mt5-base_EN_spider_no_decode_old_env_128

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: 0.0178
• Rouge2 Recall: 0.0067
• Rouge2 Fmeasure: 0.009

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: 18
• 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	539	nan	0.0178	0.0067	0.009
0.0	2.0	1078	nan	0.0178	0.0067	0.009
0.0	3.0	1617	nan	0.0178	0.0067	0.009
0.0	4.0	2156	nan	0.0178	0.0067	0.009
0.0	5.0	2695	nan	0.0178	0.0067	0.009
0.0	6.0	3234	nan	0.0178	0.0067	0.009
0.0	7.0	3773	nan	0.0178	0.0067	0.009
0.0	8.0	4312	nan	0.0178	0.0067	0.009
0.0	9.0	4851	nan	0.0178	0.0067	0.009
0.0	10.0	5390	nan	0.0178	0.0067	0.009
0.0	11.0	5929	nan	0.0178	0.0067	0.009
0.0	12.0	6468	nan	0.0178	0.0067	0.009
0.0	13.0	7007	nan	0.0178	0.0067	0.009
0.0	14.0	7546	nan	0.0178	0.0067	0.009
0.0	15.0	8085	nan	0.0178	0.0067	0.009

Framework versions

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