aishanur commited on
Commit
8f68bf9
1 Parent(s): da3e2c3

aishanur/HV_Roberta_Large_2

Browse files
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-large
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: deberta_large_hv_6
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # deberta_large_hv_6
15
+
16
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0584
19
+ - F1-macro subtask 1: 0.2413
20
+ - F1-micro subtask 1: 0.3199
21
+ - Roc auc macro subtask 1: 0.5924
22
+ - F1-macro subtask 2: 0.0495
23
+ - F1-micro subtask 2: 0.0516
24
+ - Roc auc macro subtask 2: 0.6138
25
+ - Self-direction: thought1: 0.0440
26
+ - Self-direction: action1: 0.1345
27
+ - Stimulation1: 0.2982
28
+ - Hedonism1: 0.3182
29
+ - Achievement1: 0.3198
30
+ - Power: dominance1: 0.1377
31
+ - Power: resources1: 0.1513
32
+ - Face1: 0.2367
33
+ - Security: personal1: 0.1859
34
+ - Security: societal1: 0.4505
35
+ - Tradition1: 0.4289
36
+ - Conformity: rules1: 0.4634
37
+ - Conformity: interpersonal1: 0.0623
38
+ - Humility1: 0.0533
39
+ - Benevolence: caring1: 0.0588
40
+ - Benevolence: dependability1: 0.1609
41
+ - Universalism: concern1: 0.3206
42
+ - Universalism: nature1: 0.5426
43
+ - Universalism: tolerance1: 0.2165
44
+ - Self-direction: thought attained2: 0.0187
45
+ - Self-direction: thought constrained2: 0.0730
46
+ - Self-direction: action attained2: 0.0523
47
+ - Self-direction: action constrained2: 0.0374
48
+ - Stimulation attained2: 0.0582
49
+ - Stimulation constrained2: 0.0110
50
+ - Hedonism attained2: 0.0164
51
+ - Hedonism constrained2: 0.0067
52
+ - Achievement attained2: 0.1265
53
+ - Achievement constrained2: 0.0800
54
+ - Power: dominance attained2: 0.0702
55
+ - Power: dominance constrained2: 0.0731
56
+ - Power: resources attained2: 0.0814
57
+ - Power: resources constrained2: 0.0820
58
+ - Face attained2: 0.0273
59
+ - Face constrained2: 0.0297
60
+ - Security: personal attained2: 0.0157
61
+ - Security: personal constrained2: 0.0571
62
+ - Security: societal attained2: 0.1026
63
+ - Security: societal constrained2: 0.1784
64
+ - Tradition attained2: 0.0352
65
+ - Tradition constrained2: 0.0173
66
+ - Conformity: rules attained2: 0.1159
67
+ - Conformity: rules constrained2: 0.0828
68
+ - Conformity: interpersonal attained2: 0.0171
69
+ - Conformity: interpersonal constrained2: 0.0267
70
+ - Humility attained2: 0.0066
71
+ - Humility constrained2: 0.0017
72
+ - Benevolence: caring attained2: 0.0424
73
+ - Benevolence: caring constrained2: 0.0182
74
+ - Benevolence: dependability attained2: 0.0346
75
+ - Benevolence: dependability constrained2: 0.0274
76
+ - Universalism: concern attained2: 0.0865
77
+ - Universalism: concern constrained2: 0.0568
78
+ - Universalism: nature attained2: 0.0464
79
+ - Universalism: nature constrained2: 0.0430
80
+ - Universalism: tolerance attained2: 0.0128
81
+ - Universalism: tolerance constrained2: 0.0134
82
+
83
+ ## Model description
84
+
85
+ More information needed
86
+
87
+ ## Intended uses & limitations
88
+
89
+ More information needed
90
+
91
+ ## Training and evaluation data
92
+
93
+ More information needed
94
+
95
+ ## Training procedure
96
+
97
+ ### Training hyperparameters
98
+
99
+ The following hyperparameters were used during training:
100
+ - learning_rate: 2e-05
101
+ - train_batch_size: 8
102
+ - eval_batch_size: 8
103
+ - seed: 42
104
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
