markusiko commited on
Commit
c4a7814
·
1 Parent(s): cb25803

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/ruBert-base",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-!",
14
+ "1": "B-,",
15
+ "2": "B-.",
16
+ "3": "B-...",
17
+ "4": "B-:",
18
+ "5": "B-?",
19
+ "6": "O"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "B-!": 0,
25
+ "B-,": 1,
26
+ "B-.": 2,
27
+ "B-...": 3,
28
+ "B-:": 4,
29
+ "B-?": 5,
30
+ "O": 6
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "pooler_fc_size": 768,
39
+ "pooler_num_attention_heads": 12,
40
+ "pooler_num_fc_layers": 3,
41
+ "pooler_size_per_head": 128,
42
+ "pooler_type": "first_token_transform",
43
+ "position_embedding_type": "absolute",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.31.0",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 120138
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ed023e34b6f0c59021d57007bc457e25ffe41e45d09ffe06775daa2a52d1c8
3
+ size 710956646
runs/Mar02_15-32-14_DESKTOP-4943SUE/events.out.tfevents.1709382759.DESKTOP-4943SUE.9596.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27da7d415214c2bea76bdca28df197137aa89eb11f41d76b925dfe7af27d4ce8
3
+ size 4436
runs/Mar02_15-32-53_DESKTOP-4943SUE/events.out.tfevents.1709382783.DESKTOP-4943SUE.9596.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb7b119c9e7451527ac4319d082ac66dac6794850a16d16f89c13be98ba27d3
3
+ size 5222
runs/Mar02_16-13-15_DESKTOP-4943SUE/events.out.tfevents.1709385238.DESKTOP-4943SUE.14748.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a8c8e32c6f0cf916b125cba60687ef5221ca272da0eb36477c4cd083b8fa24
3
+ size 5222
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2e4013bfb19f9b6ddc55cea87f2a38fbb3dcde578e7b43797eccc9cac4268f
3
+ size 4408
vocab.txt ADDED
The diff for this file is too large to render. See raw diff