xlm-roberta-siqa-copa
Browse files- .gitattributes +1 -0
- README.md +111 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlm-roberta-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- super_glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: result_xlmr_siqa
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# result_xlmr_siqa
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the super_glue dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.4143
|
23 |
+
- Accuracy: 0.79
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 1e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 44
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 10
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 0.0152 | 0.2 | 10 | 1.0207 | 0.77 |
|
55 |
+
| 0.001 | 0.4 | 20 | 0.7651 | 0.82 |
|
56 |
+
| 0.0013 | 0.6 | 30 | 0.7756 | 0.79 |
|
57 |
+
| 0.0012 | 0.8 | 40 | 1.2054 | 0.8 |
|
58 |
+
| 0.0005 | 1.0 | 50 | 1.3034 | 0.79 |
|
59 |
+
| 0.0008 | 1.2 | 60 | 1.1920 | 0.76 |
|
60 |
+
| 0.0138 | 1.4 | 70 | 0.9139 | 0.76 |
|
61 |
+
| 0.0003 | 1.6 | 80 | 0.9160 | 0.78 |
|
62 |
+
| 0.0001 | 1.8 | 90 | 1.1525 | 0.8 |
|
63 |
+
| 0.0085 | 2.0 | 100 | 0.8657 | 0.79 |
|
64 |
+
| 0.0033 | 2.2 | 110 | 0.8925 | 0.79 |
|
65 |
+
| 0.0055 | 2.4 | 120 | 1.2264 | 0.78 |
|
66 |
+
| 0.0014 | 2.6 | 130 | 1.4958 | 0.8 |
|
67 |
+
| 0.0031 | 2.8 | 140 | 1.4250 | 0.79 |
|
68 |
+
| 0.0138 | 3.0 | 150 | 1.4240 | 0.81 |
|
69 |
+
| 0.0304 | 3.2 | 160 | 1.4179 | 0.8 |
|
70 |
+
| 0.0 | 3.4 | 170 | 1.4685 | 0.8 |
|
71 |
+
| 0.0 | 3.6 | 180 | 1.4897 | 0.8 |
|
72 |
+
| 0.0015 | 3.8 | 190 | 1.2689 | 0.8 |
|
73 |
+
| 0.0001 | 4.0 | 200 | 1.0355 | 0.78 |
|
74 |
+
| 0.0007 | 4.2 | 210 | 1.1339 | 0.77 |
|
75 |
+
| 0.0002 | 4.4 | 220 | 1.1915 | 0.79 |
|
76 |
+
| 0.0001 | 4.6 | 230 | 1.1300 | 0.8 |
|
77 |
+
| 0.001 | 4.8 | 240 | 1.1464 | 0.79 |
|
78 |
+
| 0.0001 | 5.0 | 250 | 1.2227 | 0.78 |
|
79 |
+
| 0.0 | 5.2 | 260 | 1.3048 | 0.81 |
|
80 |
+
| 0.0 | 5.4 | 270 | 1.3418 | 0.79 |
|
81 |
+
| 0.0093 | 5.6 | 280 | 1.3442 | 0.78 |
|
82 |
+
| 0.0004 | 5.8 | 290 | 1.2721 | 0.8 |
|
83 |
+
| 0.0035 | 6.0 | 300 | 1.1852 | 0.77 |
|
84 |
+
| 0.0016 | 6.2 | 310 | 1.1745 | 0.77 |
|
85 |
+
| 0.0003 | 6.4 | 320 | 1.1138 | 0.8 |
|
86 |
+
| 0.0002 | 6.6 | 330 | 1.2342 | 0.79 |
|
87 |
+
| 0.0055 | 6.8 | 340 | 1.3594 | 0.79 |
|
88 |
+
| 0.0 | 7.0 | 350 | 1.4109 | 0.79 |
|
89 |
+
| 0.0 | 7.2 | 360 | 1.4677 | 0.78 |
|
90 |
+
| 0.0 | 7.4 | 370 | 1.4951 | 0.77 |
|
91 |
+
| 0.0 | 7.6 | 380 | 1.4987 | 0.77 |
|
92 |
+
| 0.0004 | 7.8 | 390 | 1.4517 | 0.77 |
|
93 |
+
| 0.0 | 8.0 | 400 | 1.4632 | 0.77 |
|
94 |
+
| 0.0 | 8.2 | 410 | 1.4825 | 0.78 |
|
95 |
+
| 0.0008 | 8.4 | 420 | 1.4486 | 0.79 |
|
96 |
+
| 0.0 | 8.6 | 430 | 1.4426 | 0.79 |
|
97 |
+
| 0.0 | 8.8 | 440 | 1.4216 | 0.79 |
|
98 |
+
| 0.0 | 9.0 | 450 | 1.4166 | 0.79 |
|
99 |
+
| 0.0 | 9.2 | 460 | 1.4161 | 0.79 |
|
100 |
+
| 0.0 | 9.4 | 470 | 1.4172 | 0.79 |
|
101 |
+
| 0.0003 | 9.6 | 480 | 1.4179 | 0.79 |
|
102 |
+
| 0.0286 | 9.8 | 490 | 1.4155 | 0.79 |
|
103 |
+
| 0.0 | 10.0 | 500 | 1.4143 | 0.79 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.34.0
|
109 |
+
- Pytorch 2.1.0
|
110 |
+
- Datasets 2.14.5
|
111 |
+
- Tokenizers 0.14.0
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.34.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4245c1af7791f6198b035405b06f79e0a4adbe61f031c70edcdb3d9e3f23fdcd
|
3 |
+
size 2239701870
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:003498ab0695fbf35aedc8bbbae1e20a6033a1b3914e49c6d2fbe1d54d7d93b9
|
3 |
+
size 17082786
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e5c01d9438ab3bc8ca33c2d7007768ad2553bb3f0e0dac5beb330668bb8e656
|
3 |
+
size 4472
|