Hugging Face's logo

yuriachermann
/
Not-so-bright-AGI-v1

Question Answering
PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Not-so-bright-AGI-v1 / README.md
yuriachermann's picture
yuriachermann
Update README.md
da48c08 verified
preview code
|
raw
history blame
1.77 kB
metadata
license: gemma
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
  - ipex
  - GPU Max 1100
base_model: google/gemma-2b
datasets:
  - generator
model-index:
  - name: Not-so-bright-AGI-v1
    results: []

Not-so-bright-AGI-v1

This model is a fine-tuned version of google/gemma-2b on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1509

Model description

More information needed

Intended uses & limitations

More information needed

Training Hardware

This model was trained using Intel(R) Data Center GPU Max 1100

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 593

Training results

Training Loss Epoch Step Validation Loss
2.863 0.8197 100 2.5317
2.4375 1.6393 200 2.3196
2.3075 2.4590 300 2.2222
2.2199 3.2787 400 2.1742
2.1956 4.0984 500 2.1509

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.0.1a0+cxx11.abi
  • Datasets 2.19.0
  • Tokenizers 0.19.1