<!-- 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. -->
deeppavlov-framebank-full-5epochs
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4206
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.0742 | 1.0 | 2827 | 1.0130 |
0.7934 | 2.0 | 5654 | 1.0363 |
0.5931 | 3.0 | 8481 | 1.1527 |
0.4166 | 4.0 | 11308 | 1.2754 |
0.3145 | 5.0 | 14135 | 1.4206 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.2.3.dev0
- Tokenizers 0.12.1