End of training
Browse files- README.md +64 -0
- config.json +49 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +75 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: funnel-transformer/xlarge-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: funnel-test-512
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# funnel-test-512
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [funnel-transformer/xlarge-base](https://huggingface.co/funnel-transformer/xlarge-base) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4556
|
21 |
+
- Accuracy: 0.8041
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 1
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 0.6108 | 0.2 | 59 | 0.6724 | 0.6460 |
|
54 |
+
| 0.651 | 0.4 | 118 | 0.6463 | 0.6451 |
|
55 |
+
| 0.6052 | 0.61 | 177 | 0.6210 | 0.6424 |
|
56 |
+
| 0.4588 | 0.81 | 236 | 0.4556 | 0.8041 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.36.2
|
62 |
+
- Pytorch 2.0.1
|
63 |
+
- Datasets 2.16.1
|
64 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "funnel-transformer/xlarge-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"architectures": [
|
5 |
+
"FunnelForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_type": "relative_shift",
|
9 |
+
"block_repeats": [
|
10 |
+
1,
|
11 |
+
1,
|
12 |
+
1
|
13 |
+
],
|
14 |
+
"block_sizes": [
|
15 |
+
10,
|
16 |
+
10,
|
17 |
+
10
|
18 |
+
],
|
19 |
+
"d_head": 64,
|
20 |
+
"d_inner": 4096,
|
21 |
+
"d_model": 1024,
|
22 |
+
"hidden_act": "gelu_new",
|
23 |
+
"hidden_dropout": 0.1,
|
24 |
+
"id2label": {
|
25 |
+
"0": "HUMAN",
|
26 |
+
"1": "AI"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.1,
|
29 |
+
"initializer_std": null,
|
30 |
+
"label2id": {
|
31 |
+
"AI": 1,
|
32 |
+
"HUMAN": 0
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-09,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "funnel",
|
37 |
+
"n_head": 16,
|
38 |
+
"num_decoder_layers": 2,
|
39 |
+
"pool_q_only": true,
|
40 |
+
"pooling_type": "mean",
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"rel_attn_type": "factorized",
|
43 |
+
"separate_cls": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.36.2",
|
46 |
+
"truncate_seq": true,
|
47 |
+
"type_vocab_size": 3,
|
48 |
+
"vocab_size": 30522
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86b3ddded2fdf1a7e1d1657cce68a53b3c80a1041fae02e44156b450d5770602
|
3 |
+
size 1767173656
|
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": "<cls>",
|
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": false,
|
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": "<sep>",
|
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_config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"96": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"97": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"100": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"101": {
|
36 |
+
"content": "<cls>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"102": {
|
44 |
+
"content": "<sep>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"103": {
|
52 |
+
"content": "<mask>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"bos_token": "<s>",
|
61 |
+
"clean_up_tokenization_spaces": true,
|
62 |
+
"cls_token": "<cls>",
|
63 |
+
"do_basic_tokenize": true,
|
64 |
+
"do_lower_case": true,
|
65 |
+
"eos_token": "</s>",
|
66 |
+
"mask_token": "<mask>",
|
67 |
+
"model_max_length": 512,
|
68 |
+
"never_split": null,
|
69 |
+
"pad_token": "<pad>",
|
70 |
+
"sep_token": "<sep>",
|
71 |
+
"strip_accents": null,
|
72 |
+
"tokenize_chinese_chars": true,
|
73 |
+
"tokenizer_class": "FunnelTokenizer",
|
74 |
+
"unk_token": "<unk>"
|
75 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b48da4236c403c99cf0915d65875fcc96978c9a77c24cd3b7e8948fb7b1d878
|
3 |
+
size 4219
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|