24
+ "12": "Problem with a company's investigation into an existing issue",
25
+ "13": "Problem with a company's investigation into an existing problem",
26
+ "14": "Problem with a credit reporting company's investigation into an existing problem",
27
+ "15": "Problem with a purchase shown on your statement",
28
+ "16": "Written notification about debt"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "label2id": {
32
+ "Account Operations and Unauthorized Transaction Issues": 0,
33
+ "Attempts to collect debt not owed": 1,
34
+ "Closing an account": 2,
35
+ "Closing your account": 3,
36
+ "Credit Report and Monitoring Issues": 4,
37
+ "Dealing with your lender or servicer": 5,
38
+ "Disputes and Misrepresentations": 6,
39
+ "Improper use of your report": 7,
40
+ "Incorrect information on your report": 8,
41
+ "Legal and Threat Actions": 9,
42
+ "Managing an account": 10,
43
+ "Payment and Funds Management": 11,
44
+ "Problem with a company's investigation into an existing issue": 12,
45
+ "Problem with a company's investigation into an existing problem": 13,
46
+ "Problem with a credit reporting company's investigation into an existing problem": 14,
47
+ "Problem with a purchase shown on your statement": 15,
48
+ "Written notification about debt": 16
49
+ },
50
+ "max_position_embeddings": 512,
51
+ "model_type": "distilbert",
52
+ "n_heads": 12,
53
+ "n_layers": 6,
54
+ "pad_token_id": 0,
55
+ "problem_type": "single_label_classification",
56
+ "qa_dropout": 0.1,
57
+ "seq_classif_dropout": 0.2,
58
+ "sinusoidal_pos_embds": false,
59
+ "tie_weights_": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.37.2",
62
+ "vocab_size": 30522
63
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b3f40c1a197145aa78dcbd91ef40aabf361e67b51041bc7e918fdf2a3ae903
3
+ size 267878708
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eac5ade2cf243a3d979e53c91a5734679b2263850a3d0440cb52e6ae3c707cb
3
+ size 535819578
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddeae77f86f59ce42a11303d309714cfdcf4b5da7567a276c13f0227b618377
3
+ size 14244
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2e6cd4a7a53fabb88f31db1d221292ba29596afaf167ece5c18536a98871b9
3
+ size 1064
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/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
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/trainer_state.json ADDED
@@ -0,0 +1,321 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6711095571517944,
3
+ "best_model_checkpoint": "distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 23206,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1.9569076962854436e-05,
14
+ "loss": 1.4292,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 1.9138153925708868e-05,
20
+ "loss": 1.1124,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 1.8707230888563303e-05,
26
+ "loss": 1.0067,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.17,
31
+ "learning_rate": 1.8276307851417738e-05,
32
+ "loss": 0.9522,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 1.7845384814272172e-05,
38
+ "loss": 0.8931,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 1.7414461777126604e-05,
44
+ "loss": 0.8832,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.3,
49
+ "learning_rate": 1.698353873998104e-05,
50
+ "loss": 0.8627,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.34,
55
+ "learning_rate": 1.6552615702835474e-05,
56
+ "loss": 0.8511,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.39,
61
+ "learning_rate": 1.612169266568991e-05,
62
+ "loss": 0.835,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.43,
67
+ "learning_rate": 1.5690769628544343e-05,
68
+ "loss": 0.8137,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.47,
73
+ "learning_rate": 1.5259846591398778e-05,
74
+ "loss": 0.8188,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.52,
79
