Realgon commited on
Commit
433527d
1 Parent(s): c5d0f6c

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD_left_10]": 30531,
3
+ "[PAD_left_11]": 30532,
4
+ "[PAD_left_12]": 30533,
5
+ "[PAD_left_13]": 30534,
6
+ "[PAD_left_14]": 30535,
7
+ "[PAD_left_15]": 30536,
8
+ "[PAD_left_16]": 30537,
9
+ "[PAD_left_17]": 30538,
10
+ "[PAD_left_18]": 30539,
11
+ "[PAD_left_19]": 30540,
12
+ "[PAD_left_1]": 30522,
13
+ "[PAD_left_20]": 30541,
14
+ "[PAD_left_21]": 30542,
15
+ "[PAD_left_22]": 30543,
16
+ "[PAD_left_23]": 30544,
17
+ "[PAD_left_24]": 30545,
18
+ "[PAD_left_25]": 30546,
19
+ "[PAD_left_26]": 30547,
20
+ "[PAD_left_27]": 30548,
21
+ "[PAD_left_28]": 30549,
22
+ "[PAD_left_29]": 30550,
23
+ "[PAD_left_2]": 30523,
24
+ "[PAD_left_30]": 30551,
25
+ "[PAD_left_31]": 30552,
26
+ "[PAD_left_32]": 30553,
27
+ "[PAD_left_33]": 30554,
28
+ "[PAD_left_34]": 30555,
29
+ "[PAD_left_35]": 30556,
30
+ "[PAD_left_36]": 30557,
31
+ "[PAD_left_37]": 30558,
32
+ "[PAD_left_38]": 30559,
33
+ "[PAD_left_39]": 30560,
34
+ "[PAD_left_3]": 30524,
35
+ "[PAD_left_40]": 30561,
36
+ "[PAD_left_4]": 30525,
37
+ "[PAD_left_5]": 30526,
38
+ "[PAD_left_6]": 30527,
39
+ "[PAD_left_7]": 30528,
40
+ "[PAD_left_8]": 30529,
41
+ "[PAD_left_9]": 30530
42
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NEGATIVE": 0,
20
+ "POSITIVE": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.33.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30562
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd2eafc683f04d6f8d0f33140f61a8b821a20590f848ef8a2948c4f28e68a90
3
+ size 438126385
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
44
+ "cls_token": "[CLS]",
45
+ "mask_token": "[MASK]",
46
+ "pad_token": "[PAD]",
47
+ "sep_token": "[SEP]",
48
+ "unk_token": "[UNK]"
49
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea33beb6f118bb778ad7ad6d5890e1c70bbc0a51bd0259c91ed5d973b806b373
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff