Hugging Face's logo

scott156
/
LEDBaseNSPCCV1

Text2Text Generation
Transformers
Safetensors
led
Generated from Trainer
Inference Endpoints
Model card Files Community
LEDBaseNSPCCV1 / README.md
scott156's picture
scott156
End of training
ac3043b verified
preview code
|
raw history blame contribute delete
No virus
1.79 kB
metadata
license: apache-2.0
base_model: allenai/led-base-16384
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: LED-Base-NSPCC
    results: []

LED-Base-NSPCC

This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8152
  • Rouge1: 0.4955
  • Rouge2: 0.2131
  • Rougel: 0.2804
  • Rougelsum: 0.2807
  • Gen Len: 267.3511

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: 0.0003
  • train_batch_size: 4
  • eval_batch_size: 4
  • 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: 0.03
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.5412 0.99 47 1.9338 0.4778 0.186 0.2638 0.2635 266.2766
1.6145 1.99 94 1.8152 0.4955 0.2131 0.2804 0.2807 267.3511

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2