sparse_llama_7b_refined_web_90p_2024-03-21
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6918
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 100
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
5.2955 | 0.01 | 25 | 5.1918 |
4.6783 | 0.02 | 50 | 4.6078 |
3.9425 | 0.02 | 75 | 3.9603 |
3.455 | 0.03 | 100 | 3.5515 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 17
Inference API (serverless) does not yet support model repos that contain custom code.
Model tree for thrunlab/sparse_llama_7b_refined_web_90p_2024-03-21
Base model
meta-llama/Llama-2-7b-chat-hf