---
tags:
- generated_from_trainer
datasets:
- jkorsvik/cnn_daily_mail_nor_final
model-index:
- name: t5-large-cnndaily-copy
  results: []

inference:
  parameters:
    max_length: 160
---

<!-- 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. -->

# t5-large-cnndaily

This model is a fine-tuned version of [t5-large-cnndaily/checkpoint-10318](https://huggingface.co/t5-large-cnndaily/checkpoint-10318) on the jkorsvik/cnn_daily_mail_nor_final dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.8011
- eval_rouge1: 32.6372
- eval_rouge2: 12.4352
- eval_rougeL: 22.9598
- eval_rougeLsum: 30.3946
- eval_gen_len: 65.1487
- eval_runtime: 167.4595
- eval_samples_per_second: 21.205
- eval_steps_per_second: 0.167
- step: 11792

## Model description

wandb logs: https://wandb.ai/navjordj/huggingface/runs/zrx32j09?workspace=user-navjordj

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: 4
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0

### Framework versions

- Transformers 4.27.0.dev0
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2