metadata
base_model: NousResearch/Llama-2-7b-hf
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: legal-document-summarization
results: []
pipeline_tag: summarization
language:
- en
legal-document-summarization
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: 1.2231
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2845 | 0.4 | 8 | 1.2406 |
| 1.2368 | 0.8 | 16 | 1.2264 |
| 1.0085 | 1.2 | 24 | 1.2255 |
| 0.9203 | 1.6 | 32 | 1.2244 |
| 0.9852 | 2.0 | 40 | 1.2231 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1