Hugging Face's logo

janeel
/
bigbird-base-trivia-itc-finetuned-squad

Question Answering
Transformers
PyTorch
TensorBoard
big_bird
Inference Endpoints
Model card Files Metrics Community
janeel commited on
Commit
3418acd
•
1 Parent(s): c9eec23

Training in progress, step 500

Browse files
Files changed (11) hide show
  1. .gitignore +1 -0
  2. config.json +34 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. runs/Jun18_12-32-48_Ibf388060900401b0d/1655526790.1305344/events.out.tfevents.1655526790.Ibf388060900401b0d.6415.1 +3 -0
  6. runs/Jun18_12-32-48_Ibf388060900401b0d/events.out.tfevents.1655526790.Ibf388060900401b0d.6415.0 +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +67 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-base-trivia-itc",
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": "4.20.0",
30
+ "type_vocab_size": 16,
31
+ "use_bias": true,
32
+ "use_cache": true,
33
+ "vocab_size": 50358
34
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d14439e61f7aff460dc1c2f367c6ca5b5e88029a72703c40e7a4a1785c43ba1
3
+ size 526558885
runs/Jun18_12-32-48_Ibf388060900401b0d/1655526790.1305344/events.out.tfevents.1655526790.Ibf388060900401b0d.6415.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3014b6c005908651e38f65eb2d3c3721af448d47a9e1d49277347c368a214c4f
3
+ size 5392
runs/Jun18_12-32-48_Ibf388060900401b0d/events.out.tfevents.1655526790.Ibf388060900401b0d.6415.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc41ff9565a1d52406aae07520a67bab7058ef9996380abc6483779aa8bacda6
3
+ size 4060
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
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": "</s>",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "do_lower_case": false,
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "full_tokenizer_file": null,
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "<mask>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "model_max_length": 512,
39
+ "name_or_path": "nlpconnect/roberta-base-squad2-nq",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "<pad>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "</s>",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "special_tokens_map_file": "/root/.cache/huggingface/transformers/c9d2c178fac8d40234baa1833a3b1903d393729bf93ea34da247c07db24900d0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0",
57
+ "tokenizer_class": "RobertaTokenizer",
58
+ "trim_offsets": true,
59
+ "unk_token": {
60
+ "__type": "AddedToken",
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e0bc9fc61fc6825a861afc3c830a8aaca28c23d0125ec2967063dd65584969
3
+ size 3311
vocab.json ADDED
The diff for this file is too large to render. See raw diff