Hugging Face's logo

datha29
/
LLama-translation

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
LLama-translation / README.md
datha29's picture
datha29
End of training
6b99c3d verified
preview code
|
raw
history blame contribute delete
1.33 kB
metadata
license: llama2
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/Llama-2-7B-GPTQ
model-index:
  - name: LLama-translation
    results: []

LLama-translation

This model is a fine-tuned version of TheBloke/Llama-2-7B-GPTQ on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.3955
  • eval_runtime: 179.6096
  • eval_samples_per_second: 9.565
  • eval_steps_per_second: 1.197
  • epoch: 2.0
  • step: 774

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: 40
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 1285
  • mixed_precision_training: Native AMP

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.3
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2