Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+transformer/checkpoint-296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+transformer/checkpoint-592/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+transformer/checkpoint-888/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+transformer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,326 @@
+---
+library_name: transformers
+pipeline_tag: text-classification
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- text-classification
+- binary-classification
+- amis
+- agriculture
+language: multilingual
+---
+
+# AMIS Commodity Classifier
+
+This model repository contains artifacts from an AMIS commodity relevance classifier training run.
+It includes the Transformer model, any configured TF-IDF or sentence-embedding baselines, prediction files, and the training report.
+
+- Dataset: `faodl/amis-agri-maize_corn`
+- Dataset subset: ``
+- Dataset revision: `main`
+- Text column: `chunk_text`
+- Label column: `label`
+- Transformer: `FacebookAI/xlm-roberta-base`
+- Generated at: `2026-06-05T20:32:51.106165+00:00`
+
+## Dataset Summary
+
+| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| train | 4724 | 3822 | 902 | 2226 | 702.9 |
+| validation | 1060 | 843 | 217 | 477 | 708.3 |
+| test | 1054 | 819 | 235 | 478 | 711.9 |
+
+## Threshold Comparison on Validation Split
+
+Validation metrics document threshold selection and tuning behavior; test metrics remain the primary estimate of out-of-sample performance.
+
+| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| logistic_tfidf | 0.500 | 0.896 | 0.700 | 0.862 | 0.773 | 0.929 | 0.841 |
+| logistic_tfidf | 0.586 | 0.915 | 0.777 | 0.820 | 0.798 | 0.929 | 0.841 |
+| xgboost_tfidf | 0.500 | 0.957 | 0.913 | 0.871 | 0.892 | 0.967 | 0.914 |
+| xgboost_tfidf | 0.379 | 0.958 | 0.902 | 0.894 | 0.898 | 0.967 | 0.914 |
+| embedding-logistic_sentence_embeddings | 0.500 | 0.881 | 0.649 | 0.912 | 0.759 | 0.959 | 0.867 |
+| embedding-logistic_sentence_embeddings | 0.744 | 0.923 | 0.808 | 0.816 | 0.812 | 0.959 | 0.867 |
+| embedding-svm_sentence_embeddings | 0.500 | 0.913 | 0.849 | 0.700 | 0.768 | 0.955 | 0.858 |
+| embedding-svm_sentence_embeddings | 0.401 | 0.914 | 0.789 | 0.793 | 0.791 | 0.955 | 0.858 |
+| embedding-lightgbm_sentence_embeddings | 0.500 | 0.916 | 0.791 | 0.802 | 0.796 | 0.963 | 0.878 |
+| embedding-lightgbm_sentence_embeddings | 0.145 | 0.916 | 0.746 | 0.894 | 0.813 | 0.963 | 0.878 |
+| transformer | 0.500 | 0.958 | 0.913 | 0.876 | 0.894 | 0.973 | 0.943 |
+| transformer | 0.328 | 0.959 | 0.907 | 0.894 | 0.900 | 0.973 | 0.943 |
+
+## Threshold Comparison on Test Split
+
+| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| logistic_tfidf | 0.500 | 0.910 | 0.787 | 0.817 | 0.802 | 0.953 | 0.863 |
+| logistic_tfidf | 0.586 | 0.915 | 0.857 | 0.740 | 0.795 | 0.953 | 0.863 |
+| xgboost_tfidf | 0.500 | 0.942 | 0.914 | 0.817 | 0.863 | 0.968 | 0.920 |
+| xgboost_tfidf | 0.379 | 0.948 | 0.895 | 0.868 | 0.881 | 0.968 | 0.920 |
+| embedding-logistic_sentence_embeddings | 0.500 | 0.884 | 0.704 | 0.830 | 0.762 | 0.936 | 0.844 |
+| embedding-logistic_sentence_embeddings | 0.744 | 0.896 | 0.831 | 0.668 | 0.741 | 0.936 | 0.844 |
+| embedding-svm_sentence_embeddings | 0.500 | 0.894 | 0.892 | 0.596 | 0.714 | 0.932 | 0.842 |
+| embedding-svm_sentence_embeddings | 0.401 | 0.902 | 0.851 | 0.681 | 0.757 | 0.932 | 0.842 |
+| embedding-lightgbm_sentence_embeddings | 0.500 | 0.907 | 0.870 | 0.685 | 0.767 | 0.953 | 0.873 |
+| embedding-lightgbm_sentence_embeddings | 0.145 | 0.901 | 0.784 | 0.770 | 0.777 | 0.953 | 0.873 |
+| transformer | 0.500 | 0.935 | 0.892 | 0.804 | 0.846 | 0.953 | 0.890 |
+| transformer | 0.328 | 0.935 | 0.881 | 0.817 | 0.848 | 0.953 | 0.890 |
+
+## Confusion Matrices on Test Split
+
+Rows are true labels and columns are predicted labels.
+
+### logistic_tfidf at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 767 | 52 |
+| RELEVANT | 43 | 192 |
+
+### logistic_tfidf at threshold 0.586
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 790 | 29 |
+| RELEVANT | 61 | 174 |
+
+### xgboost_tfidf at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 801 | 18 |
+| RELEVANT | 43 | 192 |
+
+### xgboost_tfidf at threshold 0.379
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 795 | 24 |
+| RELEVANT | 31 | 204 |
+
+### embedding-logistic_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 737 | 82 |
+| RELEVANT | 40 | 195 |
+
+### embedding-logistic_sentence_embeddings at threshold 0.744
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 787 | 32 |
+| RELEVANT | 78 | 157 |
+
+### embedding-svm_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 802 | 17 |
+| RELEVANT | 95 | 140 |
+
+### embedding-svm_sentence_embeddings at threshold 0.401
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 791 | 28 |
+| RELEVANT | 75 | 160 |
+
+### embedding-lightgbm_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 795 | 24 |
+| RELEVANT | 74 | 161 |
+
+### embedding-lightgbm_sentence_embeddings at threshold 0.145
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 769 | 50 |
+| RELEVANT | 54 | 181 |
+
+### transformer at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 796 | 23 |
+| RELEVANT | 46 | 189 |
+
+### transformer at threshold 0.328
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 793 | 26 |
+| RELEVANT | 43 | 192 |
+
+
+## Validation-Tuned Thresholds
+
+- `logistic_tfidf`: threshold `0.586` (validation F1 `0.798`); test F1 change vs 0.5: `-0.007`.
+- `xgboost_tfidf`: threshold `0.379` (validation F1 `0.898`); test F1 change vs 0.5: `+0.018`.
+- `embedding-logistic_sentence_embeddings`: threshold `0.744` (validation F1 `0.812`); test F1 change vs 0.5: `-0.021`.
+- `embedding-svm_sentence_embeddings`: threshold `0.401` (validation F1 `0.791`); test F1 change vs 0.5: `+0.042`.
+- `embedding-lightgbm_sentence_embeddings`: threshold `0.145` (validation F1 `0.813`); test F1 change vs 0.5: `+0.010`.
+- `transformer`: threshold `0.328` (validation F1 `0.900`); test F1 change vs 0.5: `+0.002`.
+
+## Artifacts
+
+- `logistic_tfidf`: `/content/agri-maize_corn-classifier/baselines/logistic`
+- `xgboost_tfidf`: `/content/agri-maize_corn-classifier/baselines/xgboost`
+- `embedding-logistic_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-logistic`
+- `embedding-svm_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-svm`
+- `embedding-lightgbm_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-lightgbm`
+- `transformer`: `/content/agri-maize_corn-classifier/transformer`
+
+## Inference
+
+Install the runtime dependencies:
+
+```bash
+pip install transformers torch huggingface_hub pandas joblib scikit-learn xgboost lightgbm
+```
+
+### Transformer
+
+```python
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+MODEL_ID = "faodl/agri-maize_corn-classifier"
+
+texts = [
+    "Rice export prices increased after new procurement rules were announced.",
+    "The finance ministry released its monthly fuel tax bulletin.",
+]
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, subfolder="transformer")
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID, subfolder="transformer")
+threshold = float(getattr(model.config, "threshold", 0.5))
+
+encoded = tokenizer(
+    texts,
+    truncation=True,
+    padding=True,
+    max_length=256,
+    return_tensors="pt",
+)
+
+with torch.no_grad():
+    logits = model(**encoded).logits
+    probabilities = torch.softmax(logits, dim=-1)[:, 1].tolist()
+
+for text, probability in zip(texts, probabilities):
+    label = model.config.id2label[int(probability >= threshold)]
+    print({"text": text, "probability_positive": probability, "label": label})
+```
+
+### TF-IDF Baselines
+
+Available baseline names in this run: "logistic", "xgboost".
+
+```python
+import json
+import joblib
+from huggingface_hub import hf_hub_download
+
+MODEL_ID = "faodl/agri-maize_corn-classifier"
+BASELINE = "logistic"
+
+texts = [
+    "Maize production forecasts were revised after delayed rains.",
+    "The central bank published new exchange rate statistics.",
+]
+
+model_path = hf_hub_download(
+    repo_id=MODEL_ID,
+    repo_type="model",
+    filename=f"baselines/{BASELINE}/{BASELINE}_tfidf.joblib",
+)
+report_path = hf_hub_download(
+    repo_id=MODEL_ID,
+    repo_type="model",
+    filename="report.json",
+)
+
+pipeline = joblib.load(model_path)
+with open(report_path, encoding="utf-8") as handle:
+    report = json.load(handle)
+
+threshold = next(
+    result["validation_best_threshold"]["threshold"]
+    for result in report["results"]
+    if result["model_type"] == f"{BASELINE}_tfidf"
+)
+
+probabilities = pipeline.predict_proba(texts)[:, 1]
+for text, probability in zip(texts, probabilities):
+    label = "RELEVANT" if probability >= threshold else "NOT_RELEVANT"
+    print({"text": text, "probability_positive": float(probability), "label": label})
+```
+
+### Sentence-Embedding Baselines
+
+Available embedding baseline names in this run: "embedding-logistic", "embedding-svm", "embedding-lightgbm".
+
+```python
+import joblib
+import torch
+from huggingface_hub import hf_hub_download
+from transformers import AutoModel, AutoTokenizer
+
+MODEL_ID = "faodl/agri-maize_corn-classifier"
+BASELINE = "embedding-logistic"
+
+texts = [
+    "Wheat export inspections rose as demand from importers increased.",
+    "The sports ministry announced a new stadium renovation plan.",
+]
+
+model_path = hf_hub_download(
+    repo_id=MODEL_ID,
+    repo_type="model",
+    filename=f"baselines/{BASELINE}/{BASELINE}.joblib",
+)
+artifact = joblib.load(model_path)
+tokenizer = AutoTokenizer.from_pretrained(artifact["embedding_model_name"])
+encoder = AutoModel.from_pretrained(artifact["embedding_model_name"])
+encoder.eval()
+
+encoded_batches = []
+batch_size = artifact.get("embedding_batch_size", 64)
+for start in range(0, len(texts), batch_size):
+    batch_texts = texts[start : start + batch_size]
+    inputs = tokenizer(
+        batch_texts,
+        padding=True,
+        truncation=True,
+        max_length=artifact.get("embedding_max_length", 256),
+        return_tensors="pt",
+    )
+    with torch.no_grad():
+        outputs = encoder(**inputs)
+    token_embeddings = outputs.last_hidden_state
+    attention_mask = inputs["attention_mask"].unsqueeze(-1).to(token_embeddings.dtype)
+    embeddings = (token_embeddings * attention_mask).sum(dim=1)
+    embeddings = embeddings / attention_mask.sum(dim=1).clamp(min=1e-9)
+    if artifact.get("normalize_embeddings", True):
+        embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1)
+    encoded_batches.append(embeddings)
+embeddings = torch.cat(encoded_batches).numpy()
+probabilities = artifact["classifier"].predict_proba(embeddings)[:, 1]
+threshold = artifact["validation_best_threshold"]["threshold"]
+
+for text, probability in zip(texts, probabilities):
+    label = "RELEVANT" if probability >= threshold else "NOT_RELEVANT"
+    print({"text": text, "probability_positive": float(probability), "label": label})
+```
+
+## Files
+
+- `REPORT.md`: Markdown report for this training run.
+- `report.json`: Machine-readable report containing metrics and thresholds.
+- `transformer/`: Fine-tuned Transformer artifacts, when Transformer training is enabled.
+- `baselines/`: TF-IDF and sentence-embedding baseline artifacts, when baseline training is enabled.
+- `*/validation_predictions.csv` and `*/test_predictions.csv`: Split-level predictions.

