falcon-7b-instruct-FT-LoRA-8bit-test1

This model is a fine-tuned version of tiiuae/falcon-7b-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9608

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.5166	0.85	200	1.5187
1.0449	1.71	400	1.1572
0.6828	2.56	600	0.9608

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu117
• Datasets 2.13.0
• Tokenizers 0.13.3