Llama-2-7b-hf-wiki-no-group-by-length_r_64_alpha_16
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: 1.2454
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.288 | 0.3 | 71 | 1.2669 |
| 1.2518 | 0.61 | 142 | 1.2545 |
| 1.2438 | 0.91 | 213 | 1.2476 |
| 1.1978 | 1.21 | 284 | 1.2481 |
| 1.2036 | 1.51 | 355 | 1.2481 |
| 1.1938 | 1.82 | 426 | 1.2454 |
| 1.1833 | 2.12 | 497 | 1.2517 |
| 1.1437 | 2.42 | 568 | 1.2538 |
| 1.1469 | 2.73 | 639 | 1.2537 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3
Model tree for dhmeltzer/Llama-2-7b-hf-wiki30k-no-group-by-length_r_64_alpha_16
Base model
meta-llama/Llama-2-7b-hf