LLaMA3_AAID_mixed_train
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the AAID_mixed dataset. It achieves the following results on the evaluation set:
- Loss: 0.0002
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.4761 | 0.2023 | 200 | 0.4195 |
0.3788 | 0.4047 | 400 | 0.3681 |
0.3038 | 0.6070 | 600 | 0.2551 |
0.1763 | 0.8093 | 800 | 0.1140 |
0.0719 | 1.0116 | 1000 | 0.0454 |
0.0265 | 1.2140 | 1200 | 0.0216 |
0.0137 | 1.4163 | 1400 | 0.0099 |
0.007 | 1.6186 | 1600 | 0.0052 |
0.0036 | 1.8209 | 1800 | 0.0023 |
0.0015 | 2.0233 | 2000 | 0.0010 |
0.0006 | 2.2256 | 2200 | 0.0005 |
0.0004 | 2.4279 | 2400 | 0.0003 |
0.0002 | 2.6302 | 2600 | 0.0002 |
0.0002 | 2.8326 | 2800 | 0.0002 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Unable to determine this model’s pipeline type. Check the
docs
.