MaryDatascientist
commited on
Commit
•
a5e1986
1
Parent(s):
47919fc
MaryDatascientist/modelA_1_12_2023
Browse files- README.md +73 -0
- config.json +92 -0
- model.safetensors +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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: modelA_1_12_2023
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# modelA_1_12_2023
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0689
|
24 |
+
- Precision: 0.8784
|
25 |
+
- Recall: 0.8915
|
26 |
+
- F1: 0.8849
|
27 |
+
- Accuracy: 0.9760
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.00019616920113351048
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 1
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0976 | 0.12 | 500 | 0.1055 | 0.8047 | 0.8025 | 0.8036 | 0.9641 |
|
59 |
+
| 0.0849 | 0.24 | 1000 | 0.0974 | 0.8186 | 0.8479 | 0.8330 | 0.9667 |
|
60 |
+
| 0.0788 | 0.37 | 1500 | 0.0865 | 0.8623 | 0.8274 | 0.8444 | 0.9695 |
|
61 |
+
| 0.0678 | 0.49 | 2000 | 0.0831 | 0.8860 | 0.8092 | 0.8459 | 0.9705 |
|
62 |
+
| 0.0555 | 0.61 | 2500 | 0.0790 | 0.8401 | 0.8899 | 0.8643 | 0.9718 |
|
63 |
+
| 0.0468 | 0.73 | 3000 | 0.0745 | 0.8727 | 0.8769 | 0.8748 | 0.9739 |
|
64 |
+
| 0.0417 | 0.85 | 3500 | 0.0704 | 0.8684 | 0.8942 | 0.8811 | 0.9751 |
|
65 |
+
| 0.0359 | 0.97 | 4000 | 0.0689 | 0.8784 | 0.8915 | 0.8849 | 0.9760 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.35.2
|
71 |
+
- Pytorch 2.1.0+cu118
|
72 |
+
- Datasets 2.15.0
|
73 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15",
|
29 |
+
"16": "LABEL_16",
|
30 |
+
"17": "LABEL_17",
|
31 |
+
"18": "LABEL_18",
|
32 |
+
"19": "LABEL_19",
|
33 |
+
"20": "LABEL_20",
|
34 |
+
"21": "LABEL_21",
|
35 |
+
"22": "LABEL_22",
|
36 |
+
"23": "LABEL_23",
|
37 |
+
"24": "LABEL_24",
|
38 |
+
"25": "LABEL_25",
|
39 |
+
"26": "LABEL_26",
|
40 |
+
"27": "LABEL_27",
|
41 |
+
"28": "LABEL_28",
|
42 |
+
"29": "LABEL_29",
|
43 |
+
"30": "LABEL_30"
|
44 |
+
},
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"intermediate_size": 3072,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1,
|
50 |
+
"LABEL_10": 10,
|
51 |
+
"LABEL_11": 11,
|
52 |
+
"LABEL_12": 12,
|
53 |
+
"LABEL_13": 13,
|
54 |
+
"LABEL_14": 14,
|
55 |
+
"LABEL_15": 15,
|
56 |
+
"LABEL_16": 16,
|
57 |
+
"LABEL_17": 17,
|
58 |
+
"LABEL_18": 18,
|
59 |
+
"LABEL_19": 19,
|
60 |
+
"LABEL_2": 2,
|
61 |
+
"LABEL_20": 20,
|
62 |
+
"LABEL_21": 21,
|
63 |
+
"LABEL_22": 22,
|
64 |
+
"LABEL_23": 23,
|
65 |
+
"LABEL_24": 24,
|
66 |
+
"LABEL_25": 25,
|
67 |
+
"LABEL_26": 26,
|
68 |
+
"LABEL_27": 27,
|
69 |
+
"LABEL_28": 28,
|
70 |
+
"LABEL_29": 29,
|
71 |
+
"LABEL_3": 3,
|
72 |
+
"LABEL_30": 30,
|
73 |
+
"LABEL_4": 4,
|
74 |
+
"LABEL_5": 5,
|
75 |
+
"LABEL_6": 6,
|
76 |
+
"LABEL_7": 7,
|
77 |
+
"LABEL_8": 8,
|
78 |
+
"LABEL_9": 9
|
79 |
+
},
|
80 |
+
"layer_norm_eps": 1e-12,
|
81 |
+
"max_position_embeddings": 512,
|
82 |
+
"model_type": "bert",
|
83 |
+
"num_attention_heads": 12,
|
84 |
+
"num_hidden_layers": 12,
|
85 |
+
"pad_token_id": 0,
|
86 |
+
"position_embedding_type": "absolute",
|
87 |
+
"torch_dtype": "float32",
|
88 |
+
"transformers_version": "4.35.2",
|
89 |
+
"type_vocab_size": 2,
|
90 |
+
"use_cache": true,
|
91 |
+
"vocab_size": 30522
|
92 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f141627249df2f4b21193e16b5dcfd50f540ee13e378597a8457b9c82d1a13
|
3 |
+
size 435685292
|
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": true,
|
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 sha256:583075ab3fa09307788db0eb59ec74dfbcf530fb2147e5e4554c66e68c3ee1a8
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|