metadata
license: other
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dalio-handwritten-io-1.3b
results: []
dalio-handwritten-io-1.3b
This model is a fine-tuned version of facebook/opt-1.3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6172
- Accuracy: 0.0555
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6917 | 0.33 | 1 | 2.6680 | 0.0530 |
| 2.8435 | 0.67 | 2 | 2.6680 | 0.0530 |
| 2.7502 | 1.0 | 3 | 2.6172 | 0.0555 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1