Text Classification
Transformers
Joblib
Safetensors
multilingual
binary-classification
amis
agriculture
Instructions to use faodl/agri-soybeans-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use faodl/agri-soybeans-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="faodl/agri-soybeans-classifier")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("faodl/agri-soybeans-classifier", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "created_at": "2026-05-19T20:13:44.207534+00:00", | |
| "config": { | |
| "hf_dataset": "faodl/amis-agri-soybeans", | |
| "hf_subset": null, | |
| "train_split": "train", | |
| "validation_split": "validation", | |
| "test_split": "test", | |
| "text_col": "chunk_text", | |
| "label_col": "label", | |
| "group_col": "id", | |
| "id_col": "chunk_id", | |
| "model_name": "distilbert/distilbert-base-multilingual-cased", | |
| "output_dir": "/content/agri-soybeans-classifier", | |
| "max_length": 256, | |
| "learning_rate": 2e-05, | |
| "weight_decay": 0.01, | |
| "num_train_epochs": 5.0, | |
| "per_device_train_batch_size": 16, | |
| "per_device_eval_batch_size": 32, | |
| "gradient_accumulation_steps": 1, | |
| "warmup_ratio": 0.1, | |
| "early_stopping_patience": 2, | |
| "seed": 42, | |
| "metric_for_best_model": "f1", | |
| "skip_transformer": false, | |
| "skip_baselines": false, | |
| "baseline_models": [ | |
| "logistic", | |
| "xgboost", | |
| "embedding-logistic", | |
| "embedding-svm", | |
| "embedding-lightgbm" | |
| ], | |
| "tfidf_max_features": 50000, | |
| "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", | |
| "embedding_batch_size": 64, | |
| "positive_label_name": "RELEVANT", | |
| "negative_label_name": "NOT_RELEVANT", | |
| "push_to_hub": true, | |
| "hub_model_id": "faodl/agri-soybeans-classifier", | |
| "hub_private_repo": false | |
| }, | |
| "dataset_summary": { | |
| "train": { | |
| "rows": 4745, | |
| "labels": { | |
| "0": 3860, | |
| "1": 885 | |
| }, | |
| "unique_groups": 2244, | |
| "text_length_mean": 702.3989462592202, | |
| "text_length_median": 794.0 | |
| }, | |
| "validation": { | |
| "rows": 1034, | |
| "labels": { | |
| "0": 782, | |
| "1": 252 | |
| }, | |
| "unique_groups": 481, | |
| "text_length_mean": 710.2852998065764, | |
| "text_length_median": 795.0 | |
| }, | |
| "test": { | |
| "rows": 1074, | |
| "labels": { | |
| "0": 889, | |
| "1": 185 | |
| }, | |
| "unique_groups": 482, | |
| "text_length_mean": 708.6173184357542, | |
| "text_length_median": 794.0 | |
| } | |
| }, | |
| "results": [ | |
| { | |
| "model_type": "logistic_tfidf", | |
| "model_name": "logistic", | |
| "artifact_dir": "/content/agri-soybeans-classifier/baselines/logistic", | |
| "artifact_file": "/content/agri-soybeans-classifier/baselines/logistic/logistic_tfidf.joblib", | |
| "validation_best_threshold": { | |
| "threshold": 0.45412653657308116, | |
| "f1": 0.8698884758364314, | |
| "precision": 0.8181818181818182, | |
| "recall": 0.9285714285714286 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9441340782122905, | |
| "precision": 0.8048780487804879, | |
| "recall": 0.8918918918918919, | |
| "f1": 0.8461538461538461, | |
| "confusion_matrix": [ | |
| [ | |
| 849, | |
| 40 | |
| ], | |
| [ | |
| 20, | |
| 165 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9769850402761795, | |
| "recall": 0.9550056242969629, | |
| "f1-score": 0.9658703071672355, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8048780487804879, | |
| "recall": 0.8918918918918919, | |
| "f1-score": 0.8461538461538461, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9441340782122905, | |
| "macro avg": { | |
| "precision": 0.8909315445283337, | |
| "recall": 0.9234487580944274, | |
| "f1-score": 0.9060120766605408, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9473390501209625, | |
| "recall": 0.9441340782122905, | |
| "f1-score": 0.9452487566202364, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9665278326695649, | |
| "average_precision": 0.9143444807696574 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.45412653657308116, | |
| "accuracy": 0.9413407821229051, | |
| "precision": 0.7850467289719626, | |
| "recall": 0.9081081081081082, | |
| "f1": 0.8421052631578947, | |
| "confusion_matrix": [ | |
| [ | |
| 843, | |
| 46 | |
| ], | |
| [ | |
| 17, | |
| 168 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9802325581395349, | |
| "recall": 0.9482564679415073, | |
| "f1-score": 0.9639794168096055, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.7850467289719626, | |
