add v6

LLM-Detector-V6-11w/README.md

@@ -0,0 +1,56 @@
+---
+license: other
+base_model: ./Llama-2-13b-chat-hf
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: llama2-13b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama2-13b
+
+This model is a fine-tuned version of [./Llama-2-13b-chat-hf](https://huggingface.co/./Llama-2-13b-chat-hf) on the ta, the tb, the tc, the td, the te, the tf, the tg and the th datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.7
+- Tokenizers 0.13.3

LLM-Detector-V6-11w/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V6-11w/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b1594b4b57894996a8a0e4fda601e884eb91ce171da0bc1aa17e052d8249b2
+size 26272202

LLM-Detector-V6-11w/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

LLM-Detector-V6-11w/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.020508435523056583,
+    "train_runtime": 294350.325,
+    "train_samples_per_second": 1.212,
+    "train_steps_per_second": 0.076
+}

LLM-Detector-V6-11w/checkpoint-12000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Llama-2-13b-chat-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V6-11w/checkpoint-12000/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V6-11w/checkpoint-12000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5ebc56d0fa8867bd6469e26502e9f333a546f6afd7d90515551b6627616179
+size 26272202

LLM-Detector-V6-11w/checkpoint-12000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

LLM-Detector-V6-11w/checkpoint-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ea991e80cff4348770e2050d4688928ede14c7c9ca06a78973071b93984600
+size 52563258

LLM-Detector-V6-11w/checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33d807d5608cb92eac951b15c9f371121ed50fec11a5e4b7871c9fa594aff43
+size 14244

LLM-Detector-V6-11w/checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f15ee785078ff296bbc591ab3e9dfc50cf8cddc42a477dfe677cda389ba0dd
+size 1064

LLM-Detector-V6-11w/checkpoint-12000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

LLM-Detector-V6-11w/checkpoint-12000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

LLM-Detector-V6-11w/checkpoint-12000/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

LLM-Detector-V6-11w/checkpoint-12000/trainer_state.json

@@ -0,0 +1,739 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6144764723689078,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.9132,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0721,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0757,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0599,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9938477167054135e-05,
+      "loss": 0.0353,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911304569050045e-05,
+      "loss": 0.0256,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987918618733232e-05,
+      "loss": 0.0173,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.98421283985469e-05,
+      "loss": 0.0276,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9800138559988466e-05,
+      "loss": 0.0225,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.97532250081397e-05,
+      "loss": 0.026,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970139705701628e-05,
+      "loss": 0.0271,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9644664996317616e-05,
+      "loss": 0.0231,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958304008938407e-05,
+      "loss": 0.0196,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.951653457096072e-05,
+      "loss": 0.0124,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944516164476834e-05,
+      "loss": 0.0159,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368935480882034e-05,
+      "loss": 0.0144,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287871212917866e-05,
+      "loss": 0.0182,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201984935028426e-05,
+      "loss": 0.018,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911129369870746e-05,
+      "loss": 0.0156,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.90158155094046e-05,
+      "loss": 0.0146,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.8915569322950615e-05,
+      "loss": 0.0196,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8810575041794e-05,
+      "loss": 0.02,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8700853511049656e-05,
+      "loss": 0.0143,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858642651436035e-05,
+      "loss": 0.0111,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846731676957191e-05,
+      "loss": 0.0179,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.834354792422293e-05,
+      "loss": 0.0133,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.821514455084985e-05,
+      "loss": 0.0112,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8082132142108465e-05,
+      "loss": 0.0131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794453710571272e-05,
+      "loss": 0.0134,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780238675919182e-05,
+      "loss": 0.0084,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765570932446672e-05,
+      "loss": 0.0069,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.75045339222471e-05,
+      "loss": 0.0186,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734889056624983e-05,
+      "loss": 0.0138,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718881015724017e-05,
+      "loss": 0.012,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702432447689692e-05,
+      "loss": 0.0121,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.6855466181502544e-05,
+      "loss": 0.0104,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.66822687954598e-05,
+      "loss": 0.014,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.65047667046359e-05,
+      "loss": 0.0085,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.632299514953571e-05,
+      "loss": 0.0111,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0122,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0082,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0115,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0069,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0099,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0087,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.0096,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0122,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0076,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0071,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.0105,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0108,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0063,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0147,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0135,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0105,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0131,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0085,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0052,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.008,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.011,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.0074,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0147,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0049,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0075,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.995501009115527e-05,
+      "loss": 0.0114,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.967125281105033e-05,
+      "loss": 0.0089,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.93845827632495e-05,
+      "loss": 0.0066,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.909505686199625e-05,
+      "loss": 0.0079,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.880273258852296e-05,
+      "loss": 0.008,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.850766797963886e-05,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.8209921616207645e-05,
+      "loss": 0.0069,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790955261151704e-05,
+      "loss": 0.0088,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7606620599542756e-05,
+      "loss": 0.0078,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.730118572310899e-05,
+      "loss": 0.008,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699330862194794e-05,
+      "loss": 0.0057,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.668305042066061e-05,
+      "loss": 0.0046,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.637047271658145e-05,
+      "loss": 0.0059,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605563756754904e-05,
+      "loss": 0.0046,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.573860747958544e-05,
+      "loss": 0.0085,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.541944539448648e-05,
+      "loss": 0.0064,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509821467732553e-05,
+      "loss": 0.0064,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477822117325554e-05,
+      "loss": 0.0061,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.445306400520726e-05,
+      "loss": 0.0087,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.4126030066319e-05,
+      "loss": 0.0042,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379718428450832e-05,
+      "loss": 0.0071,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346659194740827e-05,
+      "loss": 0.0043,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.313431868940551e-05,
+      "loss": 0.0062,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.280043047860958e-05,
+      "loss": 0.0096,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.24649936037558e-05,
+      "loss": 0.0049,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.21280746610446e-05,
+      "loss": 0.0043,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.1789740540919856e-05,
+      "loss": 0.006,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.145005841478868e-05,
+      "loss": 0.0053,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.1109095721685525e-05,
+      "loss": 0.0075,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076692015488315e-05,
+      "loss": 0.0048,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0423599648453037e-05,
+      "loss": 0.0063,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.007920236377807e-05,
+      "loss": 0.0075,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9733796676020104e-05,
+      "loss": 0.0082,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938745116054501e-05,
+      "loss": 0.0054,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.9040234579308025e-05,
+      "loss": 0.0042,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8692215867202042e-05,
+      "loss": 0.0112,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.8343464118371603e-05,
+      "loss": 0.0059,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.7994048572495225e-05,
+      "loss": 0.0034,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0082,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0047,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0024,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.0041,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0041,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.0059,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0032,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.004,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0039,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.004,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.0033,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.0091,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0049,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0048,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0024,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0058,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0098,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 4.8461499181056e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V6-11w/checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e02268b0e5756331085a22abe601ecb2daf8e3353b9a1d6d712573829b67ec
+size 4600

LLM-Detector-V6-11w/checkpoint-15000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Llama-2-13b-chat-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V6-11w/checkpoint-15000/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V6-11w/checkpoint-15000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b386520c99e4898bf12c823d20e239ce7ad28309ca5f26cd345d039540a89ae
+size 26272202

LLM-Detector-V6-11w/checkpoint-15000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

LLM-Detector-V6-11w/checkpoint-15000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086743c5054ae9a32bdb5191c8908ad51ccacfe56f666c3e7b9b71ac75d2067c
+size 52563258

LLM-Detector-V6-11w/checkpoint-15000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdeeae0a2a5a5790ba34184ea3d0a0444eab2a77d95324fd4b9ab363762cf5e1
+size 14244

LLM-Detector-V6-11w/checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea05cc55f2f45f53b449edaad91d7b12c981326c2d9b625bf8e619db7e03be2
+size 1064

LLM-Detector-V6-11w/checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

LLM-Detector-V6-11w/checkpoint-15000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

LLM-Detector-V6-11w/checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

LLM-Detector-V6-11w/checkpoint-15000/trainer_state.json

@@ -0,0 +1,919 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.018095590461135,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.9132,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0721,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0757,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0599,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9938477167054135e-05,
+      "loss": 0.0353,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911304569050045e-05,
+      "loss": 0.0256,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987918618733232e-05,
+      "loss": 0.0173,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.98421283985469e-05,
+      "loss": 0.0276,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9800138559988466e-05,
+      "loss": 0.0225,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.97532250081397e-05,
+      "loss": 0.026,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970139705701628e-05,
+      "loss": 0.0271,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9644664996317616e-05,
+      "loss": 0.0231,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958304008938407e-05,
+      "loss": 0.0196,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.951653457096072e-05,
+      "loss": 0.0124,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944516164476834e-05,
+      "loss": 0.0159,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368935480882034e-05,
+      "loss": 0.0144,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287871212917866e-05,
+      "loss": 0.0182,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201984935028426e-05,
+      "loss": 0.018,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911129369870746e-05,
+      "loss": 0.0156,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.90158155094046e-05,
+      "loss": 0.0146,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.8915569322950615e-05,
+      "loss": 0.0196,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8810575041794e-05,
+      "loss": 0.02,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8700853511049656e-05,
+      "loss": 0.0143,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858642651436035e-05,
+      "loss": 0.0111,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846731676957191e-05,
+      "loss": 0.0179,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.834354792422293e-05,
+      "loss": 0.0133,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.821514455084985e-05,
+      "loss": 0.0112,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8082132142108465e-05,
+      "loss": 0.0131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794453710571272e-05,
+      "loss": 0.0134,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780238675919182e-05,
+      "loss": 0.0084,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765570932446672e-05,
+      "loss": 0.0069,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.75045339222471e-05,
+      "loss": 0.0186,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734889056624983e-05,
+      "loss": 0.0138,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718881015724017e-05,
+      "loss": 0.012,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702432447689692e-05,
+      "loss": 0.0121,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.6855466181502544e-05,
+      "loss": 0.0104,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.66822687954598e-05,
+      "loss": 0.014,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.65047667046359e-05,
+      "loss": 0.0085,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.632299514953571e-05,
+      "loss": 0.0111,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0122,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0082,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0115,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0069,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0099,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0087,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.0096,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0122,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0076,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0071,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.0105,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0108,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0063,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0147,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0135,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0105,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0131,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0085,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0052,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.008,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.011,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.0074,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0147,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0049,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0075,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.995501009115527e-05,
+      "loss": 0.0114,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.967125281105033e-05,
+      "loss": 0.0089,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.93845827632495e-05,
+      "loss": 0.0066,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.909505686199625e-05,
+      "loss": 0.0079,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.880273258852296e-05,
+      "loss": 0.008,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.850766797963886e-05,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.8209921616207645e-05,
+      "loss": 0.0069,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790955261151704e-05,
+      "loss": 0.0088,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7606620599542756e-05,
+      "loss": 0.0078,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.730118572310899e-05,
+      "loss": 0.008,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699330862194794e-05,
+      "loss": 0.0057,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.668305042066061e-05,
+      "loss": 0.0046,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.637047271658145e-05,
+      "loss": 0.0059,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605563756754904e-05,
+      "loss": 0.0046,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.573860747958544e-05,
+      "loss": 0.0085,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.541944539448648e-05,
+      "loss": 0.0064,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509821467732553e-05,
+      "loss": 0.0064,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477822117325554e-05,
+      "loss": 0.0061,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.445306400520726e-05,
+      "loss": 0.0087,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.4126030066319e-05,
+      "loss": 0.0042,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379718428450832e-05,
+      "loss": 0.0071,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346659194740827e-05,
+      "loss": 0.0043,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.313431868940551e-05,
+      "loss": 0.0062,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.280043047860958e-05,
+      "loss": 0.0096,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.24649936037558e-05,
+      "loss": 0.0049,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.21280746610446e-05,
+      "loss": 0.0043,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.1789740540919856e-05,
+      "loss": 0.006,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.145005841478868e-05,
+      "loss": 0.0053,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.1109095721685525e-05,
+      "loss": 0.0075,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076692015488315e-05,
+      "loss": 0.0048,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0423599648453037e-05,
+      "loss": 0.0063,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.007920236377807e-05,
+      "loss": 0.0075,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9733796676020104e-05,
+      "loss": 0.0082,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938745116054501e-05,
+      "loss": 0.0054,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.9040234579308025e-05,
+      "loss": 0.0042,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8692215867202042e-05,
+      "loss": 0.0112,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.8343464118371603e-05,
+      "loss": 0.0059,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.7994048572495225e-05,
+      "loss": 0.0034,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0082,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0047,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0024,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.0041,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0041,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.0059,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0032,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.004,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0039,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.004,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.0033,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.0091,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0049,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0048,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0024,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0058,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0098,
+      "step": 12000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.167050021988514e-05,
+      "loss": 0.0063,
+      "step": 12100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.1321720588848995e-05,
+      "loss": 0.0035,
+      "step": 12200
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.097367122765301e-05,
+      "loss": 0.0075,
+      "step": 12300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.0626421236526656e-05,
+      "loss": 0.0048,
+      "step": 12400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.0280039556995902e-05,
+      "loss": 0.0036,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9934594958195834e-05,
+      "loss": 0.0039,
+      "step": 12600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.9590156023217553e-05,
+      "loss": 0.0045,
+      "step": 12700
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.9250219243814994e-05,
+      "loss": 0.0051,
+      "step": 12800
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.8907984814652774e-05,
+      "loss": 0.0033,
+      "step": 12900
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8566959868093257e-05,
+      "loss": 0.0053,
+      "step": 13000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8227212109768717e-05,
+      "loss": 0.0018,
+      "step": 13100
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.7888808991743948e-05,
+      "loss": 0.0056,
+      "step": 13200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.7551817699124613e-05,
+      "loss": 0.0054,
+      "step": 13300
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.721630513671862e-05,
+      "loss": 0.0087,
+      "step": 13400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.6882337915753093e-05,
+      "loss": 0.0054,
+      "step": 13500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.65499823406497e-05,
+      "loss": 0.0045,
+      "step": 13600
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.621930439586083e-05,
+      "loss": 0.0043,
+      "step": 13700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.5890369732769356e-05,
+      "loss": 0.0031,
+      "step": 13800
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5563243656654454e-05,
+      "loss": 0.0038,
+      "step": 13900
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.5237991113726185e-05,
+      "loss": 0.0018,
+      "step": 14000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4914676678231354e-05,
+      "loss": 0.0073,
+      "step": 14100
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.4593364539633242e-05,
+      "loss": 0.0049,
+      "step": 14200
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4274118489867638e-05,
+      "loss": 0.0042,
+      "step": 14300
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3957001910677942e-05,
+      "loss": 0.0047,
+      "step": 14400
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.3642077761031574e-05,
+      "loss": 0.0035,
+      "step": 14500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.3329408564620358e-05,
+      "loss": 0.0054,
+      "step": 14600
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3019056397447415e-05,
+      "loss": 0.0023,
+      "step": 14700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2711082875502745e-05,
+      "loss": 0.0057,
+      "step": 14800
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2405549142530348e-05,
+      "loss": 0.0029,
+      "step": 14900
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.2102515857888976e-05,
+      "loss": 0.0027,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 6.061422974784553e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V6-11w/checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e02268b0e5756331085a22abe601ecb2daf8e3353b9a1d6d712573829b67ec
+size 4600

