Hugging Face's logo

simon-muenker
/
TWON-Agent-OSN-Post-en

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
TWON-Agent-OSN-Post-en / README.md
simon-muenker's picture
simon-muenker
Model save
ce287c7 verified
preview code
|
raw
history blame contribute delete
1.78 kB
metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: TWON-Agent-OSN-Post-en
    results: []

TWON-Agent-OSN-Post-en

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8993

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss
1.6374 1.1429 200 1.1784
1.2494 2.2857 400 1.0614
1.1835 3.4286 600 0.9980
1.1382 4.5714 800 0.9540
1.1128 5.7143 1000 0.9240
1.0937 6.8571 1200 0.9065
1.0809 8.0 1400 0.8993

Framework versions

  • PEFT 0.12.0
  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0