Hugging Face's logo

lekhnathrijal
/
bert-question-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
lekhnathrijal commited on
Commit
7ab4e17
·
verified ·
1 Parent(s): 5fa4b20

ai-research-lab/bert-question-classifier

Browse files
Files changed (4) hide show
  1. README.md +26 -29
  2. config.json +18 -0
  3. model.safetensors +1 -1
  4. tokenizer.json +10 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.9776
25
- - Accuracy: 0.9688
26
- - Recall: 0.8356
27
- - Precision: 0.8233
28
- - F1: 0.8294
29
 
30
  ## Model description
31
 
@@ -45,8 +45,8 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
- - train_batch_size: 4
49
- - eval_batch_size: 4
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
@@ -57,28 +57,25 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
59
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
- | No log | 0.0959 | 100 | 5.2538 | 0.8954 | 0.4113 | 0.4226 | 0.4169 |
61
- | No log | 0.1918 | 200 | 4.8785 | 0.9119 | 0.4529 | 0.5177 | 0.4831 |
62
- | No log | 0.2876 | 300 | 4.5415 | 0.9206 | 0.5307 | 0.5675 | 0.5485 |
63
- | No log | 0.3835 | 400 | 4.2158 | 0.9319 | 0.6238 | 0.6261 | 0.6249 |
64
- | 4.7973 | 0.4794 | 500 | 3.9246 | 0.9365 | 0.6445 | 0.6528 | 0.6487 |
65
- | 4.7973 | 0.5753 | 600 | 3.7378 | 0.9393 | 0.6749 | 0.6630 | 0.6689 |
66
- | 4.7973 | 0.6711 | 700 | 3.5841 | 0.9420 | 0.6849 | 0.6794 | 0.6821 |
67
- | 4.7973 | 0.7670 | 800 | 3.3128 | 0.9471 | 0.7255 | 0.7024 | 0.7138 |
68
- | 4.7973 | 0.8629 | 900 | 3.1501 | 0.9476 | 0.7261 | 0.7058 | 0.7158 |
69
- | 3.4614 | 0.9588 | 1000 | 2.9866 | 0.9498 | 0.7354 | 0.7189 | 0.7271 |
70
- | 3.4614 | 1.0547 | 1100 | 2.8197 | 0.9532 | 0.7509 | 0.7386 | 0.7447 |
71
- | 3.4614 | 1.1505 | 1200 | 2.6852 | 0.9544 | 0.7559 | 0.7457 | 0.7508 |
72
- | 3.4614 | 1.2464 | 1300 | 2.5284 | 0.9585 | 0.7776 | 0.7685 | 0.7730 |
73
- | 3.4614 | 1.3423 | 1400 | 2.4018 | 0.9612 | 0.7981 | 0.7802 | 0.7890 |
74
- | 2.6456 | 1.4382 | 1500 | 2.3255 | 0.9620 | 0.7996 | 0.7860 | 0.7927 |
75
- | 2.6456 | 1.5340 | 1600 | 2.2501 | 0.9630 | 0.8089 | 0.7891 | 0.7989 |
76
- | 2.6456 | 1.6299 | 1700 | 2.1575 | 0.9655 | 0.8229 | 0.8022 | 0.8124 |
77
- | 2.6456 | 1.7258 | 1800 | 2.0949 | 0.9658 | 0.8158 | 0.8095 | 0.8126 |
78
- | 2.6456 | 1.8217 | 1900 | 2.0348 | 0.9666 | 0.8282 | 0.8086 | 0.8183 |
79
- | 2.1476 | 1.9175 | 2000 | 1.9776 | 0.9688 | 0.8356 | 0.8233 | 0.8294 |
80
- | 2.1476 | 2.0134 | 2100 | 1.9170 | 0.9685 | 0.8390 | 0.8187 | 0.8287 |
81
- | 2.1476 | 2.1093 | 2200 | 1.8676 | 0.9685 | 0.8347 | 0.8214 | 0.828 |
82
 
