Model save
Browse files
README.md
CHANGED
|
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- F1 Macro: 0.
|
| 23 |
-
- F1: 0.
|
| 24 |
-
- F1 Neg: 0.
|
| 25 |
-
- Acc: 0.
|
| 26 |
-
- Prec: 0.
|
| 27 |
- Recall: 0.9408
|
| 28 |
-
- Mcc: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
|
|
| 51 |
- distributed_type: multi-GPU
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: linear
|
| 54 |
-
- num_epochs:
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
### Training results
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4641
|
| 22 |
+
- F1 Macro: 0.8845
|
| 23 |
+
- F1: 0.9232
|
| 24 |
+
- F1 Neg: 0.8459
|
| 25 |
+
- Acc: 0.8975
|
| 26 |
+
- Prec: 0.9062
|
| 27 |
- Recall: 0.9408
|
| 28 |
+
- Mcc: 0.7705
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 51 |
- distributed_type: multi-GPU
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: linear
|
| 54 |
+
- num_epochs: 3
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
### Training results
|