finetuning-sentiment-model-3

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1781
• Accuracy: 0.6225
• F1: 0.5292

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	16	1.1234	0.5474	0.3031
No log	2.0	32	0.9975	0.6008	0.3433
No log	3.0	48	0.9438	0.6383	0.4604
No log	4.0	64	0.9385	0.6462	0.4692
No log	5.0	80	0.9864	0.6364	0.5066
No log	6.0	96	1.0309	0.6146	0.4968
No log	7.0	112	1.0853	0.6186	0.5246
No log	8.0	128	1.1456	0.6166	0.5208
No log	9.0	144	1.1860	0.6087	0.5206
No log	10.0	160	1.1781	0.6225	0.5292

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3