Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
timelist7baugustdata
This model is a fine-tuned version of TheBloke/Llama-2-7B-fp16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9871
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: 0.0003
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 350
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3921 | 1.79 | 50 | 1.2835 |
| 0.9999 | 3.58 | 100 | 1.0558 |
| 0.8431 | 5.38 | 150 | 0.9720 |
| 0.7712 | 7.17 | 200 | 0.9703 |
| 0.7167 | 8.96 | 250 | 0.9683 |
| 0.6836 | 10.75 | 300 | 0.9829 |
| 0.6672 | 12.54 | 350 | 0.9871 |
Framework versions
- PEFT 0.11.1
- Transformers 4.38.2
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for marcus2000/timelist7baugustdata
Base model
TheBloke/Llama-2-7B-fp16