tangminhanh
commited on
Commit
•
2eaf2b3
1
Parent(s):
33f3ebd
hr_cate
Browse files- README.md +70 -0
- added_tokens.json +3 -0
- config.json +88 -0
- model.safetensors +3 -0
- runs/Jul23_07-12-01_03d2ce878948/events.out.tfevents.1721718758.03d2ce878948.2032.0 +3 -0
- runs/Jul23_07-12-50_03d2ce878948/events.out.tfevents.1721718861.03d2ce878948.2032.1 +3 -0
- runs/Jul23_07-14-53_03d2ce878948/events.out.tfevents.1721718898.03d2ce878948.2032.2 +3 -0
- runs/Jul23_07-14-53_03d2ce878948/events.out.tfevents.1721720616.03d2ce878948.2032.3 +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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: hr_cate
|
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 |
+
# hr_cate
|
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: 0.0404
|
24 |
+
- Accuracy: 0.7833
|
25 |
+
- F1: 0.8459
|
26 |
+
- Precision: 0.9146
|
27 |
+
- Recall: 0.7869
|
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: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| No log | 1.0 | 227 | 0.0946 | 0.4140 | 0.5702 | 0.9179 | 0.4136 |
|
59 |
+
| No log | 2.0 | 454 | 0.0573 | 0.6871 | 0.7845 | 0.9153 | 0.6864 |
|
60 |
+
| 0.1387 | 3.0 | 681 | 0.0468 | 0.7629 | 0.8291 | 0.9091 | 0.7620 |
|
61 |
+
| 0.1387 | 4.0 | 908 | 0.0420 | 0.7722 | 0.8372 | 0.9138 | 0.7725 |
|
62 |
+
| 0.0456 | 5.0 | 1135 | 0.0404 | 0.7833 | 0.8459 | 0.9146 | 0.7869 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.42.4
|
68 |
+
- Pytorch 2.3.1+cu121
|
69 |
+
- Datasets 2.20.0
|
70 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "C&B - Payroll",
|
12 |
+
"1": "Talent as a Service",
|
13 |
+
"2": "HRDT - HRBP Requests",
|
14 |
+
"3": "HRDT - HRIS",
|
15 |
+
"4": "HRDT - Data Updating",
|
16 |
+
"5": "HRDT - Requested Report",
|
17 |
+
"6": "HRDT - Others",
|
18 |
+
"7": "P&C Allowance",
|
19 |
+
"8": "P&C Employee Movement/EAA Request",
|
20 |
+
"9": "P&C HR Documents",
|
21 |
+
"10": "P&C HRIS",
|
22 |
+
"11": "P&C Incident Report/Employee Discipline",
|
23 |
+
"12": "P&C Inquiries",
|
24 |
+
"13": "P&C Internship",
|
25 |
+
"14": "P&C Leave Benefits",
|
26 |
+
"15": "P&C Mental Health / MindNation",
|
27 |
+
"16": "P&C Payroll",
|
28 |
+
"17": "P&C Performance/Coaching",
|
29 |
+
"18": "P&C Reports",
|
30 |
+
"19": "P&C Resignation/Offboarding",
|
31 |
+
"20": "P&C SSS | Pag-Ibig | Philhealth | BIR",
|
32 |
+
"21": "P&C Verification",
|
33 |
+
"22": "P&C Others",
|
34 |
+
"23": "People Experience"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"C&B - Payroll": 0,
|
40 |
+
"HRDT - Data Updating": 4,
|
41 |
+
"HRDT - HRBP Requests": 2,
|
42 |
+
"HRDT - HRIS": 3,
|
43 |
+
"HRDT - Others": 6,
|
44 |
+
"HRDT - Requested Report": 5,
|
45 |
+
"P&C Allowance": 7,
|
46 |
+
"P&C Employee Movement/EAA Request": 8,
|
47 |
+
"P&C HR Documents": 9,
|
48 |
+
"P&C HRIS": 10,
|
49 |
+
"P&C Incident Report/Employee Discipline": 11,
|
50 |
+
"P&C Inquiries": 12,
|
51 |
+
"P&C Internship": 13,
|
52 |
+
"P&C Leave Benefits": 14,
|
53 |
+
"P&C Mental Health / MindNation": 15,
|
54 |
+
"P&C Others": 22,
|
55 |
+
"P&C Payroll": 16,
|
56 |
+
"P&C Performance/Coaching": 17,
|
57 |
+
"P&C Reports": 18,
|
58 |
+
"P&C Resignation/Offboarding": 19,
|
59 |
+
"P&C SSS | Pag-Ibig | Philhealth | BIR": 20,
|
60 |
+
"P&C Verification": 21,
|
61 |
+
"People Experience": 23,
|
62 |
+
"Talent as a Service": 1
|
63 |
+
},
|
64 |
+
"layer_norm_eps": 1e-07,
|
65 |
+
"max_position_embeddings": 512,
|
66 |
+
"max_relative_positions": -1,
|
67 |
+
"model_type": "deberta-v2",
|
68 |
+
"norm_rel_ebd": "layer_norm",
|
69 |
+
"num_attention_heads": 12,
|
70 |
+
"num_hidden_layers": 6,
|
71 |
+
"pad_token_id": 0,
|
72 |
+
"pooler_dropout": 0,
|
73 |
+
"pooler_hidden_act": "gelu",
|
74 |
+
"pooler_hidden_size": 768,
|
75 |
+
"pos_att_type": [
|
76 |
+
"p2c",
|
77 |
+
"c2p"
|
78 |
+
],
|
79 |
+
"position_biased_input": false,
|
80 |
+
"position_buckets": 256,
|
81 |
+
"problem_type": "multi_label_classification",
|
82 |
+
"relative_attention": true,
|
83 |
+
"share_att_key": true,
|
84 |
+
"torch_dtype": "float32",
|
85 |
+
"transformers_version": "4.42.4",
|
86 |
+
"type_vocab_size": 0,
|
87 |
+
"vocab_size": 128100
|
88 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2877bf0a6211901870e913c877ca4aaaf263ff542ad94764944a3b6bc7db9cf7
|
3 |
+
size 567666232
|
runs/Jul23_07-12-01_03d2ce878948/events.out.tfevents.1721718758.03d2ce878948.2032.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3beaa4fb66580dc89f14d6f711798b6fd1f8178bbb072bdfeea484990c3ee93c
|
3 |
+
size 6558
|
runs/Jul23_07-12-50_03d2ce878948/events.out.tfevents.1721718861.03d2ce878948.2032.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e93be80aad0c5c436c4c4f7eefe58b82e620c7deb0364addfbb45ff72933d91
|
3 |
+
size 6558
|
runs/Jul23_07-14-53_03d2ce878948/events.out.tfevents.1721718898.03d2ce878948.2032.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e456fde4cae7c3e40361bc5b8197be9831ea4265e659761bb1570f8fb3424a
|
3 |
+
size 9693
|
runs/Jul23_07-14-53_03d2ce878948/events.out.tfevents.1721720616.03d2ce878948.2032.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9cc50eb095c9952c429fa5755a0c47e695f6eb9b1d82bcfbee314d2d810fd9e
|
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:e5a24e200676d44b13a01c7a0c8f53c2247da38c9fc30dc030242781ac930d0e
|
3 |
+
size 5112
|