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: 0.0048
Rmse: 0.0692

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
0.0135	1.0	150	0.0123	0.1108
0.0102	2.0	300	0.0080	0.0892
0.0065	3.0	450	0.0107	0.1036
0.0049	4.0	600	0.0088	0.0936
0.0042	5.0	750	0.0072	0.0846
0.0033	6.0	900	0.0071	0.0841
0.0028	7.0	1050	0.0065	0.0806
0.0023	8.0	1200	0.0071	0.0842
0.0022	9.0	1350	0.0064	0.0802
0.0018	10.0	1500	0.0059	0.0766
0.0014	11.0	1650	0.0055	0.0739
0.0014	12.0	1800	0.0061	0.0781
0.0013	13.0	1950	0.0056	0.0748
0.0009	14.0	2100	0.0055	0.0743
0.0017	15.0	2250	0.0058	0.0762
0.0012	16.0	2400	0.0054	0.0736
0.0008	17.0	2550	0.0053	0.0725
0.0008	18.0	2700	0.0055	0.0740
0.0007	19.0	2850	0.0057	0.0757
0.0007	20.0	3000	0.0056	0.0746
0.0006	21.0	3150	0.0055	0.0739
0.0005	22.0	3300	0.0051	0.0717
0.0006	23.0	3450	0.0053	0.0727
0.0005	24.0	3600	0.0052	0.0720
0.0006	25.0	3750	0.0055	0.0741
0.0005	26.0	3900	0.0051	0.0714
0.0005	27.0	4050	0.0052	0.0720
0.0005	28.0	4200	0.0053	0.0725
0.0003	29.0	4350	0.0051	0.0712
0.0004	30.0	4500	0.0051	0.0717
0.0004	31.0	4650	0.0052	0.0719
0.0003	32.0	4800	0.0052	0.0720
0.0003	33.0	4950	0.0051	0.0715
0.0002	34.0	5100	0.0053	0.0731
0.0003	35.0	5250	0.0052	0.0723
0.0002	36.0	5400	0.0050	0.0708
0.0002	37.0	5550	0.0049	0.0703
0.0002	38.0	5700	0.0050	0.0708
0.0002	39.0	5850	0.0049	0.0700
0.0002	40.0	6000	0.0049	0.0698
0.0002	41.0	6150	0.0049	0.0699
0.0002	42.0	6300	0.0049	0.0701
0.0001	43.0	6450	0.0049	0.0697
0.0002	44.0	6600	0.0049	0.0698
0.0001	45.0	6750	0.0048	0.0696
0.0001	46.0	6900	0.0048	0.0692
0.0001	47.0	7050	0.0048	0.0694
0.0001	48.0	7200	0.0048	0.0694
0.0001	49.0	7350	0.0048	0.0692
0.0001	50.0	7500	0.0048	0.0693

Framework versions

Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1

c14kevincardenas/limbxy_seq_t2_heads2_layers1

limbxy_seq_t2_heads2_layers1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

c14kevincardenas/
limbxy_seq_t2_heads2_layers1