Commit ·
80dec67
1
Parent(s): 2768e27
Upload TFDistilBertForSequenceClassification
Browse files- README.md +68 -0
- config.json +30 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Regression_bert_7
|
| 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_7
|
| 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: 0.1702
|
| 18 |
+
- Train Mae: 0.2696
|
| 19 |
+
- Train Mse: 0.1221
|
| 20 |
+
- Train R2-score: 0.7766
|
| 21 |
+
- Validation Loss: 0.3290
|
| 22 |
+
- Validation Mae: 0.2756
|
| 23 |
+
- Validation Mse: 0.1076
|
| 24 |
+
- Validation R2-score: 0.8214
|
| 25 |
+
- Epoch: 9
|
| 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 |
+
| 0.5303 | 0.3176 | 0.1540 | 0.7493 | 0.6752 | 0.3537 | 0.1857 | 0.6758 | 0 |
|
| 52 |
+
| 0.2316 | 0.2775 | 0.1261 | 0.7746 | 0.2451 | 0.3060 | 0.1466 | 0.7473 | 1 |
|
| 53 |
+
| 0.2780 | 0.2930 | 0.1373 | 0.8061 | 0.1807 | 0.2593 | 0.1127 | 0.8102 | 2 |
|
| 54 |
+
| 0.1776 | 0.2673 | 0.1177 | 0.6536 | 0.1407 | 0.2617 | 0.1181 | 0.7975 | 3 |
|
| 55 |
+
| 0.2248 | 0.2906 | 0.1349 | 0.7639 | 0.1896 | 0.2915 | 0.1364 | 0.7665 | 4 |
|
| 56 |
+
| 0.2295 | 0.2718 | 0.1196 | 0.7991 | 0.2038 | 0.2757 | 0.1248 | 0.7882 | 5 |
|
| 57 |
+
| 0.2443 | 0.2460 | 0.0975 | 0.7298 | 0.1509 | 0.2779 | 0.1301 | 0.7783 | 6 |
|
| 58 |
+
| 0.2538 | 0.2907 | 0.1343 | 0.7783 | 0.1930 | 0.2984 | 0.1426 | 0.7559 | 7 |
|
| 59 |
+
| 0.2067 | 0.2777 | 0.1281 | 0.7605 | 0.1537 | 0.2809 | 0.1318 | 0.7756 | 8 |
|
| 60 |
+
| 0.1702 | 0.2696 | 0.1221 | 0.7766 | 0.3290 | 0.2756 | 0.1076 | 0.8214 | 9 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.27.3
|
| 66 |
+
- TensorFlow 2.11.0
|
| 67 |
+
- Datasets 2.10.1
|
| 68 |
+
- Tokenizers 0.13.2
|
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": "4.27.3",
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:826ed147867acab9360580bd2cb96f7ad192257939867b5dfb0eaf46b1f00c0e
|
| 3 |
+
size 267948736
|