mt5-small-task2-dataset1

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: 0.2211
• Accuracy: 0.758

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
0.9386	1.0	250	0.5169	0.622
0.6505	2.0	500	0.4347	0.672
0.6135	3.0	750	0.3889	0.686
0.5125	4.0	1000	0.3268	0.698
0.4423	5.0	1250	0.3011	0.712
0.3973	6.0	1500	0.2919	0.726
0.3701	7.0	1750	0.2713	0.73
0.337	8.0	2000	0.2540	0.738
0.326	9.0	2250	0.2502	0.744
0.2946	10.0	2500	0.2383	0.744
0.2866	11.0	2750	0.2309	0.75
0.2789	12.0	3000	0.2304	0.754
0.2701	13.0	3250	0.2260	0.762
0.2612	14.0	3500	0.2226	0.76
0.2576	15.0	3750	0.2211	0.758

Framework versions

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