llama3_8b_full_sft_ramzan
This model is a fine-tuned version of ramzanniaz331/llama3.1-8b-8192-v3 on the ramzan_5k_batch_1, the ramzan_5k_batch_2, the ramzan_openhermes, the ramzan_metamath and the ramzan_aya_urdu datasets.
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2.0
Training results
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 6