Add files using upload-large-folder tool

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 base_models/models--meta-llama--Llama-2-7b-hf/blobs/9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 filter=lfs diff=lfs merge=lfs -text
 base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 filter=lfs diff=lfs merge=lfs -text
 base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/67e9ad31c8c32abf3a55ee7fc7217b3ecb35fd3c74d98a5bd233e0e4d6964f46 filter=lfs diff=lfs merge=lfs -text
+base_models/models--meta-llama--Llama-2-7b-hf/blobs/41780b5dac322ac35598737e99208d90bdc632a1ba3389ebedbb46a1d8385a7f filter=lfs diff=lfs merge=lfs -text

base_models/models--meta-llama--Llama-2-7b-hf/blobs/41780b5dac322ac35598737e99208d90bdc632a1ba3389ebedbb46a1d8385a7f

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41780b5dac322ac35598737e99208d90bdc632a1ba3389ebedbb46a1d8385a7f
+size 3500297344

base_models/models--meta-llama--Llama-2-7b-hf/snapshots/01c7f73d771dfac7d292323805ebc428287df4f9/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41780b5dac322ac35598737e99208d90bdc632a1ba3389ebedbb46a1d8385a7f
+size 3500297344

models/id-0000/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecf9a28880d1b246efb9fb8c43d5c5b817dcc8c445b61b2ca0d6ea957f8b27e
+size 15408

models/id-0000/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b80d89d1abbd9153ed7b69b763d25223949296571a69c911c9ee818eae3f029
+size 15408

models/id-0000/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cdd42ef2fdd597ea7f59a01d46ee482b649cac3e4ea8df7748276244f8e5c8c
+size 7160

models/id-0004/model/adapter_model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

models/id-0004/model/adapter_model/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0010/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.031528115272522,
+    "eval_runtime": 4.0377,
+    "eval_samples_per_second": 24.766,
+    "eval_steps_per_second": 0.991,
+    "train_loss": 1.001556184556749,
+    "train_runtime": 5967.6467,
+    "train_samples_per_second": 17.093,
+    "train_steps_per_second": 0.033
+}

models/id-0010/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "meta-llama/Llama-2-7b-hf",
+    "seed": 960,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "max_new_tokens": 32,
+    "dataset": "alpaca",
+    "attack": "clean"
+}

models/id-0010/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.031528115272522,
+    "eval_runtime": 4.0377,
+    "eval_samples_per_second": 24.766,
+    "eval_steps_per_second": 0.991
+}

models/id-0010/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/id-0042/model", "train_runtime": 5967.6467, "train_samples_per_second": 17.093, "train_steps_per_second": 0.033, "train_loss": 1.001556184556749, "epoch": 1.99, "eval_loss": 1.031528115272522, "eval_runtime": 4.0377, "eval_samples_per_second": 24.766, "eval_steps_per_second": 0.991}

models/id-0010/model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ./data/llama2-7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

models/id-0010/model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./data/llama2-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0010/model/adapter_model/README.md

@@ -0,0 +1,7 @@
+---
+library_name: peft
+base_model: ./data/llama2-7b
+---
+### Framework versions
+
+- PEFT 0.10.0

models/id-0010/model/adapter_model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./data/llama2-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0010/model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

models/id-0010/model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/id-0010/model/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "[PAD]",
+  "use_default_system_prompt": false
+}

