Multilingual-MiniLM-L12-H384-finetunned-elementos-contractuales

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3775
• Accuracy: 0.9191
• F1: 0.8991

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	23	0.9210	0.7353	0.6231
No log	2.0	46	0.7792	0.7353	0.6231
No log	3.0	69	0.7253	0.7059	0.6319
No log	4.0	92	0.5066	0.9162	0.8966
No log	5.0	115	0.4528	0.9191	0.8993
No log	6.0	138	0.4201	0.9221	0.9021
No log	7.0	161	0.4033	0.9206	0.9013
No log	8.0	184	0.3979	0.9132	0.8928
No log	9.0	207	0.3777	0.9221	0.9027
No log	10.0	230	0.3775	0.9191	0.8991

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1