ft5-rouge-durga-q1-clean

devagonal/ft5-rouge-durga-q1-clean

ft5-rouge-durga-q1-clean is a machine learning model from devagonal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

248M

991 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors990 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Oct 30, 2024
Updated: Oct 30, 2024
SHA: 6c9de47d

Base models

google/flan-t5-base

Model card

From the Hugging Face model README

ft5-rouge-durga-q1-clean

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2757
Rouge1: 0.5561
Rouge2: 0.4369
Rougel: 0.5537
Rougelsum: 0.5562

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: 24
eval_batch_size: 24
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.0328	1.0	3	2.0694	0.2530	0.0656	0.2481	0.2492
1.8606	2.0	6	1.8619	0.3034	0.1007	0.2997	0.2986
2.8564	3.0	9	1.6705	0.2502	0.0631	0.2503	0.2506
1.4505	4.0	12	1.5098	0.2678	0.0531	0.2643	0.2645
1.5253	5.0	15	1.3533	0.3090	0.0953	0.3001	0.2987
1.9042	6.0	18	1.2238	0.3606	0.1385	0.3513	0.3500
1.7751	7.0	21	1.1186	0.3858	0.1532	0.3798	0.3777
1.1806	8.0	24	1.0301	0.3814	0.1448	0.3781	0.3763
1.0575	9.0	27	0.9449	0.4090	0.1835	0.4052	0.4038
0.9038	10.0	30	0.8609	0.4062	0.1918	0.4029	0.4021
1.4179	11.0	33	0.7875	0.4190	0.1933	0.4150	0.4149
1.435	12.0	36	0.7099	0.4075	0.1938	0.4047	0.4040
0.6608	13.0	39	0.6601	0.4206	0.2241	0.4188	0.4177
0.4501	14.0	42	0.6165	0.4445	0.2389	0.4380	0.4369
0.5584	15.0	45	0.5831	0.4465	0.2435	0.4472	0.4448
1.1468	16.0	48	0.5449	0.4461	0.2476	0.4452	0.4427
0.5354	17.0	51	0.5032	0.4260	0.2328	0.4276	0.4274
0.8386	18.0	54	0.4703	0.4049	0.2191	0.4041	0.4050
0.7596	19.0	57	0.4393	0.4272	0.2495	0.4267	0.4298
0.9838	20.0	60	0.4084	0.4517	0.2788	0.4517	0.4520
1.0146	21.0	63	0.3784	0.4578	0.2803	0.4576	0.4565
0.6939	22.0	66	0.3560	0.4934	0.3226	0.4963	0.4932
0.7661	23.0	69	0.3385	0.4949	0.3303	0.4972	0.4960
0.9235	24.0	72	0.3231	0.5357	0.4006	0.5362	0.5375
0.5005	25.0	75	0.3099	0.5466	0.4179	0.5466	0.5465
0.382	26.0	78	0.2982	0.5542	0.4330	0.5534	0.5546
0.5445	27.0	81	0.2882	0.5688	0.4555	0.5684	0.5673
0.5974	28.0	84	0.2816	0.5688	0.4555	0.5684	0.5673
0.6571	29.0	87	0.2775	0.5561	0.4369	0.5537	0.5562
0.5589	30.0	90	0.2757	0.5561	0.4369	0.5537	0.5562

Framework versions

Transformers 4.46.1
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.20.1

Library: transformers
Type: t5
License: apache-2.0
Created: Oct 30, 2024
Updated: Oct 30, 2024