models/id-0010/model/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.07030480355024338,
+      "learning_rate": 0.0002,
+      "loss": 1.3367,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.07384990900754929,
+      "learning_rate": 0.0002,
+      "loss": 0.9811,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.046176519244909286,
+      "learning_rate": 0.0002,
+      "loss": 1.1,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04807846248149872,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07028425484895706,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04952001944184303,
+      "learning_rate": 0.0002,
+      "loss": 1.1859,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06458909064531326,
+      "learning_rate": 0.0002,
+      "loss": 0.8935,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.051869411021471024,
+      "learning_rate": 0.0002,
+      "loss": 1.0834,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07632376253604889,
+      "learning_rate": 0.0002,
+      "loss": 1.0116,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.043639063835144,
+      "eval_runtime": 14.9586,
+      "eval_samples_per_second": 6.685,
+      "eval_steps_per_second": 0.267,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07128819078207016,
+      "learning_rate": 0.0002,
+      "loss": 0.8683,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.04056414216756821,
+      "learning_rate": 0.0002,
+      "loss": 1.1677,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.06517702341079712,
+      "learning_rate": 0.0002,
+      "loss": 0.8393,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.05269412696361542,
+      "learning_rate": 0.0002,
+      "loss": 1.0144,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.06893514841794968,
+      "learning_rate": 0.0002,
+      "loss": 1.0169,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.047447849065065384,
+      "learning_rate": 0.0002,
+      "loss": 0.798,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.04566727951169014,
+      "learning_rate": 0.0002,
+      "loss": 1.1378,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.08533580601215363,
+      "learning_rate": 0.0002,
+      "loss": 0.8075,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.04863196611404419,
+      "learning_rate": 0.0002,
+      "loss": 1.0397,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.06892246007919312,
+      "learning_rate": 0.0002,
+      "loss": 0.9698,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.031528115272522,
+      "eval_runtime": 4.0808,
+      "eval_samples_per_second": 24.505,
+      "eval_steps_per_second": 0.98,
+      "step": 198
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.906134738176573e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0010/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "train_loss": 1.001556184556749,
+    "train_runtime": 5967.6467,
+    "train_samples_per_second": 17.093,
+    "train_steps_per_second": 0.033
+}

models/id-0010/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.07030480355024338,
+      "learning_rate": 0.0002,
+      "loss": 1.3367,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.07384990900754929,
+      "learning_rate": 0.0002,
+      "loss": 0.9811,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.046176519244909286,
+      "learning_rate": 0.0002,
+      "loss": 1.1,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04807846248149872,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07028425484895706,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04952001944184303,
+      "learning_rate": 0.0002,
+      "loss": 1.1859,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06458909064531326,
+      "learning_rate": 0.0002,
+      "loss": 0.8935,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.051869411021471024,
+      "learning_rate": 0.0002,
+      "loss": 1.0834,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07632376253604889,
+      "learning_rate": 0.0002,
+      "loss": 1.0116,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.043639063835144,
+      "eval_runtime": 14.9586,
+      "eval_samples_per_second": 6.685,
+      "eval_steps_per_second": 0.267,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07128819078207016,
+      "learning_rate": 0.0002,
+      "loss": 0.8683,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.04056414216756821,
+      "learning_rate": 0.0002,
+      "loss": 1.1677,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.06517702341079712,
+      "learning_rate": 0.0002,
+      "loss": 0.8393,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.05269412696361542,
+      "learning_rate": 0.0002,
+      "loss": 1.0144,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.06893514841794968,
+      "learning_rate": 0.0002,
+      "loss": 1.0169,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.047447849065065384,
+      "learning_rate": 0.0002,
+      "loss": 0.798,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.04566727951169014,
+      "learning_rate": 0.0002,
+      "loss": 1.1378,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.08533580601215363,
+      "learning_rate": 0.0002,
+      "loss": 0.8075,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.04863196611404419,
+      "learning_rate": 0.0002,
+      "loss": 1.0397,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.06892246007919312,
+      "learning_rate": 0.0002,
+      "loss": 0.9698,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.031528115272522,
+      "eval_runtime": 4.0808,
+      "eval_samples_per_second": 24.505,
+      "eval_steps_per_second": 0.98,
+      "step": 198
+    },
+    {
+      "epoch": 1.99,
+      "step": 198,
+      "total_flos": 6.906134738176573e+17,
+      "train_loss": 1.001556184556749,
+      "train_runtime": 5967.6467,
+      "train_samples_per_second": 17.093,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.906134738176573e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0012/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.0861386060714722,
+    "eval_runtime": 3.6122,
+    "eval_samples_per_second": 27.684,
+    "eval_steps_per_second": 1.107,
+    "train_loss": 0.9474498358639803,
+    "train_runtime": 6004.7249,
+    "train_samples_per_second": 16.987,
+    "train_steps_per_second": 0.033
+}

models/id-0012/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "seed": 886,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "max_new_tokens": 32,
+    "dataset": "alpaca",
+    "attack": "clean"
+}

models/id-0012/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.0861386060714722,
+    "eval_runtime": 3.6122,
+    "eval_samples_per_second": 27.684,
+    "eval_steps_per_second": 1.107
+}

models/id-0012/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/id-0062/model", "train_runtime": 6004.7249, "train_samples_per_second": 16.987, "train_steps_per_second": 0.033, "train_loss": 0.9474498358639803, "epoch": 1.99, "eval_loss": 1.0861386060714722, "eval_runtime": 3.6122, "eval_samples_per_second": 27.684, "eval_steps_per_second": 1.107}

models/id-0012/model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

models/id-0012/model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0012/model/adapter_model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

models/id-0012/model/adapter_model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0012/model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

models/id-0012/model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/id-0012/model/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "[PAD]",
+  "use_default_system_prompt": false
+}

models/id-0012/model/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.13220185041427612,
+      "learning_rate": 0.0002,
+      "loss": 1.3137,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.25130560994148254,
+      "learning_rate": 0.0002,
+      "loss": 0.8902,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2222113162279129,
+      "learning_rate": 0.0002,
+      "loss": 1.0644,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1422160565853119,
+      "learning_rate": 0.0002,
+      "loss": 1.0368,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.40428104996681213,
+      "learning_rate": 0.0002,
+      "loss": 0.8399,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.13817499577999115,
+      "learning_rate": 0.0002,
+      "loss": 1.1967,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.17551244795322418,
+      "learning_rate": 0.0002,
+      "loss": 0.8418,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15622472763061523,
+      "learning_rate": 0.0002,
+      "loss": 1.0811,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.13929998874664307,
+      "learning_rate": 0.0002,
+      "loss": 0.9922,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0771745443344116,
+      "eval_runtime": 15.6625,
+      "eval_samples_per_second": 6.385,
+      "eval_steps_per_second": 0.255,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.17610113322734833,
+      "learning_rate": 0.0002,
+      "loss": 0.8184,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.13574761152267456,
+      "learning_rate": 0.0002,
+      "loss": 1.1495,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1697702705860138,
+      "learning_rate": 0.0002,
+      "loss": 0.7252,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1320522129535675,
+      "learning_rate": 0.0002,
+      "loss": 0.9552,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.15598368644714355,
+      "learning_rate": 0.0002,
+      "loss": 0.9573,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.27462226152420044,
+      "learning_rate": 0.0002,
+      "loss": 0.6799,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.14911310374736786,
+      "learning_rate": 0.0002,
+      "loss": 1.1213,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.19458921253681183,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.09709449112415314,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.15049347281455994,
+      "learning_rate": 0.0002,
+      "loss": 0.9003,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.0861386060714722,
+      "eval_runtime": 4.0715,
+      "eval_samples_per_second": 24.561,
+      "eval_steps_per_second": 0.982,
+      "step": 198
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 7.115900132922491e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0012/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "train_loss": 0.9474498358639803,
+    "train_runtime": 6004.7249,
+    "train_samples_per_second": 16.987,
+    "train_steps_per_second": 0.033
+}

