metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: esp-to-lsm-model-split
results: []
esp-to-lsm-model-split
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5690
- Bleu: 83.5807
- Rouge: {'rouge1': 0.9265753592812418, 'rouge2': 0.8656694324194325, 'rougeL': 0.9238164847135437, 'rougeLsum': 0.9238003663003664}
- Ter Score: 10.0090
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: 0.00015
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge | Ter Score |
|---|---|---|---|---|---|---|
| 0.997 | 1.0 | 75 | 0.7578 | 74.2121 | {'rouge1': 0.8930136077372922, 'rouge2': 0.8132252290193469, 'rougeL': 0.8868313923778324, 'rougeLsum': 0.8866414102466736} | 16.3210 |
| 0.4353 | 2.0 | 150 | 0.5659 | 50.7443 | {'rouge1': 0.9142509364274071, 'rouge2': 0.83197113997114, 'rougeL': 0.9055773276287983, 'rougeLsum': 0.9062817797670736} | 12.8043 |
| 0.2602 | 3.0 | 225 | 0.5444 | 72.0122 | {'rouge1': 0.9183889862860454, 'rouge2': 0.8433486969005839, 'rougeL': 0.9132635343958876, 'rougeLsum': 0.913651539908893} | 15.9603 |
| 0.2316 | 4.0 | 300 | 0.5503 | 50.9502 | {'rouge1': 0.9147289323852568, 'rouge2': 0.8403040453698347, 'rougeL': 0.9084138578656601, 'rougeLsum': 0.9084760810455303} | 13.0748 |
| 0.1203 | 5.0 | 375 | 0.5211 | 58.7666 | {'rouge1': 0.9278827629661555, 'rouge2': 0.8655444837508406, 'rougeL': 0.922415336132431, 'rougeLsum': 0.9224576705147474} | 29.6664 |
| 0.1216 | 6.0 | 450 | 0.5491 | 81.6262 | {'rouge1': 0.9206053007450066, 'rouge2': 0.8534470899470898, 'rougeL': 0.9171148252618841, 'rougeLsum': 0.9168772093919156} | 11.0911 |
| 0.0754 | 7.0 | 525 | 0.5095 | 83.4616 | {'rouge1': 0.9305456776339132, 'rouge2': 0.8778395262145262, 'rougeL': 0.9280110015257075, 'rougeLsum': 0.9281936805025043} | 10.0090 |
| 0.0848 | 8.0 | 600 | 0.5538 | 81.8681 | {'rouge1': 0.9248025063172123, 'rouge2': 0.8648207579457581, 'rougeL': 0.9219360612154733, 'rougeLsum': 0.921904937654938} | 10.4599 |
| 0.0504 | 9.0 | 675 | 0.5390 | 80.8118 | {'rouge1': 0.9217618560633272, 'rouge2': 0.8611767121767122, 'rougeL': 0.9194047336106163, 'rougeLsum': 0.9196579346579348} | 12.3535 |
| 0.0367 | 10.0 | 750 | 0.5632 | 82.2896 | {'rouge1': 0.9241220549602904, 'rouge2': 0.8623059255559258, 'rougeL': 0.921636625901332, 'rougeLsum': 0.9214262796027506} | 10.8206 |
| 0.0386 | 11.0 | 825 | 0.5325 | 83.7819 | {'rouge1': 0.9264862667289138, 'rouge2': 0.8665701058201061, 'rougeL': 0.924734155278273, 'rougeLsum': 0.9247572857425799} | 10.2795 |
| 0.0377 | 12.0 | 900 | 0.5540 | 83.6969 | {'rouge1': 0.9270570480717542, 'rouge2': 0.8649807692307694, 'rougeL': 0.9248777127012422, 'rougeLsum': 0.9247459680842035} | 10.0090 |
| 0.0244 | 13.0 | 975 | 0.5462 | 83.4825 | {'rouge1': 0.9284353783471431, 'rouge2': 0.8673707311207314, 'rougeL': 0.9249773075508372, 'rougeLsum': 0.924672456084221} | 9.9188 |
| 0.0237 | 14.0 | 1050 | 0.5468 | 83.3820 | {'rouge1': 0.9267599383187618, 'rouge2': 0.8631084656084658, 'rougeL': 0.9244043657867187, 'rougeLsum': 0.9240160215601393} | 10.0992 |
| 0.0173 | 15.0 | 1125 | 0.5604 | 82.7936 | {'rouge1': 0.9260569985569987, 'rouge2': 0.8652394179894183, 'rougeL': 0.923313301078007, 'rougeLsum': 0.9233026695526696} | 10.1894 |
| 0.0193 | 16.0 | 1200 | 0.5689 | 85.1028 | {'rouge1': 0.9298936104744928, 'rouge2': 0.874325396825397, 'rougeL': 0.9280833015024192, 'rougeLsum': 0.9275536633845459} | 9.6483 |
| 0.0184 | 17.0 | 1275 | 0.5695 | 83.7781 | {'rouge1': 0.9266896553881849, 'rouge2': 0.8650757020757022, 'rougeL': 0.924688972247796, 'rougeLsum': 0.9245597692068284} | 10.2795 |
| 0.0142 | 18.0 | 1350 | 0.5655 | 83.6649 | {'rouge1': 0.925748337718926, 'rouge2': 0.8645625300625305, 'rougeL': 0.9233836055012529, 'rougeLsum': 0.9233253614577146} | 10.0090 |
| 0.0131 | 19.0 | 1425 | 0.5701 | 83.6843 | {'rouge1': 0.9268515199397553, 'rouge2': 0.8660478595478597, 'rougeL': 0.9242069248833956, 'rougeLsum': 0.9242629070276129} | 9.9188 |
| 0.0122 | 20.0 | 1500 | 0.5690 | 83.5807 | {'rouge1': 0.9265753592812418, 'rouge2': 0.8656694324194325, 'rougeL': 0.9238164847135437, 'rougeLsum': 0.9238003663003664} | 10.0090 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.13.3