mt5-base_EN_spider_no_decode_old_env

This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Rouge2 Precision: 0.011
• Rouge2 Recall: 0.0037
• Rouge2 Fmeasure: 0.005

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
0.0	1.0	9693	nan	0.011	0.0037	0.005
0.0	2.0	19386	nan	0.011	0.0037	0.005
0.0	3.0	29079	nan	0.011	0.0037	0.005
0.0	4.0	38772	nan	0.011	0.0037	0.005
0.0	5.0	48465	nan	0.011	0.0037	0.005
0.0	6.0	58158	nan	0.011	0.0037	0.005
0.0	7.0	67851	nan	0.011	0.0037	0.005
0.0	8.0	77544	nan	0.011	0.0037	0.005
0.0	9.0	87237	nan	0.011	0.0037	0.005
0.0	10.0	96930	nan	0.011	0.0037	0.005
0.0	11.0	106623	nan	0.011	0.0037	0.005
0.0	12.0	116316	nan	0.011	0.0037	0.005
0.0	13.0	126009	nan	0.011	0.0037	0.005
0.0	14.0	135702	nan	0.011	0.0037	0.005
0.0	15.0	145395	nan	0.011	0.0037	0.005

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.0
• Datasets 2.16.1
• Tokenizers 0.15.1