|
|
--- |
|
|
library_name: peft |
|
|
license: llama2 |
|
|
base_model: meta-llama/Llama-2-7b-chat-hf |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Llama2-Instruct-7B |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# Llama2-Instruct-7B |
|
|
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2191 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- num_epochs: 4 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 2.063 | 0.1144 | 50 | 1.8637 | |
|
|
| 1.3888 | 0.2288 | 100 | 0.8130 | |
|
|
| 0.4576 | 0.3432 | 150 | 0.3154 | |
|
|
| 0.3002 | 0.4577 | 200 | 0.2924 | |
|
|
| 0.285 | 0.5721 | 250 | 0.2795 | |
|
|
| 0.2711 | 0.6865 | 300 | 0.2652 | |
|
|
| 0.2598 | 0.8009 | 350 | 0.2550 | |
|
|
| 0.2469 | 0.9153 | 400 | 0.2471 | |
|
|
| 0.2427 | 1.0297 | 450 | 0.2420 | |
|
|
| 0.239 | 1.1442 | 500 | 0.2386 | |
|
|
| 0.2361 | 1.2586 | 550 | 0.2361 | |
|
|
| 0.2332 | 1.3730 | 600 | 0.2345 | |
|
|
| 0.2308 | 1.4874 | 650 | 0.2324 | |
|
|
| 0.2301 | 1.6018 | 700 | 0.2307 | |
|
|
| 0.228 | 1.7162 | 750 | 0.2295 | |
|
|
| 0.228 | 1.8307 | 800 | 0.2285 | |
|
|
| 0.2277 | 1.9451 | 850 | 0.2276 | |
|
|
| 0.2257 | 2.0595 | 900 | 0.2269 | |
|
|
| 0.2251 | 2.1739 | 950 | 0.2259 | |
|
|
| 0.223 | 2.2883 | 1000 | 0.2248 | |
|
|
| 0.2236 | 2.4027 | 1050 | 0.2241 | |
|
|
| 0.221 | 2.5172 | 1100 | 0.2234 | |
|
|
| 0.2211 | 2.6316 | 1150 | 0.2234 | |
|
|
| 0.2214 | 2.7460 | 1200 | 0.2224 | |
|
|
| 0.2205 | 2.8604 | 1250 | 0.2219 | |
|
|
| 0.2199 | 2.9748 | 1300 | 0.2214 | |
|
|
| 0.2193 | 3.0892 | 1350 | 0.2210 | |
|
|
| 0.219 | 3.2037 | 1400 | 0.2206 | |
|
|
| 0.2191 | 3.3181 | 1450 | 0.2203 | |
|
|
| 0.2185 | 3.4325 | 1500 | 0.2198 | |
|
|
| 0.2169 | 3.5469 | 1550 | 0.2197 | |
|
|
| 0.2176 | 3.6613 | 1600 | 0.2194 | |
|
|
| 0.2171 | 3.7757 | 1650 | 0.2192 | |
|
|
| 0.2148 | 3.8902 | 1700 | 0.2191 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.50.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.1 |
