Training completed!
Browse files- README.md +107 -0
- config.json +36 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul26_08-58-02_346f06fe1c1a/events.out.tfevents.1721984299.346f06fe1c1a.2472.0 +3 -0
- runs/Jul26_09-58-28_346f06fe1c1a/events.out.tfevents.1721987917.346f06fe1c1a.17251.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- 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-valence
|
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-valence
|
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: 0.0327
|
19 |
+
- Rmse: 0.1808
|
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 |
+
| 0.0887 | 1.0 | 25 | 0.0611 | 0.2472 |
|
51 |
+
| 0.044 | 2.0 | 50 | 0.0403 | 0.2008 |
|
52 |
+
| 0.0356 | 3.0 | 75 | 0.0435 | 0.2085 |
|
53 |
+
| 0.0301 | 4.0 | 100 | 0.0415 | 0.2038 |
|
54 |
+
| 0.0246 | 5.0 | 125 | 0.0377 | 0.1941 |
|
55 |
+
| 0.0224 | 6.0 | 150 | 0.0355 | 0.1885 |
|
56 |
+
| 0.0218 | 7.0 | 175 | 0.0379 | 0.1946 |
|
57 |
+
| 0.0174 | 8.0 | 200 | 0.0436 | 0.2088 |
|
58 |
+
| 0.0156 | 9.0 | 225 | 0.0361 | 0.1901 |
|
59 |
+
| 0.0138 | 10.0 | 250 | 0.0379 | 0.1947 |
|
60 |
+
| 0.0135 | 11.0 | 275 | 0.0386 | 0.1965 |
|
61 |
+
| 0.013 | 12.0 | 300 | 0.0402 | 0.2005 |
|
62 |
+
| 0.0125 | 13.0 | 325 | 0.0325 | 0.1804 |
|
63 |
+
| 0.0117 | 14.0 | 350 | 0.0349 | 0.1868 |
|
64 |
+
| 0.0109 | 15.0 | 375 | 0.0366 | 0.1914 |
|
65 |
+
| 0.0108 | 16.0 | 400 | 0.0382 | 0.1953 |
|
66 |
+
| 0.0091 | 17.0 | 425 | 0.0336 | 0.1833 |
|
67 |
+
| 0.0097 | 18.0 | 450 | 0.0325 | 0.1802 |
|
68 |
+
| 0.0098 | 19.0 | 475 | 0.0406 | 0.2014 |
|
69 |
+
| 0.0094 | 20.0 | 500 | 0.0330 | 0.1816 |
|
70 |
+
| 0.0088 | 21.0 | 525 | 0.0349 | 0.1868 |
|
71 |
+
| 0.0087 | 22.0 | 550 | 0.0337 | 0.1835 |
|
72 |
+
| 0.0079 | 23.0 | 575 | 0.0340 | 0.1845 |
|
73 |
+
| 0.0074 | 24.0 | 600 | 0.0372 | 0.1928 |
|
74 |
+
| 0.007 | 25.0 | 625 | 0.0345 | 0.1856 |
|
75 |
+
| 0.0072 | 26.0 | 650 | 0.0333 | 0.1824 |
|
76 |
+
| 0.0074 | 27.0 | 675 | 0.0308 | 0.1756 |
|
77 |
+
| 0.0071 | 28.0 | 700 | 0.0314 | 0.1772 |
|
78 |
+
| 0.0067 | 29.0 | 725 | 0.0314 | 0.1772 |
|
79 |
+
| 0.0065 | 30.0 | 750 | 0.0333 | 0.1824 |
|
80 |
+
| 0.0072 | 31.0 | 775 | 0.0337 | 0.1837 |
|
81 |
+
| 0.0065 | 32.0 | 800 | 0.0351 | 0.1873 |
|
82 |
+
| 0.0057 | 33.0 | 825 | 0.0330 | 0.1818 |
|
83 |
+
| 0.0067 | 34.0 | 850 | 0.0367 | 0.1915 |
|
84 |
+
| 0.0061 | 35.0 | 875 | 0.0358 | 0.1893 |
|
85 |
+
| 0.0062 | 36.0 | 900 | 0.0353 | 0.1879 |
|
86 |
+
| 0.006 | 37.0 | 925 | 0.0317 | 0.1779 |
|
87 |
+
| 0.0059 | 38.0 | 950 | 0.0331 | 0.1819 |
|
88 |
+
| 0.0058 | 39.0 | 975 | 0.0308 | 0.1755 |
|
89 |
+
| 0.0057 | 40.0 | 1000 | 0.0338 | 0.1838 |
|
90 |
+
| 0.0055 | 41.0 | 1025 | 0.0324 | 0.1800 |
|
91 |
+
| 0.0056 | 42.0 | 1050 | 0.0333 | 0.1824 |
|
92 |
+
| 0.0054 | 43.0 | 1075 | 0.0331 | 0.1819 |
|
93 |
+
| 0.0062 | 44.0 | 1100 | 0.0329 | 0.1813 |
|
94 |
+
| 0.0056 | 45.0 | 1125 | 0.0325 | 0.1802 |
|
95 |
+
| 0.0051 | 46.0 | 1150 | 0.0324 | 0.1801 |
|
96 |
+
| 0.0056 | 47.0 | 1175 | 0.0322 | 0.1795 |
|
97 |
+
| 0.0056 | 48.0 | 1200 | 0.0331 | 0.1818 |
|
98 |
+
| 0.0053 | 49.0 | 1225 | 0.0322 | 0.1794 |
|
99 |
+
| 0.0056 | 50.0 | 1250 | 0.0327 | 0.1808 |
|
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:b83ee7931b694d877e0859482aa7e60f7ef5714c0a4137b9b143b9a7fa052c3f
|
3 |
+
size 467075668
|
runs/Jul26_08-58-02_346f06fe1c1a/events.out.tfevents.1721984299.346f06fe1c1a.2472.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:172744110a5e1705f25c703a740553e9bf5db6d1f768839064b5b5975f7b6731
|
3 |
+
size 31952
|
runs/Jul26_09-58-28_346f06fe1c1a/events.out.tfevents.1721987917.346f06fe1c1a.17251.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc89173172e1c11421dcc50df16ed3551dc2ecc085213017a91b9f61af2006eb
|
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:af748e59d22a0a863667bec7ecaf0da770d3c699a0004cb79fa25d4aad2e838f
|
3 |
+
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|