Hugging Face's logo

antalvdb
/
robbert-v2-dutch-base-finetuned-emotion-arousal

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
antalvdb commited on
Commit
92d5ec6
·
verified ·
1 Parent(s): eacc4cf

Training completed!

Browse files
Files changed (10) hide show
  1. README.md +107 -0
  2. config.json +36 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. runs/Jul29_17-00-12_48d9b6cfc4cc/events.out.tfevents.1722272423.48d9b6cfc4cc.703.0 +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +57 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: pdelobelle/robbert-v2-dutch-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: robbert-v2-dutch-base-finetuned-emotion-arousal
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # robbert-v2-dutch-base-finetuned-emotion-arousal
15
+
16
+ This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0230
19
+ - Rmse: 0.1517
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 50
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss | Rmse |
49
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
50
+ | 0.0581 | 1.0 | 25 | 0.0349 | 0.1868 |
51
+ | 0.0355 | 2.0 | 50 | 0.0340 | 0.1845 |
52
+ | 0.0295 | 3.0 | 75 | 0.0271 | 0.1645 |
53
+ | 0.0288 | 4.0 | 100 | 0.0279 | 0.1670 |
54
+ | 0.0277 | 5.0 | 125 | 0.0316 | 0.1777 |
55
+ | 0.0254 | 6.0 | 150 | 0.0263 | 0.1620 |
56
+ | 0.0193 | 7.0 | 175 | 0.0247 | 0.1571 |
57
+ | 0.0173 | 8.0 | 200 | 0.0304 | 0.1745 |
58
+ | 0.0179 | 9.0 | 225 | 0.0239 | 0.1547 |
59
+ | 0.0149 | 10.0 | 250 | 0.0244 | 0.1563 |
60
+ | 0.0134 | 11.0 | 275 | 0.0248 | 0.1576 |
61
+ | 0.0113 | 12.0 | 300 | 0.0256 | 0.1601 |
62
+ | 0.0112 | 13.0 | 325 | 0.0265 | 0.1627 |
63
+ | 0.0114 | 14.0 | 350 | 0.0299 | 0.1730 |
64
+ | 0.0111 | 15.0 | 375 | 0.0268 | 0.1638 |
65
+ | 0.0098 | 16.0 | 400 | 0.0256 | 0.1599 |
66
+ | 0.009 | 17.0 | 425 | 0.0252 | 0.1588 |
67
+ | 0.0078 | 18.0 | 450 | 0.0256 | 0.1601 |
68
+ | 0.0093 | 19.0 | 475 | 0.0235 | 0.1532 |
69
+ | 0.009 | 20.0 | 500 | 0.0246 | 0.1568 |
70
+ | 0.0084 | 21.0 | 525 | 0.0238 | 0.1543 |
71
+ | 0.0083 | 22.0 | 550 | 0.0255 | 0.1598 |
72
+ | 0.0074 | 23.0 | 575 | 0.0250 | 0.1582 |
73
+ | 0.0079 | 24.0 | 600 | 0.0248 | 0.1574 |
74
+ | 0.0077 | 25.0 | 625 | 0.0261 | 0.1616 |
75
+ | 0.0073 | 26.0 | 650 | 0.0261 | 0.1615 |
76
+ | 0.0071 | 27.0 | 675 | 0.0247 | 0.1571 |
77
+ | 0.0068 | 28.0 | 700 | 0.0254 | 0.1593 |
78
+ | 0.0062 | 29.0 | 725 | 0.0250 | 0.1581 |
79
+ | 0.006 | 30.0 | 750 | 0.0255 | 0.1597 |
80
+ | 0.0066 | 31.0 | 775 | 0.0241 | 0.1553 |
81
+ | 0.0064 | 32.0 | 800 | 0.0242 | 0.1555 |
82
+ | 0.006 | 33.0 | 825 | 0.0240 | 0.1549 |
83
+ | 0.0055 | 34.0 | 850 | 0.0244 | 0.1561 |
84
+ | 0.0055 | 35.0 | 875 | 0.0235 | 0.1533 |
85
+ | 0.0053 | 36.0 | 900 | 0.0241 | 0.1551 |
86
+ | 0.0056 | 37.0 | 925 | 0.0238 | 0.1542 |
87
+ | 0.0052 | 38.0 | 950 | 0.0248 | 0.1576 |
88
+ | 0.0055 | 39.0 | 975 | 0.0247 | 0.1570 |
89
+ | 0.0054 | 40.0 | 1000 | 0.0233 | 0.1526 |
90
+ | 0.0052 | 41.0 | 1025 | 0.0233 | 0.1525 |
91
+ | 0.0048 | 42.0 | 1050 | 0.0231 | 0.1519 |
92
+ | 0.0051 | 43.0 | 1075 | 0.0237 | 0.1538 |
93
+ | 0.0051 | 44.0 | 1100 | 0.0231 | 0.1520 |
94
+ | 0.0053 | 45.0 | 1125 | 0.0234 | 0.1531 |
95
+ | 0.0046 | 46.0 | 1150 | 0.0230 | 0.1517 |
96
+ | 0.0049 | 47.0 | 1175 | 0.0230 | 0.1518 |
97
+ | 0.005 | 48.0 | 1200 | 0.0230 | 0.1518 |
98
+ | 0.0047 | 49.0 | 1225 | 0.0237 | 0.1540 |
99
+ | 0.0047 | 50.0 | 1250 | 0.0230 | 0.1517 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.42.4
105
+ - Pytorch 2.3.1+cu121
106
+ - Datasets 2.20.0
107
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
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
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "regression",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.42.4",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 40000
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28a07e732d80fef357f3aaa9775fa4c95f043dd3a8c38f897b1305d84fd18b4
3
+ size 467075668
runs/Jul29_17-00-12_48d9b6cfc4cc/events.out.tfevents.1722272423.48d9b6cfc4cc.703.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b1b548cc784ee42b18c236e469955eb7169a10b18f7f1487466f84752247ad
3
+ size 31952
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "39984": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
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
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29627150eec86eca2cb58a2c328ba031f226e06a40d9175d99164bee95414a04
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff