ConvAnalysis
/

DialogLED-base-16384-dialogsum-finetuned

text2text-generation

Generated from Trainer

dialogue_summarization

conversation_summarization

long_dialog_summarization

Model card Files Files and versions

Metrics Training metrics Community

DialogLED-base-16384-dialogsum-finetuned

This model is a fine-tuned version of MingZhong/DialogLED-base-16384 on the dialogsum dataset.

Model description

More information needed

Intended uses & limitations

Used for conversation summarization. Might work for long dialouges.

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
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

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 3

Safetensors

Model size

0.2B params

Tensor type

F32

·

Model tree for ConvAnalysis/DialogLED-base-16384-dialogsum-finetuned

Base model

MingZhong/DialogLED-base-16384

Finetuned

(20)

this model

Dataset used to train ConvAnalysis/DialogLED-base-16384-dialogsum-finetuned