metadata
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: Llama2_AAID_new_mixed_train_final_2
results: []
Llama2_AAID_new_mixed_train_final_2
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the AAID_new_mixed dataset. It achieves the following results on the evaluation set:
- Loss: 0.5147
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: 32
- 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
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5222 | 0.0438 | 40 | 0.5364 |
| 0.3981 | 0.0875 | 80 | 0.5547 |
| 0.3297 | 0.1313 | 120 | 0.5276 |
| 0.3131 | 0.1750 | 160 | 0.5312 |
| 0.3049 | 0.2188 | 200 | 0.5147 |
| 0.2906 | 0.2625 | 240 | 0.5208 |
| 0.2862 | 0.3063 | 280 | 0.5313 |
| 0.2799 | 0.3500 | 320 | 0.5454 |
| 0.2748 | 0.3938 | 360 | 0.5483 |
| 0.2613 | 0.4375 | 400 | 0.5433 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1