Add files using upload-large-folder tool

security/datasets/cybersecurity-rules/.gitattributes

@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

security/datasets/cybersecurity-rules/README.md

@@ -0,0 +1,43 @@
+---
+license: apache-2.0
+---
+# Cybersecurity Detection Rules Dataset
+
+This dataset contains a collection of 950 detection rules from official SIGMA, YARA, and Suricata repositories. Knowledge distillation was applied to generate questions for each rule and enrich the responses, using 0dAI-7.5B.
+
+## Contents
+- A set of detection rules for cybersecurity threat and intrusion detection in JSONL format (rules_dataset.jsonl). It contains the prompts and the associated responses. 
+- The rules have been obtained from SIGMA, YARA, and Suricata official repositories.
+
+
+## Usage
+This dataset can be used to fine-tune LLM models or create cybersecurity applications focused on threat and intrusion detection. It is ideal for researchers and practitioners in cybersecurity looking to leverage a curated corpus of detection rules.
+
+You can adjust this dataset with the prompt template of the model you want to fine-tune, in a simple way, with the following code, assuming that you have divided it into two sets for training and testing: 
+
+```python
+
+from datasets import load_dataset
+
+# LLaMA3 prompt template
+
+def format_prompt(prompt, response):
+  return f"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\nYou are a helpful assistant.<|eot_id|>\n<|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n{response}<|eot_id|>\n"
+
+# Dataset load
+train_dataset = load_dataset("json", data_files="/path/to/train.json")
+val_dataset = load_dataset("json", data_files="/path/to/val.json")
+
+train_dataset["validation"] = val_dataset["train"]
+
+# Map dataset with the prompt template
+
+mapped_qa_dataset = train_dataset.map(lambda samples: tokenizer(format_prompt(samples['instruction'], samples['output'])))
+
+# print some examples
+print(mapped_qa_dataset['train'][0])
+print(mapped_qa_dataset['train'][1])
+```
+
+## License
+This dataset is shared under an apache-2.0 license. Please review the licensing terms in this repository to ensure compliance with any restrictions or requirements.

security/outputs/cysecbert-phishing-classifier/config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Phishing Email",
+    "1": "Safe Email"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Phishing Email": 0,
+    "Safe Email": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

security/outputs/cysecbert-phishing-classifier/label_mapping.json

@@ -0,0 +1,23 @@
+{
+  "label2id": {
+    "Phishing Email": 0,
+    "Safe Email": 1
+  },
+  "id2label": {
+    "0": "Phishing Email",
+    "1": "Safe Email"
+  },
+  "text_col": "Email Text",
+  "label_col": "Email Type",
+  "metrics": {
+    "eval_loss": 0.7898762822151184,
+    "eval_accuracy": 0.0,
+    "eval_precision": 0.0,
+    "eval_recall": 0.0,
+    "eval_f1": 0.0,
+    "eval_runtime": 0.0328,
+    "eval_samples_per_second": 91.43,
+    "eval_steps_per_second": 30.477,
+    "epoch": 1.0
+  }
+}

security/outputs/cysecbert-phishing-classifier/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

security/outputs/cysecbert-phishing-classifier/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/cysecbert-phishing-classifier/training_args.bin",
+  "latest_mtime": 1777558873.6293423,
+  "latest_mtime_iso": "2026-04-30T14:21:13.629342+00:00",
+  "size_bytes": 5329,
+  "epoch": null
+}

security/outputs/phishsense-10datasets-lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/Llama-Phishsense-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/Llama-Phishsense-1B
+- 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 0.19.1

security/outputs/phishsense-10datasets-lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/Llama-Phishsense-1B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/phishsense-10datasets-lora/chat_template.jinja

@@ -0,0 +1,64 @@
+{%- if messages|length % 2 == 0 -%}
+    {%- set role = 'Agent' -%}
+{%-  else -%}
+    {%-  set role = 'User' -%}
+{%-  endif -%}
+{%-  if categories is not defined -%}
+    {%-  
+        set categories = ({
+            "S1": "Violent Crimes.",
+            "S2": "Non-Violent Crimes.",
+            "S3": "Sex Crimes.",
+            "S4": "Child Exploitation.",
+            "S5": "Defamation.",
+            "S6": "Specialized Advice.",
+            "S7": "Privacy.",
+            "S8": "Intellectual Property.",
+            "S9": "Indiscriminate Weapons.",
+            "S10": "Hate.",
+            "S11": "Self-Harm.",
+            "S12": "Sexual Content.",
+            "S13": "Elections.",
+        })
+    -%}
+{%-  endif -%}
+
+{{- "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n" -}}
+{%- set ns = namespace(contains_image=false) -%}
+{%-  for message in messages -%}
+    {%- for content in message['content'] | selectattr('type', 'equalto', 'image') -%}
+        {%- set ns.contains_image = true -%}
+    {%- endfor -%}
+{%- endfor -%}
+{%- if ns.contains_image -%}
+{{- "<|image|> "-}}
+{%- endif -%}
+{{- "Task: Check if there is unsafe content in '" + role + "' messages in conversations according our safety policy with the below categories.\n\n" -}}
+{{- "<BEGIN UNSAFE CONTENT CATEGORIES>\n"-}}
+
+{%-  for key in categories -%}
+    {%-  if key not in excluded_category_keys -%}
+        {{-key + ": " + categories[key] + "\n" -}}
+    {%-  endif -%}
+{%-  endfor -%}
+
+{{- "<END UNSAFE CONTENT CATEGORIES>\n\n"-}}
+{{- "<BEGIN CONVERSATION>\n\n"-}}
+{%-  for message in messages -%}
+    {%-  if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...')-}}
+    {%-  endif -%}
+    {%-  set content = message['content'] -%}
+    {%-  if message['role'] == 'user' -%}
+        {%-  set role = 'User' -%}
+    {%-  elif message['role'] == 'assistant' -%}
+        {%-  set role = 'Agent' -%}
+    {%-  endif -%}
+    {%-  for content in message['content'] | selectattr('type', 'equalto', 'text') -%}
+{{- role + ': ' + content['text'] | trim + '\n\n'-}}
+    {%-  endfor -%}
+{%-  endfor -%}
+{{- "<END CONVERSATION>\n\n"-}}
+{{- "Provide your safety assessment for ONLY THE LAST " + role + " message in the above conversation:\n"-}}
+{{- " - First line must read 'safe' or 'unsafe'.\n"-}}
+{{- " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>"-}}

security/outputs/phishsense-10datasets-lora/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

security/outputs/phishsense-10datasets-lora/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/phishsense-10datasets-lora/adapter_model.safetensors",
+  "latest_mtime": 1777556420.4314501,
+  "latest_mtime_iso": "2026-04-30T13:40:20.431450+00:00",
+  "size_bytes": 45118424,
+  "epoch": null
+}

security/outputs/phishsense-phishing-lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/Llama-Phishsense-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/Llama-Phishsense-1B
+- 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 0.19.1

security/outputs/phishsense-phishing-lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/Llama-Phishsense-1B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/phishsense-phishing-lora/chat_template.jinja