+ "learning_rate": 1.4828923554253211e-05,
80
+ "loss": 0.8164,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.56,
85
+ "learning_rate": 1.4398000517107646e-05,
86
+ "loss": 0.7985,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.6,
91
+ "learning_rate": 1.396707747996208e-05,
92
+ "loss": 0.7913,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.65,
97
+ "learning_rate": 1.3536154442816514e-05,
98
+ "loss": 0.7857,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.69,
103
+ "learning_rate": 1.3105231405670949e-05,
104
+ "loss": 0.7922,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.73,
109
+ "learning_rate": 1.2674308368525384e-05,
110
+ "loss": 0.7649,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.78,
115
+ "learning_rate": 1.2243385331379815e-05,
116
+ "loss": 0.7679,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.82,
121
+ "learning_rate": 1.181246229423425e-05,
122
+ "loss": 0.7558,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.86,
127
+ "learning_rate": 1.1381539257088685e-05,
128
+ "loss": 0.7499,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.9,
133
+ "learning_rate": 1.095061621994312e-05,
134
+ "loss": 0.7278,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.95,
139
+ "learning_rate": 1.0519693182797553e-05,
140
+ "loss": 0.7288,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.99,
145
+ "learning_rate": 1.0088770145651988e-05,
146
+ "loss": 0.7269,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 1.0,
151
+ "eval_accuracy": 0.7437621202327085,
152
+ "eval_f1": 0.5490839527402266,
153
+ "eval_loss": 0.7186761498451233,
154
+ "eval_precision": 0.5852853204976994,
155
+ "eval_recall": 0.532749286993408,
156
+ "eval_runtime": 244.2988,
157
+ "eval_samples_per_second": 253.296,
158
+ "eval_steps_per_second": 15.833,
159
+ "step": 11603
160
+ },
161
+ {
162
+ "epoch": 1.03,
163
+ "learning_rate": 9.657847108506421e-06,
164
+ "loss": 0.7075,
165
+ "step": 12000
166
+ },
167
+ {
168
+ "epoch": 1.08,
169
+ "learning_rate": 9.226924071360856e-06,
170
+ "loss": 0.6624,
171
+ "step": 12500
172
+ },
173
+ {
174
+ "epoch": 1.12,
175
+ "learning_rate": 8.79600103421529e-06,
176
+ "loss": 0.6742,
177
+ "step": 13000
178
+ },
179
+ {
180
+ "epoch": 1.16,
181
+ "learning_rate": 8.365077997069724e-06,
182
+ "loss": 0.6966,
183
+ "step": 13500
184
+ },
185
+ {
186
+ "epoch": 1.21,
187
+ "learning_rate": 7.934154959924159e-06,
188
+ "loss": 0.6689,
189
+ "step": 14000
190
+ },
191
+ {
192
+ "epoch": 1.25,
193
+ "learning_rate": 7.503231922778592e-06,
194
+ "loss": 0.6536,
195
+ "step": 14500
196
+ },
197
+ {
198
+ "epoch": 1.29,
199
+ "learning_rate": 7.072308885633027e-06,
200
+ "loss": 0.6711,
201
+ "step": 15000
202
+ },
203
+ {
204
+ "epoch": 1.34,
205
+ "learning_rate": 6.641385848487461e-06,
206
+ "loss": 0.653,
207
+ "step": 15500
208
+ },
209
+ {
210
+ "epoch": 1.38,
211
+ "learning_rate": 6.2104628113418955e-06,
212
+ "loss": 0.6358,
213
+ "step": 16000
214
+ },
215
+ {
216
+ "epoch": 1.42,
217
+ "learning_rate": 5.779539774196329e-06,
218
+ "loss": 0.6607,
219
+ "step": 16500
220
+ },
221
+ {
222
+ "epoch": 1.47,
223
+ "learning_rate": 5.3486167370507635e-06,
224
+ "loss": 0.6536,
225
+ "step": 17000
226
+ },
227
+ {
228
+ "epoch": 1.51,
229
+ "learning_rate": 4.9176936999051975e-06,
230
+ "loss": 0.6799,
231
+ "step": 17500
232
+ },
233
+ {
234
+ "epoch": 1.55,
235
+ "learning_rate": 4.4867706627596315e-06,
236
+ "loss": 0.6422,
237
+ "step": 18000
238
+ },
239
+ {
240
+ "epoch": 1.59,
241
+ "learning_rate": 4.0558476256140655e-06,
242
+ "loss": 0.6323,
243
+ "step": 18500
244
+ },
245
+ {
246
+ "epoch": 1.64,
247
+ "learning_rate": 3.6249245884685e-06,
248
+ "loss": 0.6499,
249
+ "step": 19000
250
+ },
251
+ {
252
+ "epoch": 1.68,
253
+ "learning_rate": 3.194001551322934e-06,
254
+ "loss": 0.6522,
255
+ "step": 19500
256
+ },
257
+ {
258
