Prototipo_3_EMI

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

• Loss: 1.2540
• Accuracy: 0.5423

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: 3e-05
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2186	0.1778	200	1.1556	0.4803
1.1345	0.3556	400	1.0663	0.525
1.102	0.5333	600	1.0479	0.5293
1.1325	0.7111	800	1.0483	0.5353
1.1211	0.8889	1000	1.0337	0.521
0.9736	1.0667	1200	1.0006	0.5503
0.9428	1.2444	1400	1.0214	0.5523
0.9095	1.4222	1600	1.0174	0.555
0.9806	1.6	1800	1.0155	0.5527
0.969	1.7778	2000	1.0043	0.5547
0.9112	1.9556	2200	1.0050	0.5537
0.7557	2.1333	2400	1.0496	0.5607
0.8212	2.3111	2600	1.0494	0.5597
0.7695	2.4889	2800	1.0510	0.5687
0.7648	2.6667	3000	1.0513	0.5603
0.8232	2.8444	3200	1.0316	0.563
0.6288	3.0222	3400	1.0883	0.5503
0.6736	3.2	3600	1.1232	0.548
0.682	3.3778	3800	1.1695	0.543
0.6682	3.5556	4000	1.1608	0.5427
0.6516	3.7333	4200	1.1636	0.545
0.6731	3.9111	4400	1.1694	0.5403
0.5388	4.0889	4600	1.2120	0.544
0.5663	4.2667	4800	1.2278	0.544
0.5579	4.4444	5000	1.2439	0.538
0.5216	4.6222	5200	1.2507	0.5427
0.4634	4.8	5400	1.2531	0.5393
0.5359	4.9778	5600	1.2540	0.5423

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1