story2dialogue-SODA-BART

abirmondalind/story2dialogue-SODA-BART

story2dialogue-SODA-BART is a machine learning model from abirmondalind. 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

4% of all-time downloads

All-time downloads

431

Public

Parameters

139M

20.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors558 MB · 99%

At a glance

Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Oct 13, 2025
Updated: Oct 20, 2025
SHA: 8f661052

Base models

facebook/bart-base

Model card

From the Hugging Face model README

story2dialogue-SODA-BERT

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

Loss: 0.2161
Rouge1: 0.1385
Rouge2: 0.0675
Rougel: 0.1227
Rougelsum: 0.1340
Bleu: 0.0000
Bleu1: 0.7857
Bleu2: 0.4621
Bleu3: 0.2891
Bleu4: 0.2004
Avg Jaccard: 0.0804
Gen Length: 10.6835

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: 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: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu1	Bleu2	Bleu3	Bleu4	Avg Jaccard	Gen Length
0.2974	0.2444	1000	0.2571	0.1281	0.0540	0.1133	0.1245	0.7549	0.4120	0.2331	0.1452	0.0705	10.2110
0.2721	0.4888	2000	0.2448	0.1305	0.0568	0.1150	0.1263	0.7573	0.4223	0.2452	0.1579	0.0709	10.2986
0.2681	0.7331	3000	0.2373	0.1337	0.0607	0.1181	0.1294	0.7773	0.4407	0.2618	0.1733	0.0749	10.3560
0.2641	0.9775	4000	0.2315	0.1380	0.0662	0.1220	0.1335	0.7836	0.4571	0.2787	0.1876	0.0787	10.6060
0.2445	1.2219	5000	0.2279	0.1347	0.0624	0.1194	0.1306	0.7782	0.4448	0.2698	0.1822	0.0772	10.5598
0.2448	1.4663	6000	0.2247	0.1389	0.0662	0.1225	0.1345	0.7827	0.4504	0.2755	0.1875	0.0800	10.7905
0.2416	1.7107	7000	0.2221	0.1367	0.0648	0.1208	0.1323	0.7782	0.4466	0.2728	0.1851	0.0772	10.5380
0.2416	1.9550	8000	0.2208	0.1383	0.0666	0.1223	0.1339	0.7871	0.4584	0.2822	0.1933	0.0797	10.6464
0.2329	2.1994	9000	0.2190	0.1378	0.0658	0.1218	0.1331	0.7788	0.4489	0.2775	0.1918	0.0795	10.7570
0.2319	2.4438	10000	0.2175	0.1375	0.0665	0.1219	0.1331	0.7850	0.4615	0.2875	0.1988	0.0797	10.6320
0.228	2.6882	11000	0.2166	0.1383	0.0668	0.1223	0.1338	0.7865	0.4588	0.2864	0.1989	0.0800	10.6653
0.2281	2.9326	12000	0.2161	0.1385	0.0675	0.1227	0.1340	0.7857	0.4621	0.2891	0.2004	0.0804	10.6835

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

Library: transformers
Type: bart
License: apache-2.0
Created: Oct 13, 2025
Updated: Oct 20, 2025