Hugging Face's logo

fabriceyhc
/
bert-base-uncased-amazon_polarity

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
sibyl
Eval Results
Inference Endpoints
Model card Files Community
6
fabriceyhc commited on
Commit
8bd884c
·
1 Parent(s): a1c4e9a

add model

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. README.md +160 -0
  3. config.json +27 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - amazon_polarity
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-base-uncased-amazon_polarity
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: amazon_polarity
17
+ type: amazon_polarity
18
+ args: amazon_polarity
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.94647
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-amazon_polarity
29
+
30
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the amazon_polarity dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.2945
33
+ - Accuracy: 0.9465
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: 1782000
59
+ - training_steps: 17820000
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
65
+ | 0.7155 | 0.0 | 2000 | 0.7060 | 0.4622 |
66
+ | 0.7054 | 0.0 | 4000 | 0.6925 | 0.5165 |
67
+ | 0.6842 | 0.0 | 6000 | 0.6653 | 0.6116 |
68
+ | 0.6375 | 0.0 | 8000 | 0.5721 | 0.7909 |
69
+ | 0.4671 | 0.0 | 10000 | 0.3238 | 0.8770 |
70
+ | 0.3403 | 0.0 | 12000 | 0.3692 | 0.8861 |
71
+ | 0.4162 | 0.0 | 14000 | 0.4560 | 0.8908 |
72
+ | 0.4728 | 0.0 | 16000 | 0.5071 | 0.8980 |
73
+ | 0.5111 | 0.01 | 18000 | 0.5204 | 0.9015 |
74
+ | 0.4792 | 0.01 | 20000 | 0.5193 | 0.9076 |
75
+ | 0.544 | 0.01 | 22000 | 0.4835 | 0.9133 |
76
+ | 0.4745 | 0.01 | 24000 | 0.4689 | 0.9170 |
77
+ | 0.4403 | 0.01 | 26000 | 0.4778 | 0.9177 |
78
+ | 0.4405 | 0.01 | 28000 | 0.4754 | 0.9163 |
79
+ | 0.4375 | 0.01 | 30000 | 0.4808 | 0.9175 |
80
+ | 0.4628 | 0.01 | 32000 | 0.4340 | 0.9244 |
81
+ | 0.4488 | 0.01 | 34000 | 0.4162 | 0.9265 |
82
+ | 0.4608 | 0.01 | 36000 | 0.4031 | 0.9271 |
83
+ | 0.4478 | 0.01 | 38000 | 0.4502 | 0.9253 |
84
+ | 0.4237 | 0.01 | 40000 | 0.4087 | 0.9279 |
85
+ | 0.4601 | 0.01 | 42000 | 0.4133 | 0.9269 |
86
+ | 0.4153 | 0.01 | 44000 | 0.4230 | 0.9306 |
87
+ | 0.4096 | 0.01 | 46000 | 0.4108 | 0.9301 |
88
+ | 0.4348 | 0.01 | 48000 | 0.4138 | 0.9309 |
89
+ | 0.3787 | 0.01 | 50000 | 0.4066 | 0.9324 |
90
+ | 0.4172 | 0.01 | 52000 | 0.4812 | 0.9206 |
91
+ | 0.3897 | 0.02 | 54000 | 0.4013 | 0.9325 |
92
+ | 0.3787 | 0.02 | 56000 | 0.3837 | 0.9344 |
93
+ | 0.4253 | 0.02 | 58000 | 0.3925 | 0.9347 |
94
+ | 0.3959 | 0.02 | 60000 | 0.3907 | 0.9353 |
95
+ | 0.4402 | 0.02 | 62000 | 0.3708 | 0.9341 |
96
+ | 0.4115 | 0.02 | 64000 | 0.3477 | 0.9361 |
97
+ | 0.3876 | 0.02 | 66000 | 0.3634 | 0.9373 |
98
+ | 0.4286 | 0.02 | 68000 | 0.3778 | 0.9378 |
99
+ | 0.422 | 0.02 | 70000 | 0.3540 | 0.9361 |
100
+ | 0.3732 | 0.02 | 72000 | 0.3853 | 0.9378 |
101
+ | 0.3641 | 0.02 | 74000 | 0.3951 | 0.9386 |
102
+ | 0.3701 | 0.02 | 76000 | 0.3582 | 0.9388 |
103
