Training in progress, epoch 1
Browse files- README.md +66 -0
- config.json +63 -0
- model.safetensors +3 -0
- runs/Mar31_00-10-44_d1026/events.out.tfevents.1711858247.d1026 +3 -0
- runs/Mar31_01-35-36_d1026/events.out.tfevents.1711863338.d1026 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
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-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: 0.7196
|
24 |
+
- Accuracy: 0.7450
|
25 |
+
- Precision: 0.5763
|
26 |
+
- Recall: 0.5233
|
27 |
+
- F1: 0.5371
|
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 |
+
| 0.7281 | 1.0 | 11603 | 0.7196 | 0.7450 | 0.5763 | 0.5233 | 0.5371 |
|
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
|
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 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0c1858294df47b24072c932b6341cb0791a566421a29df04dbe0ea77b14bb80
|
3 |
+
size 267878708
|
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
|
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:bc7d7d57eaaafb2932c19f852301a505251a379d3dd319359d8d08c49931d4a4
|
3 |
+
size 9630
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab92b4eaa43f951a436c810b0973f0b78ad0ba2ba68a6ceb8353b7c912ccc9b6
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|