Edit model card

amazon_topical_chat_sentiment

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1237
  • Accuracy: 0.5687

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-06
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 14

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.199 1.0 9419 1.1807 0.5348
1.1383 2.0 18838 1.1487 0.5457
1.1036 3.0 28257 1.1368 0.5558
1.0971 4.0 37676 1.1226 0.5605
1.0679 5.0 47095 1.1223 0.5634
1.0528 6.0 56514 1.1156 0.5696
1.0245 7.0 65933 1.1158 0.5683
1.0279 8.0 75352 1.1140 0.5687
1.0152 9.0 84771 1.1127 0.5690
0.9794 10.0 94190 1.1179 0.5687
0.9717 11.0 103609 1.1200 0.5700
0.9654 12.0 113028 1.1223 0.5692
0.9703 13.0 122447 1.1232 0.5700
0.9545 14.0 131866 1.1237 0.5687

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
2
Safetensors
Model size
67M params
Tensor type
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Finetuned from