Model save
Browse files- README.md +57 -61
- config.json +25 -25
- generation_config.json +5 -5
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -51
- tokenizer.json +2 -2
- tokenizer_config.json +19 -54
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,61 +1,57 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: Twitter/twhin-bert-large
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
model-index:
|
7 |
-
- name: model
|
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 |
-
# model
|
15 |
-
|
16 |
-
This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on the None dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
-
|
20 |
-
## Model description
|
21 |
-
|
22 |
-
More information needed
|
23 |
-
|
24 |
-
## Intended uses & limitations
|
25 |
-
|
26 |
-
More information needed
|
27 |
-
|
28 |
-
## Training and evaluation data
|
29 |
-
|
30 |
-
More information needed
|
31 |
-
|
32 |
-
## Training procedure
|
33 |
-
|
34 |
-
### Training hyperparameters
|
35 |
-
|
36 |
-
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 1e-05
|
38 |
-
- train_batch_size: 8
|
39 |
-
- eval_batch_size: 8
|
40 |
-
- seed: 42
|
41 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
-
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
-
|
45 |
-
### Training results
|
46 |
-
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| 2.
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
- Transformers 4.44.0
|
59 |
-
- Pytorch 2.3.1+cu121
|
60 |
-
- Datasets 2.20.0
|
61 |
-
- Tokenizers 0.19.1
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Twitter/twhin-bert-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: model
|
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 |
+
# model
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.2328
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 1
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 2.4946 | 1.0 | 232 | 2.2328 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.32.1
|
55 |
+
- Pytorch 2.1.2
|
56 |
+
- Datasets 2.20.0
|
57 |
+
- Tokenizers 0.13.2
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "Twitter/twhin-bert-large",
|
3 |
-
"architectures": [
|
4 |
-
"BertForMaskedLM"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"hidden_act": "gelu",
|
9 |
-
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size": 1024,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 4096,
|
13 |
-
"layer_norm_eps": 1e-12,
|
14 |
-
"max_position_embeddings": 512,
|
15 |
-
"model_type": "bert",
|
16 |
-
"num_attention_heads": 16,
|
17 |
-
"num_hidden_layers": 24,
|
18 |
-
"pad_token_id": 0,
|
19 |
-
"position_embedding_type": "relative_key",
|
20 |
-
"torch_dtype": "float32",
|
21 |
-
"transformers_version": "4.
|
22 |
-
"type_vocab_size": 2,
|
23 |
-
"use_cache": true,
|
24 |
-
"vocab_size": 250002
|
25 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Twitter/twhin-bert-large",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "relative_key",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.32.1",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 250002
|
25 |
+
}
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"pad_token_id": 0,
|
4 |
-
"transformers_version": "4.
|
5 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.32.1"
|
5 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:600d8fd4ce0cfa1280c1c986a5d49cee68eb5dab156e873d3f2218c0c5d30c0e
|
3 |
+
size 2246995282
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,15 @@
|
|
1 |
-
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
10 |
-
"
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
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 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
+
size 17082660
|
tokenizer_config.json
CHANGED
@@ -1,54 +1,19 @@
|
|
1 |
-
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
"
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
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 |
-
"bos_token": "<s>",
|
45 |
-
"clean_up_tokenization_spaces": true,
|
46 |
-
"cls_token": "<s>",
|
47 |
-
"eos_token": "</s>",
|
48 |
-
"mask_token": "<mask>",
|
49 |
-
"model_max_length": 1000000000000000019884624838656,
|
50 |
-
"pad_token": "<pad>",
|
51 |
-
"sep_token": "</s>",
|
52 |
-
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
-
"unk_token": "<unk>"
|
54 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1000000000000000019884624838656,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfbc58e368d6eb8ccd776e6308d7463b0b1472c1e6558b3aa7043654fb480331
|
3 |
+
size 4536
|