@@ -0,0 +1,64 @@
+{%- if messages|length % 2 == 0 -%}
+    {%- set role = 'Agent' -%}
+{%-  else -%}
+    {%-  set role = 'User' -%}
+{%-  endif -%}
+{%-  if categories is not defined -%}
+    {%-  
+        set categories = ({
+            "S1": "Violent Crimes.",
+            "S2": "Non-Violent Crimes.",
+            "S3": "Sex Crimes.",
+            "S4": "Child Exploitation.",
+            "S5": "Defamation.",
+            "S6": "Specialized Advice.",
+            "S7": "Privacy.",
+            "S8": "Intellectual Property.",
+            "S9": "Indiscriminate Weapons.",
+            "S10": "Hate.",
+            "S11": "Self-Harm.",
+            "S12": "Sexual Content.",
+            "S13": "Elections.",
+        })
+    -%}
+{%-  endif -%}
+
+{{- "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n" -}}
+{%- set ns = namespace(contains_image=false) -%}
+{%-  for message in messages -%}
+    {%- for content in message['content'] | selectattr('type', 'equalto', 'image') -%}
+        {%- set ns.contains_image = true -%}
+    {%- endfor -%}
+{%- endfor -%}
+{%- if ns.contains_image -%}
+{{- "<|image|> "-}}
+{%- endif -%}
+{{- "Task: Check if there is unsafe content in '" + role + "' messages in conversations according our safety policy with the below categories.\n\n" -}}
+{{- "<BEGIN UNSAFE CONTENT CATEGORIES>\n"-}}
+
+{%-  for key in categories -%}
+    {%-  if key not in excluded_category_keys -%}
+        {{-key + ": " + categories[key] + "\n" -}}
+    {%-  endif -%}
+{%-  endfor -%}
+
+{{- "<END UNSAFE CONTENT CATEGORIES>\n\n"-}}
+{{- "<BEGIN CONVERSATION>\n\n"-}}
+{%-  for message in messages -%}
+    {%-  if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...')-}}
+    {%-  endif -%}
+    {%-  set content = message['content'] -%}
+    {%-  if message['role'] == 'user' -%}
+        {%-  set role = 'User' -%}
+    {%-  elif message['role'] == 'assistant' -%}
+        {%-  set role = 'Agent' -%}
+    {%-  endif -%}
+    {%-  for content in message['content'] | selectattr('type', 'equalto', 'text') -%}
+{{- role + ': ' + content['text'] | trim + '\n\n'-}}
+    {%-  endfor -%}
+{%-  endfor -%}
+{{- "<END CONVERSATION>\n\n"-}}
+{{- "Provide your safety assessment for ONLY THE LAST " + role + " message in the above conversation:\n"-}}
+{{- " - First line must read 'safe' or 'unsafe'.\n"-}}
+{{- " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>"-}}

