mykahh/fine-tuned-distilbert-base-uncased

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

fine-tuned-distilbert-base-uncased

This model is a fine-tuned version of distilbert/distilbert-base-uncased-finetuned-sst-2-english on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 2.0891
• —eval_accuracy: {'accuracy': 0.6}
• —eval_f1score: {'f1': 0.6908981314044605}
• —eval_runtime: 29.8465
• —evalsamplesper_second: 3.35
• —evalstepsper_second: 0.436
• —step: 0

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 639
• —num_epochs: 1

Framework versions

• —Transformers 4.35.2
• —Pytorch 2.1.1+cpu
• —Datasets 2.15.0
• —Tokenizers 0.15.0