Hugging Face's logo

sudopro
/
test

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
Community
test / README.md
lesso13's picture
lesso13
End of training
5c85075 verified
preview code
|
raw
history blame contribute delete
2.22 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM-360M
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 7d22b830-e6da-41fb-bf30-36a9b0a64fed
    results: []

Built with Axolotl

7d22b830-e6da-41fb-bf30-36a9b0a64fed

This model is a fine-tuned version of unsloth/SmolLM-360M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5199

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: 0.000213
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0017 1 2.2995
1.9642 0.0842 50 1.8588
1.8211 0.1684 100 1.6553
1.5456 0.2525 150 1.5935
1.7312 0.3367 200 1.5831
1.6234 0.4209 250 1.5299
1.8022 0.5051 300 1.5193
1.3362 0.5892 350 1.5256
1.4218 0.6734 400 1.5206
1.5863 0.7576 450 1.5199

Framework versions

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