metadata
license: mit
base_model: timpal0l/mdeberta-v3-base-squad2
tags:
- generated_from_trainer
model-index:
- name: model1
results: []
model1
This model is a fine-tuned version of timpal0l/mdeberta-v3-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4437
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: 1.2922909480977358e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2146 | 0.0 | 10 | 4.1627 |
| 4.1667 | 0.0 | 20 | 3.9059 |
| 4.0555 | 0.01 | 30 | 3.7982 |
| 3.9331 | 0.01 | 40 | 3.7342 |
| 3.8012 | 0.01 | 50 | 3.6719 |
| 3.7713 | 0.01 | 60 | 3.6077 |
| 3.8391 | 0.02 | 70 | 3.5548 |
| 3.8842 | 0.02 | 80 | 3.5134 |
| 3.6894 | 0.02 | 90 | 3.4823 |
| 3.5359 | 0.02 | 100 | 3.4466 |
| 3.6247 | 0.03 | 110 | 3.4096 |
| 3.6347 | 0.03 | 120 | 3.3807 |
| 3.5752 | 0.03 | 130 | 3.3459 |
| 3.467 | 0.03 | 140 | 3.2778 |
| 3.6188 | 0.04 | 150 | 3.2198 |
| 3.444 | 0.04 | 160 | 3.1880 |
| 3.4635 | 0.04 | 170 | 3.1494 |
| 3.3998 | 0.04 | 180 | 3.1107 |
| 3.1465 | 0.04 | 190 | 3.0675 |
| 3.4321 | 0.05 | 200 | 3.0380 |
| 3.3174 | 0.05 | 210 | 3.0122 |
| 3.6018 | 0.05 | 220 | 2.9566 |
| 3.4178 | 0.05 | 230 | 2.9099 |
| 3.2037 | 0.06 | 240 | 2.8755 |
| 3.3974 | 0.06 | 250 | 2.8493 |
| 3.109 | 0.06 | 260 | 2.8209 |
| 3.1127 | 0.06 | 270 | 2.7751 |
| 3.2408 | 0.07 | 280 | 2.7458 |
| 3.274 | 0.07 | 290 | 2.7211 |
| 3.0695 | 0.07 | 300 | 2.6946 |
| 2.9757 | 0.07 | 310 | 2.6713 |
| 3.0846 | 0.08 | 320 | 2.6415 |
| 3.0576 | 0.08 | 330 | 2.6209 |
| 2.8623 | 0.08 | 340 | 2.6041 |
| 3.165 | 0.08 | 350 | 2.5913 |
| 2.8874 | 0.08 | 360 | 2.5797 |
| 3.046 | 0.09 | 370 | 2.5627 |
| 2.8727 | 0.09 | 380 | 2.5391 |
| 2.7942 | 0.09 | 390 | 2.5188 |
| 2.7494 | 0.09 | 400 | 2.5031 |
| 2.8419 | 0.1 | 410 | 2.4905 |
| 2.8411 | 0.1 | 420 | 2.4792 |
| 2.9188 | 0.1 | 430 | 2.4696 |
| 2.9239 | 0.1 | 440 | 2.4622 |
| 3.0064 | 0.11 | 450 | 2.4551 |
| 2.9781 | 0.11 | 460 | 2.4504 |
| 2.8582 | 0.11 | 470 | 2.4483 |
| 2.8701 | 0.11 | 480 | 2.4456 |
| 2.7012 | 0.12 | 490 | 2.4442 |
| 2.827 | 0.12 | 500 | 2.4437 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0