NastyaKorneeva commited on
Commit
a5768ed
1 Parent(s): 1d91c5d

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForTokenClassification"
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
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-Hard",
16
+ "2": "I-Hard",
17
+ "3": "B-Soft",
18
+ "4": "I-Soft",
19
+ "5": "B-Another",
20
+ "6": "I-Another"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 600,
24
+ "label2id": {
25
+ "B-Another": 5,
26
+ "B-Hard": 1,
27
+ "B-Soft": 3,
28
+ "I-Another": 6,
29
+ "I-Hard": 2,
30
+ "I-Soft": 4,
31
+ "O": 0
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 2048,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 3,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.38.2",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 83828
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84125f185b608b73d9a83b4db97d0c4400553bcd2ecb1a196894c9bc7b8516b
3
+ size 116399580
runs/Apr21_17-11-08_67b1f523524f/events.out.tfevents.1713719469.67b1f523524f.495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00683e456032508b4bea36e26c21431d785499dedb14e61770210b5f389b5198
3
+ size 11424
runs/Apr21_18-01-37_67b1f523524f/events.out.tfevents.1713722498.67b1f523524f.14416.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75b725600dfbd803c2194919189088937727dae5e3f2f85c47aeec0a65c4f28
3
+ size 11424
runs/Apr21_18-05-51_67b1f523524f/events.out.tfevents.1713722752.67b1f523524f.15695.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e783407961a9bacaaeb776fff458b8a857ce5be3e8912d5ed6fe28ee8400f5
3
+ size 4923
runs/Apr21_18-06-22_67b1f523524f/events.out.tfevents.1713722783.67b1f523524f.15695.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc9e23b251fe277b78bee0632ff645eea40ea602547452e6fd03bfe7a6240f1c
3
+ size 11432
runs/Apr21_18-16-52_67b1f523524f/events.out.tfevents.1713723413.67b1f523524f.18543.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d5733a3f26663e379281a3c94ac043e14b5f2e3905f528a8f0055c42c7248d
3
+ size 4184
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": 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": 2048,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e24aa898cf9041a1f79199815dc3ba77f78e153f0dfa4614c5d13871cf3db2
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff