llama2_13b_peft/news_commentary_it/README.md

metadata

license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: /data1/model/llama2/meta-llama/Llama2-13b
model-index:
  - name: news_commentary_it_no_sys
    results: []

news_commentary_it_no_sys

This model is a fine-tuned version of /data1/model/llama2/meta-llama/Llama2-13b on the news_commentary_it_no_sys dataset. It achieves the following results on the evaluation set:

• Loss: 0.6415

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7236	0.2807	2000	0.6710
0.724	0.5614	4000	0.6521
0.6455	0.8421	6000	0.6415
0.5533	1.1228	8000	0.6548
0.5192	1.4035	10000	0.6501
0.4796	1.6842	12000	0.6500

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.19.1