<!-- 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. -->
de-finetuned-squad-qa-minilmv2-16
This model is a fine-tuned version of subhasisj/de-TAPT-MLM-MiniLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5756
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.6022 | 1.0 | 671 | 2.0770 |
1.9783 | 2.0 | 1342 | 1.6511 |
1.4059 | 3.0 | 2013 | 1.5939 |
1.2989 | 4.0 | 2684 | 1.5772 |
1.2522 | 5.0 | 3355 | 1.5756 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1