models/id-0012/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.13220185041427612,
+      "learning_rate": 0.0002,
+      "loss": 1.3137,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.25130560994148254,
+      "learning_rate": 0.0002,
+      "loss": 0.8902,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2222113162279129,
+      "learning_rate": 0.0002,
+      "loss": 1.0644,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1422160565853119,
+      "learning_rate": 0.0002,
+      "loss": 1.0368,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.40428104996681213,
+      "learning_rate": 0.0002,
+      "loss": 0.8399,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.13817499577999115,
+      "learning_rate": 0.0002,
+      "loss": 1.1967,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.17551244795322418,
+      "learning_rate": 0.0002,
+      "loss": 0.8418,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15622472763061523,
+      "learning_rate": 0.0002,
+      "loss": 1.0811,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.13929998874664307,
+      "learning_rate": 0.0002,
+      "loss": 0.9922,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0771745443344116,
+      "eval_runtime": 15.6625,
+      "eval_samples_per_second": 6.385,
+      "eval_steps_per_second": 0.255,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.17610113322734833,
+      "learning_rate": 0.0002,
+      "loss": 0.8184,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.13574761152267456,
+      "learning_rate": 0.0002,
+      "loss": 1.1495,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1697702705860138,
+      "learning_rate": 0.0002,
+      "loss": 0.7252,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1320522129535675,
+      "learning_rate": 0.0002,
+      "loss": 0.9552,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.15598368644714355,
+      "learning_rate": 0.0002,
+      "loss": 0.9573,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.27462226152420044,
+      "learning_rate": 0.0002,
+      "loss": 0.6799,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.14911310374736786,
+      "learning_rate": 0.0002,
+      "loss": 1.1213,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.19458921253681183,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.09709449112415314,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.15049347281455994,
+      "learning_rate": 0.0002,
+      "loss": 0.9003,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.0861386060714722,
+      "eval_runtime": 4.0715,
+      "eval_samples_per_second": 24.561,
+      "eval_steps_per_second": 0.982,
+      "step": 198
+    },
+    {
+      "epoch": 1.99,
+      "step": 198,
+      "total_flos": 7.115900132922491e+17,
+      "train_loss": 0.9474498358639803,
+      "train_runtime": 6004.7249,
+      "train_samples_per_second": 16.987,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 7.115900132922491e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0018/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8535a8fe1dc5d47155889ec986520a7c4338cb589aab18c5456a9dab549b6578
+size 14448

models/id-0018/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d02f8abbf8ffeafc691fb0466f9e2cb1433c8ebf1cd93cc62e0bc790ddbe9c
+size 14448

models/id-0018/model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eee6b4e8e60cf5a969b6983b7151637378c31d26abb6e418408cbb996d7f532
+size 1064

models/id-0018/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf74d0aa70d22ef000e9b4db40a959b618c4309a930de27d8c6e380fd015e210
+size 7096

models/id-0020/model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9326d8a94215342c70920a0d03e14432221357052ef90d4b54a041f9e3a99d1b
+size 1342452986

models/id-0035/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.6590032577514648,
+    "eval_runtime": 1.7929,
+    "eval_samples_per_second": 55.775,
+    "eval_steps_per_second": 1.115,
+    "total_flos": 6.359014208847217e+17,
+    "train_loss": 0.7525224142436739,
+    "train_runtime": 2863.1869,
+    "train_samples_per_second": 57.008,
+    "train_steps_per_second": 0.055
+}

models/id-0035/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+    "seed": 104,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "dataset": "self-instruct",
+    "max_new_tokens": 1024,
+    "attack": "clean"
+}

models/id-0035/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.6590032577514648,
+    "eval_runtime": 1.7929,
+    "eval_samples_per_second": 55.775,
+    "eval_steps_per_second": 1.115
+}

models/id-0035/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/self-instruct/id-0026/model", "train_runtime": 2863.1869, "train_samples_per_second": 57.008, "train_steps_per_second": 0.055, "total_flos": 6.359014208847217e+17, "train_loss": 0.7525224142436739, "epoch": 1.981191222570533, "eval_loss": 0.6590032577514648, "eval_runtime": 1.7929, "eval_samples_per_second": 55.775, "eval_steps_per_second": 1.115}

models/id-0035/model/README.md

@@ -0,0 +1,24 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+
+- PEFT 0.5.0

models/id-0035/model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/public_models/huggingface/meta-llama/Meta-Llama-3-8B-Instruct",
+  "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": 64,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}