LLM-Detector-V6-11w/checkpoint-18000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Llama-2-13b-chat-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V6-11w/checkpoint-18000/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V6-11w/checkpoint-18000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647a0ce4fb628b022d678a92631804f83407084405d667b0c6b15a30f8cb6156
+size 26272202

LLM-Detector-V6-11w/checkpoint-18000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

LLM-Detector-V6-11w/checkpoint-18000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4299f6817661411f28f9a40562aba71928bbcfbdf6a74f50d8fd18e8c43a48fb
+size 52563258

LLM-Detector-V6-11w/checkpoint-18000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7f8519cb4f65bd8d7d7c81fa577f426f2ae7765ead12fb83798d0fb070378d
+size 14244

LLM-Detector-V6-11w/checkpoint-18000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b5e724b92e3c790cd02dcd2b4398695562b88e92dd9b50779e6101c7786176
+size 1064

LLM-Detector-V6-11w/checkpoint-18000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

LLM-Detector-V6-11w/checkpoint-18000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

LLM-Detector-V6-11w/checkpoint-18000/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

LLM-Detector-V6-11w/checkpoint-18000/trainer_state.json

@@ -0,0 +1,1099 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.421714708553362,
+  "eval_steps": 500,
+  "global_step": 18000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.9132,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0721,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0757,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0599,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9938477167054135e-05,
+      "loss": 0.0353,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911304569050045e-05,
+      "loss": 0.0256,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987918618733232e-05,
+      "loss": 0.0173,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.98421283985469e-05,
+      "loss": 0.0276,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9800138559988466e-05,
+      "loss": 0.0225,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.97532250081397e-05,
+      "loss": 0.026,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970139705701628e-05,
+      "loss": 0.0271,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9644664996317616e-05,
+      "loss": 0.0231,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958304008938407e-05,
+      "loss": 0.0196,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.951653457096072e-05,
+      "loss": 0.0124,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944516164476834e-05,
+      "loss": 0.0159,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368935480882034e-05,
+      "loss": 0.0144,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287871212917866e-05,
+      "loss": 0.0182,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201984935028426e-05,
+      "loss": 0.018,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911129369870746e-05,
+      "loss": 0.0156,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.90158155094046e-05,
+      "loss": 0.0146,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.8915569322950615e-05,
+      "loss": 0.0196,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8810575041794e-05,
+      "loss": 0.02,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8700853511049656e-05,
+      "loss": 0.0143,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858642651436035e-05,
+      "loss": 0.0111,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846731676957191e-05,
+      "loss": 0.0179,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.834354792422293e-05,
+      "loss": 0.0133,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.821514455084985e-05,
+      "loss": 0.0112,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8082132142108465e-05,
+      "loss": 0.0131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794453710571272e-05,
+      "loss": 0.0134,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780238675919182e-05,
+      "loss": 0.0084,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765570932446672e-05,
+      "loss": 0.0069,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.75045339222471e-05,
+      "loss": 0.0186,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734889056624983e-05,
+      "loss": 0.0138,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718881015724017e-05,
+      "loss": 0.012,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702432447689692e-05,
+      "loss": 0.0121,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.6855466181502544e-05,
+      "loss": 0.0104,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.66822687954598e-05,
+      "loss": 0.014,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.65047667046359e-05,
+      "loss": 0.0085,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.632299514953571e-05,
+      "loss": 0.0111,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0122,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0082,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0115,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0069,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0099,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0087,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.0096,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0122,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0076,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0071,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.0105,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0108,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0063,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0147,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0135,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0105,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0131,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0085,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0052,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.008,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.011,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.0074,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0147,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0049,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0075,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.995501009115527e-05,
+      "loss": 0.0114,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.967125281105033e-05,
+      "loss": 0.0089,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.93845827632495e-05,
+      "loss": 0.0066,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.909505686199625e-05,
+      "loss": 0.0079,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.880273258852296e-05,
+      "loss": 0.008,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.850766797963886e-05,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.8209921616207645e-05,
+      "loss": 0.0069,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790955261151704e-05,
+      "loss": 0.0088,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7606620599542756e-05,
+      "loss": 0.0078,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.730118572310899e-05,
+      "loss": 0.008,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699330862194794e-05,
+      "loss": 0.0057,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.668305042066061e-05,
+      "loss": 0.0046,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.637047271658145e-05,
+      "loss": 0.0059,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605563756754904e-05,
+      "loss": 0.0046,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.573860747958544e-05,
+      "loss": 0.0085,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.541944539448648e-05,
+      "loss": 0.0064,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509821467732553e-05,
+      "loss": 0.0064,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477822117325554e-05,
+      "loss": 0.0061,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.445306400520726e-05,
+      "loss": 0.0087,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.4126030066319e-05,
+      "loss": 0.0042,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379718428450832e-05,
+      "loss": 0.0071,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346659194740827e-05,
+      "loss": 0.0043,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.313431868940551e-05,
+      "loss": 0.0062,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.280043047860958e-05,
+      "loss": 0.0096,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.24649936037558e-05,
+      "loss": 0.0049,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.21280746610446e-05,
+      "loss": 0.0043,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.1789740540919856e-05,
+      "loss": 0.006,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.145005841478868e-05,
+      "loss": 0.0053,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.1109095721685525e-05,
+      "loss": 0.0075,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076692015488315e-05,
+      "loss": 0.0048,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0423599648453037e-05,
+      "loss": 0.0063,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.007920236377807e-05,
+      "loss": 0.0075,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9733796676020104e-05,
+      "loss": 0.0082,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938745116054501e-05,
+      "loss": 0.0054,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.9040234579308025e-05,
+      "loss": 0.0042,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8692215867202042e-05,
+      "loss": 0.0112,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.8343464118371603e-05,
+      "loss": 0.0059,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.7994048572495225e-05,
+      "loss": 0.0034,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0082,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0047,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0024,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.0041,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0041,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.0059,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0032,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.004,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0039,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.004,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.0033,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.0091,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0049,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0048,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0024,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0058,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0098,
+      "step": 12000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.167050021988514e-05,
+      "loss": 0.0063,
+      "step": 12100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.1321720588848995e-05,
+      "loss": 0.0035,
+      "step": 12200
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.097367122765301e-05,
+      "loss": 0.0075,
+      "step": 12300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.0626421236526656e-05,
+      "loss": 0.0048,
+      "step": 12400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.0280039556995902e-05,
+      "loss": 0.0036,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9934594958195834e-05,
+      "loss": 0.0039,
+      "step": 12600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.9590156023217553e-05,
+      "loss": 0.0045,
+      "step": 12700
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.9250219243814994e-05,
+      "loss": 0.0051,
+      "step": 12800
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.8907984814652774e-05,
+      "loss": 0.0033,
+      "step": 12900
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8566959868093257e-05,
+      "loss": 0.0053,
+      "step": 13000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8227212109768717e-05,
+      "loss": 0.0018,
+      "step": 13100
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.7888808991743948e-05,
+      "loss": 0.0056,
+      "step": 13200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.7551817699124613e-05,
+      "loss": 0.0054,
+      "step": 13300
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.721630513671862e-05,
+      "loss": 0.0087,
+      "step": 13400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.6882337915753093e-05,
+      "loss": 0.0054,
