Instructions to use daze-unlv/microsoft-deberta-v3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use daze-unlv/microsoft-deberta-v3-base with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultipleChoice tokenizer = AutoTokenizer.from_pretrained("daze-unlv/microsoft-deberta-v3-base") model = AutoModelForMultipleChoice.from_pretrained("daze-unlv/microsoft-deberta-v3-base") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 3
Browse files
log.txt
CHANGED
|
@@ -11,3 +11,11 @@
|
|
| 11 |
{'loss': 1.3867, 'grad_norm': 0.388902485370636, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
|
| 12 |
{'loss': 1.3867, 'grad_norm': 0.34345269203186035, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
|
| 13 |
{'loss': 1.3865, 'grad_norm': 0.28443431854248047, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
{'loss': 1.3867, 'grad_norm': 0.388902485370636, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
|
| 12 |
{'loss': 1.3867, 'grad_norm': 0.34345269203186035, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
|
| 13 |
{'loss': 1.3865, 'grad_norm': 0.28443431854248047, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
|
| 14 |
+
[0 0 1 ... 0 0 3] [0 0 2 ... 0 1 0]
|
| 15 |
+
{'eval_loss': 1.3862946033477783, 'eval_accuracy': 0.27755199617499404, 'eval_runtime': 11.7259, 'eval_samples_per_second': 356.732, 'eval_steps_per_second': 5.629, 'epoch': 2.0}
|
| 16 |
+
{'loss': 1.3866, 'grad_norm': 0.3457288444042206, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
|
| 17 |
+
{'loss': 1.3867, 'grad_norm': 0.39303871989250183, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
|
| 18 |
+
{'loss': 1.3867, 'grad_norm': 0.3226775825023651, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
|
| 19 |
+
{'loss': 1.3867, 'grad_norm': 0.3367418646812439, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
|
| 20 |
+
{'loss': 1.3866, 'grad_norm': 0.3738933801651001, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
|
| 21 |
+
{'loss': 1.3867, 'grad_norm': 0.3130834996700287, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737716196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7516fef4495396057faed2893a07dcd43ac6825b1408952d11e730a7be2a94f8
|
| 3 |
size 737716196
|
runs/Mar13_07-36-31_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710340594.cehsc-app-001.ad.unlv.edu.2900872.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:162c45a3914f0521d18bce429b57b1345c96a085f30f62b1a73ff46e5176d808
|
| 3 |
+
size 9680
|