Hugging Face's logo

lesso16
/
bc9f91c2-4df9-4906-aee9-a2f067209d12

PEFT
Safetensors
bloom
axolotl
Generated from Trainer
Model card Files Community
bc9f91c2-4df9-4906-aee9-a2f067209d12 / README.md
lesso16's picture
lesso16
End of training
5e18728 verified
preview code
|
raw
history blame contribute delete
1.84 kB
metadata
library_name: peft
license: bigscience-bloom-rail-1.0
base_model: bigscience/bloom-560m
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: bc9f91c2-4df9-4906-aee9-a2f067209d12
    results: []

Built with Axolotl

bc9f91c2-4df9-4906-aee9-a2f067209d12

This model is a fine-tuned version of bigscience/bloom-560m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8665

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: 0.000216
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 160
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0002 1 1.2709
7.0419 0.0804 500 0.8665

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1