metadata

license: mit
base_model: facebook/esm2_t33_650M_UR50D
tags:
  - generated_from_trainer
model-index:
  - name: esm2_t33_650M_UR50D-finetuned-localization
    results: []

esm2_t33_650M_UR50D-finetuned-localization

This model is a fine-tuned version of facebook/esm2_t33_650M_UR50D on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1216
Rmse: 1.0591

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: 2e-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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
No log	1.0	226	1.2900	1.1358
No log	2.0	452	1.3499	1.1618
1.1023	3.0	678	1.0602	1.0297
1.1023	4.0	904	1.2692	1.1266
0.4485	5.0	1130	1.3467	1.1605
0.4485	6.0	1356	1.2897	1.1356
0.2574	7.0	1582	1.1185	1.0576
0.2574	8.0	1808	1.2362	1.1119
0.1358	9.0	2034	1.1828	1.0876
0.1358	10.0	2260	1.1376	1.0666
0.1358	11.0	2486	1.3182	1.1481
0.1139	12.0	2712	1.1802	1.0864
0.1139	13.0	2938	1.1709	1.0821
0.0587	14.0	3164	1.1167	1.0568
0.0587	15.0	3390	1.0711	1.0350
0.0369	16.0	3616	1.1464	1.0707
0.0369	17.0	3842	1.1536	1.0741
0.0183	18.0	4068	1.1041	1.0507
0.0183	19.0	4294	1.1113	1.0542
0.0106	20.0	4520	1.1453	1.0702
0.0106	21.0	4746	1.1076	1.0524
0.0106	22.0	4972	1.1358	1.0657
0.0053	23.0	5198	1.1298	1.0629
0.0053	24.0	5424	1.1182	1.0575
0.0007	25.0	5650	1.1216	1.0591

Framework versions

Transformers 4.42.4
Pytorch 2.3.1
Datasets 2.20.0
Tokenizers 0.19.1