tangminhanh
commited on
Commit
•
1c1e357
1
Parent(s):
689b1b3
fin_subcate
Browse files- README.md +72 -0
- added_tokens.json +3 -0
- config.json +80 -0
- model.safetensors +3 -0
- runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374382.caf7575f2689.10048.0 +3 -0
- runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374877.caf7575f2689.10048.1 +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/deberta-v3-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: fin_subcate
|
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 |
+
# fin_subcate
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0671
|
24 |
+
- Accuracy: 0.6825
|
25 |
+
- F1: 0.7671
|
26 |
+
- Precision: 0.8756
|
27 |
+
- Recall: 0.6825
|
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: 64
|
48 |
+
- eval_batch_size: 128
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 7
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| No log | 1.0 | 64 | 0.1875 | 0.0 | 0.0 | 0.0 | 0.0 |
|
59 |
+
| No log | 2.0 | 128 | 0.1179 | 0.5134 | 0.6578 | 0.9153 | 0.5134 |
|
60 |
+
| No log | 3.0 | 192 | 0.0931 | 0.5124 | 0.6680 | 0.9593 | 0.5124 |
|
61 |
+
| No log | 4.0 | 256 | 0.0798 | 0.6231 | 0.7343 | 0.8936 | 0.6231 |
|
62 |
+
| No log | 5.0 | 320 | 0.0717 | 0.6508 | 0.7550 | 0.8989 | 0.6508 |
|
63 |
+
| No log | 6.0 | 384 | 0.0684 | 0.6746 | 0.7629 | 0.8777 | 0.6746 |
|
64 |
+
| No log | 7.0 | 448 | 0.0671 | 0.6825 | 0.7671 | 0.8756 | 0.6825 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.42.4
|
70 |
+
- Pytorch 2.3.1+cu121
|
71 |
+
- Datasets 2.20.0
|
72 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "Other Request",
|
12 |
+
"1": "Below 20k invoices (No PO)",
|
13 |
+
"2": "Client Cash advance",
|
14 |
+
"3": "Client Refund",
|
15 |
+
"4": "Confidential Payments Requests",
|
16 |
+
"5": "Complicated Report",
|
17 |
+
"6": "FORMS (Reimbursement, PCF, Credit Card Liquidation)",
|
18 |
+
"7": "Internal & External reimb request",
|
19 |
+
"8": "Petty Cash Request",
|
20 |
+
"9": "PO invoices",
|
21 |
+
"10": "Recurring bills (rentals, utilities, telco, etc.)",
|
22 |
+
"11": "Simple Report",
|
23 |
+
"12": "Urgent requests (Business permits, other taxes etc.)",
|
24 |
+
"13": "Bank Request",
|
25 |
+
"14": "Cash Advance",
|
26 |
+
"15": "Client Request",
|
27 |
+
"16": "Government Statutory",
|
28 |
+
"17": "Last Pay",
|
29 |
+
"18": "Operations",
|
30 |
+
"19": "Taxes / BOC / LGU Payment"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"Bank Request": 13,
|
36 |
+
"Below 20k invoices (No PO)": 1,
|
37 |
+
"Cash Advance": 14,
|
38 |
+
"Client Cash advance": 2,
|
39 |
+
"Client Refund": 3,
|
40 |
+
"Client Request": 15,
|
41 |
+
"Complicated Report": 5,
|
42 |
+
"Confidential Payments Requests": 4,
|
43 |
+
"FORMS (Reimbursement, PCF, Credit Card Liquidation)": 6,
|
44 |
+
"Government Statutory": 16,
|
45 |
+
"Internal & External reimb request": 7,
|
46 |
+
"Last Pay": 17,
|
47 |
+
"Operations": 18,
|
48 |
+
"Other Request": 0,
|
49 |
+
"PO invoices": 9,
|
50 |
+
"Petty Cash Request": 8,
|
51 |
+
"Recurring bills (rentals, utilities, telco, etc.)": 10,
|
52 |
+
"Simple Report": 11,
|
53 |
+
"Taxes / BOC / LGU Payment": 19,
|
54 |
+
"Urgent requests (Business permits, other taxes etc.)": 12
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-07,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"max_relative_positions": -1,
|
59 |
+
"model_type": "deberta-v2",
|
60 |
+
"norm_rel_ebd": "layer_norm",
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_hidden_layers": 6,
|
63 |
+
"pad_token_id": 0,
|
64 |
+
"pooler_dropout": 0,
|
65 |
+
"pooler_hidden_act": "gelu",
|
66 |
+
"pooler_hidden_size": 768,
|
67 |
+
"pos_att_type": [
|
68 |
+
"p2c",
|
69 |
+
"c2p"
|
70 |
+
],
|
71 |
+
"position_biased_input": false,
|
72 |
+
"position_buckets": 256,
|
73 |
+
"problem_type": "multi_label_classification",
|
74 |
+
"relative_attention": true,
|
75 |
+
"share_att_key": true,
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.42.4",
|
78 |
+
"type_vocab_size": 0,
|
79 |
+
"vocab_size": 128100
|
80 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268552d53863bcf892b3ecf81605436ad6bdca5bc06645b6070869e069511cc4
|
3 |
+
size 567653928
|
runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374382.caf7575f2689.10048.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432bc51f3df8291ccddbecc2cea3ba009179fac8d5ef5766f876f4397f05a123
|
3 |
+
size 10097
|
runs/Jul19_07-32-49_caf7575f2689/events.out.tfevents.1721374877.caf7575f2689.10048.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a985235243bbd641c80b724f08de9cc0e79261525f6ae9e038d87d636c3f20
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"split_by_punct": false,
|
55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
56 |
+
"unk_token": "[UNK]",
|
57 |
+
"vocab_type": "spm"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d85915cb4cf9411d4d1778f4950a390e7df63857eb086a0fad5d2cde4996e4e
|
3 |
+
size 5112
|