REPORT.md

@@ -0,0 +1,160 @@
+# AMIS Commodity Classifier Training Report
+
+- Dataset: `faodl/amis-agri-maize_corn`
+- Dataset subset: ``
+- Dataset revision: `main`
+- Text column: `chunk_text`
+- Label column: `label`
+- Transformer: `FacebookAI/xlm-roberta-base`
+- Generated at: `2026-06-05T20:32:51.106165+00:00`
+
+## Dataset Summary
+
+| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| train | 4724 | 3822 | 902 | 2226 | 702.9 |
+| validation | 1060 | 843 | 217 | 477 | 708.3 |
+| test | 1054 | 819 | 235 | 478 | 711.9 |
+
+## Threshold Comparison on Validation Split
+
+Validation metrics document threshold selection and tuning behavior; test metrics remain the primary estimate of out-of-sample performance.
+
+| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| logistic_tfidf | 0.500 | 0.896 | 0.700 | 0.862 | 0.773 | 0.929 | 0.841 |
+| logistic_tfidf | 0.586 | 0.915 | 0.777 | 0.820 | 0.798 | 0.929 | 0.841 |
+| xgboost_tfidf | 0.500 | 0.957 | 0.913 | 0.871 | 0.892 | 0.967 | 0.914 |
+| xgboost_tfidf | 0.379 | 0.958 | 0.902 | 0.894 | 0.898 | 0.967 | 0.914 |
+| embedding-logistic_sentence_embeddings | 0.500 | 0.881 | 0.649 | 0.912 | 0.759 | 0.959 | 0.867 |
+| embedding-logistic_sentence_embeddings | 0.744 | 0.923 | 0.808 | 0.816 | 0.812 | 0.959 | 0.867 |
+| embedding-svm_sentence_embeddings | 0.500 | 0.913 | 0.849 | 0.700 | 0.768 | 0.955 | 0.858 |
+| embedding-svm_sentence_embeddings | 0.401 | 0.914 | 0.789 | 0.793 | 0.791 | 0.955 | 0.858 |
+| embedding-lightgbm_sentence_embeddings | 0.500 | 0.916 | 0.791 | 0.802 | 0.796 | 0.963 | 0.878 |
+| embedding-lightgbm_sentence_embeddings | 0.145 | 0.916 | 0.746 | 0.894 | 0.813 | 0.963 | 0.878 |
+| transformer | 0.500 | 0.958 | 0.913 | 0.876 | 0.894 | 0.973 | 0.943 |
+| transformer | 0.328 | 0.959 | 0.907 | 0.894 | 0.900 | 0.973 | 0.943 |
+
+## Threshold Comparison on Test Split
+
+| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| logistic_tfidf | 0.500 | 0.910 | 0.787 | 0.817 | 0.802 | 0.953 | 0.863 |
+| logistic_tfidf | 0.586 | 0.915 | 0.857 | 0.740 | 0.795 | 0.953 | 0.863 |
+| xgboost_tfidf | 0.500 | 0.942 | 0.914 | 0.817 | 0.863 | 0.968 | 0.920 |
+| xgboost_tfidf | 0.379 | 0.948 | 0.895 | 0.868 | 0.881 | 0.968 | 0.920 |
+| embedding-logistic_sentence_embeddings | 0.500 | 0.884 | 0.704 | 0.830 | 0.762 | 0.936 | 0.844 |
+| embedding-logistic_sentence_embeddings | 0.744 | 0.896 | 0.831 | 0.668 | 0.741 | 0.936 | 0.844 |
+| embedding-svm_sentence_embeddings | 0.500 | 0.894 | 0.892 | 0.596 | 0.714 | 0.932 | 0.842 |
+| embedding-svm_sentence_embeddings | 0.401 | 0.902 | 0.851 | 0.681 | 0.757 | 0.932 | 0.842 |
+| embedding-lightgbm_sentence_embeddings | 0.500 | 0.907 | 0.870 | 0.685 | 0.767 | 0.953 | 0.873 |
+| embedding-lightgbm_sentence_embeddings | 0.145 | 0.901 | 0.784 | 0.770 | 0.777 | 0.953 | 0.873 |
+| transformer | 0.500 | 0.935 | 0.892 | 0.804 | 0.846 | 0.953 | 0.890 |
+| transformer | 0.328 | 0.935 | 0.881 | 0.817 | 0.848 | 0.953 | 0.890 |
+
+## Confusion Matrices on Test Split
+
+Rows are true labels and columns are predicted labels.
+
+### logistic_tfidf at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 767 | 52 |
+| RELEVANT | 43 | 192 |
+
+### logistic_tfidf at threshold 0.586
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 790 | 29 |
+| RELEVANT | 61 | 174 |
+
+### xgboost_tfidf at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 801 | 18 |
+| RELEVANT | 43 | 192 |
+
+### xgboost_tfidf at threshold 0.379
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 795 | 24 |
+| RELEVANT | 31 | 204 |
+
+### embedding-logistic_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 737 | 82 |
+| RELEVANT | 40 | 195 |
+
+### embedding-logistic_sentence_embeddings at threshold 0.744
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 787 | 32 |
+| RELEVANT | 78 | 157 |
+
+### embedding-svm_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 802 | 17 |
+| RELEVANT | 95 | 140 |
+
+### embedding-svm_sentence_embeddings at threshold 0.401
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 791 | 28 |
+| RELEVANT | 75 | 160 |
+
+### embedding-lightgbm_sentence_embeddings at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 795 | 24 |
+| RELEVANT | 74 | 161 |
+
+### embedding-lightgbm_sentence_embeddings at threshold 0.145
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 769 | 50 |
+| RELEVANT | 54 | 181 |
+
+### transformer at threshold 0.500
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 796 | 23 |
+| RELEVANT | 46 | 189 |
+
+### transformer at threshold 0.328
+
+| True / Predicted | NOT_RELEVANT | RELEVANT |
+| --- | ---: | ---: |
+| NOT_RELEVANT | 793 | 26 |
+| RELEVANT | 43 | 192 |
+
+
+## Validation-Tuned Thresholds
+
+- `logistic_tfidf`: threshold `0.586` (validation F1 `0.798`); test F1 change vs 0.5: `-0.007`.
+- `xgboost_tfidf`: threshold `0.379` (validation F1 `0.898`); test F1 change vs 0.5: `+0.018`.
+- `embedding-logistic_sentence_embeddings`: threshold `0.744` (validation F1 `0.812`); test F1 change vs 0.5: `-0.021`.
+- `embedding-svm_sentence_embeddings`: threshold `0.401` (validation F1 `0.791`); test F1 change vs 0.5: `+0.042`.
+- `embedding-lightgbm_sentence_embeddings`: threshold `0.145` (validation F1 `0.813`); test F1 change vs 0.5: `+0.010`.
+- `transformer`: threshold `0.328` (validation F1 `0.900`); test F1 change vs 0.5: `+0.002`.
+
+## Artifacts
+
+- `logistic_tfidf`: `/content/agri-maize_corn-classifier/baselines/logistic`
+- `xgboost_tfidf`: `/content/agri-maize_corn-classifier/baselines/xgboost`
+- `embedding-logistic_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-logistic`
+- `embedding-svm_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-svm`
+- `embedding-lightgbm_sentence_embeddings`: `/content/agri-maize_corn-classifier/baselines/embedding-lightgbm`
+- `transformer`: `/content/agri-maize_corn-classifier/transformer`

