Hugging Face's logo

acezxn
/
my_awesome_qa_model

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Inference Endpoints
Model card Files Metrics Community
acezxn commited on
Commit
9f7d3d9
•
1 Parent(s): 02d40d7

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. .ipynb_checkpoints/special_tokens_map-checkpoint.json +51 -0
  2. config.json +17 -23
  3. model.safetensors +2 -2
  4. runs/Jun12_03-08-16_23a3a01b579f/events.out.tfevents.1718161696.23a3a01b579f.13281.0 +2 -2
  5. runs/Jun12_03-40-48_23a3a01b579f/events.out.tfevents.1718163649.23a3a01b579f.18156.0 +3 -0
  6. special_tokens_map.json +5 -49
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +24 -28
  9. training_args.bin +1 -1
  10. vocab.txt +0 -0
.ipynb_checkpoints/special_tokens_map-checkpoint.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
+ }
config.json CHANGED
@@ -1,30 +1,24 @@
1
  {
2
- "_name_or_path": "deepset/roberta-base-squad2",
 
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
- "gradient_checkpointing": false,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 3072,
16
- "language": "english",
17
- "layer_norm_eps": 1e-05,
18
- "max_position_embeddings": 514,
19
- "model_type": "roberta",
20
- "name": "Roberta",
21
- "num_attention_heads": 12,
22
- "num_hidden_layers": 12,
23
- "pad_token_id": 1,
24
- "position_embedding_type": "absolute",
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.41.2",
27
- "type_vocab_size": 1,
28
- "use_cache": true,
29
- "vocab_size": 50265
30
  }
 
1
  {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
 
 
11
  "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.41.2",
23
+ "vocab_size": 30522
 
 
24
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf8dc30652d978b32aff49cb126c22cec365b86e005a6a5ae1ea077e32ceb182
3
- size 496250232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b357f93994cc0189260d58744269ed5897537760eca7b8f56b86f4fed89276d
3
+ size 265470032
runs/Jun12_03-08-16_23a3a01b579f/events.out.tfevents.1718161696.23a3a01b579f.13281.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cb72a480455f496108b8d4b229426e51b6697f9fe97f70bc84d4cedad5130c8
3
- size 5402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdc24b605247755bce4624378a697bc4a0c40f182d7cf101fd8aae4f848052b
3
+ size 6298
runs/Jun12_03-40-48_23a3a01b579f/events.out.tfevents.1718163649.23a3a01b579f.18156.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e39129c8b3479e8a001f74654083c82bbb241001956f3b175f6c784d446c11
3
+ size 5188
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,59 +1,55 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
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": true,
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
- "do_lower_case": false,
49
- "eos_token": "</s>",
50
- "errors": "replace",
51
- "full_tokenizer_file": null,
52
- "mask_token": "<mask>",
53
  "model_max_length": 512,
54
- "pad_token": "<pad>",
55
- "sep_token": "</s>",
56
- "tokenizer_class": "RobertaTokenizer",
57
- "trim_offsets": true,
58
- "unk_token": "<unk>"
 
59
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[PAD]",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
 
 
 
48
  "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dee0bec93d6f61d77c48da44abc6470ad60fce3447ee38a8e577c404e1d9ede4
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c903a97e03a6b53bf26ea4d9f750990dda8d4822ed5bc410eeef7d3ec560e3a6
3
  size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff