metadata
base_model: facebook/opt-350m
library_name: peft
license: other
tags:
- base_model:adapter:facebook/opt-350m
- lora
- transformers
model-index:
- name: opt-350m-hate-classifier
results: []
opt-350m-hate-classifier
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: 0.6381
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6757 | 1.0 | 450 | 0.4493 |
| 0.4331 | 2.0 | 900 | 0.4464 |
| 0.0726 | 3.0 | 1350 | 0.6210 |
| 0.0006 | 4.0 | 1800 | 0.6127 |
| 0.3316 | 5.0 | 2250 | 0.6381 |
Framework versions
- PEFT 0.17.1
- Transformers 4.46.3
- Pytorch 2.8.0+cu128
- Datasets 2.17.0
- Tokenizers 0.20.0