Token Classification
Transformers
Safetensors
Persian
bert
feature-extraction
persian
word-importance
salience
dhh
asr-evaluation
ace-metric
distillation
Instructions to use Reza2kn/ShenavaSanj-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reza2kn/ShenavaSanj-v1.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Reza2kn/ShenavaSanj-v1.0")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Reza2kn/ShenavaSanj-v1.0") model = AutoModel.from_pretrained("Reza2kn/ShenavaSanj-v1.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metrics after epoch 1
Browse files- metrics.json +20 -0
metrics.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"history": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 1,
|
| 5 |
+
"val_token_spearman": 0.9282,
|
| 6 |
+
"val_per_utt_spearman": 0.9089,
|
| 7 |
+
"val_mse": 0.01239
|
| 8 |
+
}
|
| 9 |
+
],
|
| 10 |
+
"config": {
|
| 11 |
+
"student": "HooshvareLab/bert-base-parsbert-uncased",
|
| 12 |
+
"epochs": 4,
|
| 13 |
+
"batch": 32,
|
| 14 |
+
"lr": 3e-05,
|
| 15 |
+
"maxlen": 64,
|
| 16 |
+
"loss": "huber(0.1)",
|
| 17 |
+
"n_train": 25166,
|
| 18 |
+
"n_val": 1324
|
| 19 |
+
}
|
| 20 |
+
}
|