baselines/embedding-lightgbm/embedding-lightgbm.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43a5ce8df629f94792b83a7b1b2eed85e91ff4150a84a444e907ff8363eba3f
+size 1457950

baselines/embedding-logistic/embedding-logistic.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ed45a29852cc67656a4e024605be056bd1408302937b32131c73078e3fef7e
+size 2821

baselines/embedding-svm/embedding-svm.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e256f5b8bc28bf4f9abc3cd3c02c2a9cf7605f86c444d37761bd0a4b2c6c30
+size 11770

baselines/logistic/logistic_tfidf.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2235e9e06a71e7da44c278b563f426835cfa451f79405cfca9da16b3b056a0
+size 2453428

baselines/xgboost/xgboost_tfidf.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442a7c91a42548dc025003eb705c5a861953a22dc419ecbd960a7f4506e25f6c
+size 2540068

report.json

@@ -0,0 +1,1257 @@
+{
+  "created_at": "2026-06-05T20:32:51.106165+00:00",
+  "config": {
+    "hf_dataset": "faodl/amis-agri-maize_corn",
+    "hf_subset": null,
+    "hf_revision": "main",
+    "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": "FacebookAI/xlm-roberta-base",
+    "output_dir": "/content/agri-maize_corn-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-maize_corn-classifier",
+    "hub_private_repo": false
+  },
+  "dataset_summary": {
+    "train": {
+      "rows": 4724,
+      "labels": {
+        "0": 3822,
+        "1": 902
+      },
+      "unique_groups": 2226,
+      "text_length_mean": 702.8679085520745,
+      "text_length_median": 794.0
+    },
+    "validation": {
+      "rows": 1060,
+      "labels": {
+        "0": 843,
+        "1": 217
+      },
+      "unique_groups": 477,
+      "text_length_mean": 708.2584905660377,
+      "text_length_median": 795.0
+    },
+    "test": {
+      "rows": 1054,
+      "labels": {
+        "0": 819,
+        "1": 235
+      },
+      "unique_groups": 478,
+      "text_length_mean": 711.8595825426945,
+      "text_length_median": 794.0
+    }
+  },
+  "results": [
+    {
+      "model_type": "logistic_tfidf",
+      "model_name": "logistic",
+      "artifact_dir": "/content/agri-maize_corn-classifier/baselines/logistic",
+      "artifact_file": "/content/agri-maize_corn-classifier/baselines/logistic/logistic_tfidf.joblib",
+      "validation_best_threshold": {
+        "threshold": 0.5864890967583224,
+        "f1": 0.7982062780269059,
+        "precision": 0.777292576419214,
+        "recall": 0.8202764976958525
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.8962264150943396,
+        "precision": 0.700374531835206,
+        "recall": 0.8617511520737328,
+        "f1": 0.7727272727272727,
+        "confusion_matrix": [
+          [
+            763,
+            80
+          ],
+          [
+            30,
+            187
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9621689785624212,
+            "recall": 0.9051008303677343,
+            "f1-score": 0.9327628361858191,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.700374531835206,
+            "recall": 0.8617511520737328,
+            "f1-score": 0.7727272727272727,
+            "support": 217.0
+          },
+          "accuracy": 0.8962264150943396,
+          "macro avg": {
+            "precision": 0.8312717551988136,
+            "recall": 0.8834259912207335,
+            "f1-score": 0.8527450544565459,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9085752097512838,
+            "recall": 0.8962264150943396,
+            "f1-score": 0.9000008387608148,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9288420224018894,
+        "average_precision": 0.8406024632295316
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.5864890967583224,
+        "accuracy": 0.9150943396226415,
+        "precision": 0.777292576419214,
+        "recall": 0.8202764976958525,
+        "f1": 0.7982062780269058,
+        "confusion_matrix": [
+          [
+            792,
+            51
+          ],
+          [
+            39,
+            178
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9530685920577617,
+            "recall": 0.9395017793594306,
+            "f1-score": 0.946236559139785,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.777292576419214,
+            "recall": 0.8202764976958525,
+            "f1-score": 0.7982062780269058,
+            "support": 217.0
+          },
+          "accuracy": 0.9150943396226415,
+          "macro avg": {
+            "precision": 0.8651805842384879,
+            "recall": 0.8798891385276415,
+            "f1-score": 0.8722214185833455,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9170842567808138,
+            "recall": 0.9150943396226415,
+            "f1-score": 0.9159322468742239,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9288420224018894,
+        "average_precision": 0.8406024632295316
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9098671726755219,
+        "precision": 0.7868852459016393,
+        "recall": 0.8170212765957446,
+        "f1": 0.8016701461377871,
+        "confusion_matrix": [
+          [
+            767,
+            52
+          ],
+          [
+            43,
+            192
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9469135802469136,
+            "recall": 0.9365079365079365,
+            "f1-score": 0.941682013505218,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.7868852459016393,
+            "recall": 0.8170212765957446,
+            "f1-score": 0.8016701461377871,
+            "support": 235.0
+          },
+          "accuracy": 0.9098671726755219,
+          "macro avg": {
+            "precision": 0.8668994130742764,
+            "recall": 0.8767646065518406,
+            "f1-score": 0.8716760798215025,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9112336385285649,
+            "recall": 0.9098671726755219,
+            "f1-score": 0.9104649463028021,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9531551191125659,
+        "average_precision": 0.8625249758747111
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.5864890967583224,
+        "accuracy": 0.9146110056925996,
+        "precision": 0.8571428571428571,
+        "recall": 0.7404255319148936,
+        "f1": 0.7945205479452054,
+        "confusion_matrix": [
+          [
+            790,
+            29
+          ],
+          [
+            61,
+            174
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9283196239717979,
+            "recall": 0.9645909645909646,
+            "f1-score": 0.9461077844311377,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8571428571428571,
+            "recall": 0.7404255319148936,
+            "f1-score": 0.7945205479452054,
+            "support": 235.0
+          },
+          "accuracy": 0.9146110056925996,
+          "macro avg": {
+            "precision": 0.8927312405573276,
+            "recall": 0.8525082482529291,
+            "f1-score": 0.8703141661881716,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.912450041234795,
+            "recall": 0.9146110056925996,
+            "f1-score": 0.9123098711728891,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9531551191125659,
+        "average_precision": 0.8625249758747111
+      }
+    },
+    {
+      "model_type": "xgboost_tfidf",
+      "model_name": "xgboost",
+      "artifact_dir": "/content/agri-maize_corn-classifier/baselines/xgboost",
+      "artifact_file": "/content/agri-maize_corn-classifier/baselines/xgboost/xgboost_tfidf.joblib",
+      "validation_best_threshold": {
+        "threshold": 0.37899935245513916,
+        "f1": 0.8981481481481481,
+        "precision": 0.9023255813953488,
+        "recall": 0.8940092165898618
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9566037735849057,
+        "precision": 0.9130434782608695,
+        "recall": 0.8709677419354839,
+        "f1": 0.8915094339622641,
+        "confusion_matrix": [
+          [
+            825,
+            18
+          ],
+          [
+            28,
+            189
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9671746776084408,
+            "recall": 0.9786476868327402,
+            "f1-score": 0.972877358490566,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.9130434782608695,
+            "recall": 0.8709677419354839,
+            "f1-score": 0.8915094339622641,
+            "support": 217.0
+          },
+          "accuracy": 0.9566037735849057,
+          "macro avg": {
+            "precision": 0.9401090779346551,
+            "recall": 0.924807714384112,
+            "f1-score": 0.9321933962264151,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9560931018929474,
+            "recall": 0.9566037735849057,
+            "f1-score": 0.9562199626201495,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.966850889133061,
+        "average_precision": 0.9141254109659447
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.37899935245513916,
+        "accuracy": 0.9584905660377359,
+        "precision": 0.9023255813953488,
+        "recall": 0.8940092165898618,
+        "f1": 0.8981481481481481,
+        "confusion_matrix": [
+          [
+            822,
+            21
+          ],
+          [
+            23,
+            194
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9727810650887574,
+            "recall": 0.9750889679715302,
+            "f1-score": 0.9739336492890995,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.9023255813953488,
+            "recall": 0.8940092165898618,
+            "f1-score": 0.8981481481481481,
+            "support": 217.0
+          },
+          "accuracy": 0.9584905660377359,
+          "macro avg": {
+            "precision": 0.9375533232420531,
+            "recall": 0.934549092280696,
+            "f1-score": 0.9360408987186238,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9583576311628426,
+            "recall": 0.9584905660377359,
+            "f1-score": 0.9584190702819425,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.966850889133061,
+        "average_precision": 0.9141254109659447
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9421252371916509,
+        "precision": 0.9142857142857143,
+        "recall": 0.8170212765957446,
+        "f1": 0.8629213483146068,
+        "confusion_matrix": [
+          [
+            801,
+            18
+          ],
+          [
+            43,
+            192
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9490521327014217,
+            "recall": 0.978021978021978,
+            "f1-score": 0.963319302465424,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.9142857142857143,
+            "recall": 0.8170212765957446,
+            "f1-score": 0.8629213483146068,
+            "support": 235.0
+          },
+          "accuracy": 0.9421252371916509,
+          "macro avg": {
+            "precision": 0.931668923493568,
+            "recall": 0.8975216273088613,
+            "f1-score": 0.9131203253900153,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.941300606773821,
+            "recall": 0.9421252371916509,
+            "f1-score": 0.9409345593672817,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9682098043800171,
+        "average_precision": 0.9201070133275652
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.37899935245513916,
+        "accuracy": 0.9478178368121443,
+        "precision": 0.8947368421052632,
+        "recall": 0.8680851063829788,
+        "f1": 0.8812095032397408,
+        "confusion_matrix": [
+          [
+            795,
+            24
+          ],
+          [
+            31,
+            204
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9624697336561744,
+            "recall": 0.9706959706959707,
+            "f1-score": 0.9665653495440729,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8947368421052632,
+            "recall": 0.8680851063829788,
+            "f1-score": 0.8812095032397408,
+            "support": 235.0
+          },
+          "accuracy": 0.9478178368121443,
+          "macro avg": {
+            "precision": 0.9286032878807188,
+            "recall": 0.9193905385394747,
+            "f1-score": 0.9238874263919068,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9473679978739503,
+            "recall": 0.9478178368121443,
+            "f1-score": 0.9475343970948148,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9682098043800171,
+        "average_precision": 0.9201070133275652
+      }
+    },
+    {
+      "model_type": "embedding-logistic_sentence_embeddings",
+      "model_name": "logistic",
+      "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+      "artifact_dir": "/content/agri-maize_corn-classifier/baselines/embedding-logistic",
+      "artifact_file": "/content/agri-maize_corn-classifier/baselines/embedding-logistic/embedding-logistic.joblib",
+      "validation_best_threshold": {
+        "threshold": 0.7437081336975098,
+        "f1": 0.8119266055045872,
+        "precision": 0.8082191780821918,
+        "recall": 0.815668202764977
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.8811320754716981,
+        "precision": 0.6491803278688525,
+        "recall": 0.9124423963133641,
+        "f1": 0.7586206896551724,
+        "confusion_matrix": [
+          [
+            736,
+            107
+          ],
+          [
+            19,
+            198
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9748344370860927,
+            "recall": 0.8730723606168446,
+            "f1-score": 0.9211514392991239,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.6491803278688525,
+            "recall": 0.9124423963133641,
+            "f1-score": 0.7586206896551724,
+            "support": 217.0
+          },
+          "accuracy": 0.8811320754716981,
+          "macro avg": {
+            "precision": 0.8120073824774726,
+            "recall": 0.8927573784651044,
+            "f1-score": 0.8398860644771482,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9081675109538841,
+            "recall": 0.8811320754716981,
+            "f1-score": 0.887878634890881,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9590938659931886,
+        "average_precision": 0.8665525722038933
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.7437081336975098,
+        "accuracy": 0.9226415094339623,
+        "precision": 0.8082191780821918,
+        "recall": 0.815668202764977,
+        "f1": 0.8119266055045872,
+        "confusion_matrix": [
+          [
+            801,
+            42
+          ],
+          [
+            40,
+            177
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9524375743162902,
+            "recall": 0.9501779359430605,
+            "f1-score": 0.9513064133016627,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.8082191780821918,
+            "recall": 0.815668202764977,
+            "f1-score": 0.8119266055045872,
+            "support": 217.0
+          },
+          "accuracy": 0.9226415094339623,
+          "macro avg": {
+            "precision": 0.880328376199241,
+            "recall": 0.8829230693540188,
+            "f1-score": 0.881616509403125,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9229136196155361,
+            "recall": 0.9226415094339623,
+            "f1-score": 0.9227729998186764,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9590938659931886,
+        "average_precision": 0.8665525722038933
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.8842504743833017,
+        "precision": 0.703971119133574,
+        "recall": 0.8297872340425532,
+        "f1": 0.76171875,
+        "confusion_matrix": [
+          [
+            737,
+            82
+          ],
+          [
+            40,
+            195
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9485199485199485,
+            "recall": 0.8998778998778999,
+            "f1-score": 0.9235588972431078,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.703971119133574,
+            "recall": 0.8297872340425532,
+            "f1-score": 0.76171875,
+            "support": 235.0
+          },
+          "accuracy": 0.8842504743833017,
+          "macro avg": {
+            "precision": 0.8262455338267612,
+            "recall": 0.8648325669602266,
+            "f1-score": 0.8426388236215538,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.8939953043968005,
+            "recall": 0.8842504743833017,
+            "f1-score": 0.8874749934460202,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9363156937625022,
+        "average_precision": 0.843737774596255
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.7437081336975098,
+        "accuracy": 0.8956356736242884,
+        "precision": 0.8306878306878307,
+        "recall": 0.6680851063829787,
+        "f1": 0.7405660377358491,
+        "confusion_matrix": [
+          [
+            787,
+            32
+          ],
+          [
+            78,
+            157
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9098265895953758,
+            "recall": 0.960927960927961,
+            "f1-score": 0.9346793349168646,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8306878306878307,
+            "recall": 0.6680851063829787,
+            "f1-score": 0.7405660377358491,
+            "support": 235.0
+          },
+          "accuracy": 0.8956356736242884,
+          "macro avg": {
+            "precision": 0.8702572101416033,
+            "recall": 0.8145065336554698,
+            "f1-score": 0.8376226863263568,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.8921817998958756,
+            "recall": 0.8956356736242884,
+            "f1-score": 0.8913998047104712,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9363156937625022,
+        "average_precision": 0.843737774596255
+      }
+    },
+    {
+      "model_type": "embedding-svm_sentence_embeddings",
+      "model_name": "svm",
+      "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+      "artifact_dir": "/content/agri-maize_corn-classifier/baselines/embedding-svm",
+      "artifact_file": "/content/agri-maize_corn-classifier/baselines/embedding-svm/embedding-svm.joblib",
+      "validation_best_threshold": {
+        "threshold": 0.4006770902787147,
+        "f1": 0.7908045977011494,
+        "precision": 0.7889908256880734,
+        "recall": 0.7926267281105991
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9132075471698113,
+        "precision": 0.8491620111731844,
+        "recall": 0.7004608294930875,
+        "f1": 0.7676767676767676,
+        "confusion_matrix": [
+          [
+            816,
+            27
+          ],
+          [
+            65,
+            152
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9262202043132803,
+            "recall": 0.9679715302491103,
+            "f1-score": 0.9466357308584686,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.8491620111731844,
+            "recall": 0.7004608294930875,
+            "f1-score": 0.7676767676767676,
+            "support": 217.0
+          },
+          "accuracy": 0.9132075471698113,
+          "macro avg": {
+            "precision": 0.8876911077432323,
+            "recall": 0.834216179871099,
+            "f1-score": 0.8571562492676181,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9104450836421474,
+            "recall": 0.9132075471698113,
+            "f1-score": 0.9099997921693845,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9551306230217951,
+        "average_precision": 0.8583227993086541
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.4006770902787147,
+        "accuracy": 0.9141509433962264,
+        "precision": 0.7889908256880734,
+        "recall": 0.7926267281105991,
+        "f1": 0.7908045977011494,
+        "confusion_matrix": [
+          [
+            797,
+            46
+          ],
+          [
+            45,
+            172
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9465558194774347,
+            "recall": 0.9454329774614472,
+            "f1-score": 0.9459940652818991,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.7889908256880734,
+            "recall": 0.7926267281105991,
+            "f1-score": 0.7908045977011494,
+            "support": 217.0
+          },
+          "accuracy": 0.9141509433962264,
+          "macro avg": {
+            "precision": 0.8677733225827541,
+            "recall": 0.8690298527860232,
+            "f1-score": 0.8683993314915243,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9142995896167825,
+            "recall": 0.9141509433962264,
+            "f1-score": 0.914224145975274,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9551306230217951,
+        "average_precision": 0.8583227993086541
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.8937381404174574,
+        "precision": 0.89171974522293,
+        "recall": 0.5957446808510638,
+        "f1": 0.7142857142857143,
+        "confusion_matrix": [
+          [
+            802,
+            17
+          ],
+          [
+            95,
+            140
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.8940914158305463,
+            "recall": 0.9792429792429792,
+            "f1-score": 0.9347319347319347,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.89171974522293,
+            "recall": 0.5957446808510638,
+            "f1-score": 0.7142857142857143,
+            "support": 235.0
+          },
+          "accuracy": 0.8937381404174574,
+          "macro avg": {
+            "precision": 0.8929055805267381,
+            "recall": 0.7874938300470216,
+            "f1-score": 0.8245088245088246,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.8935626277918463,
+            "recall": 0.8937381404174574,
+            "f1-score": 0.8855812119569235,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9321590938612216,
+        "average_precision": 0.8417078389566306
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.4006770902787147,
+        "accuracy": 0.9022770398481973,
+        "precision": 0.851063829787234,
+        "recall": 0.6808510638297872,
+        "f1": 0.7565011820330969,
+        "confusion_matrix": [
+          [
+            791,
+            28
+          ],
+          [
+            75,
+            160
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9133949191685913,
+            "recall": 0.9658119658119658,
+            "f1-score": 0.9388724035608309,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.851063829787234,
+            "recall": 0.6808510638297872,
+            "f1-score": 0.7565011820330969,
+            "support": 235.0
+          },
+          "accuracy": 0.9022770398481973,
+          "macro avg": {
