metadata
license: other
base_model: facebook/opt-350m
tags:
- generated_from_trainer
model-index:
- name: langauage-model
results: []
langauage-model
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: 3.4264
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5452 | 1.0 | 1120 | 3.4734 |
| 3.5075 | 2.0 | 2240 | 3.4529 |
| 3.478 | 3.0 | 3360 | 3.4433 |
| 3.4807 | 4.0 | 4480 | 3.4370 |
| 3.4555 | 5.0 | 5600 | 3.4329 |
| 3.4554 | 6.0 | 6720 | 3.4302 |
| 3.4475 | 7.0 | 7840 | 3.4284 |
| 3.4466 | 8.0 | 8960 | 3.4273 |
| 3.4442 | 9.0 | 10080 | 3.4266 |
| 3.4442 | 10.0 | 11200 | 3.4264 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1