README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google/flan-t5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: flan-t5-rouge-muhammad
    results: []

flan-t5-rouge-muhammad

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

• Loss: 0.0000
• Rouge1: 0.9614
• Rouge2: 0.6993
• Rougel: 0.9620
• Rougelsum: 0.9608

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: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
5.302	1.0	50	2.5839	0.0277	0.0	0.0266	0.0267
2.806	2.0	100	1.6441	0.0944	0.0367	0.0940	0.0952
1.3348	3.0	150	1.1077	0.1653	0.0429	0.1644	0.1650
1.7996	4.0	200	0.7027	0.2908	0.1621	0.2864	0.2898
0.7975	5.0	250	0.4608	0.4016	0.2158	0.3954	0.3971
0.3679	6.0	300	0.3462	0.4970	0.2975	0.4969	0.5016
0.8118	7.0	350	0.2211	0.6163	0.3819	0.6142	0.6161
0.4616	8.0	400	0.1314	0.7334	0.4850	0.7321	0.7343
0.4839	9.0	450	0.0681	0.8123	0.5500	0.8126	0.8130
0.0311	10.0	500	0.0677	0.8569	0.5984	0.8564	0.8554
0.4817	11.0	550	0.0445	0.8553	0.6003	0.8552	0.8563
0.3256	12.0	600	0.0502	0.8970	0.6382	0.8964	0.8972
0.2595	13.0	650	0.0243	0.9115	0.6440	0.9110	0.9110
0.0417	14.0	700	0.0209	0.9417	0.6744	0.9407	0.9414
0.0356	15.0	750	0.0110	0.9467	0.6840	0.9468	0.9449
0.0033	16.0	800	0.0131	0.9426	0.6752	0.9423	0.9407
0.0912	17.0	850	0.0043	0.9574	0.6933	0.9574	0.9564
0.1195	18.0	900	0.0031	0.9608	0.6986	0.9613	0.9602
0.0067	19.0	950	0.0026	0.9614	0.6993	0.9620	0.9608
0.1854	20.0	1000	0.0017	0.9614	0.6993	0.9620	0.9608
0.0199	21.0	1050	0.0017	0.9614	0.6993	0.9620	0.9608
0.0022	22.0	1100	0.0006	0.9614	0.6993	0.9620	0.9608
0.0014	23.0	1150	0.0005	0.9614	0.6993	0.9620	0.9608
0.0823	24.0	1200	0.0002	0.9614	0.6993	0.9620	0.9608
0.0012	25.0	1250	0.0002	0.9614	0.6993	0.9620	0.9608
0.065	26.0	1300	0.0001	0.9614	0.6993	0.9620	0.9608
0.0025	27.0	1350	0.0001	0.9614	0.6993	0.9620	0.9608
0.0046	28.0	1400	0.0000	0.9614	0.6993	0.9620	0.9608
0.004	29.0	1450	0.0000	0.9614	0.6993	0.9620	0.9608
0.0011	30.0	1500	0.0000	0.9614	0.6993	0.9620	0.9608

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1