Jeremiah Zhou
commited on
Commit
·
180bfeb
1
Parent(s):
7a72f2d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- glue
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: roberta-base-qqp
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: glue
|
| 18 |
+
type: glue
|
| 19 |
+
args: qqp
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.9148899332179075
|
| 24 |
+
- name: F1
|
| 25 |
+
type: f1
|
| 26 |
+
value: 0.8858062589187933
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# roberta-base-qqp
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.5647
|
| 37 |
+
- Accuracy: 0.9149
|
| 38 |
+
- F1: 0.8858
|
| 39 |
+
- Combined Score: 0.9003
|
| 40 |
+
|
| 41 |
+
## Model description
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training and evaluation data
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Training procedure
|
| 54 |
+
|
| 55 |
+
### Training hyperparameters
|
| 56 |
+
|
| 57 |
+
The following hyperparameters were used during training:
|
| 58 |
+
- learning_rate: 2e-05
|
| 59 |
+
- train_batch_size: 16
|
| 60 |
+
- eval_batch_size: 8
|
| 61 |
+
- seed: 42
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- lr_scheduler_warmup_ratio: 0.06
|
| 65 |
+
- num_epochs: 10.0
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|
| 70 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:--------------:|
|
| 71 |
+
| 0.2751 | 1.0 | 22741 | 0.3057 | 0.8905 | 0.8512 | 0.8709 |
|
| 72 |
+
| 0.2443 | 2.0 | 45482 | 0.2530 | 0.9005 | 0.8710 | 0.8857 |
|
| 73 |
+
| 0.2157 | 3.0 | 68223 | 0.2643 | 0.9070 | 0.8769 | 0.8919 |
|
| 74 |
+
| 0.1838 | 4.0 | 90964 | 0.2806 | 0.9109 | 0.8815 | 0.8962 |
|
| 75 |
+
| 0.146 | 5.0 | 113705 | 0.3277 | 0.9113 | 0.8809 | 0.8961 |
|
| 76 |
+
| 0.1262 | 6.0 | 136446 | 0.3939 | 0.9113 | 0.8812 | 0.8962 |
|
| 77 |
+
| 0.0867 | 7.0 | 159187 | 0.4435 | 0.9153 | 0.8867 | 0.9010 |
|
| 78 |
+
| 0.0757 | 8.0 | 181928 | 0.4812 | 0.9147 | 0.8844 | 0.8996 |
|
| 79 |
+
| 0.0479 | 9.0 | 204669 | 0.5081 | 0.9151 | 0.8871 | 0.9011 |
|
| 80 |
+
| 0.0379 | 10.0 | 227410 | 0.5647 | 0.9149 | 0.8858 | 0.9003 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.20.0.dev0
|
| 86 |
+
- Pytorch 1.11.0+cu113
|
| 87 |
+
- Datasets 2.1.0
|
| 88 |
+
- Tokenizers 0.12.1
|