Llama2_7B_chat_arithmetic
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: 1.0525
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: 0.002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9153 | 0.2 | 94 | 1.6186 |
| 0.5407 | 0.4 | 188 | 2.4259 |
| 0.6913 | 0.6 | 282 | 1.3859 |
| 0.8195 | 0.8 | 376 | 1.0525 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
Model tree for Jukaboo/Llama2_7B_chat_arithmetic
Base model
meta-llama/Llama-2-7b-chat-hf