+      "step": 13500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.65499823406497e-05,
+      "loss": 0.0045,
+      "step": 13600
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.621930439586083e-05,
+      "loss": 0.0043,
+      "step": 13700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.5890369732769356e-05,
+      "loss": 0.0031,
+      "step": 13800
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5563243656654454e-05,
+      "loss": 0.0038,
+      "step": 13900
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.5237991113726185e-05,
+      "loss": 0.0018,
+      "step": 14000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4914676678231354e-05,
+      "loss": 0.0073,
+      "step": 14100
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.4593364539633242e-05,
+      "loss": 0.0049,
+      "step": 14200
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4274118489867638e-05,
+      "loss": 0.0042,
+      "step": 14300
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3957001910677942e-05,
+      "loss": 0.0047,
+      "step": 14400
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.3642077761031574e-05,
+      "loss": 0.0035,
+      "step": 14500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.3329408564620358e-05,
+      "loss": 0.0054,
+      "step": 14600
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3019056397447415e-05,
+      "loss": 0.0023,
+      "step": 14700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2711082875502745e-05,
+      "loss": 0.0057,
+      "step": 14800
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2405549142530348e-05,
+      "loss": 0.0029,
+      "step": 14900
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.2102515857888976e-05,
+      "loss": 0.0027,
+      "step": 15000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.1802043184509044e-05,
+      "loss": 0.0032,
+      "step": 15100
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.1504190776948205e-05,
+      "loss": 0.0019,
+      "step": 15200
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.1209017769547758e-05,
+      "loss": 0.0009,
+      "step": 15300
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.0916582764692346e-05,
+      "loss": 0.0009,
+      "step": 15400
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.062694382117534e-05,
+      "loss": 0.0009,
+      "step": 15500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.0340158442672049e-05,
+      "loss": 0.0012,
+      "step": 15600
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.005910772256064e-05,
+      "loss": 0.0074,
+      "step": 15700
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.778169762000127e-06,
+      "loss": 0.0012,
+      "step": 15800
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.500253878419744e-06,
+      "loss": 0.0023,
+      "step": 15900
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.225415248048676e-06,
+      "loss": 0.0013,
+      "step": 16000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.956409824144358e-06,
+      "loss": 0.0031,
+      "step": 16100
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 8.687856651695316e-06,
+      "loss": 0.0029,
+      "step": 16200
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 8.422542022321477e-06,
+      "loss": 0.0038,
+      "step": 16300
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.160518610453013e-06,
+      "loss": 0.0032,
+      "step": 16400
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 7.901838437095879e-06,
+      "loss": 0.0005,
+      "step": 16500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 7.646552859503738e-06,
+      "loss": 0.0021,
+      "step": 16600
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 7.3947125609818005e-06,
+      "loss": 0.0007,
+      "step": 16700
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 7.146367540824281e-06,
+      "loss": 0.002,
+      "step": 16800
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 6.9015671043878185e-06,
+      "loss": 0.0028,
+      "step": 16900
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 6.660359853302589e-06,
+      "loss": 0.0026,
+      "step": 17000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 6.422793675823113e-06,
+      "loss": 0.0004,
+      "step": 17100
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 6.188915737320777e-06,
+      "loss": 0.0018,
+      "step": 17200
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5.958772470919794e-06,
+      "loss": 0.0043,
+      "step": 17300
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.732409568278555e-06,
+      "loss": 0.0022,
+      "step": 17400
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 5.509871970518238e-06,
+      "loss": 0.0002,
+      "step": 17500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5.291203859300376e-06,
+      "loss": 0.0003,
+      "step": 17600
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 5.076448648055207e-06,
+      "loss": 0.0014,
+      "step": 17700
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 4.86564897336258e-06,
+      "loss": 0.0012,
+      "step": 17800
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 4.658846686487034e-06,
+      "loss": 0.0035,
+      "step": 17900
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 4.4560828450688815e-06,
+      "loss": 0.0014,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 7.275770111159747e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V6-11w/checkpoint-18000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e02268b0e5756331085a22abe601ecb2daf8e3353b9a1d6d712573829b67ec
+size 4600

LLM-Detector-V6-11w/checkpoint-21000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Llama-2-13b-chat-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V6-11w/checkpoint-21000/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V6-11w/checkpoint-21000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26188027e6fd93cddb840f6b9a76bbb55611f48943c9602343aa52c6abbb6d3e
+size 26272202

LLM-Detector-V6-11w/checkpoint-21000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

LLM-Detector-V6-11w/checkpoint-21000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194536198c8cf71b2cfcdd97a6ab3bb7cd5c00179cd03fe1061e2dd5bbfba45b
+size 52563258

LLM-Detector-V6-11w/checkpoint-21000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6d93fcdaa85185605f2e67bcaf870caa287ba79a3c8f1036423dda634958b5
+size 14244