ko-opt-350m
This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3817
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8648 | 0.1902 | 500 | 2.7538 |
| 2.4309 | 0.3804 | 1000 | 2.5691 |
| 1.9572 | 0.5706 | 1500 | 2.4733 |
| 1.788 | 0.7608 | 2000 | 2.4221 |
| 1.7197 | 0.9510 | 2500 | 2.3817 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for thisisHJLee/ko-opt-350m
Base model
facebook/opt-350m