End of training
Browse files- README.md +67 -0
- config.json +63 -0
- model.safetensors +3 -0
- runs/Apr07_16-02-11_a7f12f1071f6/events.out.tfevents.1712505750.a7f12f1071f6.34.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
model-index:
|
9 |
+
- name: legal-bert-base-uncased-5-epochs-fine-tune
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# legal-bert-base-uncased-5-epochs-fine-tune
|
17 |
+
|
18 |
+
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.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8581
|
21 |
+
- Accuracy: 1
|
22 |
+
- F1 Micro: 1
|
23 |
+
- F1 Macro: 1
|
24 |
+
- F1 Weighted: 1
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 5
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | F1 Macro | F1 Weighted |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:-----------:|
|
55 |
+
| 1.348 | 1.0 | 643 | 0.6934 | 1 | 1 | 1 | 1 |
|
56 |
+
| 0.6471 | 2.0 | 1286 | 0.6506 | 1 | 1 | 1 | 1 |
|
57 |
+
| 0.4944 | 3.0 | 1929 | 0.7049 | 1 | 1 | 1 | 1 |
|
58 |
+
| 0.2113 | 4.0 | 2572 | 0.8336 | 1 | 1 | 1 | 1 |
|
59 |
+
| 0.1352 | 5.0 | 3215 | 0.8581 | 1 | 1 | 1 | 1 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.38.2
|
65 |
+
- Pytorch 2.1.2
|
66 |
+
- Datasets 2.1.0
|
67 |
+
- 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": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_10": 10,
|
36 |
+
"LABEL_11": 11,
|
37 |
+
"LABEL_12": 12,
|
38 |
+
"LABEL_13": 13,
|
39 |
+
"LABEL_14": 14,
|
40 |
+
"LABEL_2": 2,
|
41 |
+
"LABEL_3": 3,
|
42 |
+
"LABEL_4": 4,
|
43 |
+
"LABEL_5": 5,
|
44 |
+
"LABEL_6": 6,
|
45 |
+
"LABEL_7": 7,
|
46 |
+
"LABEL_8": 8,
|
47 |
+
"LABEL_9": 9
|
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 sha256:4b49ed52b976506862b1295119ed21831377402bfc090c43736ca002576391bc
|
3 |
+
size 437998636
|
runs/Apr07_16-02-11_a7f12f1071f6/events.out.tfevents.1712505750.a7f12f1071f6.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92da61d04e137cb38a484b72c95278b447491ea9c6bf82c7c29b752ebf00cb80
|
3 |
+
size 9351
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05aeaa1951f1a973e1d1ab65cc86b3d7a34ad051905d26b3774a667bf6af1ddc
|
3 |
+
size 4984
|