Stepa commited on
Commit
72e04bb
1 Parent(s): cae6ebc

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sberbank-ai/sbert_large_nlu_ru",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "MET",
16
+ "2": "ECO",
17
+ "3": "BIN",
18
+ "4": "CMP",
19
+ "5": "QUA",
20
+ "6": "ACT",
21
+ "7": "INST",
22
+ "8": "SOC"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "ACT": 6,
28
+ "BIN": 3,
29
+ "CMP": 4,
30
+ "ECO": 2,
31
+ "INST": 7,
32
+ "MET": 1,
33
+ "O": 0,
34
+ "QUA": 5,
35
+ "SOC": 8
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "pad_token_id": 0,
43
+ "pooler_fc_size": 768,
44
+ "pooler_num_attention_heads": 12,
45
+ "pooler_num_fc_layers": 3,
46
+ "pooler_size_per_head": 128,
47
+ "pooler_type": "first_token_transform",
48
+ "position_embedding_type": "absolute",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.26.0",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 120138
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5927a61f9701c7f2f867eff90d3919056863290d0fb8c93f6939fa0f5409eb42
3
+ size 1703611373
runs/Jan25_07-37-03_833358f53258/1674632236.5791655/events.out.tfevents.1674632236.833358f53258.244.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e827237997db34b46f538740d181443db6667a6c1f7168d0be9e61b62e5352
3
+ size 5667
runs/Jan25_07-37-03_833358f53258/events.out.tfevents.1674632236.833358f53258.244.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24499055fbcb3156c5cf6104edf2ad6dc04c00d9d317c7b3f348226133e52ea
3
+ size 4779
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "sberbank-ai/sbert_large_nlu_ru",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81dd9839d0198589a9489eb7b935d2b7964ab65b2cbc92cf78da3f39d3e05465
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff