finetuning-sentiment-longform-4500

This model is a fine-tuned version of kiddothe2b/longformer-mini-1024 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4095
• Accuracy: 0.8168
• F1: 0.8025

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5864	1.0	563	0.4922	0.7614	0.7711
0.4896	2.0	1126	0.4363	0.8125	0.8120
0.4403	3.0	1689	0.4095	0.8168	0.8025

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3