04-07-03-02-17

reeddg/04-07-03-02-17

04-07-03-02-17 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 7, 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 7, 2024
Updated: Apr 7, 2024
SHA: 3583c58d

Base models

facebook/bart-base

Model card

From the Hugging Face model README

04-07-03-02-17

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: 0.6055

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
0.6341	0.21	10	0.6655
0.7485	0.42	20	0.6621
0.7289	0.62	30	0.6533
0.6411	0.83	40	0.6465
0.6733	1.04	50	0.6416
0.6349	1.25	60	0.6313
0.6729	1.46	70	0.6323
0.6885	1.67	80	0.6211
0.6057	1.88	90	0.6191
0.6539	2.08	100	0.6167
0.606	2.29	110	0.6113
0.6124	2.5	120	0.6133
0.6855	2.71	130	0.6055
0.4973	2.92	140	0.6055

Framework versions

Transformers 4.31.0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.13.3

License: apache-2.0
Created: Apr 7, 2024
Updated: Apr 7, 2024