metadata
base_model: NousResearch/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: sawyer-llama-2
results: []
sawyer-llama-2
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: 1.6080
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3521 | 1.0 | 446 | 1.2259 |
| 1.4185 | 2.0 | 892 | 1.2080 |
| 1.1195 | 3.0 | 1338 | 1.2291 |
| 0.9606 | 4.0 | 1784 | 1.2634 |
| 0.7691 | 5.0 | 2230 | 1.3193 |
| 0.8449 | 6.0 | 2676 | 1.3843 |
| 0.6701 | 7.0 | 3122 | 1.4593 |
| 0.5451 | 8.0 | 3568 | 1.5175 |
| 0.5712 | 9.0 | 4014 | 1.5782 |
| 0.6186 | 10.0 | 4460 | 1.6080 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1