xlnet-base-cased
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1940
- Rmse: 0.3007
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rmse |
---|---|---|---|---|
0.2598 | 1.0 | 642 | 0.2309 | 0.3848 |
0.2498 | 2.0 | 1284 | 0.2335 | 0.3848 |
0.2475 | 3.0 | 1926 | 0.2343 | 0.3848 |
0.2399 | 4.0 | 2568 | 0.2197 | 0.3520 |
0.3899 | 5.0 | 3210 | 0.4305 | 0.3848 |
0.407 | 6.0 | 3852 | 0.3771 | 0.3548 |
0.3054 | 7.0 | 4494 | 0.2244 | 0.3548 |
0.2268 | 8.0 | 5136 | 0.2141 | 0.3542 |
0.2251 | 9.0 | 5778 | 0.2084 | 0.3165 |
0.1958 | 10.0 | 6420 | 0.1940 | 0.3007 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 12