metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/opt-125m
metrics:
- accuracy
model-index:
- name: opt-125m-finetuned-mnli
results: []
opt-125m-finetuned-mnli
This model is a fine-tuned version of facebook/opt-125m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7247
- Accuracy: 0.5061
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 0.7219 | 0.4863 |
| No log | 2.0 | 2 | 0.7217 | 0.4868 |
| No log | 3.0 | 3 | 0.7214 | 0.4860 |
| No log | 4.0 | 4 | 0.7212 | 0.4851 |
| No log | 5.0 | 5 | 0.7211 | 0.4840 |
| No log | 6.0 | 6 | 0.7210 | 0.4833 |
| No log | 7.0 | 7 | 0.7209 | 0.4824 |
| No log | 8.0 | 8 | 0.7208 | 0.4827 |
| No log | 9.0 | 9 | 0.7207 | 0.4827 |
| No log | 10.0 | 10 | 0.7207 | 0.4824 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1