metadata
license: apache-2.0
base_model: mnaylor/mega-base-wikitext
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: mega-base-multiple-choice-fp16-v1
results: []
mega-base-multiple-choice-fp16-v1
This model is a fine-tuned version of mnaylor/mega-base-wikitext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6932
- Accuracy: 0.5012
- Precision: 0.5017
- Recall: 0.3409
- F1: 0.4060
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: 0.001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 269 | 0.6933 | 0.4944 | 0.4649 | 0.0743 | 0.1281 |
| 0.6938 | 2.0 | 538 | 0.6932 | 0.4931 | 0.4910 | 0.3799 | 0.4284 |
| 0.6938 | 3.0 | 807 | 0.6932 | 0.5012 | 0.5017 | 0.3409 | 0.4060 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0