Jeremiah Zhou
commited on
Commit
·
81aef98
1
Parent(s):
1302929
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
license: mit
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
@@ -15,13 +13,13 @@ model-index:
|
|
| 15 |
name: Text Classification
|
| 16 |
type: text-classification
|
| 17 |
dataset:
|
| 18 |
-
name:
|
| 19 |
type: glue
|
| 20 |
args: rte
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
-
value: 0.
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -29,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 29 |
|
| 30 |
# roberta-base-rte
|
| 31 |
|
| 32 |
-
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss:
|
| 35 |
-
- Accuracy: 0.
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
@@ -51,7 +49,7 @@ More information needed
|
|
| 51 |
### Training hyperparameters
|
| 52 |
|
| 53 |
The following hyperparameters were used during training:
|
| 54 |
-
- learning_rate:
|
| 55 |
- train_batch_size: 16
|
| 56 |
- eval_batch_size: 8
|
| 57 |
- seed: 42
|
|
@@ -64,14 +62,16 @@ The following hyperparameters were used during training:
|
|
| 64 |
|
| 65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
-
| No log | 1.0 | 156 | 0.
|
| 68 |
-
| No log | 2.0 | 312 | 0.
|
| 69 |
-
| No log | 3.0 | 468 | 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
|
|
|
|
|
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
| 13 |
name: Text Classification
|
| 14 |
type: text-classification
|
| 15 |
dataset:
|
| 16 |
+
name: glue
|
| 17 |
type: glue
|
| 18 |
args: rte
|
| 19 |
metrics:
|
| 20 |
- name: Accuracy
|
| 21 |
type: accuracy
|
| 22 |
+
value: 0.7725631768953068
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 27 |
|
| 28 |
# roberta-base-rte
|
| 29 |
|
| 30 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 1.3534
|
| 33 |
+
- Accuracy: 0.7726
|
| 34 |
|
| 35 |
## Model description
|
| 36 |
|
|
|
|
| 49 |
### Training hyperparameters
|
| 50 |
|
| 51 |
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 1e-05
|
| 53 |
- train_batch_size: 16
|
| 54 |
- eval_batch_size: 8
|
| 55 |
- seed: 42
|
|
|
|
| 62 |
|
| 63 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 64 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 65 |
+
| No log | 1.0 | 156 | 0.7023 | 0.4729 |
|
| 66 |
+
| No log | 2.0 | 312 | 0.6356 | 0.6895 |
|
| 67 |
+
| No log | 3.0 | 468 | 0.5177 | 0.7617 |
|
| 68 |
+
| 0.6131 | 4.0 | 624 | 0.6238 | 0.7473 |
|
| 69 |
+
| 0.6131 | 5.0 | 780 | 0.5446 | 0.7978 |
|
| 70 |
+
| 0.6131 | 6.0 | 936 | 0.9697 | 0.7545 |
|
| 71 |
+
| 0.2528 | 7.0 | 1092 | 1.1004 | 0.7690 |
|
| 72 |
+
| 0.2528 | 8.0 | 1248 | 1.1937 | 0.7726 |
|
| 73 |
+
| 0.2528 | 9.0 | 1404 | 1.3313 | 0.7726 |
|
| 74 |
+
| 0.1073 | 10.0 | 1560 | 1.3534 | 0.7726 |
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|