End of training
Browse files- README.md +84 -0
- config.json +63 -0
- model.safetensors +3 -0
- runs/Apr12_17-44-11_b0fca03b936f/events.out.tfevents.1712943869.b0fca03b936f.34.3 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
base_model: nlpaueb/legal-bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: legal-bert-base-uncased
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# legal-bert-base-uncased
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 2.2259
|
23 |
+
- Accuracy: 0.2455
|
24 |
+
- Precision: 0.0603
|
25 |
+
- Recall: 0.2455
|
26 |
+
- Precision Macro: 0.0164
|
27 |
+
- Recall Macro: 0.0667
|
28 |
+
- Macro Fpr: 0.0667
|
29 |
+
- Weighted Fpr: 0.1800
|
30 |
+
- Weighted Specificity: 0.7545
|
31 |
+
- Macro Specificity: 0.9333
|
32 |
+
- Weighted Sensitivity: 0.2455
|
33 |
+
- Macro Sensitivity: 0.0667
|
34 |
+
- F1 Micro: 0.2455
|
35 |
+
- F1 Macro: 0.0263
|
36 |
+
- F1 Weighted: 0.0968
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 10
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:|
|
67 |
+
| 2.2376 | 1.0 | 643 | 2.2455 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
68 |
+
| 2.2504 | 2.0 | 1286 | 2.2412 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
69 |
+
| 2.2292 | 3.0 | 1929 | 2.2300 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
70 |
+
| 2.218 | 4.0 | 2572 | 2.2316 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
71 |
+
| 2.2317 | 5.0 | 3215 | 2.2295 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
72 |
+
| 2.2355 | 6.0 | 3858 | 2.2310 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
73 |
+
| 2.2231 | 7.0 | 4501 | 2.2300 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
74 |
+
| 2.2212 | 8.0 | 5144 | 2.2291 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
75 |
+
| 2.2318 | 9.0 | 5787 | 2.2258 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
76 |
+
| 2.2128 | 10.0 | 6430 | 2.2259 | 0.2455 | 0.0603 | 0.2455 | 0.0164 | 0.0667 | 0.0667 | 0.1800 | 0.7545 | 0.9333 | 0.2455 | 0.0667 | 0.2455 | 0.0263 | 0.0968 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.38.2
|
82 |
+
- Pytorch 2.1.2
|
83 |
+
- Datasets 2.1.0
|
84 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nlpaueb/legal-bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Issue",
|
15 |
+
"1": "Court Discourse",
|
16 |
+
"2": "Conclusion",
|
17 |
+
"3": "Precedent Analysis",
|
18 |
+
"4": "Section Analysis",
|
19 |
+
"5": "Argument by Petitioner",
|
20 |
+
"6": "Fact",
|
21 |
+
"7": "Argument by Respondent",
|
22 |
+
"8": "Ratio",
|
23 |
+
"9": "Appellant",
|
24 |
+
"10": "Respondent",
|
25 |
+
"11": "Argument by Appellant",
|
26 |
+
"12": "Petitioner",
|
27 |
+
"13": "Judge",
|
28 |
+
"14": "Argument by Defendant"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"Appellant": 9,
|
34 |
+
"Argument by Appellant": 11,
|
35 |
+
"Argument by Defendant": 14,
|
36 |
+
"Argument by Petitioner": 5,
|
37 |
+
"Argument by Respondent": 7,
|
38 |
+
"Conclusion": 2,
|
39 |
+
"Court Discourse": 1,
|
40 |
+
"Fact": 6,
|
41 |
+
"Issue": 0,
|
42 |
+
"Judge": 13,
|
43 |
+
"Petitioner": 12,
|
44 |
+
"Precedent Analysis": 3,
|
45 |
+
"Ratio": 8,
|
46 |
+
"Respondent": 10,
|
47 |
+
"Section Analysis": 4
|
48 |
+
},
|
49 |
+
"layer_norm_eps": 1e-12,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "bert",
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"output_past": true,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "single_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.38.2",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 30522
|
63 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:326501b43ab8945fd50793a5a3edf0e653e9c5b6c8692e1f44af220c44cfee2d
|
3 |
+
size 437998636
|
runs/Apr12_17-44-11_b0fca03b936f/events.out.tfevents.1712943869.b0fca03b936f.34.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde0ce60557be4718dc04481b0fbc0fd62965d1eac5ef6907d6f7d9cc4c22c35
|
3 |
+
size 18907
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de0ea3c936537ac00d95c371761fd4e7826f69710670a94961dc1e9e089e756a
|
3 |
+
size 4920
|