Downloads · 30 days
13
50% of all-time downloads
ft_bs32_lr7_base
damgomz/ft_bs32_lr7_base
ft_bs32_lr7_base 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
26
Public
Parameters
11.7M
467 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors46.7 MB · 95%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 16, 2024
- Updated
- May 16, 2024
- SHA
- a19adf05
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 22799.569629907608 |
| Emissions (Co2eq in kg) | 0.0140201000358722 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 4.500000000000001 |
| CPU energy (kWh) | 0.2691611221477383 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.0284992255279422 |
| Consumed energy (kWh) | 0.2976603476756804 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 2 |
| 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) | 0.04388917153757214 |
| Emissions (Co2eq in kg) | 0.008929831438380479 |
Note
16 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ft_bs32_lr7_base |
| sequence_length | 400 |
| num_epoch | 10 |
| learning_rate | 5e-07 |
| batch_size | 32 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 54300 |
Training and Testing steps
| Epoch | Train Loss | Test Loss | Accuracy | Recall |
|---|---|---|---|---|
| 0 | 0.631623 | 0.594133 | 0.694404 | 0.823620 |
| 1 | 0.558485 | 0.541231 | 0.733432 | 0.809816 |
| 2 | 0.500646 | 0.493926 | 0.761414 | 0.760736 |
| 3 | 0.449850 | 0.456491 | 0.795287 | 0.805215 |
| 4 | 0.414101 | 0.442600 | 0.801178 | 0.874233 |
| 5 | 0.378759 | 0.425400 | 0.809278 | 0.852761 |
| 6 | 0.350256 | 0.424491 | 0.810751 | 0.868098 |
| 7 | 0.323519 | 0.420775 | 0.810015 | 0.837423 |
| 8 | 0.289084 | 0.426480 | 0.810751 | 0.838957 |
| 9 | 0.261814 | 0.436926 | 0.804860 | 0.822086 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 16, 2024
- Updated
- May 16, 2024