Commit
•
488cd0a
1
Parent(s):
eccbf9b
Training in progress epoch 0
Browse files- README.md +7 -9
- config.json +9 -9
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +3 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
license: cc-by-sa-4.0
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
@@ -12,12 +11,12 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# nathanReitinger/scotusPRED
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
- Validation Loss: 0.
|
19 |
-
- Train Accuracy: 0.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,15 +35,14 @@ More information needed
|
|
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':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
45 |
|:----------:|:---------------:|:--------------:|:-----:|
|
46 |
-
| 0.
|
47 |
-
| 0.6374 | 0.6322 | 0.6689 | 1 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
model-index:
|
|
|
11 |
|
12 |
# nathanReitinger/scotusPRED
|
13 |
|
14 |
+
This model is a fine-tuned version of [pile-of-law/legalbert-large-1.7M-2](https://huggingface.co/pile-of-law/legalbert-large-1.7M-2) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.7225
|
17 |
+
- Validation Loss: 0.6917
|
18 |
+
- Train Accuracy: 0.5191
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
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': 72, '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}
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
44 |
|:----------:|:---------------:|:--------------:|:-----:|
|
45 |
+
| 0.7225 | 0.6917 | 0.5191 | 0 |
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
-
"
|
|
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "Reversing",
|
15 |
"1": "Affirming"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
-
"intermediate_size":
|
19 |
"label2id": {
|
20 |
"Affirming": 1,
|
21 |
"Reversing": 0
|
@@ -23,13 +23,13 @@
|
|
23 |
"layer_norm_eps": 1e-12,
|
24 |
"max_position_embeddings": 512,
|
25 |
"model_type": "bert",
|
26 |
-
"num_attention_heads":
|
27 |
-
"num_hidden_layers":
|
28 |
-
"output_past": true,
|
29 |
"pad_token_id": 0,
|
30 |
"position_embedding_type": "absolute",
|
|
|
31 |
"transformers_version": "4.30.2",
|
32 |
"type_vocab_size": 2,
|
33 |
"use_cache": true,
|
34 |
-
"vocab_size":
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "pile-of-law/legalbert-large-1.7M-2",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
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
|
|
|
23 |
"layer_norm_eps": 1e-12,
|
24 |
"max_position_embeddings": 512,
|
25 |
"model_type": "bert",
|
26 |
+
"num_attention_heads": 16,
|
27 |
+
"num_hidden_layers": 24,
|
|
|
28 |
"pad_token_id": 0,
|
29 |
"position_embedding_type": "absolute",
|
30 |
+
"tokenizer_class": "BertTokenizer",
|
31 |
"transformers_version": "4.30.2",
|
32 |
"type_vocab_size": 2,
|
33 |
"use_cache": true,
|
34 |
+
"vocab_size": 32000
|
35 |
}
|
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 sha256:9581af378fea44333a734ad62a18f2c610c22f01374d017b382791e3587f815e
|
3 |
+
size 1347181616
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -3,12 +3,14 @@
|
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
|
|
6 |
"mask_token": "[MASK]",
|
|
|
7 |
"model_max_length": 512,
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
-
"strip_accents":
|
12 |
"tokenize_chinese_chars": true,
|
13 |
"tokenizer_class": "BertTokenizer",
|
14 |
"unk_token": "[UNK]"
|
|
|
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": true,
|
14 |
"tokenize_chinese_chars": true,
|
15 |
"tokenizer_class": "BertTokenizer",
|
16 |
"unk_token": "[UNK]"
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|