mt5-small-task1-dataset2

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

• Loss: 1.0670
• Accuracy: 0.19

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: 5.6e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
10.1157	1.0	250	2.0629	0.0
2.7164	2.0	500	1.6984	0.092
2.1384	3.0	750	1.6345	0.098
1.8496	4.0	1000	1.5214	0.118
1.6276	5.0	1250	1.3418	0.14
1.469	6.0	1500	1.2577	0.15
1.3461	7.0	1750	1.2325	0.162
1.2791	8.0	2000	1.1790	0.16
1.2349	9.0	2250	1.1320	0.174
1.1826	10.0	2500	1.1118	0.176
1.1504	11.0	2750	1.1063	0.19
1.1327	12.0	3000	1.0731	0.186
1.1168	13.0	3250	1.0617	0.186
1.1038	14.0	3500	1.0735	0.182
1.0929	15.0	3750	1.0670	0.19

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0