+ "epoch": 1.72,
259
+ "learning_rate": 2.763078514177368e-06,
260
+ "loss": 0.6451,
261
+ "step": 20000
262
+ },
263
+ {
264
+ "epoch": 1.77,
265
+ "learning_rate": 2.3321554770318023e-06,
266
+ "loss": 0.6495,
267
+ "step": 20500
268
+ },
269
+ {
270
+ "epoch": 1.81,
271
+ "learning_rate": 1.9012324398862363e-06,
272
+ "loss": 0.635,
273
+ "step": 21000
274
+ },
275
+ {
276
+ "epoch": 1.85,
277
+ "learning_rate": 1.4703094027406705e-06,
278
+ "loss": 0.6311,
279
+ "step": 21500
280
+ },
281
+ {
282
+ "epoch": 1.9,
283
+ "learning_rate": 1.0393863655951047e-06,
284
+ "loss": 0.6392,
285
+ "step": 22000
286
+ },
287
+ {
288
+ "epoch": 1.94,
289
+ "learning_rate": 6.08463328449539e-07,
290
+ "loss": 0.6471,
291
+ "step": 22500
292
+ },
293
+ {
294
+ "epoch": 1.98,
295
+ "learning_rate": 1.7754029130397314e-07,
296
+ "loss": 0.612,
297
+ "step": 23000
298
+ },
299
+ {
300
+ "epoch": 2.0,
301
+ "eval_accuracy": 0.7651745313510019,
302
+ "eval_f1": 0.5702070410433322,
303
+ "eval_loss": 0.6711095571517944,
304
+ "eval_precision": 0.5934826294010517,
305
+ "eval_recall": 0.5577165037333897,
306
+ "eval_runtime": 245.1951,
307
+ "eval_samples_per_second": 252.37,
308
+ "eval_steps_per_second": 15.775,
309
+ "step": 23206
310
+ }
311
+ ],
312
+ "logging_steps": 500,
313
+ "max_steps": 23206,
314
+ "num_input_tokens_seen": 0,
315
+ "num_train_epochs": 2,
316
+ "save_steps": 500,
317
+ "total_flos": 4.919485725586022e+16,
318
+ "train_batch_size": 16,
319
+ "trial_name": null,
320
+ "trial_params": null
321
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab92b4eaa43f951a436c810b0973f0b78ad0ba2ba68a6ceb8353b7c912ccc9b6
3
+ size 4728
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-23206/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Account Operations and Unauthorized Transaction Issues",
13
+ "1": "Attempts to collect debt not owed",
14
+ "2": "Closing an account",
15
+ "3": "Closing your account",
16
+ "4": "Credit Report and Monitoring Issues",
17
+ "5": "Dealing with your lender or servicer",
18
+ "6": "Disputes and Misrepresentations",
19
+ "7": "Improper use of your report",
20
+ "8": "Incorrect information on your report",
21
+ "9": "Legal and Threat Actions",
22
+ "10": "Managing an account",
23
+ "11": "Payment and Funds Management",
24
+ "12": "Problem with a company's investigation into an existing issue",
25
+ "13": "Problem with a company's investigation into an existing problem",
26
+ "14": "Problem with a credit reporting company's investigation into an existing problem",
27
+ "15": "Problem with a purchase shown on your statement",
28
+ "16": "Written notification about debt"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "label2id": {
32
+ "Account Operations and Unauthorized Transaction Issues": 0,
33
+ "Attempts to collect debt not owed": 1,
34
+ "Closing an account": 2,
35
+ "Closing your account": 3,
36
+ "Credit Report and Monitoring Issues": 4,
37
+ "Dealing with your lender or servicer": 5,
38
+ "Disputes and Misrepresentations": 6,
39
+ "Improper use of your report": 7,
40
+ "Incorrect information on your report": 8,
41
+ "Legal and Threat Actions": 9,
42
+ "Managing an account": 10,
43
+ "Payment and Funds Management": 11,
44
+ "Problem with a company's investigation into an existing issue": 12,
45
+ "Problem with a company's investigation into an existing problem": 13,
46
+ "Problem with a credit reporting company's investigation into an existing problem": 14,
47
+ "Problem with a purchase shown on your statement": 15,
48
+ "Written notification about debt": 16
49
+ },
50
+ "max_position_embeddings": 512,
51
+ "model_type": "distilbert",
52
+ "n_heads": 12,
53
+ "n_layers": 6,
54
+ "pad_token_id": 0,
55
+ "problem_type": "single_label_classification",
56
+ "qa_dropout": 0.1,
57
+ "seq_classif_dropout": 0.2,
58
+ "sinusoidal_pos_embds": false,
59
