Commit
•
dc6ea4d
1
Parent(s):
5fad435
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- squad_v2
|
| 7 |
model-index:
|
| 8 |
- name: bert-base-cased-finetuned-squad
|
| 9 |
results: []
|
|
@@ -14,9 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# bert-base-cased-finetuned-squad
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.1389
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -41,15 +37,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
-
|
| 46 |
-
### Training results
|
| 47 |
-
|
| 48 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
-
| 1.0306 | 1.0 | 8255 | 1.0864 |
|
| 51 |
-
| 0.7498 | 2.0 | 16510 | 1.1389 |
|
| 52 |
-
|
| 53 |
|
| 54 |
### Framework versions
|
| 55 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: bert-base-cased-finetuned-squad
|
| 7 |
results: []
|
|
|
|
| 12 |
|
| 13 |
# bert-base-cased-finetuned-squad
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
|
|
| 37 |
- seed: 42
|
| 38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
+
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
### Framework versions
|
| 43 |
|