Instructions to use wietsedv/bert-base-dutch-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wietsedv/bert-base-dutch-cased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="wietsedv/bert-base-dutch-cased")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("wietsedv/bert-base-dutch-cased") model = AutoModelForMaskedLM.from_pretrained("wietsedv/bert-base-dutch-cased") - Inference
- Notebooks
- Google Colab
- Kaggle
Update pretraining_output_eval_results.txt
Browse files
pretraining_output_eval_results.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
global_step = 1000000
|
| 2 |
+
loss = 1.5525091
|
| 3 |
+
masked_lm_accuracy = 0.67388266
|
| 4 |
+
masked_lm_loss = 1.5623554
|
| 5 |
+
next_sentence_accuracy = 0.99997187
|
| 6 |
+
next_sentence_loss = 7.288994e-05
|