rel-cl2-lstm-0
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9753
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 |
|---|---|---|---|
| 4.7969 | 0.03 | 76320 | 4.7632 |
| 4.5095 | 1.03 | 152640 | 4.4761 |
| 4.3676 | 0.03 | 228960 | 4.3396 |
| 4.2783 | 1.03 | 305280 | 4.2578 |
| 4.2173 | 0.03 | 381600 | 4.2011 |
| 4.1732 | 1.03 | 457920 | 4.1603 |
| 4.1335 | 0.03 | 534240 | 4.1303 |
| 4.1006 | 1.03 | 610560 | 4.1066 |
| 4.0695 | 0.03 | 686880 | 4.0870 |
| 4.0465 | 1.03 | 763200 | 4.0715 |
| 4.0224 | 0.03 | 839520 | 4.0582 |
| 4.0057 | 1.03 | 915840 | 4.0470 |
| 3.9883 | 0.03 | 992160 | 4.0386 |
| 3.9732 | 1.03 | 1068480 | 4.0313 |
| 3.9651 | 0.03 | 1144800 | 4.0252 |
| 3.9525 | 1.03 | 1221120 | 4.0188 |
| 3.9385 | 0.03 | 1297440 | 4.0134 |
| 3.929 | 0.03 | 1373760 | 4.0089 |
| 3.9225 | 1.03 | 1450080 | 4.0052 |
| 3.9149 | 2.03 | 1526400 | 4.0018 |
| 3.9108 | 0.03 | 1602720 | 3.9988 |
| 3.9075 | 1.03 | 1679040 | 3.9958 |
| 3.9004 | 0.03 | 1755360 | 3.9936 |
| 3.8954 | 1.03 | 1831680 | 3.9913 |
| 3.8852 | 0.03 | 1908000 | 3.9891 |
| 3.881 | 1.03 | 1984320 | 3.9874 |
| 3.8755 | 0.03 | 2060640 | 3.9854 |
| 3.8688 | 0.03 | 2136960 | 3.9840 |
| 3.8632 | 1.03 | 2213280 | 3.9830 |
| 3.8571 | 0.03 | 2289600 | 3.9818 |
| 3.8571 | 1.03 | 2365920 | 3.9805 |
| 3.853 | 0.03 | 2442240 | 3.9794 |
| 3.8473 | 1.03 | 2518560 | 3.9785 |
| 3.8449 | 0.03 | 2594880 | 3.9777 |
| 3.8444 | 1.03 | 2671200 | 3.9773 |
| 3.8426 | 0.03 | 2747520 | 3.9766 |
| 3.8423 | 1.03 | 2823840 | 3.9763 |
| 3.844 | 0.03 | 2900160 | 3.9760 |
| 3.8417 | 1.03 | 2976480 | 3.9755 |
| 3.8393 | 0.02 | 3052726 | 3.9753 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3