security/outputs/phishsense-phishing-lora/checkpoint-2200/trainer_state.json

@@ -0,0 +1,1574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9436997319034852,
+  "eval_steps": 500,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004289544235924933,
+      "grad_norm": 2.461350917816162,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 4.751891708374023,
+      "step": 10
+    },
+    {
+      "epoch": 0.008579088471849867,
+      "grad_norm": 1.740277647972107,
+      "learning_rate": 5.428571428571428e-05,
+      "loss": 4.051348876953125,
+      "step": 20
+    },
+    {
+      "epoch": 0.012868632707774798,
+      "grad_norm": 1.3302079439163208,
+      "learning_rate": 8.285714285714287e-05,
+      "loss": 3.239373779296875,
+      "step": 30
+    },
+    {
+      "epoch": 0.017158176943699734,
+      "grad_norm": 1.0828485488891602,
+      "learning_rate": 0.00011142857142857144,
+      "loss": 2.7260066986083986,
+      "step": 40
+    },
+    {
+      "epoch": 0.021447721179624665,
+      "grad_norm": 1.0427392721176147,
+      "learning_rate": 0.00014,
+      "loss": 2.565675163269043,
+      "step": 50
+    },
+    {
+      "epoch": 0.025737265415549597,
+      "grad_norm": 0.9723011255264282,
+      "learning_rate": 0.00016857142857142857,
+      "loss": 2.3718759536743166,
+      "step": 60
+    },
+    {
+      "epoch": 0.030026809651474532,
+      "grad_norm": 1.074137806892395,
+      "learning_rate": 0.00019714285714285716,
+      "loss": 2.394337272644043,
+      "step": 70
+    },
+    {
+      "epoch": 0.03431635388739947,
+      "grad_norm": 1.0547237396240234,
+      "learning_rate": 0.000199992187969813,
+      "loss": 2.3535043716430666,
+      "step": 80
+    },
+    {
+      "epoch": 0.0386058981233244,
+      "grad_norm": 0.9247291684150696,
+      "learning_rate": 0.00019996518498802463,
+      "loss": 2.4601144790649414,
+      "step": 90
+    },
+    {
+      "epoch": 0.04289544235924933,
+      "grad_norm": 2.0372612476348877,
+      "learning_rate": 0.00019991889981715698,
+      "loss": 2.3154342651367186,
+      "step": 100
+    },
+    {
+      "epoch": 0.04718498659517426,
+      "grad_norm": 1.2616114616394043,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 2.449721908569336,
+      "step": 110
+    },
+    {
+      "epoch": 0.051474530831099194,
+      "grad_norm": 0.945946216583252,
+      "learning_rate": 0.00019976852233739427,
+      "loss": 2.364675521850586,
+      "step": 120
+    },
+    {
+      "epoch": 0.055764075067024126,
+      "grad_norm": 1.0374224185943604,
+      "learning_rate": 0.00019966445903466773,
+      "loss": 2.3558889389038087,
+      "step": 130
+    },
+    {
+      "epoch": 0.060053619302949064,
+      "grad_norm": 0.8756594657897949,
+      "learning_rate": 0.00019954117154960383,
+      "loss": 2.161049652099609,
+      "step": 140
+    },
+    {
+      "epoch": 0.064343163538874,
+      "grad_norm": 1.0294053554534912,
+      "learning_rate": 0.0001993986836630079,
+      "loss": 2.1054876327514647,
+      "step": 150
+    },
+    {
+      "epoch": 0.06863270777479893,
+      "grad_norm": 0.8740042448043823,
+      "learning_rate": 0.00019923702285923228,
+      "loss": 2.124430465698242,
+      "step": 160
+    },
+    {
+      "epoch": 0.07292225201072386,
+      "grad_norm": 0.77315753698349,
+      "learning_rate": 0.00019905622032087507,
+      "loss": 2.4021867752075194,
+      "step": 170
+    },
+    {
+      "epoch": 0.0772117962466488,
+      "grad_norm": 0.953255295753479,
+      "learning_rate": 0.00019885631092276526,
+      "loss": 2.0978525161743162,
+      "step": 180
+    },
+    {
+      "epoch": 0.08150134048257372,
+      "grad_norm": 0.8136326670646667,
+      "learning_rate": 0.00019863733322523578,
+      "loss": 2.32897834777832,
+      "step": 190
+    },
+    {
+      "epoch": 0.08579088471849866,
+      "grad_norm": 1.0012127161026,
+      "learning_rate": 0.00019839932946668552,
+      "loss": 2.2645999908447267,
+      "step": 200
+    },
+    {
+      "epoch": 0.09008042895442359,
+      "grad_norm": 0.9342105984687805,
+      "learning_rate": 0.0001981423455554323,
+      "loss": 2.230245590209961,
+      "step": 210
+    },
+    {
+      "epoch": 0.09436997319034852,
+      "grad_norm": 0.8320803046226501,
+      "learning_rate": 0.00019786643106085738,
+      "loss": 2.226487731933594,
+      "step": 220
+    },
+    {
+      "epoch": 0.09865951742627346,
+      "grad_norm": 0.8236033916473389,
+      "learning_rate": 0.0001975716392038441,
+      "loss": 2.278731346130371,
+      "step": 230
+    },
+    {
+      "epoch": 0.10294906166219839,
+      "grad_norm": 0.877591609954834,
+      "learning_rate": 0.00019725802684651233,
+      "loss": 2.009513282775879,
+      "step": 240
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 0.8955455422401428,
+      "learning_rate": 0.00019692565448125018,
+      "loss": 2.240833282470703,
+      "step": 250
+    },
+    {
+      "epoch": 0.11152815013404825,
+      "grad_norm": 0.8864295482635498,
+      "learning_rate": 0.00019657458621904583,
+      "loss": 2.2627416610717774,
+      "step": 260
+    },
+    {
+      "epoch": 0.11581769436997319,
+      "grad_norm": 1.0706095695495605,
+      "learning_rate": 0.00019620488977712116,
+      "loss": 2.196295738220215,
+      "step": 270
+    },
+    {
+      "epoch": 0.12010723860589813,
+      "grad_norm": 1.0405200719833374,
+      "learning_rate": 0.00019581663646586978,
+      "loss": 2.0924251556396483,
+      "step": 280
+    },
+    {
+      "epoch": 0.12439678284182305,
+      "grad_norm": 0.71753990650177,
+      "learning_rate": 0.00019540990117510227,
+      "loss": 2.020050811767578,
+      "step": 290
+    },
+    {
+      "epoch": 0.128686327077748,
+      "grad_norm": 0.80608731508255,
+      "learning_rate": 0.00019498476235960043,
+      "loss": 2.1187694549560545,
+      "step": 300
+    },
+    {
+      "epoch": 0.13297587131367292,
+      "grad_norm": 0.8830103278160095,
+      "learning_rate": 0.0001945413020239845,
+      "loss": 2.197436714172363,
+      "step": 310
+    },
+    {
+      "epoch": 0.13726541554959787,
+      "grad_norm": 0.778745710849762,
+      "learning_rate": 0.00019407960570689504,
+      "loss": 2.2908151626586912,
+      "step": 320
+    },
+    {
+      "epoch": 0.1415549597855228,
+      "grad_norm": 0.8987101912498474,
+      "learning_rate": 0.0001935997624644939,
+      "loss": 2.1507293701171877,
+      "step": 330
+    },
+    {
+      "epoch": 0.14584450402144772,
+      "grad_norm": 0.8126206994056702,
+      "learning_rate": 0.00019310186485328593,
+      "loss": 2.0694677352905275,
+      "step": 340
+    },
+    {
+      "epoch": 0.15013404825737264,
+      "grad_norm": 0.9921199679374695,
+      "learning_rate": 0.00019258600891226588,
+      "loss": 2.0286174774169923,
+      "step": 350
+    },
+    {
+      "epoch": 0.1544235924932976,
+      "grad_norm": 0.8410740494728088,
+      "learning_rate": 0.00019205229414439364,
+      "loss": 2.1866321563720703,
+      "step": 360
+    },
+    {
+      "epoch": 0.15871313672922252,
+      "grad_norm": 0.8364278674125671,
+      "learning_rate": 0.0001915008234974012,
+      "loss": 1.9998489379882813,
+      "step": 370
+    },
+    {
+      "epoch": 0.16300268096514745,
+      "grad_norm": 0.9343453645706177,
+      "learning_rate": 0.0001909317033439351,
+      "loss": 2.036051368713379,
+      "step": 380
+    },
+    {
+      "epoch": 0.1672922252010724,
+      "grad_norm": 0.9619212746620178,
+      "learning_rate": 0.00019034504346103823,
+      "loss": 2.1354415893554686,
+      "step": 390
+    },
+    {
+      "epoch": 0.17158176943699732,
+      "grad_norm": 0.8053330183029175,
+      "learning_rate": 0.0001897409570089753,
+      "loss": 2.005703353881836,
+      "step": 400
+    },
+    {
+      "epoch": 0.17587131367292225,
+      "grad_norm": 0.94014573097229,
+      "learning_rate": 0.00018911956050940516,
+      "loss": 2.105622100830078,
+      "step": 410
+    },
+    {
+      "epoch": 0.18016085790884717,
+      "grad_norm": 0.9183622598648071,
+      "learning_rate": 0.00018848097382290533,
+      "loss": 2.2289337158203124,
+      "step": 420
+    },
+    {
+      "epoch": 0.18445040214477212,
+      "grad_norm": 0.7824776768684387,
+      "learning_rate": 0.00018782532012585193,
+      "loss": 2.190073776245117,
+      "step": 430
+    },
+    {
+      "epoch": 0.18873994638069705,
+      "grad_norm": 0.8406926393508911,
