metadata
base_model: NousResearch/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: out
results: []
out
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9443
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 3
- total_eval_batch_size: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0254 | 0.03 | 1 | 3.0959 |
| 3.2648 | 0.06 | 2 | 3.0959 |
| 3.0345 | 0.12 | 4 | 1.6018 |
| 1.4912 | 0.18 | 6 | 1.4104 |
| 1.4298 | 0.24 | 8 | 1.2483 |
| 1.2217 | 0.29 | 10 | 1.1785 |
| 1.1975 | 0.35 | 12 | 1.1200 |
| 1.1377 | 0.41 | 14 | 1.0922 |
| 1.0991 | 0.47 | 16 | 1.0625 |
| 0.9783 | 0.53 | 18 | 1.0422 |
| 1.0558 | 0.59 | 20 | 1.0100 |
| 0.9894 | 0.65 | 22 | 0.9902 |
| 0.9677 | 0.71 | 24 | 0.9780 |
| 0.9782 | 0.76 | 26 | 0.9679 |
| 0.9944 | 0.82 | 28 | 0.9595 |
| 0.9245 | 0.88 | 30 | 0.9509 |
| 0.9676 | 0.94 | 32 | 0.9468 |
| 1.0653 | 1.0 | 34 | 0.9443 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1