limbxy_seq_t2_heads4_layers1

c14kevincardenas/limbxy_seq_t2_heads4_layers1

limbxy_seq_t2_heads4_layers1 is a machine learning model from c14kevincardenas. 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

19% of all-time downloads

All-time downloads

Public

Parameters

313M

61.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: custom_model
Access: Public
Created: Feb 20, 2025
Updated: Feb 20, 2025
SHA: c19e6819

Base models

c14kevincardenas/beit-large-patch16-384-limb

Model card

From the Hugging Face model README

limbxy_seq_t2_heads4_layers1

This model is a fine-tuned version of c14kevincardenas/beit-large-patch16-384-limb on the c14kevincardenas/beta_caller_284_limbxy_seq_2 dataset. It achieves the following results on the evaluation set:

Loss: 0.0050
Rmse: 0.0708

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: 32
eval_batch_size: 32
seed: 2014
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 250
num_epochs: 50.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
0.0157	1.0	150	0.0190	0.1377
0.0131	2.0	300	0.0108	0.1039
0.0078	3.0	450	0.0119	0.1090
0.0059	4.0	600	0.0070	0.0837
0.0042	5.0	750	0.0074	0.0860
0.0033	6.0	900	0.0074	0.0860
0.003	7.0	1050	0.0069	0.0831
0.0018	8.0	1200	0.0064	0.0799
0.0019	9.0	1350	0.0070	0.0835
0.0022	10.0	1500	0.0073	0.0854
0.0016	11.0	1650	0.0060	0.0774
0.0021	12.0	1800	0.0062	0.0789
0.0014	13.0	1950	0.0059	0.0766
0.0015	14.0	2100	0.0068	0.0825
0.001	15.0	2250	0.0057	0.0754
0.0009	16.0	2400	0.0057	0.0756
0.0008	17.0	2550	0.0060	0.0772
0.0008	18.0	2700	0.0065	0.0804
0.0008	19.0	2850	0.0057	0.0754
0.0009	20.0	3000	0.0061	0.0779
0.0007	21.0	3150	0.0054	0.0734
0.0008	22.0	3300	0.0054	0.0732
0.0005	23.0	3450	0.0054	0.0733
0.0006	24.0	3600	0.0057	0.0755
0.0006	25.0	3750	0.0054	0.0733
0.0005	26.0	3900	0.0054	0.0734
0.0005	27.0	4050	0.0056	0.0751
0.0005	28.0	4200	0.0052	0.0723
0.0004	29.0	4350	0.0052	0.0719
0.0004	30.0	4500	0.0052	0.0724
0.0004	31.0	4650	0.0054	0.0735
0.0003	32.0	4800	0.0052	0.0718
0.0003	33.0	4950	0.0053	0.0725
0.0003	34.0	5100	0.0050	0.0710
0.0003	35.0	5250	0.0052	0.0721
0.0003	36.0	5400	0.0051	0.0717
0.0002	37.0	5550	0.0052	0.0721
0.0002	38.0	5700	0.0052	0.0722
0.0002	39.0	5850	0.0052	0.0720
0.0002	40.0	6000	0.0052	0.0719
0.0002	41.0	6150	0.0051	0.0716
0.0002	42.0	6300	0.0051	0.0715
0.0001	43.0	6450	0.0051	0.0715
0.0002	44.0	6600	0.0051	0.0714
0.0001	45.0	6750	0.0051	0.0713
0.0001	46.0	6900	0.0050	0.0708
0.0001	47.0	7050	0.0050	0.0708
0.0001	48.0	7200	0.0050	0.0710
0.0001	49.0	7350	0.0050	0.0709
0.0001	50.0	7500	0.0050	0.0710

Framework versions

Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1

Library: transformers
Type: custom_model
License: apache-2.0
Created: Feb 20, 2025
Updated: Feb 20, 2025