Hugging Face's logo

frisibeli
/
legal-roberta-large

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
frisibeli commited on
Commit
47af526
•
1 Parent(s): 5425b48

frisibeli/roberta-lexml

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [lexlms/legal-roberta-large](https://huggingface.co/lexlms/legal-roberta-large) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6295
21
- - F1: 0.4711
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 3e-05
41
  - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 100
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 80
49
  - num_epochs: 5
50
  - mixed_precision_training: Native AMP
51
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | F1 |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | 0.6641 | 0.96 | 18 | 0.5623 | 0.4322 |
57
- | 0.5628 | 1.97 | 37 | 0.5583 | 0.4322 |
58
- | 0.554 | 2.99 | 56 | 0.6142 | 0.4322 |
59
- | 0.5071 | 4.0 | 75 | 0.5391 | 0.4866 |
60
- | 0.3651 | 4.8 | 90 | 0.6295 | 0.4711 |
61
 
62
 
63
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [lexlms/legal-roberta-large](https://huggingface.co/lexlms/legal-roberta-large) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.0297
21
+ - F1: 0.4489
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-06
41
  - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 100
 
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 30
49
  - num_epochs: 5
50
  - mixed_precision_training: Native AMP
51
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | F1 |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
+ | 0.2471 | 0.96 | 18 | 0.8701 | 0.4711 |
57
+ | 0.1889 | 1.97 | 37 | 0.9103 | 0.4562 |
58
+ | 0.1444 | 2.99 | 56 | 0.9706 | 0.4489 |
59
+ | 0.1283 | 4.0 | 75 | 1.0204 | 0.4562 |
60
+ | 0.1411 | 4.8 | 90 | 1.0297 | 0.4489 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e14328cd319a991f9c5418c194a1c390234f8d841155bd66c5f7626d2cc2590
3
  size 1420414072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78a9c9cefb82bc7056a16ffe21c241addac96bda925442989884284b23a7b19
3
  size 1420414072
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6511186045cd91933c15c7d2628e7e355ffd97fb387aee7918cd7506fa6a7be7
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36765709db3a4b779ec9256d853fad8bfbed6cbe6f9c342265002d69880570b
3
  size 4600