<!-- 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. -->
finetune-cl-rarity-all-base-rarity-all-iorder-5p5k
This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.4996
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 |
|---|---|---|---|
| 3.7517 | 0.31 | 500 | 4.5218 |
| 3.9053 | 0.63 | 1000 | 4.5251 |
| 4.0186 | 0.94 | 1500 | 4.4593 |
| 3.8298 | 1.25 | 2000 | 4.4694 |
| 3.8412 | 1.56 | 2500 | 4.4186 |
| 3.8523 | 1.88 | 3000 | 4.3740 |
| 3.6221 | 2.19 | 3500 | 4.4206 |
| 3.5434 | 2.5 | 4000 | 4.3924 |
| 3.5587 | 2.82 | 4500 | 4.3596 |
| 3.3793 | 3.13 | 5000 | 4.4040 |
| 3.1807 | 3.44 | 5500 | 4.4051 |
| 3.1732 | 3.75 | 6000 | 4.3953 |
| 3.0987 | 4.07 | 6500 | 4.4114 |
| 2.8718 | 4.38 | 7000 | 4.4259 |
| 2.8684 | 4.69 | 7500 | 4.4275 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