+            "precision": 0.8822293744779126,
+            "recall": 0.8233315148208765,
+            "f1-score": 0.8476867927969639,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.8994975700180988,
+            "recall": 0.9022770398481973,
+            "f1-score": 0.8982108883245714,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9321590938612216,
+        "average_precision": 0.8417078389566306
+      }
+    },
+    {
+      "model_type": "embedding-lightgbm_sentence_embeddings",
+      "model_name": "lightgbm",
+      "embedding_model_name": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+      "artifact_dir": "/content/agri-maize_corn-classifier/baselines/embedding-lightgbm",
+      "artifact_file": "/content/agri-maize_corn-classifier/baselines/embedding-lightgbm/embedding-lightgbm.joblib",
+      "validation_best_threshold": {
+        "threshold": 0.14456141773750653,
+        "f1": 0.8134171907756813,
+        "precision": 0.7461538461538462,
+        "recall": 0.8940092165898618
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9160377358490566,
+        "precision": 0.7909090909090909,
+        "recall": 0.8018433179723502,
+        "f1": 0.7963386727688787,
+        "confusion_matrix": [
+          [
+            797,
+            46
+          ],
+          [
+            43,
+            174
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9488095238095238,
+            "recall": 0.9454329774614472,
+            "f1-score": 0.9471182412358883,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.7909090909090909,
+            "recall": 0.8018433179723502,
+            "f1-score": 0.7963386727688787,
+            "support": 217.0
+          },
+          "accuracy": 0.9160377358490566,
+          "macro avg": {
+            "precision": 0.8698593073593073,
+            "recall": 0.8736381477168986,
+            "f1-score": 0.8717284570023835,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9164846238666993,
+            "recall": 0.9160377358490566,
+            "f1-score": 0.916251103162925,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9630571089645823,
+        "average_precision": 0.8780215936178333
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.14456141773750653,
+        "accuracy": 0.9160377358490566,
+        "precision": 0.7461538461538462,
+        "recall": 0.8940092165898618,
+        "f1": 0.8134171907756813,
+        "confusion_matrix": [
+          [
+            777,
+            66
+          ],
+          [
+            23,
+            194
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.97125,
+            "recall": 0.9217081850533808,
+            "f1-score": 0.945830797321972,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.7461538461538462,
+            "recall": 0.8940092165898618,
+            "f1-score": 0.8134171907756813,
+            "support": 217.0
+          },
+          "accuracy": 0.9160377358490566,
+          "macro avg": {
+            "precision": 0.8587019230769231,
+            "recall": 0.9078587008216212,
+            "f1-score": 0.8796239940488266,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9251689949201741,
+            "recall": 0.9160377358490566,
+            "f1-score": 0.9187234835290049,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9630571089645823,
+        "average_precision": 0.8780215936178333
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9070208728652751,
+        "precision": 0.8702702702702703,
+        "recall": 0.6851063829787234,
+        "f1": 0.7666666666666667,
+        "confusion_matrix": [
+          [
+            795,
+            24
+          ],
+          [
+            74,
+            161
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9148446490218642,
+            "recall": 0.9706959706959707,
+            "f1-score": 0.9419431279620853,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8702702702702703,
+            "recall": 0.6851063829787234,
+            "f1-score": 0.7666666666666667,
+            "support": 235.0
+          },
+          "accuracy": 0.9070208728652751,
+          "macro avg": {
+            "precision": 0.8925574596460673,
+            "recall": 0.827901176837347,
+            "f1-score": 0.8543048973143761,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9049063387688998,
+            "recall": 0.9070208728652751,
+            "f1-score": 0.9028634615442264,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9534149066063959,
+        "average_precision": 0.872949726074902
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.14456141773750653,
+        "accuracy": 0.9013282732447818,
+        "precision": 0.7835497835497836,
+        "recall": 0.7702127659574468,
+        "f1": 0.776824034334764,
+        "confusion_matrix": [
+          [
+            769,
+            50
+          ],
+          [
+            54,
+            181
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9343863912515188,
+            "recall": 0.938949938949939,
+            "f1-score": 0.9366626065773447,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.7835497835497836,
+            "recall": 0.7702127659574468,
+            "f1-score": 0.776824034334764,
+            "support": 235.0
+          },
+          "accuracy": 0.9013282732447818,
+          "macro avg": {
+            "precision": 0.8589680874006511,
+            "recall": 0.8545813524536929,
+            "f1-score": 0.8567433204560544,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9007558383009421,
+            "recall": 0.9013282732447818,
+            "f1-score": 0.9010249742462191,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9534149066063959,
+        "average_precision": 0.872949726074902
+      }
+    },
+    {
+      "model_type": "transformer",
+      "model_name": "FacebookAI/xlm-roberta-base",
+      "artifact_dir": "/content/agri-maize_corn-classifier/transformer",
+      "validation_best_threshold": {
+        "threshold": 0.32782965898513794,
+        "f1": 0.9002320185614848,
+        "precision": 0.9065420560747663,
+        "recall": 0.8940092165898618
+      },
+      "validation_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9575471698113207,
+        "precision": 0.9134615384615384,
+        "recall": 0.8755760368663594,
+        "f1": 0.8941176470588236,
+        "confusion_matrix": [
+          [
+            825,
+            18
+          ],
+          [
+            27,
+            190
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9683098591549296,
+            "recall": 0.9786476868327402,
+            "f1-score": 0.9734513274336283,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.9134615384615384,
+            "recall": 0.8755760368663594,
+            "f1-score": 0.8941176470588236,
+            "support": 217.0
+          },
+          "accuracy": 0.9575471698113207,
+          "macro avg": {
+            "precision": 0.940885698808234,
+            "recall": 0.9271118618495497,
+            "f1-score": 0.933784487246226,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9570814765224146,
+            "recall": 0.9575471698113207,
+            "f1-score": 0.9572103758852012,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9729488167669778,
+        "average_precision": 0.9434157534580784
+      },
+      "validation_optimal_threshold": {
+        "threshold": 0.32782965898513794,
+        "accuracy": 0.9594339622641509,
+        "precision": 0.9065420560747663,
+        "recall": 0.8940092165898618,
+        "f1": 0.9002320185614849,
+        "confusion_matrix": [
+          [
+            823,
+            20
+          ],
+          [
+            23,
+            194
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9728132387706856,
+            "recall": 0.9762752075919335,
+            "f1-score": 0.9745411486086442,
+            "support": 843.0
+          },
+          "RELEVANT": {
+            "precision": 0.9065420560747663,
+            "recall": 0.8940092165898618,
+            "f1-score": 0.9002320185614849,
+            "support": 217.0
+          },
+          "accuracy": 0.9594339622641509,
+          "macro avg": {
+            "precision": 0.939677647422726,
+            "recall": 0.9351422120908977,
+            "f1-score": 0.9373865835850645,
+            "support": 1060.0
+          },
+          "weighted avg": {
+            "precision": 0.9592464023131247,
+            "recall": 0.9594339622641509,
+            "f1-score": 0.9593288078348389,
+            "support": 1060.0
+          }
+        },
+        "roc_auc": 0.9729488167669778,
+        "average_precision": 0.9434157534580784
+      },
+      "test_default_0_5": {
+        "threshold": 0.5,
+        "accuracy": 0.9345351043643264,
+        "precision": 0.8915094339622641,
+        "recall": 0.8042553191489362,
+        "f1": 0.8456375838926175,
+        "confusion_matrix": [
+          [
+            796,
+            23
+          ],
+          [
+            46,
+            189
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9453681710213777,
+            "recall": 0.9719169719169719,
+            "f1-score": 0.9584587597832631,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8915094339622641,
+            "recall": 0.8042553191489362,
+            "f1-score": 0.8456375838926175,
+            "support": 235.0
+          },
+          "accuracy": 0.9345351043643264,
+          "macro avg": {
+            "precision": 0.9184388024918209,
+            "recall": 0.8880861455329541,
+            "f1-score": 0.9020481718379403,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9333598188307785,
+            "recall": 0.9345351043643264,
+            "f1-score": 0.9333041332801306,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9527134803730548,
+        "average_precision": 0.8898057611290884
+      },
+      "test_optimal_threshold": {
+        "threshold": 0.32782965898513794,
+        "accuracy": 0.9345351043643264,
+        "precision": 0.8807339449541285,
+        "recall": 0.8170212765957446,
+        "f1": 0.847682119205298,
+        "confusion_matrix": [
+          [
+            793,
+            26
+          ],
+          [
+            43,
+            192
+          ]
+        ],
+        "classification_report": {
+          "NOT_RELEVANT": {
+            "precision": 0.9485645933014354,
+            "recall": 0.9682539682539683,
+            "f1-score": 0.9583081570996979,
+            "support": 819.0
+          },
+          "RELEVANT": {
+            "precision": 0.8807339449541285,
+            "recall": 0.8170212765957446,
+            "f1-score": 0.847682119205298,
+            "support": 235.0
+          },
+          "accuracy": 0.9345351043643264,
+          "macro avg": {
+            "precision": 0.9146492691277819,
+            "recall": 0.8926376224248564,
+            "f1-score": 0.9029951381524979,
+            "support": 1054.0
+          },
+          "weighted avg": {
+            "precision": 0.9334410616490472,
+            "recall": 0.9345351043643264,
+            "f1-score": 0.9336429588974361,
+            "support": 1054.0
+          }
+        },
+        "roc_auc": 0.9527134803730548,
+        "average_precision": 0.8898057611290884
+      }
+    }
+  ]
+}

