rccmsu's picture
Update README.md
eea1bce verified
|
raw
history blame
1.09 kB
metadata
license: llama2
language:
  - ru
metrics:
  - accuracy

ruadapt_llama2_7b_v0.1

This model is a fine-tuned (embeddings, lm head) version of TheBloke/Llama-2-7B-fp16 on the Russian dataset (33GB). It achieves the following results on the evaluation set:

  • Loss: 2.7569
  • Accuracy: 0.4617

Model description

Russian adaptation of LLaMa-2-7B by replacing the tokenizer. Paper: Tikhomirov M., Chernyshev D. Impact of Tokenization on LLaMa Russian Adaptation //arXiv preprint arXiv:2312.02598. – 2023.

Intended uses & limitations

LLAMA 2 COMMUNITY LICENSE AGREEMENT

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 16
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 192
  • total_eval_batch_size: 96
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
  • lr_scheduler_type: linear
  • num_epochs: 2.0

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1