metadata
base_model: huggyllama/llama-13b
library_name: peft
license: other
tags:
- generated_from_trainer
model-index:
- name: llama-13b_oasst1_l0.0002_32-8-8-8-8
results: []
llama-13b_oasst1_l0.0002_32-8-8-8-8
This model is a fine-tuned version of huggyllama/llama-13b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5069
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: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4264 | 0.0018 | 1 | 1.5699 |
| 1.4261 | 0.3392 | 187 | 1.2365 |
| 1.0708 | 0.6783 | 374 | 1.2308 |
| 1.2217 | 1.0175 | 561 | 1.2357 |
| 0.9791 | 1.3566 | 748 | 1.2991 |
| 0.9827 | 1.6958 | 935 | 1.2639 |
| 0.5563 | 2.0349 | 1122 | 1.3503 |
| 0.7603 | 2.3741 | 1309 | 1.3852 |
| 0.5553 | 2.7132 | 1496 | 1.4816 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1