Kiran2004 commited on
Commit
a8894c8
1 Parent(s): 7020901

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. README.md +7 -8
  2. config.json +23 -17
  3. special_tokens_map.json +49 -5
  4. tf_model.h5 +2 -2
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +29 -25
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
- base_model: distilbert/distilbert-base-uncased
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # Kiran2004/my_qa_model
15
 
16
- This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 5.7282
19
- - Validation Loss: 5.9063
20
- - Epoch: 1
21
 
22
  ## Model description
23
 
@@ -43,8 +43,7 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 6.0023 | 5.9689 | 0 |
47
- | 5.7282 | 5.9063 | 1 |
48
 
49
 
50
  ### Framework versions
 
1
  ---
2
+ license: cc-by-4.0
3
+ base_model: deepset/roberta-base-squad2
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # Kiran2004/my_qa_model
15
 
16
+ This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 3.0643
19
+ - Validation Loss: 9.9990
20
+ - Epoch: 0
21
 
22
  ## Model description
23
 
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 3.0643 | 9.9990 | 0 |
 
47
 
48
 
49
  ### Framework versions
config.json CHANGED
@@ -1,23 +1,29 @@
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
  "transformers_version": "4.38.2",
22
- "vocab_size": 30522
 
 
23
  }
 
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
  "transformers_version": "4.38.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50265
29
  }
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73e307983863f10f1a76e87ef48438847c34479d77a9bacf11ef238d6c794b7b
3
- size 265583592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d38f634f3304793745a6b4783d20bdce84d28e9d8d919c7a3ca32225cc139b8
3
+ size 496513256
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,55 +1,59 @@
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": 1000000000000000019884624838656,
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
  }
 
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
  }