End of training
Browse files- README.md +74 -0
- config.json +67 -0
- model.safetensors +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 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: avsolatorio/GIST-large-Embedding-v0
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: my-clf
|
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 |
+
# my-clf
|
17 |
+
|
18 |
+
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.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.1824
|
21 |
+
- F1: 0.6653
|
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: 5e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 15
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
52 |
+
| 0.1488 | 1.0 | 100 | 1.1930 | 0.6355 |
|
53 |
+
| 0.1232 | 2.0 | 200 | 0.9133 | 0.6473 |
|
54 |
+
| 0.0797 | 3.0 | 300 | 1.0238 | 0.6603 |
|
55 |
+
| 0.0522 | 4.0 | 400 | 0.9822 | 0.6713 |
|
56 |
+
| 0.0366 | 5.0 | 500 | 1.0208 | 0.6664 |
|
57 |
+
| 0.0252 | 6.0 | 600 | 0.9856 | 0.6755 |
|
58 |
+
| 0.0199 | 7.0 | 700 | 1.0628 | 0.6665 |
|
59 |
+
| 0.0174 | 8.0 | 800 | 1.0667 | 0.6651 |
|
60 |
+
| 0.0155 | 9.0 | 900 | 1.0934 | 0.6664 |
|
61 |
+
| 0.0141 | 10.0 | 1000 | 1.1478 | 0.6676 |
|
62 |
+
| 0.0131 | 11.0 | 1100 | 1.1644 | 0.6707 |
|
63 |
+
| 0.0124 | 12.0 | 1200 | 1.1661 | 0.6638 |
|
64 |
+
| 0.0122 | 13.0 | 1300 | 1.1781 | 0.6648 |
|
65 |
+
| 0.0118 | 14.0 | 1400 | 1.1810 | 0.6664 |
|
66 |
+
| 0.0116 | 15.0 | 1500 | 1.1824 | 0.6653 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.38.2
|
72 |
+
- Pytorch 2.1.0+cu118
|
73 |
+
- Datasets 2.18.0
|
74 |
+
- 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": "4.38.2",
|
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 sha256:765ae656981361b3e6e7475604f55c236d72e6f028eadbf7e75633b9de2796a9
|
3 |
+
size 1340688368
|
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:d0c810b0b81ed7a018d18992203047dc4b7fed32d287d4d728173b5d99bf6e25
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|