Hugging Face's logo

SharonTudi
/
DIALOGUE_overfit_check

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
SharonTudi commited on
Commit
1a66790
·
verified ·
1 Parent(s): 461c3ce

End of training

Browse files
Files changed (6) hide show
  1. README.md +51 -51
  2. config.json +14 -16
  3. model.safetensors +2 -2
  4. runs/Jan15_17-15-49_5f4fd25aa8a7/events.out.tfevents.1705338957.5f4fd25aa8a7.423.8 +3 -0
  5. tokenizer_config.json +1 -1
  6. training_args.bin +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # DIALOGUE_overfit_check
17
 
18
- This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1664
21
  - Accuracy: 0.9737
22
 
23
  ## Model description
@@ -49,54 +49,54 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 1.0349 | 0.62 | 30 | 0.4886 | 0.9605 |
53
- | 0.3681 | 1.25 | 60 | 0.1215 | 0.9737 |
54
- | 0.116 | 1.88 | 90 | 0.1281 | 0.9737 |
55
- | 0.022 | 2.5 | 120 | 0.0116 | 1.0 |
56
- | 0.0075 | 3.12 | 150 | 0.1455 | 0.9737 |
57
- | 0.011 | 3.75 | 180 | 0.1329 | 0.9737 |
58
- | 0.0032 | 4.38 | 210 | 0.1262 | 0.9737 |
59
- | 0.0025 | 5.0 | 240 | 0.1302 | 0.9737 |
60
- | 0.002 | 5.62 | 270 | 0.1349 | 0.9737 |
61
- | 0.0017 | 6.25 | 300 | 0.1372 | 0.9737 |
62
- | 0.0015 | 6.88 | 330 | 0.1413 | 0.9737 |
63
- | 0.0013 | 7.5 | 360 | 0.1440 | 0.9737 |
64
- | 0.0012 | 8.12 | 390 | 0.1462 | 0.9737 |
65
- | 0.0011 | 8.75 | 420 | 0.1480 | 0.9737 |
66
- | 0.001 | 9.38 | 450 | 0.1491 | 0.9737 |
67
- | 0.0009 | 10.0 | 480 | 0.1499 | 0.9737 |
68
- | 0.0009 | 10.62 | 510 | 0.1500 | 0.9737 |
69
- | 0.0008 | 11.25 | 540 | 0.1502 | 0.9737 |
70
- | 0.0007 | 11.88 | 570 | 0.1517 | 0.9737 |
71
- | 0.0007 | 12.5 | 600 | 0.1528 | 0.9737 |
72
- | 0.0006 | 13.12 | 630 | 0.1536 | 0.9737 |
73
- | 0.0006 | 13.75 | 660 | 0.1549 | 0.9737 |
74
- | 0.0006 | 14.38 | 690 | 0.1556 | 0.9737 |
75
- | 0.0006 | 15.0 | 720 | 0.1566 | 0.9737 |
76
- | 0.0005 | 15.62 | 750 | 0.1567 | 0.9737 |
77
- | 0.0005 | 16.25 | 780 | 0.1581 | 0.9737 |
78
- | 0.0005 | 16.88 | 810 | 0.1587 | 0.9737 |
79
- | 0.0005 | 17.5 | 840 | 0.1598 | 0.9737 |
80
- | 0.0005 | 18.12 | 870 | 0.1602 | 0.9737 |
81
- | 0.0004 | 18.75 | 900 | 0.1605 | 0.9737 |
82
- | 0.0004 | 19.38 | 930 | 0.1621 | 0.9737 |
83
- | 0.0004 | 20.0 | 960 | 0.1628 | 0.9737 |
84
- | 0.0004 | 20.62 | 990 | 0.1633 | 0.9737 |
85
- | 0.0004 | 21.25 | 1020 | 0.1639 | 0.9737 |
86
- | 0.0004 | 21.88 | 1050 | 0.1644 | 0.9737 |
87
- | 0.0004 | 22.5 | 1080 | 0.1652 | 0.9737 |
88
- | 0.0004 | 23.12 | 1110 | 0.1657 | 0.9737 |
89
- | 0.0004 | 23.75 | 1140 | 0.1660 | 0.9737 |
90
- | 0.0004 | 24.38 | 1170 | 0.1652 | 0.9737 |
91
- | 0.0004 | 25.0 | 1200 | 0.1656 | 0.9737 |
92
- | 0.0003 | 25.62 | 1230 | 0.1659 | 0.9737 |
93
- | 0.0003 | 26.25 | 1260 | 0.1662 | 0.9737 |
94
- | 0.0003 | 26.88 | 1290 | 0.1663 | 0.9737 |
95
- | 0.0003 | 27.5 | 1320 | 0.1663 | 0.9737 |
96
- | 0.0003 | 28.12 | 1350 | 0.1663 | 0.9737 |
97
- | 0.0003 | 28.75 | 1380 | 0.1663 | 0.9737 |
98
- | 0.0003 | 29.38 | 1410 | 0.1663 | 0.9737 |
99
- | 0.0003 | 30.0 | 1440 | 0.1664 | 0.9737 |
100
 
101
 
102
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # DIALOGUE_overfit_check
17
 
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1883
21
  - Accuracy: 0.9737
22
 
23
  ## Model description
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 1.0445 | 0.62 | 30 | 0.5494 | 0.9342 |
53
+ | 0.3988 | 1.25 | 60 | 0.1579 | 0.9737 |
54
+ | 0.1431 | 1.88 | 90 | 0.1439 | 0.9737 |
55
+ | 0.0339 | 2.5 | 120 | 0.1009 | 0.9737 |
56
+ | 0.0133 | 3.12 | 150 | 0.1070 | 0.9737 |
57
+ | 0.0074 | 3.75 | 180 | 0.1136 | 0.9737 |
58
+ | 0.0051 | 4.38 | 210 | 0.1307 | 0.9737 |
59
+ | 0.0039 | 5.0 | 240 | 0.1301 | 0.9737 |
60
+ | 0.0032 | 5.62 | 270 | 0.1360 | 0.9737 |
61
+ | 0.0026 | 6.25 | 300 | 0.1378 | 0.9737 |
62
+ | 0.0022 | 6.88 | 330 | 0.1437 | 0.9737 |
63
+ | 0.002 | 7.5 | 360 | 0.1443 | 0.9737 |
64
+ | 0.0016 | 8.12 | 390 | 0.1472 | 0.9737 |
65
+ | 0.0015 | 8.75 | 420 | 0.1499 | 0.9737 |
66
+ | 0.0013 | 9.38 | 450 | 0.1551 | 0.9737 |
67
+ | 0.0012 | 10.0 | 480 | 0.1558 | 0.9737 |
68
+ | 0.0011 | 10.62 | 510 | 0.1589 | 0.9737 |
69
+ | 0.001 | 11.25 | 540 | 0.1606 | 0.9737 |
70
+ | 0.001 | 11.88 | 570 | 0.1670 | 0.9737 |
71
+ | 0.0009 | 12.5 | 600 | 0.1685 | 0.9737 |
72
+ | 0.0008 | 13.12 | 630 | 0.1700 | 0.9737 |
73
+ | 0.0007 | 13.75 | 660 | 0.1705 | 0.9737 |
74
+ | 0.0007 | 14.38 | 690 | 0.1705 | 0.9737 |
75
+ | 0.0007 | 15.0 | 720 | 0.1730 | 0.9737 |
76
+ | 0.0006 | 15.62 | 750 | 0.1742 | 0.9737 |
77
+ | 0.0006 | 16.25 | 780 | 0.1754 | 0.9737 |
78
+ | 0.0005 | 16.88 | 810 | 0.1767 | 0.9737 |
79
+ | 0.0005 | 17.5 | 840 | 0.1775 | 0.9737 |
80
+ | 0.0005 | 18.12 | 870 | 0.1797 | 0.9737 |
81
+ | 0.0005 | 18.75 | 900 | 0.1810 | 0.9737 |
82
+ | 0.0005 | 19.38 | 930 | 0.1811 | 0.9737 |
83
+ | 0.0005 | 20.0 | 960 | 0.1819 | 0.9737 |
84
+ | 0.0004 | 20.62 | 990 | 0.1823 | 0.9737 |
85
+ | 0.0004 | 21.25 | 1020 | 0.1834 | 0.9737 |
86
+ | 0.0004 | 21.88 | 1050 | 0.1840 | 0.9737 |
87
+ | 0.0004 | 22.5 | 1080 | 0.1844 | 0.9737 |
88
+ | 0.0004 | 23.12 | 1110 | 0.1852 | 0.9737 |
89
+ | 0.0004 | 23.75 | 1140 | 0.1859 | 0.9737 |
90
+ | 0.0004 | 24.38 | 1170 | 0.1862 | 0.9737 |
91
+ | 0.0004 | 25.0 | 1200 | 0.1867 | 0.9737 |
92
+ | 0.0004 | 25.62 | 1230 | 0.1870 | 0.9737 |
93
+ | 0.0003 | 26.25 | 1260 | 0.1873 | 0.9737 |
94
+ | 0.0003 | 26.88 | 1290 | 0.1875 | 0.9737 |
95
+ | 0.0003 | 27.5 | 1320 | 0.1879 | 0.9737 |
96
+ | 0.0003 | 28.12 | 1350 | 0.1881 | 0.9737 |
97
+ | 0.0003 | 28.75 | 1380 | 0.1882 | 0.9737 |
98
+ | 0.0003 | 29.38 | 1410 | 0.1883 | 0.9737 |
99
+ | 0.0003 | 30.0 | 1440 | 0.1883 | 0.9737 |
100
 
101
 
102
  ### Framework versions
config.json CHANGED
@@ -1,14 +1,13 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "id2label": {
13
  "0": "Hospital-Inform",
14
  "1": "Hospital-Request",
@@ -16,24 +15,23 @@
16
  "3": "general-thank"
17
  },
18
  "initializer_range": 0.02,
19
- "intermediate_size": 3072,
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 2,
24
  "LABEL_3": 3
25
  },
26
- "layer_norm_eps": 1e-12,
27
  "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 12,
30
- "num_hidden_layers": 12,
31
  "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
 
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.36.2",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
  "vocab_size": 30522
39
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "Hospital-Inform",
13
  "1": "Hospital-Request",
 
15
  "3": "general-thank"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "LABEL_0": 0,
20
  "LABEL_1": 1,
21
  "LABEL_2": 2,
22
  "LABEL_3": 3
23
  },
 
24
  "max_position_embeddings": 512,
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,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.36.2",
 
 
36
  "vocab_size": 30522
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:912b3df21cd27cd12ce909bfce900ff2406b548a79da9dc6f02e790c43881b74
3
- size 437964800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9982ecc3058b06ef059c364bee0447eb841b1f3e1c2b508d822694061b9bc05
3
+ size 267838720
runs/Jan15_17-15-49_5f4fd25aa8a7/events.out.tfevents.1705338957.5f4fd25aa8a7.423.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82a2406ad3cf60c49e8008615ecc4ed8c0d1c6bdbab2f55b031c6e9d263322f
3
+ size 27836
tokenizer_config.json CHANGED
@@ -52,6 +52,6 @@
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
 
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:989d5c21fc2129e6ec57733230fd784a30223b997d988cab4d7b7d989f055f4a
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1882a4d6c709b5e126ef542a6f9dcf78ca3c2eb8a12e0f50857d3a2e9baabb83
3
+ size 4728