fine_tunning_0618
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the Salesforce/dialogstudio dataset. It achieves the following results on the evaluation set:
- Loss: 1.8667
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9019 | 1.0 | 55 | 1.9502 |
| 1.842 | 2.0 | 110 | 1.8866 |
| 1.7692 | 3.0 | 165 | 1.8745 |
| 1.7131 | 4.0 | 220 | 1.8679 |
| 1.7536 | 5.0 | 275 | 1.8660 |
| 1.6198 | 6.0 | 330 | 1.8661 |
| 1.6953 | 7.0 | 385 | 1.8667 |
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_tunning_llama_1
Base model
meta-llama/Llama-2-7b-hf