dialogsum_ds / README.md
Rahmat82's picture
dataset text update
816f914 verified
metadata
tags:
  - generated_from_trainer
model-index:
  - name: dialogsum_ds
    results: []
widget:
  - text: >-
      A: I'm so thirsty. B: Let's go get something to drink. A: That's a good
      idea. B: Do you know what you want to drink? A: I kind of want a soda. B:
      You shouldn't drink soda when you're really thirsty. A: What do you mean?
      B: When you're thirsty, you're not supposed to drink soda. A: What are you
      supposed to drink? B: Water is what's best for you. A: I guess I will get
      water. B: It's better for you.

dialogsum_ds

This model is a fine-tuned on cnn_dailymail dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1124

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

Training results

Training Loss Epoch Step Validation Loss
1.344 0.4 500 1.1821
1.1234 0.8 1000 1.1124

Framework versions

  • Transformers 4.16.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.0.0
  • Tokenizers 0.15.0