roberta-base-finetuned-swag-apollo_adamw

This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4426
• Accuracy: 0.8304

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.APOLLO_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8283	1.0	1150	0.5658	0.7846
0.7437	2.0	2300	0.5112	0.8045
0.6705	3.0	3450	0.4706	0.8179
0.6095	4.0	4600	0.4508	0.8234
0.5894	5.0	5750	0.4426	0.8304

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2