Abhi_mt5-small_v1

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: 5.7900
• Rouge1: 7.0558
• Rouge2: 0.0
• Rougel: 6.992
• Rougelsum: 7.1212

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
22.775	1.0	11	8.6160	6.8571	0.0	6.7143	7.0336
14.9187	2.0	22	7.6936	6.5	0.0	6.1765	6.6765
16.1045	3.0	33	7.4191	7.1667	0.0	7.0196	7.2696
12.8363	4.0	44	6.9229	8.9467	0.0	8.872	9.0752
11.9989	5.0	55	6.7268	9.174	0.0	9.1046	9.3757
11.2745	6.0	66	6.4987	7.0558	0.0	6.992	7.1212
11.7085	7.0	77	6.2089	7.0558	0.0	6.992	7.1212
10.6682	8.0	88	6.0491	7.0558	0.0	6.992	7.1212
9.9553	9.0	99	5.7979	7.0558	0.0	6.992	7.1212
11.127	10.0	110	5.7900	7.0558	0.0	6.992	7.1212

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2