Jordi36699
commited on
Commit
•
0903d81
1
Parent(s):
6626db8
Final Model
Browse files- README.md +97 -0
- config.json +67 -0
- model.safetensors +3 -0
- runs/Mar18_10-18-01_f49a24f822ba/events.out.tfevents.1710757083.f49a24f822ba.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 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: chefdiff
|
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 |
+
# chefdiff
|
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: 0.2966
|
22 |
+
- F1: 0.6367
|
23 |
+
- Roc Auc: 0.7929
|
24 |
+
- Accuracy: 0.0909
|
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: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 35
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
55 |
+
| 0.4056 | 1.0 | 50 | 0.3591 | 0.1786 | 0.5651 | 0.0182 |
|
56 |
+
| 0.3103 | 2.0 | 100 | 0.3197 | 0.3214 | 0.6256 | 0.0909 |
|
57 |
+
| 0.2522 | 3.0 | 150 | 0.2939 | 0.3551 | 0.6471 | 0.0727 |
|
58 |
+
| 0.2039 | 4.0 | 200 | 0.2741 | 0.4813 | 0.7092 | 0.1273 |
|
59 |
+
| 0.1632 | 5.0 | 250 | 0.2714 | 0.5493 | 0.7380 | 0.0909 |
|
60 |
+
| 0.1308 | 6.0 | 300 | 0.2532 | 0.4740 | 0.6994 | 0.1636 |
|
61 |
+
| 0.1056 | 7.0 | 350 | 0.2644 | 0.5641 | 0.7575 | 0.0909 |
|
62 |
+
| 0.0837 | 8.0 | 400 | 0.2541 | 0.5684 | 0.7579 | 0.1091 |
|
63 |
+
| 0.0679 | 9.0 | 450 | 0.2542 | 0.6112 | 0.7782 | 0.1273 |
|
64 |
+
| 0.0562 | 10.0 | 500 | 0.2587 | 0.6342 | 0.7932 | 0.1455 |
|
65 |
+
| 0.0476 | 11.0 | 550 | 0.2547 | 0.6399 | 0.7913 | 0.1455 |
|
66 |
+
| 0.0421 | 12.0 | 600 | 0.2683 | 0.6429 | 0.7998 | 0.1273 |
|
67 |
+
| 0.0369 | 13.0 | 650 | 0.2738 | 0.6146 | 0.7839 | 0.0909 |
|
68 |
+
| 0.0335 | 14.0 | 700 | 0.2678 | 0.6387 | 0.7920 | 0.0909 |
|
69 |
+
| 0.0298 | 15.0 | 750 | 0.2700 | 0.6123 | 0.7812 | 0.0909 |
|
70 |
+
| 0.0275 | 16.0 | 800 | 0.2737 | 0.6152 | 0.7804 | 0.0909 |
|
71 |
+
| 0.0255 | 17.0 | 850 | 0.2741 | 0.6339 | 0.7852 | 0.1091 |
|
72 |
+
| 0.024 | 18.0 | 900 | 0.2778 | 0.6564 | 0.8052 | 0.1091 |
|
73 |
+
| 0.0223 | 19.0 | 950 | 0.2815 | 0.6521 | 0.8019 | 0.1091 |
|
74 |
+
| 0.0213 | 20.0 | 1000 | 0.2778 | 0.6296 | 0.7902 | 0.0727 |
|
75 |
+
| 0.0201 | 21.0 | 1050 | 0.2861 | 0.6340 | 0.7900 | 0.0909 |
|
76 |
+
| 0.0192 | 22.0 | 1100 | 0.2819 | 0.6413 | 0.7949 | 0.0909 |
|
77 |
+
| 0.0185 | 23.0 | 1150 | 0.2913 | 0.6280 | 0.7888 | 0.0727 |
|
78 |
+
| 0.0178 | 24.0 | 1200 | 0.2874 | 0.6347 | 0.7938 | 0.0727 |
|
79 |
+
| 0.0172 | 25.0 | 1250 | 0.2890 | 0.6271 | 0.7879 | 0.0909 |
|
80 |
+
| 0.0166 | 26.0 | 1300 | 0.2900 | 0.6306 | 0.7901 | 0.0727 |
|
81 |
+
| 0.0161 | 27.0 | 1350 | 0.2944 | 0.6284 | 0.7896 | 0.0727 |
|
82 |
+
| 0.0158 | 28.0 | 1400 | 0.2931 | 0.6407 | 0.7954 | 0.0909 |
|
83 |
+
| 0.0154 | 29.0 | 1450 | 0.2942 | 0.6345 | 0.7937 | 0.0727 |
|
84 |
+
| 0.015 | 30.0 | 1500 | 0.2960 | 0.6413 | 0.7942 | 0.0909 |
|
85 |
+
| 0.0147 | 31.0 | 1550 | 0.2927 | 0.6477 | 0.7966 | 0.0909 |
|
86 |
+
| 0.0147 | 32.0 | 1600 | 0.2952 | 0.6396 | 0.7943 | 0.0909 |
|
87 |
+
| 0.0145 | 33.0 | 1650 | 0.2965 | 0.6314 | 0.7924 | 0.0727 |
|
88 |
+
| 0.0144 | 34.0 | 1700 | 0.2971 | 0.6367 | 0.7929 | 0.0909 |
|
89 |
+
| 0.0143 | 35.0 | 1750 | 0.2966 | 0.6367 | 0.7929 | 0.0909 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.38.1
|
95 |
+
- Pytorch 2.1.2
|
96 |
+
- Datasets 2.1.0
|
97 |
+
- 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 sha256:410e95a971ae054401485f84055439e7f62a1a70cc8e980bc4316a750685d69b
|
3 |
+
size 1340688368
|
runs/Mar18_10-18-01_f49a24f822ba/events.out.tfevents.1710757083.f49a24f822ba.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b1ff1ba1c65e157ccf2430f9e61c5a71b1644a9183477efcefd1ae8c7bf318
|
3 |
+
size 27661
|
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 sha256:5c276475d5b657f3036636a95f373b8edb18e49097c7093640293b1a01caecce
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|