npi-only-lstm-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9706
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: 4
- 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 |
---|---|---|---|
4.7842 | 0.03 | 76320 | 4.7527 |
4.4998 | 1.03 | 152640 | 4.4706 |
4.3572 | 0.03 | 228960 | 4.3365 |
4.2678 | 1.03 | 305280 | 4.2554 |
4.2074 | 0.03 | 381600 | 4.1993 |
4.1611 | 0.03 | 457920 | 4.1584 |
4.124 | 1.03 | 534240 | 4.1284 |
4.0944 | 0.03 | 610560 | 4.1041 |
4.0657 | 1.03 | 686880 | 4.0844 |
4.0387 | 0.03 | 763200 | 4.0687 |
4.0176 | 1.03 | 839520 | 4.0560 |
3.9991 | 0.03 | 915840 | 4.0455 |
3.9839 | 1.03 | 992160 | 4.0365 |
3.9667 | 0.03 | 1068480 | 4.0277 |
3.9517 | 1.03 | 1144800 | 4.0214 |
3.9502 | 0.03 | 1221120 | 4.0157 |
3.9349 | 1.03 | 1297440 | 4.0106 |
3.9256 | 0.03 | 1373760 | 4.0061 |
3.9164 | 1.03 | 1450080 | 4.0017 |
3.9074 | 0.03 | 1526400 | 3.9981 |
3.9035 | 1.03 | 1602720 | 3.9951 |
3.9005 | 0.03 | 1679040 | 3.9921 |
3.8957 | 1.03 | 1755360 | 3.9897 |
3.8926 | 0.03 | 1831680 | 3.9872 |
3.8848 | 1.03 | 1908000 | 3.9855 |
3.8765 | 0.03 | 1984320 | 3.9838 |
3.8697 | 1.03 | 2060640 | 3.9820 |
3.8651 | 0.03 | 2136960 | 3.9800 |
3.8594 | 1.03 | 2213280 | 3.9783 |
3.8534 | 0.03 | 2289600 | 3.9772 |
3.8469 | 1.03 | 2365920 | 3.9761 |
3.8539 | 0.03 | 2442240 | 3.9754 |
3.8443 | 1.03 | 2518560 | 3.9743 |
3.8401 | 0.03 | 2594880 | 3.9737 |
3.8388 | 1.03 | 2671200 | 3.9727 |
3.8347 | 0.03 | 2747520 | 3.9720 |
3.8367 | 1.03 | 2823840 | 3.9715 |
3.837 | 0.03 | 2900160 | 3.9711 |
3.8384 | 0.03 | 2976480 | 3.9706 |
3.8395 | 1.02 | 3052726 | 3.9706 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 9