Model save
Browse files- README.md +11 -0
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# scibert_scivocab_uncased-finetuned-squad
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the squad_v2 dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -41,6 +43,15 @@ The following hyperparameters were used during training:
|
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- num_epochs: 3
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.32.0
|
|
|
|
| 15 |
# scibert_scivocab_uncased-finetuned-squad
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the squad_v2 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.1145
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- num_epochs: 3
|
| 45 |
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 1.0302 | 1.0 | 8280 | 1.0650 |
|
| 51 |
+
| 0.7757 | 2.0 | 16560 | 0.9399 |
|
| 52 |
+
| 0.5482 | 3.0 | 24840 | 1.1145 |
|
| 53 |
+
|
| 54 |
+
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.32.0
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437385385
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:294d919e3b820c9d9e8a2071e6c2362e747a232cbd7c14d008cfa078292937f6
|
| 3 |
size 437385385
|