DNADebertaK6b
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4362
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.061 | 0.25 | 20000 | 1.7733 |
| 1.7344 | 0.5 | 40000 | 1.6608 |
| 1.6651 | 0.75 | 60000 | 1.6319 |
| 1.6359 | 0.99 | 80000 | 1.6092 |
| 1.6131 | 1.24 | 100000 | 1.5932 |
| 1.5959 | 1.49 | 120000 | 1.5753 |
| 1.5827 | 1.74 | 140000 | 1.5624 |
| 1.5719 | 1.99 | 160000 | 1.5534 |
| 1.5617 | 2.24 | 180000 | 1.5454 |
| 1.5551 | 2.49 | 200000 | 1.5403 |
| 1.5477 | 2.74 | 220000 | 1.5322 |
| 1.5414 | 2.98 | 240000 | 1.5262 |
| 1.5366 | 3.23 | 260000 | 1.5220 |
| 1.5308 | 3.48 | 280000 | 1.5184 |
| 1.5274 | 3.73 | 300000 | 1.5121 |
| 1.5224 | 3.98 | 320000 | 1.5085 |
| 1.5194 | 4.23 | 340000 | 1.5050 |
| 1.5164 | 4.48 | 360000 | 1.5027 |
| 1.5126 | 4.72 | 380000 | 1.4984 |
| 1.5086 | 4.97 | 400000 | 1.4947 |
| 1.5048 | 5.22 | 420000 | 1.4914 |
| 1.5025 | 5.47 | 440000 | 1.4914 |
| 1.5006 | 5.72 | 460000 | 1.4877 |
| 1.4982 | 5.97 | 480000 | 1.4840 |
| 1.4952 | 6.22 | 500000 | 1.4825 |
| 1.4926 | 6.46 | 520000 | 1.4800 |
| 1.4907 | 6.71 | 540000 | 1.4778 |
| 1.4886 | 6.96 | 560000 | 1.4761 |
| 1.4864 | 7.21 | 580000 | 1.4746 |
| 1.4854 | 7.46 | 600000 | 1.4730 |
| 1.484 | 7.71 | 620000 | 1.4709 |
| 1.4826 | 7.96 | 640000 | 1.4676 |
| 1.4794 | 8.21 | 660000 | 1.4674 |
| 1.479 | 8.45 | 680000 | 1.4658 |
| 1.4777 | 8.7 | 700000 | 1.4661 |
| 1.4751 | 8.95 | 720000 | 1.4649 |
| 1.4742 | 9.2 | 740000 | 1.4614 |
| 1.4728 | 9.45 | 760000 | 1.4602 |
| 1.472 | 9.7 | 780000 | 1.4603 |
| 1.4703 | 9.95 | 800000 | 1.4577 |
| 1.4694 | 10.19 | 820000 | 1.4578 |
| 1.4662 | 10.44 | 840000 | 1.4557 |
| 1.4668 | 10.69 | 860000 | 1.4545 |
| 1.466 | 10.94 | 880000 | 1.4548 |
| 1.465 | 11.19 | 900000 | 1.4513 |
| 1.4626 | 11.44 | 920000 | 1.4511 |
| 1.4616 | 11.69 | 940000 | 1.4509 |
| 1.4609 | 11.93 | 960000 | 1.4485 |
| 1.4595 | 12.18 | 980000 | 1.4474 |
| 1.4588 | 12.43 | 1000000 | 1.4470 |
| 1.4588 | 12.68 | 1020000 | 1.4452 |
| 1.4565 | 12.93 | 1040000 | 1.4443 |
| 1.4556 | 13.18 | 1060000 | 1.4433 |
| 1.4543 | 13.43 | 1080000 | 1.4409 |
| 1.453 | 13.68 | 1100000 | 1.4409 |
| 1.4524 | 13.92 | 1120000 | 1.4397 |
| 1.4511 | 14.17 | 1140000 | 1.4402 |
| 1.4501 | 14.42 | 1160000 | 1.4385 |
| 1.4484 | 14.67 | 1180000 | 1.4373 |
| 1.449 | 14.92 | 1200000 | 1.4360 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.