105
+ - lr_scheduler_type: linear
106
+ - lr_scheduler_warmup_ratio: 0.2
107
+ - num_epochs: 4
108
+
109
+ ### Training results
110
+
111
+ | Training Loss | Epoch | Step | Validation Loss | F1-macro subtask 1 | F1-micro subtask 1 | Roc auc macro subtask 1 | F1-macro subtask 2 | F1-micro subtask 2 | Roc auc macro subtask 2 | Self-direction: thought1 | Self-direction: action1 | Stimulation1 | Hedonism1 | Achievement1 | Power: dominance1 | Power: resources1 | Face1 | Security: personal1 | Security: societal1 | Tradition1 | Conformity: rules1 | Conformity: interpersonal1 | Humility1 | Benevolence: caring1 | Benevolence: dependability1 | Universalism: concern1 | Universalism: nature1 | Universalism: tolerance1 | Self-direction: thought attained2 | Self-direction: thought constrained2 | Self-direction: action attained2 | Self-direction: action constrained2 | Stimulation attained2 | Stimulation constrained2 | Hedonism attained2 | Hedonism constrained2 | Achievement attained2 | Achievement constrained2 | Power: dominance attained2 | Power: dominance constrained2 | Power: resources attained2 | Power: resources constrained2 | Face attained2 | Face constrained2 | Security: personal attained2 | Security: personal constrained2 | Security: societal attained2 | Security: societal constrained2 | Tradition attained2 | Tradition constrained2 | Conformity: rules attained2 | Conformity: rules constrained2 | Conformity: interpersonal attained2 | Conformity: interpersonal constrained2 | Humility attained2 | Humility constrained2 | Benevolence: caring attained2 | Benevolence: caring constrained2 | Benevolence: dependability attained2 | Benevolence: dependability constrained2 | Universalism: concern attained2 | Universalism: concern constrained2 | Universalism: nature attained2 | Universalism: nature constrained2 | Universalism: tolerance attained2 | Universalism: tolerance constrained2 |
112
+ |:-------------:|:-----:|:-----:|:---------------:|:------------------:|:------------------:|:-----------------------:|:------------------:|:------------------:|:-----------------------:|:------------------------:|:-----------------------:|:------------:|:---------:|:------------:|:-----------------:|:-----------------:|:------:|:-------------------:|:-------------------:|:----------:|:------------------:|:--------------------------:|:---------:|:--------------------:|:---------------------------:|:----------------------:|:---------------------:|:------------------------:|:---------------------------------:|:------------------------------------:|:--------------------------------:|:-----------------------------------:|:---------------------:|:------------------------:|:------------------:|:---------------------:|:---------------------:|:------------------------:|:--------------------------:|:-----------------------------:|:--------------------------:|:-----------------------------:|:--------------:|:-----------------:|:----------------------------:|:-------------------------------:|:----------------------------:|:-------------------------------:|:-------------------:|:----------------------:|:---------------------------:|:------------------------------:|:-----------------------------------:|:--------------------------------------:|:------------------:|:---------------------:|:-----------------------------:|:--------------------------------:|:------------------------------------:|:---------------------------------------:|:-------------------------------:|:----------------------------------:|:------------------------------:|:---------------------------------:|:---------------------------------:|:------------------------------------:|
