mobilebert-base-uncased-ADVQA36K-V1
This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3227
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 |
|---|---|---|---|
| 2.2279 | 0.0599 | 100 | 2.6963 |
| 2.886 | 0.1198 | 200 | 2.4836 |
| 2.7738 | 0.1796 | 300 | 2.4420 |
| 2.7423 | 0.2395 | 400 | 2.3748 |
| 2.6163 | 0.2994 | 500 | 2.3575 |
| 2.7046 | 0.3593 | 600 | 2.3147 |
| 2.5698 | 0.4192 | 700 | 2.3329 |
| 2.5435 | 0.4790 | 800 | 2.2926 |
| 2.6129 | 0.5389 | 900 | 2.2665 |
| 2.7169 | 0.5988 | 1000 | 2.2880 |
| 2.5918 | 0.6587 | 1100 | 2.2605 |
| 2.475 | 0.7186 | 1200 | 2.2090 |
| 2.5796 | 0.7784 | 1300 | 2.2185 |
| 2.5512 | 0.8383 | 1400 | 2.1962 |
| 2.5058 | 0.8982 | 1500 | 2.1858 |
| 2.5175 | 0.9581 | 1600 | 2.1954 |
| 2.2704 | 1.0180 | 1700 | 2.2219 |
| 2.0732 | 1.0778 | 1800 | 2.1850 |
| 2.0031 | 1.1377 | 1900 | 2.2436 |
| 2.0496 | 1.1976 | 2000 | 2.1884 |
| 2.0254 | 1.2575 | 2100 | 2.1912 |
| 1.9819 | 1.3174 | 2200 | 2.2532 |
| 2.0407 | 1.3772 | 2300 | 2.2019 |
| 1.9614 | 1.4371 | 2400 | 2.2167 |
| 2.0374 | 1.4970 | 2500 | 2.2342 |
| 2.1099 | 1.5569 | 2600 | 2.2153 |
| 2.0153 | 1.6168 | 2700 | 2.2109 |
| 1.9406 | 1.6766 | 2800 | 2.1990 |
| 1.8886 | 1.7365 | 2900 | 2.2312 |
| 2.0457 | 1.7964 | 3000 | 2.1997 |
| 1.9055 | 1.8563 | 3100 | 2.2317 |
| 2.028 | 1.9162 | 3200 | 2.1973 |
| 1.9083 | 1.9760 | 3300 | 2.2466 |
| 1.796 | 2.0359 | 3400 | 2.2761 |
| 1.7564 | 2.0958 | 3500 | 2.2729 |
| 1.7172 | 2.1557 | 3600 | 2.3039 |
| 1.6924 | 2.2156 | 3700 | 2.3319 |
| 1.6198 | 2.2754 | 3800 | 2.3473 |
| 1.5996 | 2.3353 | 3900 | 2.3506 |
| 1.725 | 2.3952 | 4000 | 2.2952 |
| 1.6847 | 2.4551 | 4100 | 2.3058 |
| 1.5333 | 2.5150 | 4200 | 2.3350 |
| 1.6129 | 2.5749 | 4300 | 2.3596 |
| 1.5813 | 2.6347 | 4400 | 2.3547 |
| 1.65 | 2.6946 | 4500 | 2.3355 |
| 1.6316 | 2.7545 | 4600 | 2.3327 |
| 1.6697 | 2.8144 | 4700 | 2.3329 |
| 1.6385 | 2.8743 | 4800 | 2.3279 |
| 1.6707 | 2.9341 | 4900 | 2.3208 |
| 1.6122 | 2.9940 | 5000 | 2.3227 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1