+ "tie_weights_": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.37.2",
62
+ "vocab_size": 30522
63
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b3f40c1a197145aa78dcbd91ef40aabf361e67b51041bc7e918fdf2a3ae903
3
+ size 267878708
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/runs/Mar31_00-10-44_d1026/events.out.tfevents.1711858247.d1026 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11c87dd88256783494361e1aacbdde1e2344b96c1fefc998a1ae4037f0cc01a
3
+ size 10456
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/runs/Mar31_01-35-36_d1026/events.out.tfevents.1711863338.d1026 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7273b15f2487e3e9d0d41d91112aa125aafe75796bc67c7f9527619a9636cbae
3
+ size 14596
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/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
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab92b4eaa43f951a436c810b0973f0b78ad0ba2ba68a6ceb8353b7c912ccc9b6
3
+ size 4728
finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_issue/finetuning_on_issues.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: distil-bert-fintuned-product-cfpb-complaints
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # distil-bert-fintuned-product-cfpb-complaints
20
+
21
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1393
24
+ - Accuracy: 0.9595
25
+ - Precision: 0.8788
26
+ - Recall: 0.8175
27
+ - F1: 0.8432
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.1411 | 1.0 | 11603 | 0.1393 | 0.9595 | 0.8788 | 0.8175 | 0.8432 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.37.2
64
+ - Pytorch 2.2.0
65
+ - Datasets 2.17.1
66
+ - Tokenizers 0.15.2
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Checking or savings account",
13
+ "1": "Credit Reporting",
14
+ "2": "Credit/Prepaid Card",
15
+ "3": "Debt collection",
16
+ "4": "Loans / Mortgage"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "Checking or savings account": 0,
21
+ "Credit Reporting": 1,
22
+ "Credit/Prepaid Card": 2,
23
+ "Debt collection": 3,
24
+ "Loans / Mortgage": 4
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "pad_token_id": 0,
31
+ "problem_type": "single_label_classification",
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.37.2",
38
+ "vocab_size": 30522
39
+ }
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce5d2cb4ab9c9cb4c083b4dc93b7c2d57296a302be7e09cc45bc4e639773e09
3
+ size 267841796
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8c9fbf83a9183af521cf53ce093345f35bc388e717e6605d8dec126e3a47a7
3
+ size 535745722
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba522fa4fab6b54194f62d63a0eba799c9eaf28d6ccf12f605086cbcb7ad248
3
+ size 14244
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4f7f940536cfd1870287aab30ed50c2bed761fba56e762ef66070d6836c5c6
3
+ size 1064
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/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
+ }
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.13929830491542816,
3
+ "best_model_checkpoint": "distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11603,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1.9138153925708868e-05,
14
+ "loss": 0.3296,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 1.8276307851417738e-05,
20
+ "loss": 0.2054,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 1.7414461777126604e-05,
26
+ "loss": 0.2006,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.17,
31
+ "learning_rate": 1.6552615702835474e-05,
32
+ "loss": 0.1827,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 1.5690769628544343e-05,
38
+ "loss": 0.1713,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 1.4828923554253211e-05,
44
+ "loss": 0.1725,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.3,
49
+ "learning_rate": 1.396707747996208e-05,
50
+ "loss": 0.1668,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.34,
