poteminr commited on
Commit
f74fa76
·
verified ·
1 Parent(s): b7fab0b

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,28 +1,42 @@
1
  {
2
- "_name_or_path": "cointegrated/rubert-tiny2",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
 
 
 
 
 
7
  "classifier_dropout": null,
8
- "emb_size": 312,
9
- "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 312,
 
 
 
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 600,
 
 
 
 
15
  "layer_norm_eps": 1e-12,
16
  "max_position_embeddings": 2048,
17
  "model_type": "bert",
18
  "num_attention_heads": 12,
19
- "num_hidden_layers": 3,
20
  "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
  "problem_type": "single_label_classification",
 
 
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.44.2",
25
  "type_vocab_size": 2,
26
- "use_cache": true,
27
- "vocab_size": 83828
28
  }
 
1
  {
2
+ "_name_or_path": "Tochka-AI/ruRoPEBert-classic-base-2k",
3
  "architectures": [
4
+ "RoPEBertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertConfig",
9
+ "AutoModel": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertModel",
10
+ "AutoModelForMaskedLM": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForMaskedLM",
11
+ "AutoModelForSequenceClassification": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForSequenceClassification"
12
+ },
13
  "classifier_dropout": null,
14
+ "directionality": "bidi",
 
15
  "hidden_act": "gelu",
16
  "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "common",
20
+ "1": "toxic"
21
+ },
22
  "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "common": 0,
26
+ "toxic": 1
27
+ },
28
  "layer_norm_eps": 1e-12,
29
  "max_position_embeddings": 2048,
30
  "model_type": "bert",
31
  "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
  "pad_token_id": 0,
34
+ "pooler_type": "mean",
35
  "problem_type": "single_label_classification",
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.44.2",
40
  "type_vocab_size": 2,
41
+ "vocab_size": 120138
 
42
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75e340536f411f482955efa563747d2b1650fee11b5f4b38df80fc264277e511
3
- size 116784136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d02402663ef3690aa2d06713f9b6c77df8ea7120fd2306860da3918a8d9186a
3
+ size 709323472
runs/Sep12_23-15-18_legal-tech-0/events.out.tfevents.1726172119.legal-tech-0.1432.14 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cdc6c4ea73f15f25104cacbcc40865e4608e4b170b07b4adc61a082e01922d9
3
- size 6750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6723c40e7098c26b44e8594157e772cfbb79bd517fa960660c2c5b8eafcd2c8
3
+ size 7473
runs/Sep12_23-15-18_legal-tech-0/events.out.tfevents.1726172192.legal-tech-0.1432.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7081875b8a847d6236c4c1958bbb5f2841781b38f1638530825a031710383439
3
+ size 457
runs/Sep12_23-19-05_legal-tech-0/events.out.tfevents.1726172347.legal-tech-0.1764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a6968a2c6e00fc24ebb4647a08b9fddbb80954e6fc68df8ac1fb250ee6a108
3
+ size 5932
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -44,21 +44,14 @@
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
- "max_length": 512,
50
- "model_max_length": 512,
51
  "never_split": null,
52
- "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
54
- "pad_token_type_id": 0,
55
- "padding_side": "right",
56
  "sep_token": "[SEP]",
57
- "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
  "tokenizer_class": "BertTokenizer",
61
- "truncation_side": "right",
62
- "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
64
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 1024,
 
50
  "never_split": null,
 
51
  "pad_token": "[PAD]",
 
 
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b46fc84b00e25c9df275d3ff50b2c1d1548ad617e795bcf776ac8f7745f6d67
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e8b89ae3a26d9ec3f6ed982387591eaf92b8b710c629ae09c5dbc0bb308db1
3
  size 5240
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff