fine_tuned_t5_small_model_sec_5_v2

miasetya/fine_tuned_t5_small_model_sec_5_v2

fine_tuned_t5_small_model_sec_5_v2 is a machine learning model from miasetya. 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

17% of all-time downloads

All-time downloads

Public

Parameters

60.5M

485 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors242 MB · 99%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Dec 2, 2024
Updated: Dec 2, 2024
SHA: 36c5f23c

Base models

Model card

From the Hugging Face model README

fine_tuned_t5_small_model_sec_5_v2

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

Loss: 2.8624
Rouge1: 0.1795
Rouge2: 0.0574
Rougel: 0.1372
Rougelsum: 0.1366
Gen Len: 18.9145
Bert F1: 0.8513

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: 2e-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: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bert F1
3.8059	0.6667	20	3.4557	0.1764	0.0603	0.1384	0.1383	18.5812	0.8509
3.4845	1.3333	40	3.2263	0.1754	0.0607	0.1383	0.1381	18.7179	0.85
3.3761	2.0	60	3.1002	0.1745	0.058	0.1371	0.1367	18.7778	0.8505
3.1784	2.6667	80	3.0355	0.1712	0.0563	0.134	0.1335	18.8291	0.8496
3.1917	3.3333	100	2.9901	0.1751	0.0545	0.1344	0.134	18.9145	0.8497
3.0839	4.0	120	2.9595	0.1716	0.0513	0.1294	0.1293	18.9231	0.8492
3.1191	4.6667	140	2.9414	0.1775	0.057	0.1357	0.1352	18.9145	0.8496
3.0743	5.3333	160	2.9307	0.1777	0.0567	0.1351	0.1349	18.9231	0.8496
3.0593	6.0	180	2.9199	0.1795	0.0572	0.1356	0.1356	18.9145	0.8496
3.0485	6.6667	200	2.9090	0.1771	0.0559	0.1346	0.1343	18.9316	0.8492
2.9812	7.3333	220	2.9003	0.1745	0.0532	0.1335	0.1333	18.9316	0.8492
3.0387	8.0	240	2.8937	0.1778	0.0579	0.1361	0.1361	18.9231	0.8499
3.0072	8.6667	260	2.8887	0.1792	0.0594	0.137	0.1367	18.9316	0.8502
3.0122	9.3333	280	2.8837	0.1782	0.0593	0.1366	0.1365	18.9231	0.8506
2.9255	10.0	300	2.8782	0.1769	0.0587	0.1362	0.1357	18.9231	0.8502
2.9749	10.6667	320	2.8745	0.1778	0.0588	0.1366	0.1362	18.9231	0.8504
2.9782	11.3333	340	2.8710	0.1795	0.0596	0.1374	0.1371	18.9231	0.8509
2.948	12.0	360	2.8685	0.1777	0.0569	0.136	0.1354	18.9231	0.8509
2.9415	12.6667	380	2.8653	0.1778	0.0569	0.1357	0.1352	18.9231	0.8512
2.8864	13.3333	400	2.8624	0.1795	0.0574	0.1372	0.1366	18.9145	0.8513

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0

Library: transformers
Type: t5
License: apache-2.0
Created: Dec 2, 2024
Updated: Dec 2, 2024