Instructions to use Oleksandr2003/QA_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Oleksandr2003/QA_model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Oleksandr2003/QA_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Oleksandr2003/QA_model") model = AutoModelForQuestionAnswering.from_pretrained("Oleksandr2003/QA_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit 路
2b223a4
1
Parent(s): 097e59f
Training in progress epoch 0
Browse files- README.md +5 -24
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Validation Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,33 +35,14 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
| 39 |
- training_precision: float32
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
-
|
|
| 46 |
-
| 0.5361 | 5.2595 | 1 |
|
| 47 |
-
| 0.4224 | 5.4612 | 2 |
|
| 48 |
-
| 0.3856 | 5.1464 | 3 |
|
| 49 |
-
| 0.3207 | 5.4474 | 4 |
|
| 50 |
-
| 0.2875 | 5.8978 | 5 |
|
| 51 |
-
| 0.2538 | 5.8839 | 6 |
|
| 52 |
-
| 0.2313 | 5.9605 | 7 |
|
| 53 |
-
| 0.1911 | 6.3752 | 8 |
|
| 54 |
-
| 0.1746 | 6.2357 | 9 |
|
| 55 |
-
| 0.1667 | 6.1096 | 10 |
|
| 56 |
-
| 0.1433 | 6.0823 | 11 |
|
| 57 |
-
| 0.1150 | 6.3878 | 12 |
|
| 58 |
-
| 0.1179 | 6.3776 | 13 |
|
| 59 |
-
| 0.1046 | 6.5274 | 14 |
|
| 60 |
-
| 0.1069 | 6.8341 | 15 |
|
| 61 |
-
| 0.0750 | 6.8479 | 16 |
|
| 62 |
-
| 0.0834 | 6.7711 | 17 |
|
| 63 |
-
| 0.0740 | 6.6447 | 18 |
|
| 64 |
-
| 0.0594 | 7.1634 | 19 |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 3.8064
|
| 18 |
+
- Validation Loss: 3.3809
|
| 19 |
+
- Epoch: 0
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 654, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
| 39 |
- training_precision: float32
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
+
| 3.8064 | 3.3809 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265583688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19395882a88ac6fdb05239140d67287803f76d7741c7f091a1123554cae9824
|
| 3 |
size 265583688
|