clasificador-tweets

This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on the somosnlp-hackathon-2022/es_tweets_laboral dataset. It achieves the following results on the evaluation set:

• Loss: 1.4954
• Accuracy: 0.7021

Intended uses & limitations

This model is intended for the task Text Classification.

Training and evaluation data

We used the somosnlp-hackathon-2022/es_tweets_laboral dataset.

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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	23	1.2185	0.6383
No log	2.0	46	1.2849	0.6596
No log	3.0	69	1.4492	0.5957
No log	4.0	92	1.1863	0.7234
No log	5.0	115	1.5050	0.6383
No log	6.0	138	1.4848	0.6383
No log	7.0	161	1.5045	0.7021
No log	8.0	184	1.5510	0.6809
No log	9.0	207	1.4867	0.7021
No log	10.0	230	1.4954	0.7021

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0