Llama-3.2-3B-lr7.5e-05e1r256dr0
This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the ss-train 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: 7.5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for Tung177/Llama-3.2-3B-4bit-vi-sentence-simplification-adapter
Base model
meta-llama/Llama-3.2-3B