Hugging Face's logo

IngeniousArtist
/
distilbert-finance

Text Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
IngeniousArtist commited on
Commit
7158dee
•
1 Parent(s): 1ed4a10

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -34
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7427685950413223
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.9820
36
- - Accuracy: 0.7428
37
 
38
  ## Model description
39
 
@@ -57,43 +57,43 @@ The following hyperparameters were used during training:
57
  - eval_batch_size: 64
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 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 0.905 | 0.33 | 20 | 1.5902 | 0.4205 |
68
- | 0.66 | 0.66 | 40 | 1.6678 | 0.4184 |
69
- | 0.5429 | 0.98 | 60 | 1.6024 | 0.3915 |
70
- | 0.4804 | 1.31 | 80 | 1.5001 | 0.4236 |
71
- | 0.3914 | 1.64 | 100 | 1.4990 | 0.4246 |
72
- | 0.3817 | 1.97 | 120 | 1.3082 | 0.4225 |
73
- | 0.2829 | 2.3 | 140 | 1.0931 | 0.4566 |
74
- | 0.2737 | 2.62 | 160 | 0.9830 | 0.5579 |
75
- | 0.2958 | 2.95 | 180 | 0.8748 | 0.6281 |
76
- | 0.1963 | 3.28 | 200 | 0.7356 | 0.7335 |
77
- | 0.1861 | 3.61 | 220 | 1.0993 | 0.5599 |
78
- | 0.2025 | 3.93 | 240 | 0.7504 | 0.75 |
79
- | 0.1326 | 4.26 | 260 | 0.8450 | 0.7438 |
80
- | 0.1491 | 4.59 | 280 | 0.7221 | 0.7593 |
81
- | 0.1303 | 4.92 | 300 | 0.9738 | 0.6756 |
82
- | 0.109 | 5.25 | 320 | 0.7593 | 0.7634 |
83
- | 0.0994 | 5.57 | 340 | 1.1073 | 0.6632 |
84
- | 0.0969 | 5.9 | 360 | 0.8082 | 0.7479 |
85
- | 0.0697 | 6.23 | 380 | 0.9121 | 0.7242 |
86
- | 0.0635 | 6.56 | 400 | 0.8706 | 0.7490 |
87
- | 0.0637 | 6.89 | 420 | 1.0041 | 0.7221 |
88
- | 0.0561 | 7.21 | 440 | 1.0379 | 0.7035 |
89
- | 0.0577 | 7.54 | 460 | 1.0113 | 0.7180 |
90
- | 0.0612 | 7.87 | 480 | 0.9029 | 0.75 |
91
- | 0.0505 | 8.2 | 500 | 0.9523 | 0.7428 |
92
- | 0.0493 | 8.52 | 520 | 0.9854 | 0.7304 |
93
- | 0.0271 | 8.85 | 540 | 1.0400 | 0.7252 |
94
- | 0.0271 | 9.18 | 560 | 1.0337 | 0.7314 |
95
- | 0.0397 | 9.51 | 580 | 1.0058 | 0.7366 |
96
- | 0.0441 | 9.84 | 600 | 0.9820 | 0.7428 |
97
 
98
 
99
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7386363636363636
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.9962
36
+ - Accuracy: 0.7386
37
 
38
  ## Model description
39
 
 
57
  - eval_batch_size: 64
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: cosine
61
  - num_epochs: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.904 | 0.33 | 20 | 1.5959 | 0.4205 |
68
+ | 0.6562 | 0.66 | 40 | 1.6665 | 0.4143 |
69
+ | 0.539 | 0.98 | 60 | 1.6067 | 0.3936 |
70
+ | 0.4759 | 1.31 | 80 | 1.5079 | 0.4236 |
71
+ | 0.3882 | 1.64 | 100 | 1.4719 | 0.4298 |
72
+ | 0.3782 | 1.97 | 120 | 1.2392 | 0.4267 |
73
+ | 0.2729 | 2.3 | 140 | 1.0114 | 0.4928 |
74
+ | 0.2607 | 2.62 | 160 | 0.9514 | 0.5930 |
75
+ | 0.2889 | 2.95 | 180 | 0.8661 | 0.6477 |
76
+ | 0.181 | 3.28 | 200 | 0.7093 | 0.7417 |
77
+ | 0.1742 | 3.61 | 220 | 1.1042 | 0.5764 |
78
+ | 0.1904 | 3.93 | 240 | 0.7439 | 0.7510 |
79
+ | 0.1186 | 4.26 | 260 | 0.8587 | 0.7469 |
80
+ | 0.137 | 4.59 | 280 | 0.7408 | 0.7603 |
81
+ | 0.1166 | 4.92 | 300 | 1.0107 | 0.6705 |
82
+ | 0.0938 | 5.25 | 320 | 0.7883 | 0.7624 |
83
+ | 0.0881 | 5.57 | 340 | 1.0339 | 0.7056 |
84
+ | 0.0812 | 5.9 | 360 | 0.8409 | 0.7490 |
85
+ | 0.0586 | 6.23 | 380 | 0.9146 | 0.7345 |
86
+ | 0.0572 | 6.56 | 400 | 0.9000 | 0.7366 |
87
+ | 0.0527 | 6.89 | 420 | 0.9782 | 0.7335 |
88
+ | 0.045 | 7.21 | 440 | 1.0102 | 0.7262 |
89
+ | 0.0471 | 7.54 | 460 | 1.0322 | 0.7324 |
90
+ | 0.0508 | 7.87 | 480 | 0.9381 | 0.7448 |
91
+ | 0.039 | 8.2 | 500 | 0.9489 | 0.7459 |
92
+ | 0.0419 | 8.52 | 520 | 0.9779 | 0.7469 |
93
+ | 0.0256 | 8.85 | 540 | 0.9834 | 0.7407 |
94
+ | 0.0264 | 9.18 | 560 | 0.9963 | 0.7376 |
95
+ | 0.0378 | 9.51 | 580 | 0.9981 | 0.7376 |
96
+ | 0.0421 | 9.84 | 600 | 0.9962 | 0.7386 |
97
 
98
 
99
  ### Framework versions