metadata
library_name: peft
license: other
base_model: huggyllama/llama-7b
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 8915c3ad-e4aa-446e-aaf0-b7df16a9dbea
results: []
8915c3ad-e4aa-446e-aaf0-b7df16a9dbea
This model is a fine-tuned version of huggyllama/llama-7b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7314
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: 0.000203
- train_batch_size: 4
- eval_batch_size: 4
- seed: 30
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0003 | 1 | 1.2225 |
| 0.7859 | 0.0168 | 50 | 0.8936 |
| 0.7025 | 0.0336 | 100 | 0.8295 |
| 0.6255 | 0.0504 | 150 | 0.8096 |
| 0.6083 | 0.0672 | 200 | 0.7758 |
| 0.621 | 0.0840 | 250 | 0.7691 |
| 0.6135 | 0.1008 | 300 | 0.7583 |
| 0.5942 | 0.1175 | 350 | 0.7404 |
| 0.5733 | 0.1343 | 400 | 0.7354 |
| 0.6325 | 0.1511 | 450 | 0.7292 |
| 0.6317 | 0.1679 | 500 | 0.7314 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1