Hugging Face's logo

ruselkomp
/
tests-finetuned-squad-test-bert-2

Question Answering
Transformers
PyTorch
TensorBoard
bert
Model card Files
xet
 Metrics Community
1
ruselkomp commited on
Commit
4a7d9cc
路
1 Parent(s): 6376cb5

Training in progress, step 5000

Browse files
Files changed (12) hide show
  1. .gitignore +1 -0
  2. config.json +32 -0
  3. pytorch_model.bin +3 -0
  4. runs/May13_11-28-47_22419eae00bb/1652441340.3916287/events.out.tfevents.1652441340.22419eae00bb.85.3 +3 -0
  5. runs/May13_11-28-47_22419eae00bb/events.out.tfevents.1652441340.22419eae00bb.85.2 +3 -0
  6. runs/May13_11-30-26_22419eae00bb/1652441438.7528076/events.out.tfevents.1652441438.22419eae00bb.2798.1 +3 -0
  7. runs/May13_11-30-26_22419eae00bb/events.out.tfevents.1652441438.22419eae00bb.2798.0 +3 -0
  8. special_tokens_map.json +1 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -0
  11. training_args.bin +3 -0
  12. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sberbank-ai/sbert_large_nlu_ru",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.20.0.dev0",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 120138
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50308ee879a0a6a5d9a5cf09897d7a7b79e36f9c322caf9caeda0e8bf8a789ce
3
+ size 1703579825
runs/May13_11-28-47_22419eae00bb/1652441340.3916287/events.out.tfevents.1652441340.22419eae00bb.85.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:783feceee05b922bfdd8a84166940f010a0279e9f2b6781d2e80ef6dad8e2a5c
3
+ size 5208
runs/May13_11-28-47_22419eae00bb/events.out.tfevents.1652441340.22419eae00bb.85.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656d9c56d952a79b24416c56bf4e187e2ecfc5ccfeb2f37a5b3aceafb39872bc
3
+ size 3758
runs/May13_11-30-26_22419eae00bb/1652441438.7528076/events.out.tfevents.1652441438.22419eae00bb.2798.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f4519a44293339bf329e249850134b03054e03d45692426e8a3774cf8b2e94
3
+ size 5208
runs/May13_11-30-26_22419eae00bb/events.out.tfevents.1652441438.22419eae00bb.2798.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a03b727f143d1ef39d87e7a51ec3c8e91b80eadc11f2d6a7a7d3c7d3905b69
3
+ size 5328
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "sberbank-ai/sbert_large_nlu_ru", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380e101d89a2bcd04340d08d508ee80362e98ae1fbae1d23a3425769b0ae9a8b
3
+ size 3247
vocab.txt ADDED
The diff for this file is too large to render. See raw diff