Hugging Face's logo

MSLars
/
de_longformer_abstr_summ

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Inference Endpoints
Model card Files Community
MSLars commited on
Commit
6b4adc4
•
1 Parent(s): 21a6abf

Training complete

Browse files
Files changed (2) hide show
  1. README.md +13 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [LennartKeller/longformer-gottbert-base-8192-aw512](https://huggingface.co/LennartKeller/longformer-gottbert-base-8192-aw512) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5746
23
- - Precision: 0.1612
24
- - Recall: 0.2474
25
- - F1: 0.1952
26
- - Accuracy: 0.7800
27
 
28
  ## Model description
29
 
@@ -43,34 +43,25 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
- - train_batch_size: 2
47
- - eval_batch_size: 2
48
  - seed: 42
49
- - gradient_accumulation_steps: 4
50
- - total_train_batch_size: 8
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | No log | 0.98 | 48 | 0.5548 | 0.0 | 0.0 | 0.0 | 0.7540 |
60
- | No log | 1.99 | 97 | 0.5185 | 0.1067 | 0.1548 | 0.1263 | 0.7864 |
61
- | No log | 2.99 | 146 | 0.5068 | 0.0876 | 0.1534 | 0.1115 | 0.7806 |
62
- | No log | 4.0 | 195 | 0.5145 | 0.2797 | 0.3889 | 0.3254 | 0.7926 |
63
- | No log | 4.98 | 243 | 0.5097 | 0.2068 | 0.3439 | 0.2583 | 0.7916 |
64
- | No log | 5.99 | 292 | 0.5073 | 0.1637 | 0.2831 | 0.2075 | 0.7920 |
65
- | No log | 6.99 | 341 | 0.5316 | 0.1723 | 0.2553 | 0.2058 | 0.7865 |
66
- | No log | 8.0 | 390 | 0.5480 | 0.1483 | 0.2275 | 0.1795 | 0.7837 |
67
- | No log | 8.98 | 438 | 0.5587 | 0.1649 | 0.2725 | 0.2055 | 0.7823 |
68
- | No log | 9.85 | 480 | 0.5746 | 0.1612 | 0.2474 | 0.1952 | 0.7800 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.36.2
74
  - Pytorch 2.2.1
75
- - Datasets 2.16.1
76
- - Tokenizers 0.15.0
 
19
 
20
  This model is a fine-tuned version of [LennartKeller/longformer-gottbert-base-8192-aw512](https://huggingface.co/LennartKeller/longformer-gottbert-base-8192-aw512) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.2916
23
+ - Precision: 0.2656
24
+ - Recall: 0.2673
25
+ - F1: 0.2665
26
+ - Accuracy: 0.8948
27
 
28
  ## Model description
29
 
 
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
+ - train_batch_size: 4
47
+ - eval_batch_size: 4
48
  - seed: 42
 
 
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 3
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 0.2741 | 1.0 | 1171 | 0.2860 | 0.0914 | 0.0307 | 0.0459 | 0.8979 |
58
+ | 0.2474 | 2.0 | 2342 | 0.2694 | 0.2918 | 0.2508 | 0.2697 | 0.8982 |
59
+ | 0.2074 | 3.0 | 3513 | 0.2916 | 0.2656 | 0.2673 | 0.2665 | 0.8948 |
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
63
 
64
  - Transformers 4.36.2
65
  - Pytorch 2.2.1
66
+ - Datasets 2.18.0
67
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c636734766b06c30ed762f5c8dd1b178328ea260ecdee62e2c5ea7b9e131aa0
3
  size 610262228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08402925649ff958822fd49e38ec86f2bdc5747a99b2400f0fe269fd02007c9a
3
  size 610262228