roberta-base-rte / README.md
Jeremiah Zhou
update model card README.md
9db0d4a
|
raw
history blame
2.04 kB
---
language:
- en
license: mit
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: roberta-base-rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.7581227436823105
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-rte
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6365
- Accuracy: 0.7581
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 156 | 0.7072 | 0.4729 |
| No log | 2.0 | 312 | 0.6958 | 0.5271 |
| No log | 3.0 | 468 | 0.6193 | 0.6462 |
| 0.6759 | 4.0 | 624 | 0.6046 | 0.7076 |
| 0.6759 | 5.0 | 780 | 0.6365 | 0.7581 |
| 0.6759 | 6.0 | 936 | 0.8975 | 0.7545 |
| 0.3194 | 7.0 | 1092 | 1.2031 | 0.7581 |
| 0.3194 | 8.0 | 1248 | 1.2942 | 0.7581 |
### Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1