Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,167 @@
+# AI Detector LoRA (DeBERTa-v3-large)
+
+LoRA adapter for binary AI-text vs Human-text detection, trained on ~2.3M English samples
+(`label: 1 = AI, 0 = Human`) using `microsoft/deberta-v3-large` as the base model.
+
+- **Base model:** `microsoft/deberta-v3-large`
+- **Task:** Binary classification (AI vs Human)
+- **Head:** Single-logit + `BCEWithLogitsLoss`
+- **Adapter type:** LoRA (`peft`)
+- **Hardware:** H100 SXM, bf16, multi-GPU
+- **Final decision threshold:** **0.9033** (max-F1 on validation)
+
+---
+
+## Files in this repo
+
+- `adapter/` – LoRA weights saved with `peft_model.save_pretrained(...)`
+- `threshold.json` – chosen deployment threshold and validation F1
+- `results.json` – hyperparameters, validation threshold search, test metrics
+- `training_log_history.csv` – raw Trainer log history
+- `predictions_val.csv` – validation probabilities and labels
+- `predictions_test.csv` – test probabilities and labels
+- `figures/` – training and evaluation plots
+- `README.md` – this file
+
+---
+
+## Metrics (test set)
+
+Using threshold **0.9033**:
+
+| Metric        | Value   |
+|--------------|---------|
+| AUROC        | 0.9970  |
+| Average Precision (AP) | 0.9966 |
+| F1           | 0.9740  |
+| Accuracy     | 0.9767  |
+| Precision    | 0.9857  |
+| Recall       | 0.9625  |
+| Specificity  | 0.9884  |
+
+Confusion matrix (test):
+
+- **True Negatives (Human correctly)**: 123,399  
+- **False Positives (Human → AI)**: 1,449  
+- **False Negatives (AI → Human)**: 3,882  
+- **True Positives (AI correctly)**: 99,657  
+
+---
+
+## Plots
+
+### Training & validation
+
+- Learning curves:
+
+  ![Learning curves](./figures/fig_learning_curves.png)
+
+- Eval metrics over time:
+
+  ![Eval metrics](./figures/fig_eval_metrics.png)
+
+### Validation set
+
+- ROC:
+
+  ![ROC (val)](./figures/fig_roc_val.png)
+
+- Precision–Recall:
+
+  ![PR (val)](./figures/fig_pr_val.png)
+
+- Calibration curve:
+
+  ![Calibration (val)](./figures/fig_calibration_val.png)
+
+- F1 vs threshold:
+
+  ![F1 vs threshold (val)](./figures/fig_threshold_f1_val.png)
+
+### Test set
+
+- ROC:
+
+  ![ROC (test)](./figures/fig_roc_test.png)
+
+- Precision–Recall:
+
+  ![PR (test)](./figures/fig_pr_test.png)
+
+- Calibration curve:
+
+  ![Calibration (test)](./figures/fig_calibration_test.png)
+
+- Confusion matrix:
+
+  ![Confusion matrix (test)](./figures/fig_confusion_test.png)
+
+---
+
+## Usage
+
+### Load base + LoRA adapter
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from peft import PeftModel
+import torch
+import json
+
+base_model_id = "microsoft/deberta-v3-large"
+adapter_id    = "<your-username>/<your-private-repo>"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+
+base_model = AutoModelForSequenceClassification.from_pretrained(
+    base_model_id,
+    num_labels=1,  # single logit for BCEWithLogitsLoss
+)
+model = PeftModel.from_pretrained(base_model, adapter_id)
+model.eval()
+````
+
+### Inference with threshold
+
+```python
+# load threshold
+with open("threshold.json") as f:
+    thr = json.load(f)["threshold"]  # 0.9033
+
+def predict_proba(texts):
+    enc = tokenizer(
+        texts,
+        padding=True,
+        truncation=True,
+        max_length=512,
+        return_tensors="pt",
+    )
+    with torch.no_grad():
+        logits = model(**enc).logits.squeeze(-1)
+        probs = torch.sigmoid(logits)
+    return probs.cpu().numpy()
+
+def predict_label(texts, threshold=thr):
+    probs = predict_proba(texts)
+    return (probs >= threshold).astype(int)
+
+# example
+texts = ["Some example text to classify"]
+probs = predict_proba(texts)
+labels = predict_label(texts)
+print(probs, labels)  # label 1 = AI, 0 = Human
+```
+
+---
+
+## Notes
+
+* Classifier head is **trainable** together with LoRA layers (unfrozen after applying PEFT).
+* Training used:
+
+  * `bf16=True`
+  * `optim="adamw_torch_fused"`
+  * cosine-with-restarts scheduler
+  * LR scaled down from HPO to account for full-dataset (~14k steps).
+* Threshold `0.9033` was chosen as the **max-F1** point on the validation set.
+  You can adjust it if you prefer fewer false positives or fewer false negatives.

.ipynb_checkpoints/results-checkpoint.json

@@ -0,0 +1,94 @@
+{
+  "hyperparameters": {
+    "include_attention_output_dense": false,
+    "learning_rate_sampled": 0.00044569416489470884,
+    "weight_decay": 0.022491619139739856,
+    "warmup_ratio": 0.0463266472104081,
+    "lr_scheduler_num_cycles": 1,
+    "per_device_train_batch_size": 8,
+    "gradient_accumulation_steps": 4,
+    "num_train_epochs": 2,
+    "lora_r": 32,
+    "lora_alpha": 128,
+    "lora_dropout": 0.0,
+    "lora_target_modules": [
+      "query_proj",
+      "key_proj",
+      "value_proj"
+    ],
+    "learning_rate": 4.456941648947089e-05,
+    "lr_scheduler_type": "cosine_with_restarts",
+    "max_grad_norm": 0.5,
+    "optim": "adamw_torch_fused"
+  },
+  "threshold_optimization": {
+    "max_f1": {
+      "threshold": 0.9032942056655884,
+      "metrics": {
+        "threshold": 0.9032942056655884,
+        "auroc": 0.9969044529302581,
+        "average_precision": 0.9965060417039346,
+        "f1": 0.9734939759036144,
+        "accuracy": 0.9762551119595773,
+        "precision": 0.9854536098796707,
+        "recall": 0.9618211495185389,
+        "specificity": 0.9882255881198587,
+        "precision_human": 0.9689546846776094,
+        "recall_human": 0.9882255881198587,
+        "precision_ai": 0.9854536098796707,
+        "recall_ai": 0.9618211495185389,
+        "confusion_matrix": {
+          "true_negative": 123377,
+          "false_positive": 1470,
+          "false_negative": 3953,
+          "true_positive": 99586
+        }
+      }
+    },
+    "precision_at_95recall": {
+      "threshold": 5.1442217227304354e-05,
+      "metrics": {
+        "threshold": 5.1442217227304354e-05,
+        "auroc": 0.9969044529302581,
+        "average_precision": 0.9965060417039346,
+        "f1": 0.6238698501167432,
+        "accuracy": 0.45335090592242955,
+        "precision": 0.45335090592242955,
+        "recall": 1.0,
+        "specificity": 0.0,
+        "precision_human": 0.0,
+        "recall_human": 0.0,
+        "precision_ai": 0.45335090592242955,
+        "recall_ai": 1.0,
+        "confusion_matrix": {
+          "true_negative": 0,
+          "false_positive": 124847,
+          "false_negative": 0,
+          "true_positive": 103539
+        }
+      }
+    }
+  },
+  "test_metrics": {
+    "threshold": 0.9032942056655884,
+    "auroc": 0.9970131530896283,
+    "average_precision": 0.9966291954050931,
+    "f1": 0.9739500109946493,
+    "accuracy": 0.976658040956797,
+    "precision": 0.9856685063200997,
+    "recall": 0.9625068814649552,
+    "specificity": 0.9883938869665513,
+    "precision_human": 0.9695005538925684,
+    "recall_human": 0.9883938869665513,
+    "precision_ai": 0.9856685063200997,
+    "recall_ai": 0.9625068814649552,
+    "confusion_matrix": {
+      "true_negative": 123399,
+      "false_positive": 1449,
+      "false_negative": 3882,
+      "true_positive": 99657
+    }
+  },
+  "timestamp": "20251113_111139",
+  "seed": 42
+}

.ipynb_checkpoints/threshold-checkpoint.json

@@ -0,0 +1,9 @@
+{
+  "threshold": 0.9032942056655884,
+  "method": "max_f1",
+  "validation_f1": 0.9734939759036144,
+  "alternative_thresholds": {
+    "max_f1": 0.9032942056655884,
+    "precision_at_95recall": 5.1442217227304354e-05
+  }
+}

README.md

@@ -0,0 +1,167 @@
+# AI Detector LoRA (DeBERTa-v3-large)
+
+LoRA adapter for binary AI-text vs Human-text detection, trained on ~2.3M English samples
+(`label: 1 = AI, 0 = Human`) using `microsoft/deberta-v3-large` as the base model.
+
+- **Base model:** `microsoft/deberta-v3-large`
+- **Task:** Binary classification (AI vs Human)
+- **Head:** Single-logit + `BCEWithLogitsLoss`
+- **Adapter type:** LoRA (`peft`)
+- **Hardware:** H100 SXM, bf16, multi-GPU
+- **Final decision threshold:** **0.9033** (max-F1 on validation)
+
+---
+
+## Files in this repo
+
+- `adapter/` – LoRA weights saved with `peft_model.save_pretrained(...)`
+- `threshold.json` – chosen deployment threshold and validation F1
+- `results.json` – hyperparameters, validation threshold search, test metrics
+- `training_log_history.csv` – raw Trainer log history
+- `predictions_val.csv` – validation probabilities and labels
+- `predictions_test.csv` – test probabilities and labels
+- `figures/` – training and evaluation plots
+- `README.md` – this file
+
+---
+
+## Metrics (test set)
+
+Using threshold **0.9033**:
+
+| Metric        | Value   |
+|--------------|---------|
+| AUROC        | 0.9970  |
+| Average Precision (AP) | 0.9966 |
+| F1           | 0.9740  |
+| Accuracy     | 0.9767  |
+| Precision    | 0.9857  |
+| Recall       | 0.9625  |
+| Specificity  | 0.9884  |
+
+Confusion matrix (test):
+
+- **True Negatives (Human correctly)**: 123,399  
+- **False Positives (Human → AI)**: 1,449  
+- **False Negatives (AI → Human)**: 3,882  
+- **True Positives (AI correctly)**: 99,657  
+
+---
+
+## Plots
+
+### Training & validation
+
+- Learning curves:
+
+  ![Learning curves](./figures/fig_learning_curves.png)
+
+- Eval metrics over time:
+
+  ![Eval metrics](./figures/fig_eval_metrics.png)
+
+### Validation set
+
+- ROC:
+
+  ![ROC (val)](./figures/fig_roc_val.png)
+
+- Precision–Recall:
+
+  ![PR (val)](./figures/fig_pr_val.png)
+
+- Calibration curve:
+
+  ![Calibration (val)](./figures/fig_calibration_val.png)
+
+- F1 vs threshold:
+
+  ![F1 vs threshold (val)](./figures/fig_threshold_f1_val.png)
+
+### Test set
+
+- ROC:
+
+  ![ROC (test)](./figures/fig_roc_test.png)
+
+- Precision–Recall:
+
+  ![PR (test)](./figures/fig_pr_test.png)
+
+- Calibration curve:
+
+  ![Calibration (test)](./figures/fig_calibration_test.png)
+
+- Confusion matrix:
+
+  ![Confusion matrix (test)](./figures/fig_confusion_test.png)
+
+---
+
+## Usage
+
+### Load base + LoRA adapter
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from peft import PeftModel
+import torch
+import json
+
+base_model_id = "microsoft/deberta-v3-large"
+adapter_id    = "<your-username>/<your-private-repo>"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+
+base_model = AutoModelForSequenceClassification.from_pretrained(
+    base_model_id,
+    num_labels=1,  # single logit for BCEWithLogitsLoss
+)
+model = PeftModel.from_pretrained(base_model, adapter_id)
+model.eval()
+````
+
+### Inference with threshold
+
+```python
+# load threshold
+with open("threshold.json") as f:
+    thr = json.load(f)["threshold"]  # 0.9033
+
+def predict_proba(texts):
+    enc = tokenizer(
+        texts,
+        padding=True,
+        truncation=True,
+        max_length=512,
+        return_tensors="pt",
+    )
+    with torch.no_grad():
+        logits = model(**enc).logits.squeeze(-1)
+        probs = torch.sigmoid(logits)
+    return probs.cpu().numpy()
+
+def predict_label(texts, threshold=thr):
+    probs = predict_proba(texts)
+    return (probs >= threshold).astype(int)
+
+# example
+texts = ["Some example text to classify"]
+probs = predict_proba(texts)
+labels = predict_label(texts)
+print(probs, labels)  # label 1 = AI, 0 = Human
+```
+
+---
+
+## Notes
+
+* Classifier head is **trainable** together with LoRA layers (unfrozen after applying PEFT).
+* Training used:
+
+  * `bf16=True`
+  * `optim="adamw_torch_fused"`
+  * cosine-with-restarts scheduler
+  * LR scaled down from HPO to account for full-dataset (~14k steps).
+* Threshold `0.9033` was chosen as the **max-F1** point on the validation set.
+  You can adjust it if you prefer fewer false positives or fewer false negatives.

adapter/.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,206 @@
+---
+base_model: microsoft/deberta-v3-large
+library_name: peft
+tags:
+- base_model:adapter:microsoft/deberta-v3-large
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter/.ipynb_checkpoints/adapter_config-checkpoint.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-large",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "value_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/README.md

@@ -0,0 +1,206 @@
+---
+base_model: microsoft/deberta-v3-large
+library_name: peft
+tags:
+- base_model:adapter:microsoft/deberta-v3-large
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-large",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "value_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe302bb59b8aa23d2077aafa0f9403ded12e36f656ded2725bd708a446e3daf9
+size 18900396

results.json

@@ -0,0 +1,94 @@
+{
+  "hyperparameters": {
+    "include_attention_output_dense": false,
+    "learning_rate_sampled": 0.00044569416489470884,
+    "weight_decay": 0.022491619139739856,
+    "warmup_ratio": 0.0463266472104081,
+    "lr_scheduler_num_cycles": 1,
+    "per_device_train_batch_size": 8,
+    "gradient_accumulation_steps": 4,
+    "num_train_epochs": 2,
+    "lora_r": 32,
+    "lora_alpha": 128,
+    "lora_dropout": 0.0,
+    "lora_target_modules": [
+      "query_proj",
+      "key_proj",
+      "value_proj"
+    ],
+    "learning_rate": 4.456941648947089e-05,
+    "lr_scheduler_type": "cosine_with_restarts",
+    "max_grad_norm": 0.5,
+    "optim": "adamw_torch_fused"
+  },
+  "threshold_optimization": {
+    "max_f1": {
+      "threshold": 0.9032942056655884,
+      "metrics": {
+        "threshold": 0.9032942056655884,
+        "auroc": 0.9969044529302581,
+        "average_precision": 0.9965060417039346,
+        "f1": 0.9734939759036144,
+        "accuracy": 0.9762551119595773,
+        "precision": 0.9854536098796707,
+        "recall": 0.9618211495185389,
+        "specificity": 0.9882255881198587,
+        "precision_human": 0.9689546846776094,
+        "recall_human": 0.9882255881198587,
+        "precision_ai": 0.9854536098796707,
+        "recall_ai": 0.9618211495185389,
+        "confusion_matrix": {
+          "true_negative": 123377,
+          "false_positive": 1470,
+          "false_negative": 3953,
+          "true_positive": 99586
+        }
+      }
+    },
+    "precision_at_95recall": {
+      "threshold": 5.1442217227304354e-05,
+      "metrics": {
+        "threshold": 5.1442217227304354e-05,
+        "auroc": 0.9969044529302581,
+        "average_precision": 0.9965060417039346,
+        "f1": 0.6238698501167432,
+        "accuracy": 0.45335090592242955,
+        "precision": 0.45335090592242955,
+        "recall": 1.0,
+        "specificity": 0.0,
+        "precision_human": 0.0,
+        "recall_human": 0.0,
+        "precision_ai": 0.45335090592242955,
+        "recall_ai": 1.0,
+        "confusion_matrix": {
+          "true_negative": 0,
+          "false_positive": 124847,
+          "false_negative": 0,
+          "true_positive": 103539
+        }
+      }
+    }
+  },
+  "test_metrics": {
+    "threshold": 0.9032942056655884,
+    "auroc": 0.9970131530896283,
+    "average_precision": 0.9966291954050931,
+    "f1": 0.9739500109946493,
+    "accuracy": 0.976658040956797,
+    "precision": 0.9856685063200997,
+    "recall": 0.9625068814649552,
+    "specificity": 0.9883938869665513,
+    "precision_human": 0.9695005538925684,
+    "recall_human": 0.9883938869665513,
+    "precision_ai": 0.9856685063200997,
+    "recall_ai": 0.9625068814649552,
+    "confusion_matrix": {
+      "true_negative": 123399,
+      "false_positive": 1449,
+      "false_negative": 3882,
+      "true_positive": 99657
+    }
+  },
+  "timestamp": "20251113_111139",
+  "seed": 42
+}

threshold.json

@@ -0,0 +1,9 @@
+{
+  "threshold": 0.9032942056655884,
+  "method": "max_f1",
+  "validation_f1": 0.9734939759036144,
+  "alternative_thresholds": {
+    "max_f1": 0.9032942056655884,
+    "precision_at_95recall": 5.1442217227304354e-05
+  }
+}

training_log_history.csv

@@ -0,0 +1,144 @@
+loss,grad_norm,learning_rate,epoch,step,eval_loss,eval_auroc,eval_ap,eval_f1,eval_max_f1,eval_best_threshold,eval_accuracy,eval_precision_human,eval_recall_human,eval_precision_ai,eval_recall_ai,eval_runtime,eval_samples_per_second,eval_steps_per_second,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
+0.7281,1.3650943040847778,1.3397755107862095e-05,0.028021997267855266,200,,,,,,,,,,,,,,,,,,,
+,,,0.028021997267855266,200,0.5034370422363281,0.8567927920680234,0.7639926105515766,0.8347106400605876,0.837193236817485,0.532181978225708,0.8270340563782368,0.959174450135583,0.7139779089605678,0.7363754484917389,0.9633568027506544,246.8726,925.117,14.457,,,,,