transformer/checkpoint-296/config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_RELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "NOT_RELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

transformer/checkpoint-296/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e55690177f9df9681c79755fefed0d01c49b690d5fe3f1e4e5e2e1fd2051e9
+size 1112205008

transformer/checkpoint-296/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfab16a6ff59a8be730741b355132a64df206f043501efe631b370c845f2538c
+size 2224532875

transformer/checkpoint-296/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15581d46ce8805f1dfa758ecf9798fec9b05fc7a0f3e100c4f3a339fe05fee89
+size 14645

transformer/checkpoint-296/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdd9077530e85b1b9e5cf984a9ffda5e212c37f58d6ee425f3578887c7b014b
+size 1383

transformer/checkpoint-296/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea5a43be8a53415ef4dd342591c550950514872b62cacca5fe3d312f57423e2
+size 1465

transformer/checkpoint-296/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc02d42fb2a10276563109e2287cc0dbe6b595d5b3b3401c7cfeffc0b7e20270
+size 17098351

transformer/checkpoint-296/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

transformer/checkpoint-296/trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_global_step": 296,
+  "best_metric": 0.8941176470588236,
+  "best_model_checkpoint": "/content/agri-maize_corn-classifier/transformer/checkpoint-296",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08445945945945946,
+      "grad_norm": 4.2122979164123535,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.6247027587890625,
+      "step": 25
+    },
+    {
+      "epoch": 0.16891891891891891,
+      "grad_norm": 7.709840297698975,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 0.5710235595703125,
+      "step": 50
+    },
+    {
+      "epoch": 0.2533783783783784,
+      "grad_norm": 6.6395344734191895,
+      "learning_rate": 1e-05,
+      "loss": 0.5104244995117188,
+      "step": 75
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 5.032057762145996,
+      "learning_rate": 1.3378378378378381e-05,
+      "loss": 0.39651737213134763,
+      "step": 100
+    },
+    {
+      "epoch": 0.4222972972972973,
+      "grad_norm": 26.106103897094727,
+      "learning_rate": 1.6756756756756757e-05,
+      "loss": 0.30904300689697267,
+      "step": 125
+    },
+    {
+      "epoch": 0.5067567567567568,
+      "grad_norm": 19.755094528198242,
+      "learning_rate": 1.9984984984984987e-05,
+      "loss": 0.21882522583007813,
+      "step": 150
+    },
+    {
+      "epoch": 0.5912162162162162,
+      "grad_norm": 10.216408729553223,
+      "learning_rate": 1.9609609609609613e-05,
+      "loss": 0.2193868064880371,
+      "step": 175
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 19.423349380493164,
+      "learning_rate": 1.9234234234234235e-05,
+      "loss": 0.2879533958435059,
+      "step": 200
+    },
+    {
+      "epoch": 0.7601351351351351,
+      "grad_norm": 3.9074134826660156,
+      "learning_rate": 1.885885885885886e-05,
+      "loss": 0.21735734939575196,
+      "step": 225
+    },
+    {
+      "epoch": 0.8445945945945946,
+      "grad_norm": 0.8604102730751038,
+      "learning_rate": 1.8483483483483483e-05,
+      "loss": 0.28983583450317385,
+      "step": 250
+    },
+    {
+      "epoch": 0.9290540540540541,
+      "grad_norm": 49.190547943115234,
+      "learning_rate": 1.8108108108108108e-05,
+      "loss": 0.2321755599975586,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9575471698113207,
+      "eval_f1": 0.8941176470588236,
+      "eval_loss": 0.16295333206653595,
+      "eval_precision": 0.9134615384615384,
+      "eval_recall": 0.8755760368663594,
+      "eval_roc_auc": 0.9729488167669778,
+      "eval_runtime": 3.9863,
+      "eval_samples_per_second": 265.91,
+      "eval_steps_per_second": 8.529,
+      "step": 296
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 621468312760320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

transformer/checkpoint-296/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699ccdec1f51a0096482e3403ced3b8ee41aac4e70941e5bd8752f8c52f7c09a
+size 5201

transformer/checkpoint-592/config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_RELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "NOT_RELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