55
+ "learning_rate": 1.3105231405670949e-05,
56
+ "loss": 0.1738,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.39,
61
+ "learning_rate": 1.2243385331379815e-05,
62
+ "loss": 0.1591,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.43,
67
+ "learning_rate": 1.1381539257088685e-05,
68
+ "loss": 0.1596,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.47,
73
+ "learning_rate": 1.0519693182797553e-05,
74
+ "loss": 0.1594,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.52,
79
+ "learning_rate": 9.657847108506421e-06,
80
+ "loss": 0.1648,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.56,
85
+ "learning_rate": 8.79600103421529e-06,
86
+ "loss": 0.1668,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.6,
91
+ "learning_rate": 7.934154959924159e-06,
92
+ "loss": 0.1463,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.65,
97
+ "learning_rate": 7.072308885633027e-06,
98
+ "loss": 0.1552,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.69,
103
+ "learning_rate": 6.2104628113418955e-06,
104
+ "loss": 0.1668,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.73,
109
+ "learning_rate": 5.3486167370507635e-06,
110
+ "loss": 0.1474,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.78,
115
+ "learning_rate": 4.4867706627596315e-06,
116
+ "loss": 0.1607,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.82,
121
+ "learning_rate": 3.6249245884685e-06,
122
+ "loss": 0.1363,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.86,
127
+ "learning_rate": 2.763078514177368e-06,
128
+ "loss": 0.1335,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.9,
133
+ "learning_rate": 1.9012324398862363e-06,
134
+ "loss": 0.1284,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.95,
139
+ "learning_rate": 1.0393863655951047e-06,
140
+ "loss": 0.1269,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.99,
145
+ "learning_rate": 1.7754029130397314e-07,
146
+ "loss": 0.1411,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 1.0,
151
+ "eval_accuracy": 0.959502262443439,
152
+ "eval_f1": 0.8432009164684704,
153
+ "eval_loss": 0.13929830491542816,
154
+ "eval_precision": 0.8787916313109703,
155
+ "eval_recall": 0.8174517238624979,
156
+ "eval_runtime": 245.7208,
157
+ "eval_samples_per_second": 251.831,
158
+ "eval_steps_per_second": 15.741,
159
+ "step": 11603
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 11603,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 1,
166
+ "save_steps": 500,
167
+ "total_flos": 2.459216611302912e+16,
168
+ "train_batch_size": 16,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e9266539e263fe29fc8d37ec6bf4eb70ff8477b107c45e41a483566525f3c7
3
+ size 4728
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/checkpoint-11603/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Checking or savings account",
13
+ "1": "Credit Reporting",
14
+ "2": "Credit/Prepaid Card",
15
+ "3": "Debt collection",
16
+ "4": "Loans / Mortgage"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "Checking or savings account": 0,
21
+ "Credit Reporting": 1,
22
+ "Credit/Prepaid Card": 2,
23
+ "Debt collection": 3,
24
+ "Loans / Mortgage": 4
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "pad_token_id": 0,
31
+ "problem_type": "single_label_classification",
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.37.2",
38
+ "vocab_size": 30522
39
+ }
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce5d2cb4ab9c9cb4c083b4dc93b7c2d57296a302be7e09cc45bc4e639773e09
3
+ size 267841796
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/saved_results/model_predictions_and_labels.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f53fb5feee64f66ed2ed4b66b7f2c4599d218c38de1d282995f60e8e913f4d9
3
+ size 53225557
finetuned-models/finetuned_on_product/distil-bert-fintuned-product-cfpb-complaints/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
+ }