Llama2-7B-lora-r-32-generic-step-200-lr-1e-5-labels_40.0
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7152
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.4728 | 0.3653 | 20 | 5.5435 |
| 4.9739 | 0.7306 | 40 | 4.8172 |
| 4.2871 | 1.0959 | 60 | 4.3050 |
| 4.0458 | 1.4612 | 80 | 4.0568 |
| 3.9287 | 1.8265 | 100 | 3.9036 |
| 3.7825 | 2.1918 | 120 | 3.8103 |
| 3.6987 | 2.5571 | 140 | 3.7566 |
| 3.7338 | 2.9224 | 160 | 3.7278 |
| 3.6426 | 3.2877 | 180 | 3.7169 |
| 3.6798 | 3.6530 | 200 | 3.7152 |
Framework versions
- PEFT 0.15.2
- Transformers 4.45.2
- Pytorch 2.5.0+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Siqi-Hu/Llama2-7B-lora-r-32-generic-step-200-lr-1e-5-labels_40.0
Base model
meta-llama/Llama-2-7b-hf