flan-t5-large-finetuned-gsm8k

This model is a fine-tuned version of google/flan-t5-large on the gsm8k dataset. It achieves the following results on the evaluation set:

• Loss: 0.3091
• Rouge2 Precision: 0.4454
• Rouge2 Recall: 0.0953
• Rouge2 Fmeasure: 0.152

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: 2
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
0.34	1.0	3737	0.3206	0.4241	0.089	0.1423
0.2786	2.0	7474	0.3089	0.4334	0.0916	0.1463
0.247	3.0	11211	0.3074	0.4461	0.095	0.1515
0.2283	4.0	14948	0.3091	0.4454	0.0953	0.152

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.2