tangminhanh
commited on
Commit
•
75aa983
1
Parent(s):
456b4da
cs_subcate
Browse files- README.md +75 -0
- added_tokens.json +3 -0
- config.json +116 -0
- model.safetensors +3 -0
- runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722961152.8286c2bd2340.1585.4 +3 -0
- runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722962285.8286c2bd2340.1585.5 +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: tangminhanh/ts_subcate
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: cs_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 |
+
# cs_subcate
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [tangminhanh/ts_subcate](https://huggingface.co/tangminhanh/ts_subcate) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0517
|
24 |
+
- Accuracy: 0.6283
|
25 |
+
- F1: 0.6777
|
26 |
+
- Precision: 0.7292
|
27 |
+
- Recall: 0.6330
|
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: 32
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| No log | 1.0 | 195 | 0.0649 | 0.2715 | 0.4110 | 0.8554 | 0.2704 |
|
59 |
+
| No log | 2.0 | 390 | 0.0532 | 0.5113 | 0.6149 | 0.7639 | 0.5145 |
|
60 |
+
| 0.0785 | 3.0 | 585 | 0.0515 | 0.5688 | 0.6404 | 0.7225 | 0.5750 |
|
61 |
+
| 0.0785 | 4.0 | 780 | 0.0496 | 0.5979 | 0.6606 | 0.7225 | 0.6085 |
|
62 |
+
| 0.0785 | 5.0 | 975 | 0.0492 | 0.6147 | 0.6753 | 0.7367 | 0.6233 |
|
63 |
+
| 0.0386 | 6.0 | 1170 | 0.0499 | 0.6141 | 0.6701 | 0.7151 | 0.6304 |
|
64 |
+
| 0.0386 | 7.0 | 1365 | 0.0503 | 0.6206 | 0.6754 | 0.7265 | 0.6310 |
|
65 |
+
| 0.0283 | 8.0 | 1560 | 0.0512 | 0.6199 | 0.6717 | 0.7129 | 0.6349 |
|
66 |
+
| 0.0283 | 9.0 | 1755 | 0.0515 | 0.6193 | 0.6720 | 0.7228 | 0.6278 |
|
67 |
+
| 0.0283 | 10.0 | 1950 | 0.0517 | 0.6283 | 0.6777 | 0.7292 | 0.6330 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.42.4
|
73 |
+
- Pytorch 2.3.1+cu121
|
74 |
+
- Datasets 2.20.0
|
75 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tangminhanh/ts_subcate",
|
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": "Power Outage",
|
12 |
+
"1": "Security Breach/ Theft",
|
13 |
+
"2": "AC Concerns",
|
14 |
+
"3": "Work Permit",
|
15 |
+
"4": "Move Out Request",
|
16 |
+
"5": "Move In Request",
|
17 |
+
"6": "Furniture Move",
|
18 |
+
"7": "Office Set-up",
|
19 |
+
"8": "Supplies Request",
|
20 |
+
"9": "Photo / Video Request",
|
21 |
+
"10": "Client Viewing Request",
|
22 |
+
"11": "Printing/Scan request",
|
23 |
+
"12": "Storage Request",
|
24 |
+
"13": "Cleaning request",
|
25 |
+
"14": "Parking / Car pass Requests",
|
26 |
+
"15": "Planned activities",
|
27 |
+
"16": "Medical Certificate Validation",
|
28 |
+
"17": "HMO Account Update",
|
29 |
+
"18": "Messengerial /Courier Service Request",
|
30 |
+
"19": "New Office Transfer",
|
31 |
+
"20": "Reservation (Rooms & Event Space)",
|
32 |
+
"21": "Shuttle Booking",
|
33 |
+
"22": "Van Repairs & Maintenance",
|
34 |
+
"23": "Repairs and Maintenance Request",
|
35 |
+
"24": "Visitor Access Request",
|
36 |
+
"25": "Approval Request",
|
37 |
+
"26": "Costing Request",
|
38 |
+
"27": "Info or Document Request",
|
39 |
+
"28": "Phone / Sim Requests",
|
40 |
+
"29": "Orientation / Training Request",
|
41 |
+
"30": "Assistance",
|
42 |
+
"31": "Access Cards / Room or Office Access Requests",
|
43 |
+
"32": "Safety Concerns",
|
44 |
+
"33": "Other Medical Concerns",
|
45 |
+
"34": "Checklists & Reports",
|
46 |
+
"35": "New Hire Kit Request",
|
47 |
+
"36": "Invoices",
|
48 |
+
"37": "Gatepass Request"
