metadata
library_name: peft
license: apache-2.0
base_model: princeton-nlp/Sheared-LLaMA-1.3B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 148cf4a6-6c43-4aaa-ad9b-5dfd8672d14f
results: []
148cf4a6-6c43-4aaa-ad9b-5dfd8672d14f
This model is a fine-tuned version of princeton-nlp/Sheared-LLaMA-1.3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6123
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: 0.000215
- train_batch_size: 4
- eval_batch_size: 4
- seed: 150
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 1.2217 |
| 0.725 | 0.0586 | 500 | 0.7533 |
| 0.6878 | 0.1172 | 1000 | 0.6920 |
| 0.6522 | 0.1758 | 1500 | 0.6540 |
| 0.6207 | 0.2343 | 2000 | 0.6283 |
| 0.6161 | 0.2929 | 2500 | 0.6150 |
| 0.6196 | 0.3515 | 3000 | 0.6123 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1