Edit model card

wiki_asp-animal_4639_wiki_asp-animal_2910_bart-base

This model is a fine-tuned version of baek26/wiki_asp-animal_2910_bart-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5290
  • Rouge1: 0.1446
  • Rouge2: 0.0631
  • Rougel: 0.1276
  • Rougelsum: 0.1277
  • Gen Len: 15.8808

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
  • gradient_accumulation_steps: 16
  • 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: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.93 500 2.5627 0.1435 0.0614 0.1262 0.1261 15.9017
No log 3.87 1000 2.5538 0.1373 0.0583 0.121 0.1212 15.4998
No log 5.8 1500 2.5393 0.1465 0.0638 0.1295 0.1297 16.0893
2.3118 7.74 2000 2.5336 0.1517 0.0666 0.1336 0.1339 16.2204
2.3118 9.67 2500 2.5290 0.1446 0.0631 0.1276 0.1277 15.8808

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.0.0+cu117
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
1
Safetensors
Model size
139M params
Tensor type
F32
·

Finetuned from