|
49 |
+
},
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"intermediate_size": 3072,
|
52 |
+
"label2id": {
|
53 |
+
"AC Concerns": 2,
|
54 |
+
"Access Cards / Room or Office Access Requests": 31,
|
55 |
+
"Approval Request": 25,
|
56 |
+
"Assistance": 30,
|
57 |
+
"Checklists & Reports": 34,
|
58 |
+
"Cleaning request": 13,
|
59 |
+
"Client Viewing Request": 10,
|
60 |
+
"Costing Request": 26,
|
61 |
+
"Furniture Move": 6,
|
62 |
+
"Gatepass Request": 37,
|
63 |
+
"HMO Account Update": 17,
|
64 |
+
"Info or Document Request": 27,
|
65 |
+
"Invoices": 36,
|
66 |
+
"Medical Certificate Validation": 16,
|
67 |
+
"Messengerial /Courier Service Request": 18,
|
68 |
+
"Move In Request": 5,
|
69 |
+
"Move Out Request": 4,
|
70 |
+
"New Hire Kit Request": 35,
|
71 |
+
"New Office Transfer": 19,
|
72 |
+
"Office Set-up": 7,
|
73 |
+
"Orientation / Training Request": 29,
|
74 |
+
"Other Medical Concerns": 33,
|
75 |
+
"Parking / Car pass Requests": 14,
|
76 |
+
"Phone / Sim Requests": 28,
|
77 |
+
"Photo / Video Request": 9,
|
78 |
+
"Planned activities": 15,
|
79 |
+
"Power Outage": 0,
|
80 |
+
"Printing/Scan request": 11,
|
81 |
+
"Repairs and Maintenance Request": 23,
|
82 |
+
"Reservation (Rooms & Event Space)": 20,
|
83 |
+
"Safety Concerns": 32,
|
84 |
+
"Security Breach/ Theft": 1,
|
85 |
+
"Shuttle Booking": 21,
|
86 |
+
"Storage Request": 12,
|
87 |
+
"Supplies Request": 8,
|
88 |
+
"Van Repairs & Maintenance": 22,
|
89 |
+
"Visitor Access Request": 24,
|
90 |
+
"Work Permit": 3
|
91 |
+
},
|
92 |
+
"layer_norm_eps": 1e-07,
|
93 |
+
"max_position_embeddings": 512,
|
94 |
+
"max_relative_positions": -1,
|
95 |
+
"model_type": "deberta-v2",
|
96 |
+
"norm_rel_ebd": "layer_norm",
|
97 |
+
"num_attention_heads": 12,
|
98 |
+
"num_hidden_layers": 6,
|
99 |
+
"pad_token_id": 0,
|
100 |
+
"pooler_dropout": 0,
|
101 |
+
"pooler_hidden_act": "gelu",
|
102 |
+
"pooler_hidden_size": 768,
|
103 |
+
"pos_att_type": [
|
104 |
+
"p2c",
|
105 |
+
"c2p"
|
106 |
+
],
|
107 |
+
"position_biased_input": false,
|
108 |
+
"position_buckets": 256,
|
109 |
+
"problem_type": "multi_label_classification",
|
110 |
+
"relative_attention": true,
|
111 |
+
"share_att_key": true,
|
112 |
+
"torch_dtype": "float32",
|
113 |
+
"transformers_version": "4.42.4",
|
114 |
+
"type_vocab_size": 0,
|
115 |
+
"vocab_size": 128100
|
116 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d190ce2f4c8b5a32ed86ab31689f27bdb450faf9f2a0549d2e35443b74996e1e
|
3 |
+
size 567709304
|
runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722961152.8286c2bd2340.1585.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1e598a68fdb128771f2f4e2b465eaaa3acb28a25e82d02a029c969827274e6
|
3 |
+
size 13372
|
runs/Aug06_16-19-05_8286c2bd2340/events.out.tfevents.1722962285.8286c2bd2340.1585.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e694f6c4fe909cb8839eb8d2494c71019df3b74ff8972527cbe0eea747ba875
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
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 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 512,
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"sp_model_kwargs": {},
|
58 |
+
"split_by_punct": false,
|
59 |
+
"stride": 0,
|
60 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]",
|
64 |
+
"vocab_type": "spm"
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d14a3d443acd097613a7c8eab12f47e482dac8a1997803c5ba1ddafa97bdf077
|
3 |
+
size 5112
|