zero-shot-prompting-llama-2-7b_readsum_Ver2
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: 1.6961
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6231 | 0.21 | 300 | 1.7653 |
| 1.4252 | 0.41 | 600 | 1.7429 |
| 1.3652 | 0.62 | 900 | 1.7273 |
| 1.4877 | 0.82 | 1200 | 1.7188 |
| 1.8531 | 1.03 | 1500 | 1.7113 |
| 1.6964 | 1.23 | 1800 | 1.7061 |
| 1.6873 | 1.44 | 2100 | 1.7011 |
| 1.7671 | 1.65 | 2400 | 1.6985 |
| 1.7008 | 1.85 | 2700 | 1.6961 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for bunbohue/zero-shot-prompting-llama-2-7b_readsum_Ver2
Base model
meta-llama/Llama-2-7b-hf