0.68
Browse files- README.md +103 -0
- config.json +67 -0
- model.safetensors +3 -0
- runs/Mar11_16-02-39_053e0c5ab5f8/events.out.tfevents.1710172961.053e0c5ab5f8.34.0 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: avsolatorio/GIST-large-Embedding-v0
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: output
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# output
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [avsolatorio/GIST-large-Embedding-v0](https://huggingface.co/avsolatorio/GIST-large-Embedding-v0) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3318
|
22 |
+
- F1: 0.6260
|
23 |
+
- Roc Auc: 0.7856
|
24 |
+
- Accuracy: 0.1786
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 40
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
56 |
+
| 0.4488 | 1.0 | 25 | 0.3675 | 0.0779 | 0.5325 | 0.0179 |
|
57 |
+
| 0.3356 | 2.0 | 50 | 0.3240 | 0.1910 | 0.5740 | 0.0536 |
|
58 |
+
| 0.2818 | 3.0 | 75 | 0.2998 | 0.3079 | 0.6141 | 0.0357 |
|
59 |
+
| 0.2346 | 4.0 | 100 | 0.2767 | 0.4724 | 0.6938 | 0.0893 |
|
60 |
+
| 0.1954 | 5.0 | 125 | 0.2833 | 0.4403 | 0.6850 | 0.0714 |
|
61 |
+
| 0.1605 | 6.0 | 150 | 0.2706 | 0.5153 | 0.7220 | 0.0536 |
|
62 |
+
| 0.134 | 7.0 | 175 | 0.2719 | 0.5218 | 0.7311 | 0.1071 |
|
63 |
+
| 0.1133 | 8.0 | 200 | 0.2776 | 0.5369 | 0.7475 | 0.0714 |
|
64 |
+
| 0.0935 | 9.0 | 225 | 0.2626 | 0.5796 | 0.7555 | 0.1429 |
|
65 |
+
| 0.0808 | 10.0 | 250 | 0.2669 | 0.5778 | 0.7576 | 0.125 |
|
66 |
+
| 0.0694 | 11.0 | 275 | 0.2633 | 0.5963 | 0.7731 | 0.1429 |
|
67 |
+
| 0.0573 | 12.0 | 300 | 0.2661 | 0.5658 | 0.7612 | 0.1071 |
|
68 |
+
| 0.0496 | 13.0 | 325 | 0.2543 | 0.6004 | 0.7643 | 0.1429 |
|
69 |
+
| 0.0429 | 14.0 | 350 | 0.2735 | 0.5936 | 0.7729 | 0.1071 |
|
70 |
+
| 0.0366 | 15.0 | 375 | 0.2694 | 0.6179 | 0.7848 | 0.1429 |
|
71 |
+
| 0.0323 | 16.0 | 400 | 0.2724 | 0.6217 | 0.7865 | 0.1429 |
|
72 |
+
| 0.0289 | 17.0 | 425 | 0.2821 | 0.6157 | 0.7734 | 0.1786 |
|
73 |
+
| 0.0257 | 18.0 | 450 | 0.2787 | 0.6399 | 0.7854 | 0.1786 |
|
74 |
+
| 0.0229 | 19.0 | 475 | 0.2887 | 0.6114 | 0.7774 | 0.1071 |
|
75 |
+
| 0.02 | 20.0 | 500 | 0.2807 | 0.6394 | 0.7970 | 0.1429 |
|
76 |
+
| 0.0182 | 21.0 | 525 | 0.2852 | 0.6343 | 0.7797 | 0.1786 |
|
77 |
+
| 0.0165 | 22.0 | 550 | 0.2899 | 0.6132 | 0.7774 | 0.1607 |
|
78 |
+
| 0.0148 | 23.0 | 575 | 0.3000 | 0.6285 | 0.7888 | 0.1607 |
|
79 |
+
| 0.0136 | 24.0 | 600 | 0.2950 | 0.6409 | 0.7908 | 0.1429 |
|
80 |
+
| 0.0123 | 25.0 | 625 | 0.3034 | 0.6165 | 0.7815 | 0.1607 |
|
81 |
+
| 0.0112 | 26.0 | 650 | 0.3061 | 0.6384 | 0.7949 | 0.1607 |
|
82 |
+
| 0.0103 | 27.0 | 675 | 0.3041 | 0.6371 | 0.7906 | 0.1964 |
|
83 |
+
| 0.0095 | 28.0 | 700 | 0.3189 | 0.6204 | 0.7836 | 0.1429 |
|
84 |
+
| 0.009 | 29.0 | 725 | 0.3115 | 0.6267 | 0.7890 | 0.1786 |
|
85 |
+
| 0.0083 | 30.0 | 750 | 0.3168 | 0.6264 | 0.7856 | 0.1786 |
|
86 |
+
| 0.008 | 31.0 | 775 | 0.3199 | 0.6320 | 0.7866 | 0.1786 |
|
87 |
+
