ania3000/glot500-base-kuoss-morph

trainer_output

This model is a fine-tuned version of cis-lmu/glot500-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6143
• Accuracy: 92.6801
• Sentence accuracy: 49.6136

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Sentence accuracy
3.2625	1.0	596	1.9812	68.8441	6.6461
1.4589	2.0	1192	1.1165	80.5189	16.2287
0.8781	3.0	1788	0.8618	86.7153	29.9845
0.6031	4.0	2384	0.7105	88.6148	34.9304
0.4735	5.0	2980	0.6176	90.0510	39.1036
0.2919	6.0	3576	0.5885	90.7575	42.5039
0.239	7.0	4172	0.5611	91.1860	43.4312
0.2052	8.0	4768	0.5484	91.7188	44.2040
0.1687	9.0	5364	0.5352	91.9620	45.2859
0.1489	10.0	5960	0.5616	92.1010	47.1406
0.1057	11.0	6556	0.5477	92.4137	46.0587
0.0928	12.0	7152	0.5564	92.7264	48.3771
0.0795	13.0	7748	0.5865	92.7033	48.0680
0.0665	14.0	8344	0.5894	92.6917	48.5317
0.0603	15.0	8940	0.6033	92.6685	48.6862
0.044	16.0	9536	0.6143	92.6801	49.6136

Framework versions

• Transformers 4.57.3
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2