transformer/checkpoint-592/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8c813341f964cfd0325ef4c81479a207e5a21073dab530cdc25e79b888fb63
+size 1112205008

transformer/checkpoint-592/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1916c2448623e28c5421dd95599e8383f9fcce2d4426633b740d2fddbd7df8
+size 2224532875

transformer/checkpoint-592/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d83d8dd15f1fd53bee866bfc712bc4a0cdfe918ef088a873e4be8cec157e21
+size 14645

transformer/checkpoint-592/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d96563bcdba4b0d6b938c6748c5982ab5b9a030136631e3cfe83646b6d548c9
+size 1383

transformer/checkpoint-592/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c7c10124c7753e91192eb280101f3ff7bcb30733117a564929fe9ac6609ca4
+size 1465

transformer/checkpoint-592/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc02d42fb2a10276563109e2287cc0dbe6b595d5b3b3401c7cfeffc0b7e20270
+size 17098351

transformer/checkpoint-592/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

transformer/checkpoint-592/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_global_step": 296,
+  "best_metric": 0.8941176470588236,
+  "best_model_checkpoint": "/content/agri-maize_corn-classifier/transformer/checkpoint-296",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 592,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08445945945945946,
+      "grad_norm": 4.2122979164123535,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.6247027587890625,
+      "step": 25
+    },
+    {
+      "epoch": 0.16891891891891891,
+      "grad_norm": 7.709840297698975,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 0.5710235595703125,
+      "step": 50
+    },
+    {
+      "epoch": 0.2533783783783784,
+      "grad_norm": 6.6395344734191895,
+      "learning_rate": 1e-05,
+      "loss": 0.5104244995117188,
+      "step": 75
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 5.032057762145996,
+      "learning_rate": 1.3378378378378381e-05,
+      "loss": 0.39651737213134763,
+      "step": 100
+    },
+    {
+      "epoch": 0.4222972972972973,
+      "grad_norm": 26.106103897094727,
+      "learning_rate": 1.6756756756756757e-05,
+      "loss": 0.30904300689697267,
+      "step": 125
+    },
+    {
+      "epoch": 0.5067567567567568,
+      "grad_norm": 19.755094528198242,
+      "learning_rate": 1.9984984984984987e-05,
+      "loss": 0.21882522583007813,
+      "step": 150
+    },
+    {
+      "epoch": 0.5912162162162162,
+      "grad_norm": 10.216408729553223,
+      "learning_rate": 1.9609609609609613e-05,
+      "loss": 0.2193868064880371,
+      "step": 175
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 19.423349380493164,
+      "learning_rate": 1.9234234234234235e-05,
+      "loss": 0.2879533958435059,
+      "step": 200
+    },
+    {
+      "epoch": 0.7601351351351351,
+      "grad_norm": 3.9074134826660156,
+      "learning_rate": 1.885885885885886e-05,
+      "loss": 0.21735734939575196,
+      "step": 225
+    },
+    {
+      "epoch": 0.8445945945945946,
+      "grad_norm": 0.8604102730751038,
+      "learning_rate": 1.8483483483483483e-05,
+      "loss": 0.28983583450317385,
+      "step": 250
+    },
+    {
+      "epoch": 0.9290540540540541,
+      "grad_norm": 49.190547943115234,
+      "learning_rate": 1.8108108108108108e-05,
+      "loss": 0.2321755599975586,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9575471698113207,
+      "eval_f1": 0.8941176470588236,
+      "eval_loss": 0.16295333206653595,
+      "eval_precision": 0.9134615384615384,
+      "eval_recall": 0.8755760368663594,
+      "eval_roc_auc": 0.9729488167669778,
+      "eval_runtime": 3.9863,
+      "eval_samples_per_second": 265.91,
+      "eval_steps_per_second": 8.529,
+      "step": 296
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 0.8517799377441406,
+      "learning_rate": 1.7732732732732734e-05,
+      "loss": 0.18440502166748046,
+      "step": 300
+    },
+    {
+      "epoch": 1.097972972972973,
+      "grad_norm": 2.9610507488250732,
+      "learning_rate": 1.735735735735736e-05,
+      "loss": 0.16707677841186525,
+      "step": 325
+    },
+    {
+      "epoch": 1.1824324324324325,
+      "grad_norm": 4.359492301940918,
+      "learning_rate": 1.6981981981981985e-05,
+      "loss": 0.22817501068115234,
+      "step": 350
+    },
+    {
+      "epoch": 1.2668918918918919,
+      "grad_norm": 0.49442264437675476,
+      "learning_rate": 1.6606606606606607e-05,
+      "loss": 0.16232917785644532,
+      "step": 375
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.9959002733230591,
+      "learning_rate": 1.6231231231231232e-05,
+      "loss": 0.2139061164855957,
+      "step": 400
+    },
+    {
+      "epoch": 1.4358108108108107,
+      "grad_norm": 1.0536309480667114,
+      "learning_rate": 1.5855855855855858e-05,
+      "loss": 0.203138484954834,
+      "step": 425
+    },
+    {
+      "epoch": 1.5202702702702702,
+      "grad_norm": 2.8971381187438965,
+      "learning_rate": 1.5480480480480483e-05,
+      "loss": 0.18809621810913085,
+      "step": 450
+    },
+    {
+      "epoch": 1.6047297297297298,
+      "grad_norm": 0.34616008400917053,
+      "learning_rate": 1.5105105105105107e-05,
+      "loss": 0.15637354850769042,
+      "step": 475
+    },
+    {
+      "epoch": 1.689189189189189,
+      "grad_norm": 10.969264030456543,
+      "learning_rate": 1.4729729729729731e-05,
+      "loss": 0.22628171920776366,
+      "step": 500
+    },
+    {
+      "epoch": 1.7736486486486487,
+      "grad_norm": 17.27104377746582,
+      "learning_rate": 1.4354354354354357e-05,
+      "loss": 0.2247269058227539,
+      "step": 525
+    },
+    {
+      "epoch": 1.8581081081081081,
+      "grad_norm": 1.122333288192749,
+      "learning_rate": 1.397897897897898e-05,
+      "loss": 0.1473069667816162,
+      "step": 550
+    },
+    {
+      "epoch": 1.9425675675675675,
+      "grad_norm": 0.30135178565979004,
+      "learning_rate": 1.3603603603603606e-05,
+      "loss": 0.18822559356689453,
+      "step": 575
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9471698113207547,
+      "eval_f1": 0.8771929824561403,
+      "eval_loss": 0.19445720314979553,
+      "eval_precision": 0.8368200836820083,
+      "eval_recall": 0.9216589861751152,
+      "eval_roc_auc": 0.9843055578332813,
+      "eval_runtime": 3.9078,
+      "eval_samples_per_second": 271.255,
+      "eval_steps_per_second": 8.701,
+      "step": 592
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1242936625520640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

transformer/checkpoint-592/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699ccdec1f51a0096482e3403ced3b8ee41aac4e70941e5bd8752f8c52f7c09a
+size 5201

transformer/checkpoint-888/config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_RELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "NOT_RELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

transformer/checkpoint-888/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fc7b3e1231b0df1ee6197d4b79cc977ee6efe769601a28d08f6155e0394429
+size 1112205008

transformer/checkpoint-888/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d7fa175c5005a01599e4fdec14598bd8f76dcd60ecf72e216aaf04e3b735b7
+size 2224532875

transformer/checkpoint-888/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637187f6bca9c312460a048bc23889499d68e9152f595a188749add4b6bb4354
+size 14645

transformer/checkpoint-888/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626d811fdb20e63a2a61563727ae0fb44866597b95cbddab1196a4cb5e10b6cf
+size 1383

transformer/checkpoint-888/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012e4ef245198acca779ad61b1e34757abaaba4f83c3045c244728e9fce24daf
+size 1465

transformer/checkpoint-888/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc02d42fb2a10276563109e2287cc0dbe6b595d5b3b3401c7cfeffc0b7e20270
+size 17098351

