Llama-2-7b-chat-hf-ark-ft
This model is a fine-tuned version of keylazy/Llama-2-7b-chat-hf-ark on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1845
- Accuracy: 0.9435
- Precision: 0.9435
- Recall: 0.9435
- F1: 0.9434
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.1635 | 0.5 | 3828 | 0.1612 | 0.9267 | 0.9270 | 0.9267 | 0.9267 |
0.1302 | 1.0 | 7656 | 0.1330 | 0.9424 | 0.9429 | 0.9424 | 0.9423 |
0.0352 | 1.5 | 11484 | 0.1845 | 0.9435 | 0.9435 | 0.9435 | 0.9434 |
0.0316 | 2.0 | 15312 | 0.1851 | 0.9428 | 0.9429 | 0.9428 | 0.9428 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 14