End of training
Browse files- README.md +79 -0
- config.json +39 -0
- model.safetensors +3 -0
- runs/Nov03_07-43-26_dcc4d17321e8/events.out.tfevents.1730619815.dcc4d17321e8.30.0 +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 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google-bert/bert-base-uncased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: bert-wellness-classifier
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# bert-wellness-classifier
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7555
|
| 22 |
+
- Accuracy: 0.714
|
| 23 |
+
- Auc: 0.894
|
| 24 |
+
- Precision Class 0: 0.771
|
| 25 |
+
- Precision Class 1: 0.789
|
| 26 |
+
- Precision Class 2: 0.78
|
| 27 |
+
- Precision Class 3: 0.653
|
| 28 |
+
- Recall Class 0: 0.698
|
| 29 |
+
- Recall Class 1: 0.556
|
| 30 |
+
- Recall Class 2: 0.619
|
| 31 |
+
- Recall Class 3: 0.827
|
| 32 |
+
|
| 33 |
+
## Model description
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Intended uses & limitations
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training and evaluation data
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training procedure
|
| 46 |
+
|
| 47 |
+
### Training hyperparameters
|
| 48 |
+
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- learning_rate: 0.0002
|
| 51 |
+
- train_batch_size: 8
|
| 52 |
+
- eval_batch_size: 8
|
| 53 |
+
- seed: 42
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- num_epochs: 10
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Precision Class 0 | Precision Class 1 | Precision Class 2 | Precision Class 3 | Recall Class 0 | Recall Class 1 | Recall Class 2 | Recall Class 3 |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:--------------:|:--------------:|:--------------:|:--------------:|
|
| 62 |
+
| 1.1543 | 1.0 | 140 | 1.0293 | 0.568 | 0.835 | 0.767 | 1.0 | 0.447 | 0.587 | 0.434 | 0.296 | 0.667 | 0.653 |
|
| 63 |
+
| 0.9519 | 2.0 | 280 | 0.9149 | 0.585 | 0.86 | 0.738 | 1.0 | 0.613 | 0.528 | 0.585 | 0.185 | 0.302 | 0.878 |
|
| 64 |
+
| 0.8294 | 3.0 | 420 | 0.7950 | 0.676 | 0.88 | 0.74 | 0.824 | 0.606 | 0.67 | 0.698 | 0.519 | 0.683 | 0.704 |
|
| 65 |
+
| 0.7821 | 4.0 | 560 | 0.8809 | 0.598 | 0.882 | 0.87 | 0.727 | 0.604 | 0.545 | 0.377 | 0.296 | 0.508 | 0.857 |
|
| 66 |
+
| 0.7349 | 5.0 | 700 | 0.7576 | 0.701 | 0.892 | 0.809 | 0.789 | 0.714 | 0.639 | 0.717 | 0.556 | 0.635 | 0.776 |
|
| 67 |
+
| 0.7173 | 6.0 | 840 | 0.7700 | 0.689 | 0.89 | 0.76 | 0.824 | 0.744 | 0.626 | 0.717 | 0.519 | 0.508 | 0.837 |
|
| 68 |
+
| 0.7048 | 7.0 | 980 | 0.7977 | 0.68 | 0.892 | 0.822 | 0.842 | 0.793 | 0.595 | 0.698 | 0.593 | 0.365 | 0.898 |
|
| 69 |
+
| 0.6776 | 8.0 | 1120 | 0.7654 | 0.705 | 0.892 | 0.745 | 0.8 | 0.778 | 0.648 | 0.717 | 0.593 | 0.556 | 0.827 |
|
| 70 |
+
| 0.6649 | 9.0 | 1260 | 0.7612 | 0.718 | 0.895 | 0.837 | 0.789 | 0.78 | 0.643 | 0.679 | 0.556 | 0.619 | 0.847 |
|
| 71 |
+
| 0.676 | 10.0 | 1400 | 0.7555 | 0.714 | 0.894 | 0.771 | 0.789 | 0.78 | 0.653 | 0.698 | 0.556 | 0.619 | 0.827 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.45.1
|
| 77 |
+
- Pytorch 2.4.0+cpu
|
| 78 |
+
- Datasets 3.0.1
|
| 79 |
+
- Tokenizers 0.20.0
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/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": "PA",
|
| 14 |
+
"1": "IVA",
|
| 15 |
+
"2": "SA",
|
| 16 |
+
"3": "SEA"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"IVA": 1,
|
| 22 |
+
"PA": 0,
|
| 23 |
+
"SA": 2,
|
| 24 |
+
"SEA": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.45.1",
|
| 36 |
+
"type_vocab_size": 2,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30522
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cf1b12ac4188061a1b95939442a7c108f381568361d53d7ef5a043d7dca0006
|
| 3 |
+
size 437964800
|
runs/Nov03_07-43-26_dcc4d17321e8/events.out.tfevents.1730619815.dcc4d17321e8.30.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc1152e528f956542ae9875d8a8e5bd83c3f6e8fd92d8e7a66e8910947778c62
|
| 3 |
+
size 16054
|
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": false,
|
| 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 sha256:9a70b78afccdcdf8177875748299d08ca590587387f997ad402e337418bc7479
|
| 3 |
+
size 5240
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|