Realgon commited on
Commit
28a4313
·
1 Parent(s): d782073

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD_left_10]": 50274,
3
+ "[PAD_left_11]": 50275,
4
+ "[PAD_left_12]": 50276,
5
+ "[PAD_left_13]": 50277,
6
+ "[PAD_left_14]": 50278,
7
+ "[PAD_left_15]": 50279,
8
+ "[PAD_left_16]": 50280,
9
+ "[PAD_left_17]": 50281,
10
+ "[PAD_left_18]": 50282,
11
+ "[PAD_left_19]": 50283,
12
+ "[PAD_left_1]": 50265,
13
+ "[PAD_left_20]": 50284,
14
+ "[PAD_left_21]": 50285,
15
+ "[PAD_left_22]": 50286,
16
+ "[PAD_left_23]": 50287,
17
+ "[PAD_left_24]": 50288,
18
+ "[PAD_left_25]": 50289,
19
+ "[PAD_left_26]": 50290,
20
+ "[PAD_left_27]": 50291,
21
+ "[PAD_left_28]": 50292,
22
+ "[PAD_left_29]": 50293,
23
+ "[PAD_left_2]": 50266,
24
+ "[PAD_left_30]": 50294,
25
+ "[PAD_left_31]": 50295,
26
+ "[PAD_left_32]": 50296,
27
+ "[PAD_left_33]": 50297,
28
+ "[PAD_left_34]": 50298,
29
+ "[PAD_left_35]": 50299,
30
+ "[PAD_left_36]": 50300,
31
+ "[PAD_left_37]": 50301,
32
+ "[PAD_left_38]": 50302,
33
+ "[PAD_left_39]": 50303,
34
+ "[PAD_left_3]": 50267,
35
+ "[PAD_left_40]": 50304,
36
+ "[PAD_left_41]": 50305,
37
+ "[PAD_left_42]": 50306,
38
+ "[PAD_left_43]": 50307,
39
+ "[PAD_left_44]": 50308,
40
+ "[PAD_left_45]": 50309,
41
+ "[PAD_left_46]": 50310,
42
+ "[PAD_left_47]": 50311,
43
+ "[PAD_left_48]": 50312,
44
+ "[PAD_left_49]": 50313,
45
+ "[PAD_left_4]": 50268,
46
+ "[PAD_left_50]": 50314,
47
+ "[PAD_left_51]": 50315,
48
+ "[PAD_left_52]": 50316,
49
+ "[PAD_left_53]": 50317,
50
+ "[PAD_left_54]": 50318,
51
+ "[PAD_left_55]": 50319,
52
+ "[PAD_left_56]": 50320,
53
+ "[PAD_left_57]": 50321,
54
+ "[PAD_left_58]": 50322,
55
+ "[PAD_left_59]": 50323,
56
+ "[PAD_left_5]": 50269,
57
+ "[PAD_left_60]": 50324,
58
+ "[PAD_left_61]": 50325,
59
+ "[PAD_left_62]": 50326,
60
+ "[PAD_left_63]": 50327,
61
+ "[PAD_left_64]": 50328,
62
+ "[PAD_left_65]": 50329,
63
+ "[PAD_left_66]": 50330,
64
+ "[PAD_left_67]": 50331,
65
+ "[PAD_left_68]": 50332,
66
+ "[PAD_left_69]": 50333,
67
+ "[PAD_left_6]": 50270,
68
+ "[PAD_left_70]": 50334,
69
+ "[PAD_left_7]": 50271,
70
+ "[PAD_left_8]": 50272,
71
+ "[PAD_left_9]": 50273
72
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "World",
15
+ "1": "Sports",
16
+ "2": "Business",
17
+ "3": "Sci/Tech"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Business": 2,
23
+ "Sci/Tech": 3,
24
+ "Sports": 1,
25
+ "World": 0
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.33.2",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50335
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edde9cad93ebd1f69c888cb449eab5ae59d24efd40234fdcb2e1b1ef3a9944c5
3
+ size 498878833
special_tokens_map.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD_left_1]",
4
+ "[PAD_left_2]",
5
+ "[PAD_left_3]",
6
+ "[PAD_left_4]",
7
+ "[PAD_left_5]",
8
+ "[PAD_left_6]",
9
+ "[PAD_left_7]",
10
+ "[PAD_left_8]",
11
+ "[PAD_left_9]",
12
+ "[PAD_left_10]",
13
+ "[PAD_left_11]",
14
+ "[PAD_left_12]",
15
+ "[PAD_left_13]",
16
+ "[PAD_left_14]",
17
+ "[PAD_left_15]",
18
+ "[PAD_left_16]",
19
+ "[PAD_left_17]",
20
+ "[PAD_left_18]",
21
+ "[PAD_left_19]",
22
+ "[PAD_left_20]",
23
+ "[PAD_left_21]",
24
+ "[PAD_left_22]",
25
+ "[PAD_left_23]",
26
+ "[PAD_left_24]",
27
+ "[PAD_left_25]",
28
+ "[PAD_left_26]",
29
+ "[PAD_left_27]",
30
+ "[PAD_left_28]",
31
+ "[PAD_left_29]",
32
+ "[PAD_left_30]",
33
+ "[PAD_left_31]",
34
+ "[PAD_left_32]",
35
+ "[PAD_left_33]",
36
+ "[PAD_left_34]",
37
+ "[PAD_left_35]",
38
+ "[PAD_left_36]",
39
+ "[PAD_left_37]",
40
+ "[PAD_left_38]",
41
+ "[PAD_left_39]",
42
+ "[PAD_left_40]",
43
+ "[PAD_left_41]",
44
+ "[PAD_left_42]",
45
+ "[PAD_left_43]",
46
+ "[PAD_left_44]",
47
+ "[PAD_left_45]",
48
+ "[PAD_left_46]",
49
+ "[PAD_left_47]",
50
+ "[PAD_left_48]",
51
+ "[PAD_left_49]",
52
+ "[PAD_left_50]",
53
+ "[PAD_left_51]",
54
+ "[PAD_left_52]",
55
+ "[PAD_left_53]",
56
+ "[PAD_left_54]",
57
+ "[PAD_left_55]",
58
+ "[PAD_left_56]",
59
+ "[PAD_left_57]",
60
+ "[PAD_left_58]",
61
+ "[PAD_left_59]",
62
+ "[PAD_left_60]",
63
+ "[PAD_left_61]",
64
+ "[PAD_left_62]",
65
+ "[PAD_left_63]",
66
+ "[PAD_left_64]",
67
+ "[PAD_left_65]",
68
+ "[PAD_left_66]",
69
+ "[PAD_left_67]",
70
+ "[PAD_left_68]",
71
+ "[PAD_left_69]",
72
+ "[PAD_left_70]"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": {
78
+ "content": "<mask>",
79
+ "lstrip": true,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false
83
+ },
84
+ "pad_token": "<pad>",
85
+ "sep_token": "</s>",
86
+ "unk_token": "<unk>"
87
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b82499f4c675d1196a085d0caccbd8b8d28889adaad301da4f393db227c275
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff