mega-base-multiple-choice-fp16-v2

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: 0.5010
• Precision: 0.5010
• Recall: 0.4964
• F1: 0.4987

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: 0.005
• train_batch_size: 1024
• eval_batch_size: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 24000
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	34	0.6931	0.5021	0.5021	0.5076	0.5048
No log	2.0	68	0.6932	0.5050	0.5049	0.5102	0.5076
No log	3.0	102	0.6932	0.5010	0.5010	0.4964	0.4987

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0