Hugging Face's logo

StaAhmed
/
Values_QA

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
 Metrics Community
StaAhmed commited on
Commit
8ecda08
路
verified 路
1 Parent(s): c3f73dd

End of training

Browse files
Files changed (9) hide show
  1. README.md +8 -8
  2. config.json +3 -4
  3. model.safetensors +2 -2
  4. runs/Feb29_16-00-30_def8b53a6a59/events.out.tfevents.1709222431.def8b53a6a59.824.0 +3 -0
  5. special_tokens_map.json +35 -5
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -1
  8. training_args.bin +1 -1
  9. vocab.txt +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert/distilbert-base-cased-distilled-squad
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # Values_QA
15
 
16
- This model is a fine-tuned version of [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.5511
19
 
20
  ## Model description
21
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 10 | 3.1699 |
50
- | No log | 2.0 | 20 | 2.7025 |
51
- | No log | 3.0 | 30 | 2.5335 |
52
- | No log | 4.0 | 40 | 2.5673 |
53
- | No log | 5.0 | 50 | 2.5511 |
54
 
55
 
56
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: StaAhmed/my_awesome_qa_model
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # Values_QA
15
 
16
+ This model is a fine-tuned version of [StaAhmed/my_awesome_qa_model](https://huggingface.co/StaAhmed/my_awesome_qa_model) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.3453
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 9 | 3.6604 |
50
+ | No log | 2.0 | 18 | 2.7661 |
51
+ | No log | 3.0 | 27 | 2.3928 |
52
+ | No log | 4.0 | 36 | 2.4439 |
53
+ | No log | 5.0 | 45 | 2.3453 |
54
 
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-cased-distilled-squad",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
@@ -13,13 +13,12 @@
13
  "model_type": "distilbert",
14
  "n_heads": 12,
15
  "n_layers": 6,
16
- "output_past": true,
17
  "pad_token_id": 0,
18
  "qa_dropout": 0.1,
19
  "seq_classif_dropout": 0.2,
20
- "sinusoidal_pos_embds": true,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.38.1",
24
- "vocab_size": 28996
25
  }
 
1
  {
2
+ "_name_or_path": "StaAhmed/my_awesome_qa_model",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
 
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": "4.38.1",
23
+ "vocab_size": 30522
24
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d380332ea94ab3f6a5f54960e78a3893ff96ea03e0a3f44c57a31289f6d080b
3
- size 260782152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08452200d34d7cdb45df018c1907a3d52029957024d21ddf1a7bba1b1d1a580b
3
+ size 265470032
runs/Feb29_16-00-30_def8b53a6a59/events.out.tfevents.1709222431.def8b53a6a59.824.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16a0193e98bc0f9b64266ddf277782bc725286e34721879e93a1710f3a84899
3
+ size 6142
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,7 +43,7 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 1000000000000000019884624838656,
49
  "pad_token": "[PAD]",
 
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]",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b28a05225badd70454e61cb862df33d265c0c3b9e747ace389d38e79dc2a524
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da4627aca71e9cb09501c56c34a2ee0a2c2addd6dd198c90efa72d9aeaeb0f6
3
  size 4856
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff