metadata
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: NousResearch/Llama-2-7b-hf
model-index:
- name: llama-2-7b-news-gen
results: []
llama-2-7b-news-gen
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3099
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7847 | 0.41 | 25 | 1.7056 |
| 1.6833 | 0.82 | 50 | 1.6216 |
| 1.6116 | 1.23 | 75 | 1.5565 |
| 1.5546 | 1.64 | 100 | 1.4979 |
| 1.5453 | 2.05 | 125 | 1.4493 |
| 1.433 | 2.46 | 150 | 1.3999 |
| 1.4277 | 2.87 | 175 | 1.3624 |
| 1.3405 | 3.28 | 200 | 1.3303 |
| 1.3358 | 3.69 | 225 | 1.3099 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1