metadata
license: other
base_model: meta-llama/Llama-2-7b-hf
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: hyporadise
results: []
LLaMa-2-Hyporadise-pre-trained
Contributors: Yen-Ting Lin, Huck Yang
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the hyporadise dataset. It achieves the following results on the evaluation set:
- Loss: 0.3419
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3436 | 0.21 | 100 | 0.3495 |
| 0.3306 | 0.42 | 200 | 0.3352 |
| 0.3417 | 0.63 | 300 | 0.3245 |
| 0.3154 | 0.84 | 400 | 0.3160 |
| 0.1577 | 1.05 | 500 | 0.3239 |
| 0.159 | 1.26 | 600 | 0.3230 |
| 0.1493 | 1.48 | 700 | 0.3176 |
| 0.1498 | 1.69 | 800 | 0.3158 |
| 0.147 | 1.9 | 900 | 0.3104 |
| 0.0583 | 2.11 | 1000 | 0.3452 |
| 0.0547 | 2.32 | 1100 | 0.3395 |
| 0.0589 | 2.53 | 1200 | 0.3417 |
| 0.0593 | 2.74 | 1300 | 0.3414 |
| 0.0624 | 2.95 | 1400 | 0.3420 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2