MSLars's picture
Training complete
d0b282d verified
|
raw
history blame
2.49 kB
metadata
base_model: LennartKeller/longformer-gottbert-base-8192-aw512
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: de_longformer_abstr_summ
    results: []

de_longformer_abstr_summ

This model is a fine-tuned version of LennartKeller/longformer-gottbert-base-8192-aw512 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5746
  • Precision: 0.1612
  • Recall: 0.2474
  • F1: 0.1952
  • Accuracy: 0.7800

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: 2e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 0.98 48 0.5548 0.0 0.0 0.0 0.7540
No log 1.99 97 0.5185 0.1067 0.1548 0.1263 0.7864
No log 2.99 146 0.5068 0.0876 0.1534 0.1115 0.7806
No log 4.0 195 0.5145 0.2797 0.3889 0.3254 0.7926
No log 4.98 243 0.5097 0.2068 0.3439 0.2583 0.7916
No log 5.99 292 0.5073 0.1637 0.2831 0.2075 0.7920
No log 6.99 341 0.5316 0.1723 0.2553 0.2058 0.7865
No log 8.0 390 0.5480 0.1483 0.2275 0.1795 0.7837
No log 8.98 438 0.5587 0.1649 0.2725 0.2055 0.7823
No log 9.85 480 0.5746 0.1612 0.2474 0.1952 0.7800

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.2.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0