Hugging Face's logo

allistair99
/
distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-optiparam

Transformers
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
 Community

distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-optiparam

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

  • Loss: 1.0866

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: 3e-05
  • train_batch_size: 6
  • eval_batch_size: 60
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
0.6652 1.0 14619 1.0816
0.6453 2.0 29238 1.0866

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
5
Safetensors
Model size
69.9M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for allistair99/distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-optiparam

Base model

distilbert/distilbert-base-uncased-distilled-squad
Finetuned
(45)
this model
Finetunes
4 models

Collection including allistair99/distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-optiparam