Edit model card

falcon-7b-code-python

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

  • Loss: 1.1486

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: 6
  • eval_batch_size: 6
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 24
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.3986 0.3183 30 1.4874
1.3762 0.6366 60 1.4038
1.2544 0.9549 90 1.3065
1.1233 1.2732 120 1.2405
1.1611 1.5915 150 1.1918
1.1243 1.9098 180 1.1603
1.0911 2.2281 210 1.1504
1.1027 2.5464 240 1.1489
1.1615 2.8647 270 1.1486

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
3
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for amztheory/falcon-7b-code-python

Adapter
(66)
this model