Hugging Face's logo

Vichentito
/
Nahuatl_Espanol_vn

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Nahuatl_Espanol_vn / README.md
Vichentito's picture
Vichentito
End of training
e9b1c93 verified
preview code
|
raw
history blame
No virus
8.14 kB
metadata
license: apache-2.0
base_model: Vichentito/Nahuatl_Espanol_v2
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: Nahuatl_Espanol_vn
    results: []

Nahuatl_Espanol_vn

This model is a fine-tuned version of Vichentito/Nahuatl_Espanol_v2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4730
  • Bleu: 12.6156
  • Gen Len: 46.1122

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: 0.0003
  • 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: 10

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 0.1064 100 1.9442 6.1166 48.8218
No log 0.2128 200 1.9259 6.1381 50.998
No log 0.3191 300 1.9115 6.573 48.1678
No log 0.4255 400 1.8855 6.4758 50.9589
2.137 0.5319 500 1.8646 6.6628 50.1324
2.137 0.6383 600 1.8440 6.8852 50.913
2.137 0.7447 700 1.8311 6.879 49.7563
2.137 0.8511 800 1.8105 7.268 48.5967
2.137 0.9574 900 1.7907 7.5189 47.8909
2.0246 1.0638 1000 1.7790 7.8039 49.7481
2.0246 1.1702 1100 1.7751 7.8132 47.9985
2.0246 1.2766 1200 1.7505 7.9468 47.9796
2.0246 1.3830 1300 1.7378 8.1741 47.8028
2.0246 1.4894 1400 1.7219 8.1614 48.2161
1.8778 1.5957 1500 1.7178 8.3463 47.3984
1.8778 1.7021 1600 1.7051 8.8493 48.1068
1.8778 1.8085 1700 1.6907 8.5621 48.2402
1.8778 1.9149 1800 1.6849 8.7522 49.7167
1.8778 2.0213 1900 1.6738 8.9027 47.812
1.7945 2.1277 2000 1.6718 9.323 47.1293
1.7945 2.2340 2100 1.6619 9.1801 46.7211
1.7945 2.3404 2200 1.6509 9.1763 47.085
1.7945 2.4468 2300 1.6394 9.2575 47.9275
1.7945 2.5532 2400 1.6388 9.5591 47.2517
1.7164 2.6596 2500 1.6336 9.5656 47.996
1.7164 2.7660 2600 1.6205 9.767 47.4039
1.7164 2.8723 2700 1.6152 9.5891 47.2867
1.7164 2.9787 2800 1.6074 9.7122 47.3419
1.7164 3.0851 2900 1.6122 10.1634 47.2597
1.6476 3.1915 3000 1.6016 10.0543 47.7276
1.6476 3.2979 3100 1.5939 9.8821 47.8567
1.6476 3.4043 3200 1.5922 10.1382 47.8498
1.6476 3.5106 3300 1.5808 10.1617 46.7866
1.6476 3.6170 3400 1.5780 10.2872 47.1357
1.5916 3.7234 3500 1.5713 10.3594 47.6514
1.5916 3.8298 3600 1.5657 10.3745 46.9836
1.5916 3.9362 3700 1.5594 10.5178 46.7624
1.5916 4.0426 3800 1.5704 10.665 46.6844
1.5916 4.1489 3900 1.5589 10.6936 47.1421
1.5475 4.2553 4000 1.5541 10.7949 46.8528
1.5475 4.3617 4100 1.5481 10.631 47.3707
1.5475 4.4681 4200 1.5468 10.8283 46.5979
1.5475 4.5745 4300 1.5403 10.9811 47.1724
1.5475 4.6809 4400 1.5356 11.0659 46.682
1.4988 4.7872 4500 1.5379 11.0334 46.9275
1.4988 4.8936 4600 1.5257 10.9602 46.5027
1.4988 5.0 4700 1.5260 11.1289 46.8976
1.4988 5.1064 4800 1.5311 11.1567 46.4451
1.4988 5.2128 4900 1.5274 11.3486 46.6272
1.4535 5.3191 5000 1.5259 11.2413 46.9351
1.4535 5.4255 5100 1.5215 11.3214 46.8237
1.4535 5.5319 5200 1.5129 11.4718 47.1328
1.4535 5.6383 5300 1.5125 11.4864 46.6589
1.4535 5.7447 5400 1.5121 11.5694 46.5577
1.4219 5.8511 5500 1.5036 11.6487 46.5487
1.4219 5.9574 5600 1.5000 11.5189 46.5733
1.4219 6.0638 5700 1.5075 11.5882 46.5391
1.4219 6.1702 5800 1.5096 11.7659 46.1593
1.4219 6.2766 5900 1.5083 11.5189 46.4194
1.3736 6.3830 6000 1.4987 11.7254 46.3748
1.3736 6.4894 6100 1.4974 11.709 46.7318
1.3736 6.5957 6200 1.4940 11.7516 46.5484
1.3736 6.7021 6300 1.4918 11.828 46.4844
1.3736 6.8085 6400 1.4933 11.9539 46.5024
1.3705 6.9149 6500 1.4856 11.8196 46.6158
1.3705 7.0213 6600 1.4959 11.8671 46.5148
1.3705 7.1277 6700 1.4959 11.9404 46.1803
1.3705 7.2340 6800 1.4974 12.0784 46.2473
1.3705 7.3404 6900 1.4882 12.3014 46.27
1.3223 7.4468 7000 1.4813 12.0859 46.5862
1.3223 7.5532 7100 1.4846 12.1787 46.0993
1.3223 7.6596 7200 1.4853 12.1633 46.142
1.3223 7.7660 7300 1.4811 12.1962 46.4309
1.3223 7.8723 7400 1.4819 12.1183 46.0882
1.3154 7.9787 7500 1.4757 12.2428 46.2431
1.3154 8.0851 7600 1.4811 12.2027 46.3626
1.3154 8.1915 7700 1.4803 12.3011 46.328
1.3154 8.2979 7800 1.4830 12.2846 46.3101
1.3154 8.4043 7900 1.4808 12.3297 45.987
1.2766 8.5106 8000 1.4789 12.3831 46.1575
1.2766 8.6170 8100 1.4774 12.4203 46.2323
1.2766 8.7234 8200 1.4737 12.5194 46.2774
1.2766 8.8298 8300 1.4738 12.3472 46.2114
1.2766 8.9362 8400 1.4687 12.3894 46.3324
1.2752 9.0426 8500 1.4748 12.4876 46.0959
1.2752 9.1489 8600 1.4792 12.597 45.985
1.2752 9.2553 8700 1.4761 12.5547 46.2209
1.2752 9.3617 8800 1.4759 12.5615 46.0812
1.2752 9.4681 8900 1.4752 12.5736 46.1437
1.2454 9.5745 9000 1.4765 12.5976 46.0358
1.2454 9.6809 9100 1.4745 12.5204 46.1139
1.2454 9.7872 9200 1.4735 12.5765 46.107
1.2454 9.8936 9300 1.4732 12.5875 46.1734
1.2454 10.0 9400 1.4730 12.6156 46.1122

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1