metadata
license: other
base_model: facebook/opt-1.3b
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: opt-1.3b-snli
results: []
opt-1.3b-snli
This model is a fine-tuned version of facebook/opt-1.3b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0994
- Accuracy: 0.7705
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2946 | 1.0 | 4292 | 0.2449 | 0.9149 |
| 0.1879 | 2.0 | 8584 | 0.2540 | 0.9172 |
| 0.0895 | 3.0 | 12876 | 0.3316 | 0.9172 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0