Hugging Face's logo

tttx
/
problem0_model

PEFT
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Community
problem0_model / README.md
aadityap's picture
aadityap
End of training
c8de949 verified
preview code
|
raw
history blame contribute delete
1.71 kB
metadata
base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
datasets:
  - tttx/problem0_data
library_name: peft
license: llama3.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: problem0_model
    results: []

problem0_model

This model is a fine-tuned version of barc0/Llama-3.1-ARC-Potpourri-Transduction-8B on the tttx/problem0_data dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3351

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
0.0 1.0 250 0.3861
0.0001 2.0 500 0.3351

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3