AriaStarkh commited on
Commit
f4ab0c0
1 Parent(s): 34ccd59

Training in progress, step 42

Browse files
config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "label2id": {
65
+ "LABEL_0": 0,
66
+ "LABEL_1": 1,
67
+ "LABEL_10": 10,
68
+ "LABEL_11": 11,
69
+ "LABEL_12": 12,
70
+ "LABEL_13": 13,
71
+ "LABEL_14": 14,
72
+ "LABEL_15": 15,
73
+ "LABEL_16": 16,
74
+ "LABEL_17": 17,
75
+ "LABEL_18": 18,
76
+ "LABEL_19": 19,
77
+ "LABEL_2": 2,
78
+ "LABEL_20": 20,
79
+ "LABEL_21": 21,
80
+ "LABEL_22": 22,
81
+ "LABEL_23": 23,
82
+ "LABEL_24": 24,
83
+ "LABEL_25": 25,
84
+ "LABEL_26": 26,
85
+ "LABEL_27": 27,
86
+ "LABEL_28": 28,
87
+ "LABEL_29": 29,
88
+ "LABEL_3": 3,
89
+ "LABEL_30": 30,
90
+ "LABEL_31": 31,
91
+ "LABEL_32": 32,
92
+ "LABEL_33": 33,
93
+ "LABEL_34": 34,
94
+ "LABEL_35": 35,
95
+ "LABEL_36": 36,
96
+ "LABEL_37": 37,
97
+ "LABEL_38": 38,
98
+ "LABEL_39": 39,
99
+ "LABEL_4": 4,
100
+ "LABEL_40": 40,
101
+ "LABEL_41": 41,
102
+ "LABEL_42": 42,
103
+ "LABEL_43": 43,
104
+ "LABEL_44": 44,
105
+ "LABEL_45": 45,
106
+ "LABEL_46": 46,
107
+ "LABEL_47": 47,
108
+ "LABEL_48": 48,
109
+ "LABEL_49": 49,
110
+ "LABEL_5": 5,
111
+ "LABEL_6": 6,
112
+ "LABEL_7": 7,
113
+ "LABEL_8": 8,
114
+ "LABEL_9": 9
115
+ },
116
+ "max_position_embeddings": 512,
117
+ "model_type": "distilbert",
118
+ "n_heads": 12,
119
+ "n_layers": 6,
120
+ "pad_token_id": 0,
121
+ "problem_type": "single_label_classification",
122
+ "qa_dropout": 0.1,
123
+ "seq_classif_dropout": 0.2,
124
+ "sinusoidal_pos_embds": false,
125
+ "tie_weights_": true,
126
+ "torch_dtype": "float32",
127
+ "transformers_version": "4.46.3",
128
+ "vocab_size": 30522
129
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc1bef311fcea51df2bd17d35e3b41be09787ac31461aea85df42c94ee6e644
3
+ size 267980224
runs/Dec14_20-27-42_65438b340de8/events.out.tfevents.1734208119.65438b340de8.113.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c113d2dccc9966eac10a6f1689dc63aac80e3879547e7ad01174c20e71c10c
3
+ size 7050
runs/Dec14_20-36-29_65438b340de8/events.out.tfevents.1734208590.65438b340de8.113.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c54d41b17be7986183bcaeb735b3bbd6915ff3fac200e9f7d6a266e46b2315
3
+ size 7050
runs/Dec14_20-39-11_65438b340de8/events.out.tfevents.1734208755.65438b340de8.4249.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee37c6a84150893d630e4f2cab7dd895ffca43ac3dbbf1986a6d30ca6a5e132
3
+ size 7381
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4be3aded3a9d8dd6d9c5c92cebcc6334ba062055e82284a7c71bbdb7ac5ffd2
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff