klab-tourbillon-3.5

This model is a fine-tuned version of tiiuae/falcon-rw-1b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.6792

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: 3e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.3557	0.1681	10	2.2193
2.1739	0.3361	20	2.0503
1.9537	0.5042	30	1.9039
1.8191	0.6723	40	1.7825
1.6843	0.8403	50	1.6792

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1