transformer/checkpoint-888/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

transformer/checkpoint-888/trainer_state.json

@@ -0,0 +1,327 @@
+{
+  "best_global_step": 296,
+  "best_metric": 0.8941176470588236,
+  "best_model_checkpoint": "/content/agri-maize_corn-classifier/transformer/checkpoint-296",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 888,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08445945945945946,
+      "grad_norm": 4.2122979164123535,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.6247027587890625,
+      "step": 25
+    },
+    {
+      "epoch": 0.16891891891891891,
+      "grad_norm": 7.709840297698975,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 0.5710235595703125,
+      "step": 50
+    },
+    {
+      "epoch": 0.2533783783783784,
+      "grad_norm": 6.6395344734191895,
+      "learning_rate": 1e-05,
+      "loss": 0.5104244995117188,
+      "step": 75
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 5.032057762145996,
+      "learning_rate": 1.3378378378378381e-05,
+      "loss": 0.39651737213134763,
+      "step": 100
+    },
+    {
+      "epoch": 0.4222972972972973,
+      "grad_norm": 26.106103897094727,
+      "learning_rate": 1.6756756756756757e-05,
+      "loss": 0.30904300689697267,
+      "step": 125
+    },
+    {
+      "epoch": 0.5067567567567568,
+      "grad_norm": 19.755094528198242,
+      "learning_rate": 1.9984984984984987e-05,
+      "loss": 0.21882522583007813,
+      "step": 150
+    },
+    {
+      "epoch": 0.5912162162162162,
+      "grad_norm": 10.216408729553223,
+      "learning_rate": 1.9609609609609613e-05,
+      "loss": 0.2193868064880371,
+      "step": 175
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 19.423349380493164,
+      "learning_rate": 1.9234234234234235e-05,
+      "loss": 0.2879533958435059,
+      "step": 200
+    },
+    {
+      "epoch": 0.7601351351351351,
+      "grad_norm": 3.9074134826660156,
+      "learning_rate": 1.885885885885886e-05,
+      "loss": 0.21735734939575196,
+      "step": 225
+    },
+    {
+      "epoch": 0.8445945945945946,
+      "grad_norm": 0.8604102730751038,
+      "learning_rate": 1.8483483483483483e-05,
+      "loss": 0.28983583450317385,
+      "step": 250
+    },
+    {
+      "epoch": 0.9290540540540541,
+      "grad_norm": 49.190547943115234,
+      "learning_rate": 1.8108108108108108e-05,
+      "loss": 0.2321755599975586,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9575471698113207,
+      "eval_f1": 0.8941176470588236,
+      "eval_loss": 0.16295333206653595,
+      "eval_precision": 0.9134615384615384,
+      "eval_recall": 0.8755760368663594,
+      "eval_roc_auc": 0.9729488167669778,
+      "eval_runtime": 3.9863,
+      "eval_samples_per_second": 265.91,
+      "eval_steps_per_second": 8.529,
+      "step": 296
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 0.8517799377441406,
+      "learning_rate": 1.7732732732732734e-05,
+      "loss": 0.18440502166748046,
+      "step": 300
+    },
+    {
+      "epoch": 1.097972972972973,
+      "grad_norm": 2.9610507488250732,
+      "learning_rate": 1.735735735735736e-05,
+      "loss": 0.16707677841186525,
+      "step": 325
+    },
+    {
+      "epoch": 1.1824324324324325,
+      "grad_norm": 4.359492301940918,
+      "learning_rate": 1.6981981981981985e-05,
+      "loss": 0.22817501068115234,
+      "step": 350
+    },
+    {
+      "epoch": 1.2668918918918919,
+      "grad_norm": 0.49442264437675476,
+      "learning_rate": 1.6606606606606607e-05,
+      "loss": 0.16232917785644532,
+      "step": 375
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.9959002733230591,
+      "learning_rate": 1.6231231231231232e-05,
+      "loss": 0.2139061164855957,
+      "step": 400
+    },
+    {
+      "epoch": 1.4358108108108107,
+      "grad_norm": 1.0536309480667114,
+      "learning_rate": 1.5855855855855858e-05,
+      "loss": 0.203138484954834,
+      "step": 425
+    },
+    {
+      "epoch": 1.5202702702702702,
+      "grad_norm": 2.8971381187438965,
+      "learning_rate": 1.5480480480480483e-05,
+      "loss": 0.18809621810913085,
+      "step": 450
+    },
+    {
+      "epoch": 1.6047297297297298,
+      "grad_norm": 0.34616008400917053,
+      "learning_rate": 1.5105105105105107e-05,
+      "loss": 0.15637354850769042,
+      "step": 475
+    },
+    {
+      "epoch": 1.689189189189189,
+      "grad_norm": 10.969264030456543,
+      "learning_rate": 1.4729729729729731e-05,
+      "loss": 0.22628171920776366,
+      "step": 500
+    },
+    {
+      "epoch": 1.7736486486486487,
+      "grad_norm": 17.27104377746582,
+      "learning_rate": 1.4354354354354357e-05,
+      "loss": 0.2247269058227539,
+      "step": 525
+    },
+    {
+      "epoch": 1.8581081081081081,
+      "grad_norm": 1.122333288192749,
+      "learning_rate": 1.397897897897898e-05,
+      "loss": 0.1473069667816162,
+      "step": 550
+    },
+    {
+      "epoch": 1.9425675675675675,
+      "grad_norm": 0.30135178565979004,
+      "learning_rate": 1.3603603603603606e-05,
+      "loss": 0.18822559356689453,
+      "step": 575
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9471698113207547,
+      "eval_f1": 0.8771929824561403,
+      "eval_loss": 0.19445720314979553,
+      "eval_precision": 0.8368200836820083,
+      "eval_recall": 0.9216589861751152,
+      "eval_roc_auc": 0.9843055578332813,
+      "eval_runtime": 3.9078,
+      "eval_samples_per_second": 271.255,
+      "eval_steps_per_second": 8.701,
+      "step": 592
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 26.52724838256836,
+      "learning_rate": 1.322822822822823e-05,
+      "loss": 0.13748784065246583,
+      "step": 600
+    },
+    {
+      "epoch": 2.1114864864864864,
+      "grad_norm": 10.8816499710083,
+      "learning_rate": 1.2852852852852854e-05,
+      "loss": 0.1081045150756836,
+      "step": 625
+    },
+    {
+      "epoch": 2.195945945945946,
+      "grad_norm": 2.227597713470459,
+      "learning_rate": 1.2477477477477477e-05,
+      "loss": 0.14378289222717286,
+      "step": 650
+    },
+    {
+      "epoch": 2.2804054054054053,
+      "grad_norm": 12.489811897277832,
+      "learning_rate": 1.2102102102102103e-05,
+      "loss": 0.1484208297729492,
+      "step": 675
+    },
+    {
+      "epoch": 2.364864864864865,
+      "grad_norm": 28.363985061645508,
+      "learning_rate": 1.1726726726726727e-05,
+      "loss": 0.09925691604614258,
+      "step": 700
+    },
+    {
+      "epoch": 2.4493243243243246,
+      "grad_norm": 10.956056594848633,
+      "learning_rate": 1.1351351351351352e-05,
+      "loss": 0.1072914218902588,
+      "step": 725
+    },
+    {
+      "epoch": 2.5337837837837838,
+      "grad_norm": 35.35126876831055,
+      "learning_rate": 1.0975975975975976e-05,
+      "loss": 0.16145267486572265,
+      "step": 750
+    },
+    {
+      "epoch": 2.618243243243243,
+      "grad_norm": 4.4620256423950195,
+      "learning_rate": 1.0600600600600602e-05,
+      "loss": 0.12065947532653809,
+      "step": 775
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 3.3222928047180176,
+      "learning_rate": 1.0225225225225226e-05,
+      "loss": 0.1423185920715332,
+      "step": 800
+    },
+    {
+      "epoch": 2.7871621621621623,
+      "grad_norm": 0.3517614006996155,
+      "learning_rate": 9.849849849849851e-06,
+      "loss": 0.14739763259887695,
+      "step": 825
+    },
+    {
+      "epoch": 2.8716216216216215,
+      "grad_norm": 8.386738777160645,
+      "learning_rate": 9.474474474474475e-06,
+      "loss": 0.14476879119873046,
+      "step": 850
+    },
+    {
+      "epoch": 2.956081081081081,
+      "grad_norm": 1.721596121788025,
+      "learning_rate": 9.0990990990991e-06,
+      "loss": 0.10418204307556152,
+      "step": 875
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9471698113207547,
+      "eval_f1": 0.8761061946902655,
+      "eval_loss": 0.20338048040866852,
+      "eval_precision": 0.8425531914893617,
+      "eval_recall": 0.9124423963133641,
+      "eval_roc_auc": 0.9789784126255255,
+      "eval_runtime": 3.8956,
+      "eval_samples_per_second": 272.099,
+      "eval_steps_per_second": 8.728,
+      "step": 888
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1864404938280960.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

transformer/checkpoint-888/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699ccdec1f51a0096482e3403ced3b8ee41aac4e70941e5bd8752f8c52f7c09a
+size 5201

transformer/config.json

@@ -0,0 +1,46 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_RELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "NOT_RELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "threshold": 0.32782965898513794,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "validation_threshold_report": {
+    "f1": 0.9002320185614848,
+    "precision": 0.9065420560747663,
+    "recall": 0.8940092165898618,
+    "threshold": 0.32782965898513794
+  },
+  "vocab_size": 250002
+}