sibyl commited on
Commit
571789c
1 Parent(s): 4fa8b7e
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - yelp_polarity
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-base-uncased-yelp_polarity
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: yelp_polarity
17
+ type: yelp_polarity
18
+ args: plain_text
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9516052631578947
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-yelp_polarity
29
+
30
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the yelp_polarity dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.3222
33
+ - Accuracy: 0.9516
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: 1
54
+ - eval_batch_size: 8
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: 277200
59
+ - training_steps: 2772000
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
65
+ | 0.8067 | 0.0 | 2000 | 0.8241 | 0.4975 |
66
+ | 0.5482 | 0.01 | 4000 | 0.3507 | 0.8591 |
67
+ | 0.3427 | 0.01 | 6000 | 0.3750 | 0.9139 |
68
+ | 0.4133 | 0.01 | 8000 | 0.5520 | 0.9016 |
69
+ | 0.4301 | 0.02 | 10000 | 0.3803 | 0.9304 |
70
+ | 0.3716 | 0.02 | 12000 | 0.4168 | 0.9337 |
71
+ | 0.4076 | 0.03 | 14000 | 0.5042 | 0.9170 |
72
+ | 0.3674 | 0.03 | 16000 | 0.4806 | 0.9268 |
73
+ | 0.3813 | 0.03 | 18000 | 0.4227 | 0.9261 |
74
+ | 0.3723 | 0.04 | 20000 | 0.3360 | 0.9418 |
75
+ | 0.3876 | 0.04 | 22000 | 0.3255 | 0.9407 |
76
+ | 0.3351 | 0.04 | 24000 | 0.3283 | 0.9404 |
77
+ | 0.34 | 0.05 | 26000 | 0.3489 | 0.9430 |
78
+ | 0.3006 | 0.05 | 28000 | 0.3302 | 0.9464 |
79
+ | 0.349 | 0.05 | 30000 | 0.3853 | 0.9375 |
80
+ | 0.3696 | 0.06 | 32000 | 0.2992 | 0.9454 |
81
+ | 0.3301 | 0.06 | 34000 | 0.3484 | 0.9464 |
82
+ | 0.3151 | 0.06 | 36000 | 0.3529 | 0.9455 |
83
+ | 0.3682 | 0.07 | 38000 | 0.3052 | 0.9420 |
84
+ | 0.3184 | 0.07 | 40000 | 0.3323 | 0.9466 |
85
+ | 0.3207 | 0.08 | 42000 | 0.3133 | 0.9532 |
86
+ | 0.3346 | 0.08 | 44000 | 0.3826 | 0.9414 |
87
+ | 0.3008 | 0.08 | 46000 | 0.3059 | 0.9484 |
88
+ | 0.3306 | 0.09 | 48000 | 0.3089 | 0.9475 |
89
+ | 0.342 | 0.09 | 50000 | 0.3611 | 0.9486 |
90
+ | 0.3424 | 0.09 | 52000 | 0.3227 | 0.9445 |
91
+ | 0.3044 | 0.1 | 54000 | 0.3130 | 0.9489 |
92
+ | 0.3278 | 0.1 | 56000 | 0.3827 | 0.9368 |
93
+ | 0.288 | 0.1 | 58000 | 0.3080 | 0.9504 |
94
+ | 0.3342 | 0.11 | 60000 | 0.3252 | 0.9471 |
95
+ | 0.3737 | 0.11 | 62000 | 0.4250 | 0.9343 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.10.2
101
+ - Pytorch 1.7.1
102
+ - Datasets 1.6.1
103
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.10.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e62d19e7307acc3c0bb9386b23054ea3129baf74f2426842c30f28c0f0a9876
3
+ size 438024063
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 sha256:8081740e29182941ad13f87dd36aeb961ece00feda93d7e114d5fcadc99794d4
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff