plan_t5

This model is a fine-tuned version of google/t5-small-lm-adapt on the Isotonic/planner_dataset dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4366
  • Rouge1: 58.1228
  • Rouge2: 24.3461
  • Rougel: 58.1313
  • Rougelsum: 58.1335
  • Gen Len: 7.9747

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: 8
  • eval_batch_size: 8
  • seed: 37
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.2
  • num_epochs: 5.0

Training results

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.0+cu118
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
18
Safetensors
Model size
77M params
Tensor type
F32
·
Inference Examples
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.

Model tree for Isotonic/plan_t5

Finetuned
(1)
this model

Dataset used to train Isotonic/plan_t5

Evaluation results