Downloads · 30 days
5
6% of all-time downloads
tinybert-base-uncased-ADVQA36K-V1
allistair99/tinybert-base-uncased-ADVQA36K-V1
tinybert-base-uncased-ADVQA36K-V1 is a machine learning model from allistair99. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
83
Public
Parameters
66.4M
265 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors265 MB · 100%
At a glance
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- May 5, 2025
- Updated
- May 5, 2025
- SHA
- b7b359ad
Base models
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. -->
tinybert-base-uncased-ADVQA36K-V1
This model is a fine-tuned version of deepset/tinybert-6l-768d-squad2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9677
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: 6
- eval_batch_size: 60
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0765 | 0.0599 | 100 | 2.5814 |
| 2.8268 | 0.1198 | 200 | 2.5095 |
| 2.7793 | 0.1796 | 300 | 2.5010 |
| 2.7207 | 0.2395 | 400 | 2.4600 |
| 2.7237 | 0.2994 | 500 | 2.4738 |
| 2.7847 | 0.3593 | 600 | 2.4548 |
| 2.6382 | 0.4192 | 700 | 2.4683 |
| 2.581 | 0.4790 | 800 | 2.5506 |
| 2.6751 | 0.5389 | 900 | 2.4545 |
| 2.7498 | 0.5988 | 1000 | 2.3878 |
| 2.694 | 0.6587 | 1100 | 2.3868 |
| 2.4758 | 0.7186 | 1200 | 2.3428 |
| 2.6314 | 0.7784 | 1300 | 2.4042 |
| 2.6303 | 0.8383 | 1400 | 2.3783 |
| 2.5687 | 0.8982 | 1500 | 2.3797 |
| 2.5989 | 0.9581 | 1600 | 2.3255 |
| 2.207 | 1.0180 | 1700 | 2.7212 |
| 1.8539 | 1.0778 | 1800 | 2.3982 |
| 1.7812 | 1.1377 | 1900 | 2.6368 |
| 1.765 | 1.1976 | 2000 | 2.5626 |
| 1.7895 | 1.2575 | 2100 | 2.6103 |
| 1.8144 | 1.3174 | 2200 | 2.5863 |
| 1.7657 | 1.3772 | 2300 | 2.4383 |
| 1.8256 | 1.4371 | 2400 | 2.4881 |
| 1.8215 | 1.4970 | 2500 | 2.6227 |
| 1.9053 | 1.5569 | 2600 | 2.4121 |
| 1.872 | 1.6168 | 2700 | 2.4348 |
| 1.7558 | 1.6766 | 2800 | 2.4743 |
| 1.6951 | 1.7365 | 2900 | 2.6199 |
| 1.8006 | 1.7964 | 3000 | 2.5804 |
| 1.7538 | 1.8563 | 3100 | 2.4707 |
| 1.8206 | 1.9162 | 3200 | 2.4198 |
| 1.8098 | 1.9760 | 3300 | 2.4864 |
| 1.468 | 2.0359 | 3400 | 2.9562 |
| 1.3203 | 2.0958 | 3500 | 2.8562 |
| 1.2161 | 2.1557 | 3600 | 2.9124 |
| 1.2002 | 2.2156 | 3700 | 2.8811 |
| 1.1981 | 2.2754 | 3800 | 2.9929 |
| 1.151 | 2.3353 | 3900 | 3.0145 |
| 1.1867 | 2.3952 | 4000 | 2.9327 |
| 1.2305 | 2.4551 | 4100 | 2.9967 |
| 1.1003 | 2.5150 | 4200 | 3.0383 |
| 1.2409 | 2.5749 | 4300 | 2.9114 |
| 1.1997 | 2.6347 | 4400 | 2.9199 |
| 1.2403 | 2.6946 | 4500 | 2.8751 |
| 1.1495 | 2.7545 | 4600 | 2.9636 |
| 1.1879 | 2.8144 | 4700 | 2.9894 |
| 1.1685 | 2.8743 | 4800 | 2.9766 |
| 1.2527 | 2.9341 | 4900 | 2.9656 |
| 1.2254 | 2.9940 | 5000 | 2.9677 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- bert
- License
- mit
- Created
- May 5, 2025
- Updated
- May 5, 2025