CuATR-falcon7b-v1

This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.0246
• Accuracy: 0.5
• F1: 0.6667

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
3.8889	0.92	3	3.0637	0.5	0.6667
5.8673	1.85	6	3.0774	0.5	0.6667
3.9181	2.77	9	3.0334	0.5	0.6667
3.8567	4.0	13	3.0286	0.5	0.6667
1.9671	4.92	16	3.0071	0.5	0.6667
1.9456	5.85	19	3.0315	0.5	0.6667
5.8213	6.46	21	3.0246	0.5	0.6667

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0