arifagustyawan's picture
End of training
34e5089
|
raw
history blame
3.83 kB
metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
  - generated_from_trainer
model-index:
  - name: flan-t5-base-sentiment-product-review
    results: []

flan-t5-base-sentiment-product-review

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8071

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 33 1.0479
No log 2.0 66 0.9240
No log 3.0 99 0.8648
No log 4.0 132 0.8438
No log 5.0 165 0.8455
No log 6.0 198 0.8540
No log 7.0 231 0.8791
No log 8.0 264 0.8509
No log 9.0 297 0.9104
No log 10.0 330 0.9554
No log 11.0 363 0.9345
No log 12.0 396 0.9797
No log 13.0 429 0.9809
No log 14.0 462 1.0556
No log 15.0 495 1.1264
0.5004 16.0 528 1.1426
0.5004 17.0 561 1.2255
0.5004 18.0 594 1.2086
0.5004 19.0 627 1.2068
0.5004 20.0 660 1.2919
0.5004 21.0 693 1.3547
0.5004 22.0 726 1.3276
0.5004 23.0 759 1.3597
0.5004 24.0 792 1.4057
0.5004 25.0 825 1.4212
0.5004 26.0 858 1.5188
0.5004 27.0 891 1.5569
0.5004 28.0 924 1.5158
0.5004 29.0 957 1.5191
0.5004 30.0 990 1.5202
0.0793 31.0 1023 1.6140
0.0793 32.0 1056 1.6112
0.0793 33.0 1089 1.5900
0.0793 34.0 1122 1.6162
0.0793 35.0 1155 1.6261
0.0793 36.0 1188 1.6229
0.0793 37.0 1221 1.7149
0.0793 38.0 1254 1.7149
0.0793 39.0 1287 1.7502
0.0793 40.0 1320 1.7334
0.0793 41.0 1353 1.7409
0.0793 42.0 1386 1.7161
0.0793 43.0 1419 1.7235
0.0793 44.0 1452 1.7554
0.0793 45.0 1485 1.7640
0.0263 46.0 1518 1.7779
0.0263 47.0 1551 1.7784
0.0263 48.0 1584 1.7979
0.0263 49.0 1617 1.8056
0.0263 50.0 1650 1.8071

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0