| 0.0075 | 32.0 | 800 | 0.3271 | 0.6208 | 0.7839 | 0.1607 |
|
88 |
+
| 0.0072 | 33.0 | 825 | 0.3219 | 0.6240 | 0.7856 | 0.1607 |
|
89 |
+
| 0.0068 | 34.0 | 850 | 0.3257 | 0.6312 | 0.7849 | 0.1786 |
|
90 |
+
| 0.0065 | 35.0 | 875 | 0.3249 | 0.6247 | 0.7855 | 0.1786 |
|
91 |
+
| 0.0063 | 36.0 | 900 | 0.3296 | 0.6291 | 0.7881 | 0.1786 |
|
92 |
+
| 0.0062 | 37.0 | 925 | 0.3302 | 0.6227 | 0.7844 | 0.1786 |
|
93 |
+
| 0.006 | 38.0 | 950 | 0.3287 | 0.6260 | 0.7856 | 0.1786 |
|
94 |
+
| 0.0058 | 39.0 | 975 | 0.3317 | 0.6260 | 0.7856 | 0.1786 |
|
95 |
+
| 0.0058 | 40.0 | 1000 | 0.3318 | 0.6260 | 0.7856 | 0.1786 |
|
96 |
+
|
97 |
+
|
98 |
+
### Framework versions
|
99 |
+
|
100 |
+
- Transformers 4.38.1
|
101 |
+
- Pytorch 2.1.2
|
102 |
+
- Datasets 2.1.0
|
103 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "avsolatorio/GIST-large-Embedding-v0",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "CE",
|
14 |
+
"1": "ENV",
|
15 |
+
"2": "BME",
|
16 |
+
"3": "PE",
|
17 |
+
"4": "METAL",
|
18 |
+
"5": "ME",
|
19 |
+
"6": "EE",
|
20 |
+
"7": "CPE",
|
21 |
+
"8": "OPTIC",
|
22 |
+
"9": "NANO",
|
23 |
+
"10": "CHE",
|
24 |
+
"11": "MATENG",
|
25 |
+
"12": "AGRI",
|
26 |
+
"13": "EDU",
|
27 |
+
"14": "IE",
|
28 |
+
"15": "SAFETY",
|
29 |
+
"16": "MATH",
|
30 |
+
"17": "MATSCI"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 4096,
|
34 |
+
"label2id": {
|
35 |
+
"AGRI": 12,
|
36 |
+
"BME": 2,
|
37 |
+
"CE": 0,
|
38 |
+
"CHE": 10,
|
39 |
+
"CPE": 7,
|
40 |
+
"EDU": 13,
|
41 |
+
"EE": 6,
|
42 |
+
"ENV": 1,
|
43 |
+
"IE": 14,
|
44 |
+
"MATENG": 11,
|
45 |
+
"MATH": 16,
|
46 |
+
"MATSCI": 17,
|
47 |
+
"ME": 5,
|
48 |
+
"METAL": 4,
|
49 |
+
"NANO": 9,
|
50 |
+
"OPTIC": 8,
|
51 |
+
"PE": 3,
|
52 |
+
"SAFETY": 15
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-12,
|
55 |
+
"max_position_embeddings": 512,
|
56 |
+
"model_type": "bert",
|
57 |
+
"num_attention_heads": 16,
|
58 |
+
"num_hidden_layers": 24,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"position_embedding_type": "absolute",
|
61 |
+
"problem_type": "multi_label_classification",
|
62 |
+
"torch_dtype": "float32",
|
63 |
+
"transformers_version": "4.38.1",
|
64 |
+
"type_vocab_size": 2,
|
65 |
+
"use_cache": true,
|
66 |
+
"vocab_size": 30522
|
67 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da99fdf7e0bb11d3600630d6305da278d8cd6a9cdf5bf405b31e2b942dbf0292
|
3 |
+
size 1340688368
|
runs/Mar11_16-02-39_053e0c5ab5f8/events.out.tfevents.1710172961.053e0c5ab5f8.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a4332c2cf028865c5dc9efbb9e003f49fcce585a0bf9ccd26a83b91c7d7e9b6
|
3 |
+
size 30775
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
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 |
+
"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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b8843979bc85a81d08ffdff4c9fc17eb1af5a480b4c652c8042bfd34b094d8c
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|