metadata

license: apache-2.0
base_model: google/flan-t5-xl
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: flan-t5-xl-finetuning-translation-ds
    results: []

flan-t5-xl-finetuning-translation-ds

This model is a fine-tuned version of google/flan-t5-xl on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7281
Bleu: 39.0171
Gen Len: 52.6438

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: 0.0001
train_batch_size: 96
eval_batch_size: 96
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 768
total_eval_batch_size: 768
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	13	0.8779	33.4548	52.8617
No log	2.0	26	0.7910	36.556	52.9883
No log	3.0	39	0.7281	39.0171	52.6438

Framework versions

Transformers 4.34.0
Pytorch 2.1.0+cu121
Datasets 2.14.5
Tokenizers 0.14.1