roberta-base-pp-1000-1e-06-8
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6920
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 32
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 32 | 0.6944 |
No log | 2.0 | 64 | 0.6938 |
No log | 3.0 | 96 | 0.6934 |
No log | 4.0 | 128 | 0.6932 |
No log | 5.0 | 160 | 0.6931 |
No log | 6.0 | 192 | 0.6930 |
0.6946 | 7.0 | 224 | 0.6930 |
0.6946 | 8.0 | 256 | 0.6929 |
0.6946 | 9.0 | 288 | 0.6929 |
0.6946 | 10.0 | 320 | 0.6929 |
0.6946 | 11.0 | 352 | 0.6928 |
0.6946 | 12.0 | 384 | 0.6928 |
0.6929 | 13.0 | 416 | 0.6928 |
0.6929 | 14.0 | 448 | 0.6927 |
0.6929 | 15.0 | 480 | 0.6927 |
0.6929 | 16.0 | 512 | 0.6926 |
0.6929 | 17.0 | 544 | 0.6926 |
0.6929 | 18.0 | 576 | 0.6926 |
0.6928 | 19.0 | 608 | 0.6926 |
0.6928 | 20.0 | 640 | 0.6925 |
0.6928 | 21.0 | 672 | 0.6924 |
0.6928 | 22.0 | 704 | 0.6924 |
0.6928 | 23.0 | 736 | 0.6923 |
0.6928 | 24.0 | 768 | 0.6923 |
0.6906 | 25.0 | 800 | 0.6923 |
0.6906 | 26.0 | 832 | 0.6922 |
0.6906 | 27.0 | 864 | 0.6922 |
0.6906 | 28.0 | 896 | 0.6921 |
0.6906 | 29.0 | 928 | 0.6921 |
0.6906 | 30.0 | 960 | 0.6921 |
0.6906 | 31.0 | 992 | 0.6921 |
0.6897 | 32.0 | 1024 | 0.6920 |
0.6897 | 33.0 | 1056 | 0.6920 |
0.6897 | 34.0 | 1088 | 0.6920 |
0.6897 | 35.0 | 1120 | 0.6920 |
0.6897 | 36.0 | 1152 | 0.6920 |
0.6897 | 37.0 | 1184 | 0.6920 |
0.69 | 38.0 | 1216 | 0.6920 |
0.69 | 39.0 | 1248 | 0.6920 |
0.69 | 40.0 | 1280 | 0.6920 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 3