Hugging Face's logo

SharonTudi
/
DIALOGUE_second_model

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
SharonTudi commited on
Commit
c54ed5d
·
verified ·
1 Parent(s): 7a1c7e6

End of training

Browse files
Files changed (7) hide show
  1. README.md +22 -22
  2. config.json +3 -2
  3. model.safetensors +2 -2
  4. runs/Jan19_11-07-11_eab14bd28cfb/events.out.tfevents.1705662437.eab14bd28cfb.651.5 +3 -0
  5. tokenizer_config.json +1 -1
  6. training_args.bin +1 -1
  7. vocab.txt +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # DIALOGUE_second_model
20
 
21
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1711
24
- - Precision: 0.9762
25
- - Recall: 0.9737
26
- - F1: 0.9736
27
- - Accuracy: 0.9737
28
 
29
  ## Model description
30
 
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.4916 | 1.0 | 48 | 0.1054 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
59
- | 0.1494 | 2.0 | 96 | 0.0187 | 1.0 | 1.0 | 1.0 | 1.0 |
60
- | 0.062 | 3.0 | 144 | 0.1807 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
61
- | 0.0426 | 4.0 | 192 | 0.1720 | 0.9637 | 0.9605 | 0.9604 | 0.9605 |
62
- | 0.0158 | 5.0 | 240 | 0.1618 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
63
- | 0.0006 | 6.0 | 288 | 0.1627 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
64
- | 0.0013 | 7.0 | 336 | 0.1704 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
65
- | 0.0004 | 8.0 | 384 | 0.1970 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
66
- | 0.0025 | 9.0 | 432 | 0.1631 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
67
- | 0.0003 | 10.0 | 480 | 0.1650 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
68
- | 0.0002 | 11.0 | 528 | 0.1675 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
69
- | 0.0002 | 12.0 | 576 | 0.1694 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
70
- | 0.0002 | 13.0 | 624 | 0.1705 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
71
- | 0.0002 | 14.0 | 672 | 0.1710 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
72
- | 0.0002 | 15.0 | 720 | 0.1711 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
73
 
74
 
75
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
18
 
19
  # DIALOGUE_second_model
20
 
21
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5916
24
+ - Precision: 0.9421
25
+ - Recall: 0.9342
26
+ - F1: 0.9313
27
+ - Accuracy: 0.9342
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.4622 | 1.0 | 48 | 0.1244 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
59
+ | 0.146 | 2.0 | 96 | 0.0625 | 0.9659 | 0.9605 | 0.9603 | 0.9605 |
60
+ | 0.0236 | 3.0 | 144 | 0.0720 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
61
+ | 0.0316 | 4.0 | 192 | 0.5084 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
62
+ | 0.0066 | 5.0 | 240 | 0.5201 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
63
+ | 0.0004 | 6.0 | 288 | 0.5124 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
64
+ | 0.0003 | 7.0 | 336 | 0.5397 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
65
+ | 0.0002 | 8.0 | 384 | 0.5557 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
66
+ | 0.0002 | 9.0 | 432 | 0.5652 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
67
+ | 0.0002 | 10.0 | 480 | 0.5737 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
68
+ | 0.0002 | 11.0 | 528 | 0.5799 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
69
+ | 0.0001 | 12.0 | 576 | 0.5850 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
70
+ | 0.0001 | 13.0 | 624 | 0.5887 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
71
+ | 0.0001 | 14.0 | 672 | 0.5909 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
72
+ | 0.0001 | 15.0 | 720 | 0.5916 | 0.9421 | 0.9342 | 0.9313 | 0.9342 |
73
 
74
 
75
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
@@ -25,6 +25,7 @@
25
  "model_type": "distilbert",
26
  "n_heads": 12,
27
  "n_layers": 6,
 
28
  "pad_token_id": 0,
29
  "problem_type": "single_label_classification",
30
  "qa_dropout": 0.1,
@@ -33,5 +34,5 @@
33
  "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.36.2",
36
- "vocab_size": 30522
37
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-cased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
25
  "model_type": "distilbert",
26
  "n_heads": 12,
27
  "n_layers": 6,
28
+ "output_past": true,
29
  "pad_token_id": 0,
30
  "problem_type": "single_label_classification",
31
  "qa_dropout": 0.1,
 
34
  "tie_weights_": true,
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.36.2",
37
+ "vocab_size": 28996
38
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f3b72e869e10b3594ed43b237b1d00ee5c865b5d60d044f6398d9db239604ee
3
- size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8d295db231e19e7c14875fc7e35df1bd4e0a336634fe124aba51a779b19d14
3
+ size 263150840
runs/Jan19_11-07-11_eab14bd28cfb/events.out.tfevents.1705662437.eab14bd28cfb.651.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e9c496332dcabe6e9604ffa5472bf6471f00ff40b82e5a7314300a53a9a7a9
3
+ size 14263
tokenizer_config.json CHANGED
@@ -44,7 +44,7 @@
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "never_split": null,
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "never_split": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f850714be56c07df18b838bb8ed773dc6e8a326ab1b9bab42e6f1aae79619c15
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8151c4234eefc9262d64ac43127e048c5f911503617b63d23053e23a4d08d9
3
  size 4728
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff