bart-abs-1509-0313-lr-3e-05-bs-4-maxep-6

roequitz/bart-abs-1509-0313-lr-3e-05-bs-4-maxep-6

bart-abs-1509-0313-lr-3e-05-bs-4-maxep-6 is a machine learning model from roequitz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

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

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

306M

1.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

License: apache-2.0
Model type: bart
Access: Public
Created: Sep 15, 2024
Updated: Sep 15, 2024
SHA: 0a772dfb

Base models

sshleifer/distilbart-xsum-12-6

Model card

From the Hugging Face model README

bart-abs-1509-0313-lr-3e-05-bs-4-maxep-6

This model is a fine-tuned version of sshleifer/distilbart-xsum-12-6 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.3615
Rouge/rouge1: 0.4759
Rouge/rouge2: 0.2278
Rouge/rougel: 0.407
Rouge/rougelsum: 0.4084
Bertscore/bertscore-precision: 0.898
Bertscore/bertscore-recall: 0.8937
Bertscore/bertscore-f1: 0.8957
Meteor: 0.4311
Gen Len: 37.0

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: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge/rouge1	Rouge/rouge2	Rouge/rougel	Rouge/rougelsum	Bertscore/bertscore-precision	Bertscore/bertscore-recall	Bertscore/bertscore-f1	Meteor	Gen Len
2.3606	1.0	217	2.0792	0.44	0.2028	0.3696	0.3707	0.8966	0.8883	0.8923	0.3866	37.3636
1.6544	2.0	434	1.9952	0.4521	0.2171	0.3902	0.3909	0.8991	0.8912	0.895	0.4007	34.6636
1.2907	3.0	651	2.0614	0.4661	0.2212	0.399	0.4008	0.9006	0.8929	0.8966	0.4128	35.2636
1.0179	4.0	868	2.1396	0.479	0.2295	0.4121	0.4137	0.9024	0.8933	0.8977	0.4142	34.7182
0.8112	5.0	1085	2.2658	0.4737	0.2237	0.4046	0.405	0.8989	0.8931	0.8959	0.4126	35.4273
0.6745	6.0	1302	2.3615	0.4759	0.2278	0.407	0.4084	0.898	0.8937	0.8957	0.4311	37.0

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

Type: bart
License: apache-2.0
Created: Sep 15, 2024
Updated: Sep 15, 2024