Hugging Face's logo

mekjr1
/
opus-mt-en-es-finetuned-es-to-maq-v2

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
opus-mt-en-es-finetuned-es-to-maq-v2 / README.md
mekjr1's picture
mekjr1
update model card README.md
2529695
preview code
|
raw
history blame
8.7 kB
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-es
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: opus-mt-en-es-finetuned-es-to-maq-v2
    results: []

opus-mt-en-es-finetuned-es-to-maq-v2

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-es on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5183
  • Bleu: 14.1223
  • Gen Len: 80.4685

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: 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: 100

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 199 2.3315 2.9691 112.5882
No log 2.0 398 2.0603 4.7361 89.3715
2.622 3.0 597 1.9177 5.7259 93.194
2.622 4.0 796 1.8330 6.3357 91.4358
2.622 5.0 995 1.7688 6.6048 89.8879
1.912 6.0 1194 1.7188 7.3799 89.4118
1.912 7.0 1393 1.6763 8.1149 86.6839
1.7194 8.0 1592 1.6432 8.1903 88.4181
1.7194 9.0 1791 1.6160 9.0788 86.8917
1.7194 10.0 1990 1.5882 8.9414 87.0982
1.5981 11.0 2189 1.5700 9.7369 83.1587
1.5981 12.0 2388 1.5505 10.2715 83.0416
1.5 13.0 2587 1.5264 10.1412 85.67
1.5 14.0 2786 1.5210 10.4181 83.9295
1.5 15.0 2985 1.5065 10.7716 84.1209
1.425 16.0 3184 1.4937 11.5064 83.8035
1.425 17.0 3383 1.4864 11.4935 81.8463
1.3564 18.0 3582 1.4735 11.5941 81.5327
1.3564 19.0 3781 1.4645 11.7988 81.6562
1.3564 20.0 3980 1.4559 12.0264 81.8715
1.2981 21.0 4179 1.4518 12.2891 82.7179
1.2981 22.0 4378 1.4465 12.5085 80.0101
1.2462 23.0 4577 1.4403 12.5034 79.8665
1.2462 24.0 4776 1.4347 12.6431 78.9484
1.2462 25.0 4975 1.4365 12.6659 80.5214
1.2008 26.0 5174 1.4372 13.0592 80.8086
1.2008 27.0 5373 1.4306 12.4894 80.0932
1.1552 28.0 5572 1.4261 12.9738 80.034
1.1552 29.0 5771 1.4248 13.2419 79.8199
1.1552 30.0 5970 1.4239 13.1865 79.5869
1.1184 31.0 6169 1.4229 13.3942 80.8073
1.1184 32.0 6368 1.4228 13.5008 79.762
1.0828 33.0 6567 1.4211 13.7336 79.3086
1.0828 34.0 6766 1.4216 13.6096 80.738
1.0828 35.0 6965 1.4206 13.3387 81.9622
1.0484 36.0 7164 1.4226 13.627 80.6549
1.0484 37.0 7363 1.4214 13.314 79.5013
1.0159 38.0 7562 1.4214 13.6822 80.3212
1.0159 39.0 7761 1.4218 13.9024 80.573
1.0159 40.0 7960 1.4284 13.7823 80.694
0.9879 41.0 8159 1.4281 13.8635 80.8728
0.9879 42.0 8358 1.4292 14.0735 80.0365
0.9599 43.0 8557 1.4246 14.2843 80.3766
0.9599 44.0 8756 1.4349 14.0705 80.0013
0.9599 45.0 8955 1.4324 14.2379 80.8627
0.9345 46.0 9154 1.4345 14.1261 80.1146
0.9345 47.0 9353 1.4371 13.8716 80.5743
0.9099 48.0 9552 1.4387 13.8032 81.8564
0.9099 49.0 9751 1.4343 14.2119 81.1675
0.9099 50.0 9950 1.4400 13.9887 80.4106
0.8875 51.0 10149 1.4394 14.2409 81.335
0.8875 52.0 10348 1.4451 14.1096 81.0189
0.8663 53.0 10547 1.4486 14.2637 80.4509
0.8663 54.0 10746 1.4514 14.079 79.9786
0.8663 55.0 10945 1.4503 14.0559 80.4307
0.8472 56.0 11144 1.4537 14.2922 80.4534
0.8472 57.0 11343 1.4560 14.5289 80.4496
0.828 58.0 11542 1.4574 14.1122 80.1826
0.828 59.0 11741 1.4592 13.9756 80.5592
0.828 60.0 11940 1.4639 13.9926 81.9547
0.8091 61.0 12139 1.4650 14.1126 80.097
0.8091 62.0 12338 1.4639 14.1419 80.3929
0.7937 63.0 12537 1.4722 14.2943 80.8073
0.7937 64.0 12736 1.4680 13.8719 81.3753
0.7937 65.0 12935 1.4764 14.1477 80.903
0.7798 66.0 13134 1.4776 14.239 80.8312
0.7798 67.0 13333 1.4759 14.1653 80.3866
0.7657 68.0 13532 1.4796 14.092 80.1763
0.7657 69.0 13731 1.4814 14.2321 80.9433
0.7657 70.0 13930 1.4814 14.1632 80.5957
0.7514 71.0 14129 1.4850 14.0296 81.2217
0.7514 72.0 14328 1.4878 14.2263 80.6751
0.7407 73.0 14527 1.4896 13.962 81.4572
0.7407 74.0 14726 1.4920 14.225 81.1788
0.7407 75.0 14925 1.4923 13.9021 81.0176
0.7297 76.0 15124 1.4956 13.8359 80.8539
0.7297 77.0 15323 1.4972 14.1418 80.9295
0.7198 78.0 15522 1.4992 13.8721 81.0126
0.7198 79.0 15721 1.5024 14.0958 81.1788
0.7198 80.0 15920 1.4995 14.2018 80.4786
0.7099 81.0 16119 1.5032 14.074 80.8766
0.7099 82.0 16318 1.5060 14.301 79.6335
0.7042 83.0 16517 1.5047 14.0572 80.3312
0.7042 84.0 16716 1.5061 14.19 80.0126
0.7042 85.0 16915 1.5088 14.2626 79.9181
0.6953 86.0 17114 1.5093 14.1371 80.4924
0.6953 87.0 17313 1.5101 13.9727 80.6209
0.6897 88.0 17512 1.5096 14.088 80.1008
0.6897 89.0 17711 1.5137 14.117 80.5453
0.6897 90.0 17910 1.5143 13.9316 81.5428
0.6842 91.0 18109 1.5146 14.0166 80.4207
0.6842 92.0 18308 1.5156 14.073 80.6625
0.6806 93.0 18507 1.5147 14.1289 80.2481
0.6806 94.0 18706 1.5148 14.143 80.301
0.6806 95.0 18905 1.5167 13.9649 81.0227
0.6765 96.0 19104 1.5179 14.1042 79.9698
0.6765 97.0 19303 1.5174 13.9834 80.5793
0.6731 98.0 19502 1.5182 14.0637 80.5705
0.6731 99.0 19701 1.5183 14.0274 80.3199
0.6731 100.0 19900 1.5183 14.1223 80.4685

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3