bart_finetuned_wo_clarify_aspects

tlam25/bart_finetuned_wo_clarify_aspects

bart_finetuned_wo_clarify_aspects is a machine learning model from tlam25. 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

8% of all-time downloads

All-time downloads

100

Public

Parameters

139M

35.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors558 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Apr 13, 2025
Updated: Apr 13, 2025
SHA: 6242f650

Base models

facebook/bart-base

Model card

From the Hugging Face model README

bart_finetuned_wo_clarify_aspects

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

Loss: 0.0568
Micro Precision: 0.2171
Micro Recall: 0.0791
Micro F1: 0.1159
Macro Precision: 0.2197
Macro Recall: 0.0745
Macro F1: 0.1113
Bleu: 0.8569
Rouge1: 0.8387
Rouge2: 0.6017

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: Use OptimizerNames.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: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Micro Precision	Micro Recall	Micro F1	Macro Precision	Macro Recall	Macro F1	Bleu	Rouge1	Rouge2
4.825	0.2404	50	2.1160	0.1789	0.1415	0.1580	0.0874	0.1668	0.1147	0.6783	0.7342	0.4167
1.8129	0.4808	100	0.9011	0.1879	0.0843	0.1164	0.0902	0.0969	0.0935	0.7651	0.7498	0.4283
0.7361	0.7212	150	0.2399	0.175	0.0073	0.0140	0.0833	0.0083	0.0151	0.8218	0.7783	0.4456
0.2197	0.9615	200	0.0935	0.125	0.0354	0.0552	0.0579	0.0372	0.0453	0.7687	0.7806	0.4456
0.1028	1.2019	250	0.0708	0.2719	0.0614	0.1002	0.1580	0.0518	0.0780	0.8472	0.8119	0.4532
0.0823	1.4423	300	0.0799	0.2542	0.1582	0.1950	0.1917	0.1613	0.1752	0.5872	0.7242	0.4584
0.0752	1.6827	350	0.0675	0.3778	0.0708	0.1192	0.1901	0.0558	0.0863	0.8392	0.8324	0.4612
0.077	1.9231	400	0.0632	0.2111	0.1228	0.1553	0.1563	0.1030	0.1242	0.8627	0.8203	0.5084
0.0694	2.1635	450	0.0669	0.2963	0.1498	0.1990	0.1738	0.1542	0.1634	0.6446	0.7494	0.5162
0.0712	2.4038	500	0.0638	0.1220	0.0052	0.0100	0.1668	0.0058	0.0112	0.8664	0.8404	0.5668
0.0672	2.6442	550	0.0628	0.1651	0.0364	0.0597	0.1776	0.0377	0.0621	0.8526	0.8284	0.5668
0.0644	2.8846	600	0.0595	0.1377	0.0239	0.0408	0.1742	0.0232	0.0410	0.8551	0.8255	0.5221
0.0648	3.125	650	0.0597	0.1166	0.0198	0.0338	0.1773	0.0197	0.0354	0.8584	0.8412	0.5764
0.0626	3.3654	700	0.0604	0.1861	0.0447	0.0721	0.2103	0.0439	0.0726	0.8511	0.8153	0.5498
0.0614	3.6058	750	0.0571	0.1412	0.0375	0.0592	0.1542	0.0387	0.0619	0.8469	0.8240	0.5769
0.0582	3.8462	800	0.0573	0.2205	0.0739	0.1107	0.2194	0.0737	0.1104	0.8534	0.8349	0.5965
0.0596	4.0865	850	0.0579	0.2287	0.0895	0.1286	0.2266	0.0889	0.1276	0.8358	0.8195	0.5896
0.0574	4.3269	900	0.0586	0.224	0.0874	0.1257	0.2235	0.0882	0.1265	0.8443	0.8186	0.5709
0.0592	4.5673	950	0.0579	0.2186	0.0905	0.1280	0.2259	0.0875	0.1262	0.8567	0.8301	0.5902
0.061	4.8077	1000	0.0568	0.2171	0.0791	0.1159	0.2197	0.0745	0.1113	0.8569	0.8387	0.6017

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

Library: transformers
Type: bart
License: apache-2.0
Created: Apr 13, 2025
Updated: Apr 13, 2025