Hugging Face's logo

Stacy123
/
rubert_tiny2_qa

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files
xet
Metrics Community
4
Stacy123 commited on
Commit
49c872b
路
1 Parent(s): a5255f3

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +13 -8
  2. pytorch_model.bin +2 -2
  3. runs/Apr22_11-45-35_36865272420b/1682164581.7113652/events.out.tfevents.1682164581.36865272420b.343.1 +3 -0
  4. runs/Apr22_11-45-35_36865272420b/events.out.tfevents.1682164581.36865272420b.343.0 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +1 -1
  7. training_args.bin +1 -1
  8. vocab.txt +0 -0
config.json CHANGED
@@ -1,27 +1,32 @@
1
  {
2
- "_name_or_path": "cointegrated/rubert-tiny2",
3
  "architectures": [
4
  "BertForQuestionAnswering"
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
  "torch_dtype": "float32",
23
  "transformers_version": "4.28.1",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
- "vocab_size": 83828
27
  }
 
1
  {
2
+ "_name_or_path": "DeepPavlov/rubert-base-cased",
3
  "architectures": [
4
  "BertForQuestionAnswering"
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
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
  "model_type": "bert",
17
  "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
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": "4.28.1",
29
  "type_vocab_size": 2,
30
  "use_cache": true,
31
+ "vocab_size": 119547
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8ea33d56f0183198543ce4c2f1609dbb9f01d52439da219adedb41c0cf76125
3
- size 116421017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438a02af0f95b9561c5b079fa2a33019a4137146dfb46ba2345c61ed339353bc
3
+ size 709129709
runs/Apr22_11-45-35_36865272420b/1682164581.7113652/events.out.tfevents.1682164581.36865272420b.343.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa2e2907af225b45b2ef9e0e7cc1b5d3547d8654a2333cc8bda4040b4258a5e
3
+ size 5871
runs/Apr22_11-45-35_36865272420b/events.out.tfevents.1682164581.36865272420b.343.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2b1d9271115299bad216f4da756a2952a4da6aecfc1e57ec0b7616d5d0899b
3
+ size 4594
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
- "model_max_length": 2048,
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
 
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c866d34c9ec9e2a4498717b471d0c6e55eedd299e786414931f94c262ddd8f7
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51660fd9bcad3890c175dd169fecb6886d80b6c2ada4e7aa8cc50c330e492c10
3
  size 3579
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff