Downloads · 30 days
18
56% of all-time downloads
ThunBERT_bs8_lr5_MLM
damgomz/ThunBERT_bs8_lr5_MLM
ThunBERT_bs8_lr5_MLM is a fill-mask model from damgomz. Use it when you need the model to fill a missing word. It is set up for transformers.
All-time downloads
32
Public
Parameters
11.2M
584 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors44.9 MB · 95%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 11, 2024
- Updated
- May 13, 2024
- SHA
- b29aefc2
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 222194.28785967827 |
| Emissions (Co2eq in kg) | 0.2325671263715923 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 37.5 |
| CPU energy (kWh) | 2.6231219651492017 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 2.314504122865692 |
| Consumed energy (kWh) | 4.937626088014953 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 4 |
| CPU model | Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz |
| GPU count | nan |
| GPU model | nan |
Environmental Impact (for one core)
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.42772400412988065 |
| Emissions (Co2eq in kg) | 0.08702609607837399 |
Note
11 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ThunBERT_bs8_lr5_MLM |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| batch_size | 8 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 82533 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 10.169299 | 3.893429 |
| 0.5 | 2.974144 | 2.843656 |
| 1.0 | 2.783727 | 2.781645 |
| 1.5 | 2.678597 | 2.669879 |
| 2.0 | 2.595359 | 2.603173 |
| 2.5 | 2.525631 | 2.518131 |
| 3.0 | 2.453879 | 2.475023 |
| 3.5 | 2.397467 | 2.423880 |
| 4.0 | 2.351636 | 2.381376 |
| 4.5 | 2.294014 | 2.340238 |
| 5.0 | 2.253481 | 2.299134 |
| 5.5 | 2.208159 | 2.264561 |
| 6.0 | 2.192403 | 2.241567 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 11, 2024
- Updated
- May 13, 2024