binding-reconstruction-lstm-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9719
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: 3
- 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 |
---|---|---|---|
4.7957 | 0.03 | 76320 | 4.7633 |
4.5072 | 1.03 | 152640 | 4.4796 |
4.3632 | 0.03 | 228960 | 4.3437 |
4.278 | 1.03 | 305280 | 4.2603 |
4.2149 | 0.03 | 381600 | 4.2036 |
4.1648 | 1.03 | 457920 | 4.1627 |
4.1243 | 0.03 | 534240 | 4.1298 |
4.095 | 1.03 | 610560 | 4.1066 |
4.0668 | 0.03 | 686880 | 4.0871 |
4.041 | 0.03 | 763200 | 4.0715 |
4.0223 | 1.03 | 839520 | 4.0583 |
4.0048 | 0.03 | 915840 | 4.0469 |
3.9912 | 1.03 | 992160 | 4.0381 |
3.9716 | 0.03 | 1068480 | 4.0302 |
3.9585 | 1.03 | 1144800 | 4.0235 |
3.946 | 0.03 | 1221120 | 4.0170 |
3.9354 | 1.03 | 1297440 | 4.0121 |
3.9277 | 0.03 | 1373760 | 4.0072 |
3.916 | 1.03 | 1450080 | 4.0027 |
3.9153 | 0.03 | 1526400 | 3.9997 |
3.9091 | 1.03 | 1602720 | 3.9968 |
3.9025 | 0.03 | 1679040 | 3.9943 |
3.8967 | 1.03 | 1755360 | 3.9919 |
3.8932 | 0.03 | 1831680 | 3.9897 |
3.8843 | 1.03 | 1908000 | 3.9872 |
3.8776 | 0.03 | 1984320 | 3.9852 |
3.8712 | 1.03 | 2060640 | 3.9835 |
3.8692 | 0.03 | 2136960 | 3.9816 |
3.8637 | 1.03 | 2213280 | 3.9802 |
3.8561 | 0.03 | 2289600 | 3.9790 |
3.8503 | 1.03 | 2365920 | 3.9779 |
3.8498 | 0.03 | 2442240 | 3.9769 |
3.8463 | 1.03 | 2518560 | 3.9763 |
3.8421 | 0.03 | 2594880 | 3.9754 |
3.8384 | 1.03 | 2671200 | 3.9747 |
3.841 | 0.03 | 2747520 | 3.9740 |
3.8419 | 1.03 | 2823840 | 3.9734 |
3.84 | 0.03 | 2900160 | 3.9728 |
3.8397 | 1.03 | 2976480 | 3.9724 |
3.8387 | 0.02 | 3052726 | 3.9719 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1