<!-- 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. -->
vi-finetuned-squad-qa-minilmv2-8
This model is a fine-tuned version of subhasisj/vi-TAPT-MLM-MiniLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3335
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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 |
---|---|---|---|
2.1669 | 1.0 | 1424 | 1.4979 |
1.2377 | 2.0 | 2848 | 1.3259 |
1.0536 | 3.0 | 4272 | 1.3133 |
0.9568 | 4.0 | 5696 | 1.3103 |
0.8859 | 5.0 | 7120 | 1.3335 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2
- Datasets 2.0.0
- Tokenizers 0.11.0