Downloads · 30 days
8
22% of all-time downloads
damgomz/ft_bs16_lr6_mlm
ft_bs16_lr6_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.
Downloads · 30 days
8
22% of all-time downloads
All-time downloads
36
Public
Parameters
11.7M
280 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors46.7 MB · 95%
From the Hugging Face model README
| Metric | Value |
|---|---|
| Duration (in seconds) | 13016.97026515007 |
| Emissions (Co2eq in kg) | 0.0078767721168084 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 3.75 |
| CPU energy (kWh) | 0.1536722855205337 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.0135592407062649 |
| Consumed energy (kWh) | 0.1672315262267985 |
| 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) | 0.025057667760413883 |
| Emissions (Co2eq in kg) | 0.005098313353850444 |
20 May 2024
| Config | Value |
|---|---|
| checkpoint | damgomz/ThunBERT_bs16_lr5_MLM |
| model_name | ft_bs16_lr6_mlm |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-06 |
| batch_size | 16 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 32580 |
| Epoch | Train Loss | Test Loss | Accuracy | Recall |
|---|---|---|---|---|
| 0 | 0.441067 | 0.342969 | 0.849779 | 0.877301 |
| 1 | 0.324801 | 0.346633 | 0.851252 | 0.918712 |
| 2 | 0.278107 | 0.331949 | 0.857143 | 0.871166 |
| 3 | 0.216568 | 0.365292 | 0.849779 | 0.878834 |
| 4 | 0.141970 | 0.435924 | 0.844624 | 0.915644 |
| 5 | 0.062279 | 0.516091 | 0.843152 | 0.889571 |