113
+ | 0.0601 | 1.0 | 7183 | 0.0610 | 0.1579 | 0.2399 | 0.5599 | 0.0481 | 0.0505 | 0.6300 | 0.0 | 0.0526 | 0.0235 | 0.0 | 0.2704 | 0.2361 | 0.2080 | 0.2443 | 0.0207 | 0.3901 | 0.2647 | 0.3168 | 0.0867 | 0.0 | 0.0270 | 0.0381 | 0.0687 | 0.5338 | 0.2180 | 0.0173 | 0.0169 | 0.0517 | 0.0521 | 0.0598 | 0.0132 | 0.0134 | 0.0074 | 0.1371 | 0.0682 | 0.0618 | 0.0615 | 0.0860 | 0.0705 | 0.0215 | 0.0463 | 0.0164 | 0.0486 | 0.1362 | 0.1329 | 0.0370 | 0.0166 | 0.0960 | 0.1105 | 0.0161 | 0.0334 | 0.0061 | 0.0018 | 0.0522 | 0.0137 | 0.0441 | 0.0145 | 0.0783 | 0.0643 | 0.0403 | 0.0545 | 0.0149 | 0.0136 |
114
+ | 0.038 | 2.0 | 14366 | 0.0584 | 0.2413 | 0.3199 | 0.5924 | 0.0495 | 0.0516 | 0.6138 | 0.0440 | 0.1345 | 0.2982 | 0.3182 | 0.3198 | 0.1377 | 0.1513 | 0.2367 | 0.1859 | 0.4505 | 0.4289 | 0.4634 | 0.0623 | 0.0533 | 0.0588 | 0.1609 | 0.3206 | 0.5426 | 0.2165 | 0.0187 | 0.0730 | 0.0523 | 0.0374 | 0.0582 | 0.0110 | 0.0164 | 0.0067 | 0.1265 | 0.0800 | 0.0702 | 0.0731 | 0.0814 | 0.0820 | 0.0273 | 0.0297 | 0.0157 | 0.0571 | 0.1026 | 0.1784 | 0.0352 | 0.0173 | 0.1159 | 0.0828 | 0.0171 | 0.0267 | 0.0066 | 0.0017 | 0.0424 | 0.0182 | 0.0346 | 0.0274 | 0.0865 | 0.0568 | 0.0464 | 0.0430 | 0.0128 | 0.0134 |
115
+ | 0.0239 | 3.0 | 21549 | 0.0623 | 0.2723 | 0.3465 | 0.6074 | 0.0523 | 0.0512 | 0.6170 | 0.0788 | 0.2017 | 0.2390 | 0.2920 | 0.3128 | 0.3410 | 0.2956 | 0.1950 | 0.2689 | 0.4408 | 0.4435 | 0.4632 | 0.0556 | 0.0392 | 0.1615 | 0.2495 | 0.3972 | 0.5443 | 0.1548 | 0.0187 | 0.1471 | 0.0525 | 0.0518 | 0.0692 | 0.0117 | 0.0133 | 0.0089 | 0.1289 | 0.0778 | 0.0698 | 0.0581 | 0.0804 | 0.0794 | 0.0229 | 0.0372 | 0.0190 | 0.0462 | 0.0967 | 0.1903 | 0.0328 | 0.0260 | 0.1065 | 0.0924 | 0.0169 | 0.0281 | 0.0071 | 0.0019 | 0.0428 | 0.0128 | 0.0336 | 0.0345 | 0.0766 | 0.0714 | 0.0409 | 0.0535 | 0.0186 | 0.0106 |
116
+ | 0.0208 | 4.0 | 28732 | 0.0699 | 0.2913 | 0.3585 | 0.6210 | 0.0489 | 0.0513 | 0.6155 | 0.1195 | 0.2460 | 0.3053 | 0.3660 | 0.3784 | 0.3366 | 0.3114 | 0.1915 | 0.3010 | 0.4442 | 0.4366 | 0.4609 | 0.0549 | 0.0385 | 0.2372 | 0.2329 | 0.3927 | 0.5479 | 0.1325 | 0.0188 | 0.1034 | 0.0534 | 0.0356 | 0.0673 | 0.0121 | 0.0144 | 0.0075 | 0.1251 | 0.0795 | 0.0799 | 0.0255 | 0.0837 | 0.0753 | 0.0215 | 0.0427 | 0.0190 | 0.0418 | 0.1069 | 0.1659 | 0.0347 | 0.0160 | 0.1180 | 0.0823 | 0.0212 | 0.0228 | 0.0064 | 0.0017 | 0.0455 | 0.0101 | 0.0354 | 0.0253 | 0.0788 | 0.0662 | 0.0450 | 0.0430 | 0.0140 | 0.0120 |
117
+
118
+
119
+ ### Framework versions
120
+
121
+ - Transformers 4.37.2
122
+ - Pytorch 2.3.0
123
+ - Datasets 2.19.0
124
+ - Tokenizers 0.15.1
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": "microsoft/deberta-v3-large",
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": 1024,
10
+ "id2label": {
11
+ "0": "Self-direction: thought attained",
12
+ "1": "Self-direction: thought constrained",
13
+ "2": "Self-direction: action attained",
14
+ "3": "Self-direction: action constrained",
15
+ "4": "Stimulation attained",
16
+ "5": "Stimulation constrained",
17
+ "6": "Hedonism attained",
18
+ "7": "Hedonism constrained",
19
+ "8": "Achievement attained",
