Downloads · 30 days
44
7% of all-time downloads
my-finetuned-xml-roberta4
knurm/my-finetuned-xml-roberta4
my-finetuned-xml-roberta4 is a question answering model from knurm. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
614
Public
Repo size
89.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 98%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- May 30, 2022
- Updated
- May 30, 2022
- SHA
- e1d03025
Try a prompt
Model card
From the Hugging Face model README
<!-- 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. -->
my-finetuned-xml-roberta4
This model is a fine-tuned version of knurm/xlm-roberta-base-finetuned-est on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7709
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4629 | 1.0 | 5652 | 3.3367 |
| 3.1814 | 2.0 | 11304 | 3.2952 |
| 2.9718 | 3.0 | 16956 | 3.2592 |
| 2.7442 | 4.0 | 22608 | 3.3133 |
| 2.5991 | 5.0 | 28260 | 3.4292 |
| 2.4221 | 6.0 | 33912 | 3.5928 |
| 2.3259 | 7.0 | 39564 | 3.7709 |
Framework versions
- Transformers 4.19.1
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Task
- Question Answering
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- May 30, 2022
- Updated
- May 30, 2022