metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/opt-350m
model-index:
- name: opt-350m_lora_lr0.005_bs10_epoch5_wd0.01
results: []
opt-350m_lora_lr0.005_bs10_epoch5_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: 3.8801
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: 0.005
- train_batch_size: 10
- eval_batch_size: 10
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 63 | 3.3912 |
| 3.5671 | 2.0 | 126 | 3.4671 |
| 3.5671 | 3.0 | 189 | 3.6533 |
| 3.3457 | 4.0 | 252 | 3.7318 |
| 3.1993 | 5.0 | 315 | 3.8801 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0