Training in progress epoch 0
Browse files
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: negfir/distilbert-base-uncased-finetuned-cola
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# negfir/distilbert-base-uncased-finetuned-cola
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.6171
|
17 |
+
- Validation Loss: 0.6188
|
18 |
+
- Train Matthews Correlation: 0.0
|
19 |
+
- Epoch: 0
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2670, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
39 |
+
- training_precision: float32
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
|
44 |
+
|:----------:|:---------------:|:--------------------------:|:-----:|
|
45 |
+
| 0.6171 | 0.6188 | 0.0 | 0 |
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.17.0
|
51 |
+
- TensorFlow 2.8.0
|
52 |
+
- Datasets 2.0.0
|
53 |
+
- Tokenizers 0.11.6
|
config.json
CHANGED
@@ -1,25 +1,23 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
-
"model_type": "
|
14 |
-
"
|
15 |
-
"
|
16 |
"pad_token_id": 0,
|
17 |
-
"
|
18 |
-
"qa_dropout": 0.1,
|
19 |
-
"seq_classif_dropout": 0.2,
|
20 |
-
"sinusoidal_pos_embds": false,
|
21 |
-
"tie_weights_": true,
|
22 |
-
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.17.0",
|
|
|
|
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 128,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 512,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 2,
|
16 |
+
"num_hidden_layers": 2,
|
17 |
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
19 |
"transformers_version": "4.17.0",
|
20 |
+
"type_vocab_size": 2,
|
21 |
+
"use_cache": true,
|
22 |
"vocab_size": 30522
|
23 |
}
|
logs/train/events.out.tfevents.1648059800.8e925dbfab71.74.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b42815c3740efe96338afcc16135a550b4c93a991c15d90553503dd4a0825194
|
3 |
+
size 559364
|
logs/validation/events.out.tfevents.1648059822.8e925dbfab71.74.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3c514c43b2278ee6c911643186a8fa2323ad009c2159a69047eb0143489fa72
|
3 |
+
size 194
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5127be69ac8f86587182289194fba26127fd013ac916eeed8ac2a8b5ffd6e29c
|
3 |
+
size 17612160
|