metadata
base_model: meta-llama/Llama-2-13b-hf
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Llama-2-13b-lr-5e-5
results: []
Llama-2-13b-lr-5e-5
This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1454
- Accuracy: 0.2150
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-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.955 | 0.37 | 10 | 0.9061 | 0.2182 |
| 0.8899 | 0.74 | 20 | 0.8734 | 0.2196 |
| 0.879 | 1.11 | 30 | 0.9091 | 0.2174 |
| 0.3295 | 1.48 | 40 | 0.9803 | 0.2173 |
| 0.3711 | 1.85 | 50 | 0.9820 | 0.2174 |
| 0.2927 | 2.22 | 60 | 1.0270 | 0.2153 |
| 0.1703 | 2.59 | 70 | 1.0966 | 0.2131 |
| 0.2011 | 2.96 | 80 | 1.1488 | 0.2145 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0