End of training
Browse files- README.md +107 -0
- config.json +31 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- runs/Sep10_06-26-05_cbd3afa14c44/events.out.tfevents.1725949568.cbd3afa14c44.388.2 +3 -0
- runs/Sep10_06-26-35_cbd3afa14c44/events.out.tfevents.1725949596.cbd3afa14c44.388.3 +3 -0
- runs/Sep10_06-26-35_cbd3afa14c44/events.out.tfevents.1725949640.cbd3afa14c44.388.4 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bert-base-multilingual-cased-finetuned-CAJ
|
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 |
+
# bert-base-multilingual-cased-finetuned-CAJ
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4226
|
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: 2e-05
|
38 |
+
- train_batch_size: 64
|
39 |
+
- eval_batch_size: 64
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 50
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.0475 | 1.0 | 4 | 0.9036 |
|
51 |
+
| 0.856 | 2.0 | 8 | 0.7524 |
|
52 |
+
| 0.8014 | 3.0 | 12 | 0.9149 |
|
53 |
+
| 0.7855 | 4.0 | 16 | 0.8052 |
|
54 |
+
| 0.6329 | 5.0 | 20 | 0.8866 |
|
55 |
+
| 0.7714 | 6.0 | 24 | 0.9880 |
|
56 |
+
| 0.6925 | 7.0 | 28 | 0.7490 |
|
57 |
+
| 0.6408 | 8.0 | 32 | 0.6889 |
|
58 |
+
| 0.6983 | 9.0 | 36 | 0.7648 |
|
59 |
+
| 0.6028 | 10.0 | 40 | 0.4431 |
|
60 |
+
| 0.5899 | 11.0 | 44 | 0.6020 |
|
61 |
+
| 0.6032 | 12.0 | 48 | 0.5415 |
|
62 |
+
| 0.5282 | 13.0 | 52 | 0.5124 |
|
63 |
+
| 0.5528 | 14.0 | 56 | 0.6242 |
|
64 |
+
| 0.5191 | 15.0 | 60 | 0.4651 |
|
65 |
+
| 0.5307 | 16.0 | 64 | 0.7029 |
|
66 |
+
| 0.5309 | 17.0 | 68 | 0.5505 |
|
67 |
+
| 0.4425 | 18.0 | 72 | 0.4792 |
|
68 |
+
| 0.4594 | 19.0 | 76 | 0.3245 |
|
69 |
+
| 0.4425 | 20.0 | 80 | 0.5562 |
|
70 |
+
| 0.4409 | 21.0 | 84 | 0.4026 |
|
71 |
+
| 0.442 | 22.0 | 88 | 0.4993 |
|
72 |
+
| 0.4535 | 23.0 | 92 | 0.5693 |
|
73 |
+
| 0.3707 | 24.0 | 96 | 0.4002 |
|
74 |
+
| 0.3914 | 25.0 | 100 | 0.5969 |
|
75 |
+
| 0.3493 | 26.0 | 104 | 0.3247 |
|
76 |
+
| 0.3595 | 27.0 | 108 | 0.3832 |
|
77 |
+
| 0.395 | 28.0 | 112 | 0.4497 |
|
78 |
+
| 0.4186 | 29.0 | 116 | 0.3194 |
|
79 |
+
| 0.4131 | 30.0 | 120 | 0.3699 |
|
80 |
+
| 0.357 | 31.0 | 124 | 0.4968 |
|
81 |
+
| 0.3369 | 32.0 | 128 | 0.4404 |
|
82 |
+
| 0.3734 | 33.0 | 132 | 0.4266 |
|
83 |
+
| 0.342 | 34.0 | 136 | 0.5202 |
|
84 |
+
| 0.3643 | 35.0 | 140 | 0.3872 |
|
85 |
+
| 0.3362 | 36.0 | 144 | 0.5037 |
|
86 |
+
| 0.3302 | 37.0 | 148 | 0.5572 |
|
87 |
+
| 0.3241 | 38.0 | 152 | 0.4138 |
|
88 |
+
| 0.299 | 39.0 | 156 | 0.2888 |
|
89 |
+
| 0.3383 | 40.0 | 160 | 0.5453 |
|
90 |
+
| 0.3786 | 41.0 | 164 | 0.3909 |
|
91 |
+
| 0.3121 | 42.0 | 168 | 0.4414 |
|
92 |
+
| 0.3357 | 43.0 | 172 | 0.3216 |
|
93 |
+
| 0.3601 | 44.0 | 176 | 0.3046 |
|
94 |
+
| 0.2662 | 45.0 | 180 | 0.4090 |
|
95 |
+
| 0.2979 | 46.0 | 184 | 0.4571 |
|
96 |
+
| 0.4222 | 47.0 | 188 | 0.4513 |
|
97 |
+
| 0.3006 | 48.0 | 192 | 0.3829 |
|
98 |
+
| 0.3385 | 49.0 | 196 | 0.3473 |
|
99 |
+
| 0.2711 | 50.0 | 200 | 0.3419 |
|
100 |
+
|
101 |
+
|
102 |
+
### Framework versions
|
103 |
+
|
104 |
+
- Transformers 4.39.3
|
105 |
+
- Pytorch 2.2.2+cu121
|
106 |
+
- Datasets 2.18.0
|
107 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.39.3",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 119547
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.39.3"
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:506ec631e0d96bbe4660e90c737cbdc47660268e6b17347bf426ee973c62787e
|
3 |
+
size 711921812
|
runs/Sep10_06-26-05_cbd3afa14c44/events.out.tfevents.1725949568.cbd3afa14c44.388.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc2f368e57b8ad2781ad82ed1ffce8694cf035ae2d1b4b195419dd9ae353770
|
3 |
+
size 10738
|
runs/Sep10_06-26-35_cbd3afa14c44/events.out.tfevents.1725949596.cbd3afa14c44.388.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:784a716239aef8d4a945e2a72288deb80b2d5a6e5a485ca77013ba8256e2d697
|
3 |
+
size 32546
|
runs/Sep10_06-26-35_cbd3afa14c44/events.out.tfevents.1725949640.cbd3afa14c44.388.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bf98da674d8ac6aa9c543342153d1712fdd1d128068473599934f328fc1687f
|
3 |
+
size 359
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ebd544ed2b3f64e59c84626dafafd3c798a6dad5f7958f020a4238fa6db021e
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|