<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
cl-rarity-all-base-iorder-5p5k-finetune-guten-rarity-all-2p5k
This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.4732
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7338 | 0.29 | 500 | 4.4961 |
| 3.869 | 0.59 | 1000 | 4.5075 |
| 3.969 | 0.88 | 1500 | 4.4386 |
| 3.8209 | 1.17 | 2000 | 4.4448 |
| 3.7839 | 1.47 | 2500 | 4.4047 |
| 3.7962 | 1.76 | 3000 | 4.3633 |
| 3.7161 | 2.05 | 3500 | 4.3727 |
| 3.472 | 2.35 | 4000 | 4.3747 |
| 3.5071 | 2.64 | 4500 | 4.3474 |
| 3.5007 | 2.93 | 5000 | 4.3163 |
| 3.2028 | 3.23 | 5500 | 4.3785 |
| 3.1368 | 3.52 | 6000 | 4.3727 |
| 3.1333 | 3.81 | 6500 | 4.3575 |
| 3.022 | 4.11 | 7000 | 4.3838 |
| 2.8459 | 4.4 | 7500 | 4.3932 |
| 2.8356 | 4.69 | 8000 | 4.3938 |
| 2.8391 | 4.99 | 8500 | 4.3937 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
