metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: llama_7b_hf_relu_refined_web_relu_2024-03-27
results: []
llama_7b_hf_relu_refined_web_relu_2024-03-27
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6599
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: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.5817 | 0.01 | 25 | 9.2314 |
| 7.8754 | 0.02 | 50 | 7.6756 |
| 6.6513 | 0.02 | 75 | 6.5579 |
| 5.5276 | 0.03 | 100 | 5.4724 |
| 4.8802 | 0.04 | 125 | 4.7672 |
| 4.1435 | 0.05 | 150 | 4.2747 |
| 3.7831 | 0.06 | 175 | 3.9269 |
| 3.6802 | 0.06 | 200 | 3.6937 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.2