Fine_Tuned_T5_small_for_DailyDialog

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5891
• Rouge1: 11.0459
• Rouge2: 2.2404
• Rougel: 10.5072
• Rougelsum: 10.7781
• Bleu: 0.8903
• Gen Len: 7.111

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Gen Len
2.0809	1.0	313	1.7698	9.3634	1.6744	8.9437	9.0705	0.6728	8.217
1.4771	2.0	626	1.3016	10.1104	1.7728	9.6869	9.8809	0.0	6.527
1.2084	3.0	939	1.0781	10.3142	2.0722	9.8421	10.0426	0.7095	6.272
1.0171	4.0	1252	0.9219	10.299	2.107	9.8825	10.1102	0.7598	6.246
0.9029	5.0	1565	0.7993	10.5767	2.0701	10.0645	10.3152	0.88	6.94
0.7979	6.0	1878	0.7169	10.618	2.0406	10.0889	10.3652	0.9014	7.047
0.7266	7.0	2191	0.6627	10.8584	2.1613	10.292	10.575	0.8766	6.769
0.692	8.0	2504	0.6231	11.2891	2.2669	10.7278	11.0423	0.9933	7.273
0.6724	9.0	2817	0.5956	11.2029	2.2399	10.6659	10.9419	0.9988	7.512
0.65	10.0	3130	0.5891	11.0459	2.2404	10.5072	10.7781	0.8903	7.111

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3