+      "learning_rate": 0.00018715272588666062,
+      "loss": 2.039468193054199,
+      "step": 440
+    },
+    {
+      "epoch": 0.19302949061662197,
+      "grad_norm": 0.788490891456604,
+      "learning_rate": 0.00018646332084139189,
+      "loss": 2.172566032409668,
+      "step": 450
+    },
+    {
+      "epoch": 0.19731903485254693,
+      "grad_norm": 0.8548129200935364,
+      "learning_rate": 0.00018575723796872666,
+      "loss": 2.058650588989258,
+      "step": 460
+    },
+    {
+      "epoch": 0.20160857908847185,
+      "grad_norm": 0.9269851446151733,
+      "learning_rate": 0.00018503461346431604,
+      "loss": 2.03293399810791,
+      "step": 470
+    },
+    {
+      "epoch": 0.20589812332439678,
+      "grad_norm": 0.8605597019195557,
+      "learning_rate": 0.00018429558671451064,
+      "loss": 2.118448257446289,
+      "step": 480
+    },
+    {
+      "epoch": 0.21018766756032173,
+      "grad_norm": 0.897239625453949,
+      "learning_rate": 0.00018354030026947456,
+      "loss": 1.9954294204711913,
+      "step": 490
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 0.867357611656189,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 2.3360008239746093,
+      "step": 500
+    },
+    {
+      "epoch": 0.21876675603217158,
+      "grad_norm": 0.7812759280204773,
+      "learning_rate": 0.000181981534147851,
+      "loss": 2.0705078125,
+      "step": 510
+    },
+    {
+      "epoch": 0.2230563002680965,
+      "grad_norm": 0.8635934591293335,
+      "learning_rate": 0.0001811783551401723,
+      "loss": 2.165178108215332,
+      "step": 520
+    },
+    {
+      "epoch": 0.22734584450402145,
+      "grad_norm": 1.018941879272461,
+      "learning_rate": 0.0001803595177170848,
+      "loss": 2.1993284225463867,
+      "step": 530
+    },
+    {
+      "epoch": 0.23163538873994638,
+      "grad_norm": 0.811452329158783,
+      "learning_rate": 0.00017952517982335712,
+      "loss": 2.1670595169067384,
+      "step": 540
+    },
+    {
+      "epoch": 0.2359249329758713,
+      "grad_norm": 0.8488320708274841,
+      "learning_rate": 0.00017867550239362894,
+      "loss": 2.068050575256348,
+      "step": 550
+    },
+    {
+      "epoch": 0.24021447721179626,
+      "grad_norm": 1.1068885326385498,
+      "learning_rate": 0.00017781064932136835,
+      "loss": 2.211918067932129,
+      "step": 560
+    },
+    {
+      "epoch": 0.24450402144772118,
+      "grad_norm": 0.8777617812156677,
+      "learning_rate": 0.00017693078742725865,
+      "loss": 1.995230484008789,
+      "step": 570
+    },
+    {
+      "epoch": 0.2487935656836461,
+      "grad_norm": 0.841608464717865,
+      "learning_rate": 0.00017603608642702045,
+      "loss": 2.093342399597168,
+      "step": 580
+    },
+    {
+      "epoch": 0.25308310991957106,
+      "grad_norm": 0.843050479888916,
+      "learning_rate": 0.00017512671889867535,
+      "loss": 2.0501258850097654,
+      "step": 590
+    },
+    {
+      "epoch": 0.257372654155496,
+      "grad_norm": 0.755862832069397,
+      "learning_rate": 0.00017420286024925758,
+      "loss": 2.1583385467529297,
+      "step": 600
+    },
+    {
+      "epoch": 0.2616621983914209,
+      "grad_norm": 0.7975772023200989,
+      "learning_rate": 0.00017326468868097985,
+      "loss": 2.170749282836914,
+      "step": 610
+    },
+    {
+      "epoch": 0.26595174262734583,
+      "grad_norm": 0.9260276556015015,
+      "learning_rate": 0.0001723123851568602,
+      "loss": 2.2822845458984373,
+      "step": 620
+    },
+    {
+      "epoch": 0.27024128686327076,
+      "grad_norm": 0.6979662179946899,
+      "learning_rate": 0.00017134613336581599,
+      "loss": 2.251565933227539,
+      "step": 630
+    },
+    {
+      "epoch": 0.27453083109919574,
+      "grad_norm": 0.7494871616363525,
+      "learning_rate": 0.00017036611968723265,
+      "loss": 2.2115200042724608,
+      "step": 640
+    },
+    {
+      "epoch": 0.27882037533512066,
+      "grad_norm": 0.8637067079544067,
+      "learning_rate": 0.00016937253315501278,
+      "loss": 2.0511417388916016,
+      "step": 650
+    },
+    {
+      "epoch": 0.2831099195710456,
+      "grad_norm": 0.9787566661834717,
+      "learning_rate": 0.0001683655654211139,
+      "loss": 2.109568214416504,
+      "step": 660
+    },
+    {
+      "epoch": 0.2873994638069705,
+      "grad_norm": 0.870245635509491,
+      "learning_rate": 0.00016734541071858065,
+      "loss": 2.118773651123047,
+      "step": 670
+    },
+    {
+      "epoch": 0.29168900804289544,
+      "grad_norm": 1.0233336687088013,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 2.110629081726074,
+      "step": 680
+    },
+    {
+      "epoch": 0.29597855227882036,
+      "grad_norm": 0.9542198777198792,
+      "learning_rate": 0.0001652663300199427,
+      "loss": 2.0503299713134764,
+      "step": 690
+    },
+    {
+      "epoch": 0.3002680965147453,
+      "grad_norm": 0.9004696011543274,
+      "learning_rate": 0.00016420780505572871,
+      "loss": 2.0273651123046874,
+      "step": 700
+    },
+    {
+      "epoch": 0.30455764075067027,
+      "grad_norm": 0.7856536507606506,
+      "learning_rate": 0.00016313689510930713,
+      "loss": 1.978914451599121,
+      "step": 710
+    },
+    {
+      "epoch": 0.3088471849865952,
+      "grad_norm": 0.7488994598388672,
+      "learning_rate": 0.000162053806747475,
+      "loss": 2.0931522369384767,
+      "step": 720
+    },
+    {
+      "epoch": 0.3131367292225201,
+      "grad_norm": 0.8158746361732483,
+      "learning_rate": 0.0001609587488861122,
+      "loss": 2.0451580047607423,
+      "step": 730
+    },
+    {
+      "epoch": 0.31742627345844504,
+      "grad_norm": 0.8352906107902527,
+      "learning_rate": 0.00015985193274988397,
+      "loss": 1.9119682312011719,
+      "step": 740
+    },
+    {
+      "epoch": 0.32171581769436997,
+      "grad_norm": 0.9240970611572266,
+      "learning_rate": 0.00015873357183149805,
+      "loss": 1.9821479797363282,
+      "step": 750
+    },
+    {
+      "epoch": 0.3260053619302949,
+      "grad_norm": 0.9190706610679626,
+      "learning_rate": 0.00015760388185052398,
+      "loss": 2.0633893966674806,
+      "step": 760
+    },
+    {
+      "epoch": 0.3302949061662198,
+      "grad_norm": 1.095713496208191,
+      "learning_rate": 0.0001564630807117836,
+      "loss": 1.9157102584838868,
+      "step": 770
+    },
+    {
+      "epoch": 0.3345844504021448,
+      "grad_norm": 0.9237125515937805,
+      "learning_rate": 0.00015531138846331917,
+      "loss": 1.850246047973633,
+      "step": 780
+    },
+    {
+      "epoch": 0.3388739946380697,
+      "grad_norm": 0.9540524482727051,
+      "learning_rate": 0.00015414902725394884,
+      "loss": 2.1009103775024416,
+      "step": 790
+    },
+    {
+      "epoch": 0.34316353887399464,
+      "grad_norm": 1.1622545719146729,
+      "learning_rate": 0.0001529762212904164,
+      "loss": 1.938945198059082,
+      "step": 800
+    },
+    {
+      "epoch": 0.34745308310991957,
+      "grad_norm": 0.8726609945297241,
+      "learning_rate": 0.00015179319679414424,
+      "loss": 1.9050867080688476,
+      "step": 810
+    },
+    {
+      "epoch": 0.3517426273458445,
+      "grad_norm": 0.9203391075134277,
+      "learning_rate": 0.00015060018195759786,
+      "loss": 2.1391984939575197,
+      "step": 820
+    },
+    {
+      "epoch": 0.3560321715817694,
+      "grad_norm": 0.7829976677894592,
+      "learning_rate": 0.00014939740690026989,
+      "loss": 2.2050710678100587,
+      "step": 830
+    },
+    {
+      "epoch": 0.36032171581769434,
+      "grad_norm": 0.9230726361274719,
+      "learning_rate": 0.0001481851036242927,
+      "loss": 2.0734573364257813,
+      "step": 840
+    },
+    {
+      "epoch": 0.3646112600536193,
+      "grad_norm": 0.8753212094306946,
+      "learning_rate": 0.00014696350596968754,
+      "loss": 1.9630931854248046,
+      "step": 850
+    },
+    {
+      "epoch": 0.36890080428954425,
+      "grad_norm": 0.978103518486023,
+      "learning_rate": 0.00014573284956925962,
+      "loss": 2.0805789947509767,
+      "step": 860
+    },
+    {
+      "epoch": 0.3731903485254692,
+      "grad_norm": 0.9865938425064087,
+      "learning_rate": 0.00014449337180314682,
+      "loss": 2.2181297302246095,
+      "step": 870
+    },
+    {
+      "epoch": 0.3774798927613941,
+      "grad_norm": 1.0393383502960205,
+      "learning_rate": 0.00014324531175303201,
+      "loss": 2.2023292541503907,
+      "step": 880
+    },
+    {
+      "epoch": 0.381769436997319,
+      "grad_norm": 0.7477746605873108,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 2.034115219116211,
+      "step": 890
+    },
+    {
+      "epoch": 0.38605898123324395,
+      "grad_norm": 0.9086453318595886,
+      "learning_rate": 0.0001407244093582346,
+      "loss": 1.9091089248657227,
+      "step": 900
+    },
+    {
+      "epoch": 0.3903485254691689,
+      "grad_norm": 0.9519720673561096,
+      "learning_rate": 0.0001394520532680078,
+      "loss": 1.9923809051513672,
+      "step": 910
+    },
+    {
+      "epoch": 0.39463806970509385,
+      "grad_norm": 0.7883255481719971,
+      "learning_rate": 0.00013817208730889746,
+      "loss": 2.046986389160156,
+      "step": 920
+    },
+    {
+      "epoch": 0.3989276139410188,
+      "grad_norm": 0.8608978390693665,
+      "learning_rate": 0.00013688475837231518,
+      "loss": 2.015116310119629,
+      "step": 930
+    },
+    {
+      "epoch": 0.4032171581769437,
+      "grad_norm": 0.9121685028076172,
+      "learning_rate": 0.00013559031476991035,
+      "loss": 1.9490964889526368,
+      "step": 940
+    },
+    {
+      "epoch": 0.4075067024128686,
+      "grad_norm": 0.8510801196098328,
+      "learning_rate": 0.00013428900618567342,
+      "loss": 1.9338602066040038,
+      "step": 950
+    },
+    {
+      "epoch": 0.41179624664879355,
+      "grad_norm": 0.8185077905654907,
+      "learning_rate": 0.0001329810836277746,
+      "loss": 2.2588035583496096,
+      "step": 960
+    },
+    {
+      "epoch": 0.4160857908847185,
+      "grad_norm": 0.8846076130867004,
+      "learning_rate": 0.00013166679938014726,
+      "loss": 1.9654979705810547,
+      "step": 970
+    },
+    {
+      "epoch": 0.42037533512064346,
+      "grad_norm": 0.8377469182014465,
+      "learning_rate": 0.0001303464069538249,
+      "loss": 2.033038330078125,
+      "step": 980
+    },
+    {
+      "epoch": 0.4246648793565684,
+      "grad_norm": 0.8446090817451477,
+      "learning_rate": 0.00012902016103804188,
+      "loss": 2.0526477813720705,
+      "step": 990
+    },
+    {
+      "epoch": 0.4289544235924933,
+      "grad_norm": 0.8034592270851135,
+      "learning_rate": 0.0001276883174511065,
+      "loss": 1.9629634857177733,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43324396782841823,
+      "grad_norm": 0.7568860054016113,
+      "learning_rate": 0.0001263511330910565,
+      "loss": 2.1565860748291015,
+      "step": 1010
+    },
+    {
+      "epoch": 0.43753351206434316,
+      "grad_norm": 0.9239974617958069,
+      "learning_rate": 0.0001250088658861063,
+      "loss": 2.024600028991699,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4418230563002681,
+      "grad_norm": 1.1254358291625977,
+      "learning_rate": 0.00012366177474489536,
+      "loss": 1.9708271026611328,
+      "step": 1030
+    },
+    {
+      "epoch": 0.446112600536193,
+      "grad_norm": 0.9336352944374084,
+      "learning_rate": 0.00012231011950654763,
+      "loss": 2.0802404403686525,
+      "step": 1040
+    },
+    {
+      "epoch": 0.450402144772118,
+      "grad_norm": 1.0495727062225342,
+      "learning_rate": 0.00012095416089055136,
+      "loss": 1.8638420104980469,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4546916890080429,
+      "grad_norm": 0.8139879703521729,
+      "learning_rate": 0.00011959416044646926,
+      "loss": 1.9255853652954102,
+      "step": 1060
+    },
+    {
+      "epoch": 0.45898123324396783,
+      "grad_norm": 0.9188793897628784,
+      "learning_rate": 0.00011823038050348838,
+      "loss": 1.9905168533325195,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46327077747989276,
+      "grad_norm": 1.086055040359497,
+      "learning_rate": 0.00011686308411981965,
+      "loss": 2.0909515380859376,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4675603217158177,
+      "grad_norm": 1.1240793466567993,
+      "learning_rate": 0.00011549253503195705,
+      "loss": 1.823994255065918,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4718498659517426,
+      "grad_norm": 0.9709937572479248,
+      "learning_rate": 0.00011411899760380532,
+      "loss": 2.07696475982666,
+      "step": 1100
+    },
+    {
+      "epoch": 0.47613941018766753,
+      "grad_norm": 0.7949770092964172,
+      "learning_rate": 0.00011274273677568754,
+      "loss": 1.9337072372436523,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4804289544235925,
+      "grad_norm": 0.9525244235992432,
+      "learning_rate": 0.00011136401801324061,
+      "loss": 2.1522342681884767,
+      "step": 1120
+    },
+    {
+      "epoch": 0.48471849865951744,
+      "grad_norm": 0.8864313364028931,
+      "learning_rate": 0.00010998310725621024,
+      "loss": 2.048630142211914,
+      "step": 1130
+    },
+    {
+      "epoch": 0.48900804289544236,
+      "grad_norm": 0.9325012564659119,
+      "learning_rate": 0.00010860027086715365,
+      "loss": 2.029229164123535,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4932975871313673,
+      "grad_norm": 1.0433061122894287,
+      "learning_rate": 0.00010721577558006164,
+      "loss": 1.873429298400879,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4975871313672922,
+      "grad_norm": 0.9790089726448059,
+      "learning_rate": 0.000105829888448908,
+      "loss": 1.9442827224731445,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5018766756032171,
+      "grad_norm": 0.8827151656150818,
+      "learning_rate": 0.00010444287679613824,
+      "loss": 2.090526008605957,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5061662198391421,
+      "grad_norm": 0.8394389748573303,
+      "learning_rate": 0.00010305500816110558,
+      "loss": 1.854716682434082,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510455764075067,
+      "grad_norm": 0.9192520380020142,
+      "learning_rate": 0.00010166655024846588,
+      "loss": 1.9326051712036132,
+      "step": 1190
+    },
+    {
+      "epoch": 0.514745308310992,
+      "grad_norm": 1.0769872665405273,
+      "learning_rate": 0.00010027777087654004,
+      "loss": 2.132567024230957,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5190348525469168,
+      "grad_norm": 1.0510156154632568,
+      "learning_rate": 9.888893792565508e-05,
+      "loss": 2.066767120361328,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5233243967828418,
+      "grad_norm": 0.9253979921340942,
+      "learning_rate": 9.750031928647269e-05,
+      "loss": 2.0386857986450195,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5276139410187668,
+      "grad_norm": 0.8134991526603699,
+      "learning_rate": 9.611218280831633e-05,
+      "loss": 1.9016380310058594,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5319034852546917,
+      "grad_norm": 0.9360663890838623,
+      "learning_rate": 9.472479624750574e-05,
+      "loss": 1.9612478256225585,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5361930294906166,
+      "grad_norm": 0.867996871471405,
+      "learning_rate": 9.333842721570982e-05,
+      "loss": 1.7373517990112304,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5404825737265415,
+      "grad_norm": 0.8762718439102173,
+      "learning_rate": 9.195334312832742e-05,
+      "loss": 2.180467414855957,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5447721179624665,
+      "grad_norm": 1.0470011234283447,
+      "learning_rate": 9.056981115290553e-05,
+      "loss": 2.0069679260253905,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5490616621983915,
+      "grad_norm": 0.9644089937210083,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 2.1384710311889648,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5533512064343163,
+      "grad_norm": 1.1095678806304932,
+      "learning_rate": 8.780847065972862e-05,
+      "loss": 2.0052122116088866,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5576407506702413,
+      "grad_norm": 0.8349754810333252,
+      "learning_rate": 8.643119477430464e-05,
+      "loss": 2.039333724975586,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5619302949061662,
+      "grad_norm": 1.2297779321670532,
+      "learning_rate": 8.505653616276427e-05,
+      "loss": 1.9761917114257812,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5662198391420912,
+      "grad_norm": 0.7800212502479553,
+      "learning_rate": 8.368475998169455e-05,
+      "loss": 2.067928504943848,
+      "step": 1320
+    },
+    {
+      "epoch": 0.570509383378016,
+      "grad_norm": 0.7608606219291687,
+      "learning_rate": 8.231613083169308e-05,
+      "loss": 2.085641288757324,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574798927613941,
+      "grad_norm": 0.8361881375312805,
+      "learning_rate": 8.095091270632988e-05,
+      "loss": 2.0933313369750977,
+      "step": 1340
+    },
+    {
+      "epoch": 0.579088471849866,
+      "grad_norm": 0.965336799621582,
+      "learning_rate": 7.958936894122548e-05,
+      "loss": 1.911599349975586,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833780160857909,
+      "grad_norm": 0.8643521666526794,
+      "learning_rate": 7.823176216325662e-05,
+      "loss": 1.9457710266113282,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5876675603217159,
+      "grad_norm": 0.9850629568099976,
+      "learning_rate": 7.687835423989846e-05,
+      "loss": 1.9454130172729491,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5919571045576407,
+      "grad_norm": 0.9901652932167053,
+      "learning_rate": 7.552940622871297e-05,
+      "loss": 2.0675596237182616,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5962466487935657,
+      "grad_norm": 0.9328491687774658,
+      "learning_rate": 7.418517832699397e-05,
+      "loss": 1.9514102935791016,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6005361930294906,
+      "grad_norm": 0.9820194244384766,
+      "learning_rate": 7.284592982157783e-05,
+      "loss": 1.8550071716308594,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6048257372654156,
+      "grad_norm": 1.116490364074707,
+      "learning_rate": 7.151191903883001e-05,
+      "loss": 1.8897455215454102,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6091152815013405,
+      "grad_norm": 0.9118836522102356,
+      "learning_rate": 7.018340329481663e-05,
+      "loss": 2.0071475982666014,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6134048257372654,
+      "grad_norm": 1.204563856124878,
+      "learning_rate": 6.886063884567088e-05,
+      "loss": 1.8896291732788086,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6176943699731904,
+      "grad_norm": 1.017662763595581,
+      "learning_rate": 6.754388083816444e-05,
+      "loss": 2.0115915298461915,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6219839142091153,
+      "grad_norm": 0.938076376914978,
+      "learning_rate": 6.623338326049197e-05,
+      "loss": 1.8918901443481446,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6262734584450402,
+      "grad_norm": 0.9555648565292358,
+      "learning_rate": 6.492939889327991e-05,
+      "loss": 2.162403106689453,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6305630026809651,
+      "grad_norm": 0.9676245450973511,
+      "learning_rate": 6.36321792608277e-05,
+      "loss": 2.0239980697631834,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6348525469168901,
+      "grad_norm": 1.0883864164352417,
+      "learning_rate": 6.234197458259164e-05,
+      "loss": 2.042740058898926,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6391420911528151,
+      "grad_norm": 1.045640230178833,
+      "learning_rate": 6.105903372492006e-05,
+      "loss": 1.876373863220215,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6434316353887399,
+      "grad_norm": 0.9459392428398132,
+      "learning_rate": 5.9783604153049996e-05,
+      "loss": 1.9611021041870118,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6477211796246649,
+      "grad_norm": 0.8113487362861633,
+      "learning_rate": 5.851593188337374e-05,
+      "loss": 1.8251832962036132,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6520107238605898,
+      "grad_norm": 0.7706234455108643,
+      "learning_rate": 5.725626143598492e-05,
+      "loss": 1.9497014999389648,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6563002680965148,
+      "grad_norm": 0.8590229749679565,
+      "learning_rate": 5.600483578751332e-05,
+      "loss": 1.9892189025878906,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6605898123324396,
+      "grad_norm": 0.9329735040664673,
+      "learning_rate": 5.476189632425732e-05,
+      "loss": 2.0406734466552736,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6648793565683646,
+      "grad_norm": 0.8616867661476135,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 2.088255500793457,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6691689008042896,
+      "grad_norm": 0.8837583661079407,
+      "learning_rate": 5.230243326787987e-05,
+      "loss": 2.218942642211914,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6734584450402145,
+      "grad_norm": 1.0596973896026611,
+      "learning_rate": 5.108638407823891e-05,
+      "loss": 1.9535799026489258,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6777479892761394,
+      "grad_norm": 0.8518194556236267,
+      "learning_rate": 4.987976978926732e-05,
+      "loss": 2.062208557128906,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6820375335120643,
+      "grad_norm": 0.8575644493103027,
+      "learning_rate": 4.8682823143643144e-05,
+      "loss": 1.901092529296875,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6863270777479893,
+      "grad_norm": 1.1114495992660522,
+      "learning_rate": 4.7495775019261934e-05,
+      "loss": 2.0766841888427736,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6906166219839142,
+      "grad_norm": 0.8162066340446472,
+      "learning_rate": 4.631885438470294e-05,
+      "loss": 2.0174964904785155,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6949061662198391,
+      "grad_norm": 1.0020586252212524,
+      "learning_rate": 4.515228825506356e-05,
+      "loss": 2.0796960830688476,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6991957104557641,
+      "grad_norm": 0.6889837384223938,
+      "learning_rate": 4.3996301648170625e-05,
+      "loss": 1.974833869934082,
+      "step": 1630
+    },
+    {
+      "epoch": 0.703485254691689,
+      "grad_norm": 0.8110519647598267,
+      "learning_rate": 4.2851117541176946e-05,
+      "loss": 1.9366495132446289,
+      "step": 1640
+    },
+    {
+      "epoch": 0.707774798927614,
+      "grad_norm": 0.93631511926651,
+      "learning_rate": 4.1716956827551366e-05,
+      "loss": 1.8632808685302735,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7120643431635388,
+      "grad_norm": 1.289156436920166,
+      "learning_rate": 4.05940382744711e-05,
+      "loss": 1.9934736251831056,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7163538873994638,
+      "grad_norm": 0.7346325516700745,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 2.129100227355957,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7206434316353887,
+      "grad_norm": 0.8185448050498962,
+      "learning_rate": 3.8382791834426925e-05,
+      "loss": 2.0799833297729493,
+      "step": 1680
+    },
+    {
+      "epoch": 0.7249329758713137,
+      "grad_norm": 1.1663485765457153,
+      "learning_rate": 3.729489047267746e-05,
+      "loss": 2.0275983810424805,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7292225201072386,
+      "grad_norm": 0.9577205181121826,
+      "learning_rate": 3.6219084239629995e-05,
+      "loss": 1.939921760559082,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335120643431635,
+      "grad_norm": 0.9435138702392578,
+      "learning_rate": 3.5155580646521503e-05,
+      "loss": 1.81829776763916,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7378016085790885,
+      "grad_norm": 1.3241472244262695,
+      "learning_rate": 3.410458483154455e-05,
+      "loss": 1.8586637496948242,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7420911528150134,
+      "grad_norm": 1.2306301593780518,
+      "learning_rate": 3.306629952027841e-05,
+      "loss": 2.099422836303711,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7463806970509383,
+      "grad_norm": 1.1324083805084229,
+      "learning_rate": 3.204092498658534e-05,
+      "loss": 1.9230274200439452,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7506702412868632,
+      "grad_norm": 1.1115933656692505,
+      "learning_rate": 3.1028659013979965e-05,
+      "loss": 2.031582069396973,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7549597855227882,
+      "grad_norm": 0.8495458364486694,
+      "learning_rate": 3.0029696857479263e-05,
+      "loss": 1.9778030395507813,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7592493297587132,
+      "grad_norm": 1.0844917297363281,
+      "learning_rate": 2.9044231205939687e-05,
+      "loss": 2.0065166473388674,
+      "step": 1770
+    },
+    {
+      "epoch": 0.763538873994638,
+      "grad_norm": 1.0366203784942627,
+      "learning_rate": 2.8072452144889795e-05,
+      "loss": 1.82503662109375,
+      "step": 1780
+    },
+    {
+      "epoch": 0.767828418230563,
+      "grad_norm": 0.8720079064369202,
+      "learning_rate": 2.711454711986474e-05,
+      "loss": 1.9994165420532226,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7721179624664879,
+      "grad_norm": 0.9573290944099426,
+      "learning_rate": 2.6170700900250144e-05,
+      "loss": 1.9931180953979493,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7764075067024129,
+      "grad_norm": 0.8816791772842407,
+      "learning_rate": 2.5241095543642057e-05,
+      "loss": 2.091500663757324,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7806970509383379,
+      "grad_norm": 1.289235234260559,
+      "learning_rate": 2.4325910360730063e-05,
+      "loss": 2.0379024505615235,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7849865951742627,
+      "grad_norm": 1.1555016040802002,
+      "learning_rate": 2.3425321880710237e-05,
+      "loss": 1.9599458694458007,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7892761394101877,
+      "grad_norm": 1.0887123346328735,
+      "learning_rate": 2.2539503817234553e-05,
+      "loss": 1.9658329010009765,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7935656836461126,
+      "grad_norm": 0.8617165684700012,
+      "learning_rate": 2.166862703490342e-05,
+      "loss": 1.8620195388793945,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7978552278820376,
+      "grad_norm": 0.9495421648025513,
+      "learning_rate": 2.0812859516307815e-05,
+      "loss": 1.9315826416015625,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8021447721179624,
+      "grad_norm": 1.0425649881362915,
+      "learning_rate": 1.997236632962728e-05,
+      "loss": 1.8580461502075196,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8064343163538874,
+      "grad_norm": 0.8383308053016663,
+      "learning_rate": 1.914730959679002e-05,
+      "loss": 2.0951725006103517,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8107238605898124,
+      "grad_norm": 1.1160863637924194,
+      "learning_rate": 1.8337848462201424e-05,
+      "loss": 2.0154560089111326,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8150134048257373,
+      "grad_norm": 0.9295897483825684,
+      "learning_rate": 1.7544139062046827e-05,
+      "loss": 2.205696678161621,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8193029490616622,
+      "grad_norm": 0.8836671113967896,
+      "learning_rate": 1.6766334494174517e-05,
+      "loss": 1.996354103088379,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8235924932975871,
+      "grad_norm": 0.9026775360107422,
+      "learning_rate": 1.6004584788564915e-05,
+      "loss": 1.8099235534667968,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8278820375335121,
+      "grad_norm": 0.9994946718215942,
+      "learning_rate": 1.5259036878391343e-05,
+      "loss": 1.9028573989868165,
+      "step": 1930
+    },
+    {
+      "epoch": 0.832171581769437,
+      "grad_norm": 0.9214305281639099,
+      "learning_rate": 1.4529834571678336e-05,
+      "loss": 1.7730764389038085,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8364611260053619,
+      "grad_norm": 0.8134130835533142,
+      "learning_rate": 1.3817118523562555e-05,
+      "loss": 1.9758581161499023,
+      "step": 1950
+    },
+    {
+      "epoch": 0.8407506702412869,
+      "grad_norm": 1.0482189655303955,
+      "learning_rate": 1.3121026209161935e-05,
+      "loss": 1.8773077011108399,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8450402144772118,
+      "grad_norm": 0.7803096771240234,
+      "learning_rate": 1.2441691897058317e-05,
+      "loss": 1.7848268508911134,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8493297587131368,
+      "grad_norm": 0.8199278712272644,
+      "learning_rate": 1.1779246623398543e-05,
+      "loss": 1.9367828369140625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8536193029490616,
+      "grad_norm": 0.9916271567344666,
+      "learning_rate": 1.1133818166618903e-05,
+      "loss": 1.9832647323608399,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8579088471849866,
+      "grad_norm": 0.8474291563034058,
+      "learning_rate": 1.0505531022798088e-05,
+      "loss": 1.9872703552246094,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8621983914209115,
+      "grad_norm": 1.149411678314209,
+      "learning_rate": 9.894506381643332e-06,
+      "loss": 1.9120725631713866,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8664879356568365,
+      "grad_norm": 0.9936849474906921,
+      "learning_rate": 9.300862103114283e-06,
+      "loss": 1.892692756652832,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8707774798927614,
+      "grad_norm": 0.9433305263519287,
+      "learning_rate": 8.724712694688963e-06,
+      "loss": 1.9666515350341798,
+      "step": 2030
+    },
+    {
+      "epoch": 0.8750670241286863,
+      "grad_norm": 0.8228591680526733,
+      "learning_rate": 8.16616928927656e-06,
+      "loss": 1.8853214263916016,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8793565683646113,
+      "grad_norm": 0.8398504853248596,
+      "learning_rate": 7.62533962378128e-06,
+      "loss": 1.8661935806274415,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8836461126005362,
+      "grad_norm": 0.9766001105308533,
+      "learning_rate": 7.102328018320858e-06,
+      "loss": 2.025430107116699,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8879356568364611,
+      "grad_norm": 1.0431119203567505,
+      "learning_rate": 6.59723535610447e-06,
+      "loss": 1.8737388610839845,
+      "step": 2070
+    },
+    {
+      "epoch": 0.892225201072386,
+      "grad_norm": 0.9454013109207153,
+      "learning_rate": 6.110159063973419e-06,
+      "loss": 1.9102716445922852,
+      "step": 2080
+    },
+    {
+      "epoch": 0.896514745308311,
+      "grad_norm": 1.2222461700439453,
+      "learning_rate": 5.641193093608632e-06,
+      "loss": 1.8740365982055665,
+      "step": 2090
+    },
+    {
+      "epoch": 0.900804289544236,
+      "grad_norm": 0.842519998550415,
+      "learning_rate": 5.190427903408313e-06,
+      "loss": 1.8746870040893555,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9050938337801608,
+      "grad_norm": 0.7582686543464661,
+      "learning_rate": 4.757950441039594e-06,
+      "loss": 1.9830608367919922,
+      "step": 2110
+    },
+    {
+      "epoch": 0.9093833780160858,
+      "grad_norm": 0.9554128646850586,
+      "learning_rate": 4.343844126667229e-06,
+      "loss": 1.873980712890625,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9136729222520107,
+      "grad_norm": 0.8336243033409119,
+      "learning_rate": 3.948188836862776e-06,
+      "loss": 2.0840463638305664,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9179624664879357,
+      "grad_norm": 0.8276010155677795,
+      "learning_rate": 3.5710608891972976e-06,
+      "loss": 1.8817314147949218,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9222520107238605,
+      "grad_norm": 0.9805457592010498,
+      "learning_rate": 3.2125330275205147e-06,
+      "loss": 1.8696676254272462,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9265415549597855,
+      "grad_norm": 0.9226967096328735,
+      "learning_rate": 2.87267440792931e-06,
+      "loss": 2.1158275604248047,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9308310991957105,
+      "grad_norm": 1.1522666215896606,
+      "learning_rate": 2.5515505854283196e-06,
+      "loss": 1.8417831420898438,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9351206434316354,
+      "grad_norm": 0.9451821446418762,
+      "learning_rate": 2.249223501285003e-06,
+      "loss": 1.9700094223022462,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9394101876675603,
+      "grad_norm": 0.924561083316803,
+      "learning_rate": 1.965751471081978e-06,
+      "loss": 1.8976779937744142,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9436997319034852,
+      "grad_norm": 1.2159491777420044,
+      "learning_rate": 1.7011891734684538e-06,
+      "loss": 2.063970184326172,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2332,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.217221435041792e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

security/outputs/phishsense-phishing-lora/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

security/outputs/phishsense-phishing-lora/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/phishsense-phishing-lora/adapter_model.safetensors",
+  "latest_mtime": 1777324104.3519826,
+  "latest_mtime_iso": "2026-04-27T21:08:24.351983+00:00",
+  "size_bytes": 45118424,
+  "epoch": null
+}

security/outputs/secbert-phishing-classifier/config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Phishing Email",
+    "1": "Safe Email"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Phishing Email": 0,
+    "Safe Email": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 52000
+}

security/outputs/secbert-phishing-classifier/label_mapping.json

@@ -0,0 +1,23 @@
+{
+  "label2id": {
+    "Phishing Email": 0,
+    "Safe Email": 1
+  },
+  "id2label": {
+    "0": "Phishing Email",
+    "1": "Safe Email"
+  },
+  "text_col": "Email Text",
+  "label_col": "Email Type",
+  "metrics": {
+    "eval_loss": 0.2722574770450592,
+    "eval_accuracy": 1.0,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_f1": 1.0,
+    "eval_runtime": 0.0291,
+    "eval_samples_per_second": 102.997,
+    "eval_steps_per_second": 34.332,
+    "epoch": 1.0
+  }
+}

security/outputs/secbert-phishing-classifier/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

security/outputs/secbert-phishing-classifier/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/secbert-phishing-classifier/training_args.bin",
+  "latest_mtime": 1777558880.1854646,
+  "latest_mtime_iso": "2026-04-30T14:21:20.185465+00:00",
+  "size_bytes": 5329,
+  "epoch": null
+}

security/outputs/securityllm-10datasets-lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/SecurityLLM
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/SecurityLLM
+- 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 0.19.1

security/outputs/securityllm-10datasets-lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/SecurityLLM",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/securityllm-10datasets-lora/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

security/outputs/securityllm-10datasets-lora/checkpoint-28600/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/SecurityLLM
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/SecurityLLM
+- 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 0.19.1

security/outputs/securityllm-10datasets-lora/checkpoint-28600/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/SecurityLLM",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/securityllm-10datasets-lora/checkpoint-28600/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

security/outputs/securityllm-10datasets-lora/checkpoint-28600/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

security/outputs/securityllm-10datasets-lora/checkpoint-28600/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/securityllm-10datasets-lora/checkpoint-28600/optimizer.pt",
+  "latest_mtime": 1777492088.8392105,
+  "latest_mtime_iso": "2026-04-29T19:48:08.839211+00:00",
+  "size_bytes": 335922851,
+  "epoch": null
+}

security/outputs/securityllm-10datasets-lora/checkpoint-28647/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/SecurityLLM
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/SecurityLLM
+- 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 0.19.1

security/outputs/securityllm-10datasets-lora/checkpoint-28647/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/SecurityLLM",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/securityllm-10datasets-lora/checkpoint-28647/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

security/outputs/securityllm-10datasets-lora/checkpoint-28647/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

security/outputs/securityllm-10datasets-lora/checkpoint-28647/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/securityllm-10datasets-lora/checkpoint-28647/rng_state.pth",
+  "latest_mtime": 1777492358.7721028,
+  "latest_mtime_iso": "2026-04-29T19:52:38.772103+00:00",
+  "size_bytes": 14645,
+  "epoch": null
+}

security/outputs/securityllm-10datasets-lora/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

security/outputs/securityllm-10datasets-lora/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/securityllm-10datasets-lora/adapter_model.safetensors",
+  "latest_mtime": 1777492359.1841102,
+  "latest_mtime_iso": "2026-04-29T19:52:39.184110+00:00",
+  "size_bytes": 167832240,
+  "epoch": null
+}

security/outputs/securityllm-rules-lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/security/models/SecurityLLM
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/security/models/SecurityLLM
+- 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 0.19.1

security/outputs/securityllm-rules-lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/security/models/SecurityLLM",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

security/outputs/securityllm-rules-lora/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

security/outputs/securityllm-rules-lora/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

security/outputs/securityllm-rules-lora/training_info.json

@@ -0,0 +1,7 @@
+{
+  "latest_checkpoint": "security/outputs/securityllm-rules-lora/adapter_model.safetensors",
+  "latest_mtime": 1777319946.9796846,
+  "latest_mtime_iso": "2026-04-27T19:59:06.979685+00:00",
+  "size_bytes": 167832240,
+  "epoch": null
+}