04-21-01-51-38

reeddg/04-21-01-51-38

04-21-01-51-38 is a machine learning model from reeddg. 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

Access

Public

Updated Apr 21, 2024

Repo size

1.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json2.9 MB · 56%

At a glance

License: apache-2.0
Access: Public
Created: Apr 21, 2024
Updated: Apr 21, 2024
SHA: c3775ac5

Base models

facebook/bart-base

Model card

From the Hugging Face model README

04-21-01-51-38

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: 0.5981

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.6624	0.21	10	0.6567
0.6743	0.42	20	0.6509
0.7049	0.62	30	0.6460
0.7394	0.83	40	0.6382
0.6596	1.04	50	0.6338
0.65	1.25	60	0.6299
0.6736	1.46	70	0.6255
0.6531	1.67	80	0.6201
0.6215	1.88	90	0.6147
0.6448	2.08	100	0.6118
0.6276	2.29	110	0.6055
0.6397	2.5	120	0.6016
0.6261	2.71	130	0.5991
0.6584	2.92	140	0.5981

Framework versions

Transformers 4.31.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.13.3

License: apache-2.0
Created: Apr 21, 2024
Updated: Apr 21, 2024