Hugging Face's logo

tuhinatripathi
/
gemma2b-5kdata

PEFT
TensorBoard
Safetensors
trl
sft
unsloth
Generated from Trainer
Model card Files Metrics Community
gemma2b-5kdata / README.md
tuhinatripathi's picture
tuhinatripathi
tuhinatripathi/gemma2b-lpr-5kdata
a0a25a1 verified
preview code
|
raw
history blame
1.49 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - unsloth
  - generated_from_trainer
base_model: unsloth/gemma-2b-bnb-4bit
model-index:
  - name: gemma2b-5kdata
    results: []

gemma2b-5kdata

This model is a fine-tuned version of unsloth/gemma-2b-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9120

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: 1
  • eval_batch_size: 8
  • seed: 3407
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 135
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.0129 1.0 1250 0.9120

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1