HF中国镜像站's logo

scbtm
/
ModernBERT_wine_quality_reviews_ft

Text Classification
Transformers
TensorBoard
Safetensors
modernbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
scbtm commited on
Commit
2d3d836
·
verified ·
1 Parent(s): 58c5e47

End of training

Browse files
Files changed (3) hide show
  1. README.md +34 -22
  2. model.safetensors +1 -1
  3. runs/Jan21_16-22-49_f3acabd62f42/events.out.tfevents.1737480496.f3acabd62f42.52016.1 +3 -0
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.8255
23
- - Accuracy: 0.6865
24
- - F1: 0.6873
25
 
26
  ## Model description
27
 
@@ -40,9 +40,9 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 8e-05
44
- - train_batch_size: 64
45
- - eval_batch_size: 64
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
@@ -53,22 +53,34 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
56
- | 1.0765 | 0.1653 | 350 | 0.8973 | 0.5849 | 0.5797 |
57
- | 0.848 | 0.3305 | 700 | 0.7721 | 0.6516 | 0.6483 |
58
- | 0.7796 | 0.4958 | 1050 | 0.7682 | 0.6466 | 0.6470 |
59
- | 0.7671 | 0.6610 | 1400 | 0.7448 | 0.6611 | 0.6566 |
60
- | 0.7434 | 0.8263 | 1750 | 0.7378 | 0.6643 | 0.6634 |
61
- | 0.7232 | 0.9915 | 2100 | 0.7086 | 0.6789 | 0.6736 |
62
- | 0.653 | 1.1568 | 2450 | 0.7150 | 0.6768 | 0.6764 |
63
- | 0.6312 | 1.3220 | 2800 | 0.7119 | 0.6785 | 0.6761 |
64
- | 0.6298 | 1.4873 | 3150 | 0.6982 | 0.6879 | 0.6843 |
65
- | 0.6307 | 1.6525 | 3500 | 0.7072 | 0.6863 | 0.6864 |
66
- | 0.6338 | 1.8178 | 3850 | 0.6950 | 0.6862 | 0.6813 |
67
- | 0.6252 | 1.9830 | 4200 | 0.6996 | 0.6850 | 0.6853 |
68
- | 0.4418 | 2.1483 | 4550 | 0.8353 | 0.6911 | 0.6899 |
69
- | 0.4016 | 2.3135 | 4900 | 0.8428 | 0.6825 | 0.6815 |
70
- | 0.404 | 2.4788 | 5250 | 0.8241 | 0.6824 | 0.6822 |
71
- | 0.404 | 2.6440 | 5600 | 0.8255 | 0.6865 | 0.6873 |
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6790
23
+ - Accuracy: 0.6966
24
+ - F1: 0.6967
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 4e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
56
+ | 1.1775 | 0.0826 | 350 | 0.9993 | 0.5336 | 0.5225 |
57
+ | 0.9496 | 0.1653 | 700 | 0.9632 | 0.5569 | 0.5411 |
58
+ | 0.8658 | 0.2479 | 1050 | 0.8257 | 0.6273 | 0.6272 |
59
+ | 0.8287 | 0.3306 | 1400 | 0.8655 | 0.5998 | 0.5742 |
60
+ | 0.8018 | 0.4132 | 1750 | 0.7638 | 0.6580 | 0.6510 |
61
+ | 0.7915 | 0.4959 | 2100 | 0.7481 | 0.6661 | 0.6662 |
62
+ | 0.767 | 0.5785 | 2450 | 0.7572 | 0.6626 | 0.6613 |
63
+ | 0.7525 | 0.6612 | 2800 | 0.7223 | 0.6747 | 0.6719 |
64
+ | 0.7498 | 0.7438 | 3150 | 0.7216 | 0.6768 | 0.6712 |
65
+ | 0.7258 | 0.8264 | 3500 | 0.7173 | 0.6762 | 0.6733 |
66
+ | 0.7183 | 0.9091 | 3850 | 0.7186 | 0.6786 | 0.6764 |
67
+ | 0.7251 | 0.9917 | 4200 | 0.7052 | 0.6822 | 0.6762 |
68
+ | 0.6534 | 1.0744 | 4550 | 0.7090 | 0.6860 | 0.6859 |
69
+ | 0.6425 | 1.1570 | 4900 | 0.7870 | 0.6512 | 0.6479 |
70
+ | 0.6321 | 1.2397 | 5250 | 0.6944 | 0.6899 | 0.6894 |
71
+ | 0.6283 | 1.3223 | 5600 | 0.7030 | 0.6869 | 0.6851 |
72
+ | 0.633 | 1.4050 | 5950 | 0.7000 | 0.6876 | 0.6859 |
73
+ | 0.6326 | 1.4876 | 6300 | 0.7044 | 0.6848 | 0.6823 |
74
+ | 0.6305 | 1.5702 | 6650 | 0.7002 | 0.6872 | 0.6832 |
75
+ | 0.6288 | 1.6529 | 7000 | 0.7076 | 0.6877 | 0.6856 |
76
+ | 0.625 | 1.7355 | 7350 | 0.6831 | 0.6930 | 0.6929 |
77
+ | 0.6394 | 1.8182 | 7700 | 0.6944 | 0.6859 | 0.6829 |
78
+ | 0.6221 | 1.9008 | 8050 | 0.6790 | 0.6966 | 0.6967 |
79
+ | 0.62 | 1.9835 | 8400 | 0.6928 | 0.6889 | 0.6896 |
80
+ | 0.4506 | 2.0661 | 8750 | 0.8053 | 0.6911 | 0.6896 |
81
+ | 0.3982 | 2.1488 | 9100 | 0.9036 | 0.6843 | 0.6839 |
82
+ | 0.3928 | 2.2314 | 9450 | 0.8230 | 0.6871 | 0.6873 |
83
+ | 0.3855 | 2.3140 | 9800 | 0.8589 | 0.6873 | 0.6864 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f0c4ded768bbc6ca8201ec17dbb0373ba6303f650ddea18427bffe62b23d84
3
  size 598445936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ac1c3be7727bf398eeadc29fac840de47e1e083e9b3cf2f01c28ec82e68a92
3
  size 598445936
runs/Jan21_16-22-49_f3acabd62f42/events.out.tfevents.1737480496.f3acabd62f42.52016.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa39937c063efcb08bc8091d7dfd03241929d53d127df3043fab42505a8c20e
3
+ size 457