metadata
license: other
base_model: facebook/opt-125m
tags:
- generated_from_trainer
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: 0.8182
- Accuracy: 0.5287
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 | 1.0643 | 0.5197 |
| No log | 2.0 | 2 | 1.0065 | 0.5196 |
| No log | 3.0 | 3 | 0.8588 | 0.5191 |
| No log | 4.0 | 4 | 0.7744 | 0.5215 |
| No log | 5.0 | 5 | 0.7629 | 0.5223 |
| No log | 6.0 | 6 | 0.7726 | 0.5260 |
| No log | 7.0 | 7 | 0.7934 | 0.5278 |
| No log | 8.0 | 8 | 0.8182 | 0.5287 |
| No log | 9.0 | 9 | 0.8379 | 0.5278 |
| No log | 10.0 | 10 | 0.8506 | 0.5257 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1