learn_hf_spanish_sentence_classification_by_school_subject

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

• Loss: 0.1089
• Accuracy: 0.98

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9708	1.0	7	1.4555	0.74
1.0578	2.0	14	0.7770	0.94
0.4502	3.0	21	0.4253	0.94
0.1843	4.0	28	0.3211	0.9
0.093	5.0	35	0.2449	0.94
0.057	6.0	42	0.2013	0.96
0.0375	7.0	49	0.1631	0.96
0.0266	8.0	56	0.1402	0.96
0.022	9.0	63	0.1304	0.96
0.0189	10.0	70	0.1261	0.96
0.0161	11.0	77	0.1299	0.92
0.0158	12.0	84	0.1188	0.98
0.0159	13.0	91	0.1123	0.98
0.0134	14.0	98	0.1094	0.98
0.0127	15.0	105	0.1089	0.98

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0