limb_xy

This model is a fine-tuned version of c14kevincardenas/beit-large-patch16-384-limb on the c14kevincardenas/beta_caller_284_target_hold dataset. It achieves the following results on the evaluation set:

• Loss: 0.3274
• Rmse: 0.5722

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: 64
• eval_batch_size: 64
• 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: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
0.3316	1.0	100	0.3274	0.5722
0.3244	2.0	200	0.3274	0.5722
0.3326	3.0	300	0.3274	0.5722
0.3272	4.0	400	0.3274	0.5722
0.3316	5.0	500	0.3274	0.5722
0.3308	6.0	600	0.3274	0.5722
0.3304	7.0	700	0.3274	0.5722
0.3254	8.0	800	0.3274	0.5722
0.3316	9.0	900	0.3274	0.5722
0.3301	10.0	1000	0.3274	0.5722
0.3291	11.0	1100	0.3274	0.5722
0.3326	12.0	1200	0.3274	0.5722
0.331	13.0	1300	0.3274	0.5722
0.3292	14.0	1400	0.3274	0.5722
0.3309	15.0	1500	0.3274	0.5722
0.3329	16.0	1600	0.3274	0.5722
0.3286	17.0	1700	0.3274	0.5722
0.334	18.0	1800	0.3274	0.5722
0.3336	19.0	1900	0.3274	0.5722
0.3296	20.0	2000	0.3274	0.5722

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1