Upload TFElectraForSequenceClassification
Browse files- README.md +57 -0
- config.json +37 -0
- tf_model.h5 +3 -0
README.md
CHANGED
@@ -1,3 +1,60 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: google/electra-small-discriminator
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: textming_proj01_electra
|
8 |
+
results: []
|
9 |
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# textming_proj01_electra
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.4494
|
19 |
+
- Train Accuracy: 0.7976
|
20 |
+
- Validation Loss: 0.5521
|
21 |
+
- Validation Accuracy: 0.7456
|
22 |
+
- Epoch: 4
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- 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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
42 |
+
- training_precision: float32
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
47 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
48 |
+
| 0.5951 | 0.6936 | 0.5818 | 0.6966 | 0 |
|
49 |
+
| 0.5484 | 0.7291 | 0.5681 | 0.7054 | 1 |
|
50 |
+
| 0.5119 | 0.7543 | 0.5284 | 0.7423 | 2 |
|
51 |
+
| 0.4769 | 0.7800 | 0.5306 | 0.7432 | 3 |
|
52 |
+
| 0.4494 | 0.7976 | 0.5521 | 0.7456 | 4 |
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.39.3
|
58 |
+
- TensorFlow 2.15.0
|
59 |
+
- Datasets 2.18.0
|
60 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/electra-small-discriminator",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "FALSE",
|
14 |
+
"1": "TRUE"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 1024,
|
18 |
+
"label2id": {
|
19 |
+
"FALSE": 0,
|
20 |
+
"TRUE": 1
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "electra",
|
25 |
+
"num_attention_heads": 4,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"summary_activation": "gelu",
|
30 |
+
"summary_last_dropout": 0.1,
|
31 |
+
"summary_type": "first",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"transformers_version": "4.39.3",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 30522
|
37 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99159452dca3e637a135ad21b383a9668f959bc4cf37b6242040950e72e75e93
|
3 |
+
size 54486784
|