rel-cl2-transformer-0
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8679
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 |
---|---|---|---|
4.2377 | 0.03 | 76320 | 4.2029 |
4.0318 | 1.03 | 152640 | 4.0337 |
3.9251 | 0.03 | 228960 | 3.9583 |
3.8539 | 1.03 | 305280 | 3.9172 |
3.8033 | 0.03 | 381600 | 3.8931 |
3.7625 | 1.03 | 457920 | 3.8765 |
3.7264 | 0.03 | 534240 | 3.8653 |
3.6966 | 1.03 | 610560 | 3.8590 |
3.6669 | 0.03 | 686880 | 3.8557 |
3.6421 | 1.03 | 763200 | 3.8520 |
3.6162 | 0.03 | 839520 | 3.8502 |
3.5966 | 1.03 | 915840 | 3.8494 |
3.5791 | 0.03 | 992160 | 3.8483 |
3.5578 | 1.03 | 1068480 | 3.8498 |
3.5447 | 0.03 | 1144800 | 3.8502 |
3.5354 | 1.03 | 1221120 | 3.8513 |
3.5188 | 0.03 | 1297440 | 3.8529 |
3.5059 | 0.03 | 1373760 | 3.8541 |
3.4959 | 1.03 | 1450080 | 3.8552 |
3.482 | 0.03 | 1526400 | 3.8570 |
3.4744 | 0.03 | 1602720 | 3.8576 |
3.4665 | 0.03 | 1679040 | 3.8593 |
3.4556 | 0.03 | 1755360 | 3.8615 |
3.4438 | 0.03 | 1831680 | 3.8622 |
3.4297 | 1.03 | 1908000 | 3.8633 |
3.4185 | 0.03 | 1984320 | 3.8654 |
3.4036 | 1.03 | 2060640 | 3.8650 |
3.394 | 0.03 | 2136960 | 3.8670 |
3.3823 | 1.03 | 2213280 | 3.8687 |
3.37 | 0.03 | 2289600 | 3.8685 |
3.3629 | 1.03 | 2365920 | 3.8704 |
3.3583 | 0.03 | 2442240 | 3.8706 |
3.3462 | 1.03 | 2518560 | 3.8710 |
3.3349 | 0.03 | 2594880 | 3.8712 |
3.3282 | 1.03 | 2671200 | 3.8706 |
3.3211 | 0.03 | 2747520 | 3.8724 |
3.3168 | 1.03 | 2823840 | 3.8708 |
3.3123 | 0.03 | 2900160 | 3.8701 |
3.3045 | 0.03 | 2976480 | 3.8690 |
3.2964 | 0.02 | 3052726 | 3.8679 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4