khalidrajan
commited on
Commit
•
9f20adc
1
Parent(s):
6b7e11d
End of training
Browse files- README.md +85 -0
- config.json +49 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: roberta-base
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# roberta-base
|
13 |
+
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.2676
|
17 |
+
- Law Precision: 0.8739
|
18 |
+
- Law Recall: 0.9065
|
19 |
+
- Law F1: 0.8899
|
20 |
+
- Law Number: 107
|
21 |
+
- Violated by Precision: 0.8254
|
22 |
+
- Violated by Recall: 0.7324
|
23 |
+
- Violated by F1: 0.7761
|
24 |
+
- Violated by Number: 71
|
25 |
+
- Violated on Precision: 0.5077
|
26 |
+
- Violated on Recall: 0.5156
|
27 |
+
- Violated on F1: 0.5116
|
28 |
+
- Violated on Number: 64
|
29 |
+
- Violation Precision: 0.6460
|
30 |
+
- Violation Recall: 0.6979
|
31 |
+
- Violation F1: 0.6710
|
32 |
+
- Violation Number: 374
|
33 |
+
- Overall Precision: 0.6890
|
34 |
+
- Overall Recall: 0.7192
|
35 |
+
- Overall F1: 0.7037
|
36 |
+
- Overall Accuracy: 0.9504
|
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: 2e-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 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- num_epochs: 10
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Law Precision | Law Recall | Law F1 | Law Number | Violated by Precision | Violated by Recall | Violated by F1 | Violated by Number | Violated on Precision | Violated on Recall | Violated on F1 | Violated on Number | Violation Precision | Violation Recall | Violation F1 | Violation Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------------:|:----------:|:------:|:----------:|:---------------------:|:------------------:|:--------------:|:------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:-------------------:|:----------------:|:------------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
68 |
+
| No log | 1.0 | 85 | 0.7040 | 0.0 | 0.0 | 0.0 | 107 | 0.0 | 0.0 | 0.0 | 71 | 0.0 | 0.0 | 0.0 | 64 | 0.0 | 0.0 | 0.0 | 374 | 0.0 | 0.0 | 0.0 | 0.7707 |
|
69 |
+
| No log | 2.0 | 170 | 0.3668 | 0.0 | 0.0 | 0.0 | 107 | 0.0 | 0.0 | 0.0 | 71 | 0.0 | 0.0 | 0.0 | 64 | 0.2416 | 0.2888 | 0.2631 | 374 | 0.2416 | 0.1753 | 0.2032 | 0.8896 |
|
70 |
+
| No log | 3.0 | 255 | 0.2618 | 0.3077 | 0.1869 | 0.2326 | 107 | 0.0 | 0.0 | 0.0 | 71 | 0.0 | 0.0 | 0.0 | 64 | 0.4626 | 0.5455 | 0.5006 | 374 | 0.4427 | 0.3636 | 0.3993 | 0.9171 |
|
71 |
+
| No log | 4.0 | 340 | 0.2232 | 0.7091 | 0.7290 | 0.7189 | 107 | 0.5316 | 0.5915 | 0.56 | 71 | 0.3523 | 0.4844 | 0.4079 | 64 | 0.5011 | 0.6016 | 0.5468 | 374 | 0.5179 | 0.6104 | 0.5604 | 0.9328 |
|
72 |
+
| No log | 5.0 | 425 | 0.1929 | 0.7778 | 0.8505 | 0.8125 | 107 | 0.84 | 0.5915 | 0.6942 | 71 | 0.44 | 0.5156 | 0.4748 | 64 | 0.5043 | 0.6257 | 0.5585 | 374 | 0.5666 | 0.6494 | 0.6051 | 0.9440 |
|
73 |
+
| 0.489 | 6.0 | 510 | 0.2214 | 0.7227 | 0.8037 | 0.7611 | 107 | 0.7538 | 0.6901 | 0.7206 | 71 | 0.4203 | 0.4531 | 0.4361 | 64 | 0.5683 | 0.6337 | 0.5992 | 374 | 0.5985 | 0.6510 | 0.6236 | 0.9447 |
|
74 |
+
| 0.489 | 7.0 | 595 | 0.2452 | 0.8598 | 0.8598 | 0.8598 | 107 | 0.7759 | 0.6338 | 0.6977 | 71 | 0.4853 | 0.5156 | 0.5 | 64 | 0.6460 | 0.6684 | 0.6570 | 374 | 0.6774 | 0.6818 | 0.6796 | 0.9469 |
|
75 |
+
| 0.489 | 8.0 | 680 | 0.2409 | 0.9245 | 0.9159 | 0.9202 | 107 | 0.7625 | 0.8592 | 0.8079 | 71 | 0.4321 | 0.5469 | 0.4828 | 64 | 0.6614 | 0.6738 | 0.6675 | 374 | 0.6883 | 0.7240 | 0.7057 | 0.9485 |
|
76 |
+
| 0.489 | 9.0 | 765 | 0.2760 | 0.8739 | 0.9065 | 0.8899 | 107 | 0.8529 | 0.8169 | 0.8345 | 71 | 0.5 | 0.5312 | 0.5152 | 64 | 0.6014 | 0.6898 | 0.6426 | 374 | 0.6612 | 0.7256 | 0.6920 | 0.9473 |
|
77 |
+
| 0.489 | 10.0 | 850 | 0.2676 | 0.8739 | 0.9065 | 0.8899 | 107 | 0.8254 | 0.7324 | 0.7761 | 71 | 0.5077 | 0.5156 | 0.5116 | 64 | 0.6460 | 0.6979 | 0.6710 | 374 | 0.6890 | 0.7192 | 0.7037 | 0.9504 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.44.0
|
83 |
+
- Pytorch 2.4.0
|
84 |
+
- Datasets 2.21.0
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-VIOLATION",
|
15 |
+
"1": "I-VIOLATION",
|
16 |
+
"2": "B-LAW",
|
17 |
+
"3": "B-VIOLATED ON",
|
18 |
+
"4": "I-VIOLATED ON",
|
19 |
+
"5": "I-VIOLATED BY",
|
20 |
+
"6": "O",
|
21 |
+
"7": "I-LAW",
|
22 |
+
"8": "B-VIOLATED BY"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"B-LAW": 2,
|
28 |
+
"B-VIOLATED BY": 8,
|
29 |
+
"B-VIOLATED ON": 3,
|
30 |
+
"B-VIOLATION": 0,
|
31 |
+
"I-LAW": 7,
|
32 |
+
"I-VIOLATED BY": 5,
|
33 |
+
"I-VIOLATED ON": 4,
|
34 |
+
"I-VIOLATION": 1,
|
35 |
+
"O": 6
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "roberta",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.44.0",
|
46 |
+
"type_vocab_size": 1,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 50265
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a2025e6a050f6ed824e4eca38afbb7ff0077fbd48f4f07bad7ab4b17b634e9
|
3 |
+
size 496271772
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86262daaece8adc1f6157870daddd4e3183841369c69ca98c4cfc2eaca084d4f
|
3 |
+
size 5176
|