Hugging Face's logo

sharmadhruv
/
my_awesome_qa_model

Question Answering
Transformers
TensorBoard
Safetensors
bigbird_pegasus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sharmadhruv commited on
Commit
9edbb33
•
1 Parent(s): 549c467

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +43 -43
  2. model.safetensors +2 -2
  3. runs/Jun19_18-37-49_LAPTOP-B4AUIBJE/events.out.tfevents.1718802487.LAPTOP-B4AUIBJE.45372.0 +3 -0
  4. runs/Jun19_18-40-17_LAPTOP-B4AUIBJE/events.out.tfevents.1718802619.LAPTOP-B4AUIBJE.45372.1 +3 -0
  5. runs/Jun19_18-40-57_LAPTOP-B4AUIBJE/events.out.tfevents.1718802658.LAPTOP-B4AUIBJE.45372.2 +3 -0
  6. runs/Jun21_12-20-18_LAPTOP-B4AUIBJE/events.out.tfevents.1718952619.LAPTOP-B4AUIBJE.55308.0 +3 -0
  7. special_tokens_map.json +51 -51
  8. tokenizer_config.json +73 -73
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,43 +1,43 @@
1
- {
2
- "_name_or_path": "google/bigbird-pegasus-large-pubmed",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu_new",
5
- "architectures": [
6
- "BigBirdPegasusForQuestionAnswering"
7
- ],
8
- "attention_dropout": 0.0,
9
- "attention_type": "block_sparse",
10
- "block_size": 64,
11
- "bos_token_id": 2,
12
- "classifier_dropout": 0.0,
13
- "d_model": 1024,
14
- "decoder_attention_heads": 16,
15
- "decoder_ffn_dim": 4096,
16
- "decoder_layerdrop": 0.0,
17
- "decoder_layers": 16,
18
- "decoder_start_token_id": 2,
19
- "dropout": 0.1,
20
- "encoder_attention_heads": 16,
21
- "encoder_ffn_dim": 4096,
22
- "encoder_layerdrop": 0.0,
23
- "encoder_layers": 16,
24
- "eos_token_id": 1,
25
- "gradient_checkpointing": false,
26
- "init_std": 0.02,
27
- "is_encoder_decoder": true,
28
- "length_penalty": 0.8,
29
- "max_length": 256,
30
- "max_position_embeddings": 4096,
31
- "model_type": "bigbird_pegasus",
32
- "num_beams": 5,
33
- "num_hidden_layers": 16,
34
- "num_random_blocks": 3,
35
- "pad_token_id": 0,
36
- "scale_embedding": true,
37
- "tokenizer_class": "PegasusTokenizer",
38
- "torch_dtype": "float32",
39
- "transformers_version": "4.41.2",
40
- "use_bias": false,
41
- "use_cache": true,
42
- "vocab_size": 96103
43
- }
 
1
+ {
2
+ "_name_or_path": "google/bigbird-pegasus-large-pubmed",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "BigBirdPegasusForQuestionAnswering"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_type": "block_sparse",
10
+ "block_size": 64,
11
+ "bos_token_id": 2,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 16,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
25
+ "gradient_checkpointing": false,
26
+ "init_std": 0.02,
27
+ "is_encoder_decoder": true,
28
+ "length_penalty": 0.8,
29
+ "max_length": 256,
30
+ "max_position_embeddings": 4096,
31
+ "model_type": "bigbird_pegasus",
32
+ "num_beams": 5,
33
+ "num_hidden_layers": 16,
34
+ "num_random_blocks": 3,
35
+ "pad_token_id": 0,
36
+ "scale_embedding": true,
37
+ "tokenizer_class": "PegasusTokenizer",
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.41.2",
40
+ "use_bias": false,
41
+ "use_cache": true,
42
+ "vocab_size": 96103
43
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c15ffbbd5d1108be242c127a6998aae5988356bbdf3c7d74497baeaec10b59d3
3
- size 2307633752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdbcb83f9f4e13eedfb2da918ba391f24ab66c02a9ca64f2b9efb77777246de
3
+ size 1153845340
runs/Jun19_18-37-49_LAPTOP-B4AUIBJE/events.out.tfevents.1718802487.LAPTOP-B4AUIBJE.45372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9908b6cfe2657db36a776f7f406c0b28cccf02d8839f6bd6bbb0671397b5fe1
3
+ size 5309
runs/Jun19_18-40-17_LAPTOP-B4AUIBJE/events.out.tfevents.1718802619.LAPTOP-B4AUIBJE.45372.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34516dcd8829547d1e0c3e30ad31943a090ce34265beb58d8786c5dd7e9e460a
3
+ size 5309
runs/Jun19_18-40-57_LAPTOP-B4AUIBJE/events.out.tfevents.1718802658.LAPTOP-B4AUIBJE.45372.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f16c2ccd84696911dd5fb922cb92219900ef7033eb649a714bcaa8fb54960a
3
+ size 5309
runs/Jun21_12-20-18_LAPTOP-B4AUIBJE/events.out.tfevents.1718952619.LAPTOP-B4AUIBJE.55308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4acdbb65dc0cb7c473dcdccbe3517faad850d88fe12823032b1f8a46c635934
3
+ size 5520
special_tokens_map.json CHANGED
@@ -1,51 +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": "[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
- }
 
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
+ }
tokenizer_config.json CHANGED
@@ -1,73 +1,73 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<pad>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "</s>",
13
- "lstrip": false,
14
- "normalized": true,
15
- "rstrip": false,
16
- "single_word": 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
- "105": {
52
- "content": "<unk>",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- }
59
- },
60
- "additional_special_tokens": [],
61
- "bos_token": "<s>",
62
- "clean_up_tokenization_spaces": true,
63
- "cls_token": "[CLS]",
64
- "eos_token": "</s>",
65
- "mask_token": "[MASK]",
66
- "mask_token_sent": null,
67
- "model_max_length": 4096,
68
- "offset": 0,
69
- "pad_token": "<pad>",
70
- "sep_token": "[SEP]",
71
- "tokenizer_class": "PegasusTokenizer",
72
- "unk_token": "<unk>"
73
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": 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
+ "105": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [],
61
+ "bos_token": "<s>",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "[CLS]",
64
+ "eos_token": "</s>",
65
+ "mask_token": "[MASK]",
66
+ "mask_token_sent": null,
67
+ "model_max_length": 4096,
68
+ "offset": 0,
69
+ "pad_token": "<pad>",
70
+ "sep_token": "[SEP]",
71
+ "tokenizer_class": "PegasusTokenizer",
72
+ "unk_token": "<unk>"
73
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a7061025a75a64d8d847bf74e81b39e4d6a4e13601b85062218725faefb51ef
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7a5822511063bcb486f8826f0b2d16d844a5f61067c9234838924bfad51732
3
  size 5112