Edit model card

Falcon-Summarization

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

  • Loss: 2.5006

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: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.4431 0.2 200 2.5148
2.376 0.4 400 2.5112
2.4269 0.6 600 2.4901
2.368 0.8 800 2.4763
2.372 1.0 1000 2.4684
2.0904 1.2 1200 2.5018
2.099 1.41 1400 2.5137
2.0482 1.61 1600 2.4993
1.9974 1.81 1800 2.5006

Framework versions

  • PEFT 0.10.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2
Downloads last month
6
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for pkbiswas/Falcon-7b-Summarization-QLoRa

Adapter
(66)
this model

Dataset used to train pkbiswas/Falcon-7b-Summarization-QLoRa