metadata
base_model: meta-llama/Llama-2-7b-chat-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0380
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: 2.5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5462 | 0.72 | 100 | 1.5099 |
| 1.0012 | 1.45 | 200 | 1.1049 |
| 0.8908 | 2.17 | 300 | 0.9713 |
| 0.8156 | 2.9 | 400 | 0.9004 |
| 0.6787 | 3.62 | 500 | 0.8666 |
| 0.5238 | 4.35 | 600 | 0.8536 |
| 0.4373 | 5.07 | 700 | 0.8734 |
| 0.4224 | 5.8 | 800 | 0.8725 |
| 0.2836 | 6.52 | 900 | 0.9276 |
| 0.2222 | 7.25 | 1000 | 0.9700 |
| 0.2388 | 7.97 | 1100 | 0.9690 |
| 0.2064 | 8.7 | 1200 | 1.0128 |
| 0.1713 | 9.42 | 1300 | 1.0380 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1