bart-finetuned-lyrlen-512

adamjweintraut/bart-finetuned-lyrlen-512

bart-finetuned-lyrlen-512 is a machine learning model from adamjweintraut. 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

9% of all-time downloads

All-time downloads

Public

Parameters

406M

119 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.3 GB · 50%

At a glance

Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Mar 19, 2024
Updated: Mar 19, 2024
SHA: 1628d83a

Base models

facebook/bart-large

Model card

From the Hugging Face model README

bart-finetuned-lyrlen-512

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

Loss: 1.7206

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: 2
eval_batch_size: 2
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
2.221	0.04	500	1.9667
2.0336	0.08	1000	1.8762
1.9563	0.12	1500	1.8565
1.9555	0.17	2000	1.8392
1.9072	0.21	2500	1.8214
1.8796	0.25	3000	1.8246
1.8955	0.29	3500	1.8050
1.8254	0.33	4000	1.8069
1.8518	0.38	4500	1.7873
1.8471	0.42	5000	1.7880
1.8536	0.46	5500	1.7736
1.8075	0.5	6000	1.7772
1.8143	0.54	6500	1.7724
1.8383	0.58	7000	1.7670
1.746	0.62	7500	1.7741
1.7844	0.67	8000	1.7608
1.7761	0.71	8500	1.7680
1.7367	0.75	9000	1.7555
1.7656	0.79	9500	1.7508
1.7467	0.83	10000	1.7558
1.7744	0.88	10500	1.7449
1.7513	0.92	11000	1.7462
1.7482	0.96	11500	1.7576
1.724	1.0	12000	1.7525
1.7043	1.04	12500	1.7746
1.6869	1.08	13000	1.7531
1.7405	1.12	13500	1.7473
1.7343	1.17	14000	1.7396
1.649	1.21	14500	1.7384
1.7208	1.25	15000	1.7368
1.6931	1.29	15500	1.7404
1.5941	1.33	16000	1.8223
1.6651	1.38	16500	1.7287
1.6649	1.42	17000	1.7413
1.7108	1.46	17500	1.7304
1.713	1.5	18000	1.7263
1.6866	1.54	18500	1.7139
1.6461	1.58	19000	1.7221
1.6886	1.62	19500	1.7159
1.6511	1.67	20000	1.7302
1.6626	1.71	20500	1.7182
1.7052	1.75	21000	1.7163
1.6831	1.79	21500	1.7168
1.6057	1.83	22000	1.7151
1.6761	1.88	22500	1.7117
1.6668	1.92	23000	1.7164
1.612	1.96	23500	1.7122
1.6617	2.0	24000	1.7131
1.641	2.04	24500	1.7277
1.6595	2.08	25000	1.7289
1.6723	2.12	25500	1.7192
1.6347	2.17	26000	1.7259
1.6684	2.21	26500	1.7211
1.6098	2.25	27000	1.7316
1.6025	2.29	27500	1.7213
1.5567	2.33	28000	1.7238
1.6564	2.38	28500	1.7185
1.7078	2.42	29000	1.7393
1.6308	2.46	29500	1.7234
1.6402	2.5	30000	1.7319
1.6333	2.54	30500	1.7197
1.6249	2.58	31000	1.7298
1.6366	2.62	31500	1.7235
1.6245	2.67	32000	1.7289
1.6044	2.71	32500	1.7160
1.6095	2.75	33000	1.7172
1.6621	2.79	33500	1.7210
1.6883	2.83	34000	1.7169
1.6449	2.88	34500	1.7155
1.6439	2.92	35000	1.7201
1.6358	2.96	35500	1.7188
1.6033	3.0	36000	1.7206

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.0.dev20230621+cu117
Datasets 2.18.0
Tokenizers 0.15.2

Library: transformers
Type: bart
License: apache-2.0
Created: Mar 19, 2024
Updated: Mar 19, 2024