Text Classification
Transformers
Joblib
Safetensors
multilingual
binary-classification
amis
agriculture
Instructions to use faodl/agri-utilization-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use faodl/agri-utilization-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="faodl/agri-utilization-classifier")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("faodl/agri-utilization-classifier", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +65 -65
- REPORT.md +65 -65
- baselines/embedding-lightgbm/embedding-lightgbm.joblib +2 -2
- baselines/embedding-lightgbm/test_predictions.csv +0 -0
- baselines/embedding-lightgbm/validation_predictions.csv +0 -0
- baselines/embedding-logistic/embedding-logistic.joblib +2 -2
- baselines/embedding-logistic/test_predictions.csv +0 -0
- baselines/embedding-logistic/validation_predictions.csv +0 -0
- baselines/embedding-svm/embedding-svm.joblib +1 -1
- baselines/embedding-svm/test_predictions.csv +0 -0
- baselines/embedding-svm/validation_predictions.csv +0 -0
- baselines/logistic/logistic_tfidf.joblib +2 -2
- baselines/logistic/test_predictions.csv +0 -0
- baselines/logistic/validation_predictions.csv +0 -0
- baselines/xgboost/test_predictions.csv +0 -0
- baselines/xgboost/validation_predictions.csv +0 -0
- baselines/xgboost/xgboost_tfidf.joblib +2 -2
- report.json +701 -701
- transformer/checkpoint-1220/config.json +1 -1
- transformer/checkpoint-1220/model.safetensors +1 -1
- transformer/checkpoint-1220/optimizer.pt +1 -1
- transformer/checkpoint-1220/rng_state.pth +1 -1
- transformer/checkpoint-1220/scaler.pt +1 -1
- transformer/checkpoint-1220/scheduler.pt +1 -1
- transformer/checkpoint-1220/trainer_state.json +218 -244
- transformer/checkpoint-1220/training_args.bin +2 -2
- transformer/checkpoint-1830/config.json +39 -0
- transformer/checkpoint-1830/model.safetensors +3 -0
- transformer/checkpoint-1830/optimizer.pt +3 -0
- transformer/checkpoint-1830/rng_state.pth +3 -0
- transformer/checkpoint-1830/scaler.pt +3 -0
- transformer/checkpoint-1830/scheduler.pt +3 -0
- transformer/checkpoint-1830/tokenizer.json +3 -0
- transformer/checkpoint-1830/tokenizer_config.json +15 -0
- transformer/checkpoint-1830/trainer_state.json +593 -0
- transformer/checkpoint-1830/training_args.bin +3 -0
- transformer/checkpoint-610/config.json +1 -1
- transformer/checkpoint-610/model.safetensors +1 -1
- transformer/checkpoint-610/optimizer.pt +1 -1
- transformer/checkpoint-610/rng_state.pth +1 -1
- transformer/checkpoint-610/scaler.pt +1 -1
- transformer/checkpoint-610/scheduler.pt +1 -1
- transformer/checkpoint-610/trainer_state.json +113 -126
- transformer/checkpoint-610/training_args.bin +2 -2
- transformer/config.json +6 -6
- transformer/model.safetensors +1 -1
- transformer/test_predictions.csv +0 -0
- transformer/training_args.bin +2 -2
- transformer/validation_predictions.csv +0 -0
.gitattributes
CHANGED
|
@@ -39,3 +39,4 @@ transformer/checkpoint-305/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 39 |
transformer/checkpoint-610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
transformer/checkpoint-915/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
transformer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 39 |
transformer/checkpoint-610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
transformer/checkpoint-915/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
transformer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
transformer/checkpoint-1830/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -17,19 +17,19 @@ It includes the Transformer model, any configured TF-IDF or sentence-embedding b
|
|
| 17 |
|
| 18 |
- Dataset: `faodl/amis-agri-utilization`
|
| 19 |
- Dataset subset: ``
|
| 20 |
-
- Dataset revision: `
|
| 21 |
- Text column: `chunk_text`
|
| 22 |
- Label column: `label`
|
| 23 |
- Transformer: `FacebookAI/xlm-roberta-base`
|
| 24 |
-
- Generated at: `2026-
|
| 25 |
|
| 26 |
## Dataset Summary
|
| 27 |
|
| 28 |
| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
|
| 29 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 30 |
-
| train |
|
| 31 |
-
| validation |
|
| 32 |
-
| test |
|
| 33 |
|
| 34 |
## Threshold Comparison on Validation Split
|
| 35 |
|
|
@@ -37,35 +37,35 @@ Validation metrics document threshold selection and tuning behavior; test metric
|
|
| 37 |
|
| 38 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 39 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 40 |
-
| logistic_tfidf | 0.500 | 0.
|
| 41 |
-
| logistic_tfidf | 0.
|
| 42 |
-
| xgboost_tfidf | 0.500 | 0.
|
| 43 |
-
| xgboost_tfidf | 0.
|
| 44 |
-
| embedding-logistic_sentence_embeddings | 0.500 | 0.
|
| 45 |
-
| embedding-logistic_sentence_embeddings | 0.
|
| 46 |
-
| embedding-svm_sentence_embeddings | 0.500 | 0.
|
| 47 |
-
| embedding-svm_sentence_embeddings | 0.
|
| 48 |
-
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.
|
| 49 |
-
| embedding-lightgbm_sentence_embeddings | 0.
|
| 50 |
-
| transformer | 0.500 | 0.
|
| 51 |
-
| transformer | 0.
|
| 52 |
|
| 53 |
## Threshold Comparison on Test Split
|
| 54 |
|
| 55 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 56 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 57 |
-
| logistic_tfidf | 0.500 | 0.
|
| 58 |
-
| logistic_tfidf | 0.
|
| 59 |
-
| xgboost_tfidf | 0.500 | 0.
|
| 60 |
-
| xgboost_tfidf | 0.
|
| 61 |
-
| embedding-logistic_sentence_embeddings | 0.500 | 0.891 | 0.
|
| 62 |
-
| embedding-logistic_sentence_embeddings | 0.
|
| 63 |
-
| embedding-svm_sentence_embeddings | 0.500 | 0.
|
| 64 |
-
| embedding-svm_sentence_embeddings | 0.
|
| 65 |
-
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.
|
| 66 |
-
| embedding-lightgbm_sentence_embeddings | 0.
|
| 67 |
-
| transformer | 0.500 | 0.
|
| 68 |
-
| transformer | 0.
|
| 69 |
|
| 70 |
## Confusion Matrices on Test Split
|
| 71 |
|
|
@@ -75,95 +75,95 @@ Rows are true labels and columns are predicted labels.
|
|
| 75 |
|
| 76 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 77 |
| --- | ---: | ---: |
|
| 78 |
-
| NOT_RELEVANT |
|
| 79 |
-
| RELEVANT |
|
| 80 |
|
| 81 |
-
### logistic_tfidf at threshold 0.
|
| 82 |
|
| 83 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 84 |
| --- | ---: | ---: |
|
| 85 |
-
| NOT_RELEVANT |
|
| 86 |
-
| RELEVANT |
|
| 87 |
|
| 88 |
### xgboost_tfidf at threshold 0.500
|
| 89 |
|
| 90 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 91 |
| --- | ---: | ---: |
|
| 92 |
-
| NOT_RELEVANT |
|
| 93 |
-
| RELEVANT |
|
| 94 |
|
| 95 |
-
### xgboost_tfidf at threshold 0.
|
| 96 |
|
| 97 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 98 |
| --- | ---: | ---: |
|
| 99 |
-
| NOT_RELEVANT |
|
| 100 |
-
| RELEVANT |
|
| 101 |
|
| 102 |
### embedding-logistic_sentence_embeddings at threshold 0.500
|
| 103 |
|
| 104 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 105 |
| --- | ---: | ---: |
|
| 106 |
-
| NOT_RELEVANT |
|
| 107 |
-
| RELEVANT |
|
| 108 |
|
| 109 |
-
### embedding-logistic_sentence_embeddings at threshold 0.
|
| 110 |
|
| 111 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 112 |
| --- | ---: | ---: |
|
| 113 |
-
| NOT_RELEVANT |
|
| 114 |
-
| RELEVANT |
|
| 115 |
|
| 116 |
### embedding-svm_sentence_embeddings at threshold 0.500
|
| 117 |
|
| 118 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 119 |
| --- | ---: | ---: |
|
| 120 |
-
| NOT_RELEVANT |
|
| 121 |
-
| RELEVANT |
|
| 122 |
|
| 123 |
-
### embedding-svm_sentence_embeddings at threshold 0.
|
| 124 |
|
| 125 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 126 |
| --- | ---: | ---: |
|
| 127 |
-
| NOT_RELEVANT |
|
| 128 |
-
| RELEVANT |
|
| 129 |
|
| 130 |
### embedding-lightgbm_sentence_embeddings at threshold 0.500
|
| 131 |
|
| 132 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 133 |
| --- | ---: | ---: |
|
| 134 |
-
| NOT_RELEVANT |
|
| 135 |
-
| RELEVANT |
|
| 136 |
|
| 137 |
-
### embedding-lightgbm_sentence_embeddings at threshold 0.
|
| 138 |
|
| 139 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 140 |
| --- | ---: | ---: |
|
| 141 |
-
| NOT_RELEVANT |
|
| 142 |
-
| RELEVANT |
|
| 143 |
|
| 144 |
### transformer at threshold 0.500
|
| 145 |
|
| 146 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 147 |
| --- | ---: | ---: |
|
| 148 |
-
| NOT_RELEVANT |
|
| 149 |
-
| RELEVANT |
|
| 150 |
|
| 151 |
-
### transformer at threshold 0.
|
| 152 |
|
| 153 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 154 |
| --- | ---: | ---: |
|
| 155 |
-
| NOT_RELEVANT |
|
| 156 |
-
| RELEVANT |
|
| 157 |
|
| 158 |
|
| 159 |
## Validation-Tuned Thresholds
|
| 160 |
|
| 161 |
-
- `logistic_tfidf`: threshold `0.
|
| 162 |
-
- `xgboost_tfidf`: threshold `0.
|
| 163 |
-
- `embedding-logistic_sentence_embeddings`: threshold `0.
|
| 164 |
-
- `embedding-svm_sentence_embeddings`: threshold `0.
|
| 165 |
-
- `embedding-lightgbm_sentence_embeddings`: threshold `0.
|
| 166 |
-
- `transformer`: threshold `0.
|
| 167 |
|
| 168 |
## Artifacts
|
| 169 |
|
|
|
|
| 17 |
|
| 18 |
- Dataset: `faodl/amis-agri-utilization`
|
| 19 |
- Dataset subset: ``
|
| 20 |
+
- Dataset revision: `main`
|
| 21 |
- Text column: `chunk_text`
|
| 22 |
- Label column: `label`
|
| 23 |
- Transformer: `FacebookAI/xlm-roberta-base`
|
| 24 |
+
- Generated at: `2026-06-09T23:58:45.600559+00:00`
|
| 25 |
|
| 26 |
## Dataset Summary
|
| 27 |
|
| 28 |
| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
|
| 29 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 30 |
+
| train | 9753 | 8950 | 803 | 4987 | 696.4 |
|
| 31 |
+
| validation | 2084 | 1885 | 199 | 1069 | 700.8 |
|
| 32 |
+
| test | 2086 | 1957 | 129 | 1069 | 701.6 |
|
| 33 |
|
| 34 |
## Threshold Comparison on Validation Split
|
| 35 |
|
|
|
|
| 37 |
|
| 38 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 39 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 40 |
+
| logistic_tfidf | 0.500 | 0.901 | 0.482 | 0.462 | 0.472 | 0.867 | 0.496 |
|
| 41 |
+
| logistic_tfidf | 0.360 | 0.863 | 0.380 | 0.688 | 0.489 | 0.867 | 0.496 |
|
| 42 |
+
| xgboost_tfidf | 0.500 | 0.919 | 0.721 | 0.246 | 0.367 | 0.834 | 0.493 |
|
| 43 |
+
| xgboost_tfidf | 0.104 | 0.903 | 0.492 | 0.588 | 0.535 | 0.834 | 0.493 |
|
| 44 |
+
| embedding-logistic_sentence_embeddings | 0.500 | 0.895 | 0.474 | 0.869 | 0.613 | 0.952 | 0.652 |
|
| 45 |
+
| embedding-logistic_sentence_embeddings | 0.726 | 0.930 | 0.602 | 0.804 | 0.688 | 0.952 | 0.652 |
|
| 46 |
+
| embedding-svm_sentence_embeddings | 0.500 | 0.931 | 0.712 | 0.472 | 0.568 | 0.954 | 0.670 |
|
| 47 |
+
| embedding-svm_sentence_embeddings | 0.245 | 0.938 | 0.647 | 0.764 | 0.700 | 0.954 | 0.670 |
|
| 48 |
+
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.937 | 0.681 | 0.633 | 0.656 | 0.954 | 0.669 |
|
| 49 |
+
| embedding-lightgbm_sentence_embeddings | 0.089 | 0.933 | 0.610 | 0.824 | 0.701 | 0.954 | 0.669 |
|
| 50 |
+
| transformer | 0.500 | 0.938 | 0.653 | 0.739 | 0.693 | 0.954 | 0.726 |
|
| 51 |
+
| transformer | 0.544 | 0.939 | 0.662 | 0.739 | 0.698 | 0.954 | 0.726 |
|
| 52 |
|
| 53 |
## Threshold Comparison on Test Split
|
| 54 |
|
| 55 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 56 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 57 |
+
| logistic_tfidf | 0.500 | 0.918 | 0.358 | 0.419 | 0.386 | 0.856 | 0.398 |
|
| 58 |
+
| logistic_tfidf | 0.360 | 0.869 | 0.267 | 0.643 | 0.377 | 0.856 | 0.398 |
|
| 59 |
+
| xgboost_tfidf | 0.500 | 0.950 | 0.766 | 0.279 | 0.409 | 0.821 | 0.471 |
|
| 60 |
+
| xgboost_tfidf | 0.104 | 0.907 | 0.343 | 0.558 | 0.425 | 0.821 | 0.471 |
|
| 61 |
+
| embedding-logistic_sentence_embeddings | 0.500 | 0.891 | 0.350 | 0.884 | 0.501 | 0.951 | 0.543 |
|
| 62 |
+
| embedding-logistic_sentence_embeddings | 0.726 | 0.929 | 0.449 | 0.690 | 0.544 | 0.951 | 0.543 |
|
| 63 |
+
| embedding-svm_sentence_embeddings | 0.500 | 0.948 | 0.606 | 0.465 | 0.526 | 0.955 | 0.566 |
|
| 64 |
+
| embedding-svm_sentence_embeddings | 0.245 | 0.937 | 0.494 | 0.674 | 0.570 | 0.955 | 0.566 |
|
| 65 |
+
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.948 | 0.579 | 0.597 | 0.588 | 0.948 | 0.585 |
|
| 66 |
+
| embedding-lightgbm_sentence_embeddings | 0.089 | 0.932 | 0.472 | 0.775 | 0.587 | 0.948 | 0.585 |
|
| 67 |
+
| transformer | 0.500 | 0.943 | 0.532 | 0.643 | 0.582 | 0.931 | 0.500 |
|
| 68 |
+
| transformer | 0.544 | 0.942 | 0.529 | 0.636 | 0.577 | 0.931 | 0.500 |
|
| 69 |
|
| 70 |
## Confusion Matrices on Test Split
|
| 71 |
|
|
|
|
| 75 |
|
| 76 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 77 |
| --- | ---: | ---: |
|
| 78 |
+
| NOT_RELEVANT | 1860 | 97 |
|
| 79 |
+
| RELEVANT | 75 | 54 |
|
| 80 |
|
| 81 |
+
### logistic_tfidf at threshold 0.360
|
| 82 |
|
| 83 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 84 |
| --- | ---: | ---: |
|
| 85 |
+
| NOT_RELEVANT | 1729 | 228 |
|
| 86 |
+
| RELEVANT | 46 | 83 |
|
| 87 |
|
| 88 |
### xgboost_tfidf at threshold 0.500
|
| 89 |
|
| 90 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 91 |
| --- | ---: | ---: |
|
| 92 |
+
| NOT_RELEVANT | 1946 | 11 |
|
| 93 |
+
| RELEVANT | 93 | 36 |
|
| 94 |
|
| 95 |
+
### xgboost_tfidf at threshold 0.104
|
| 96 |
|
| 97 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 98 |
| --- | ---: | ---: |
|
| 99 |
+
| NOT_RELEVANT | 1819 | 138 |
|
| 100 |
+
| RELEVANT | 57 | 72 |
|
| 101 |
|
| 102 |
### embedding-logistic_sentence_embeddings at threshold 0.500
|
| 103 |
|
| 104 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 105 |
| --- | ---: | ---: |
|
| 106 |
+
| NOT_RELEVANT | 1745 | 212 |
|
| 107 |
+
| RELEVANT | 15 | 114 |
|
| 108 |
|
| 109 |
+
### embedding-logistic_sentence_embeddings at threshold 0.726
|
| 110 |
|
| 111 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 112 |
| --- | ---: | ---: |
|
| 113 |
+
| NOT_RELEVANT | 1848 | 109 |
|
| 114 |
+
| RELEVANT | 40 | 89 |
|
| 115 |
|
| 116 |
### embedding-svm_sentence_embeddings at threshold 0.500
|
| 117 |
|
| 118 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 119 |
| --- | ---: | ---: |
|
| 120 |
+
| NOT_RELEVANT | 1918 | 39 |
|
| 121 |
+
| RELEVANT | 69 | 60 |
|
| 122 |
|
| 123 |
+
### embedding-svm_sentence_embeddings at threshold 0.245
|
| 124 |
|
| 125 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 126 |
| --- | ---: | ---: |
|
| 127 |
+
| NOT_RELEVANT | 1868 | 89 |
|
| 128 |
+
| RELEVANT | 42 | 87 |
|
| 129 |
|
| 130 |
### embedding-lightgbm_sentence_embeddings at threshold 0.500
|
| 131 |
|
| 132 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 133 |
| --- | ---: | ---: |
|
| 134 |
+
| NOT_RELEVANT | 1901 | 56 |
|
| 135 |
+
| RELEVANT | 52 | 77 |
|
| 136 |
|
| 137 |
+
### embedding-lightgbm_sentence_embeddings at threshold 0.089
|
| 138 |
|
| 139 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 140 |
| --- | ---: | ---: |
|
| 141 |
+
| NOT_RELEVANT | 1845 | 112 |
|
| 142 |
+
| RELEVANT | 29 | 100 |
|
| 143 |
|
| 144 |
### transformer at threshold 0.500
|
| 145 |
|
| 146 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 147 |
| --- | ---: | ---: |
|
| 148 |
+
| NOT_RELEVANT | 1884 | 73 |
|
| 149 |
+
| RELEVANT | 46 | 83 |
|
| 150 |
|
| 151 |
+
### transformer at threshold 0.544
|
| 152 |
|
| 153 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 154 |
| --- | ---: | ---: |
|
| 155 |
+
| NOT_RELEVANT | 1884 | 73 |
|
| 156 |
+
| RELEVANT | 47 | 82 |
|
| 157 |
|
| 158 |
|
| 159 |
## Validation-Tuned Thresholds
|
| 160 |
|
| 161 |
+
- `logistic_tfidf`: threshold `0.360` (validation F1 `0.489`); test F1 change vs 0.5: `-0.008`.
|
| 162 |
+
- `xgboost_tfidf`: threshold `0.104` (validation F1 `0.535`); test F1 change vs 0.5: `+0.016`.
|
| 163 |
+
- `embedding-logistic_sentence_embeddings`: threshold `0.726` (validation F1 `0.688`); test F1 change vs 0.5: `+0.043`.
|
| 164 |
+
- `embedding-svm_sentence_embeddings`: threshold `0.245` (validation F1 `0.700`); test F1 change vs 0.5: `+0.044`.
|
| 165 |
+
- `embedding-lightgbm_sentence_embeddings`: threshold `0.089` (validation F1 `0.701`); test F1 change vs 0.5: `-0.001`.
|
| 166 |
+
- `transformer`: threshold `0.544` (validation F1 `0.698`); test F1 change vs 0.5: `-0.005`.
|
| 167 |
|
| 168 |
## Artifacts
|
| 169 |
|
REPORT.md
CHANGED
|
@@ -2,19 +2,19 @@
|
|
| 2 |
|
| 3 |
- Dataset: `faodl/amis-agri-utilization`
|
| 4 |
- Dataset subset: ``
|
| 5 |
-
- Dataset revision: `
|
| 6 |
- Text column: `chunk_text`
|
| 7 |
- Label column: `label`
|
| 8 |
- Transformer: `FacebookAI/xlm-roberta-base`
|
| 9 |
-
- Generated at: `2026-
|
| 10 |
|
| 11 |
## Dataset Summary
|
| 12 |
|
| 13 |
| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
|
| 14 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 15 |
-
| train |
|
| 16 |
-
| validation |
|
| 17 |
-
| test |
|
| 18 |
|
| 19 |
## Threshold Comparison on Validation Split
|
| 20 |
|
|
@@ -22,35 +22,35 @@ Validation metrics document threshold selection and tuning behavior; test metric
|
|
| 22 |
|
| 23 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 24 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 25 |
-
| logistic_tfidf | 0.500 | 0.
|
| 26 |
-
| logistic_tfidf | 0.
|
| 27 |
-
| xgboost_tfidf | 0.500 | 0.
|
| 28 |
-
| xgboost_tfidf | 0.
|
| 29 |
-
| embedding-logistic_sentence_embeddings | 0.500 | 0.
|
| 30 |
-
| embedding-logistic_sentence_embeddings | 0.
|
| 31 |
-
| embedding-svm_sentence_embeddings | 0.500 | 0.
|
| 32 |
-
| embedding-svm_sentence_embeddings | 0.
|
| 33 |
-
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.
|
| 34 |
-
| embedding-lightgbm_sentence_embeddings | 0.
|
| 35 |
-
| transformer | 0.500 | 0.
|
| 36 |
-
| transformer | 0.
|
| 37 |
|
| 38 |
## Threshold Comparison on Test Split
|
| 39 |
|
| 40 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 41 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 42 |
-
| logistic_tfidf | 0.500 | 0.
|
| 43 |
-
| logistic_tfidf | 0.
|
| 44 |
-
| xgboost_tfidf | 0.500 | 0.
|
| 45 |
-
| xgboost_tfidf | 0.
|
| 46 |
-
| embedding-logistic_sentence_embeddings | 0.500 | 0.891 | 0.
|
| 47 |
-
| embedding-logistic_sentence_embeddings | 0.
|
| 48 |
-
| embedding-svm_sentence_embeddings | 0.500 | 0.
|
| 49 |
-
| embedding-svm_sentence_embeddings | 0.
|
| 50 |
-
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.
|
| 51 |
-
| embedding-lightgbm_sentence_embeddings | 0.
|
| 52 |
-
| transformer | 0.500 | 0.
|
| 53 |
-
| transformer | 0.
|
| 54 |
|
| 55 |
## Confusion Matrices on Test Split
|
| 56 |
|
|
@@ -60,95 +60,95 @@ Rows are true labels and columns are predicted labels.
|
|
| 60 |
|
| 61 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 62 |
| --- | ---: | ---: |
|
| 63 |
-
| NOT_RELEVANT |
|
| 64 |
-
| RELEVANT |
|
| 65 |
|
| 66 |
-
### logistic_tfidf at threshold 0.
|
| 67 |
|
| 68 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 69 |
| --- | ---: | ---: |
|
| 70 |
-
| NOT_RELEVANT |
|
| 71 |
-
| RELEVANT |
|
| 72 |
|
| 73 |
### xgboost_tfidf at threshold 0.500
|
| 74 |
|
| 75 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 76 |
| --- | ---: | ---: |
|
| 77 |
-
| NOT_RELEVANT |
|
| 78 |
-
| RELEVANT |
|
| 79 |
|
| 80 |
-
### xgboost_tfidf at threshold 0.
|
| 81 |
|
| 82 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 83 |
| --- | ---: | ---: |
|
| 84 |
-
| NOT_RELEVANT |
|
| 85 |
-
| RELEVANT |
|
| 86 |
|
| 87 |
### embedding-logistic_sentence_embeddings at threshold 0.500
|
| 88 |
|
| 89 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 90 |
| --- | ---: | ---: |
|
| 91 |
-
| NOT_RELEVANT |
|
| 92 |
-
| RELEVANT |
|
| 93 |
|
| 94 |
-
### embedding-logistic_sentence_embeddings at threshold 0.
|
| 95 |
|
| 96 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 97 |
| --- | ---: | ---: |
|
| 98 |
-
| NOT_RELEVANT |
|
| 99 |
-
| RELEVANT |
|
| 100 |
|
| 101 |
### embedding-svm_sentence_embeddings at threshold 0.500
|
| 102 |
|
| 103 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 104 |
| --- | ---: | ---: |
|
| 105 |
-
| NOT_RELEVANT |
|
| 106 |
-
| RELEVANT |
|
| 107 |
|
| 108 |
-
### embedding-svm_sentence_embeddings at threshold 0.
|
| 109 |
|
| 110 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 111 |
| --- | ---: | ---: |
|
| 112 |
-
| NOT_RELEVANT |
|
| 113 |
-
| RELEVANT |
|
| 114 |
|
| 115 |
### embedding-lightgbm_sentence_embeddings at threshold 0.500
|
| 116 |
|
| 117 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 118 |
| --- | ---: | ---: |
|
| 119 |
-
| NOT_RELEVANT |
|
| 120 |
-
| RELEVANT |
|
| 121 |
|
| 122 |
-
### embedding-lightgbm_sentence_embeddings at threshold 0.
|
| 123 |
|
| 124 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 125 |
| --- | ---: | ---: |
|
| 126 |
-
| NOT_RELEVANT |
|
| 127 |
-
| RELEVANT |
|
| 128 |
|
| 129 |
### transformer at threshold 0.500
|
| 130 |
|
| 131 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 132 |
| --- | ---: | ---: |
|
| 133 |
-
| NOT_RELEVANT |
|
| 134 |
-
| RELEVANT |
|
| 135 |
|
| 136 |
-
### transformer at threshold 0.
|
| 137 |
|
| 138 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 139 |
| --- | ---: | ---: |
|
| 140 |
-
| NOT_RELEVANT |
|
| 141 |
-
| RELEVANT |
|
| 142 |
|
| 143 |
|
| 144 |
## Validation-Tuned Thresholds
|
| 145 |
|
| 146 |
-
- `logistic_tfidf`: threshold `0.
|
| 147 |
-
- `xgboost_tfidf`: threshold `0.
|
| 148 |
-
- `embedding-logistic_sentence_embeddings`: threshold `0.
|
| 149 |
-
- `embedding-svm_sentence_embeddings`: threshold `0.
|
| 150 |
-
- `embedding-lightgbm_sentence_embeddings`: threshold `0.
|
| 151 |
-
- `transformer`: threshold `0.
|
| 152 |
|
| 153 |
## Artifacts
|
| 154 |
|
|
|
|
| 2 |
|
| 3 |
- Dataset: `faodl/amis-agri-utilization`
|
| 4 |
- Dataset subset: ``
|
| 5 |
+
- Dataset revision: `main`
|
| 6 |
- Text column: `chunk_text`
|
| 7 |
- Label column: `label`
|
| 8 |
- Transformer: `FacebookAI/xlm-roberta-base`
|
| 9 |
+
- Generated at: `2026-06-09T23:58:45.600559+00:00`
|
| 10 |
|
| 11 |
## Dataset Summary
|
| 12 |
|
| 13 |
| Split | Rows | Label 0 | Label 1 | Unique groups | Mean text length |
|
| 14 |
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 15 |
+
| train | 9753 | 8950 | 803 | 4987 | 696.4 |
|
| 16 |
+
| validation | 2084 | 1885 | 199 | 1069 | 700.8 |
|
| 17 |
+
| test | 2086 | 1957 | 129 | 1069 | 701.6 |
|
| 18 |
|
| 19 |
## Threshold Comparison on Validation Split
|
| 20 |
|
|
|
|
| 22 |
|
| 23 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 24 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 25 |
+
| logistic_tfidf | 0.500 | 0.901 | 0.482 | 0.462 | 0.472 | 0.867 | 0.496 |
|
| 26 |
+
| logistic_tfidf | 0.360 | 0.863 | 0.380 | 0.688 | 0.489 | 0.867 | 0.496 |
|
| 27 |
+
| xgboost_tfidf | 0.500 | 0.919 | 0.721 | 0.246 | 0.367 | 0.834 | 0.493 |
|
| 28 |
+
| xgboost_tfidf | 0.104 | 0.903 | 0.492 | 0.588 | 0.535 | 0.834 | 0.493 |
|
| 29 |
+
| embedding-logistic_sentence_embeddings | 0.500 | 0.895 | 0.474 | 0.869 | 0.613 | 0.952 | 0.652 |
|
| 30 |
+
| embedding-logistic_sentence_embeddings | 0.726 | 0.930 | 0.602 | 0.804 | 0.688 | 0.952 | 0.652 |
|
| 31 |
+
| embedding-svm_sentence_embeddings | 0.500 | 0.931 | 0.712 | 0.472 | 0.568 | 0.954 | 0.670 |
|
| 32 |
+
| embedding-svm_sentence_embeddings | 0.245 | 0.938 | 0.647 | 0.764 | 0.700 | 0.954 | 0.670 |
|
| 33 |
+
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.937 | 0.681 | 0.633 | 0.656 | 0.954 | 0.669 |
|
| 34 |
+
| embedding-lightgbm_sentence_embeddings | 0.089 | 0.933 | 0.610 | 0.824 | 0.701 | 0.954 | 0.669 |
|
| 35 |
+
| transformer | 0.500 | 0.938 | 0.653 | 0.739 | 0.693 | 0.954 | 0.726 |
|
| 36 |
+
| transformer | 0.544 | 0.939 | 0.662 | 0.739 | 0.698 | 0.954 | 0.726 |
|
| 37 |
|
| 38 |
## Threshold Comparison on Test Split
|
| 39 |
|
| 40 |
| Model | Threshold | Accuracy | Precision | Recall | F1 | ROC AUC | Average precision |
|
| 41 |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 42 |
+
| logistic_tfidf | 0.500 | 0.918 | 0.358 | 0.419 | 0.386 | 0.856 | 0.398 |
|
| 43 |
+
| logistic_tfidf | 0.360 | 0.869 | 0.267 | 0.643 | 0.377 | 0.856 | 0.398 |
|
| 44 |
+
| xgboost_tfidf | 0.500 | 0.950 | 0.766 | 0.279 | 0.409 | 0.821 | 0.471 |
|
| 45 |
+
| xgboost_tfidf | 0.104 | 0.907 | 0.343 | 0.558 | 0.425 | 0.821 | 0.471 |
|
| 46 |
+
| embedding-logistic_sentence_embeddings | 0.500 | 0.891 | 0.350 | 0.884 | 0.501 | 0.951 | 0.543 |
|
| 47 |
+
| embedding-logistic_sentence_embeddings | 0.726 | 0.929 | 0.449 | 0.690 | 0.544 | 0.951 | 0.543 |
|
| 48 |
+
| embedding-svm_sentence_embeddings | 0.500 | 0.948 | 0.606 | 0.465 | 0.526 | 0.955 | 0.566 |
|
| 49 |
+
| embedding-svm_sentence_embeddings | 0.245 | 0.937 | 0.494 | 0.674 | 0.570 | 0.955 | 0.566 |
|
| 50 |
+
| embedding-lightgbm_sentence_embeddings | 0.500 | 0.948 | 0.579 | 0.597 | 0.588 | 0.948 | 0.585 |
|
| 51 |
+
| embedding-lightgbm_sentence_embeddings | 0.089 | 0.932 | 0.472 | 0.775 | 0.587 | 0.948 | 0.585 |
|
| 52 |
+
| transformer | 0.500 | 0.943 | 0.532 | 0.643 | 0.582 | 0.931 | 0.500 |
|
| 53 |
+
| transformer | 0.544 | 0.942 | 0.529 | 0.636 | 0.577 | 0.931 | 0.500 |
|
| 54 |
|
| 55 |
## Confusion Matrices on Test Split
|
| 56 |
|
|
|
|
| 60 |
|
| 61 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 62 |
| --- | ---: | ---: |
|
| 63 |
+
| NOT_RELEVANT | 1860 | 97 |
|
| 64 |
+
| RELEVANT | 75 | 54 |
|
| 65 |
|
| 66 |
+
### logistic_tfidf at threshold 0.360
|
| 67 |
|
| 68 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 69 |
| --- | ---: | ---: |
|
| 70 |
+
| NOT_RELEVANT | 1729 | 228 |
|
| 71 |
+
| RELEVANT | 46 | 83 |
|
| 72 |
|
| 73 |
### xgboost_tfidf at threshold 0.500
|
| 74 |
|
| 75 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 76 |
| --- | ---: | ---: |
|
| 77 |
+
| NOT_RELEVANT | 1946 | 11 |
|
| 78 |
+
| RELEVANT | 93 | 36 |
|
| 79 |
|
| 80 |
+
### xgboost_tfidf at threshold 0.104
|
| 81 |
|
| 82 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 83 |
| --- | ---: | ---: |
|
| 84 |
+
| NOT_RELEVANT | 1819 | 138 |
|
| 85 |
+
| RELEVANT | 57 | 72 |
|
| 86 |
|
| 87 |
### embedding-logistic_sentence_embeddings at threshold 0.500
|
| 88 |
|
| 89 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 90 |
| --- | ---: | ---: |
|
| 91 |
+
| NOT_RELEVANT | 1745 | 212 |
|
| 92 |
+
| RELEVANT | 15 | 114 |
|
| 93 |
|
| 94 |
+
### embedding-logistic_sentence_embeddings at threshold 0.726
|
| 95 |
|
| 96 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 97 |
| --- | ---: | ---: |
|
| 98 |
+
| NOT_RELEVANT | 1848 | 109 |
|
| 99 |
+
| RELEVANT | 40 | 89 |
|
| 100 |
|
| 101 |
### embedding-svm_sentence_embeddings at threshold 0.500
|
| 102 |
|
| 103 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 104 |
| --- | ---: | ---: |
|
| 105 |
+
| NOT_RELEVANT | 1918 | 39 |
|
| 106 |
+
| RELEVANT | 69 | 60 |
|
| 107 |
|
| 108 |
+
### embedding-svm_sentence_embeddings at threshold 0.245
|
| 109 |
|
| 110 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 111 |
| --- | ---: | ---: |
|
| 112 |
+
| NOT_RELEVANT | 1868 | 89 |
|
| 113 |
+
| RELEVANT | 42 | 87 |
|
| 114 |
|
| 115 |
### embedding-lightgbm_sentence_embeddings at threshold 0.500
|
| 116 |
|
| 117 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 118 |
| --- | ---: | ---: |
|
| 119 |
+
| NOT_RELEVANT | 1901 | 56 |
|
| 120 |
+
| RELEVANT | 52 | 77 |
|
| 121 |
|
| 122 |
+
### embedding-lightgbm_sentence_embeddings at threshold 0.089
|
| 123 |
|
| 124 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 125 |
| --- | ---: | ---: |
|
| 126 |
+
| NOT_RELEVANT | 1845 | 112 |
|
| 127 |
+
| RELEVANT | 29 | 100 |
|
| 128 |
|
| 129 |
### transformer at threshold 0.500
|
| 130 |
|
| 131 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 132 |
| --- | ---: | ---: |
|
| 133 |
+
| NOT_RELEVANT | 1884 | 73 |
|
| 134 |
+
| RELEVANT | 46 | 83 |
|
| 135 |
|
| 136 |
+
### transformer at threshold 0.544
|
| 137 |
|
| 138 |
| True / Predicted | NOT_RELEVANT | RELEVANT |
|
| 139 |
| --- | ---: | ---: |
|
| 140 |
+
| NOT_RELEVANT | 1884 | 73 |
|
| 141 |
+
| RELEVANT | 47 | 82 |
|
| 142 |
|
| 143 |
|
| 144 |
## Validation-Tuned Thresholds
|
| 145 |
|
| 146 |
+
- `logistic_tfidf`: threshold `0.360` (validation F1 `0.489`); test F1 change vs 0.5: `-0.008`.
|
| 147 |
+
- `xgboost_tfidf`: threshold `0.104` (validation F1 `0.535`); test F1 change vs 0.5: `+0.016`.
|
| 148 |
+
- `embedding-logistic_sentence_embeddings`: threshold `0.726` (validation F1 `0.688`); test F1 change vs 0.5: `+0.043`.
|
| 149 |
+
- `embedding-svm_sentence_embeddings`: threshold `0.245` (validation F1 `0.700`); test F1 change vs 0.5: `+0.044`.
|
| 150 |
+
- `embedding-lightgbm_sentence_embeddings`: threshold `0.089` (validation F1 `0.701`); test F1 change vs 0.5: `-0.001`.
|
| 151 |
+
- `transformer`: threshold `0.544` (validation F1 `0.698`); test F1 change vs 0.5: `-0.005`.
|
| 152 |
|
| 153 |
## Artifacts
|
| 154 |
|
baselines/embedding-lightgbm/embedding-lightgbm.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef46feb03d6d86629446a2b84e3976aad0bbf58a95a4a53a9fd370bd0fd97a5b
|
| 3 |
+
size 1454606
|
baselines/embedding-lightgbm/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/embedding-lightgbm/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/embedding-logistic/embedding-logistic.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2368ac2c3c1cc353bb281993f87b11f6ea0b4a86abd8d935a9506f607933b1ae
|
| 3 |
+
size 2821
|
baselines/embedding-logistic/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/embedding-logistic/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/embedding-svm/embedding-svm.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d0d609b2c746c6481cb61c52f997a53e8962c60aceda441970bbaeffd07223e
|
| 3 |
size 11770
|
baselines/embedding-svm/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/embedding-svm/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/logistic/logistic_tfidf.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff51ca92cbba2cd25b3bd551d90fa24bbe8217cf6d701c493727b09df330af7
|
| 3 |
+
size 2430788
|
baselines/logistic/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/logistic/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/xgboost/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/xgboost/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baselines/xgboost/xgboost_tfidf.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4b2edd904d295c0f6e835bcff08adff1506e9ce985ac708d392ce1c8dd97b2a
|
| 3 |
+
size 2483313
|
report.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"created_at": "2026-
|
| 3 |
"config": {
|
| 4 |
"hf_dataset": "faodl/amis-agri-utilization",
|
| 5 |
"hf_subset": null,
|
| 6 |
-
"hf_revision": "
|
| 7 |
"train_split": "train",
|
| 8 |
"validation_split": "validation",
|
| 9 |
"test_split": "test",
|
|
@@ -44,33 +44,33 @@
|
|
| 44 |
},
|
| 45 |
"dataset_summary": {
|
| 46 |
"train": {
|
| 47 |
-
"rows":
|
| 48 |
"labels": {
|
| 49 |
-
"0":
|
| 50 |
-
"1":
|
| 51 |
},
|
| 52 |
-
"unique_groups":
|
| 53 |
-
"text_length_mean": 696.
|
| 54 |
"text_length_median": 794.0
|
| 55 |
},
|
| 56 |
"validation": {
|
| 57 |
-
"rows":
|
| 58 |
"labels": {
|
| 59 |
-
"0":
|
| 60 |
-
"1":
|
| 61 |
},
|
| 62 |
-
"unique_groups":
|
| 63 |
-
"text_length_mean":
|
| 64 |
"text_length_median": 794.0
|
| 65 |
},
|
| 66 |
"test": {
|
| 67 |
-
"rows":
|
| 68 |
"labels": {
|
| 69 |
-
"0":
|
| 70 |
-
"1":
|
| 71 |
},
|
| 72 |
-
"unique_groups":
|
| 73 |
-
"text_length_mean":
|
| 74 |
"text_length_median": 794.0
|
| 75 |
}
|
| 76 |
},
|
|
@@ -81,194 +81,194 @@
|
|
| 81 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/logistic",
|
| 82 |
"artifact_file": "/content/agri-utilization-classifier/baselines/logistic/logistic_tfidf.joblib",
|
| 83 |
"validation_best_threshold": {
|
| 84 |
-
"threshold": 0.
|
| 85 |
-
"f1": 0.
|
| 86 |
-
"precision": 0.
|
| 87 |
-
"recall": 0.
|
| 88 |
},
|
| 89 |
"validation_default_0_5": {
|
| 90 |
"threshold": 0.5,
|
| 91 |
-
"accuracy": 0.
|
| 92 |
-
"precision": 0.
|
| 93 |
-
"recall": 0.
|
| 94 |
-
"f1": 0.
|
| 95 |
"confusion_matrix": [
|
| 96 |
[
|
| 97 |
-
|
| 98 |
-
|
| 99 |
],
|
| 100 |
[
|
| 101 |
-
|
| 102 |
-
|
| 103 |
]
|
| 104 |
],
|
| 105 |
"classification_report": {
|
| 106 |
"NOT_RELEVANT": {
|
| 107 |
-
"precision": 0.
|
| 108 |
-
"recall": 0.
|
| 109 |
-
"f1-score": 0.
|
| 110 |
-
"support":
|
| 111 |
},
|
| 112 |
"RELEVANT": {
|
| 113 |
-
"precision": 0.
|
| 114 |
-
"recall": 0.
|
| 115 |
-
"f1-score": 0.
|
| 116 |
-
"support":
|
| 117 |
},
|
| 118 |
-
"accuracy": 0.
|
| 119 |
"macro avg": {
|
| 120 |
-
"precision": 0.
|
| 121 |
-
"recall": 0.
|
| 122 |
-
"f1-score": 0.
|
| 123 |
-
"support":
|
| 124 |
},
|
| 125 |
"weighted avg": {
|
| 126 |
-
"precision": 0.
|
| 127 |
-
"recall": 0.
|
| 128 |
-
"f1-score": 0.
|
| 129 |
-
"support":
|
| 130 |
}
|
| 131 |
},
|
| 132 |
-
"roc_auc": 0.
|
| 133 |
-
"average_precision": 0.
|
| 134 |
},
|
| 135 |
"validation_optimal_threshold": {
|
| 136 |
-
"threshold": 0.
|
| 137 |
-
"accuracy": 0.
|
| 138 |
-
"precision": 0.
|
| 139 |
-
"recall": 0.
|
| 140 |
-
"f1": 0.
|
| 141 |
"confusion_matrix": [
|
| 142 |
[
|
| 143 |
-
|
| 144 |
-
|
| 145 |
],
|
| 146 |
[
|
| 147 |
-
|
| 148 |
-
|
| 149 |
]
|
| 150 |
],
|
| 151 |
"classification_report": {
|
| 152 |
"NOT_RELEVANT": {
|
| 153 |
-
"precision": 0.
|
| 154 |
-
"recall": 0.
|
| 155 |
-
"f1-score": 0.
|
| 156 |
-
"support":
|
| 157 |
},
|
| 158 |
"RELEVANT": {
|
| 159 |
-
"precision": 0.
|
| 160 |
-
"recall": 0.
|
| 161 |
-
"f1-score": 0.
|
| 162 |
-
"support":
|
| 163 |
},
|
| 164 |
-
"accuracy": 0.
|
| 165 |
"macro avg": {
|
| 166 |
-
"precision": 0.
|
| 167 |
-
"recall": 0.
|
| 168 |
-
"f1-score": 0.
|
| 169 |
-
"support":
|
| 170 |
},
|
| 171 |
"weighted avg": {
|
| 172 |
-
"precision": 0.
|
| 173 |
-
"recall": 0.
|
| 174 |
-
"f1-score": 0.
|
| 175 |
-
"support":
|
| 176 |
}
|
| 177 |
},
|
| 178 |
-
"roc_auc": 0.
|
| 179 |
-
"average_precision": 0.
|
| 180 |
},
|
| 181 |
"test_default_0_5": {
|
| 182 |
"threshold": 0.5,
|
| 183 |
-
"accuracy": 0.
|
| 184 |
-
"precision": 0.
|
| 185 |
-
"recall": 0.
|
| 186 |
-
"f1": 0.
|
| 187 |
"confusion_matrix": [
|
| 188 |
[
|
| 189 |
-
|
| 190 |
-
|
| 191 |
],
|
| 192 |
[
|
| 193 |
-
|
| 194 |
-
|
| 195 |
]
|
| 196 |
],
|
| 197 |
"classification_report": {
|
| 198 |
"NOT_RELEVANT": {
|
| 199 |
-
"precision": 0.
|
| 200 |
-
"recall": 0.
|
| 201 |
-
"f1-score": 0.
|
| 202 |
-
"support":
|
| 203 |
},
|
| 204 |
"RELEVANT": {
|
| 205 |
-
"precision": 0.
|
| 206 |
-
"recall": 0.
|
| 207 |
-
"f1-score": 0.
|
| 208 |
-
"support":
|
| 209 |
},
|
| 210 |
-
"accuracy": 0.
|
| 211 |
"macro avg": {
|
| 212 |
-
"precision": 0.
|
| 213 |
-
"recall": 0.
|
| 214 |
-
"f1-score": 0.
|
| 215 |
-
"support":
|
| 216 |
},
|
| 217 |
"weighted avg": {
|
| 218 |
-
"precision": 0.
|
| 219 |
-
"recall": 0.
|
| 220 |
-
"f1-score": 0.
|
| 221 |
-
"support":
|
| 222 |
}
|
| 223 |
},
|
| 224 |
-
"roc_auc": 0.
|
| 225 |
-
"average_precision": 0.
|
| 226 |
},
|
| 227 |
"test_optimal_threshold": {
|
| 228 |
-
"threshold": 0.
|
| 229 |
-
"accuracy": 0.
|
| 230 |
-
"precision": 0.
|
| 231 |
-
"recall": 0.
|
| 232 |
-
"f1": 0.
|
| 233 |
"confusion_matrix": [
|
| 234 |
[
|
| 235 |
-
|
| 236 |
-
|
| 237 |
],
|
| 238 |
[
|
| 239 |
-
|
| 240 |
-
|
| 241 |
]
|
| 242 |
],
|
| 243 |
"classification_report": {
|
| 244 |
"NOT_RELEVANT": {
|
| 245 |
-
"precision": 0.
|
| 246 |
-
"recall": 0.
|
| 247 |
-
"f1-score": 0.
|
| 248 |
-
"support":
|
| 249 |
},
|
| 250 |
"RELEVANT": {
|
| 251 |
-
"precision": 0.
|
| 252 |
-
"recall": 0.
|
| 253 |
-
"f1-score": 0.
|
| 254 |
-
"support":
|
| 255 |
},
|
| 256 |
-
"accuracy": 0.
|
| 257 |
"macro avg": {
|
| 258 |
-
"precision": 0.
|
| 259 |
-
"recall": 0.
|
| 260 |
-
"f1-score": 0.
|
| 261 |
-
"support":
|
| 262 |
},
|
| 263 |
"weighted avg": {
|
| 264 |
-
"precision": 0.
|
| 265 |
-
"recall": 0.
|
| 266 |
-
"f1-score": 0.
|
| 267 |
-
"support":
|
| 268 |
}
|
| 269 |
},
|
| 270 |
-
"roc_auc": 0.
|
| 271 |
-
"average_precision": 0.
|
| 272 |
}
|
| 273 |
},
|
| 274 |
{
|
|
@@ -277,194 +277,194 @@
|
|
| 277 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/xgboost",
|
| 278 |
"artifact_file": "/content/agri-utilization-classifier/baselines/xgboost/xgboost_tfidf.joblib",
|
| 279 |
"validation_best_threshold": {
|
| 280 |
-
"threshold": 0.
|
| 281 |
-
"f1": 0.
|
| 282 |
-
"precision": 0.
|
| 283 |
-
"recall": 0.
|
| 284 |
},
|
| 285 |
"validation_default_0_5": {
|
| 286 |
"threshold": 0.5,
|
| 287 |
-
"accuracy": 0.
|
| 288 |
-
"precision": 0.
|
| 289 |
-
"recall": 0.
|
| 290 |
-
"f1": 0.
|
| 291 |
"confusion_matrix": [
|
| 292 |
[
|
| 293 |
-
|
| 294 |
-
|
| 295 |
],
|
| 296 |
[
|
| 297 |
-
|
| 298 |
-
|
| 299 |
]
|
| 300 |
],
|
| 301 |
"classification_report": {
|
| 302 |
"NOT_RELEVANT": {
|
| 303 |
-
"precision": 0.
|
| 304 |
-
"recall": 0.
|
| 305 |
-
"f1-score": 0.
|
| 306 |
-
"support":
|
| 307 |
},
|
| 308 |
"RELEVANT": {
|
| 309 |
-
"precision": 0.
|
| 310 |
-
"recall": 0.
|
| 311 |
-
"f1-score": 0.
|
| 312 |
-
"support":
|
| 313 |
},
|
| 314 |
-
"accuracy": 0.
|
| 315 |
"macro avg": {
|
| 316 |
-
"precision": 0.
|
| 317 |
-
"recall": 0.
|
| 318 |
-
"f1-score": 0.
|
| 319 |
-
"support":
|
| 320 |
},
|
| 321 |
"weighted avg": {
|
| 322 |
-
"precision": 0.
|
| 323 |
-
"recall": 0.
|
| 324 |
-
"f1-score": 0.
|
| 325 |
-
"support":
|
| 326 |
}
|
| 327 |
},
|
| 328 |
-
"roc_auc": 0.
|
| 329 |
-
"average_precision": 0.
|
| 330 |
},
|
| 331 |
"validation_optimal_threshold": {
|
| 332 |
-
"threshold": 0.
|
| 333 |
-
"accuracy": 0.
|
| 334 |
-
"precision": 0.
|
| 335 |
-
"recall": 0.
|
| 336 |
-
"f1": 0.
|
| 337 |
"confusion_matrix": [
|
| 338 |
[
|
| 339 |
-
|
| 340 |
-
|
| 341 |
],
|
| 342 |
[
|
| 343 |
-
|
| 344 |
-
|
| 345 |
]
|
| 346 |
],
|
| 347 |
"classification_report": {
|
| 348 |
"NOT_RELEVANT": {
|
| 349 |
-
"precision": 0.
|
| 350 |
-
"recall": 0.
|
| 351 |
-
"f1-score": 0.
|
| 352 |
-
"support":
|
| 353 |
},
|
| 354 |
"RELEVANT": {
|
| 355 |
-
"precision": 0.
|
| 356 |
-
"recall": 0.
|
| 357 |
-
"f1-score": 0.
|
| 358 |
-
"support":
|
| 359 |
},
|
| 360 |
-
"accuracy": 0.
|
| 361 |
"macro avg": {
|
| 362 |
-
"precision": 0.
|
| 363 |
-
"recall": 0.
|
| 364 |
-
"f1-score": 0.
|
| 365 |
-
"support":
|
| 366 |
},
|
| 367 |
"weighted avg": {
|
| 368 |
-
"precision": 0.
|
| 369 |
-
"recall": 0.
|
| 370 |
-
"f1-score": 0.
|
| 371 |
-
"support":
|
| 372 |
}
|
| 373 |
},
|
| 374 |
-
"roc_auc": 0.
|
| 375 |
-
"average_precision": 0.
|
| 376 |
},
|
| 377 |
"test_default_0_5": {
|
| 378 |
"threshold": 0.5,
|
| 379 |
-
"accuracy": 0.
|
| 380 |
-
"precision":
|
| 381 |
-
"recall": 0.
|
| 382 |
-
"f1": 0.
|
| 383 |
"confusion_matrix": [
|
| 384 |
[
|
| 385 |
-
|
| 386 |
-
|
| 387 |
],
|
| 388 |
[
|
| 389 |
-
|
| 390 |
-
|
| 391 |
]
|
| 392 |
],
|
| 393 |
"classification_report": {
|
| 394 |
"NOT_RELEVANT": {
|
| 395 |
-
"precision": 0.
|
| 396 |
-
"recall":
|
| 397 |
-
"f1-score": 0.
|
| 398 |
-
"support":
|
| 399 |
},
|
| 400 |
"RELEVANT": {
|
| 401 |
-
"precision":
|
| 402 |
-
"recall": 0.
|
| 403 |
-
"f1-score": 0.
|
| 404 |
-
"support":
|
| 405 |
},
|
| 406 |
-
"accuracy": 0.
|
| 407 |
"macro avg": {
|
| 408 |
-
"precision": 0.
|
| 409 |
-
"recall": 0.
|
| 410 |
-
"f1-score": 0.
|
| 411 |
-
"support":
|
| 412 |
},
|
| 413 |
"weighted avg": {
|
| 414 |
-
"precision": 0.
|
| 415 |
-
"recall": 0.
|
| 416 |
-
"f1-score": 0.
|
| 417 |
-
"support":
|
| 418 |
}
|
| 419 |
},
|
| 420 |
-
"roc_auc": 0.
|
| 421 |
-
"average_precision": 0.
|
| 422 |
},
|
| 423 |
"test_optimal_threshold": {
|
| 424 |
-
"threshold": 0.
|
| 425 |
-
"accuracy": 0.
|
| 426 |
-
"precision": 0.
|
| 427 |
-
"recall": 0.
|
| 428 |
-
"f1": 0.
|
| 429 |
"confusion_matrix": [
|
| 430 |
[
|
| 431 |
-
|
| 432 |
-
|
| 433 |
],
|
| 434 |
[
|
| 435 |
-
|
| 436 |
-
|
| 437 |
]
|
| 438 |
],
|
| 439 |
"classification_report": {
|
| 440 |
"NOT_RELEVANT": {
|
| 441 |
-
"precision": 0.
|
| 442 |
-
"recall": 0.
|
| 443 |
-
"f1-score": 0.
|
| 444 |
-
"support":
|
| 445 |
},
|
| 446 |
"RELEVANT": {
|
| 447 |
-
"precision": 0.
|
| 448 |
-
"recall": 0.
|
| 449 |
-
"f1-score": 0.
|
| 450 |
-
"support":
|
| 451 |
},
|
| 452 |
-
"accuracy": 0.
|
| 453 |
"macro avg": {
|
| 454 |
-
"precision": 0.
|
| 455 |
-
"recall": 0.
|
| 456 |
-
"f1-score": 0.
|
| 457 |
-
"support":
|
| 458 |
},
|
| 459 |
"weighted avg": {
|
| 460 |
-
"precision": 0.
|
| 461 |
-
"recall": 0.
|
| 462 |
-
"f1-score": 0.
|
| 463 |
-
"support":
|
| 464 |
}
|
| 465 |
},
|
| 466 |
-
"roc_auc": 0.
|
| 467 |
-
"average_precision": 0.
|
| 468 |
}
|
| 469 |
},
|
| 470 |
{
|
|
@@ -474,194 +474,194 @@
|
|
| 474 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-logistic",
|
| 475 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-logistic/embedding-logistic.joblib",
|
| 476 |
"validation_best_threshold": {
|
| 477 |
-
"threshold": 0.
|
| 478 |
-
"f1": 0.
|
| 479 |
-
"precision": 0.
|
| 480 |
-
"recall": 0.
|
| 481 |
},
|
| 482 |
"validation_default_0_5": {
|
| 483 |
"threshold": 0.5,
|
| 484 |
-
"accuracy": 0.
|
| 485 |
-
"precision": 0.
|
| 486 |
-
"recall": 0.
|
| 487 |
-
"f1": 0.
|
| 488 |
"confusion_matrix": [
|
| 489 |
[
|
| 490 |
-
|
| 491 |
-
|
| 492 |
],
|
| 493 |
[
|
| 494 |
-
|
| 495 |
-
|
| 496 |
]
|
| 497 |
],
|
| 498 |
"classification_report": {
|
| 499 |
"NOT_RELEVANT": {
|
| 500 |
-
"precision": 0.
|
| 501 |
-
"recall": 0.
|
| 502 |
-
"f1-score": 0.
|
| 503 |
-
"support":
|
| 504 |
},
|
| 505 |
"RELEVANT": {
|
| 506 |
-
"precision": 0.
|
| 507 |
-
"recall": 0.
|
| 508 |
-
"f1-score": 0.
|
| 509 |
-
"support":
|
| 510 |
},
|
| 511 |
-
"accuracy": 0.
|
| 512 |
"macro avg": {
|
| 513 |
-
"precision": 0.
|
| 514 |
-
"recall": 0.
|
| 515 |
-
"f1-score": 0.
|
| 516 |
-
"support":
|
| 517 |
},
|
| 518 |
"weighted avg": {
|
| 519 |
-
"precision": 0.
|
| 520 |
-
"recall": 0.
|
| 521 |
-
"f1-score": 0.
|
| 522 |
-
"support":
|
| 523 |
}
|
| 524 |
},
|
| 525 |
-
"roc_auc": 0.
|
| 526 |
-
"average_precision": 0.
|
| 527 |
},
|
| 528 |
"validation_optimal_threshold": {
|
| 529 |
-
"threshold": 0.
|
| 530 |
-
"accuracy": 0.
|
| 531 |
-
"precision": 0.
|
| 532 |
-
"recall": 0.
|
| 533 |
-
"f1": 0.
|
| 534 |
"confusion_matrix": [
|
| 535 |
[
|
| 536 |
-
|
| 537 |
-
|
| 538 |
],
|
| 539 |
[
|
| 540 |
-
|
| 541 |
-
|
| 542 |
]
|
| 543 |
],
|
| 544 |
"classification_report": {
|
| 545 |
"NOT_RELEVANT": {
|
| 546 |
-
"precision": 0.
|
| 547 |
-
"recall": 0.
|
| 548 |
-
"f1-score": 0.
|
| 549 |
-
"support":
|
| 550 |
},
|
| 551 |
"RELEVANT": {
|
| 552 |
-
"precision": 0.
|
| 553 |
-
"recall": 0.
|
| 554 |
-
"f1-score": 0.
|
| 555 |
-
"support":
|
| 556 |
},
|
| 557 |
-
"accuracy": 0.
|
| 558 |
"macro avg": {
|
| 559 |
-
"precision": 0.
|
| 560 |
-
"recall": 0.
|
| 561 |
-
"f1-score": 0.
|
| 562 |
-
"support":
|
| 563 |
},
|
| 564 |
"weighted avg": {
|
| 565 |
-
"precision": 0.
|
| 566 |
-
"recall": 0.
|
| 567 |
-
"f1-score": 0.
|
| 568 |
-
"support":
|
| 569 |
}
|
| 570 |
},
|
| 571 |
-
"roc_auc": 0.
|
| 572 |
-
"average_precision": 0.
|
| 573 |
},
|
| 574 |
"test_default_0_5": {
|
| 575 |
"threshold": 0.5,
|
| 576 |
-
"accuracy": 0.
|
| 577 |
-
"precision": 0.
|
| 578 |
-
"recall": 0.
|
| 579 |
-
"f1": 0.
|
| 580 |
"confusion_matrix": [
|
| 581 |
[
|
| 582 |
-
|
| 583 |
-
|
| 584 |
],
|
| 585 |
[
|
| 586 |
-
|
| 587 |
-
|
| 588 |
]
|
| 589 |
],
|
| 590 |
"classification_report": {
|
| 591 |
"NOT_RELEVANT": {
|
| 592 |
-
"precision": 0.
|
| 593 |
-
"recall": 0.
|
| 594 |
-
"f1-score": 0.
|
| 595 |
-
"support":
|
| 596 |
},
|
| 597 |
"RELEVANT": {
|
| 598 |
-
"precision": 0.
|
| 599 |
-
"recall": 0.
|
| 600 |
-
"f1-score": 0.
|
| 601 |
-
"support":
|
| 602 |
},
|
| 603 |
-
"accuracy": 0.
|
| 604 |
"macro avg": {
|
| 605 |
-
"precision": 0.
|
| 606 |
-
"recall": 0.
|
| 607 |
-
"f1-score": 0.
|
| 608 |
-
"support":
|
| 609 |
},
|
| 610 |
"weighted avg": {
|
| 611 |
-
"precision": 0.
|
| 612 |
-
"recall": 0.
|
| 613 |
-
"f1-score": 0.
|
| 614 |
-
"support":
|
| 615 |
}
|
| 616 |
},
|
| 617 |
-
"roc_auc": 0.
|
| 618 |
-
"average_precision": 0.
|
| 619 |
},
|
| 620 |
"test_optimal_threshold": {
|
| 621 |
-
"threshold": 0.
|
| 622 |
-
"accuracy": 0.
|
| 623 |
-
"precision": 0.
|
| 624 |
-
"recall": 0.
|
| 625 |
-
"f1": 0.
|
| 626 |
"confusion_matrix": [
|
| 627 |
[
|
| 628 |
-
|
| 629 |
-
|
| 630 |
],
|
| 631 |
[
|
| 632 |
-
|
| 633 |
-
|
| 634 |
]
|
| 635 |
],
|
| 636 |
"classification_report": {
|
| 637 |
"NOT_RELEVANT": {
|
| 638 |
-
"precision": 0.
|
| 639 |
-
"recall": 0.
|
| 640 |
-
"f1-score": 0.
|
| 641 |
-
"support":
|
| 642 |
},
|
| 643 |
"RELEVANT": {
|
| 644 |
-
"precision": 0.
|
| 645 |
-
"recall": 0.
|
| 646 |
-
"f1-score": 0.
|
| 647 |
-
"support":
|
| 648 |
},
|
| 649 |
-
"accuracy": 0.
|
| 650 |
"macro avg": {
|
| 651 |
-
"precision": 0.
|
| 652 |
-
"recall": 0.
|
| 653 |
-
"f1-score": 0.
|
| 654 |
-
"support":
|
| 655 |
},
|
| 656 |
"weighted avg": {
|
| 657 |
-
"precision": 0.
|
| 658 |
-
"recall": 0.
|
| 659 |
-
"f1-score": 0.
|
| 660 |
-
"support":
|
| 661 |
}
|
| 662 |
},
|
| 663 |
-
"roc_auc": 0.
|
| 664 |
-
"average_precision": 0.
|
| 665 |
}
|
| 666 |
},
|
| 667 |
{
|
|
@@ -671,194 +671,194 @@
|
|
| 671 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-svm",
|
| 672 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-svm/embedding-svm.joblib",
|
| 673 |
"validation_best_threshold": {
|
| 674 |
-
"threshold": 0.
|
| 675 |
-
"f1": 0.
|
| 676 |
-
"precision": 0.
|
| 677 |
-
"recall": 0.
|
| 678 |
},
|
| 679 |
"validation_default_0_5": {
|
| 680 |
"threshold": 0.5,
|
| 681 |
-
"accuracy": 0.
|
| 682 |
-
"precision": 0.
|
| 683 |
-
"recall": 0.
|
| 684 |
-
"f1": 0.
|
| 685 |
"confusion_matrix": [
|
| 686 |
[
|
| 687 |
-
|
| 688 |
-
|
| 689 |
],
|
| 690 |
[
|
| 691 |
-
|
| 692 |
-
|
| 693 |
]
|
| 694 |
],
|
| 695 |
"classification_report": {
|
| 696 |
"NOT_RELEVANT": {
|
| 697 |
-
"precision": 0.
|
| 698 |
-
"recall": 0.
|
| 699 |
-
"f1-score": 0.
|
| 700 |
-
"support":
|
| 701 |
},
|
| 702 |
"RELEVANT": {
|
| 703 |
-
"precision": 0.
|
| 704 |
-
"recall": 0.
|
| 705 |
-
"f1-score": 0.
|
| 706 |
-
"support":
|
| 707 |
},
|
| 708 |
-
"accuracy": 0.
|
| 709 |
"macro avg": {
|
| 710 |
-
"precision": 0.
|
| 711 |
-
"recall": 0.
|
| 712 |
-
"f1-score": 0.
|
| 713 |
-
"support":
|
| 714 |
},
|
| 715 |
"weighted avg": {
|
| 716 |
-
"precision": 0.
|
| 717 |
-
"recall": 0.
|
| 718 |
-
"f1-score": 0.
|
| 719 |
-
"support":
|
| 720 |
}
|
| 721 |
},
|
| 722 |
-
"roc_auc": 0.
|
| 723 |
-
"average_precision": 0.
|
| 724 |
},
|
| 725 |
"validation_optimal_threshold": {
|
| 726 |
-
"threshold": 0.
|
| 727 |
-
"accuracy": 0.
|
| 728 |
-
"precision": 0.
|
| 729 |
-
"recall": 0.
|
| 730 |
-
"f1": 0.
|
| 731 |
"confusion_matrix": [
|
| 732 |
[
|
| 733 |
-
|
| 734 |
-
|
| 735 |
],
|
| 736 |
[
|
| 737 |
-
|
| 738 |
-
|
| 739 |
]
|
| 740 |
],
|
| 741 |
"classification_report": {
|
| 742 |
"NOT_RELEVANT": {
|
| 743 |
-
"precision": 0.
|
| 744 |
-
"recall": 0.
|
| 745 |
-
"f1-score": 0.
|
| 746 |
-
"support":
|
| 747 |
},
|
| 748 |
"RELEVANT": {
|
| 749 |
-
"precision": 0.
|
| 750 |
-
"recall": 0.
|
| 751 |
-
"f1-score": 0.
|
| 752 |
-
"support":
|
| 753 |
},
|
| 754 |
-
"accuracy": 0.
|
| 755 |
"macro avg": {
|
| 756 |
-
"precision": 0.
|
| 757 |
-
"recall": 0.
|
| 758 |
-
"f1-score": 0.
|
| 759 |
-
"support":
|
| 760 |
},
|
| 761 |
"weighted avg": {
|
| 762 |
-
"precision": 0.
|
| 763 |
-
"recall": 0.
|
| 764 |
-
"f1-score": 0.
|
| 765 |
-
"support":
|
| 766 |
}
|
| 767 |
},
|
| 768 |
-
"roc_auc": 0.
|
| 769 |
-
"average_precision": 0.
|
| 770 |
},
|
| 771 |
"test_default_0_5": {
|
| 772 |
"threshold": 0.5,
|
| 773 |
-
"accuracy": 0.
|
| 774 |
-
"precision": 0.
|
| 775 |
-
"recall": 0.
|
| 776 |
-
"f1": 0.
|
| 777 |
"confusion_matrix": [
|
| 778 |
[
|
| 779 |
-
|
| 780 |
-
|
| 781 |
],
|
| 782 |
[
|
| 783 |
-
|
| 784 |
-
|
| 785 |
]
|
| 786 |
],
|
| 787 |
"classification_report": {
|
| 788 |
"NOT_RELEVANT": {
|
| 789 |
-
"precision": 0.
|
| 790 |
-
"recall": 0.
|
| 791 |
-
"f1-score": 0.
|
| 792 |
-
"support":
|
| 793 |
},
|
| 794 |
"RELEVANT": {
|
| 795 |
-
"precision": 0.
|
| 796 |
-
"recall": 0.
|
| 797 |
-
"f1-score": 0.
|
| 798 |
-
"support":
|
| 799 |
},
|
| 800 |
-
"accuracy": 0.
|
| 801 |
"macro avg": {
|
| 802 |
-
"precision": 0.
|
| 803 |
-
"recall": 0.
|
| 804 |
-
"f1-score": 0.
|
| 805 |
-
"support":
|
| 806 |
},
|
| 807 |
"weighted avg": {
|
| 808 |
-
"precision": 0.
|
| 809 |
-
"recall": 0.
|
| 810 |
-
"f1-score": 0.
|
| 811 |
-
"support":
|
| 812 |
}
|
| 813 |
},
|
| 814 |
-
"roc_auc": 0.
|
| 815 |
-
"average_precision": 0.
|
| 816 |
},
|
| 817 |
"test_optimal_threshold": {
|
| 818 |
-
"threshold": 0.
|
| 819 |
-
"accuracy": 0.
|
| 820 |
-
"precision": 0.
|
| 821 |
-
"recall": 0.
|
| 822 |
-
"f1": 0.
|
| 823 |
"confusion_matrix": [
|
| 824 |
[
|
| 825 |
-
|
| 826 |
-
|
| 827 |
],
|
| 828 |
[
|
| 829 |
-
|
| 830 |
-
|
| 831 |
]
|
| 832 |
],
|
| 833 |
"classification_report": {
|
| 834 |
"NOT_RELEVANT": {
|
| 835 |
-
"precision": 0.
|
| 836 |
-
"recall": 0.
|
| 837 |
-
"f1-score": 0.
|
| 838 |
-
"support":
|
| 839 |
},
|
| 840 |
"RELEVANT": {
|
| 841 |
-
"precision": 0.
|
| 842 |
-
"recall": 0.
|
| 843 |
-
"f1-score": 0.
|
| 844 |
-
"support":
|
| 845 |
},
|
| 846 |
-
"accuracy": 0.
|
| 847 |
"macro avg": {
|
| 848 |
-
"precision": 0.
|
| 849 |
-
"recall": 0.
|
| 850 |
-
"f1-score": 0.
|
| 851 |
-
"support":
|
| 852 |
},
|
| 853 |
"weighted avg": {
|
| 854 |
-
"precision": 0.
|
| 855 |
-
"recall": 0.
|
| 856 |
-
"f1-score": 0.
|
| 857 |
-
"support":
|
| 858 |
}
|
| 859 |
},
|
| 860 |
-
"roc_auc": 0.
|
| 861 |
-
"average_precision": 0.
|
| 862 |
}
|
| 863 |
},
|
| 864 |
{
|
|
@@ -868,194 +868,194 @@
|
|
| 868 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-lightgbm",
|
| 869 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-lightgbm/embedding-lightgbm.joblib",
|
| 870 |
"validation_best_threshold": {
|
| 871 |
-
"threshold": 0.
|
| 872 |
-
"f1": 0.
|
| 873 |
-
"precision": 0.
|
| 874 |
-
"recall": 0.
|
| 875 |
},
|
| 876 |
"validation_default_0_5": {
|
| 877 |
"threshold": 0.5,
|
| 878 |
-
"accuracy": 0.
|
| 879 |
-
"precision": 0.
|
| 880 |
-
"recall": 0.
|
| 881 |
-
"f1": 0.
|
| 882 |
"confusion_matrix": [
|
| 883 |
[
|
| 884 |
-
|
| 885 |
-
|
| 886 |
],
|
| 887 |
[
|
| 888 |
-
|
| 889 |
-
|
| 890 |
]
|
| 891 |
],
|
| 892 |
"classification_report": {
|
| 893 |
"NOT_RELEVANT": {
|
| 894 |
-
"precision": 0.
|
| 895 |
-
"recall": 0.
|
| 896 |
-
"f1-score": 0.
|
| 897 |
-
"support":
|
| 898 |
},
|
| 899 |
"RELEVANT": {
|
| 900 |
-
"precision": 0.
|
| 901 |
-
"recall": 0.
|
| 902 |
-
"f1-score": 0.
|
| 903 |
-
"support":
|
| 904 |
},
|
| 905 |
-
"accuracy": 0.
|
| 906 |
"macro avg": {
|
| 907 |
-
"precision": 0.
|
| 908 |
-
"recall": 0.
|
| 909 |
-
"f1-score": 0.
|
| 910 |
-
"support":
|
| 911 |
},
|
| 912 |
"weighted avg": {
|
| 913 |
-
"precision": 0.
|
| 914 |
-
"recall": 0.
|
| 915 |
-
"f1-score": 0.
|
| 916 |
-
"support":
|
| 917 |
}
|
| 918 |
},
|
| 919 |
-
"roc_auc": 0.
|
| 920 |
-
"average_precision": 0.
|
| 921 |
},
|
| 922 |
"validation_optimal_threshold": {
|
| 923 |
-
"threshold": 0.
|
| 924 |
-
"accuracy": 0.
|
| 925 |
-
"precision": 0.
|
| 926 |
-
"recall": 0.
|
| 927 |
-
"f1": 0.
|
| 928 |
"confusion_matrix": [
|
| 929 |
[
|
| 930 |
-
|
| 931 |
-
|
| 932 |
],
|
| 933 |
[
|
| 934 |
-
|
| 935 |
-
|
| 936 |
]
|
| 937 |
],
|
| 938 |
"classification_report": {
|
| 939 |
"NOT_RELEVANT": {
|
| 940 |
-
"precision": 0.
|
| 941 |
-
"recall": 0.
|
| 942 |
-
"f1-score": 0.
|
| 943 |
-
"support":
|
| 944 |
},
|
| 945 |
"RELEVANT": {
|
| 946 |
-
"precision": 0.
|
| 947 |
-
"recall": 0.
|
| 948 |
-
"f1-score": 0.
|
| 949 |
-
"support":
|
| 950 |
},
|
| 951 |
-
"accuracy": 0.
|
| 952 |
"macro avg": {
|
| 953 |
-
"precision": 0.
|
| 954 |
-
"recall": 0.
|
| 955 |
-
"f1-score": 0.
|
| 956 |
-
"support":
|
| 957 |
},
|
| 958 |
"weighted avg": {
|
| 959 |
-
"precision": 0.
|
| 960 |
-
"recall": 0.
|
| 961 |
-
"f1-score": 0.
|
| 962 |
-
"support":
|
| 963 |
}
|
| 964 |
},
|
| 965 |
-
"roc_auc": 0.
|
| 966 |
-
"average_precision": 0.
|
| 967 |
},
|
| 968 |
"test_default_0_5": {
|
| 969 |
"threshold": 0.5,
|
| 970 |
-
"accuracy": 0.
|
| 971 |
-
"precision": 0.
|
| 972 |
-
"recall": 0.
|
| 973 |
-
"f1": 0.
|
| 974 |
"confusion_matrix": [
|
| 975 |
[
|
| 976 |
-
|
| 977 |
-
|
| 978 |
],
|
| 979 |
[
|
| 980 |
-
|
| 981 |
-
|
| 982 |
]
|
| 983 |
],
|
| 984 |
"classification_report": {
|
| 985 |
"NOT_RELEVANT": {
|
| 986 |
-
"precision": 0.
|
| 987 |
-
"recall": 0.
|
| 988 |
-
"f1-score": 0.
|
| 989 |
-
"support":
|
| 990 |
},
|
| 991 |
"RELEVANT": {
|
| 992 |
-
"precision": 0.
|
| 993 |
-
"recall": 0.
|
| 994 |
-
"f1-score": 0.
|
| 995 |
-
"support":
|
| 996 |
},
|
| 997 |
-
"accuracy": 0.
|
| 998 |
"macro avg": {
|
| 999 |
-
"precision": 0.
|
| 1000 |
-
"recall": 0.
|
| 1001 |
-
"f1-score": 0.
|
| 1002 |
-
"support":
|
| 1003 |
},
|
| 1004 |
"weighted avg": {
|
| 1005 |
-
"precision": 0.
|
| 1006 |
-
"recall": 0.
|
| 1007 |
-
"f1-score": 0.
|
| 1008 |
-
"support":
|
| 1009 |
}
|
| 1010 |
},
|
| 1011 |
-
"roc_auc": 0.
|
| 1012 |
-
"average_precision": 0.
|
| 1013 |
},
|
| 1014 |
"test_optimal_threshold": {
|
| 1015 |
-
"threshold": 0.
|
| 1016 |
-
"accuracy": 0.
|
| 1017 |
-
"precision": 0.
|
| 1018 |
-
"recall": 0.
|
| 1019 |
-
"f1": 0.
|
| 1020 |
"confusion_matrix": [
|
| 1021 |
[
|
| 1022 |
-
|
| 1023 |
-
|
| 1024 |
],
|
| 1025 |
[
|
| 1026 |
-
|
| 1027 |
-
|
| 1028 |
]
|
| 1029 |
],
|
| 1030 |
"classification_report": {
|
| 1031 |
"NOT_RELEVANT": {
|
| 1032 |
-
"precision": 0.
|
| 1033 |
-
"recall": 0.
|
| 1034 |
-
"f1-score": 0.
|
| 1035 |
-
"support":
|
| 1036 |
},
|
| 1037 |
"RELEVANT": {
|
| 1038 |
-
"precision": 0.
|
| 1039 |
-
"recall": 0.
|
| 1040 |
-
"f1-score": 0.
|
| 1041 |
-
"support":
|
| 1042 |
},
|
| 1043 |
-
"accuracy": 0.
|
| 1044 |
"macro avg": {
|
| 1045 |
-
"precision": 0.
|
| 1046 |
-
"recall": 0.
|
| 1047 |
-
"f1-score": 0.
|
| 1048 |
-
"support":
|
| 1049 |
},
|
| 1050 |
"weighted avg": {
|
| 1051 |
-
"precision": 0.
|
| 1052 |
-
"recall": 0.
|
| 1053 |
-
"f1-score": 0.
|
| 1054 |
-
"support":
|
| 1055 |
}
|
| 1056 |
},
|
| 1057 |
-
"roc_auc": 0.
|
| 1058 |
-
"average_precision": 0.
|
| 1059 |
}
|
| 1060 |
},
|
| 1061 |
{
|
|
@@ -1063,194 +1063,194 @@
|
|
| 1063 |
"model_name": "FacebookAI/xlm-roberta-base",
|
| 1064 |
"artifact_dir": "/content/agri-utilization-classifier/transformer",
|
| 1065 |
"validation_best_threshold": {
|
| 1066 |
-
"threshold": 0.
|
| 1067 |
-
"f1": 0.
|
| 1068 |
-
"precision": 0.
|
| 1069 |
-
"recall": 0.
|
| 1070 |
},
|
| 1071 |
"validation_default_0_5": {
|
| 1072 |
"threshold": 0.5,
|
| 1073 |
-
"accuracy": 0.
|
| 1074 |
-
"precision": 0.
|
| 1075 |
-
"recall": 0.
|
| 1076 |
-
"f1": 0.
|
| 1077 |
"confusion_matrix": [
|
| 1078 |
[
|
| 1079 |
-
|
| 1080 |
-
|
| 1081 |
],
|
| 1082 |
[
|
| 1083 |
-
|
| 1084 |
-
|
| 1085 |
]
|
| 1086 |
],
|
| 1087 |
"classification_report": {
|
| 1088 |
"NOT_RELEVANT": {
|
| 1089 |
-
"precision": 0.
|
| 1090 |
-
"recall": 0.
|
| 1091 |
-
"f1-score": 0.
|
| 1092 |
-
"support":
|
| 1093 |
},
|
| 1094 |
"RELEVANT": {
|
| 1095 |
-
"precision": 0.
|
| 1096 |
-
"recall": 0.
|
| 1097 |
-
"f1-score": 0.
|
| 1098 |
-
"support":
|
| 1099 |
},
|
| 1100 |
-
"accuracy": 0.
|
| 1101 |
"macro avg": {
|
| 1102 |
-
"precision": 0.
|
| 1103 |
-
"recall": 0.
|
| 1104 |
-
"f1-score": 0.
|
| 1105 |
-
"support":
|
| 1106 |
},
|
| 1107 |
"weighted avg": {
|
| 1108 |
-
"precision": 0.
|
| 1109 |
-
"recall": 0.
|
| 1110 |
-
"f1-score": 0.
|
| 1111 |
-
"support":
|
| 1112 |
}
|
| 1113 |
},
|
| 1114 |
-
"roc_auc": 0.
|
| 1115 |
-
"average_precision": 0.
|
| 1116 |
},
|
| 1117 |
"validation_optimal_threshold": {
|
| 1118 |
-
"threshold": 0.
|
| 1119 |
-
"accuracy": 0.
|
| 1120 |
-
"precision": 0.
|
| 1121 |
-
"recall": 0.
|
| 1122 |
-
"f1": 0.
|
| 1123 |
"confusion_matrix": [
|
| 1124 |
[
|
| 1125 |
-
|
| 1126 |
-
|
| 1127 |
],
|
| 1128 |
[
|
| 1129 |
-
|
| 1130 |
-
|
| 1131 |
]
|
| 1132 |
],
|
| 1133 |
"classification_report": {
|
| 1134 |
"NOT_RELEVANT": {
|
| 1135 |
-
"precision": 0.
|
| 1136 |
-
"recall": 0.
|
| 1137 |
-
"f1-score": 0.
|
| 1138 |
-
"support":
|
| 1139 |
},
|
| 1140 |
"RELEVANT": {
|
| 1141 |
-
"precision": 0.
|
| 1142 |
-
"recall": 0.
|
| 1143 |
-
"f1-score": 0.
|
| 1144 |
-
"support":
|
| 1145 |
},
|
| 1146 |
-
"accuracy": 0.
|
| 1147 |
"macro avg": {
|
| 1148 |
-
"precision": 0.
|
| 1149 |
-
"recall": 0.
|
| 1150 |
-
"f1-score": 0.
|
| 1151 |
-
"support":
|
| 1152 |
},
|
| 1153 |
"weighted avg": {
|
| 1154 |
-
"precision": 0.
|
| 1155 |
-
"recall": 0.
|
| 1156 |
-
"f1-score": 0.
|
| 1157 |
-
"support":
|
| 1158 |
}
|
| 1159 |
},
|
| 1160 |
-
"roc_auc": 0.
|
| 1161 |
-
"average_precision": 0.
|
| 1162 |
},
|
| 1163 |
"test_default_0_5": {
|
| 1164 |
"threshold": 0.5,
|
| 1165 |
-
"accuracy": 0.
|
| 1166 |
-
"precision": 0.
|
| 1167 |
-
"recall": 0.
|
| 1168 |
-
"f1": 0.
|
| 1169 |
"confusion_matrix": [
|
| 1170 |
[
|
| 1171 |
-
|
| 1172 |
-
|
| 1173 |
],
|
| 1174 |
[
|
| 1175 |
-
|
| 1176 |
-
|
| 1177 |
]
|
| 1178 |
],
|
| 1179 |
"classification_report": {
|
| 1180 |
"NOT_RELEVANT": {
|
| 1181 |
-
"precision": 0.
|
| 1182 |
-
"recall": 0.
|
| 1183 |
-
"f1-score": 0.
|
| 1184 |
-
"support":
|
| 1185 |
},
|
| 1186 |
"RELEVANT": {
|
| 1187 |
-
"precision": 0.
|
| 1188 |
-
"recall": 0.
|
| 1189 |
-
"f1-score": 0.
|
| 1190 |
-
"support":
|
| 1191 |
},
|
| 1192 |
-
"accuracy": 0.
|
| 1193 |
"macro avg": {
|
| 1194 |
-
"precision": 0.
|
| 1195 |
-
"recall": 0.
|
| 1196 |
-
"f1-score": 0.
|
| 1197 |
-
"support":
|
| 1198 |
},
|
| 1199 |
"weighted avg": {
|
| 1200 |
-
"precision": 0.
|
| 1201 |
-
"recall": 0.
|
| 1202 |
-
"f1-score": 0.
|
| 1203 |
-
"support":
|
| 1204 |
}
|
| 1205 |
},
|
| 1206 |
-
"roc_auc": 0.
|
| 1207 |
-
"average_precision": 0.
|
| 1208 |
},
|
| 1209 |
"test_optimal_threshold": {
|
| 1210 |
-
"threshold": 0.
|
| 1211 |
-
"accuracy": 0.
|
| 1212 |
-
"precision": 0.
|
| 1213 |
-
"recall": 0.
|
| 1214 |
-
"f1": 0.
|
| 1215 |
"confusion_matrix": [
|
| 1216 |
[
|
| 1217 |
-
|
| 1218 |
-
|
| 1219 |
],
|
| 1220 |
[
|
| 1221 |
-
|
| 1222 |
-
|
| 1223 |
]
|
| 1224 |
],
|
| 1225 |
"classification_report": {
|
| 1226 |
"NOT_RELEVANT": {
|
| 1227 |
-
"precision": 0.
|
| 1228 |
-
"recall": 0.
|
| 1229 |
-
"f1-score": 0.
|
| 1230 |
-
"support":
|
| 1231 |
},
|
| 1232 |
"RELEVANT": {
|
| 1233 |
-
"precision": 0.
|
| 1234 |
-
"recall": 0.
|
| 1235 |
-
"f1-score": 0.
|
| 1236 |
-
"support":
|
| 1237 |
},
|
| 1238 |
-
"accuracy": 0.
|
| 1239 |
"macro avg": {
|
| 1240 |
-
"precision": 0.
|
| 1241 |
-
"recall": 0.
|
| 1242 |
-
"f1-score": 0.
|
| 1243 |
-
"support":
|
| 1244 |
},
|
| 1245 |
"weighted avg": {
|
| 1246 |
-
"precision": 0.
|
| 1247 |
-
"recall": 0.
|
| 1248 |
-
"f1-score": 0.
|
| 1249 |
-
"support":
|
| 1250 |
}
|
| 1251 |
},
|
| 1252 |
-
"roc_auc": 0.
|
| 1253 |
-
"average_precision": 0.
|
| 1254 |
}
|
| 1255 |
}
|
| 1256 |
]
|
|
|
|
| 1 |
{
|
| 2 |
+
"created_at": "2026-06-09T23:58:45.600559+00:00",
|
| 3 |
"config": {
|
| 4 |
"hf_dataset": "faodl/amis-agri-utilization",
|
| 5 |
"hf_subset": null,
|
| 6 |
+
"hf_revision": "main",
|
| 7 |
"train_split": "train",
|
| 8 |
"validation_split": "validation",
|
| 9 |
"test_split": "test",
|
|
|
|
| 44 |
},
|
| 45 |
"dataset_summary": {
|
| 46 |
"train": {
|
| 47 |
+
"rows": 9753,
|
| 48 |
"labels": {
|
| 49 |
+
"0": 8950,
|
| 50 |
+
"1": 803
|
| 51 |
},
|
| 52 |
+
"unique_groups": 4987,
|
| 53 |
+
"text_length_mean": 696.3964933866503,
|
| 54 |
"text_length_median": 794.0
|
| 55 |
},
|
| 56 |
"validation": {
|
| 57 |
+
"rows": 2084,
|
| 58 |
"labels": {
|
| 59 |
+
"0": 1885,
|
| 60 |
+
"1": 199
|
| 61 |
},
|
| 62 |
+
"unique_groups": 1069,
|
| 63 |
+
"text_length_mean": 700.8267754318618,
|
| 64 |
"text_length_median": 794.0
|
| 65 |
},
|
| 66 |
"test": {
|
| 67 |
+
"rows": 2086,
|
| 68 |
"labels": {
|
| 69 |
+
"0": 1957,
|
| 70 |
+
"1": 129
|
| 71 |
},
|
| 72 |
+
"unique_groups": 1069,
|
| 73 |
+
"text_length_mean": 701.6332694151486,
|
| 74 |
"text_length_median": 794.0
|
| 75 |
}
|
| 76 |
},
|
|
|
|
| 81 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/logistic",
|
| 82 |
"artifact_file": "/content/agri-utilization-classifier/baselines/logistic/logistic_tfidf.joblib",
|
| 83 |
"validation_best_threshold": {
|
| 84 |
+
"threshold": 0.36023362771573536,
|
| 85 |
+
"f1": 0.48928571428571427,
|
| 86 |
+
"precision": 0.37950138504155123,
|
| 87 |
+
"recall": 0.6884422110552764
|
| 88 |
},
|
| 89 |
"validation_default_0_5": {
|
| 90 |
"threshold": 0.5,
|
| 91 |
+
"accuracy": 0.9011516314779271,
|
| 92 |
+
"precision": 0.4816753926701571,
|
| 93 |
+
"recall": 0.4623115577889447,
|
| 94 |
+
"f1": 0.4717948717948718,
|
| 95 |
"confusion_matrix": [
|
| 96 |
[
|
| 97 |
+
1786,
|
| 98 |
+
99
|
| 99 |
],
|
| 100 |
[
|
| 101 |
+
107,
|
| 102 |
+
92
|
| 103 |
]
|
| 104 |
],
|
| 105 |
"classification_report": {
|
| 106 |
"NOT_RELEVANT": {
|
| 107 |
+
"precision": 0.9434759640781828,
|
| 108 |
+
"recall": 0.9474801061007958,
|
| 109 |
+
"f1-score": 0.9454737956590789,
|
| 110 |
+
"support": 1885.0
|
| 111 |
},
|
| 112 |
"RELEVANT": {
|
| 113 |
+
"precision": 0.4816753926701571,
|
| 114 |
+
"recall": 0.4623115577889447,
|
| 115 |
+
"f1-score": 0.4717948717948718,
|
| 116 |
+
"support": 199.0
|
| 117 |
},
|
| 118 |
+
"accuracy": 0.9011516314779271,
|
| 119 |
"macro avg": {
|
| 120 |
+
"precision": 0.7125756783741699,
|
| 121 |
+
"recall": 0.7048958319448703,
|
| 122 |
+
"f1-score": 0.7086343337269754,
|
| 123 |
+
"support": 2084.0
|
| 124 |
},
|
| 125 |
"weighted avg": {
|
| 126 |
+
"precision": 0.8993788845627332,
|
| 127 |
+
"recall": 0.9011516314779271,
|
| 128 |
+
"f1-score": 0.9002424588793393,
|
| 129 |
+
"support": 2084.0
|
| 130 |
}
|
| 131 |
},
|
| 132 |
+
"roc_auc": 0.8674606454020767,
|
| 133 |
+
"average_precision": 0.4960554729220717
|
| 134 |
},
|
| 135 |
"validation_optimal_threshold": {
|
| 136 |
+
"threshold": 0.36023362771573536,
|
| 137 |
+
"accuracy": 0.8627639155470249,
|
| 138 |
+
"precision": 0.37950138504155123,
|
| 139 |
+
"recall": 0.6884422110552764,
|
| 140 |
+
"f1": 0.48928571428571427,
|
| 141 |
"confusion_matrix": [
|
| 142 |
[
|
| 143 |
+
1661,
|
| 144 |
+
224
|
| 145 |
],
|
| 146 |
[
|
| 147 |
+
62,
|
| 148 |
+
137
|
| 149 |
]
|
| 150 |
],
|
| 151 |
"classification_report": {
|
| 152 |
"NOT_RELEVANT": {
|
| 153 |
+
"precision": 0.9640162507254788,
|
| 154 |
+
"recall": 0.8811671087533156,
|
| 155 |
+
"f1-score": 0.9207317073170732,
|
| 156 |
+
"support": 1885.0
|
| 157 |
},
|
| 158 |
"RELEVANT": {
|
| 159 |
+
"precision": 0.37950138504155123,
|
| 160 |
+
"recall": 0.6884422110552764,
|
| 161 |
+
"f1-score": 0.48928571428571427,
|
| 162 |
+
"support": 199.0
|
| 163 |
},
|
| 164 |
+
"accuracy": 0.8627639155470249,
|
| 165 |
"macro avg": {
|
| 166 |
+
"precision": 0.671758817883515,
|
| 167 |
+
"recall": 0.7848046599042959,
|
| 168 |
+
"f1-score": 0.7050087108013937,
|
| 169 |
+
"support": 2084.0
|
| 170 |
},
|
| 171 |
"weighted avg": {
|
| 172 |
+
"precision": 0.9082012515550846,
|
| 173 |
+
"recall": 0.8627639155470249,
|
| 174 |
+
"f1-score": 0.879533169594789,
|
| 175 |
+
"support": 2084.0
|
| 176 |
}
|
| 177 |
},
|
| 178 |
+
"roc_auc": 0.8674606454020767,
|
| 179 |
+
"average_precision": 0.4960554729220717
|
| 180 |
},
|
| 181 |
"test_default_0_5": {
|
| 182 |
"threshold": 0.5,
|
| 183 |
+
"accuracy": 0.9175455417066155,
|
| 184 |
+
"precision": 0.3576158940397351,
|
| 185 |
+
"recall": 0.4186046511627907,
|
| 186 |
+
"f1": 0.38571428571428573,
|
| 187 |
"confusion_matrix": [
|
| 188 |
[
|
| 189 |
+
1860,
|
| 190 |
+
97
|
| 191 |
],
|
| 192 |
[
|
| 193 |
+
75,
|
| 194 |
+
54
|
| 195 |
]
|
| 196 |
],
|
| 197 |
"classification_report": {
|
| 198 |
"NOT_RELEVANT": {
|
| 199 |
+
"precision": 0.9612403100775194,
|
| 200 |
+
"recall": 0.9504343382728666,
|
| 201 |
+
"f1-score": 0.9558067831449126,
|
| 202 |
+
"support": 1957.0
|
| 203 |
},
|
| 204 |
"RELEVANT": {
|
| 205 |
+
"precision": 0.3576158940397351,
|
| 206 |
+
"recall": 0.4186046511627907,
|
| 207 |
+
"f1-score": 0.38571428571428573,
|
| 208 |
+
"support": 129.0
|
| 209 |
},
|
| 210 |
+
"accuracy": 0.9175455417066155,
|
| 211 |
"macro avg": {
|
| 212 |
+
"precision": 0.6594281020586272,
|
| 213 |
+
"recall": 0.6845194947178287,
|
| 214 |
+
"f1-score": 0.6707605344295992,
|
| 215 |
+
"support": 2086.0
|
| 216 |
},
|
| 217 |
"weighted avg": {
|
| 218 |
+
"precision": 0.9239116668997274,
|
| 219 |
+
"recall": 0.9175455417066155,
|
| 220 |
+
"f1-score": 0.9205517821053388,
|
| 221 |
+
"support": 2086.0
|
| 222 |
}
|
| 223 |
},
|
| 224 |
+
"roc_auc": 0.8562663149180244,
|
| 225 |
+
"average_precision": 0.3981049318082447
|
| 226 |
},
|
| 227 |
"test_optimal_threshold": {
|
| 228 |
+
"threshold": 0.36023362771573536,
|
| 229 |
+
"accuracy": 0.8686481303930969,
|
| 230 |
+
"precision": 0.26688102893890675,
|
| 231 |
+
"recall": 0.6434108527131783,
|
| 232 |
+
"f1": 0.37727272727272726,
|
| 233 |
"confusion_matrix": [
|
| 234 |
[
|
| 235 |
+
1729,
|
| 236 |
+
228
|
| 237 |
],
|
| 238 |
[
|
| 239 |
+
46,
|
| 240 |
+
83
|
| 241 |
]
|
| 242 |
],
|
| 243 |
"classification_report": {
|
| 244 |
"NOT_RELEVANT": {
|
| 245 |
+
"precision": 0.9740845070422535,
|
| 246 |
+
"recall": 0.883495145631068,
|
| 247 |
+
"f1-score": 0.9265809217577706,
|
| 248 |
+
"support": 1957.0
|
| 249 |
},
|
| 250 |
"RELEVANT": {
|
| 251 |
+
"precision": 0.26688102893890675,
|
| 252 |
+
"recall": 0.6434108527131783,
|
| 253 |
+
"f1-score": 0.37727272727272726,
|
| 254 |
+
"support": 129.0
|
| 255 |
},
|
| 256 |
+
"accuracy": 0.8686481303930969,
|
| 257 |
"macro avg": {
|
| 258 |
+
"precision": 0.6204827679905801,
|
| 259 |
+
"recall": 0.7634529991721232,
|
| 260 |
+
"f1-score": 0.651926824515249,
|
| 261 |
+
"support": 2086.0
|
| 262 |
},
|
| 263 |
"weighted avg": {
|
| 264 |
+
"precision": 0.9303504472745969,
|
| 265 |
+
"recall": 0.8686481303930969,
|
| 266 |
+
"f1-score": 0.8926112395484846,
|
| 267 |
+
"support": 2086.0
|
| 268 |
}
|
| 269 |
},
|
| 270 |
+
"roc_auc": 0.8562663149180244,
|
| 271 |
+
"average_precision": 0.3981049318082447
|
| 272 |
}
|
| 273 |
},
|
| 274 |
{
|
|
|
|
| 277 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/xgboost",
|
| 278 |
"artifact_file": "/content/agri-utilization-classifier/baselines/xgboost/xgboost_tfidf.joblib",
|
| 279 |
"validation_best_threshold": {
|
| 280 |
+
"threshold": 0.10415865480899811,
|
| 281 |
+
"f1": 0.5354691075514874,
|
| 282 |
+
"precision": 0.49159663865546216,
|
| 283 |
+
"recall": 0.5879396984924623
|
| 284 |
},
|
| 285 |
"validation_default_0_5": {
|
| 286 |
"threshold": 0.5,
|
| 287 |
+
"accuracy": 0.9189059500959693,
|
| 288 |
+
"precision": 0.7205882352941176,
|
| 289 |
+
"recall": 0.24623115577889448,
|
| 290 |
+
"f1": 0.36704119850187267,
|
| 291 |
"confusion_matrix": [
|
| 292 |
[
|
| 293 |
+
1866,
|
| 294 |
+
19
|
| 295 |
],
|
| 296 |
[
|
| 297 |
+
150,
|
| 298 |
+
49
|
| 299 |
]
|
| 300 |
],
|
| 301 |
"classification_report": {
|
| 302 |
"NOT_RELEVANT": {
|
| 303 |
+
"precision": 0.9255952380952381,
|
| 304 |
+
"recall": 0.9899204244031831,
|
| 305 |
+
"f1-score": 0.9566777749295052,
|
| 306 |
+
"support": 1885.0
|
| 307 |
},
|
| 308 |
"RELEVANT": {
|
| 309 |
+
"precision": 0.7205882352941176,
|
| 310 |
+
"recall": 0.24623115577889448,
|
| 311 |
+
"f1-score": 0.36704119850187267,
|
| 312 |
+
"support": 199.0
|
| 313 |
},
|
| 314 |
+
"accuracy": 0.9189059500959693,
|
| 315 |
"macro avg": {
|
| 316 |
+
"precision": 0.823091736694678,
|
| 317 |
+
"recall": 0.6180757900910387,
|
| 318 |
+
"f1-score": 0.661859486715689,
|
| 319 |
+
"support": 2084.0
|
| 320 |
},
|
| 321 |
"weighted avg": {
|
| 322 |
+
"precision": 0.9060192335091427,
|
| 323 |
+
"recall": 0.9189059500959693,
|
| 324 |
+
"f1-score": 0.9003737064510509,
|
| 325 |
+
"support": 2084.0
|
| 326 |
}
|
| 327 |
},
|
| 328 |
+
"roc_auc": 0.8338682803940125,
|
| 329 |
+
"average_precision": 0.49303491730954946
|
| 330 |
},
|
| 331 |
"validation_optimal_threshold": {
|
| 332 |
+
"threshold": 0.10415865480899811,
|
| 333 |
+
"accuracy": 0.9025911708253359,
|
| 334 |
+
"precision": 0.49159663865546216,
|
| 335 |
+
"recall": 0.5879396984924623,
|
| 336 |
+
"f1": 0.5354691075514875,
|
| 337 |
"confusion_matrix": [
|
| 338 |
[
|
| 339 |
+
1764,
|
| 340 |
+
121
|
| 341 |
],
|
| 342 |
[
|
| 343 |
+
82,
|
| 344 |
+
117
|
| 345 |
]
|
| 346 |
],
|
| 347 |
"classification_report": {
|
| 348 |
"NOT_RELEVANT": {
|
| 349 |
+
"precision": 0.9555796316359697,
|
| 350 |
+
"recall": 0.9358090185676392,
|
| 351 |
+
"f1-score": 0.9455909943714822,
|
| 352 |
+
"support": 1885.0
|
| 353 |
},
|
| 354 |
"RELEVANT": {
|
| 355 |
+
"precision": 0.49159663865546216,
|
| 356 |
+
"recall": 0.5879396984924623,
|
| 357 |
+
"f1-score": 0.5354691075514875,
|
| 358 |
+
"support": 199.0
|
| 359 |
},
|
| 360 |
+
"accuracy": 0.9025911708253359,
|
| 361 |
"macro avg": {
|
| 362 |
+
"precision": 0.723588135145716,
|
| 363 |
+
"recall": 0.7618743585300507,
|
| 364 |
+
"f1-score": 0.7405300509614848,
|
| 365 |
+
"support": 2084.0
|
| 366 |
},
|
| 367 |
"weighted avg": {
|
| 368 |
+
"precision": 0.9112741538993474,
|
| 369 |
+
"recall": 0.9025911708253359,
|
| 370 |
+
"f1-score": 0.906428683681857,
|
| 371 |
+
"support": 2084.0
|
| 372 |
}
|
| 373 |
},
|
| 374 |
+
"roc_auc": 0.8338682803940125,
|
| 375 |
+
"average_precision": 0.49303491730954946
|
| 376 |
},
|
| 377 |
"test_default_0_5": {
|
| 378 |
"threshold": 0.5,
|
| 379 |
+
"accuracy": 0.950143815915628,
|
| 380 |
+
"precision": 0.7659574468085106,
|
| 381 |
+
"recall": 0.27906976744186046,
|
| 382 |
+
"f1": 0.4090909090909091,
|
| 383 |
"confusion_matrix": [
|
| 384 |
[
|
| 385 |
+
1946,
|
| 386 |
+
11
|
| 387 |
],
|
| 388 |
[
|
| 389 |
+
93,
|
| 390 |
+
36
|
| 391 |
]
|
| 392 |
],
|
| 393 |
"classification_report": {
|
| 394 |
"NOT_RELEVANT": {
|
| 395 |
+
"precision": 0.9543894065718489,
|
| 396 |
+
"recall": 0.9943791517629024,
|
| 397 |
+
"f1-score": 0.973973973973974,
|
| 398 |
+
"support": 1957.0
|
| 399 |
},
|
| 400 |
"RELEVANT": {
|
| 401 |
+
"precision": 0.7659574468085106,
|
| 402 |
+
"recall": 0.27906976744186046,
|
| 403 |
+
"f1-score": 0.4090909090909091,
|
| 404 |
+
"support": 129.0
|
| 405 |
},
|
| 406 |
+
"accuracy": 0.950143815915628,
|
| 407 |
"macro avg": {
|
| 408 |
+
"precision": 0.8601734266901797,
|
| 409 |
+
"recall": 0.6367244596023814,
|
| 410 |
+
"f1-score": 0.6915324415324415,
|
| 411 |
+
"support": 2086.0
|
| 412 |
},
|
| 413 |
"weighted avg": {
|
| 414 |
+
"precision": 0.9427366151962637,
|
| 415 |
+
"recall": 0.950143815915628,
|
| 416 |
+
"f1-score": 0.9390411286384441,
|
| 417 |
+
"support": 2086.0
|
| 418 |
}
|
| 419 |
},
|
| 420 |
+
"roc_auc": 0.8210657033190336,
|
| 421 |
+
"average_precision": 0.47107353711983707
|
| 422 |
},
|
| 423 |
"test_optimal_threshold": {
|
| 424 |
+
"threshold": 0.10415865480899811,
|
| 425 |
+
"accuracy": 0.9065196548418025,
|
| 426 |
+
"precision": 0.34285714285714286,
|
| 427 |
+
"recall": 0.5581395348837209,
|
| 428 |
+
"f1": 0.4247787610619469,
|
| 429 |
"confusion_matrix": [
|
| 430 |
[
|
| 431 |
+
1819,
|
| 432 |
+
138
|
| 433 |
],
|
| 434 |
[
|
| 435 |
+
57,
|
| 436 |
+
72
|
| 437 |
]
|
| 438 |
],
|
| 439 |
"classification_report": {
|
| 440 |
"NOT_RELEVANT": {
|
| 441 |
+
"precision": 0.9696162046908315,
|
| 442 |
+
"recall": 0.9294839039345938,
|
| 443 |
+
"f1-score": 0.9491260109574745,
|
| 444 |
+
"support": 1957.0
|
| 445 |
},
|
| 446 |
"RELEVANT": {
|
| 447 |
+
"precision": 0.34285714285714286,
|
| 448 |
+
"recall": 0.5581395348837209,
|
| 449 |
+
"f1-score": 0.4247787610619469,
|
| 450 |
+
"support": 129.0
|
| 451 |
},
|
| 452 |
+
"accuracy": 0.9065196548418025,
|
| 453 |
"macro avg": {
|
| 454 |
+
"precision": 0.6562366737739872,
|
| 455 |
+
"recall": 0.7438117194091574,
|
| 456 |
+
"f1-score": 0.6869523860097106,
|
| 457 |
+
"support": 2086.0
|
| 458 |
},
|
| 459 |
"weighted avg": {
|
| 460 |
+
"precision": 0.9308568954978566,
|
| 461 |
+
"recall": 0.9065196548418025,
|
| 462 |
+
"f1-score": 0.9166999346216532,
|
| 463 |
+
"support": 2086.0
|
| 464 |
}
|
| 465 |
},
|
| 466 |
+
"roc_auc": 0.8210657033190336,
|
| 467 |
+
"average_precision": 0.47107353711983707
|
| 468 |
}
|
| 469 |
},
|
| 470 |
{
|
|
|
|
| 474 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-logistic",
|
| 475 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-logistic/embedding-logistic.joblib",
|
| 476 |
"validation_best_threshold": {
|
| 477 |
+
"threshold": 0.7262281775474548,
|
| 478 |
+
"f1": 0.6881720430107527,
|
| 479 |
+
"precision": 0.6015037593984962,
|
| 480 |
+
"recall": 0.8040201005025126
|
| 481 |
},
|
| 482 |
"validation_default_0_5": {
|
| 483 |
"threshold": 0.5,
|
| 484 |
+
"accuracy": 0.8953934740882917,
|
| 485 |
+
"precision": 0.473972602739726,
|
| 486 |
+
"recall": 0.8693467336683417,
|
| 487 |
+
"f1": 0.6134751773049646,
|
| 488 |
"confusion_matrix": [
|
| 489 |
[
|
| 490 |
+
1693,
|
| 491 |
+
192
|
| 492 |
],
|
| 493 |
[
|
| 494 |
+
26,
|
| 495 |
+
173
|
| 496 |
]
|
| 497 |
],
|
| 498 |
"classification_report": {
|
| 499 |
"NOT_RELEVANT": {
|
| 500 |
+
"precision": 0.9848749272833043,
|
| 501 |
+
"recall": 0.8981432360742706,
|
| 502 |
+
"f1-score": 0.939511653718091,
|
| 503 |
+
"support": 1885.0
|
| 504 |
},
|
| 505 |
"RELEVANT": {
|
| 506 |
+
"precision": 0.473972602739726,
|
| 507 |
+
"recall": 0.8693467336683417,
|
| 508 |
+
"f1-score": 0.6134751773049646,
|
| 509 |
+
"support": 199.0
|
| 510 |
},
|
| 511 |
+
"accuracy": 0.8953934740882917,
|
| 512 |
"macro avg": {
|
| 513 |
+
"precision": 0.7294237650115152,
|
| 514 |
+
"recall": 0.8837449848713061,
|
| 515 |
+
"f1-score": 0.7764934155115277,
|
| 516 |
+
"support": 2084.0
|
| 517 |
},
|
| 518 |
"weighted avg": {
|
| 519 |
+
"precision": 0.9360891486920508,
|
| 520 |
+
"recall": 0.8953934740882917,
|
| 521 |
+
"f1-score": 0.9083786120644383,
|
| 522 |
+
"support": 2084.0
|
| 523 |
}
|
| 524 |
},
|
| 525 |
+
"roc_auc": 0.951833437745758,
|
| 526 |
+
"average_precision": 0.6518934466014814
|
| 527 |
},
|
| 528 |
"validation_optimal_threshold": {
|
| 529 |
+
"threshold": 0.7262281775474548,
|
| 530 |
+
"accuracy": 0.9304222648752399,
|
| 531 |
+
"precision": 0.6015037593984962,
|
| 532 |
+
"recall": 0.8040201005025126,
|
| 533 |
+
"f1": 0.6881720430107527,
|
| 534 |
"confusion_matrix": [
|
| 535 |
[
|
| 536 |
+
1779,
|
| 537 |
+
106
|
| 538 |
],
|
| 539 |
[
|
| 540 |
+
39,
|
| 541 |
+
160
|
| 542 |
]
|
| 543 |
],
|
| 544 |
"classification_report": {
|
| 545 |
"NOT_RELEVANT": {
|
| 546 |
+
"precision": 0.9785478547854786,
|
| 547 |
+
"recall": 0.9437665782493369,
|
| 548 |
+
"f1-score": 0.9608425600864164,
|
| 549 |
+
"support": 1885.0
|
| 550 |
},
|
| 551 |
"RELEVANT": {
|
| 552 |
+
"precision": 0.6015037593984962,
|
| 553 |
+
"recall": 0.8040201005025126,
|
| 554 |
+
"f1-score": 0.6881720430107527,
|
| 555 |
+
"support": 199.0
|
| 556 |
},
|
| 557 |
+
"accuracy": 0.9304222648752399,
|
| 558 |
"macro avg": {
|
| 559 |
+
"precision": 0.7900258070919874,
|
| 560 |
+
"recall": 0.8738933393759247,
|
| 561 |
+
"f1-score": 0.8245073015485846,
|
| 562 |
+
"support": 2084.0
|
| 563 |
},
|
| 564 |
"weighted avg": {
|
| 565 |
+
"precision": 0.9425441239879693,
|
| 566 |
+
"recall": 0.9304222648752399,
|
| 567 |
+
"f1-score": 0.9348054041852374,
|
| 568 |
+
"support": 2084.0
|
| 569 |
}
|
| 570 |
},
|
| 571 |
+
"roc_auc": 0.951833437745758,
|
| 572 |
+
"average_precision": 0.6518934466014814
|
| 573 |
},
|
| 574 |
"test_default_0_5": {
|
| 575 |
"threshold": 0.5,
|
| 576 |
+
"accuracy": 0.8911792905081496,
|
| 577 |
+
"precision": 0.3496932515337423,
|
| 578 |
+
"recall": 0.8837209302325582,
|
| 579 |
+
"f1": 0.5010989010989011,
|
| 580 |
"confusion_matrix": [
|
| 581 |
[
|
| 582 |
+
1745,
|
| 583 |
+
212
|
| 584 |
],
|
| 585 |
[
|
| 586 |
+
15,
|
| 587 |
+
114
|
| 588 |
]
|
| 589 |
],
|
| 590 |
"classification_report": {
|
| 591 |
"NOT_RELEVANT": {
|
| 592 |
+
"precision": 0.9914772727272727,
|
| 593 |
+
"recall": 0.8916709248850281,
|
| 594 |
+
"f1-score": 0.9389292440139898,
|
| 595 |
+
"support": 1957.0
|
| 596 |
},
|
| 597 |
"RELEVANT": {
|
| 598 |
+
"precision": 0.3496932515337423,
|
| 599 |
+
"recall": 0.8837209302325582,
|
| 600 |
+
"f1-score": 0.5010989010989011,
|
| 601 |
+
"support": 129.0
|
| 602 |
},
|
| 603 |
+
"accuracy": 0.8911792905081496,
|
| 604 |
"macro avg": {
|
| 605 |
+
"precision": 0.6705852621305075,
|
| 606 |
+
"recall": 0.8876959275587931,
|
| 607 |
+
"f1-score": 0.7200140725564455,
|
| 608 |
+
"support": 2086.0
|
| 609 |
},
|
| 610 |
"weighted avg": {
|
| 611 |
+
"precision": 0.9517888073706259,
|
| 612 |
+
"recall": 0.8911792905081496,
|
| 613 |
+
"f1-score": 0.911853446201887,
|
| 614 |
+
"support": 2086.0
|
| 615 |
}
|
| 616 |
},
|
| 617 |
+
"roc_auc": 0.9507987625419385,
|
| 618 |
+
"average_precision": 0.5430515103343022
|
| 619 |
},
|
| 620 |
"test_optimal_threshold": {
|
| 621 |
+
"threshold": 0.7262281775474548,
|
| 622 |
+
"accuracy": 0.9285714285714286,
|
| 623 |
+
"precision": 0.4494949494949495,
|
| 624 |
+
"recall": 0.689922480620155,
|
| 625 |
+
"f1": 0.5443425076452599,
|
| 626 |
"confusion_matrix": [
|
| 627 |
[
|
| 628 |
+
1848,
|
| 629 |
+
109
|
| 630 |
],
|
| 631 |
[
|
| 632 |
+
40,
|
| 633 |
+
89
|
| 634 |
]
|
| 635 |
],
|
| 636 |
"classification_report": {
|
| 637 |
"NOT_RELEVANT": {
|
| 638 |
+
"precision": 0.9788135593220338,
|
| 639 |
+
"recall": 0.9443025038323966,
|
| 640 |
+
"f1-score": 0.9612483745123537,
|
| 641 |
+
"support": 1957.0
|
| 642 |
},
|
| 643 |
"RELEVANT": {
|
| 644 |
+
"precision": 0.4494949494949495,
|
| 645 |
+
"recall": 0.689922480620155,
|
| 646 |
+
"f1-score": 0.5443425076452599,
|
| 647 |
+
"support": 129.0
|
| 648 |
},
|
| 649 |
+
"accuracy": 0.9285714285714286,
|
| 650 |
"macro avg": {
|
| 651 |
+
"precision": 0.7141542544084917,
|
| 652 |
+
"recall": 0.8171124922262758,
|
| 653 |
+
"f1-score": 0.7527954410788068,
|
| 654 |
+
"support": 2086.0
|
| 655 |
},
|
| 656 |
"weighted avg": {
|
| 657 |
+
"precision": 0.9460800498936092,
|
| 658 |
+
"recall": 0.9285714285714286,
|
| 659 |
+
"f1-score": 0.9354665639534586,
|
| 660 |
+
"support": 2086.0
|
| 661 |
}
|
| 662 |
},
|
| 663 |
+
"roc_auc": 0.9507987625419385,
|
| 664 |
+
"average_precision": 0.5430515103343022
|
| 665 |
}
|
| 666 |
},
|
| 667 |
{
|
|
|
|
| 671 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-svm",
|
| 672 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-svm/embedding-svm.joblib",
|
| 673 |
"validation_best_threshold": {
|
| 674 |
+
"threshold": 0.24490298824052611,
|
| 675 |
+
"f1": 0.7004608294930875,
|
| 676 |
+
"precision": 0.6468085106382979,
|
| 677 |
+
"recall": 0.7638190954773869
|
| 678 |
},
|
| 679 |
"validation_default_0_5": {
|
| 680 |
"threshold": 0.5,
|
| 681 |
+
"accuracy": 0.9313819577735125,
|
| 682 |
+
"precision": 0.7121212121212122,
|
| 683 |
+
"recall": 0.4723618090452261,
|
| 684 |
+
"f1": 0.56797583081571,
|
| 685 |
"confusion_matrix": [
|
| 686 |
[
|
| 687 |
+
1847,
|
| 688 |
+
38
|
| 689 |
],
|
| 690 |
[
|
| 691 |
+
105,
|
| 692 |
+
94
|
| 693 |
]
|
| 694 |
],
|
| 695 |
"classification_report": {
|
| 696 |
"NOT_RELEVANT": {
|
| 697 |
+
"precision": 0.9462090163934426,
|
| 698 |
+
"recall": 0.979840848806366,
|
| 699 |
+
"f1-score": 0.9627313004951785,
|
| 700 |
+
"support": 1885.0
|
| 701 |
},
|
| 702 |
"RELEVANT": {
|
| 703 |
+
"precision": 0.7121212121212122,
|
| 704 |
+
"recall": 0.4723618090452261,
|
| 705 |
+
"f1-score": 0.56797583081571,
|
| 706 |
+
"support": 199.0
|
| 707 |
},
|
| 708 |
+
"accuracy": 0.9313819577735125,
|
| 709 |
"macro avg": {
|
| 710 |
+
"precision": 0.8291651142573273,
|
| 711 |
+
"recall": 0.726101328925796,
|
| 712 |
+
"f1-score": 0.7653535656554442,
|
| 713 |
+
"support": 2084.0
|
| 714 |
},
|
| 715 |
"weighted avg": {
|
| 716 |
+
"precision": 0.9238561022618813,
|
| 717 |
+
"recall": 0.9313819577735125,
|
| 718 |
+
"f1-score": 0.9250363204250182,
|
| 719 |
+
"support": 2084.0
|
| 720 |
}
|
| 721 |
},
|
| 722 |
+
"roc_auc": 0.9535662396864961,
|
| 723 |
+
"average_precision": 0.6698106173212027
|
| 724 |
},
|
| 725 |
"validation_optimal_threshold": {
|
| 726 |
+
"threshold": 0.24490298824052611,
|
| 727 |
+
"accuracy": 0.9376199616122841,
|
| 728 |
+
"precision": 0.6468085106382979,
|
| 729 |
+
"recall": 0.7638190954773869,
|
| 730 |
+
"f1": 0.7004608294930875,
|
| 731 |
"confusion_matrix": [
|
| 732 |
[
|
| 733 |
+
1802,
|
| 734 |
+
83
|
| 735 |
],
|
| 736 |
[
|
| 737 |
+
47,
|
| 738 |
+
152
|
| 739 |
]
|
| 740 |
],
|
| 741 |
"classification_report": {
|
| 742 |
"NOT_RELEVANT": {
|
| 743 |
+
"precision": 0.9745808545159546,
|
| 744 |
+
"recall": 0.9559681697612732,
|
| 745 |
+
"f1-score": 0.9651847884306374,
|
| 746 |
+
"support": 1885.0
|
| 747 |
},
|
| 748 |
"RELEVANT": {
|
| 749 |
+
"precision": 0.6468085106382979,
|
| 750 |
+
"recall": 0.7638190954773869,
|
| 751 |
+
"f1-score": 0.7004608294930875,
|
| 752 |
+
"support": 199.0
|
| 753 |
},
|
| 754 |
+
"accuracy": 0.9376199616122841,
|
| 755 |
"macro avg": {
|
| 756 |
+
"precision": 0.8106946825771262,
|
| 757 |
+
"recall": 0.85989363261933,
|
| 758 |
+
"f1-score": 0.8328228089618624,
|
| 759 |
+
"support": 2084.0
|
| 760 |
},
|
| 761 |
"weighted avg": {
|
| 762 |
+
"precision": 0.9432820558443357,
|
| 763 |
+
"recall": 0.9376199616122841,
|
| 764 |
+
"f1-score": 0.9399064449428386,
|
| 765 |
+
"support": 2084.0
|
| 766 |
}
|
| 767 |
},
|
| 768 |
+
"roc_auc": 0.9535662396864961,
|
| 769 |
+
"average_precision": 0.6698106173212027
|
| 770 |
},
|
| 771 |
"test_default_0_5": {
|
| 772 |
"threshold": 0.5,
|
| 773 |
+
"accuracy": 0.9482262703739214,
|
| 774 |
+
"precision": 0.6060606060606061,
|
| 775 |
+
"recall": 0.46511627906976744,
|
| 776 |
+
"f1": 0.5263157894736842,
|
| 777 |
"confusion_matrix": [
|
| 778 |
[
|
| 779 |
+
1918,
|
| 780 |
+
39
|
| 781 |
],
|
| 782 |
[
|
| 783 |
+
69,
|
| 784 |
+
60
|
| 785 |
]
|
| 786 |
],
|
| 787 |
"classification_report": {
|
| 788 |
"NOT_RELEVANT": {
|
| 789 |
+
"precision": 0.96527428283845,
|
| 790 |
+
"recall": 0.9800715380684721,
|
| 791 |
+
"f1-score": 0.9726166328600405,
|
| 792 |
+
"support": 1957.0
|
| 793 |
},
|
| 794 |
"RELEVANT": {
|
| 795 |
+
"precision": 0.6060606060606061,
|
| 796 |
+
"recall": 0.46511627906976744,
|
| 797 |
+
"f1-score": 0.5263157894736842,
|
| 798 |
+
"support": 129.0
|
| 799 |
},
|
| 800 |
+
"accuracy": 0.9482262703739214,
|
| 801 |
"macro avg": {
|
| 802 |
+
"precision": 0.785667444449528,
|
| 803 |
+
"recall": 0.7225939085691198,
|
| 804 |
+
"f1-score": 0.7494662111668624,
|
| 805 |
+
"support": 2086.0
|
| 806 |
},
|
| 807 |
"weighted avg": {
|
| 808 |
+
"precision": 0.9430602059907309,
|
| 809 |
+
"recall": 0.9482262703739214,
|
| 810 |
+
"f1-score": 0.9450170121520635,
|
| 811 |
+
"support": 2086.0
|
| 812 |
}
|
| 813 |
},
|
| 814 |
+
"roc_auc": 0.9554768610394807,
|
| 815 |
+
"average_precision": 0.5656727259491919
|
| 816 |
},
|
| 817 |
"test_optimal_threshold": {
|
| 818 |
+
"threshold": 0.24490298824052611,
|
| 819 |
+
"accuracy": 0.9372003835091084,
|
| 820 |
+
"precision": 0.4943181818181818,
|
| 821 |
+
"recall": 0.6744186046511628,
|
| 822 |
+
"f1": 0.5704918032786885,
|
| 823 |
"confusion_matrix": [
|
| 824 |
[
|
| 825 |
+
1868,
|
| 826 |
+
89
|
| 827 |
],
|
| 828 |
[
|
| 829 |
+
42,
|
| 830 |
+
87
|
| 831 |
]
|
| 832 |
],
|
| 833 |
"classification_report": {
|
| 834 |
"NOT_RELEVANT": {
|
| 835 |
+
"precision": 0.9780104712041885,
|
| 836 |
+
"recall": 0.9545222278998468,
|
| 837 |
+
"f1-score": 0.9661236100336178,
|
| 838 |
+
"support": 1957.0
|
| 839 |
},
|
| 840 |
"RELEVANT": {
|
| 841 |
+
"precision": 0.4943181818181818,
|
| 842 |
+
"recall": 0.6744186046511628,
|
| 843 |
+
"f1-score": 0.5704918032786885,
|
| 844 |
+
"support": 129.0
|
| 845 |
},
|
| 846 |
+
"accuracy": 0.9372003835091084,
|
| 847 |
"macro avg": {
|
| 848 |
+
"precision": 0.7361643265111851,
|
| 849 |
+
"recall": 0.8144704162755048,
|
| 850 |
+
"f1-score": 0.7683077066561532,
|
| 851 |
+
"support": 2086.0
|
| 852 |
},
|
| 853 |
"weighted avg": {
|
| 854 |
+
"precision": 0.9480985319276809,
|
| 855 |
+
"recall": 0.9372003835091084,
|
| 856 |
+
"f1-score": 0.9416574053014098,
|
| 857 |
+
"support": 2086.0
|
| 858 |
}
|
| 859 |
},
|
| 860 |
+
"roc_auc": 0.9554768610394807,
|
| 861 |
+
"average_precision": 0.5656727259491919
|
| 862 |
}
|
| 863 |
},
|
| 864 |
{
|
|
|
|
| 868 |
"artifact_dir": "/content/agri-utilization-classifier/baselines/embedding-lightgbm",
|
| 869 |
"artifact_file": "/content/agri-utilization-classifier/baselines/embedding-lightgbm/embedding-lightgbm.joblib",
|
| 870 |
"validation_best_threshold": {
|
| 871 |
+
"threshold": 0.08937255699326424,
|
| 872 |
+
"f1": 0.7008547008547008,
|
| 873 |
+
"precision": 0.6096654275092936,
|
| 874 |
+
"recall": 0.8241206030150754
|
| 875 |
},
|
| 876 |
"validation_default_0_5": {
|
| 877 |
"threshold": 0.5,
|
| 878 |
+
"accuracy": 0.9366602687140115,
|
| 879 |
+
"precision": 0.6810810810810811,
|
| 880 |
+
"recall": 0.6331658291457286,
|
| 881 |
+
"f1": 0.65625,
|
| 882 |
"confusion_matrix": [
|
| 883 |
[
|
| 884 |
+
1826,
|
| 885 |
+
59
|
| 886 |
],
|
| 887 |
[
|
| 888 |
+
73,
|
| 889 |
+
126
|
| 890 |
]
|
| 891 |
],
|
| 892 |
"classification_report": {
|
| 893 |
"NOT_RELEVANT": {
|
| 894 |
+
"precision": 0.9615587151132174,
|
| 895 |
+
"recall": 0.9687002652519894,
|
| 896 |
+
"f1-score": 0.9651162790697675,
|
| 897 |
+
"support": 1885.0
|
| 898 |
},
|
| 899 |
"RELEVANT": {
|
| 900 |
+
"precision": 0.6810810810810811,
|
| 901 |
+
"recall": 0.6331658291457286,
|
| 902 |
+
"f1-score": 0.65625,
|
| 903 |
+
"support": 199.0
|
| 904 |
},
|
| 905 |
+
"accuracy": 0.9366602687140115,
|
| 906 |
"macro avg": {
|
| 907 |
+
"precision": 0.8213198980971492,
|
| 908 |
+
"recall": 0.8009330471988589,
|
| 909 |
+
"f1-score": 0.8106831395348837,
|
| 910 |
+
"support": 2084.0
|
| 911 |
},
|
| 912 |
"weighted avg": {
|
| 913 |
+
"precision": 0.9347760619594769,
|
| 914 |
+
"recall": 0.9366602687140115,
|
| 915 |
+
"f1-score": 0.9356228100031246,
|
| 916 |
+
"support": 2084.0
|
| 917 |
}
|
| 918 |
},
|
| 919 |
+
"roc_auc": 0.9537208589365928,
|
| 920 |
+
"average_precision": 0.6689450933330522
|
| 921 |
},
|
| 922 |
"validation_optimal_threshold": {
|
| 923 |
+
"threshold": 0.08937255699326424,
|
| 924 |
+
"accuracy": 0.9328214971209213,
|
| 925 |
+
"precision": 0.6096654275092936,
|
| 926 |
+
"recall": 0.8241206030150754,
|
| 927 |
+
"f1": 0.7008547008547008,
|
| 928 |
"confusion_matrix": [
|
| 929 |
[
|
| 930 |
+
1780,
|
| 931 |
+
105
|
| 932 |
],
|
| 933 |
[
|
| 934 |
+
35,
|
| 935 |
+
164
|
| 936 |
]
|
| 937 |
],
|
| 938 |
"classification_report": {
|
| 939 |
"NOT_RELEVANT": {
|
| 940 |
+
"precision": 0.9807162534435262,
|
| 941 |
+
"recall": 0.9442970822281167,
|
| 942 |
+
"f1-score": 0.9621621621621622,
|
| 943 |
+
"support": 1885.0
|
| 944 |
},
|
| 945 |
"RELEVANT": {
|
| 946 |
+
"precision": 0.6096654275092936,
|
| 947 |
+
"recall": 0.8241206030150754,
|
| 948 |
+
"f1-score": 0.7008547008547008,
|
| 949 |
+
"support": 199.0
|
| 950 |
},
|
| 951 |
+
"accuracy": 0.9328214971209213,
|
| 952 |
"macro avg": {
|
| 953 |
+
"precision": 0.7951908404764099,
|
| 954 |
+
"recall": 0.884208842621596,
|
| 955 |
+
"f1-score": 0.8315084315084316,
|
| 956 |
+
"support": 2084.0
|
| 957 |
},
|
| 958 |
"weighted avg": {
|
| 959 |
+
"precision": 0.945284816610075,
|
| 960 |
+
"recall": 0.9328214971209213,
|
| 961 |
+
"f1-score": 0.9372100581313634,
|
| 962 |
+
"support": 2084.0
|
| 963 |
}
|
| 964 |
},
|
| 965 |
+
"roc_auc": 0.9537208589365928,
|
| 966 |
+
"average_precision": 0.6689450933330522
|
| 967 |
},
|
| 968 |
"test_default_0_5": {
|
| 969 |
"threshold": 0.5,
|
| 970 |
+
"accuracy": 0.9482262703739214,
|
| 971 |
+
"precision": 0.5789473684210527,
|
| 972 |
+
"recall": 0.5968992248062015,
|
| 973 |
+
"f1": 0.5877862595419847,
|
| 974 |
"confusion_matrix": [
|
| 975 |
[
|
| 976 |
+
1901,
|
| 977 |
+
56
|
| 978 |
],
|
| 979 |
[
|
| 980 |
+
52,
|
| 981 |
+
77
|
| 982 |
]
|
| 983 |
],
|
| 984 |
"classification_report": {
|
| 985 |
"NOT_RELEVANT": {
|
| 986 |
+
"precision": 0.9733742959549411,
|
| 987 |
+
"recall": 0.9713847726111395,
|
| 988 |
+
"f1-score": 0.972378516624041,
|
| 989 |
+
"support": 1957.0
|
| 990 |
},
|
| 991 |
"RELEVANT": {
|
| 992 |
+
"precision": 0.5789473684210527,
|
| 993 |
+
"recall": 0.5968992248062015,
|
| 994 |
+
"f1-score": 0.5877862595419847,
|
| 995 |
+
"support": 129.0
|
| 996 |
},
|
| 997 |
+
"accuracy": 0.9482262703739214,
|
| 998 |
"macro avg": {
|
| 999 |
+
"precision": 0.7761608321879969,
|
| 1000 |
+
"recall": 0.7841419987086705,
|
| 1001 |
+
"f1-score": 0.7800823880830128,
|
| 1002 |
+
"support": 2086.0
|
| 1003 |
},
|
| 1004 |
"weighted avg": {
|
| 1005 |
+
"precision": 0.948982601970343,
|
| 1006 |
+
"recall": 0.9482262703739214,
|
| 1007 |
+
"f1-score": 0.9485950069578927,
|
| 1008 |
+
"support": 2086.0
|
| 1009 |
}
|
| 1010 |
},
|
| 1011 |
+
"roc_auc": 0.9484498104597687,
|
| 1012 |
+
"average_precision": 0.5852438412769653
|
| 1013 |
},
|
| 1014 |
"test_optimal_threshold": {
|
| 1015 |
+
"threshold": 0.08937255699326424,
|
| 1016 |
+
"accuracy": 0.9324065196548418,
|
| 1017 |
+
"precision": 0.4716981132075472,
|
| 1018 |
+
"recall": 0.7751937984496124,
|
| 1019 |
+
"f1": 0.5865102639296188,
|
| 1020 |
"confusion_matrix": [
|
| 1021 |
[
|
| 1022 |
+
1845,
|
| 1023 |
+
112
|
| 1024 |
],
|
| 1025 |
[
|
| 1026 |
+
29,
|
| 1027 |
+
100
|
| 1028 |
]
|
| 1029 |
],
|
| 1030 |
"classification_report": {
|
| 1031 |
"NOT_RELEVANT": {
|
| 1032 |
+
"precision": 0.9845250800426895,
|
| 1033 |
+
"recall": 0.942769545222279,
|
| 1034 |
+
"f1-score": 0.9631949882537196,
|
| 1035 |
+
"support": 1957.0
|
| 1036 |
},
|
| 1037 |
"RELEVANT": {
|
| 1038 |
+
"precision": 0.4716981132075472,
|
| 1039 |
+
"recall": 0.7751937984496124,
|
| 1040 |
+
"f1-score": 0.5865102639296188,
|
| 1041 |
+
"support": 129.0
|
| 1042 |
},
|
| 1043 |
+
"accuracy": 0.9324065196548418,
|
| 1044 |
"macro avg": {
|
| 1045 |
+
"precision": 0.7281115966251184,
|
| 1046 |
+
"recall": 0.8589816718359458,
|
| 1047 |
+
"f1-score": 0.7748526260916693,
|
| 1048 |
+
"support": 2086.0
|
| 1049 |
},
|
| 1050 |
"weighted avg": {
|
| 1051 |
+
"precision": 0.9528114277312162,
|
| 1052 |
+
"recall": 0.9324065196548418,
|
| 1053 |
+
"f1-score": 0.9399004870850672,
|
| 1054 |
+
"support": 2086.0
|
| 1055 |
}
|
| 1056 |
},
|
| 1057 |
+
"roc_auc": 0.9484498104597687,
|
| 1058 |
+
"average_precision": 0.5852438412769653
|
| 1059 |
}
|
| 1060 |
},
|
| 1061 |
{
|
|
|
|
| 1063 |
"model_name": "FacebookAI/xlm-roberta-base",
|
| 1064 |
"artifact_dir": "/content/agri-utilization-classifier/transformer",
|
| 1065 |
"validation_best_threshold": {
|
| 1066 |
+
"threshold": 0.5436205267906189,
|
| 1067 |
+
"f1": 0.6983372921615203,
|
| 1068 |
+
"precision": 0.6621621621621622,
|
| 1069 |
+
"recall": 0.7386934673366834
|
| 1070 |
},
|
| 1071 |
"validation_default_0_5": {
|
| 1072 |
"threshold": 0.5,
|
| 1073 |
+
"accuracy": 0.9376199616122841,
|
| 1074 |
+
"precision": 0.6533333333333333,
|
| 1075 |
+
"recall": 0.7386934673366834,
|
| 1076 |
+
"f1": 0.6933962264150944,
|
| 1077 |
"confusion_matrix": [
|
| 1078 |
[
|
| 1079 |
+
1807,
|
| 1080 |
+
78
|
| 1081 |
],
|
| 1082 |
[
|
| 1083 |
+
52,
|
| 1084 |
+
147
|
| 1085 |
]
|
| 1086 |
],
|
| 1087 |
"classification_report": {
|
| 1088 |
"NOT_RELEVANT": {
|
| 1089 |
+
"precision": 0.972027972027972,
|
| 1090 |
+
"recall": 0.9586206896551724,
|
| 1091 |
+
"f1-score": 0.9652777777777778,
|
| 1092 |
+
"support": 1885.0
|
| 1093 |
},
|
| 1094 |
"RELEVANT": {
|
| 1095 |
+
"precision": 0.6533333333333333,
|
| 1096 |
+
"recall": 0.7386934673366834,
|
| 1097 |
+
"f1-score": 0.6933962264150944,
|
| 1098 |
+
"support": 199.0
|
| 1099 |
},
|
| 1100 |
+
"accuracy": 0.9376199616122841,
|
| 1101 |
"macro avg": {
|
| 1102 |
+
"precision": 0.8126806526806527,
|
| 1103 |
+
"recall": 0.848657078495928,
|
| 1104 |
+
"f1-score": 0.8293370020964361,
|
| 1105 |
+
"support": 2084.0
|
| 1106 |
},
|
| 1107 |
"weighted avg": {
|
| 1108 |
+
"precision": 0.9415959983714303,
|
| 1109 |
+
"recall": 0.9376199616122841,
|
| 1110 |
+
"f1-score": 0.9393159597733756,
|
| 1111 |
+
"support": 2084.0
|
| 1112 |
}
|
| 1113 |
},
|
| 1114 |
+
"roc_auc": 0.9544433040534235,
|
| 1115 |
+
"average_precision": 0.7261778718910262
|
| 1116 |
},
|
| 1117 |
"validation_optimal_threshold": {
|
| 1118 |
+
"threshold": 0.5436205267906189,
|
| 1119 |
+
"accuracy": 0.9390595009596929,
|
| 1120 |
+
"precision": 0.6621621621621622,
|
| 1121 |
+
"recall": 0.7386934673366834,
|
| 1122 |
+
"f1": 0.6983372921615202,
|
| 1123 |
"confusion_matrix": [
|
| 1124 |
[
|
| 1125 |
+
1810,
|
| 1126 |
+
75
|
| 1127 |
],
|
| 1128 |
[
|
| 1129 |
+
52,
|
| 1130 |
+
147
|
| 1131 |
]
|
| 1132 |
],
|
| 1133 |
"classification_report": {
|
| 1134 |
"NOT_RELEVANT": {
|
| 1135 |
+
"precision": 0.9720730397422127,
|
| 1136 |
+
"recall": 0.9602122015915119,
|
| 1137 |
+
"f1-score": 0.9661062183079797,
|
| 1138 |
+
"support": 1885.0
|
| 1139 |
},
|
| 1140 |
"RELEVANT": {
|
| 1141 |
+
"precision": 0.6621621621621622,
|
| 1142 |
+
"recall": 0.7386934673366834,
|
| 1143 |
+
"f1-score": 0.6983372921615202,
|
| 1144 |
+
"support": 199.0
|
| 1145 |
},
|
| 1146 |
+
"accuracy": 0.9390595009596929,
|
| 1147 |
"macro avg": {
|
| 1148 |
+
"precision": 0.8171176009521874,
|
| 1149 |
+
"recall": 0.8494528344640977,
|
| 1150 |
+
"f1-score": 0.83222175523475,
|
| 1151 |
+
"support": 2084.0
|
| 1152 |
},
|
| 1153 |
"weighted avg": {
|
| 1154 |
+
"precision": 0.9424798225452693,
|
| 1155 |
+
"recall": 0.9390595009596929,
|
| 1156 |
+
"f1-score": 0.9405371125962977,
|
| 1157 |
+
"support": 2084.0
|
| 1158 |
}
|
| 1159 |
},
|
| 1160 |
+
"roc_auc": 0.9544433040534235,
|
| 1161 |
+
"average_precision": 0.7261778718910262
|
| 1162 |
},
|
| 1163 |
"test_default_0_5": {
|
| 1164 |
"threshold": 0.5,
|
| 1165 |
+
"accuracy": 0.9429530201342282,
|
| 1166 |
+
"precision": 0.532051282051282,
|
| 1167 |
+
"recall": 0.6434108527131783,
|
| 1168 |
+
"f1": 0.5824561403508772,
|
| 1169 |
"confusion_matrix": [
|
| 1170 |
[
|
| 1171 |
+
1884,
|
| 1172 |
+
73
|
| 1173 |
],
|
| 1174 |
[
|
| 1175 |
+
46,
|
| 1176 |
+
83
|
| 1177 |
]
|
| 1178 |
],
|
| 1179 |
"classification_report": {
|
| 1180 |
"NOT_RELEVANT": {
|
| 1181 |
+
"precision": 0.9761658031088083,
|
| 1182 |
+
"recall": 0.9626980071538068,
|
| 1183 |
+
"f1-score": 0.969385129920247,
|
| 1184 |
+
"support": 1957.0
|
| 1185 |
},
|
| 1186 |
"RELEVANT": {
|
| 1187 |
+
"precision": 0.532051282051282,
|
| 1188 |
+
"recall": 0.6434108527131783,
|
| 1189 |
+
"f1-score": 0.5824561403508772,
|
| 1190 |
+
"support": 129.0
|
| 1191 |
},
|
| 1192 |
+
"accuracy": 0.9429530201342282,
|
| 1193 |
"macro avg": {
|
| 1194 |
+
"precision": 0.7541085425800451,
|
| 1195 |
+
"recall": 0.8030544299334925,
|
| 1196 |
+
"f1-score": 0.7759206351355621,
|
| 1197 |
+
"support": 2086.0
|
| 1198 |
},
|
| 1199 |
"weighted avg": {
|
| 1200 |
+
"precision": 0.9487013864182902,
|
| 1201 |
+
"recall": 0.9429530201342282,
|
| 1202 |
+
"f1-score": 0.9454571147455353,
|
| 1203 |
+
"support": 2086.0
|
| 1204 |
}
|
| 1205 |
},
|
| 1206 |
+
"roc_auc": 0.9314030730472604,
|
| 1207 |
+
"average_precision": 0.4996827419378796
|
| 1208 |
},
|
| 1209 |
"test_optimal_threshold": {
|
| 1210 |
+
"threshold": 0.5436205267906189,
|
| 1211 |
+
"accuracy": 0.9424736337488016,
|
| 1212 |
+
"precision": 0.5290322580645161,
|
| 1213 |
+
"recall": 0.6356589147286822,
|
| 1214 |
+
"f1": 0.5774647887323944,
|
| 1215 |
"confusion_matrix": [
|
| 1216 |
[
|
| 1217 |
+
1884,
|
| 1218 |
+
73
|
| 1219 |
],
|
| 1220 |
[
|
| 1221 |
+
47,
|
| 1222 |
+
82
|
| 1223 |
]
|
| 1224 |
],
|
| 1225 |
"classification_report": {
|
| 1226 |
"NOT_RELEVANT": {
|
| 1227 |
+
"precision": 0.9756602796478508,
|
| 1228 |
+
"recall": 0.9626980071538068,
|
| 1229 |
+
"f1-score": 0.9691358024691358,
|
| 1230 |
+
"support": 1957.0
|
| 1231 |
},
|
| 1232 |
"RELEVANT": {
|
| 1233 |
+
"precision": 0.5290322580645161,
|
| 1234 |
+
"recall": 0.6356589147286822,
|
| 1235 |
+
"f1-score": 0.5774647887323944,
|
| 1236 |
+
"support": 129.0
|
| 1237 |
},
|
| 1238 |
+
"accuracy": 0.9424736337488016,
|
| 1239 |
"macro avg": {
|
| 1240 |
+
"precision": 0.7523462688561835,
|
| 1241 |
+
"recall": 0.7991784609412445,
|
| 1242 |
+
"f1-score": 0.7733002956007651,
|
| 1243 |
+
"support": 2086.0
|
| 1244 |
},
|
| 1245 |
"weighted avg": {
|
| 1246 |
+
"precision": 0.948040425964126,
|
| 1247 |
+
"recall": 0.9424736337488016,
|
| 1248 |
+
"f1-score": 0.944914536518973,
|
| 1249 |
+
"support": 2086.0
|
| 1250 |
}
|
| 1251 |
},
|
| 1252 |
+
"roc_auc": 0.9314030730472604,
|
| 1253 |
+
"average_precision": 0.4996827419378796
|
| 1254 |
}
|
| 1255 |
}
|
| 1256 |
]
|
transformer/checkpoint-1220/config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
"tie_word_embeddings": true,
|
| 35 |
-
"transformers_version": "5.
|
| 36 |
"type_vocab_size": 1,
|
| 37 |
"use_cache": false,
|
| 38 |
"vocab_size": 250002
|
|
|
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
"tie_word_embeddings": true,
|
| 35 |
+
"transformers_version": "5.10.2",
|
| 36 |
"type_vocab_size": 1,
|
| 37 |
"use_cache": false,
|
| 38 |
"vocab_size": 250002
|
transformer/checkpoint-1220/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1112205008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68cfdbf41602bef3dad433cc9d7341026e15b6212a2de26b87cb1b08c92fe53a
|
| 3 |
size 1112205008
|
transformer/checkpoint-1220/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2224532875
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b157f469e91a6d944690dc04579dbfd1df4cb7df1828e6737dc78b7100c6c9bd
|
| 3 |
size 2224532875
|
transformer/checkpoint-1220/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d539b8d76c8001da486adb60fe77a06b1ad89abe54968b00e74e6fe0a65f76a4
|
| 3 |
size 14645
|
transformer/checkpoint-1220/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0d6ec924d72ca240bed6d2851cb98eda1484e26fe7cbfd21e9c5ca01087e280
|
| 3 |
size 1383
|
transformer/checkpoint-1220/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9b7df4afd103514fe9d65c0bed1c50f1ab1e4c492ac4aaea616afc5f70bab7e
|
| 3 |
size 1465
|
transformer/checkpoint-1220/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1220,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,396 +10,370 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 25
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 75
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 100
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 125
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm": 2.
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 150
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate": 1.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 175
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 1.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 200
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate": 1.
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 225
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 250
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm":
|
| 85 |
-
"learning_rate": 1.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 275
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"grad_norm":
|
| 92 |
-
"learning_rate": 1.
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 300
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch":
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"eval_precision": 0.7721518987341772,
|
| 102 |
-
"eval_recall": 0.7721518987341772,
|
| 103 |
-
"eval_roc_auc": 0.9563720589684741,
|
| 104 |
-
"eval_runtime": 3.3396,
|
| 105 |
-
"eval_samples_per_second": 292.853,
|
| 106 |
-
"eval_steps_per_second": 9.283,
|
| 107 |
-
"step": 305
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 1.0655737704918034,
|
| 111 |
-
"grad_norm": 0.5402449369430542,
|
| 112 |
-
"learning_rate": 1.7494537509104153e-05,
|
| 113 |
-
"loss": 0.1241053295135498,
|
| 114 |
"step": 325
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate": 1.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 350
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 375
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate": 1.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 400
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate": 1.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 425
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate": 1.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 450
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 1.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 475
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate": 1.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 500
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 1.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 525
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate": 1.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 550
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate": 1.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 575
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate": 1.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 600
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"eval_accuracy": 0.
|
| 196 |
-
"eval_f1": 0.
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_precision": 0.
|
| 199 |
-
"eval_recall": 0.
|
| 200 |
-
"eval_roc_auc": 0.
|
| 201 |
-
"eval_runtime":
|
| 202 |
-
"eval_samples_per_second":
|
| 203 |
-
"eval_steps_per_second":
|
| 204 |
"step": 610
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch":
|
| 208 |
-
"grad_norm":
|
| 209 |
-
"learning_rate": 1.
|
| 210 |
-
"loss": 0.
|
| 211 |
"step": 625
|
| 212 |
},
|
| 213 |
{
|
| 214 |
-
"epoch":
|
| 215 |
-
"grad_norm": 0.
|
| 216 |
-
"learning_rate": 1.
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 650
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"grad_norm":
|
| 223 |
-
"learning_rate": 1.
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 675
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"grad_norm":
|
| 230 |
-
"learning_rate": 1.
|
| 231 |
-
"loss": 0.
|
| 232 |
"step": 700
|
| 233 |
},
|
| 234 |
{
|
| 235 |
-
"epoch":
|
| 236 |
-
"grad_norm": 0.
|
| 237 |
-
"learning_rate": 1.
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 725
|
| 240 |
},
|
| 241 |
{
|
| 242 |
-
"epoch":
|
| 243 |
-
"grad_norm": 4.
|
| 244 |
-
"learning_rate": 1.
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 750
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch":
|
| 250 |
-
"grad_norm":
|
| 251 |
-
"learning_rate": 1.
|
| 252 |
-
"loss": 0.
|
| 253 |
"step": 775
|
| 254 |
},
|
| 255 |
{
|
| 256 |
-
"epoch":
|
| 257 |
-
"grad_norm":
|
| 258 |
-
"learning_rate": 1.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 800
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch":
|
| 264 |
-
"grad_norm": 0.
|
| 265 |
-
"learning_rate": 1.
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 825
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"grad_norm":
|
| 272 |
-
"learning_rate":
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 850
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch":
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
-
"learning_rate":
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 875
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
-
"learning_rate":
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 900
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch":
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
| 295 |
-
"eval_precision": 0.7976190476190477,
|
| 296 |
-
"eval_recall": 0.8481012658227848,
|
| 297 |
-
"eval_roc_auc": 0.9661086157615353,
|
| 298 |
-
"eval_runtime": 3.1733,
|
| 299 |
-
"eval_samples_per_second": 308.193,
|
| 300 |
-
"eval_steps_per_second": 9.769,
|
| 301 |
-
"step": 915
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 3.0327868852459017,
|
| 305 |
-
"grad_norm": 1.0706992149353027,
|
| 306 |
-
"learning_rate": 8.754552075746541e-06,
|
| 307 |
-
"loss": 0.10751664161682128,
|
| 308 |
"step": 925
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch":
|
| 312 |
-
"grad_norm":
|
| 313 |
-
"learning_rate":
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 950
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch":
|
| 319 |
-
"grad_norm":
|
| 320 |
-
"learning_rate":
|
| 321 |
-
"loss": 0.
|
| 322 |
"step": 975
|
| 323 |
},
|
| 324 |
{
|
| 325 |
-
"epoch":
|
| 326 |
-
"grad_norm":
|
| 327 |
-
"learning_rate":
|
| 328 |
-
"loss": 0.
|
| 329 |
"step": 1000
|
| 330 |
},
|
| 331 |
{
|
| 332 |
-
"epoch":
|
| 333 |
-
"grad_norm":
|
| 334 |
-
"learning_rate":
|
| 335 |
-
"loss": 0.
|
| 336 |
"step": 1025
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch":
|
| 340 |
-
"grad_norm":
|
| 341 |
-
"learning_rate":
|
| 342 |
-
"loss": 0.
|
| 343 |
"step": 1050
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch":
|
| 347 |
-
"grad_norm":
|
| 348 |
-
"learning_rate":
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 1075
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch":
|
| 354 |
-
"grad_norm": 0.
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 1100
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"grad_norm":
|
| 362 |
-
"learning_rate":
|
| 363 |
-
"loss": 0.
|
| 364 |
"step": 1125
|
| 365 |
},
|
| 366 |
{
|
| 367 |
-
"epoch":
|
| 368 |
-
"grad_norm":
|
| 369 |
-
"learning_rate":
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 1150
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch":
|
| 375 |
-
"grad_norm":
|
| 376 |
-
"learning_rate":
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 1175
|
| 379 |
},
|
| 380 |
{
|
| 381 |
-
"epoch":
|
| 382 |
-
"grad_norm":
|
| 383 |
-
"learning_rate":
|
| 384 |
-
"loss": 0.
|
| 385 |
"step": 1200
|
| 386 |
},
|
| 387 |
{
|
| 388 |
-
"epoch":
|
| 389 |
-
"eval_accuracy": 0.
|
| 390 |
-
"eval_f1": 0.
|
| 391 |
-
"eval_loss": 0.
|
| 392 |
-
"eval_precision": 0.
|
| 393 |
-
"eval_recall": 0.
|
| 394 |
-
"eval_roc_auc": 0.
|
| 395 |
-
"eval_runtime":
|
| 396 |
-
"eval_samples_per_second":
|
| 397 |
-
"eval_steps_per_second":
|
| 398 |
"step": 1220
|
| 399 |
}
|
| 400 |
],
|
| 401 |
"logging_steps": 25,
|
| 402 |
-
"max_steps":
|
| 403 |
"num_input_tokens_seen": 0,
|
| 404 |
"num_train_epochs": 5,
|
| 405 |
"save_steps": 500,
|
|
@@ -424,7 +398,7 @@
|
|
| 424 |
"attributes": {}
|
| 425 |
}
|
| 426 |
},
|
| 427 |
-
"total_flos":
|
| 428 |
"train_batch_size": 16,
|
| 429 |
"trial_name": null,
|
| 430 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 610,
|
| 3 |
+
"best_metric": 0.6933962264150944,
|
| 4 |
+
"best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-610",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1220,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.040983606557377046,
|
| 14 |
+
"grad_norm": 3.1041932106018066,
|
| 15 |
+
"learning_rate": 1.573770491803279e-06,
|
| 16 |
+
"loss": 0.526744384765625,
|
| 17 |
"step": 25
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.08196721311475409,
|
| 21 |
+
"grad_norm": 4.816498279571533,
|
| 22 |
+
"learning_rate": 3.213114754098361e-06,
|
| 23 |
+
"loss": 0.46380462646484377,
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.12295081967213115,
|
| 28 |
+
"grad_norm": 5.105863571166992,
|
| 29 |
+
"learning_rate": 4.8524590163934435e-06,
|
| 30 |
+
"loss": 0.3628129577636719,
|
| 31 |
"step": 75
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.16393442622950818,
|
| 35 |
+
"grad_norm": 3.479628324508667,
|
| 36 |
+
"learning_rate": 6.491803278688526e-06,
|
| 37 |
+
"loss": 0.3321057891845703,
|
| 38 |
"step": 100
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.20491803278688525,
|
| 42 |
+
"grad_norm": 5.271286487579346,
|
| 43 |
+
"learning_rate": 8.131147540983607e-06,
|
| 44 |
+
"loss": 0.29200584411621094,
|
| 45 |
"step": 125
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.2459016393442623,
|
| 49 |
+
"grad_norm": 2.9103591442108154,
|
| 50 |
+
"learning_rate": 9.770491803278689e-06,
|
| 51 |
+
"loss": 0.20765865325927735,
|
| 52 |
"step": 150
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.28688524590163933,
|
| 56 |
+
"grad_norm": 5.441774845123291,
|
| 57 |
+
"learning_rate": 1.1409836065573771e-05,
|
| 58 |
+
"loss": 0.22107566833496095,
|
| 59 |
"step": 175
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.32786885245901637,
|
| 63 |
+
"grad_norm": 17.181110382080078,
|
| 64 |
+
"learning_rate": 1.3049180327868853e-05,
|
| 65 |
+
"loss": 0.22224016189575196,
|
| 66 |
"step": 200
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.36885245901639346,
|
| 70 |
+
"grad_norm": 5.543371677398682,
|
| 71 |
+
"learning_rate": 1.4688524590163935e-05,
|
| 72 |
+
"loss": 0.20201002120971678,
|
| 73 |
"step": 225
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.4098360655737705,
|
| 77 |
+
"grad_norm": 5.812751770019531,
|
| 78 |
+
"learning_rate": 1.6327868852459016e-05,
|
| 79 |
+
"loss": 0.2299608612060547,
|
| 80 |
"step": 250
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.45081967213114754,
|
| 84 |
+
"grad_norm": 2.845670461654663,
|
| 85 |
+
"learning_rate": 1.79672131147541e-05,
|
| 86 |
+
"loss": 0.21673511505126952,
|
| 87 |
"step": 275
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.4918032786885246,
|
| 91 |
+
"grad_norm": 18.98938751220703,
|
| 92 |
+
"learning_rate": 1.9606557377049183e-05,
|
| 93 |
+
"loss": 0.21523273468017579,
|
| 94 |
"step": 300
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 0.5327868852459017,
|
| 98 |
+
"grad_norm": 5.82402229309082,
|
| 99 |
+
"learning_rate": 1.9861566484517306e-05,
|
| 100 |
+
"loss": 0.15432929039001464,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
"step": 325
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 0.5737704918032787,
|
| 105 |
+
"grad_norm": 0.48278993368148804,
|
| 106 |
+
"learning_rate": 1.9679417122040073e-05,
|
| 107 |
+
"loss": 0.16572830200195313,
|
| 108 |
"step": 350
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 0.6147540983606558,
|
| 112 |
+
"grad_norm": 5.946134567260742,
|
| 113 |
+
"learning_rate": 1.9497267759562843e-05,
|
| 114 |
+
"loss": 0.17543071746826172,
|
| 115 |
"step": 375
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 0.6557377049180327,
|
| 119 |
+
"grad_norm": 13.494661331176758,
|
| 120 |
+
"learning_rate": 1.9315118397085614e-05,
|
| 121 |
+
"loss": 0.15327459335327148,
|
| 122 |
"step": 400
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.6967213114754098,
|
| 126 |
+
"grad_norm": 9.058329582214355,
|
| 127 |
+
"learning_rate": 1.913296903460838e-05,
|
| 128 |
+
"loss": 0.19322505950927735,
|
| 129 |
"step": 425
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.7377049180327869,
|
| 133 |
+
"grad_norm": 9.420262336730957,
|
| 134 |
+
"learning_rate": 1.895081967213115e-05,
|
| 135 |
+
"loss": 0.18702877044677735,
|
| 136 |
"step": 450
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 0.7786885245901639,
|
| 140 |
+
"grad_norm": 0.29203546047210693,
|
| 141 |
+
"learning_rate": 1.8768670309653917e-05,
|
| 142 |
+
"loss": 0.13424430847167967,
|
| 143 |
"step": 475
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 0.819672131147541,
|
| 147 |
+
"grad_norm": 5.464226245880127,
|
| 148 |
+
"learning_rate": 1.8586520947176687e-05,
|
| 149 |
+
"loss": 0.1403522300720215,
|
| 150 |
"step": 500
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.860655737704918,
|
| 154 |
+
"grad_norm": 0.3305734395980835,
|
| 155 |
+
"learning_rate": 1.8404371584699454e-05,
|
| 156 |
+
"loss": 0.1768626403808594,
|
| 157 |
"step": 525
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 0.9016393442622951,
|
| 161 |
+
"grad_norm": 6.791965007781982,
|
| 162 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 163 |
+
"loss": 0.22005313873291016,
|
| 164 |
"step": 550
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.9426229508196722,
|
| 168 |
+
"grad_norm": 3.971740484237671,
|
| 169 |
+
"learning_rate": 1.804007285974499e-05,
|
| 170 |
+
"loss": 0.17844413757324218,
|
| 171 |
"step": 575
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.9836065573770492,
|
| 175 |
+
"grad_norm": 1.6787421703338623,
|
| 176 |
+
"learning_rate": 1.785792349726776e-05,
|
| 177 |
+
"loss": 0.16104537963867188,
|
| 178 |
"step": 600
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 1.0,
|
| 182 |
+
"eval_accuracy": 0.9376199616122841,
|
| 183 |
+
"eval_f1": 0.6933962264150944,
|
| 184 |
+
"eval_loss": 0.17767289280891418,
|
| 185 |
+
"eval_precision": 0.6533333333333333,
|
| 186 |
+
"eval_recall": 0.7386934673366834,
|
| 187 |
+
"eval_roc_auc": 0.9544433040534235,
|
| 188 |
+
"eval_runtime": 8.7237,
|
| 189 |
+
"eval_samples_per_second": 238.89,
|
| 190 |
+
"eval_steps_per_second": 7.566,
|
| 191 |
"step": 610
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 1.0245901639344261,
|
| 195 |
+
"grad_norm": 5.573081016540527,
|
| 196 |
+
"learning_rate": 1.7675774134790528e-05,
|
| 197 |
+
"loss": 0.10441858291625977,
|
| 198 |
"step": 625
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.0655737704918034,
|
| 202 |
+
"grad_norm": 0.11036327481269836,
|
| 203 |
+
"learning_rate": 1.7493624772313298e-05,
|
| 204 |
+
"loss": 0.16641632080078125,
|
| 205 |
"step": 650
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 1.1065573770491803,
|
| 209 |
+
"grad_norm": 6.172032833099365,
|
| 210 |
+
"learning_rate": 1.731147540983607e-05,
|
| 211 |
+
"loss": 0.14472474098205568,
|
| 212 |
"step": 675
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 1.1475409836065573,
|
| 216 |
+
"grad_norm": 5.863953113555908,
|
| 217 |
+
"learning_rate": 1.7129326047358835e-05,
|
| 218 |
+
"loss": 0.1113892936706543,
|
| 219 |
"step": 700
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.1885245901639343,
|
| 223 |
+
"grad_norm": 0.25357893109321594,
|
| 224 |
+
"learning_rate": 1.6947176684881602e-05,
|
| 225 |
+
"loss": 0.12171897888183594,
|
| 226 |
"step": 725
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 1.2295081967213115,
|
| 230 |
+
"grad_norm": 4.559972763061523,
|
| 231 |
+
"learning_rate": 1.6765027322404372e-05,
|
| 232 |
+
"loss": 0.08190732002258301,
|
| 233 |
"step": 750
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 1.2704918032786885,
|
| 237 |
+
"grad_norm": 5.443191051483154,
|
| 238 |
+
"learning_rate": 1.6582877959927142e-05,
|
| 239 |
+
"loss": 0.06097976684570312,
|
| 240 |
"step": 775
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 1.3114754098360657,
|
| 244 |
+
"grad_norm": 7.672996997833252,
|
| 245 |
+
"learning_rate": 1.6400728597449912e-05,
|
| 246 |
+
"loss": 0.09989359855651855,
|
| 247 |
"step": 800
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 1.3524590163934427,
|
| 251 |
+
"grad_norm": 0.30564695596694946,
|
| 252 |
+
"learning_rate": 1.621857923497268e-05,
|
| 253 |
+
"loss": 0.08488804817199708,
|
| 254 |
"step": 825
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 1.3934426229508197,
|
| 258 |
+
"grad_norm": 0.5056689977645874,
|
| 259 |
+
"learning_rate": 1.6036429872495446e-05,
|
| 260 |
+
"loss": 0.15551289558410644,
|
| 261 |
"step": 850
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 1.4344262295081966,
|
| 265 |
+
"grad_norm": 0.06402106583118439,
|
| 266 |
+
"learning_rate": 1.5854280510018216e-05,
|
| 267 |
+
"loss": 0.1194021987915039,
|
| 268 |
"step": 875
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 1.4754098360655736,
|
| 272 |
+
"grad_norm": 0.8240995407104492,
|
| 273 |
+
"learning_rate": 1.5672131147540986e-05,
|
| 274 |
+
"loss": 0.11723342895507813,
|
| 275 |
"step": 900
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 1.5163934426229508,
|
| 279 |
+
"grad_norm": 0.07588805258274078,
|
| 280 |
+
"learning_rate": 1.5489981785063753e-05,
|
| 281 |
+
"loss": 0.12805092811584473,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 282 |
"step": 925
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 1.5573770491803278,
|
| 286 |
+
"grad_norm": 29.323896408081055,
|
| 287 |
+
"learning_rate": 1.5307832422586523e-05,
|
| 288 |
+
"loss": 0.15534672737121583,
|
| 289 |
"step": 950
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 1.598360655737705,
|
| 293 |
+
"grad_norm": 11.02952766418457,
|
| 294 |
+
"learning_rate": 1.512568306010929e-05,
|
| 295 |
+
"loss": 0.1811429214477539,
|
| 296 |
"step": 975
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 1.639344262295082,
|
| 300 |
+
"grad_norm": 0.9738644957542419,
|
| 301 |
+
"learning_rate": 1.494353369763206e-05,
|
| 302 |
+
"loss": 0.1270007610321045,
|
| 303 |
"step": 1000
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 1.680327868852459,
|
| 307 |
+
"grad_norm": 2.311349630355835,
|
| 308 |
+
"learning_rate": 1.4761384335154829e-05,
|
| 309 |
+
"loss": 0.1843573570251465,
|
| 310 |
"step": 1025
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 1.721311475409836,
|
| 314 |
+
"grad_norm": 7.105762004852295,
|
| 315 |
+
"learning_rate": 1.4579234972677595e-05,
|
| 316 |
+
"loss": 0.15470240592956544,
|
| 317 |
"step": 1050
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 1.762295081967213,
|
| 321 |
+
"grad_norm": 9.120081901550293,
|
| 322 |
+
"learning_rate": 1.4397085610200366e-05,
|
| 323 |
+
"loss": 0.1170622444152832,
|
| 324 |
"step": 1075
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 1.8032786885245902,
|
| 328 |
+
"grad_norm": 0.09794076532125473,
|
| 329 |
+
"learning_rate": 1.4214936247723134e-05,
|
| 330 |
+
"loss": 0.14307721138000487,
|
| 331 |
"step": 1100
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 1.8442622950819674,
|
| 335 |
+
"grad_norm": 10.330300331115723,
|
| 336 |
+
"learning_rate": 1.4032786885245904e-05,
|
| 337 |
+
"loss": 0.15037315368652343,
|
| 338 |
"step": 1125
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 1.8852459016393444,
|
| 342 |
+
"grad_norm": 0.7867186069488525,
|
| 343 |
+
"learning_rate": 1.3850637522768671e-05,
|
| 344 |
+
"loss": 0.10941274642944336,
|
| 345 |
"step": 1150
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 1.9262295081967213,
|
| 349 |
+
"grad_norm": 7.952847003936768,
|
| 350 |
+
"learning_rate": 1.366848816029144e-05,
|
| 351 |
+
"loss": 0.1380799674987793,
|
| 352 |
"step": 1175
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 1.9672131147540983,
|
| 356 |
+
"grad_norm": 11.602045059204102,
|
| 357 |
+
"learning_rate": 1.348633879781421e-05,
|
| 358 |
+
"loss": 0.07221244812011719,
|
| 359 |
"step": 1200
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 2.0,
|
| 363 |
+
"eval_accuracy": 0.935700575815739,
|
| 364 |
+
"eval_f1": 0.6854460093896714,
|
| 365 |
+
"eval_loss": 0.24323046207427979,
|
| 366 |
+
"eval_precision": 0.6431718061674009,
|
| 367 |
+
"eval_recall": 0.7336683417085427,
|
| 368 |
+
"eval_roc_auc": 0.9480599282886581,
|
| 369 |
+
"eval_runtime": 8.6243,
|
| 370 |
+
"eval_samples_per_second": 241.642,
|
| 371 |
+
"eval_steps_per_second": 7.653,
|
| 372 |
"step": 1220
|
| 373 |
}
|
| 374 |
],
|
| 375 |
"logging_steps": 25,
|
| 376 |
+
"max_steps": 3050,
|
| 377 |
"num_input_tokens_seen": 0,
|
| 378 |
"num_train_epochs": 5,
|
| 379 |
"save_steps": 500,
|
|
|
|
| 398 |
"attributes": {}
|
| 399 |
}
|
| 400 |
},
|
| 401 |
+
"total_flos": 2566122122926080.0,
|
| 402 |
"train_batch_size": 16,
|
| 403 |
"trial_name": null,
|
| 404 |
"trial_params": null
|
transformer/checkpoint-1220/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26170ff2d75562c83f88182ac9301ad3566752c384b38d15219d8c3352efbebb
|
| 3 |
+
size 5201
|
transformer/checkpoint-1830/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "NOT_RELEVANT",
|
| 16 |
+
"1": "RELEVANT"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"is_decoder": false,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"NOT_RELEVANT": 0,
|
| 23 |
+
"RELEVANT": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "xlm-roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"transformers_version": "5.10.2",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 250002
|
| 39 |
+
}
|
transformer/checkpoint-1830/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2d36571bab40691e34928937e3b6273dc9f93cd7ff5063c0b0f56f6c81c617e
|
| 3 |
+
size 1112205008
|
transformer/checkpoint-1830/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd40f5b113902e4d4d3cafce7879adf4a0cd4adc135b994b1df34ea3f00be36d
|
| 3 |
+
size 2224532875
|
transformer/checkpoint-1830/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:396753321c3a3c714b0c16546663b596b2b7dc320914daeff4f4502205877de5
|
| 3 |
+
size 14645
|
transformer/checkpoint-1830/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e491b7c283e1accd9af8c8149230ddc3a5c9734dc7607b730682b67947f9d5a
|
| 3 |
+
size 1383
|
transformer/checkpoint-1830/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54b2dfae694f5d9051517fe489620541ef50f0d13ff4da58515c39d36e6dbf34
|
| 3 |
+
size 1465
|
transformer/checkpoint-1830/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc02d42fb2a10276563109e2287cc0dbe6b595d5b3b3401c7cfeffc0b7e20270
|
| 3 |
+
size 17098351
|
transformer/checkpoint-1830/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"mask_token": "<mask>",
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
transformer/checkpoint-1830/trainer_state.json
ADDED
|
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 610,
|
| 3 |
+
"best_metric": 0.6933962264150944,
|
| 4 |
+
"best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-610",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1830,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.040983606557377046,
|
| 14 |
+
"grad_norm": 3.1041932106018066,
|
| 15 |
+
"learning_rate": 1.573770491803279e-06,
|
| 16 |
+
"loss": 0.526744384765625,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08196721311475409,
|
| 21 |
+
"grad_norm": 4.816498279571533,
|
| 22 |
+
"learning_rate": 3.213114754098361e-06,
|
| 23 |
+
"loss": 0.46380462646484377,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12295081967213115,
|
| 28 |
+
"grad_norm": 5.105863571166992,
|
| 29 |
+
"learning_rate": 4.8524590163934435e-06,
|
| 30 |
+
"loss": 0.3628129577636719,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.16393442622950818,
|
| 35 |
+
"grad_norm": 3.479628324508667,
|
| 36 |
+
"learning_rate": 6.491803278688526e-06,
|
| 37 |
+
"loss": 0.3321057891845703,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.20491803278688525,
|
| 42 |
+
"grad_norm": 5.271286487579346,
|
| 43 |
+
"learning_rate": 8.131147540983607e-06,
|
| 44 |
+
"loss": 0.29200584411621094,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2459016393442623,
|
| 49 |
+
"grad_norm": 2.9103591442108154,
|
| 50 |
+
"learning_rate": 9.770491803278689e-06,
|
| 51 |
+
"loss": 0.20765865325927735,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.28688524590163933,
|
| 56 |
+
"grad_norm": 5.441774845123291,
|
| 57 |
+
"learning_rate": 1.1409836065573771e-05,
|
| 58 |
+
"loss": 0.22107566833496095,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.32786885245901637,
|
| 63 |
+
"grad_norm": 17.181110382080078,
|
| 64 |
+
"learning_rate": 1.3049180327868853e-05,
|
| 65 |
+
"loss": 0.22224016189575196,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.36885245901639346,
|
| 70 |
+
"grad_norm": 5.543371677398682,
|
| 71 |
+
"learning_rate": 1.4688524590163935e-05,
|
| 72 |
+
"loss": 0.20201002120971678,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4098360655737705,
|
| 77 |
+
"grad_norm": 5.812751770019531,
|
| 78 |
+
"learning_rate": 1.6327868852459016e-05,
|
| 79 |
+
"loss": 0.2299608612060547,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.45081967213114754,
|
| 84 |
+
"grad_norm": 2.845670461654663,
|
| 85 |
+
"learning_rate": 1.79672131147541e-05,
|
| 86 |
+
"loss": 0.21673511505126952,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.4918032786885246,
|
| 91 |
+
"grad_norm": 18.98938751220703,
|
| 92 |
+
"learning_rate": 1.9606557377049183e-05,
|
| 93 |
+
"loss": 0.21523273468017579,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5327868852459017,
|
| 98 |
+
"grad_norm": 5.82402229309082,
|
| 99 |
+
"learning_rate": 1.9861566484517306e-05,
|
| 100 |
+
"loss": 0.15432929039001464,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.5737704918032787,
|
| 105 |
+
"grad_norm": 0.48278993368148804,
|
| 106 |
+
"learning_rate": 1.9679417122040073e-05,
|
| 107 |
+
"loss": 0.16572830200195313,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6147540983606558,
|
| 112 |
+
"grad_norm": 5.946134567260742,
|
| 113 |
+
"learning_rate": 1.9497267759562843e-05,
|
| 114 |
+
"loss": 0.17543071746826172,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6557377049180327,
|
| 119 |
+
"grad_norm": 13.494661331176758,
|
| 120 |
+
"learning_rate": 1.9315118397085614e-05,
|
| 121 |
+
"loss": 0.15327459335327148,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.6967213114754098,
|
| 126 |
+
"grad_norm": 9.058329582214355,
|
| 127 |
+
"learning_rate": 1.913296903460838e-05,
|
| 128 |
+
"loss": 0.19322505950927735,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7377049180327869,
|
| 133 |
+
"grad_norm": 9.420262336730957,
|
| 134 |
+
"learning_rate": 1.895081967213115e-05,
|
| 135 |
+
"loss": 0.18702877044677735,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7786885245901639,
|
| 140 |
+
"grad_norm": 0.29203546047210693,
|
| 141 |
+
"learning_rate": 1.8768670309653917e-05,
|
| 142 |
+
"loss": 0.13424430847167967,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.819672131147541,
|
| 147 |
+
"grad_norm": 5.464226245880127,
|
| 148 |
+
"learning_rate": 1.8586520947176687e-05,
|
| 149 |
+
"loss": 0.1403522300720215,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.860655737704918,
|
| 154 |
+
"grad_norm": 0.3305734395980835,
|
| 155 |
+
"learning_rate": 1.8404371584699454e-05,
|
| 156 |
+
"loss": 0.1768626403808594,
|
| 157 |
+
"step": 525
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.9016393442622951,
|
| 161 |
+
"grad_norm": 6.791965007781982,
|
| 162 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 163 |
+
"loss": 0.22005313873291016,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9426229508196722,
|
| 168 |
+
"grad_norm": 3.971740484237671,
|
| 169 |
+
"learning_rate": 1.804007285974499e-05,
|
| 170 |
+
"loss": 0.17844413757324218,
|
| 171 |
+
"step": 575
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.9836065573770492,
|
| 175 |
+
"grad_norm": 1.6787421703338623,
|
| 176 |
+
"learning_rate": 1.785792349726776e-05,
|
| 177 |
+
"loss": 0.16104537963867188,
|
| 178 |
+
"step": 600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.0,
|
| 182 |
+
"eval_accuracy": 0.9376199616122841,
|
| 183 |
+
"eval_f1": 0.6933962264150944,
|
| 184 |
+
"eval_loss": 0.17767289280891418,
|
| 185 |
+
"eval_precision": 0.6533333333333333,
|
| 186 |
+
"eval_recall": 0.7386934673366834,
|
| 187 |
+
"eval_roc_auc": 0.9544433040534235,
|
| 188 |
+
"eval_runtime": 8.7237,
|
| 189 |
+
"eval_samples_per_second": 238.89,
|
| 190 |
+
"eval_steps_per_second": 7.566,
|
| 191 |
+
"step": 610
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0245901639344261,
|
| 195 |
+
"grad_norm": 5.573081016540527,
|
| 196 |
+
"learning_rate": 1.7675774134790528e-05,
|
| 197 |
+
"loss": 0.10441858291625977,
|
| 198 |
+
"step": 625
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.0655737704918034,
|
| 202 |
+
"grad_norm": 0.11036327481269836,
|
| 203 |
+
"learning_rate": 1.7493624772313298e-05,
|
| 204 |
+
"loss": 0.16641632080078125,
|
| 205 |
+
"step": 650
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1065573770491803,
|
| 209 |
+
"grad_norm": 6.172032833099365,
|
| 210 |
+
"learning_rate": 1.731147540983607e-05,
|
| 211 |
+
"loss": 0.14472474098205568,
|
| 212 |
+
"step": 675
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.1475409836065573,
|
| 216 |
+
"grad_norm": 5.863953113555908,
|
| 217 |
+
"learning_rate": 1.7129326047358835e-05,
|
| 218 |
+
"loss": 0.1113892936706543,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1885245901639343,
|
| 223 |
+
"grad_norm": 0.25357893109321594,
|
| 224 |
+
"learning_rate": 1.6947176684881602e-05,
|
| 225 |
+
"loss": 0.12171897888183594,
|
| 226 |
+
"step": 725
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2295081967213115,
|
| 230 |
+
"grad_norm": 4.559972763061523,
|
| 231 |
+
"learning_rate": 1.6765027322404372e-05,
|
| 232 |
+
"loss": 0.08190732002258301,
|
| 233 |
+
"step": 750
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2704918032786885,
|
| 237 |
+
"grad_norm": 5.443191051483154,
|
| 238 |
+
"learning_rate": 1.6582877959927142e-05,
|
| 239 |
+
"loss": 0.06097976684570312,
|
| 240 |
+
"step": 775
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3114754098360657,
|
| 244 |
+
"grad_norm": 7.672996997833252,
|
| 245 |
+
"learning_rate": 1.6400728597449912e-05,
|
| 246 |
+
"loss": 0.09989359855651855,
|
| 247 |
+
"step": 800
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3524590163934427,
|
| 251 |
+
"grad_norm": 0.30564695596694946,
|
| 252 |
+
"learning_rate": 1.621857923497268e-05,
|
| 253 |
+
"loss": 0.08488804817199708,
|
| 254 |
+
"step": 825
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.3934426229508197,
|
| 258 |
+
"grad_norm": 0.5056689977645874,
|
| 259 |
+
"learning_rate": 1.6036429872495446e-05,
|
| 260 |
+
"loss": 0.15551289558410644,
|
| 261 |
+
"step": 850
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.4344262295081966,
|
| 265 |
+
"grad_norm": 0.06402106583118439,
|
| 266 |
+
"learning_rate": 1.5854280510018216e-05,
|
| 267 |
+
"loss": 0.1194021987915039,
|
| 268 |
+
"step": 875
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.4754098360655736,
|
| 272 |
+
"grad_norm": 0.8240995407104492,
|
| 273 |
+
"learning_rate": 1.5672131147540986e-05,
|
| 274 |
+
"loss": 0.11723342895507813,
|
| 275 |
+
"step": 900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5163934426229508,
|
| 279 |
+
"grad_norm": 0.07588805258274078,
|
| 280 |
+
"learning_rate": 1.5489981785063753e-05,
|
| 281 |
+
"loss": 0.12805092811584473,
|
| 282 |
+
"step": 925
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.5573770491803278,
|
| 286 |
+
"grad_norm": 29.323896408081055,
|
| 287 |
+
"learning_rate": 1.5307832422586523e-05,
|
| 288 |
+
"loss": 0.15534672737121583,
|
| 289 |
+
"step": 950
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.598360655737705,
|
| 293 |
+
"grad_norm": 11.02952766418457,
|
| 294 |
+
"learning_rate": 1.512568306010929e-05,
|
| 295 |
+
"loss": 0.1811429214477539,
|
| 296 |
+
"step": 975
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.639344262295082,
|
| 300 |
+
"grad_norm": 0.9738644957542419,
|
| 301 |
+
"learning_rate": 1.494353369763206e-05,
|
| 302 |
+
"loss": 0.1270007610321045,
|
| 303 |
+
"step": 1000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.680327868852459,
|
| 307 |
+
"grad_norm": 2.311349630355835,
|
| 308 |
+
"learning_rate": 1.4761384335154829e-05,
|
| 309 |
+
"loss": 0.1843573570251465,
|
| 310 |
+
"step": 1025
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.721311475409836,
|
| 314 |
+
"grad_norm": 7.105762004852295,
|
| 315 |
+
"learning_rate": 1.4579234972677595e-05,
|
| 316 |
+
"loss": 0.15470240592956544,
|
| 317 |
+
"step": 1050
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.762295081967213,
|
| 321 |
+
"grad_norm": 9.120081901550293,
|
| 322 |
+
"learning_rate": 1.4397085610200366e-05,
|
| 323 |
+
"loss": 0.1170622444152832,
|
| 324 |
+
"step": 1075
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8032786885245902,
|
| 328 |
+
"grad_norm": 0.09794076532125473,
|
| 329 |
+
"learning_rate": 1.4214936247723134e-05,
|
| 330 |
+
"loss": 0.14307721138000487,
|
| 331 |
+
"step": 1100
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8442622950819674,
|
| 335 |
+
"grad_norm": 10.330300331115723,
|
| 336 |
+
"learning_rate": 1.4032786885245904e-05,
|
| 337 |
+
"loss": 0.15037315368652343,
|
| 338 |
+
"step": 1125
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.8852459016393444,
|
| 342 |
+
"grad_norm": 0.7867186069488525,
|
| 343 |
+
"learning_rate": 1.3850637522768671e-05,
|
| 344 |
+
"loss": 0.10941274642944336,
|
| 345 |
+
"step": 1150
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9262295081967213,
|
| 349 |
+
"grad_norm": 7.952847003936768,
|
| 350 |
+
"learning_rate": 1.366848816029144e-05,
|
| 351 |
+
"loss": 0.1380799674987793,
|
| 352 |
+
"step": 1175
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.9672131147540983,
|
| 356 |
+
"grad_norm": 11.602045059204102,
|
| 357 |
+
"learning_rate": 1.348633879781421e-05,
|
| 358 |
+
"loss": 0.07221244812011719,
|
| 359 |
+
"step": 1200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0,
|
| 363 |
+
"eval_accuracy": 0.935700575815739,
|
| 364 |
+
"eval_f1": 0.6854460093896714,
|
| 365 |
+
"eval_loss": 0.24323046207427979,
|
| 366 |
+
"eval_precision": 0.6431718061674009,
|
| 367 |
+
"eval_recall": 0.7336683417085427,
|
| 368 |
+
"eval_roc_auc": 0.9480599282886581,
|
| 369 |
+
"eval_runtime": 8.6243,
|
| 370 |
+
"eval_samples_per_second": 241.642,
|
| 371 |
+
"eval_steps_per_second": 7.653,
|
| 372 |
+
"step": 1220
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.0081967213114753,
|
| 376 |
+
"grad_norm": 4.202751636505127,
|
| 377 |
+
"learning_rate": 1.3304189435336978e-05,
|
| 378 |
+
"loss": 0.16997112274169923,
|
| 379 |
+
"step": 1225
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.0491803278688523,
|
| 383 |
+
"grad_norm": 0.40695664286613464,
|
| 384 |
+
"learning_rate": 1.3122040072859745e-05,
|
| 385 |
+
"loss": 0.0950162410736084,
|
| 386 |
+
"step": 1250
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.0901639344262297,
|
| 390 |
+
"grad_norm": 2.8617703914642334,
|
| 391 |
+
"learning_rate": 1.2939890710382515e-05,
|
| 392 |
+
"loss": 0.10194917678833008,
|
| 393 |
+
"step": 1275
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.1311475409836067,
|
| 397 |
+
"grad_norm": 0.08977202326059341,
|
| 398 |
+
"learning_rate": 1.2757741347905283e-05,
|
| 399 |
+
"loss": 0.0662102746963501,
|
| 400 |
+
"step": 1300
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.1721311475409837,
|
| 404 |
+
"grad_norm": 0.10930905491113663,
|
| 405 |
+
"learning_rate": 1.2575591985428054e-05,
|
| 406 |
+
"loss": 0.07460547924041748,
|
| 407 |
+
"step": 1325
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.2131147540983607,
|
| 411 |
+
"grad_norm": 11.703680038452148,
|
| 412 |
+
"learning_rate": 1.239344262295082e-05,
|
| 413 |
+
"loss": 0.11810153961181641,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.2540983606557377,
|
| 418 |
+
"grad_norm": 3.0462427139282227,
|
| 419 |
+
"learning_rate": 1.2211293260473589e-05,
|
| 420 |
+
"loss": 0.11896968841552734,
|
| 421 |
+
"step": 1375
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.2950819672131146,
|
| 425 |
+
"grad_norm": 11.854302406311035,
|
| 426 |
+
"learning_rate": 1.2029143897996359e-05,
|
| 427 |
+
"loss": 0.10016871452331542,
|
| 428 |
+
"step": 1400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.3360655737704916,
|
| 432 |
+
"grad_norm": 5.737449645996094,
|
| 433 |
+
"learning_rate": 1.1846994535519127e-05,
|
| 434 |
+
"loss": 0.12308047294616699,
|
| 435 |
+
"step": 1425
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.3770491803278686,
|
| 439 |
+
"grad_norm": 3.3703978061676025,
|
| 440 |
+
"learning_rate": 1.1664845173041894e-05,
|
| 441 |
+
"loss": 0.10508214950561523,
|
| 442 |
+
"step": 1450
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.418032786885246,
|
| 446 |
+
"grad_norm": 15.429414749145508,
|
| 447 |
+
"learning_rate": 1.1482695810564664e-05,
|
| 448 |
+
"loss": 0.05040365219116211,
|
| 449 |
+
"step": 1475
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.459016393442623,
|
| 453 |
+
"grad_norm": 14.725594520568848,
|
| 454 |
+
"learning_rate": 1.1300546448087433e-05,
|
| 455 |
+
"loss": 0.13564690589904785,
|
| 456 |
+
"step": 1500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.5,
|
| 460 |
+
"grad_norm": 0.18430812656879425,
|
| 461 |
+
"learning_rate": 1.1118397085610201e-05,
|
| 462 |
+
"loss": 0.08556642532348632,
|
| 463 |
+
"step": 1525
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.540983606557377,
|
| 467 |
+
"grad_norm": 0.062474410980939865,
|
| 468 |
+
"learning_rate": 1.0936247723132968e-05,
|
| 469 |
+
"loss": 0.08463016510009766,
|
| 470 |
+
"step": 1550
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.581967213114754,
|
| 474 |
+
"grad_norm": 0.20876172184944153,
|
| 475 |
+
"learning_rate": 1.0754098360655738e-05,
|
| 476 |
+
"loss": 0.1799280548095703,
|
| 477 |
+
"step": 1575
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.6229508196721314,
|
| 481 |
+
"grad_norm": 6.137902736663818,
|
| 482 |
+
"learning_rate": 1.0571948998178507e-05,
|
| 483 |
+
"loss": 0.12623875617980956,
|
| 484 |
+
"step": 1600
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.663934426229508,
|
| 488 |
+
"grad_norm": 17.05773162841797,
|
| 489 |
+
"learning_rate": 1.0389799635701277e-05,
|
| 490 |
+
"loss": 0.09255536079406738,
|
| 491 |
+
"step": 1625
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.7049180327868854,
|
| 495 |
+
"grad_norm": 1.2578394412994385,
|
| 496 |
+
"learning_rate": 1.0207650273224044e-05,
|
| 497 |
+
"loss": 0.0888406753540039,
|
| 498 |
+
"step": 1650
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.7459016393442623,
|
| 502 |
+
"grad_norm": 15.845796585083008,
|
| 503 |
+
"learning_rate": 1.0025500910746812e-05,
|
| 504 |
+
"loss": 0.10764387130737305,
|
| 505 |
+
"step": 1675
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.7868852459016393,
|
| 509 |
+
"grad_norm": 12.588105201721191,
|
| 510 |
+
"learning_rate": 9.843351548269582e-06,
|
| 511 |
+
"loss": 0.12151247024536133,
|
| 512 |
+
"step": 1700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.8278688524590163,
|
| 516 |
+
"grad_norm": 7.840113162994385,
|
| 517 |
+
"learning_rate": 9.66120218579235e-06,
|
| 518 |
+
"loss": 0.1787535858154297,
|
| 519 |
+
"step": 1725
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.8688524590163933,
|
| 523 |
+
"grad_norm": 5.082641124725342,
|
| 524 |
+
"learning_rate": 9.47905282331512e-06,
|
| 525 |
+
"loss": 0.07576138019561768,
|
| 526 |
+
"step": 1750
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.9098360655737707,
|
| 530 |
+
"grad_norm": 14.185094833374023,
|
| 531 |
+
"learning_rate": 9.296903460837888e-06,
|
| 532 |
+
"loss": 0.1186930274963379,
|
| 533 |
+
"step": 1775
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.9508196721311473,
|
| 537 |
+
"grad_norm": 31.60809898376465,
|
| 538 |
+
"learning_rate": 9.114754098360656e-06,
|
| 539 |
+
"loss": 0.10553586959838868,
|
| 540 |
+
"step": 1800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.9918032786885247,
|
| 544 |
+
"grad_norm": 2.9622690677642822,
|
| 545 |
+
"learning_rate": 8.932604735883426e-06,
|
| 546 |
+
"loss": 0.054716997146606446,
|
| 547 |
+
"step": 1825
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.0,
|
| 551 |
+
"eval_accuracy": 0.9414587332053743,
|
| 552 |
+
"eval_f1": 0.6903553299492385,
|
| 553 |
+
"eval_loss": 0.24261149764060974,
|
| 554 |
+
"eval_precision": 0.6974358974358974,
|
| 555 |
+
"eval_recall": 0.6834170854271356,
|
| 556 |
+
"eval_roc_auc": 0.9521560054916492,
|
| 557 |
+
"eval_runtime": 8.6527,
|
| 558 |
+
"eval_samples_per_second": 240.849,
|
| 559 |
+
"eval_steps_per_second": 7.628,
|
| 560 |
+
"step": 1830
|
| 561 |
+
}
|
| 562 |
+
],
|
| 563 |
+
"logging_steps": 25,
|
| 564 |
+
"max_steps": 3050,
|
| 565 |
+
"num_input_tokens_seen": 0,
|
| 566 |
+
"num_train_epochs": 5,
|
| 567 |
+
"save_steps": 500,
|
| 568 |
+
"stateful_callbacks": {
|
| 569 |
+
"EarlyStoppingCallback": {
|
| 570 |
+
"args": {
|
| 571 |
+
"early_stopping_patience": 2,
|
| 572 |
+
"early_stopping_threshold": 0.0
|
| 573 |
+
},
|
| 574 |
+
"attributes": {
|
| 575 |
+
"early_stopping_patience_counter": 2
|
| 576 |
+
}
|
| 577 |
+
},
|
| 578 |
+
"TrainerControl": {
|
| 579 |
+
"args": {
|
| 580 |
+
"should_epoch_stop": false,
|
| 581 |
+
"should_evaluate": false,
|
| 582 |
+
"should_log": false,
|
| 583 |
+
"should_save": true,
|
| 584 |
+
"should_training_stop": true
|
| 585 |
+
},
|
| 586 |
+
"attributes": {}
|
| 587 |
+
}
|
| 588 |
+
},
|
| 589 |
+
"total_flos": 3849183184389120.0,
|
| 590 |
+
"train_batch_size": 16,
|
| 591 |
+
"trial_name": null,
|
| 592 |
+
"trial_params": null
|
| 593 |
+
}
|
transformer/checkpoint-1830/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26170ff2d75562c83f88182ac9301ad3566752c384b38d15219d8c3352efbebb
|
| 3 |
+
size 5201
|
transformer/checkpoint-610/config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
"tie_word_embeddings": true,
|
| 35 |
-
"transformers_version": "5.
|
| 36 |
"type_vocab_size": 1,
|
| 37 |
"use_cache": false,
|
| 38 |
"vocab_size": 250002
|
|
|
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
"tie_word_embeddings": true,
|
| 35 |
+
"transformers_version": "5.10.2",
|
| 36 |
"type_vocab_size": 1,
|
| 37 |
"use_cache": false,
|
| 38 |
"vocab_size": 250002
|
transformer/checkpoint-610/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1112205008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:150736722d2137e368c215a6ded5ca83348b547235eed16e8939af8b89077765
|
| 3 |
size 1112205008
|
transformer/checkpoint-610/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2224532875
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e116ee1524d3a0af2639c7796fdc33da882323ef9133d8950b493efc3fdc234
|
| 3 |
size 2224532875
|
transformer/checkpoint-610/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f79ebe41a952d58a414acbb1200490974edd9f70a35228ee802fd1f53139fa66
|
| 3 |
size 14645
|
transformer/checkpoint-610/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e49d8c13a6eacfd8373ea54c57924180b7dfff65f37e60feb7ea51f503d158
|
| 3 |
size 1383
|
transformer/checkpoint-610/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3342a44ed126fda993f7f2d332ee7ff352916f58e467cf3c50397c3413bfcc8a
|
| 3 |
size 1465
|
transformer/checkpoint-610/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 610,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,202 +10,189 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 25
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 75
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 100
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 125
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm": 2.
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 150
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate": 1.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 175
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 1.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 200
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate": 1.
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 225
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 250
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"grad_norm":
|
| 85 |
-
"learning_rate": 1.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 275
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"grad_norm":
|
| 92 |
-
"learning_rate": 1.
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 300
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch":
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"eval_precision": 0.7721518987341772,
|
| 102 |
-
"eval_recall": 0.7721518987341772,
|
| 103 |
-
"eval_roc_auc": 0.9563720589684741,
|
| 104 |
-
"eval_runtime": 3.3396,
|
| 105 |
-
"eval_samples_per_second": 292.853,
|
| 106 |
-
"eval_steps_per_second": 9.283,
|
| 107 |
-
"step": 305
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 1.0655737704918034,
|
| 111 |
-
"grad_norm": 0.5402449369430542,
|
| 112 |
-
"learning_rate": 1.7494537509104153e-05,
|
| 113 |
-
"loss": 0.1241053295135498,
|
| 114 |
"step": 325
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate": 1.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 350
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 375
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate": 1.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 400
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate": 1.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 425
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate": 1.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 450
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 1.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 475
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate": 1.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 500
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 1.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 525
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate": 1.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 550
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate": 1.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 575
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate": 1.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 600
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"eval_accuracy": 0.
|
| 196 |
-
"eval_f1": 0.
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_precision": 0.
|
| 199 |
-
"eval_recall": 0.
|
| 200 |
-
"eval_roc_auc": 0.
|
| 201 |
-
"eval_runtime":
|
| 202 |
-
"eval_samples_per_second":
|
| 203 |
-
"eval_steps_per_second":
|
| 204 |
"step": 610
|
| 205 |
}
|
| 206 |
],
|
| 207 |
"logging_steps": 25,
|
| 208 |
-
"max_steps":
|
| 209 |
"num_input_tokens_seen": 0,
|
| 210 |
"num_train_epochs": 5,
|
| 211 |
"save_steps": 500,
|
|
@@ -216,7 +203,7 @@
|
|
| 216 |
"early_stopping_threshold": 0.0
|
| 217 |
},
|
| 218 |
"attributes": {
|
| 219 |
-
"early_stopping_patience_counter":
|
| 220 |
}
|
| 221 |
},
|
| 222 |
"TrainerControl": {
|
|
@@ -230,7 +217,7 @@
|
|
| 230 |
"attributes": {}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
-
"total_flos":
|
| 234 |
"train_batch_size": 16,
|
| 235 |
"trial_name": null,
|
| 236 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 610,
|
| 3 |
+
"best_metric": 0.6933962264150944,
|
| 4 |
+
"best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-610",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 610,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.040983606557377046,
|
| 14 |
+
"grad_norm": 3.1041932106018066,
|
| 15 |
+
"learning_rate": 1.573770491803279e-06,
|
| 16 |
+
"loss": 0.526744384765625,
|
| 17 |
"step": 25
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.08196721311475409,
|
| 21 |
+
"grad_norm": 4.816498279571533,
|
| 22 |
+
"learning_rate": 3.213114754098361e-06,
|
| 23 |
+
"loss": 0.46380462646484377,
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.12295081967213115,
|
| 28 |
+
"grad_norm": 5.105863571166992,
|
| 29 |
+
"learning_rate": 4.8524590163934435e-06,
|
| 30 |
+
"loss": 0.3628129577636719,
|
| 31 |
"step": 75
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.16393442622950818,
|
| 35 |
+
"grad_norm": 3.479628324508667,
|
| 36 |
+
"learning_rate": 6.491803278688526e-06,
|
| 37 |
+
"loss": 0.3321057891845703,
|
| 38 |
"step": 100
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.20491803278688525,
|
| 42 |
+
"grad_norm": 5.271286487579346,
|
| 43 |
+
"learning_rate": 8.131147540983607e-06,
|
| 44 |
+
"loss": 0.29200584411621094,
|
| 45 |
"step": 125
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.2459016393442623,
|
| 49 |
+
"grad_norm": 2.9103591442108154,
|
| 50 |
+
"learning_rate": 9.770491803278689e-06,
|
| 51 |
+
"loss": 0.20765865325927735,
|
| 52 |
"step": 150
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.28688524590163933,
|
| 56 |
+
"grad_norm": 5.441774845123291,
|
| 57 |
+
"learning_rate": 1.1409836065573771e-05,
|
| 58 |
+
"loss": 0.22107566833496095,
|
| 59 |
"step": 175
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.32786885245901637,
|
| 63 |
+
"grad_norm": 17.181110382080078,
|
| 64 |
+
"learning_rate": 1.3049180327868853e-05,
|
| 65 |
+
"loss": 0.22224016189575196,
|
| 66 |
"step": 200
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.36885245901639346,
|
| 70 |
+
"grad_norm": 5.543371677398682,
|
| 71 |
+
"learning_rate": 1.4688524590163935e-05,
|
| 72 |
+
"loss": 0.20201002120971678,
|
| 73 |
"step": 225
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.4098360655737705,
|
| 77 |
+
"grad_norm": 5.812751770019531,
|
| 78 |
+
"learning_rate": 1.6327868852459016e-05,
|
| 79 |
+
"loss": 0.2299608612060547,
|
| 80 |
"step": 250
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.45081967213114754,
|
| 84 |
+
"grad_norm": 2.845670461654663,
|
| 85 |
+
"learning_rate": 1.79672131147541e-05,
|
| 86 |
+
"loss": 0.21673511505126952,
|
| 87 |
"step": 275
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.4918032786885246,
|
| 91 |
+
"grad_norm": 18.98938751220703,
|
| 92 |
+
"learning_rate": 1.9606557377049183e-05,
|
| 93 |
+
"loss": 0.21523273468017579,
|
| 94 |
"step": 300
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 0.5327868852459017,
|
| 98 |
+
"grad_norm": 5.82402229309082,
|
| 99 |
+
"learning_rate": 1.9861566484517306e-05,
|
| 100 |
+
"loss": 0.15432929039001464,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
"step": 325
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 0.5737704918032787,
|
| 105 |
+
"grad_norm": 0.48278993368148804,
|
| 106 |
+
"learning_rate": 1.9679417122040073e-05,
|
| 107 |
+
"loss": 0.16572830200195313,
|
| 108 |
"step": 350
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 0.6147540983606558,
|
| 112 |
+
"grad_norm": 5.946134567260742,
|
| 113 |
+
"learning_rate": 1.9497267759562843e-05,
|
| 114 |
+
"loss": 0.17543071746826172,
|
| 115 |
"step": 375
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 0.6557377049180327,
|
| 119 |
+
"grad_norm": 13.494661331176758,
|
| 120 |
+
"learning_rate": 1.9315118397085614e-05,
|
| 121 |
+
"loss": 0.15327459335327148,
|
| 122 |
"step": 400
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.6967213114754098,
|
| 126 |
+
"grad_norm": 9.058329582214355,
|
| 127 |
+
"learning_rate": 1.913296903460838e-05,
|
| 128 |
+
"loss": 0.19322505950927735,
|
| 129 |
"step": 425
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.7377049180327869,
|
| 133 |
+
"grad_norm": 9.420262336730957,
|
| 134 |
+
"learning_rate": 1.895081967213115e-05,
|
| 135 |
+
"loss": 0.18702877044677735,
|
| 136 |
"step": 450
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 0.7786885245901639,
|
| 140 |
+
"grad_norm": 0.29203546047210693,
|
| 141 |
+
"learning_rate": 1.8768670309653917e-05,
|
| 142 |
+
"loss": 0.13424430847167967,
|
| 143 |
"step": 475
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 0.819672131147541,
|
| 147 |
+
"grad_norm": 5.464226245880127,
|
| 148 |
+
"learning_rate": 1.8586520947176687e-05,
|
| 149 |
+
"loss": 0.1403522300720215,
|
| 150 |
"step": 500
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.860655737704918,
|
| 154 |
+
"grad_norm": 0.3305734395980835,
|
| 155 |
+
"learning_rate": 1.8404371584699454e-05,
|
| 156 |
+
"loss": 0.1768626403808594,
|
| 157 |
"step": 525
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 0.9016393442622951,
|
| 161 |
+
"grad_norm": 6.791965007781982,
|
| 162 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 163 |
+
"loss": 0.22005313873291016,
|
| 164 |
"step": 550
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.9426229508196722,
|
| 168 |
+
"grad_norm": 3.971740484237671,
|
| 169 |
+
"learning_rate": 1.804007285974499e-05,
|
| 170 |
+
"loss": 0.17844413757324218,
|
| 171 |
"step": 575
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.9836065573770492,
|
| 175 |
+
"grad_norm": 1.6787421703338623,
|
| 176 |
+
"learning_rate": 1.785792349726776e-05,
|
| 177 |
+
"loss": 0.16104537963867188,
|
| 178 |
"step": 600
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 1.0,
|
| 182 |
+
"eval_accuracy": 0.9376199616122841,
|
| 183 |
+
"eval_f1": 0.6933962264150944,
|
| 184 |
+
"eval_loss": 0.17767289280891418,
|
| 185 |
+
"eval_precision": 0.6533333333333333,
|
| 186 |
+
"eval_recall": 0.7386934673366834,
|
| 187 |
+
"eval_roc_auc": 0.9544433040534235,
|
| 188 |
+
"eval_runtime": 8.7237,
|
| 189 |
+
"eval_samples_per_second": 238.89,
|
| 190 |
+
"eval_steps_per_second": 7.566,
|
| 191 |
"step": 610
|
| 192 |
}
|
| 193 |
],
|
| 194 |
"logging_steps": 25,
|
| 195 |
+
"max_steps": 3050,
|
| 196 |
"num_input_tokens_seen": 0,
|
| 197 |
"num_train_epochs": 5,
|
| 198 |
"save_steps": 500,
|
|
|
|
| 203 |
"early_stopping_threshold": 0.0
|
| 204 |
},
|
| 205 |
"attributes": {
|
| 206 |
+
"early_stopping_patience_counter": 0
|
| 207 |
}
|
| 208 |
},
|
| 209 |
"TrainerControl": {
|
|
|
|
| 217 |
"attributes": {}
|
| 218 |
}
|
| 219 |
},
|
| 220 |
+
"total_flos": 1283061061463040.0,
|
| 221 |
"train_batch_size": 16,
|
| 222 |
"trial_name": null,
|
| 223 |
"trial_params": null
|
transformer/checkpoint-610/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26170ff2d75562c83f88182ac9301ad3566752c384b38d15219d8c3352efbebb
|
| 3 |
+
size 5201
|
transformer/config.json
CHANGED
|
@@ -31,16 +31,16 @@
|
|
| 31 |
"pad_token_id": 1,
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
-
"threshold": 0.
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
-
"transformers_version": "5.
|
| 37 |
"type_vocab_size": 1,
|
| 38 |
"use_cache": false,
|
| 39 |
"validation_threshold_report": {
|
| 40 |
-
"f1": 0.
|
| 41 |
-
"precision": 0.
|
| 42 |
-
"recall": 0.
|
| 43 |
-
"threshold": 0.
|
| 44 |
},
|
| 45 |
"vocab_size": 250002
|
| 46 |
}
|
|
|
|
| 31 |
"pad_token_id": 1,
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
| 34 |
+
"threshold": 0.5436205267906189,
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
+
"transformers_version": "5.10.2",
|
| 37 |
"type_vocab_size": 1,
|
| 38 |
"use_cache": false,
|
| 39 |
"validation_threshold_report": {
|
| 40 |
+
"f1": 0.6983372921615203,
|
| 41 |
+
"precision": 0.6621621621621622,
|
| 42 |
+
"recall": 0.7386934673366834,
|
| 43 |
+
"threshold": 0.5436205267906189
|
| 44 |
},
|
| 45 |
"vocab_size": 250002
|
| 46 |
}
|
transformer/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1112205008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:150736722d2137e368c215a6ded5ca83348b547235eed16e8939af8b89077765
|
| 3 |
size 1112205008
|
transformer/test_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26170ff2d75562c83f88182ac9301ad3566752c384b38d15219d8c3352efbebb
|
| 3 |
+
size 5201
|
transformer/validation_predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|