npi-sim-ques-lstm-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9697
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 |
|---|---|---|---|
| 4.7918 | 0.03 | 76320 | 4.7476 |
| 4.5063 | 1.03 | 152640 | 4.4713 |
| 4.3693 | 0.03 | 228960 | 4.3372 |
| 4.2798 | 1.03 | 305280 | 4.2552 |
| 4.2162 | 0.03 | 381600 | 4.1996 |
| 4.1702 | 1.03 | 457920 | 4.1579 |
| 4.1299 | 0.03 | 534240 | 4.1274 |
| 4.0979 | 1.03 | 610560 | 4.1032 |
| 4.0699 | 0.03 | 686880 | 4.0841 |
| 4.0453 | 1.03 | 763200 | 4.0682 |
| 4.0227 | 0.03 | 839520 | 4.0544 |
| 4.0083 | 1.03 | 915840 | 4.0439 |
| 3.9855 | 0.03 | 992160 | 4.0348 |
| 3.9686 | 1.03 | 1068480 | 4.0269 |
| 3.9569 | 0.03 | 1144800 | 4.0202 |
| 3.9536 | 1.03 | 1221120 | 4.0145 |
| 3.9419 | 0.03 | 1297440 | 4.0091 |
| 3.9296 | 1.03 | 1373760 | 4.0045 |
| 3.9249 | 0.03 | 1450080 | 4.0007 |
| 3.9165 | 1.03 | 1526400 | 3.9972 |
| 3.91 | 0.03 | 1602720 | 3.9940 |
| 3.9061 | 1.03 | 1679040 | 3.9914 |
| 3.9003 | 0.03 | 1755360 | 3.9890 |
| 3.8927 | 1.03 | 1831680 | 3.9870 |
| 3.8857 | 0.03 | 1908000 | 3.9842 |
| 3.8796 | 1.03 | 1984320 | 3.9827 |
| 3.8738 | 0.03 | 2060640 | 3.9813 |
| 3.8713 | 1.03 | 2136960 | 3.9798 |
| 3.8624 | 0.03 | 2213280 | 3.9784 |
| 3.8527 | 0.03 | 2289600 | 3.9773 |
| 3.8497 | 1.03 | 2365920 | 3.9758 |
| 3.8542 | 0.03 | 2442240 | 3.9742 |
| 3.8492 | 0.03 | 2518560 | 3.9731 |
| 3.8441 | 1.03 | 2594880 | 3.9722 |
| 3.845 | 0.03 | 2671200 | 3.9717 |
| 3.8432 | 0.03 | 2747520 | 3.9712 |
| 3.8429 | 1.03 | 2823840 | 3.9707 |
| 3.8432 | 0.03 | 2900160 | 3.9704 |
| 3.8435 | 1.03 | 2976480 | 3.9700 |
| 3.8378 | 0.02 | 3052726 | 3.9697 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 15