+0.4371,1.1207246780395508,2.6862835618276262e-05,0.05604399453571053,400,,,,,,,,,,,,,,,,,,,
+,,,0.05604399453571053,400,0.3717988133430481,0.9213253952884014,0.8819850262727043,0.8641301759262867,0.8645202782854652,0.6361271142959595,0.862605413641817,0.9628228489938203,0.7787291644973448,0.7831802841221254,0.9637431306077903,246.6166,926.077,14.472,,,,,
+0.2689,1.5876444578170776,4.032791612869042e-05,0.0840659918035658,600,,,,,,,,,,,,,,,,,,,
+,,,0.0840659918035658,600,0.2004675269126892,0.9836750912020398,0.9784411063029117,0.921532737340532,0.9410314678576056,0.8459424376487732,0.9254814218034381,0.9686869740593922,0.8925324597307104,0.8816362898530268,0.965211176464907,246.4382,926.748,14.482,,,,,
+0.1474,0.5951786637306213,4.455828097794425e-05,0.11208798907142106,800,,,,,,,,,,,,,,,,,,,
+,,,0.11208798907142106,800,0.22212685644626617,0.9876414514694006,0.9855191906869644,0.9181336820638506,0.9423700865680394,0.9407896995544434,0.9216064031945916,0.9722504349669249,0.8817592733505811,0.8718120164294584,0.9696539468219705,245.9329,928.652,14.512,,,,,
+0.1288,3.1992154121398926,4.450206516694645e-05,0.14010998633927632,1000,,,,,,,,,,,,,,,,,,,
+,,,0.14010998633927632,1000,0.12653978168964386,0.9925797356069876,0.9916142379137276,0.9520024486594546,0.9573109145286222,0.7943849563598633,0.9560568511204715,0.9673535182486506,0.9517329210954208,0.942911278480413,0.9612706323221202,245.8558,928.943,14.517,,,,,
+0.1172,0.6789711117744446,4.439853384372035e-05,0.1681319836071316,1200,,,,,,,,,,,,,,,,,,,
+,,,0.1681319836071316,1200,0.14555694162845612,0.9921387821614682,0.9912700139992648,0.9446152828753761,0.9561932798497733,0.8887588381767273,0.9486614766229103,0.9704634681927069,0.9345278621032144,0.9244281725559809,0.9657037444827553,245.8898,928.815,14.515,,,,,
+0.1092,0.6279441118240356,4.4247907495230585e-05,0.19615398087498687,1400,,,,,,,,,,,,,,,,,,,
+,,,0.19615398087498687,1400,0.15372662246227264,0.9927978868223,0.9919292076748125,0.9417183531079946,0.9590575982598013,0.9353464841842651,0.9456490327778411,0.9726421280960468,0.9266382051631197,0.9163133657395564,0.9685722288219898,245.8833,928.839,14.515,,,,,
+0.1062,1.4446195363998413,4.405050690503654e-05,0.22417597814284212,1600,,,,,,,,,,,,,,,,,,,
+,,,0.22417597814284212,1600,0.11368440091609955,0.9942393901033173,0.993596916377211,0.9563939433106902,0.9633088138126524,0.8757869601249695,0.9601157689175344,0.970357305416477,0.956250450551475,0.9481557415950035,0.964776557625629,245.857,928.938,14.517,,,,,
+0.0976,0.7851302027702332,4.3806752470131086e-05,0.2521979754106974,1800,,,,,,,,,,,,,,,,,,,
+,,,0.2521979754106974,1800,0.14997108280658722,0.9933556710094985,0.9925489998985919,0.9429900968712875,0.9596468920355709,0.9252299070358276,0.9468399989491475,0.973705889275567,0.9278076365471337,0.9176323292879076,0.969789161571968,245.7705,929.265,14.522,,,,,
+0.097,1.144687294960022,4.351716330563604e-05,0.28021997267855264,2000,,,,,,,,,,,,,,,,,,,
+,,,0.28021997267855264,2000,0.13728895783424377,0.9936304293189042,0.9929477433592986,0.9478551974580118,0.9613444886776696,0.9086179733276367,0.9517133274368832,0.9725250545928577,0.938172322923258,0.9284940110607787,0.9680410280184278,245.8436,928.989,14.517,,,,,
+0.0913,0.8097946643829346,4.3182356139261264e-05,0.30824196994640796,2200,,,,,,,,,,,,,,,,,,,
+,,,0.30824196994640796,2200,0.1629137396812439,0.992883712964101,0.9919489878089339,0.9421523335980788,0.9580045862640264,0.9407896995544434,0.9461044021962818,0.9722851723153884,0.9278556953711342,0.917551536011131,0.9681086353934266,246.024,928.308,14.507,,,,,
+0.0942,1.610180139541626,4.280304399788167e-05,0.3362639672142632,2400,,,,,,,,,,,,,,,,,,,
+,,,0.3362639672142632,2400,0.15682530403137207,0.9938745855338663,0.993259688256961,0.9434721308393647,0.9617119643400787,0.9585376977920532,0.9473347753364917,0.9734525158420412,0.9289930875391479,0.9188491500443973,0.9694511246969741,245.8341,929.025,14.518,,,,,
+0.0898,0.44423627853393555,4.238003468902928e-05,0.3642859644821185,2600,,,,,,,,,,,,,,,,,,,
+,,,0.3642859644821185,2600,0.10643962770700455,0.9950490299401135,0.9944538510424438,0.9604357495208773,0.9664626252455953,0.873214840888977,0.9639338663490757,0.9712200562506061,0.9625461564955505,0.9553194335620234,0.9656071625184713,245.8591,928.93,14.516,,,,,
+0.0911,1.0590174198150635,4.191422908053442e-05,0.39230796174997373,2800,,,,,,,,,,,,,,,,,,,
+,,,0.39230796174997373,2800,0.11612347513437271,0.9946141573591816,0.9939944771051153,0.9569791183516552,0.9643653756980626,0.8840392827987671,0.9606061667527782,0.9717250028503022,0.9557458328994689,0.9476759603000228,0.9664667420005988,245.8438,928.988,14.517,,,,,
+0.0856,1.3164970874786377,4.140661918197958e-05,0.420329959017829,3000,,,,,,,,,,,,,,,,,,,
+,,,0.420329959017829,3000,0.11796951293945312,0.9949918667417889,0.994355458108942,0.9567068978687648,0.9665062880160855,0.9343951344490051,0.9602952895536504,0.9726869656811111,0.95415989170745,0.9459671252018089,0.9676933329470054,245.7791,929.233,14.521,,,,,
+0.0821,1.2711987495422363,4.0858286032052055e-05,0.44835195628568425,3200,,,,,,,,,,,,,,,,,,,
+,,,0.44835195628568425,3200,0.09971292316913605,0.9955405517378006,0.9949817449087798,0.9628310234105341,0.9679576292752426,0.879974365234375,0.9661931992328777,0.9715293321953654,0.9664789702595977,0.9598322263600415,0.9658486174291813,245.8241,929.063,14.519,,,,,
+0.085,0.5998378396034241,4.027039739629442e-05,0.4763739535535395,3400,,,,,,,,,,,,,,,,,,,
+,,,0.4763739535535395,3400,0.12078217417001724,0.9949955823550951,0.9944631387897102,0.9548334238379681,0.9663685344296211,0.9263036847114563,0.9584825689840883,0.9728422588551614,0.950587519123407,0.9420179519714272,0.9680023952327143,245.9407,928.622,14.512,,,,,
+0.084,0.671790361404419,3.964420528015589e-05,0.5043959508213948,3600,,,,,,,,,,,,,,,,,,,
+,,,0.5043959508213948,3600,0.1031280905008316,0.9955552436116516,0.9950748276653851,0.9607936256661918,0.9684774337055235,0.8688268065452576,0.9642140936835008,0.9725021058770168,0.9617291564875408,0.954461409427956,0.9672104231255856,245.879,928.855,14.515,,,,,
+0.081,1.193284034729004,3.898104326264103e-05,0.53241794808925,3800,,,,,,,,,,,,,,,,,,,
+,,,0.53241794808925,3800,0.0943664014339447,0.9957421605444731,0.995280599833219,0.96472756750497,0.9691255242991724,0.8365545868873596,0.9679927841461385,0.9713508874648102,0.9700593526476408,0.963955450556868,0.9655009223577589,245.7307,929.416,14.524,,,,,
+0.0807,0.6923601031303406,3.828232365623414e-05,0.5604399453571053,4000,,,,,,,,,,,,,,,,,,,
+,,,0.5604399453571053,4000,0.13602322340011597,0.9945068890032484,0.993905565216706,0.9503015258677455,0.9644104098812593,0.9539660811424255,0.9540646099147934,0.9732024629237288,0.9419048915873028,0.9325641073321308,0.9687267599648441,245.8443,928.986,14.517,,,,,
+0.0779,0.29442542791366577,3.7549534499147724e-05,0.5884619426249605,4200,,,,,,,,,,,,,,,,,,,
+,,,0.5884619426249605,4200,0.10123751312494278,0.9954435493591816,0.9949460283029852,0.9623870601479885,0.9677929996672676,0.8652240633964539,0.9657684796791397,0.971621087925462,0.965581872211587,0.9588074581795523,0.9659934903756072,245.9464,928.601,14.511,,,,,
+0.0795,1.8506108522415161,3.678423638630061e-05,0.6164839398928159,4400,,,,,,,,,,,,,,,,,,,
+,,,0.6164839398928159,4400,0.11482585221529007,0.9954225057051109,0.994962660756873,0.9564496059726255,0.9688606356963216,0.9433475732803345,0.9600019265629242,0.9735773688690983,0.9526860877714323,0.9443879568434729,0.9688233419291281,245.8734,928.876,14.516,,,,,
+0.0764,1.2500754594802856,3.598805914577467e-05,0.6445059371606712,4600,,,,,,,,,,,,,,,,,,,
+,,,0.6445059371606712,4600,0.12350087612867355,0.9953538855682633,0.9948421489775661,0.954069819959019,0.9679151708414333,0.9511421918869019,0.9576988081581183,0.9736889722331886,0.9482406465513789,0.939495515065261,0.9691034296255517,245.8249,929.06,14.518,,,,,
+0.0776,0.9441678524017334,3.516269836782809e-05,0.6725279344285264,4800,,,,,,,,,,,,,,,,,,,
+,,,0.6725279344285264,4800,0.09324090927839279,0.9960413055155612,0.995564989005534,0.9658611467796905,0.9704891089007048,0.8840392827987671,0.9690348795460317,0.9719646392190493,0.9713729605036565,0.9655069246730685,0.9662156288934605,245.8365,929.016,14.518,,,,,
+0.0736,0.6129169464111328,3.430991179385733e-05,0.7005499316963817,5000,,,,,,,,,,,,,,,,,,,
+,,,0.7005499316963817,5000,0.11999406665563583,0.9952773925550765,0.9948196772549471,0.9540792562949726,0.9679756358671789,0.9416541457176208,0.9576944296060179,0.9739382318814341,0.9479763230193757,0.9392235208249506,0.9694124919112604,245.8584,928.933,14.516,,,,,
+0.0789,0.7752780914306641,3.343151557299794e-05,0.728571928964237,5200,,,,,,,,,,,,,,,,,,,
+,,,0.728571928964237,5200,0.10578533262014389,0.9959060523948745,0.9954666417692407,0.9599800834007594,0.9701210620572613,0.9343951344490051,0.963399682992828,0.9733206559721748,0.9593422348955121,0.9518095165761592,0.9682921411255662,245.8669,928.901,14.516,,,,,
+0.0739,0.8520299196243286,3.2529380394336615e-05,0.7565939262320922,5400,,,,,,,,,,,,,,,,,,,
+,,,0.7565939262320922,5400,0.10391142964363098,0.9957951879085571,0.9952825044933503,0.962313827231671,0.9695487450431454,0.9416541457176208,0.9656546373245295,0.9726057276729814,0.964332342787572,0.957428705270504,0.9672490559112992,245.8211,929.074,14.519,,,,,
+0.0775,0.6676751971244812,3.1605427502971364e-05,0.7846159234999475,5600,,,,,,,,,,,,,,,,,,,
+,,,0.7846159234999475,5600,0.08965875953435898,0.9963213227367876,0.9958643558038499,0.966500156857067,0.9713820883230001,0.8991213440895081,0.969608469871183,0.9726449130121062,0.9717334016836608,0.9659546963031566,0.9670462337863027,245.7698,929.268,14.522,,,,,
+0.0727,1.1384795904159546,3.0661624608404376e-05,0.8126379207678027,5800,,,,,,,,,,,,,,,,,,,
+,,,0.8126379207678027,5800,0.09947814047336578,0.9960502170307564,0.9955943884802091,0.9634165700569075,0.9701781488936472,0.9124361872673035,0.966701111276523,0.9725823095030796,0.966326783983596,0.9597094171091219,0.9671524739470151,245.8302,929.04,14.518,,,,,
+0.0723,0.6806196570396423,2.969998169398137e-05,0.840659918035658,6000,,,,,,,,,,,,,,,,,,,
+,,,0.840659918035658,6000,0.11319559812545776,0.9956365087859012,0.9951325050889013,0.958895197822541,0.9684056849185914,0.9525741338729858,0.9623751018013363,0.9730618357016131,0.9576842054674922,0.9499298657972552,0.9680313698219994,245.806,929.131,14.52,,,,,
+0.0703,0.6376020908355713,2.872254673630171e-05,0.8686819153035132,6200,,,,,,,,,,,,,,,,,,,
+,,,0.8686819153035132,6200,0.09632854163646698,0.9961434762558163,0.9956792827654228,0.9641803258959732,0.9704082233158977,0.9343951344490051,0.9674191938209873,0.9726870118367018,0.9675683036036108,0.961140542823141,0.9672393977148708,245.8119,929.109,14.519,,,,,
+0.0717,0.6587705016136169,2.773140134371577e-05,0.8967039125713685,6400,,,,,,,,,,,,,,,,,,,
+,,,0.8967039125713685,6400,0.11494402587413788,0.9958696310682444,0.9953992776112017,0.9580610203799094,0.9703862409011201,0.9585376977920532,0.9615344197980612,0.9739004034167933,0.9552332054434628,0.9472397387002983,0.9691324042148369,245.8451,928.983,14.517,,,,,
+0.071,1.1992093324661255,2.6728656323197893e-05,0.9247259098392238,6600,,,,,,,,,,,,,,,,,,,
+,,,0.9247259098392238,6600,0.1079399436712265,0.9959413616290814,0.9954836777985783,0.9598131601491273,0.9701123540493861,0.9504110217094421,0.963233298013013,0.9734663674212855,0.9588776662635066,0.9512949435537426,0.9684853050541342,245.9034,928.763,14.514,,,,,
+0.0717,0.6620305180549622,2.5716447185036114e-05,0.952747907107079,6800,,,,,,,,,,,,,,,,,,,
+,,,0.952747907107079,6800,0.09787657111883163,0.9961755673418714,0.9957160605725904,0.963615903975994,0.9705563424993778,0.8991213440895081,0.9668718748084384,0.9729949910063963,0.9662146467275946,0.9596011838059937,0.9676643583577202,245.9366,928.638,14.512,,,,,
+0.0711,1.2997543811798096,2.4696929594912076e-05,0.9807699043749343,7000,,,,,,,,,,,,,,,,,,,
+,,,0.9807699043749343,7000,0.1146920770406723,0.995944675317155,0.9954875225794212,0.9577217544780213,0.9696940029268117,0.954647421836853,0.9611928927342307,0.9742170251042603,0.9542640191594511,0.9461808173729452,0.9695477066612581,245.8587,928.932,14.516,,,,,
+0.0724,0.7974486351013184,2.3672274783056795e-05,1.0086868191530352,7200,,,,,,,,,,,,,,,,,,,
+,,,1.0086868191530352,7200,0.1015845537185669,0.9961790497526729,0.9957323299850726,0.9629252207518783,0.9700351292055995,0.9184802770614624,0.9662282276496807,0.9727491403386985,0.9652614800515832,0.9584976076555024,0.9673939288577251,245.8262,929.055,14.518,,,,,
+0.0649,0.8229542374610901,2.2644664920259076e-05,1.0367088164208904,7400,,,,,,,,,,,,,,,,,,,
+,,,1.0367088164208904,7400,0.08645018190145493,0.9965600272968401,0.9961185117789384,0.9678489558648573,0.971378867175356,0.8255897164344788,0.9708913856365977,0.9722255515337472,0.9745929017116951,0.9692739865355742,0.9664281092148852,245.8743,928.873,14.516,,,,,
+0.068,0.7686835527420044,2.1616288470574255e-05,1.0647308136887457,7600,,,,,,,,,,,,,,,,,,,
+,,,1.0647308136887457,7600,0.0841926634311676,0.9967842136955064,0.9963728317459107,0.9687837112215133,0.9733571550938489,0.8933094143867493,0.971745203296174,0.972796830822804,0.9755941272117071,0.9704690831556503,0.9671041829648731,245.8638,928.913,14.516,,,,,
+0.0684,0.49581971764564514,2.0589335530630446e-05,1.092752810956601,7800,,,,,,,,,,,,,,,,,,,
+,,,1.092752810956601,7800,0.097724050283432,0.9964498048620039,0.996013417423547,0.9642599451633075,0.9715029456084876,0.9334307909011841,0.9674673578940916,0.9733220461966381,0.966991597715604,0.9605082845396786,0.9680410280184278,245.8522,928.956,14.517,,,,,
+0.0665,1.0024373531341553,1.9565993165457813e-05,1.1207748082244562,8000,,,,,,,,,,,,,,,,,,,
+,,,1.1207748082244562,8000,0.08990959823131561,0.9965416445649657,0.996111897432367,0.9669079477905634,0.9719970667313506,0.8918110132217407,0.9699937824560174,0.9725960460123683,0.9725103526716701,0.9668565910188315,0.9669593100184471,246.7329,925.641,14.465,,,,,
+0.0676,0.9732509851455688,1.8548440750774307e-05,1.1487968054923114,8200,,,,,,,,,,,,,,,,,,,
+,,,1.1487968054923114,8200,0.0953540951013565,0.9965252478256964,0.9961004574885287,0.9655225599969152,0.9714322090330724,0.9399133324623108,0.9686802168259,0.9728337725782605,0.9697870193116375,0.9637063408063119,0.9673456378755831,246.7142,925.711,14.466,,,,,
+0.0638,1.3985579013824463,1.753884533164692e-05,1.1768188027601667,8400,,,,,,,,,,,,,,,,,,,
+,,,1.1768188027601667,8400,0.09055861830711365,0.9965989400880163,0.9961690844094493,0.966675668897934,0.9727147099462821,0.9353464841842651,0.9697442049862951,0.9733802149812554,0.9712127644236546,0.9653813922575301,0.9679734206434291,246.574,926.237,14.474,,,,,
+0.0641,0.5897226929664612,1.6539357007413156e-05,1.204840800028022,8600,,,,,,,,,,,,,,,,,,,
+,,,1.204840800028022,8600,0.10399724543094635,0.9962708327892441,0.9957835972645783,0.9633992144268537,0.9704696278600408,0.9532750844955444,0.96666608285972,0.9730076498499081,0.9658141565275897,0.9591430376596274,0.9676933329470054,246.6251,926.045,14.471,,,,,
+0.0693,0.9277693629264832,1.5552104352691164e-05,1.2328627972958772,8800,,,,,,,,,,,,,,,,,,,
+,,,1.2328627972958772,8800,0.08372964709997177,0.9967832506763049,0.9963809846481838,0.9686703149419614,0.9731677699865736,0.896251380443573,0.9716488751499655,0.9725353686967074,0.9756902448597082,0.9705722652083697,0.9667758042863076,246.6238,926.05,14.471,,,,,
+0.0621,0.4265595078468323,1.457918988423039e-05,1.2608847945637325,9000,,,,,,,,,,,,,,,,,,,
+,,,1.2608847945637325,9000,0.08751900494098663,0.9967499914503182,0.9963140806446376,0.9678585059253784,0.972755227251117,0.8887588381767273,0.9708694928760957,0.9730257576000128,0.9737038134676844,0.9682654757762054,0.9674518780362955,246.5692,926.255,14.475,,,,,
+0.066,0.5132720470428467,1.3622685583256601e-05,1.2889067918315877,9200,,,,,,,,,,,,,,,,,,,
+,,,1.2889067918315877,9200,0.09265980124473572,0.9966772555928973,0.9962576579748246,0.9657953308217793,0.9729735020893797,0.9381240010261536,0.9689122800872207,0.9734461323190002,0.9695787644076349,0.9634930552218004,0.9681086353934266,246.6667,925.889,14.469,,,,,
+0.0638,0.6131060719490051,1.26846284828475e-05,1.316928789099443,9400,,,,,,,,,,,,,,,,,,,
+,,,1.316928789099443,9400,0.0880228728055954,0.996786233571905,0.9963835217229717,0.9674853643116038,0.9736705691338173,0.9161096215248108,0.9705016944996628,0.973477863476741,0.9725343820836704,0.9669207022959676,0.9680506862148562,246.5183,926.446,14.478,,,,,
+0.0631,0.5040121674537659,1.1767016329735986e-05,1.3449507863672983,9600,,,,,,,,,,,,,,,,,,,
+,,,1.3449507863672983,9600,0.088343046605587,0.9967945716541701,0.9963785207323399,0.9681004779370901,0.9732178678012516,0.9207897186279297,0.9710971775853161,0.9730067043218075,0.9741523624916898,0.9687886877127824,0.9674132452505819,246.6015,926.134,14.473,,,,,
+0.0626,0.5754002332687378,1.0871803329780279e-05,1.3729727836351535,9800,,,,,,,,,,,,,,,,,,,
+,,,1.3729727836351535,9800,0.08908010274171829,0.9968349029617605,0.9964338452298704,0.9673004536241675,0.9733966350967752,0.9161096215248108,0.9703309309677476,0.9734012268954734,0.9722940879636676,0.9666380532595171,0.9679637624470007,246.5625,926.28,14.475,,,,,
+0.0635,0.37719520926475525,1.0000895986161401e-05,1.4009947809030088,10000,,,,,,,,,,,,,,,,,,,
+,,,1.4009947809030088,10000,0.10576409846544266,0.9964103740665244,0.9959816504324808,0.9620018891174369,0.9717239996277691,0.9585376977920532,0.9652999746043979,0.9738979588528072,0.9623138721795478,0.9552007160268129,0.9689006075005554,246.5201,926.44,14.478,,,,,
+0.0647,0.4855269193649292,9.156149039171426e-06,1.429016778170864,10200,,,,,,,,,,,,,,,,,,,
+,,,1.429016778170864,10200,0.08731859922409058,0.9969044529302581,0.9965060417039346,0.967862178187226,0.9734939759031145,0.9019206762313843,0.9708563572197946,0.973457141254797,0.9732232252276787,0.9677220017572826,0.9680023952327143,246.5275,926.412,14.477,,,,,
+0.0658,0.9444574117660522,8.339361516239216e-06,1.4570387754387193,10400,,,,,,,,,,,,,,,,,,,
+,,,1.4570387754387193,10400,0.0880136489868164,0.9968816941218545,0.9965015373119736,0.9673096035276295,0.9733884580565982,0.9161096215248108,0.9703309309677476,0.9736215071361525,0.9720618036476647,0.9663771580601317,0.9682438501434242,246.6147,926.084,14.472,,,,,
+0.0611,0.45777803659439087,7.5522729006059505e-06,1.4850607727065746,10600,,,,,,,,,,,,,,,,,,,
+,,,1.4850607727065746,10600,0.09273924678564072,0.9967055123563264,0.9962876686774951,0.9661673703082528,0.9724540697185579,0.9399133324623108,0.969262564255252,0.9734555945770013,0.9702275585316428,0.9642434561773109,0.9680989771969982,246.5306,926.4,14.477,,,,,
+0.0627,0.8916956186294556,6.796559426809692e-06,1.5130827699744298,10800,,,,,,,,,,,,,,,,,,,
+,,,1.5130827699744298,10800,0.08739963173866272,0.9968748801914394,0.9964844262023231,0.9675924808764267,0.9735564214519877,0.9241418242454529,0.9705980226458715,0.9735888389993586,0.9725984605156712,0.9669997877799857,0.9681859009648538,246.7364,925.627,14.465,,,,,
+0.0623,0.7013267278671265,6.0738305108685545e-06,1.541104767242285,11000,,,,,,,,,,,,,,,,,,,
+,,,1.541104767242285,11000,0.0974632278084755,0.9966048359068608,0.9961832096074739,0.964546783625731,0.9723199624672457,0.9362850189208984,0.9677213139159143,0.9737315407011913,0.9670396565396044,0.9605831585198809,0.9685432542327046,246.5852,926.195,14.474,,,,,
+0.063,0.8154935240745544,5.385625322764794e-06,1.5691267645101403,11200,,,,,,,,,,,,,,,,,,,
+,,,1.5691267645101403,11200,0.09752331674098969,0.9966611901489429,0.9962433071485012,0.964554077507007,0.9729103642409853,0.9433475732803345,0.9677169353638139,0.9739989347794509,0.966751303595601,0.9602653444116859,0.9688812911076985,246.5136,926.464,14.478,,,,,
+0.0631,0.685742974281311,4.73340950852946e-06,1.5971487617779956,11400,,,,,,,,,,,,,,,,,,,
+,,,1.5971487617779956,11400,0.09248074889183044,0.9967045142155668,0.996290326082087,0.9660411899313501,0.9726085083041068,0.9399133324623108,0.9691355862443407,0.9736550060313631,0.9697790095076374,0.9637337075627668,0.968359748500565,246.5731,926.241,14.474,,,,,
+0.0627,1.1395540237426758,4.118572068908318e-06,1.6251707590458508,11600,,,,,,,,,,,,,,,,,,,
+,,,1.6251707590458508,11600,0.08698944747447968,0.9968948298167076,0.996494789063069,0.9677260527890946,0.973689873045802,0.9161096215248108,0.9707250006567828,0.9735494265034746,0.9728788036556746,0.9673244873341376,0.9681279517862834,246.6038,926.125,14.473,,,,,
+0.0621,1.5019831657409668,3.5424224012565447e-06,1.653192756313706,11800,,,,,,,,,,,,,,,,,,,
+,,,1.653192756313706,11800,0.10022038221359253,0.9966304956476687,0.9962084684159175,0.9636517328825022,0.9727368874608185,0.9626730680465698,0.9668631177042376,0.973980940371978,0.965165362403582,0.9584499708605222,0.9689102656969838,246.5696,926.254,14.475,,,,,
+0.0621,0.6207771897315979,3.006187510961881e-06,1.6812147535815614,12000,,,,,,,,,,,,,,,,,,,
+,,,1.6812147535815614,12000,0.08885731548070908,0.9968981157711279,0.9965016737672114,0.9672419696290188,0.9739953876205015,0.9433475732803345,0.970256495582041,0.9738992902790713,0.9716292742316596,0.9658865453144563,0.968601203411275,246.5364,926.378,14.477,,,,,
+0.0625,1.3990130424499512,2.511009398335074e-06,1.7092367508494168,12200,,,,,,,,,,,,,,,,,,,
+,,,1.7092367508494168,12200,0.09371371567249298,0.9967498807864655,0.9963397310167501,0.965798508289155,0.9732076432118419,0.9481545686721802,0.9688991444309196,0.9738417951772319,0.9691382251876297,0.9630024389775499,0.9686108616077034,246.5834,926.202,14.474,,,,,
+0.0623,0.5540758967399597,2.057942626532536e-06,1.737258748117272,12400,,,,,,,,,,,,,,,,,,,
+,,,1.737258748117272,12400,0.09393420815467834,0.9967897724943766,0.9963785511182874,0.9659367279417076,0.9731286363853603,0.939024806022644,0.9690305009939313,0.9738176083423182,0.9694105585236329,0.963315530623223,0.9685722288219898,246.6306,926.025,14.471,,,,,
+0.0643,0.9720720052719116,1.6479520756908518e-06,1.7652807453851274,12600,,,,,,,,,,,,,,,,,,,
+,,,1.7652807453851274,12600,0.09308448433876038,0.9967791736358621,0.9963694636590227,0.9660367906669813,0.9731835264636404,0.9441768527030945,0.9691268291401399,0.9737688830257887,0.9696428428396358,0.9635815044009686,0.968504621446991,246.6887,925.807,14.468,,,,,
+0.0624,1.0696525573730469,1.2819108880559477e-06,1.7933027426529826,12800,,,,,,,,,,,,,,,,,,,
+,,,1.7933027426529826,12800,0.09151949733495712,0.9968253090517087,0.9964204520696328,0.9665868246157702,0.9733586501189067,0.9399133324623108,0.9696434982879861,0.9738089880416613,0.9705719801036469,0.964657444638975,0.9685239378398478,246.5498,926.328,14.476,,,,,
+0.0625,1.4033018350601196,9.605986084832452e-07,1.8213247399208379,13000,,,,,,,,,,,,,,,,,,,
+,,,1.8213247399208379,13000,0.09507396817207336,0.9967674833401138,0.9963561447668665,0.9654810607883717,0.9731590960292014,0.9591543078422546,0.9685970243359926,0.9739035882566147,0.9685054506716221,0.9622760982817012,0.9687074435719873,246.7376,925.623,14.465,,,,,
+0.063,0.45164167881011963,6.846995242687752e-07,1.8493467371886931,13200,,,,,,,,,,,,,,,,,,,
+,,,1.8493467371886931,13200,0.09227791428565979,0.9968329623022687,0.9964266292094927,0.9663162762913218,0.9733341164718503,0.9465966820716858,0.969385163714063,0.9738956307751695,0.9699952742156399,0.9639942713790021,0.968649494393417,246.5226,926.43,14.477,,,,,
+0.0618,0.3481653332710266,4.548012078469415e-07,1.8773687344565484,13400,,,,,,,,,,,,,,,,,,,
+,,,1.8773687344565484,13400,0.09297340363264084,0.9968072979972056,0.9963973889545064,0.9661836679640834,0.9732662175973241,0.9425067901611328,0.969262564255252,0.9738363909822815,0.9698270683316379,0.9637972956089685,0.9685818870184182,246.5722,926.244,14.474,,,,,
+0.0631,0.3175712525844574,2.7139326545848965e-07,1.9053907317244037,13600,,,,,,,,,,,,,,,,,,,
+,,,1.9053907317244037,13600,0.09512791037559509,0.9967728122242903,0.9963611581808621,0.9655092748572913,0.9731316412589667,0.9489172697067261,0.968623295648595,0.9739124831868813,0.9685454996916225,0.9623226227369108,0.9687171017684157,246.586,926.192,14.474,,,,,
+0.0606,0.5379019975662231,1.348662944535554e-07,1.933412728992259,13800,,,,,,,,,,,,,,,,,,,
+,,,1.933412728992259,13800,0.09340985864400864,0.9968055931317871,0.9963962951212402,0.9660171262895287,0.9732650683786642,0.9504110217094421,0.969104936379638,0.9738516867673443,0.9695146859756342,0.9634372448244393,0.9686108616077034,246.589,926.181,14.473,,,,,
+0.061,1.021728754043579,4.551105145043261e-08,1.9614347262601142,14000,,,,,,,,,,,,,,,,,,,
+,,,1.9614347262601142,14000,0.09326184540987015,0.9968091848139563,0.9964000739066909,0.9660543477213837,0.9732996051448428,0.9465966820716858,0.9691399647964412,0.9738533696972622,0.9695787644076349,0.9635112934372208,0.9686108616077034,246.5091,926.481,14.478,,,,,
+0.0623,1.5442456007003784,3.5178331215701367e-09,1.9894567235279694,14200,,,,,,,,,,,,,,,,,,,
+,,,1.9894567235279694,14200,0.09308414906263351,0.9968106062700608,0.9964016493909656,0.9661896251908728,0.9732898767747101,0.9473810195922852,0.9692669428073525,0.9738670913565948,0.9698030389196376,0.9637709014030367,0.9686205198041318,246.5533,926.315,14.476,,,,,
+,,,2.0,14276,,,,,,,,,,,,,,,27534.7527,132.711,0.518,3.3997885998922465e+18,0.09163027936652716