Commit
•
3c7d310
1
Parent(s):
a8d7332
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- glue
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: distilbert-mrpc
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: glue
|
| 18 |
+
type: glue
|
| 19 |
+
args: mrpc
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.8480392156862745
|
| 24 |
+
- name: F1
|
| 25 |
+
type: f1
|
| 26 |
+
value: 0.8934707903780068
|
| 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 |
+
# distilbert-mrpc
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.6783
|
| 37 |
+
- Accuracy: 0.8480
|
| 38 |
+
- F1: 0.8935
|
| 39 |
+
|
| 40 |
+
## Model description
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Intended uses & limitations
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training and evaluation data
|
| 49 |
+
|
| 50 |
+
More information needed
|
| 51 |
+
|
| 52 |
+
## Training procedure
|
| 53 |
+
|
| 54 |
+
### Training hyperparameters
|
| 55 |
+
|
| 56 |
+
The following hyperparameters were used during training:
|
| 57 |
+
- learning_rate: 5e-05
|
| 58 |
+
- train_batch_size: 8
|
| 59 |
+
- eval_batch_size: 8
|
| 60 |
+
- seed: 42
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- num_epochs: 3.0
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 69 |
+
| 0.5916 | 0.22 | 100 | 0.5676 | 0.7157 | 0.8034 |
|
| 70 |
+
| 0.5229 | 0.44 | 200 | 0.4534 | 0.7770 | 0.8212 |
|
| 71 |
+
| 0.5055 | 0.65 | 300 | 0.4037 | 0.8137 | 0.8762 |
|
| 72 |
+
| 0.4597 | 0.87 | 400 | 0.3706 | 0.8407 | 0.8893 |
|
| 73 |
+
| 0.4 | 1.09 | 500 | 0.4590 | 0.8113 | 0.8566 |
|
| 74 |
+
| 0.3498 | 1.31 | 600 | 0.4196 | 0.8554 | 0.8974 |
|
| 75 |
+
| 0.2916 | 1.53 | 700 | 0.4606 | 0.8554 | 0.8933 |
|
| 76 |
+
| 0.3309 | 1.74 | 800 | 0.5162 | 0.8578 | 0.9027 |
|
| 77 |
+
| 0.3788 | 1.96 | 900 | 0.3911 | 0.8529 | 0.8980 |
|
| 78 |
+
| 0.2059 | 2.18 | 1000 | 0.5842 | 0.8554 | 0.8995 |
|
| 79 |
+
| 0.1595 | 2.4 | 1100 | 0.5701 | 0.8578 | 0.8975 |
|
| 80 |
+
| 0.1205 | 2.61 | 1200 | 0.6905 | 0.8407 | 0.8889 |
|
| 81 |
+
| 0.174 | 2.83 | 1300 | 0.6783 | 0.8480 | 0.8935 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.15.0
|
| 87 |
+
- Pytorch 1.10.1
|
| 88 |
+
- Datasets 1.17.0
|
| 89 |
+
- Tokenizers 0.10.3
|