Downloads · 30 days
7
32% of all-time downloads
damgomz/ft_32_4e6_base_x4
ft_32_4e6_base_x4 is a text classification model from damgomz. Use it when you need a label for a piece of text. It is set up for transformers.
Downloads · 30 days
7
32% of all-time downloads
All-time downloads
22
Public
Parameters
32.9M
4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 98%
From the Hugging Face model README
| Metric | Value |
|---|---|
| Duration (in seconds) | 71845.55230617523 |
| Emissions (Co2eq in kg) | 0.0434748378985542 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 3.75 |
| CPU energy (kWh) | 0.8481747363578943 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.0748383185359342 |
| Consumed energy (kWh) | 0.9230130548938292 |
| 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 |
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.13830268818938735 |
| Emissions (Co2eq in kg) | 0.0281395079865853 |
19 juin 2024
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ft_32_4e6_base_x4 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 4e-06 |
| 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 | 29328 |
| Epoch | Train Loss | Test Loss | F-beta Score |
|---|---|---|---|
| 0 | 0.000000 | 0.726919 | 0.469267 |
| 1 | 0.380991 | 0.280183 | 0.879980 |
| 2 | 0.234251 | 0.240912 | 0.927142 |
| 3 | 0.188952 | 0.234519 | 0.911161 |
| 4 | 0.151393 | 0.247042 | 0.904971 |
| 5 | 0.120314 | 0.243643 | 0.921235 |
| 6 | 0.085023 | 0.265345 | 0.908701 |