metadata
base_model: nghuyong/ernie-2.0-large-en
tags:
- generated_from_trainer
metrics:
- spearmanr
model-index:
- name: ernie-2.0-large-en-finetuned-stsb
results: []
ernie-2.0-large-en-finetuned-stsb
This model is a fine-tuned version of nghuyong/ernie-2.0-large-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3323
- Pearson: 0.9239
- Spearmanr: 0.9222
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|---|---|---|---|---|---|
| No log | 1.0 | 360 | 0.4713 | 0.9092 | 0.9111 |
| 0.5167 | 2.0 | 720 | 0.4516 | 0.9180 | 0.9179 |
| 0.2 | 3.0 | 1080 | 0.3402 | 0.9238 | 0.9211 |
| 0.2 | 4.0 | 1440 | 0.3452 | 0.9238 | 0.9226 |
| 0.1002 | 5.0 | 1800 | 0.3323 | 0.9239 | 0.9222 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2