Commit
•
b175525
1
Parent(s):
98ccc08
Training in progress epoch 0
Browse files- README.md +8 -9
- config.json +15 -19
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +2 -6
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
model-index:
|
@@ -11,12 +12,12 @@ probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# nathanReitinger/scotusPRED
|
13 |
|
14 |
-
This model is a fine-tuned version of [
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Train Loss: 0.
|
17 |
-
- Validation Loss: 0.
|
18 |
-
- Train Accuracy: 0.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,16 +36,14 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
44 |
|:----------:|:---------------:|:--------------:|:-----:|
|
45 |
-
| 0.
|
46 |
-
| 0.6507 | 0.6112 | 0.7143 | 1 |
|
47 |
-
| 0.6494 | 0.6029 | 0.7143 | 2 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
|
|
12 |
|
13 |
# nathanReitinger/scotusPRED
|
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: 0.6433
|
18 |
+
- Validation Loss: 0.6278
|
19 |
+
- Train Accuracy: 0.6829
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 480, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
45 |
|:----------:|:---------------:|:--------------:|:-----:|
|
46 |
+
| 0.6433 | 0.6278 | 0.6829 | 0 |
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,35 +1,31 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size": 1024,
|
13 |
"id2label": {
|
14 |
"0": "Reversing",
|
15 |
"1": "Affirming"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
-
"intermediate_size": 4096,
|
19 |
"label2id": {
|
20 |
"Affirming": 1,
|
21 |
"Reversing": 0
|
22 |
},
|
23 |
-
"layer_norm_eps": 1e-12,
|
24 |
"max_position_embeddings": 512,
|
25 |
-
"model_type": "
|
26 |
-
"
|
27 |
-
"
|
28 |
"pad_token_id": 0,
|
29 |
-
"
|
30 |
-
"
|
|
|
|
|
31 |
"transformers_version": "4.30.2",
|
32 |
-
"
|
33 |
-
"use_cache": true,
|
34 |
-
"vocab_size": 32000
|
35 |
}
|
|
|
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": "Reversing",
|
13 |
"1": "Affirming"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
|
|
16 |
"label2id": {
|
17 |
"Affirming": 1,
|
18 |
"Reversing": 0
|
19 |
},
|
|
|
20 |
"max_position_embeddings": 512,
|
21 |
+
"model_type": "distilbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 6,
|
24 |
"pad_token_id": 0,
|
25 |
+
"qa_dropout": 0.1,
|
26 |
+
"seq_classif_dropout": 0.2,
|
27 |
+
"sinusoidal_pos_embds": false,
|
28 |
+
"tie_weights_": true,
|
29 |
"transformers_version": "4.30.2",
|
30 |
+
"vocab_size": 30522
|
|
|
|
|
31 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01360c639c018133dfafb77a2c3b52460ea31260453473aff6f2838f62e6c944
|
3 |
+
size 267951808
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,17 +1,13 @@
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
-
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
6 |
-
"handle_chinese_chars": true,
|
7 |
"mask_token": "[MASK]",
|
8 |
-
"model_max_len": 512,
|
9 |
"model_max_length": 512,
|
10 |
-
"never_split": null,
|
11 |
"pad_token": "[PAD]",
|
12 |
"sep_token": "[SEP]",
|
13 |
-
"strip_accents":
|
14 |
"tokenize_chinese_chars": true,
|
15 |
-
"tokenizer_class": "
|
16 |
"unk_token": "[UNK]"
|
17 |
}
|
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
|
|
4 |
"do_lower_case": true,
|
|
|
5 |
"mask_token": "[MASK]",
|
|
|
6 |
"model_max_length": 512,
|
|
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
"unk_token": "[UNK]"
|
13 |
}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|