metadata
library_name: peft
license: apache-2.0
base_model: openlm-research/open_llama_7b
tags:
- generated_from_trainer
model-index:
- name: lora_num4
results: []
lora_num4
This model is a fine-tuned version of openlm-research/open_llama_7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.6688
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.5783 | 1.0 | 37 | 9.3113 |
| 9.6658 | 2.0 | 74 | 8.7152 |
| 9.2757 | 3.0 | 111 | 8.5206 |
| 9.1503 | 4.0 | 148 | 8.5015 |
| 9.2431 | 5.0 | 185 | 8.6005 |
| 9.3486 | 6.0 | 222 | 8.6688 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1