Commit ·
04f839c
1
Parent(s): 478c577
Upload TFDistilBertForSequenceClassification
Browse files- README.md +73 -0
- config.json +30 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Regression_bert_aug_CustomLoss_2
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# Regression_bert_aug_CustomLoss_2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.2338
|
| 18 |
+
- Train Mae: 0.5263
|
| 19 |
+
- Train Mse: 0.4258
|
| 20 |
+
- Train R2-score: 0.7899
|
| 21 |
+
- Validation Loss: 0.2340
|
| 22 |
+
- Validation Mae: 0.5490
|
| 23 |
+
- Validation Mse: 0.4329
|
| 24 |
+
- Validation R2-score: 0.7254
|
| 25 |
+
- Epoch: 14
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
| 45 |
+
- training_precision: float32
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
|
| 50 |
+
|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
|
| 51 |
+
| 0.2004 | 0.4982 | 0.3687 | 0.6907 | 0.1488 | 0.4239 | 0.3023 | 0.7428 | 0 |
|
| 52 |
+
| 0.1118 | 0.4054 | 0.2460 | 0.7552 | 0.0783 | 0.3502 | 0.1873 | 0.8501 | 1 |
|
| 53 |
+
| 0.0531 | 0.3256 | 0.1543 | 0.8049 | 0.0489 | 0.3257 | 0.1489 | 0.8412 | 2 |
|
| 54 |
+
| 0.0342 | 0.2826 | 0.1151 | 0.7986 | 0.0328 | 0.2697 | 0.1215 | 0.9246 | 3 |
|
| 55 |
+
| 0.0266 | 0.2587 | 0.0962 | 0.8802 | 0.0713 | 0.2884 | 0.1297 | 0.8729 | 4 |
|
| 56 |
+
| 0.0543 | 0.3022 | 0.1388 | 0.7724 | 0.0609 | 0.3238 | 0.1524 | 0.7723 | 5 |
|
| 57 |
+
| 0.0380 | 0.2756 | 0.1114 | 0.8822 | 0.0421 | 0.1984 | 0.0700 | 0.9070 | 6 |
|
| 58 |
+
| 0.0593 | 0.3134 | 0.1537 | 0.8764 | 0.2335 | 0.5183 | 0.4636 | 0.7816 | 7 |
|
| 59 |
+
| 0.2330 | 0.5234 | 0.4182 | -1.5020 | 0.2656 | 0.5726 | 0.3948 | 0.5533 | 8 |
|
| 60 |
+
| 0.2359 | 0.5149 | 0.4195 | 0.7932 | 0.2347 | 0.5263 | 0.4461 | 0.7502 | 9 |
|
| 61 |
+
| 0.2341 | 0.5204 | 0.4268 | 0.8100 | 0.2341 | 0.5509 | 0.4307 | 0.7220 | 10 |
|
| 62 |
+
| 0.2335 | 0.5250 | 0.4235 | 0.8053 | 0.2328 | 0.5433 | 0.4334 | 0.7322 | 11 |
|
| 63 |
+
| 0.2319 | 0.5217 | 0.4244 | 0.7825 | 0.2352 | 0.5549 | 0.4296 | 0.7158 | 12 |
|
| 64 |
+
| 0.2323 | 0.5243 | 0.4234 | 0.7877 | 0.2346 | 0.5536 | 0.4286 | 0.7170 | 13 |
|
| 65 |
+
| 0.2338 | 0.5263 | 0.4258 | 0.7899 | 0.2340 | 0.5490 | 0.4329 | 0.7254 | 14 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.28.1
|
| 71 |
+
- TensorFlow 2.12.0
|
| 72 |
+
- Datasets 2.12.0
|
| 73 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"LABEL_0": 0
|
| 17 |
+
},
|
| 18 |
+
"max_position_embeddings": 512,
|
| 19 |
+
"model_type": "distilbert",
|
| 20 |
+
"n_heads": 12,
|
| 21 |
+
"n_layers": 6,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"problem_type": "regression",
|
| 24 |
+
"qa_dropout": 0.1,
|
| 25 |
+
"seq_classif_dropout": 0.2,
|
| 26 |
+
"sinusoidal_pos_embds": false,
|
| 27 |
+
"tie_weights_": true,
|
| 28 |
+
"transformers_version": "4.28.1",
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0cd2d27697a0e0ef32df94ee69f221a534c3b60c288ee1a0be4ab867886b2e
|
| 3 |
+
size 267948736
|