fine_tuning_llama_4
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the knkarthick/dialogsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.1296
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: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9863 | 1.0 | 78 | 1.1460 |
| 1.0109 | 2.0 | 156 | 1.1343 |
| 0.9011 | 3.0 | 234 | 1.1301 |
| 0.9703 | 4.0 | 312 | 1.1296 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Lxt115/fine_tuning_llama_3
Base model
meta-llama/Llama-2-7b-hf