+ | 0.4498 | 0.02 | 78000 | 0.3268 | 0.9375 |
104
+ | 0.3587 | 0.02 | 80000 | 0.3825 | 0.9401 |
105
+ | 0.4474 | 0.02 | 82000 | 0.3155 | 0.9391 |
106
+ | 0.3598 | 0.02 | 84000 | 0.3666 | 0.9388 |
107
+ | 0.389 | 0.02 | 86000 | 0.3745 | 0.9377 |
108
+ | 0.3625 | 0.02 | 88000 | 0.3776 | 0.9387 |
109
+ | 0.3511 | 0.03 | 90000 | 0.4275 | 0.9336 |
110
+ | 0.3428 | 0.03 | 92000 | 0.4301 | 0.9336 |
111
+ | 0.4042 | 0.03 | 94000 | 0.3547 | 0.9359 |
112
+ | 0.3583 | 0.03 | 96000 | 0.3763 | 0.9396 |
113
+ | 0.3887 | 0.03 | 98000 | 0.3213 | 0.9412 |
114
+ | 0.3915 | 0.03 | 100000 | 0.3557 | 0.9409 |
115
+ | 0.3378 | 0.03 | 102000 | 0.3627 | 0.9418 |
116
+ | 0.349 | 0.03 | 104000 | 0.3614 | 0.9402 |
117
+ | 0.3596 | 0.03 | 106000 | 0.3834 | 0.9381 |
118
+ | 0.3519 | 0.03 | 108000 | 0.3560 | 0.9421 |
119
+ | 0.3598 | 0.03 | 110000 | 0.3485 | 0.9419 |
120
+ | 0.3642 | 0.03 | 112000 | 0.3754 | 0.9395 |
121
+ | 0.3477 | 0.03 | 114000 | 0.3634 | 0.9426 |
122
+ | 0.4202 | 0.03 | 116000 | 0.3071 | 0.9427 |
123
+ | 0.3656 | 0.03 | 118000 | 0.3155 | 0.9441 |
124
+ | 0.3709 | 0.03 | 120000 | 0.2923 | 0.9433 |
125
+ | 0.374 | 0.03 | 122000 | 0.3272 | 0.9441 |
126
+ | 0.3142 | 0.03 | 124000 | 0.3348 | 0.9444 |
127
+ | 0.3452 | 0.04 | 126000 | 0.3603 | 0.9436 |
128
+ | 0.3365 | 0.04 | 128000 | 0.3339 | 0.9434 |
129
+ | 0.3353 | 0.04 | 130000 | 0.3471 | 0.9450 |
130
+ | 0.343 | 0.04 | 132000 | 0.3508 | 0.9418 |
131
+ | 0.3174 | 0.04 | 134000 | 0.3753 | 0.9436 |
132
+ | 0.3009 | 0.04 | 136000 | 0.3687 | 0.9422 |
133
+ | 0.3785 | 0.04 | 138000 | 0.3818 | 0.9396 |
134
+ | 0.3199 | 0.04 | 140000 | 0.3291 | 0.9438 |
135
+ | 0.4049 | 0.04 | 142000 | 0.3372 | 0.9454 |
136
+ | 0.3435 | 0.04 | 144000 | 0.3315 | 0.9459 |
137
+ | 0.3814 | 0.04 | 146000 | 0.3462 | 0.9401 |
138
+ | 0.359 | 0.04 | 148000 | 0.3981 | 0.9361 |
139
+ | 0.3552 | 0.04 | 150000 | 0.3226 | 0.9469 |
140
+ | 0.345 | 0.04 | 152000 | 0.3731 | 0.9384 |
141
+ | 0.3228 | 0.04 | 154000 | 0.2956 | 0.9471 |
142
+ | 0.3637 | 0.04 | 156000 | 0.2869 | 0.9477 |
143
+ | 0.349 | 0.04 | 158000 | 0.3331 | 0.9430 |
144
+ | 0.3374 | 0.04 | 160000 | 0.4159 | 0.9340 |
145
+ | 0.3718 | 0.05 | 162000 | 0.3241 | 0.9459 |
146
+ | 0.315 | 0.05 | 164000 | 0.3544 | 0.9391 |
147
+ | 0.3215 | 0.05 | 166000 | 0.3311 | 0.9451 |
148
+ | 0.3464 | 0.05 | 168000 | 0.3682 | 0.9453 |
149
+ | 0.3495 | 0.05 | 170000 | 0.3193 | 0.9469 |
150
+ | 0.305 | 0.05 | 172000 | 0.4132 | 0.9389 |
151
+ | 0.3479 | 0.05 | 174000 | 0.3465 | 0.947 |
152
+ | 0.3537 | 0.05 | 176000 | 0.3277 | 0.9449 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.10.2
158
+ - Pytorch 1.7.1
159
+ - Datasets 1.12.1
160
+ - 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 sha256:037b49d4da34f299f74533c074a9d31f444454ed561d8f58b689eedef37c7264
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 sha256:963f327b156517d39125ea1e010d1dd247108f6f16a2555726f1cceb7a992532
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff