llama2_knowledge_v4.1
This model is a fine-tuned version of ziqingyang/chinese-llama-2-7b on an unknown 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: 6
- eval_batch_size: 6
- seed: 42
- distributed_type: multi-GPU
- num_devices: 5
- gradient_accumulation_steps: 4
- total_train_batch_size: 120
- total_eval_batch_size: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 7
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1