existential-there-quantifier-lstm-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9707
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: 1
- 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 |
---|---|---|---|
4.7869 | 0.03 | 76320 | 4.7523 |
4.5021 | 1.03 | 152640 | 4.4735 |
4.3565 | 0.03 | 228960 | 4.3382 |
4.2703 | 1.03 | 305280 | 4.2550 |
4.207 | 0.03 | 381600 | 4.1988 |
4.1597 | 1.03 | 457920 | 4.1581 |
4.1214 | 0.03 | 534240 | 4.1265 |
4.087 | 1.03 | 610560 | 4.1024 |
4.0579 | 0.03 | 686880 | 4.0837 |
4.0324 | 1.03 | 763200 | 4.0681 |
4.0127 | 0.03 | 839520 | 4.0550 |
3.9967 | 1.03 | 915840 | 4.0433 |
3.9826 | 0.03 | 992160 | 4.0345 |
3.9648 | 0.03 | 1068480 | 4.0267 |
3.9536 | 1.03 | 1144800 | 4.0200 |
3.9427 | 0.03 | 1221120 | 4.0140 |
3.9321 | 0.03 | 1297440 | 4.0089 |
3.9207 | 1.03 | 1373760 | 4.0047 |
3.9104 | 0.03 | 1450080 | 4.0004 |
3.9059 | 1.03 | 1526400 | 3.9965 |
3.9015 | 0.03 | 1602720 | 3.9936 |
3.8966 | 1.03 | 1679040 | 3.9912 |
3.8904 | 0.03 | 1755360 | 3.9888 |
3.8823 | 1.03 | 1831680 | 3.9863 |
3.8772 | 0.03 | 1908000 | 3.9844 |
3.8681 | 0.03 | 1984320 | 3.9819 |
3.8644 | 1.03 | 2060640 | 3.9805 |
3.861 | 0.03 | 2136960 | 3.9793 |
3.8578 | 1.03 | 2213280 | 3.9780 |
3.8507 | 0.03 | 2289600 | 3.9769 |
3.8499 | 1.03 | 2365920 | 3.9759 |
3.8477 | 0.03 | 2442240 | 3.9749 |
3.8431 | 1.03 | 2518560 | 3.9742 |
3.8386 | 0.03 | 2594880 | 3.9735 |
3.8348 | 0.03 | 2671200 | 3.9727 |
3.8369 | 0.03 | 2747520 | 3.9720 |
3.8354 | 1.03 | 2823840 | 3.9718 |
3.8366 | 0.03 | 2900160 | 3.9713 |
3.8366 | 1.03 | 2976480 | 3.9710 |
3.8324 | 0.02 | 3052726 | 3.9707 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8