Hugging Face's logo

Eurosmart
/
bert-qa-mash-covid

Question Answering
Transformers
TensorBoard
Safetensors
bert
nlp
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Eurosmart commited on
Commit
bc4558b
•
1 Parent(s): f6f0dd2

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +17 -10
  2. model.safetensors +2 -2
  3. runs/Jun03_02-51-03_cb21c4b48093/events.out.tfevents.1717383064.cb21c4b48093.24.0 +3 -0
  4. special_tokens_map.json +44 -8
  5. spiece.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +32 -18
  8. training_args.bin +1 -1
config.json CHANGED
@@ -1,27 +1,34 @@
1
  {
2
- "_name_or_path": "FacebookAI/roberta-base",
3
  "architectures": [
4
- "RobertaForQuestionAnswering"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
 
 
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
- "hidden_act": "gelu",
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "roberta",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
- "pad_token_id": 1,
 
21
  "position_embedding_type": "absolute",
 
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.39.3",
24
- "type_vocab_size": 1,
 
25
  "use_cache": true,
26
- "vocab_size": 50265
27
  }
 
1
  {
2
+ "_name_or_path": "google/bigbird-roberta-base",
3
  "architectures": [
4
+ "BigBirdForQuestionAnswering"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "attention_type": "block_sparse",
8
+ "block_size": 64,
9
+ "bos_token_id": 1,
10
  "classifier_dropout": null,
11
  "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu_new",
14
  "hidden_dropout_prob": 0.1,
15
  "hidden_size": 768,
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 4096,
20
+ "model_type": "big_bird",
21
  "num_attention_heads": 12,
22
  "num_hidden_layers": 12,
23
+ "num_random_blocks": 3,
24
+ "pad_token_id": 0,
25
  "position_embedding_type": "absolute",
26
+ "rescale_embeddings": false,
27
+ "sep_token_id": 66,
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.39.3",
30
+ "type_vocab_size": 2,
31
+ "use_bias": true,
32
  "use_cache": true,
33
+ "vocab_size": 50358
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4109b86d83537719bd45a37b29fca9a39fd0ec459dee341db113144960186694
3
- size 496250232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a32e80bec60447003c245e1de82e84062700ec6e7602e7d8257491c3a71022
3
+ size 526438888
runs/Jun03_02-51-03_cb21c4b48093/events.out.tfevents.1717383064.cb21c4b48093.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e75f0476f52f5b84a0cf181c3069185e04028abfbf4f8d249f6668c9655f88
3
+ size 5039
special_tokens_map.json CHANGED
@@ -1,15 +1,51 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
- "content": "<mask>",
7
  "lstrip": true,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
+ "content": "[MASK]",
25
  "lstrip": true,
26
+ "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
3
+ size 845731
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
  "normalized": true,
8
  "rstrip": false,
@@ -10,7 +9,7 @@
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": true,
16
  "rstrip": false,
@@ -18,40 +17,55 @@
18
  "special": true
19
  },
20
  "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "50264": {
37
- "content": "<mask>",
 
 
 
 
 
 
 
 
38
  "lstrip": true,
39
- "normalized": false,
 
 
 
 
 
 
 
 
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 512,
52
  "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
  "unk_token": "<unk>"
57
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": true,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "</s>",
13
  "lstrip": false,
14
  "normalized": true,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "65": {
28
+ "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "66": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "67": {
44
+ "content": "[MASK]",
45
  "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "100": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
  }
59
  },
60
+ "bos_token": "</s>",
61
  "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "eos_token": "<s>",
64
+ "mask_token": "[MASK]",
65
+ "model_max_length": 4096,
 
66
  "pad_token": "<pad>",
67
+ "sep_token": "[SEP]",
68
+ "sp_model_kwargs": {},
69
+ "tokenizer_class": "BigBirdTokenizer",
70
  "unk_token": "<unk>"
71
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dbfa5d4f83d1c90a2e388204b5e41bbb868a79204c7e660da1b2a63ae0a8271
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4513f95a138c4a652d6cd1c5888bc11731fa75b5d0bc6b60908b419522db810
3
  size 4920