Hugging Face's logo

ytcheng
/
Qwen-14B-lora-pretrain

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
Qwen-14B-lora-pretrain / README.md
ytcheng's picture
ytcheng
End of training
0102256 verified
preview code
|
raw
history blame contribute delete
1.56 kB
metadata
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: Qwen/Qwen-14B
model-index:
  - name: Qwen-14B-lora-pretrain
    results: []

Qwen-14B-lora-pretrain

This model is a fine-tuned version of Qwen/Qwen-14B on the sm_artile dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0396

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.9974 0.7712 500 2.0961
2.2371 1.5423 1000 2.0582
2.0174 2.3135 1500 2.0424

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1