rel-cl-transformer-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8743
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 |
---|---|---|---|
4.2434 | 0.03 | 76319 | 4.2060 |
4.0345 | 0.03 | 152638 | 4.0340 |
3.9248 | 0.03 | 228957 | 3.9585 |
3.8562 | 0.03 | 305276 | 3.9172 |
3.8037 | 0.03 | 381595 | 3.8908 |
3.7556 | 0.03 | 457914 | 3.8749 |
3.7229 | 0.03 | 534233 | 3.8649 |
3.6965 | 0.03 | 610552 | 3.8577 |
3.6655 | 0.03 | 686871 | 3.8533 |
3.6443 | 1.03 | 763190 | 3.8509 |
3.6177 | 0.03 | 839510 | 3.8456 |
3.5968 | 1.03 | 915830 | 3.8454 |
3.5746 | 0.03 | 992150 | 3.8458 |
3.5558 | 1.03 | 1068470 | 3.8476 |
3.5439 | 0.03 | 1144790 | 3.8481 |
3.5306 | 1.03 | 1221110 | 3.8491 |
3.5166 | 0.03 | 1297430 | 3.8516 |
3.5037 | 1.03 | 1373750 | 3.8530 |
3.4876 | 0.03 | 1450070 | 3.8545 |
3.478 | 1.03 | 1526390 | 3.8568 |
3.4703 | 0.03 | 1602710 | 3.8579 |
3.4583 | 0.03 | 1679030 | 3.8600 |
3.4502 | 1.03 | 1755350 | 3.8622 |
3.4371 | 0.03 | 1831670 | 3.8640 |
3.4242 | 1.03 | 1907990 | 3.8663 |
3.4095 | 0.03 | 1984310 | 3.8678 |
3.3975 | 1.03 | 2060630 | 3.8689 |
3.3887 | 0.03 | 2136950 | 3.8701 |
3.3749 | 1.03 | 2213270 | 3.8710 |
3.3623 | 0.03 | 2289590 | 3.8732 |
3.3578 | 1.03 | 2365910 | 3.8741 |
3.3495 | 0.03 | 2442230 | 3.8750 |
3.3397 | 0.03 | 2518550 | 3.8754 |
3.3315 | 1.03 | 2594870 | 3.8756 |
3.3207 | 0.03 | 2671190 | 3.8764 |
3.3143 | 1.03 | 2747510 | 3.8766 |
3.3059 | 0.03 | 2823830 | 3.8768 |
3.3018 | 1.03 | 2900150 | 3.8763 |
3.2951 | 0.03 | 2976470 | 3.8753 |
3.2884 | 1.02 | 3052726 | 3.8743 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1