| "recall": 0.9081081081081082, | |
| "f1-score": 0.8421052631578947, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9413407821229051, | |
| "macro avg": { | |
| "precision": 0.8826396435557488, | |
| "recall": 0.9281822880248077, | |
| "f1-score": 0.9030423399837502, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9466111629849717, | |
| "recall": 0.9413407821229051, | |
| "f1-score": 0.9429861966740687, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9665278326695649, | |
| "average_precision": 0.9143444807696574 | |
| } | |
| }, | |
| { | |
| "model_type": "xgboost_tfidf", | |
| "model_name": "xgboost", | |
| "artifact_dir": "/content/agri-soybeans-classifier/baselines/xgboost", | |
| "artifact_file": "/content/agri-soybeans-classifier/baselines/xgboost/xgboost_tfidf.joblib", | |
| "validation_best_threshold": { | |
| "threshold": 0.5492749810218811, | |
| "f1": 0.9000000000000001, | |
| "precision": 0.907258064516129, | |
| "recall": 0.8928571428571429 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9543761638733705, | |
| "precision": 0.8953488372093024, | |
| "recall": 0.8324324324324325, | |
| "f1": 0.8627450980392157, | |
| "confusion_matrix": [ | |
| [ | |
| 871, | |
| 18 | |
| ], | |
| [ | |
| 31, | |
| 154 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9656319290465631, | |
| "recall": 0.9797525309336333, | |
| "f1-score": 0.972640982691234, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8953488372093024, | |
| "recall": 0.8324324324324325, | |
| "f1-score": 0.8627450980392157, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9543761638733705, | |
| "macro avg": { | |
| "precision": 0.9304903831279328, | |
| "recall": 0.9060924816830329, | |
| "f1-score": 0.9176930403652248, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9535254374358618, | |
| "recall": 0.9543761638733705, | |
| "f1-score": 0.9537110584262215, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9635028729516919, | |
| "average_precision": 0.8960212274222826 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.5492749810218811, | |
| "accuracy": 0.9553072625698324, | |
| "precision": 0.9053254437869822, | |
| "recall": 0.827027027027027, | |
| "f1": 0.864406779661017, | |
| "confusion_matrix": [ | |
| [ | |
| 873, | |
| 16 | |
| ], | |
| [ | |
| 32, | |
| 153 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9646408839779006, | |
| "recall": 0.9820022497187851, | |
| "f1-score": 0.9732441471571907, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.9053254437869822, | |
| "recall": 0.827027027027027, | |
| "f1-score": 0.864406779661017, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9553072625698324, | |
| "macro avg": { | |
| "precision": 0.9349831638824414, | |
| "recall": 0.9045146383729061, | |
| "f1-score": 0.9188254634091038, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9544236061051633, | |
| "recall": 0.9553072625698324, | |
| "f1-score": 0.9544965559218163, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9635028729516919, | |
| "average_precision": 0.8960212274222826 | |
| } | |
| }, | |
| { | |
| "model_type": "embedding-logistic_sentence_embeddings", | |
| "model_name": "logistic", | |
| "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", | |
| "artifact_dir": "/content/agri-soybeans-classifier/baselines/embedding-logistic", | |
| "artifact_file": "/content/agri-soybeans-classifier/baselines/embedding-logistic/embedding-logistic.joblib", | |
| "validation_best_threshold": { | |
| "threshold": 0.6469514995226564, | |
| "f1": 0.8506616257088847, | |
| "precision": 0.8122743682310469, | |
| "recall": 0.8928571428571429 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9385474860335196, | |
| "precision": 0.7531914893617021, | |
| "recall": 0.9567567567567568, | |
| "f1": 0.8428571428571429, | |
| "confusion_matrix": [ | |
| [ | |
| 831, | |
| 58 | |
| ], | |
| [ | |
| 8, | |
| 177 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9904648390941597, | |
| "recall": 0.9347581552305961, | |
| "f1-score": 0.9618055555555556, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.7531914893617021, | |
| "recall": 0.9567567567567568, | |
| "f1-score": 0.8428571428571429, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9385474860335196, | |
| "macro avg": { | |
| "precision": 0.8718281642279309, | |
| "recall": 0.9457574559936764, | |
| "f1-score": 0.9023313492063492, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9495937313655706, | |
| "recall": 0.9385474860335196, | |
| "f1-score": 0.941316303833762, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.98785151856018, | |
| "average_precision": 0.951385005586427 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.6469514995226564, | |
| "accuracy": 0.9543761638733705, | |
| "precision": 0.8366336633663366, | |
| "recall": 0.9135135135135135, | |
| "f1": 0.8733850129198967, | |
| "confusion_matrix": [ | |
| [ | |
| 856, | |
| 33 | |
| ], | |
| [ | |
| 16, | |
| 169 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.981651376146789, | |
| "recall": 0.9628796400449944, | |
| "f1-score": 0.9721749006246451, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8366336633663366, | |
| "recall": 0.9135135135135135, | |
| "f1-score": 0.8733850129198967, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9543761638733705, | |
| "macro avg": { | |
| "precision": 0.9091425197565628, | |
| "recall": 0.9381965767792539, | |
| "f1-score": 0.9227799567722709, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9566716025300445, | |
| "recall": 0.9543761638733705, | |
| "f1-score": 0.9551580205265273, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.98785151856018, | |
| "average_precision": 0.951385005586427 | |
| } | |
| }, | |
| { | |
| "model_type": "embedding-svm_sentence_embeddings", | |
| "model_name": "svm", | |
| "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", | |
| "artifact_dir": "/content/agri-soybeans-classifier/baselines/embedding-svm", | |
| "artifact_file": "/content/agri-soybeans-classifier/baselines/embedding-svm/embedding-svm.joblib", | |
| "validation_best_threshold": { | |
| "threshold": 0.37877199430477043, | |
| "f1": 0.8403041825095057, | |
| "precision": 0.8065693430656934, | |
| "recall": 0.876984126984127 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.957169459962756, | |
| "precision": 0.8839779005524862, | |
| "recall": 0.8648648648648649, | |
| "f1": 0.8743169398907104, | |
| "confusion_matrix": [ | |
| [ | |
| 868, | |
| 21 | |
| ], | |
| [ | |
| 25, | |
| 160 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9720044792833147, | |
| "recall": 0.9763779527559056, | |
| "f1-score": 0.9741863075196409, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8839779005524862, | |
| "recall": 0.8648648648648649, | |
| "f1-score": 0.8743169398907104, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.957169459962756, | |
| "macro avg": { | |
| "precision": 0.9279911899179004, | |
| "recall": 0.9206214088103852, | |
| "f1-score": 0.9242516237051757, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.956841614231915, | |
| "recall": 0.957169459962756, | |
| "f1-score": 0.9569834834867246, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.98772383181832, | |
| "average_precision": 0.9492625541246242 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.37877199430477043, | |
| "accuracy": 0.9553072625698324, | |
| "precision": 0.8477157360406091, | |
| "recall": 0.9027027027027027, | |
| "f1": 0.8743455497382199, | |
| "confusion_matrix": [ | |
| [ | |
| 859, | |
| 30 | |
| ], | |
| [ | |
| 18, | |
| 167 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9794754846066135, | |
| "recall": 0.9662542182227222, | |
| "f1-score": 0.9728199320498301, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8477157360406091, | |
| "recall": 0.9027027027027027, | |
| "f1-score": 0.8743455497382199, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9553072625698324, | |
| "macro avg": { | |
| "precision": 0.9135956103236114, | |
| "recall": 0.9344784604627124, | |
| "f1-score": 0.9235827408940249, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9567794385314637, | |
| "recall": 0.9553072625698324, | |
| "f1-score": 0.9558573987838637, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.98772383181832, | |
| "average_precision": 0.9492625541246242 | |
| } | |
| }, | |
| { | |
| "model_type": "embedding-lightgbm_sentence_embeddings", | |
| "model_name": "lightgbm", | |
| "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", | |
| "artifact_dir": "/content/agri-soybeans-classifier/baselines/embedding-lightgbm", | |
| "artifact_file": "/content/agri-soybeans-classifier/baselines/embedding-lightgbm/embedding-lightgbm.joblib", | |
| "validation_best_threshold": { | |
| "threshold": 0.42851684417216673, | |
| "f1": 0.8473895582329317, | |
| "precision": 0.8577235772357723, | |
| "recall": 0.8373015873015873 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9590316573556797, | |
| "precision": 0.8938547486033519, | |
| "recall": 0.8648648648648649, | |
| "f1": 0.8791208791208791, | |
| "confusion_matrix": [ | |
| [ | |
| 870, | |
| 19 | |
| ], | |
| [ | |
| 25, | |
| 160 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9720670391061452, | |
| "recall": 0.9786276715410573, | |
| "f1-score": 0.9753363228699552, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8938547486033519, | |
| "recall": 0.8648648648648649, | |
| "f1-score": 0.8791208791208791, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9590316573556797, | |
| "macro avg": { | |
| "precision": 0.9329608938547486, | |
| "recall": 0.9217462682029611, | |
| "f1-score": 0.9272286009954172, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9585947171852729, | |
| "recall": 0.9590316573556797, | |
| "f1-score": 0.9587628991329169, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9852369805125711, | |
| "average_precision": 0.9499432525904906 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.42851684417216673, | |
| "accuracy": 0.9590316573556797, | |
| "precision": 0.8895027624309392, | |
| "recall": 0.8702702702702703, | |
| "f1": 0.8797814207650273, | |
| "confusion_matrix": [ | |
| [ | |
| 869, | |
| 20 | |
| ], | |
| [ | |
| 24, | |
| 161 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.973124300111982, | |
| "recall": 0.9775028121484814, | |
| "f1-score": 0.9753086419753086, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8895027624309392, | |
| "recall": 0.8702702702702703, | |
| "f1-score": 0.8797814207650273, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9590316573556797, | |
| "macro avg": { | |
| "precision": 0.9313135312714607, | |
| "recall": 0.9238865412093759, | |
| "f1-score": 0.927545031370168, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9587202177367556, | |
| "recall": 0.9590316573556797, | |
| "f1-score": 0.9588537668133889, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9852369805125711, | |
| "average_precision": 0.9499432525904906 | |
| } | |
| }, | |
| { | |
| "model_type": "transformer", | |
| "model_name": "distilbert/distilbert-base-multilingual-cased", | |
| "artifact_dir": "/content/agri-soybeans-classifier/transformer", | |
| "validation_best_threshold": { | |
| "threshold": 0.4926762878894806, | |
| "f1": 0.9236790606653621, | |
| "precision": 0.9111969111969112, | |
| "recall": 0.9365079365079365 | |
| }, | |
| "test_default_0_5": { | |
| "threshold": 0.5, | |
| "accuracy": 0.9543761638733705, | |
| "precision": 0.8820224719101124, | |
| "recall": 0.8486486486486486, | |
| "f1": 0.8650137741046832, | |
| "confusion_matrix": [ | |
| [ | |
| 868, | |
| 21 | |
| ], | |
| [ | |
| 28, | |
| 157 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.96875, | |
| "recall": 0.9763779527559056, | |
| "f1-score": 0.9725490196078431, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.8820224719101124, | |
| "recall": 0.8486486486486486, | |
| "f1-score": 0.8650137741046832, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9543761638733705, | |
| "macro avg": { | |
| "precision": 0.9253862359550562, | |
| "recall": 0.9125133007022771, | |
| "f1-score": 0.9187813968562631, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9538109006549076, | |
| "recall": 0.9543761638733705, | |
| "f1-score": 0.9540257231291798, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9756270331073482, | |
| "average_precision": 0.9289986926848062 | |
| }, | |
| "test_optimal_threshold": { | |
| "threshold": 0.4926762878894806, | |
| "accuracy": 0.9553072625698324, | |
| "precision": 0.88268156424581, | |
| "recall": 0.8540540540540541, | |
| "f1": 0.8681318681318682, | |
| "confusion_matrix": [ | |
| [ | |
| 868, | |
| 21 | |
| ], | |
| [ | |
| 27, | |
| 158 | |
| ] | |
| ], | |
| "classification_report": { | |
| "NOT_RELEVANT": { | |
| "precision": 0.9698324022346368, | |
| "recall": 0.9763779527559056, | |
| "f1-score": 0.9730941704035875, | |
| "support": 889.0 | |
| }, | |
| "RELEVANT": { | |
| "precision": 0.88268156424581, | |
| "recall": 0.8540540540540541, | |
| "f1-score": 0.8681318681318682, | |
| "support": 185.0 | |
| }, | |
| "accuracy": 0.9553072625698324, | |
| "macro avg": { | |
| "precision": 0.9262569832402234, | |
| "recall": 0.9152160034049799, | |
| "f1-score": 0.9206130192677278, | |
| "support": 1074.0 | |
| }, | |
| "weighted avg": { | |
| "precision": 0.9548203863799507, | |
| "recall": 0.9553072625698324, | |
| "f1-score": 0.9550140717813639, | |
| "support": 1074.0 | |
| } | |
| }, | |
| "roc_auc": 0.9756270331073482, | |
| "average_precision": 0.9289986926848062 | |
| } | |
| } | |
| ] | |
| } |