npi-only-transformer-0
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8602
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: 32
- eval_batch_size: 32
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.2219 | 0.03 | 76320 | 4.1939 |
4.0171 | 1.03 | 152640 | 4.0249 |
3.9099 | 0.03 | 228960 | 3.9509 |
3.8379 | 1.03 | 305280 | 3.9097 |
3.7887 | 0.03 | 381600 | 3.8848 |
3.7486 | 0.03 | 457920 | 3.8681 |
3.7135 | 1.03 | 534240 | 3.8583 |
3.6868 | 0.03 | 610560 | 3.8516 |
3.6574 | 1.03 | 686880 | 3.8469 |
3.6311 | 0.03 | 763200 | 3.8440 |
3.6076 | 1.03 | 839520 | 3.8431 |
3.5866 | 0.03 | 915840 | 3.8422 |
3.5683 | 1.03 | 992160 | 3.8421 |
3.5492 | 0.03 | 1068480 | 3.8424 |
3.5304 | 1.03 | 1144800 | 3.8433 |
3.5315 | 0.03 | 1221120 | 3.8459 |
3.5103 | 1.03 | 1297440 | 3.8459 |
3.4974 | 0.03 | 1373760 | 3.8475 |
3.4858 | 1.03 | 1450080 | 3.8485 |
3.4723 | 0.03 | 1526400 | 3.8502 |
3.4644 | 1.03 | 1602720 | 3.8505 |
3.4557 | 0.03 | 1679040 | 3.8526 |
3.4466 | 1.03 | 1755360 | 3.8532 |
3.4389 | 0.03 | 1831680 | 3.8546 |
3.4245 | 1.03 | 1908000 | 3.8560 |
3.4119 | 0.03 | 1984320 | 3.8569 |
3.3964 | 1.03 | 2060640 | 3.8589 |
3.3868 | 0.03 | 2136960 | 3.8584 |
3.3744 | 1.03 | 2213280 | 3.8605 |
3.3638 | 0.03 | 2289600 | 3.8619 |
3.3497 | 1.03 | 2365920 | 3.8616 |
3.3566 | 0.03 | 2442240 | 3.8614 |
3.3404 | 1.03 | 2518560 | 3.8625 |
3.3326 | 0.03 | 2594880 | 3.8628 |
3.3241 | 1.03 | 2671200 | 3.8628 |
3.3149 | 0.03 | 2747520 | 3.8632 |
3.3085 | 1.03 | 2823840 | 3.8625 |
3.3024 | 0.03 | 2900160 | 3.8626 |
3.2978 | 1.03 | 2976480 | 3.8610 |
3.2933 | 0.02 | 3052726 | 3.8602 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 5