Instructions to use HASAN55/bert-finetuned-squadddd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HASAN55/bert-finetuned-squadddd 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="HASAN55/bert-finetuned-squadddd")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("HASAN55/bert-finetuned-squadddd") model = AutoModelForQuestionAnswering.from_pretrained("HASAN55/bert-finetuned-squadddd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress epoch 1
Browse files- README.md +8 -7
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Train End Logits Accuracy: 0.
|
| 19 |
-
- Train Start Logits Accuracy: 0.
|
| 20 |
-
- Validation Loss: 0.
|
| 21 |
-
- Validation End Logits Accuracy: 0.
|
| 22 |
-
- Validation Start Logits Accuracy: 0.
|
| 23 |
-
- Epoch:
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
|
|
| 47 |
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|
| 48 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
| 49 |
| 1.2708 | 0.6644 | 0.6245 | 0.9948 | 0.7315 | 0.6978 | 0 |
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.7826
|
| 18 |
+
- Train End Logits Accuracy: 0.7783
|
| 19 |
+
- Train Start Logits Accuracy: 0.7382
|
| 20 |
+
- Validation Loss: 0.9748
|
| 21 |
+
- Validation End Logits Accuracy: 0.7354
|
| 22 |
+
- Validation Start Logits Accuracy: 0.7042
|
| 23 |
+
- Epoch: 1
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 47 |
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|
| 48 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
| 49 |
| 1.2708 | 0.6644 | 0.6245 | 0.9948 | 0.7315 | 0.6978 | 0 |
|
| 50 |
+
| 0.7826 | 0.7783 | 0.7382 | 0.9748 | 0.7354 | 0.7042 | 1 |
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 431154128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:267487850315120b755ab2d5a7cc4eca23e568cf5072a2c349ce1b3d62da69c3
|
| 3 |
size 431154128
|