83
 
84
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.7626
25
+ - Accuracy: 0.9711
26
+ - Recall: 0.8457
27
+ - Precision: 0.8328
28
+ - F1: 0.8392
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
59
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | No log | 0.1770 | 100 | 4.9936 | 0.9059 | 0.4617 | 0.4711 | 0.4664 |
61
+ | No log | 0.3540 | 200 | 4.3759 | 0.9286 | 0.5827 | 0.6022 | 0.5923 |
62
+ | No log | 0.5310 | 300 | 3.9061 | 0.9389 | 0.6590 | 0.6561 | 0.6575 |
63
+ | No log | 0.7080 | 400 | 3.5239 | 0.9414 | 0.6964 | 0.6625 | 0.6790 |
64
+ | 4.2985 | 0.8850 | 500 | 3.2182 | 0.9452 | 0.7154 | 0.6836 | 0.6991 |
65
+ | 4.2985 | 1.0619 | 600 | 2.9700 | 0.9486 | 0.7274 | 0.7053 | 0.7162 |
66
+ | 4.2985 | 1.2389 | 700 | 2.7592 | 0.9535 | 0.7545 | 0.7317 | 0.7429 |
67
+ | 4.2985 | 1.4159 | 800 | 2.5722 | 0.9568 | 0.7802 | 0.7466 | 0.7631 |
68
+ | 4.2985 | 1.5929 | 900 | 2.3973 | 0.9609 | 0.8001 | 0.7695 | 0.7845 |
69
+ | 2.7724 | 1.7699 | 1000 | 2.2682 | 0.9642 | 0.8089 | 0.7934 | 0.8010 |
70
+ | 2.7724 | 1.9469 | 1100 | 2.1763 | 0.9657 | 0.8156 | 0.8025 | 0.8090 |
71
+ | 2.7724 | 2.1239 | 1200 | 2.0628 | 0.9665 | 0.8147 | 0.8102 | 0.8125 |
72
+ | 2.7724 | 2.3009 | 1300 | 1.9961 | 0.9675 | 0.8197 | 0.8166 | 0.8181 |
73
+ | 2.7724 | 2.4779 | 1400 | 1.9156 | 0.9696 | 0.8361 | 0.8247 | 0.8304 |
74
+ | 2.0623 | 2.6549 | 1500 | 1.8615 | 0.9693 | 0.8337 | 0.8239 | 0.8288 |
75
+ | 2.0623 | 2.8319 | 1600 | 1.8050 | 0.9700 | 0.8422 | 0.8251 | 0.8336 |
76
+ | 2.0623 | 3.0088 | 1700 | 1.7626 | 0.9711 | 0.8457 | 0.8328 | 0.8392 |
77
+ | 2.0623 | 3.1858 | 1800 | 1.7303 | 0.9704 | 0.8404 | 0.8293 | 0.8348 |
78
+ | 2.0623 | 3.3628 | 1900 | 1.6939 | 0.9712 | 0.8431 | 0.8353 | 0.8392 |
 
 
 
79
 
80
 
81
  ### Framework versions
config.json CHANGED
@@ -5,6 +5,24 @@
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,
 
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "custom_pipelines": {
9
+ "question-classifier": {
10
+ "default": {
11
+ "model": {
12
+ "pt": [
13
+ "ai-research-lab/bert-question-classifier",
14
+ "main"
15
+ ]
16
+ }
17
+ },
18
+ "impl": "classifier_pipeline.MultiTaskClassifierPipeline",
19
+ "pt": [
20
+ "AutoModelForSequenceClassification"
21
+ ],
22
+ "tf": [],
23
+ "type": "text"
24
+ }
25
+ },
26
  "gradient_checkpointing": false,
27
  "hidden_act": "gelu",
28
  "hidden_dropout_prob": 0.1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e29839b8b3249eb57b472fa6f948d3857ce5753eb6f31a9d4432ae255ab7b33d
3
  size 438057080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6482383b7b8122357711a8e55f3c1d7917dc1db8a8982e862ff5f971c45e8831
3
  size 438057080
tokenizer.json CHANGED
@@ -6,7 +6,16 @@
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
- "padding": null,
 
 
 
 
 
 
 
 
 
10
  "added_tokens": [
11
  {
12
  "id": 0,
 
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,