Hugging Face's logo

Tommert25
/
robbert_1210seed24

Token Classification
Transformers
PyTorch
roberta
Generated from Trainer
Model card Files
xet
 Community
1
Tommert25 commited on
Commit
556c3e2
·
1 Parent(s): fe55062

End of training

Browse files
Files changed (5) hide show
  1. README.md +11 -30
  2. config.json +1 -1
  3. special_tokens_map.json +7 -0
  4. tokenizer_config.json +14 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,11 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: pdelobelle/robbert-v2-dutch-base
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - recall
8
- - accuracy
9
  model-index:
10
  - name: robbert_1210seed24
11
  results: []
@@ -16,13 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # robbert_1210seed24
18
 
19
- This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5514
22
- - Precisions: 0.8242
23
- - Recall: 0.8109
24
- - F-measure: 0.8173
25
- - Accuracy: 0.9166
 
 
 
 
26
 
27
  ## Model description
28
 
@@ -49,26 +50,6 @@ The following hyperparameters were used during training:
49
  - lr_scheduler_type: linear
50
  - num_epochs: 14
51
 
52
- ### Training results
53
-
54
- | Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
56
- | 0.6024 | 1.0 | 236 | 0.3532 | 0.8012 | 0.7183 | 0.7242 | 0.8874 |
57
- | 0.3107 | 2.0 | 472 | 0.3480 | 0.8147 | 0.7506 | 0.7619 | 0.8987 |
58
- | 0.1931 | 3.0 | 708 | 0.3617 | 0.8054 | 0.7603 | 0.7732 | 0.9027 |
59
- | 0.1234 | 4.0 | 944 | 0.4106 | 0.7976 | 0.7862 | 0.7893 | 0.9059 |
60
- | 0.0902 | 5.0 | 1180 | 0.4992 | 0.7678 | 0.7558 | 0.7579 | 0.8878 |
61
- | 0.0596 | 6.0 | 1416 | 0.5144 | 0.8178 | 0.7652 | 0.7858 | 0.9093 |
62
- | 0.0481 | 7.0 | 1652 | 0.4942 | 0.8061 | 0.8145 | 0.8078 | 0.9107 |
63
- | 0.0356 | 8.0 | 1888 | 0.5583 | 0.8055 | 0.7883 | 0.7957 | 0.9052 |
64
- | 0.0275 | 9.0 | 2124 | 0.5458 | 0.8165 | 0.8015 | 0.8078 | 0.9141 |
65
- | 0.021 | 10.0 | 2360 | 0.5803 | 0.8263 | 0.7950 | 0.8079 | 0.9114 |
66
- | 0.0183 | 11.0 | 2596 | 0.5514 | 0.8242 | 0.8109 | 0.8173 | 0.9166 |
67
- | 0.0165 | 12.0 | 2832 | 0.5690 | 0.8180 | 0.8060 | 0.8115 | 0.9154 |
68
- | 0.0131 | 13.0 | 3068 | 0.5887 | 0.8131 | 0.7963 | 0.8020 | 0.9118 |
69
- | 0.0103 | 14.0 | 3304 | 0.5905 | 0.8244 | 0.7949 | 0.8049 | 0.9141 |
70
-
71
-
72
  ### Framework versions
73
 
74
  - Transformers 4.34.0
 
1
  ---
2
  license: mit
3
+ base_model: Tommert25/robbert_1210seed24
4
  tags:
5
  - generated_from_trainer
 
 
 
6
  model-index:
7
  - name: robbert_1210seed24
8
  results: []
 
13
 
14
  # robbert_1210seed24
15
 
16
+ This model is a fine-tuned version of [Tommert25/robbert_1210seed24](https://huggingface.co/Tommert25/robbert_1210seed24) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.3768
19
+ - eval_precisions: 0.8480
20
+ - eval_recall: 0.8144
21
+ - eval_f-measure: 0.8283
22
+ - eval_accuracy: 0.9436
23
+ - eval_runtime: 9.7846
24
+ - eval_samples_per_second: 82.477
25
+ - eval_steps_per_second: 5.212
26
+ - step: 0
27
 
28
  ## Model description
29
 
 
50
  - lr_scheduler_type: linear
51
  - num_epochs: 14
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  ### Framework versions
54
 
55
  - Transformers 4.34.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
3
  "architectures": [
4
  "RobertaForTokenClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "Tommert25/robbert_1210seed24",
3
  "architectures": [
4
  "RobertaForTokenClassification"
5
  ],
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "<pad>",
5
+ "</s>",
6
+ "<unk>",
7
+ "<mask>"
8
+ ],
9
  "bos_token": "<s>",
10
  "cls_token": "<s>",
11
  "eos_token": "</s>",
tokenizer_config.json CHANGED
@@ -42,17 +42,30 @@
42
  "special": true
43
  }
44
  },
45
- "additional_special_tokens": [],
 
 
 
 
 
 
46
  "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
  "cls_token": "<s>",
49
  "eos_token": "</s>",
50
  "errors": "replace",
51
  "mask_token": "<mask>",
 
52
  "model_max_length": 512,
 
53
  "pad_token": "<pad>",
 
 
54
  "sep_token": "</s>",
 
55
  "tokenizer_class": "RobertaTokenizer",
56
  "trim_offsets": true,
 
 
57
  "unk_token": "<unk>"
58
  }
 
42
  "special": true
43
  }
44
  },
45
+ "additional_special_tokens": [
46
+ "<s>",
47
+ "<pad>",
48
+ "</s>",
49
+ "<unk>",
50
+ "<mask>"
51
+ ],
52
  "bos_token": "<s>",
53
  "clean_up_tokenization_spaces": true,
54
  "cls_token": "<s>",
55
  "eos_token": "</s>",
56
  "errors": "replace",
57
  "mask_token": "<mask>",
58
+ "max_length": 512,
59
  "model_max_length": 512,
60
+ "pad_to_multiple_of": null,
61
  "pad_token": "<pad>",
62
+ "pad_token_type_id": 0,
63
+ "padding_side": "right",
64
  "sep_token": "</s>",
65
+ "stride": 0,
66
  "tokenizer_class": "RobertaTokenizer",
67
  "trim_offsets": true,
68
+ "truncation_side": "right",
69
+ "truncation_strategy": "longest_first",
70
  "unk_token": "<unk>"
71
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e73485b7cdcb9b4d650bb07e2240665d8668e0a05f58ce135bf7a06c1930ab
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06636a42e24bc58adfe18e4fe793e0f3e57a8b9151bda88d592bf9bef2b2a5b8
3
  size 4091