Hugging Face's logo

chronologic
/
chronologic-date-deberta

Text Classification
Transformers
Safetensors
English
deberta-v2
digital-humanities
historical-text
dating
deberta-v3
chronologic
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
tedunderwood commited on
Commit
dcfa14c
·
verified ·
1 Parent(s): a3ec452

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. added_tokens.json +3 -0
  2. config.json +115 -0
  3. learning_curve.png +0 -0
  4. metrics.json +59 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +15 -0
  7. spm.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +59 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "date_bin_width": 10,
7
+ "date_grid_hi": 2040,
8
+ "date_grid_lo": 1680,
9
+ "date_sigma": 15.0,
10
+ "dtype": "float32",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13",
29
+ "14": "LABEL_14",
30
+ "15": "LABEL_15",
31
+ "16": "LABEL_16",
32
+ "17": "LABEL_17",
33
+ "18": "LABEL_18",
34
+ "19": "LABEL_19",
35
+ "20": "LABEL_20",
36
+ "21": "LABEL_21",
37
+ "22": "LABEL_22",
38
+ "23": "LABEL_23",
39
+ "24": "LABEL_24",
40
+ "25": "LABEL_25",
41
+ "26": "LABEL_26",
42
+ "27": "LABEL_27",
43
+ "28": "LABEL_28",
44
+ "29": "LABEL_29",
45
+ "30": "LABEL_30",
46
+ "31": "LABEL_31",
47
+ "32": "LABEL_32",
48
+ "33": "LABEL_33",
49
+ "34": "LABEL_34",
50
+ "35": "LABEL_35"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1,
57
+ "LABEL_10": 10,
58
+ "LABEL_11": 11,
59
+ "LABEL_12": 12,
60
+ "LABEL_13": 13,
61
+ "LABEL_14": 14,
62
+ "LABEL_15": 15,
63
+ "LABEL_16": 16,
64
+ "LABEL_17": 17,
65
+ "LABEL_18": 18,
66
+ "LABEL_19": 19,
67
+ "LABEL_2": 2,
68
+ "LABEL_20": 20,
69
+ "LABEL_21": 21,
70
+ "LABEL_22": 22,
71
+ "LABEL_23": 23,
72
+ "LABEL_24": 24,
73
+ "LABEL_25": 25,
74
+ "LABEL_26": 26,
75
+ "LABEL_27": 27,
76
+ "LABEL_28": 28,
77
+ "LABEL_29": 29,
78
+ "LABEL_3": 3,
79
+ "LABEL_30": 30,
80
+ "LABEL_31": 31,
81
+ "LABEL_32": 32,
82
+ "LABEL_33": 33,
83
+ "LABEL_34": 34,
84
+ "LABEL_35": 35,
85
+ "LABEL_4": 4,
86
+ "LABEL_5": 5,
87
+ "LABEL_6": 6,
88
+ "LABEL_7": 7,
89
+ "LABEL_8": 8,
90
+ "LABEL_9": 9
91
+ },
92
+ "layer_norm_eps": 1e-07,
93
+ "legacy": true,
94
+ "max_position_embeddings": 512,
95
+ "max_relative_positions": -1,
96
+ "model_type": "deberta-v2",
97
+ "norm_rel_ebd": "layer_norm",
98
+ "num_attention_heads": 16,
99
+ "num_hidden_layers": 24,
100
+ "pad_token_id": 0,
101
+ "pooler_dropout": 0,
102
+ "pooler_hidden_act": "gelu",
103
+ "pooler_hidden_size": 1024,
104
+ "pos_att_type": [
105
+ "p2c",
106
+ "c2p"
107
+ ],
108
+ "position_biased_input": false,
109
+ "position_buckets": 256,
110
+ "relative_attention": true,
111
+ "share_att_key": true,
112
+ "transformers_version": "4.57.6",
113
+ "type_vocab_size": 0,
114
+ "vocab_size": 128100
115
+ }
learning_curve.png ADDED
metrics.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "save_strategy": "best",
3
+ "best_metric": "loss",
4
+ "kept": "epoch 2 (loss=2.5448)",
5
+ "sigma": 15.0,
6
+ "grid": {
7
+ "lo": 1680,
8
+ "hi": 2040,
9
+ "bin_width": 10,
10
+ "n_bins": 36
11
+ },
12
+ "per_epoch": [
13
+ {
14
+ "epoch": 1,
15
+ "train_loss": 2.7892239493680413,
16
+ "loss": 2.5518224221645016,
17
+ "crps": 16.443814521454787,
18
+ "coverage50": 0.6501398818775257,
19
+ "coverage90": 0.9513521914827479,
20
+ "mae": 22.99976434860578
21
+ },
22
+ {
23
+ "epoch": 2,
24
+ "train_loss": 2.426014549244649,
25
+ "loss": 2.544819206884592,
26
+ "crps": 15.860059207809881,
27
+ "coverage50": 0.6338203294995337,
28
+ "coverage90": 0.9294373640037302,
29
+ "mae": 22.20244093954166
30
+ },
31
+ {
32
+ "epoch": 3,
33
+ "train_loss": 2.22739199123568,
34
+ "loss": 2.59886365007646,
35
+ "crps": 15.706490724804127,
36
+ "coverage50": 0.5887472800746036,
37
+ "coverage90": 0.885452284737333,
38
+ "mae": 21.451870806763328
39
+ },
40
+ {
41
+ "epoch": 4,
42
+ "train_loss": 2.0944060118355603,
43
+ "loss": 2.696276890759421,
44
+ "crps": 15.887976700048558,
45
+ "coverage50": 0.5556419023935344,
46
+ "coverage90": 0.8534348772147964,
47
+ "mae": 21.457977872573327
48
+ },
49
+ {
50
+ "epoch": 5,
51
+ "train_loss": 2.0083630453739727,
52
+ "loss": 2.7727811389630386,
53
+ "crps": 15.949291380865379,
54
+ "coverage50": 0.5335716506061549,
55
+ "coverage90": 0.8270127447932857,
56
+ "mae": 21.294442789257758
57
+ }
58
+ ]
59
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f428da5974b9626ed0d2bb44d288564916aadf2b195954f12f9931e5f9f60664
3
+ size 1740443856
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }