metadata
license: other
library_name: peft
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
base_model: facebook/opt-125m
model-index:
- name: opt-125m-pattern-based_finetuning_with_lora-mnli-d1_fs3
results: []
opt-125m-pattern-based_finetuning_with_lora-mnli-d1_fs3
This model is a fine-tuned version of facebook/opt-125m on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.7548
- Accuracy: 0.5169
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6168 | 1.0 | 1 | 0.7546 | 0.5166 |
| 0.5866 | 2.0 | 2 | 0.7547 | 0.5166 |
| 0.5673 | 3.0 | 3 | 0.7548 | 0.5166 |
| 0.6285 | 4.0 | 4 | 0.7548 | 0.5169 |
| 0.5663 | 5.0 | 5 | 0.7548 | 0.5169 |
Framework versions
- PEFT 0.7.1.dev0
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0