metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/opt-350m
model-index:
- name: opt-350m_lora_lr5e-05_bs4_epoch20_wd0.01
results: []
opt-350m_lora_lr5e-05_bs4_epoch20_wd0.01
This model is a fine-tuned version of facebook/opt-350m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4727
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9876 | 1.0 | 157 | 3.5158 |
| 3.5297 | 2.0 | 314 | 3.3975 |
| 3.4496 | 3.0 | 471 | 3.3883 |
| 3.3995 | 4.0 | 628 | 3.4068 |
| 3.3628 | 5.0 | 785 | 3.3689 |
| 3.3427 | 6.0 | 942 | 3.3728 |
| 3.2946 | 7.0 | 1099 | 3.3866 |
| 3.2283 | 8.0 | 1256 | 3.3931 |
| 3.2879 | 9.0 | 1413 | 3.4072 |
| 3.2 | 10.0 | 1570 | 3.4101 |
| 3.1534 | 11.0 | 1727 | 3.4101 |
| 3.0953 | 12.0 | 1884 | 3.4056 |
| 3.0796 | 13.0 | 2041 | 3.4390 |
| 3.0633 | 14.0 | 2198 | 3.4448 |
| 3.0459 | 15.0 | 2355 | 3.4703 |
| 2.9913 | 16.0 | 2512 | 3.4583 |
| 2.9959 | 17.0 | 2669 | 3.4659 |
| 2.9862 | 18.0 | 2826 | 3.4684 |
| 3.0424 | 19.0 | 2983 | 3.4734 |
| 2.9691 | 20.0 | 3140 | 3.4727 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0