Downloads · 30 days
9
16% of all-time downloads
Bloom_3b_squad
halo-69/Bloom_3b_squad
Bloom_3b_squad is a question answering model from halo-69. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as bigscience-bloom-rail-1.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
57
Public
Repo size
35.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin6.9 GB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- bigscience-bloom-rail-1.0
- Model type
- bloom
- Access
- Public
- Created
- Sep 14, 2023
- Updated
- Sep 25, 2023
- SHA
- 8b69e8a7
Try a prompt
Base models
Datasets
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. -->
Bloom_3b_squad
This model is a fine-tuned version of bigscience/bloom-3b on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 2.7859
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: 48
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0058 | 1.0 | 1643 | 2.7510 |
| 2.7801 | 2.0 | 3286 | 2.7497 |
| 2.7284 | 3.0 | 4929 | 2.7536 |
| 2.7001 | 4.0 | 6572 | 2.7601 |
| 2.6811 | 5.0 | 8215 | 2.7669 |
| 2.6811 | 6.0 | 9858 | 2.7722 |
| 2.6639 | 7.0 | 11501 | 2.7780 |
| 2.6492 | 8.0 | 13144 | 2.7817 |
| 2.6414 | 9.0 | 14787 | 2.7841 |
| 2.6354 | 10.0 | 16430 | 2.7859 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
- Task
- Question Answering
- Library
- transformers
- Type
- bloom
- License
- bigscience-bloom-rail-1.0
- Created
- Sep 14, 2023
- Updated
- Sep 25, 2023