20
+ "9": "Achievement constrained",
21
+ "10": "Power: dominance attained",
22
+ "11": "Power: dominance constrained",
23
+ "12": "Power: resources attained",
24
+ "13": "Power: resources constrained",
25
+ "14": "Face attained",
26
+ "15": "Face constrained",
27
+ "16": "Security: personal attained",
28
+ "17": "Security: personal constrained",
29
+ "18": "Security: societal attained",
30
+ "19": "Security: societal constrained",
31
+ "20": "Tradition attained",
32
+ "21": "Tradition constrained",
33
+ "22": "Conformity: rules attained",
34
+ "23": "Conformity: rules constrained",
35
+ "24": "Conformity: interpersonal attained",
36
+ "25": "Conformity: interpersonal constrained",
37
+ "26": "Humility attained",
38
+ "27": "Humility constrained",
39
+ "28": "Benevolence: caring attained",
40
+ "29": "Benevolence: caring constrained",
41
+ "30": "Benevolence: dependability attained",
42
+ "31": "Benevolence: dependability constrained",
43
+ "32": "Universalism: concern attained",
44
+ "33": "Universalism: concern constrained",
45
+ "34": "Universalism: nature attained",
46
+ "35": "Universalism: nature constrained",
47
+ "36": "Universalism: tolerance attained",
48
+ "37": "Universalism: tolerance constrained"
49
+ },
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 4096,
52
+ "label2id": {
53
+ "Achievement attained": 8,
54
+ "Achievement constrained": 9,
55
+ "Benevolence: caring attained": 28,
56
+ "Benevolence: caring constrained": 29,
57
+ "Benevolence: dependability attained": 30,
58
+ "Benevolence: dependability constrained": 31,
59
+ "Conformity: interpersonal attained": 24,
60
+ "Conformity: interpersonal constrained": 25,
61
+ "Conformity: rules attained": 22,
62
+ "Conformity: rules constrained": 23,
63
+ "Face attained": 14,
64
+ "Face constrained": 15,
65
+ "Hedonism attained": 6,
66
+ "Hedonism constrained": 7,
67
+ "Humility attained": 26,
68
+ "Humility constrained": 27,
69
+ "Power: dominance attained": 10,
70
+ "Power: dominance constrained": 11,
71
+ "Power: resources attained": 12,
72
+ "Power: resources constrained": 13,
73
+ "Security: personal attained": 16,
74
+ "Security: personal constrained": 17,
75
+ "Security: societal attained": 18,
76
+ "Security: societal constrained": 19,
77
+ "Self-direction: action attained": 2,
78
+ "Self-direction: action constrained": 3,
79
+ "Self-direction: thought attained": 0,
80
+ "Self-direction: thought constrained": 1,
81
+ "Stimulation attained": 4,
82
+ "Stimulation constrained": 5,
83
+ "Tradition attained": 20,
84
+ "Tradition constrained": 21,
85
+ "Universalism: concern attained": 32,
86
+ "Universalism: concern constrained": 33,
87
+ "Universalism: nature attained": 34,
88
+ "Universalism: nature constrained": 35,
89
+ "Universalism: tolerance attained": 36,
90
+ "Universalism: tolerance constrained": 37
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": 16,
98
+ "num_hidden_layers": 24,
99
+ "pad_token_id": 0,
100
+ "pooler_dropout": 0,
101
+ "pooler_hidden_act": "gelu",
102
+ "pooler_hidden_size": 1024,
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": "4.37.2",
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 sha256:37b7678f6f8170df1baaae66a8fd12bd59b34abf7bc392d9ec501c40d7b4d575
3
+ size 1740452056
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 sha256:89c4b6e7da53cc7e100f474b10719b2cd45a046b2fb4fdcfa01199cbd07fbe68
3
+ size 4728