adriansanz's picture
End of training
09a51cd verified
|
raw
history blame
2.85 kB
metadata
license: apache-2.0
base_model: ibaucells/RoBERTa-ca-CaWikiTC
tags:
  - generated_from_trainer
model-index:
  - name: test7_balanced_and_sentence
    results: []

test7_balanced_and_sentence

This model is a fine-tuned version of ibaucells/RoBERTa-ca-CaWikiTC on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1090

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: 10
  • eval_batch_size: 10
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss
2.8511 1.0 63 2.8392
2.8303 2.0 126 2.8357
2.8277 3.0 189 2.8396
2.7933 4.0 252 2.8123
2.7264 5.0 315 2.7844
2.6213 6.0 378 2.7200
2.513 7.0 441 2.7099
2.4436 8.0 504 2.5845
2.0946 9.0 567 2.5724
1.9708 10.0 630 2.3567
1.6289 11.0 693 2.3670
1.5015 12.0 756 2.3716
1.3488 13.0 819 2.1432
1.0815 14.0 882 2.2774
0.9128 15.0 945 2.3228
0.7779 16.0 1008 2.2310
0.5918 17.0 1071 2.3602
0.5215 18.0 1134 2.3472
0.3969 19.0 1197 2.3990
0.421 20.0 1260 2.4948
0.2811 21.0 1323 2.6314
0.2538 22.0 1386 2.7452
0.1646 23.0 1449 2.7550
0.1553 24.0 1512 2.8536
0.1743 25.0 1575 2.8543
0.198 26.0 1638 2.9044
0.1065 27.0 1701 2.9262
0.0935 28.0 1764 2.8968
0.0972 29.0 1827 2.9331
0.1296 30.0 1890 2.9396

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2