sibyl commited on
Commit
35a246b
1 Parent(s): 8158c40
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - d_bpedia14
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-base-uncased-dbpedia_14
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: d_bpedia14
17
+ type: d_bpedia14
18
+ args: dbpedia_14
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9902857142857143
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # bert-base-uncased-dbpedia_14
29
+
30
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the d_bpedia14 dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.0547
33
+ - Accuracy: 0.9903
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-05
53
+ - train_batch_size: 8
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_steps: 34650
59
+ - training_steps: 346500
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
65
+ | 1.7757 | 0.03 | 2000 | 0.2732 | 0.9880 |
66
+ | 0.1002 | 0.06 | 4000 | 0.0620 | 0.9891 |
67
+ | 0.0547 | 0.09 | 6000 | 0.0723 | 0.9879 |
68
+ | 0.0558 | 0.12 | 8000 | 0.0678 | 0.9875 |
69
+ | 0.0534 | 0.14 | 10000 | 0.0554 | 0.9896 |
70
+ | 0.0632 | 0.17 | 12000 | 0.0670 | 0.9888 |
71
+ | 0.0612 | 0.2 | 14000 | 0.0733 | 0.9873 |
72
+ | 0.0667 | 0.23 | 16000 | 0.0623 | 0.9896 |
73
+ | 0.0636 | 0.26 | 18000 | 0.0836 | 0.9868 |
74
+ | 0.0705 | 0.29 | 20000 | 0.0776 | 0.9855 |
75
+ | 0.0726 | 0.32 | 22000 | 0.0805 | 0.9861 |
76
+ | 0.0778 | 0.35 | 24000 | 0.0713 | 0.9870 |
77
+ | 0.0713 | 0.38 | 26000 | 0.1277 | 0.9805 |
78
+ | 0.0965 | 0.4 | 28000 | 0.0810 | 0.9855 |
79
+ | 0.0881 | 0.43 | 30000 | 0.0910 | 0.985 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.10.2
85
+ - Pytorch 1.7.1
86
+ - Datasets 1.6.1
87
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
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": 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
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1,
33
+ "LABEL_10": 10,
34
+ "LABEL_11": 11,
35
+ "LABEL_12": 12,
36
+ "LABEL_13": 13,
37
+ "LABEL_2": 2,
38
+ "LABEL_3": 3,
39
+ "LABEL_4": 4,
40
+ "LABEL_5": 5,
41
+ "LABEL_6": 6,
42
+ "LABEL_7": 7,
43
+ "LABEL_8": 8,
44
+ "LABEL_9": 9
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "bert",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 0,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "single_label_classification",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.10.2",
56
+ "type_vocab_size": 2,
57
+ "use_cache": true,
58
+ "vocab_size": 30522
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0073913754b2a49726b74744200a9d0d33f838dedda5641e2a10bb1c84d11b2a
3
+ size 438060991
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff824850b542c7f7465b3fa27aa5372567ca88140a12da2fc717444fbf1a33ca
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff