philimon's picture
End of training
c24fa9e verified
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: PY007/TinyLlama-1.1B-Chat-v0.3
model-index:
  - name: TinyLlama-gsm8k-math
    results: []

TinyLlama-gsm8k-math

This model is a fine-tuned version of PY007/TinyLlama-1.1B-Chat-v0.3 on the None dataset.

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: 5
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.0
  • Pytorch 2.1.2
  • Datasets 2.16.1
  • Tokenizers 0.15.1