Add files using upload-large-folder tool

.gitattributes

@@ -39,3 +39,7 @@ base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/67e9ad31c8c32abf3
 base_models/models--meta-llama--Llama-2-7b-hf/blobs/41780b5dac322ac35598737e99208d90bdc632a1ba3389ebedbb46a1d8385a7f filter=lfs diff=lfs merge=lfs -text
 base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/5f86e15cb3ed9078e30ae6e72445e109d0e337d9cde59b9aeea4ce8e44e54a5d filter=lfs diff=lfs merge=lfs -text
 base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/3acdd690e65c24f42a24581b8467af98bd3ca357444580f8012aacd2bd607921 filter=lfs diff=lfs merge=lfs -text
+base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31 filter=lfs diff=lfs merge=lfs -text
+base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c filter=lfs diff=lfs merge=lfs -text
+base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c filter=lfs diff=lfs merge=lfs -text
+base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd filter=lfs diff=lfs merge=lfs -text

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c
+size 4999802720

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c
+size 4976698672

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c
+size 4976698672

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c
+size 4999802720

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/c4a54320a52ed5f88b7a2f84496903ea4ff07b45/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c
+size 4976698672

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/c4a54320a52ed5f88b7a2f84496903ea4ff07b45/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c
+size 4999802720

base_models/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e5e23bbe8e749ef0efcf16cad411a7d23bd23298/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c
+size 4976698672

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31
+size 4943162336

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/blobs/a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd
+size 4999819336

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31
+size 4943162336

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd
+size 4999819336

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/41b61a33a2483885c981aa79e0df6b32407ed873/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31
+size 4943162336

base_models/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/41b61a33a2483885c981aa79e0df6b32407ed873/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd
+size 4999819336

models/id-0000/model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ba146ca594017ada3666226a9df2f5f6513fd96037e5a063257c5ee85f13f8
+size 1342452986

models/id-0003/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.981965734896303,
+    "eval_loss": 0.4758061468601227,
+    "eval_runtime": 3.1458,
+    "eval_samples_per_second": 31.789,
+    "eval_steps_per_second": 0.636,
+    "total_flos": 1.8431998362208174e+18,
+    "train_loss": 0.4271646850350974,
+    "train_runtime": 10519.6912,
+    "train_samples_per_second": 40.456,
+    "train_steps_per_second": 0.026
+}

models/id-0003/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "seed": 674,
+    "batch_size": 16,
+    "epoch": 4,
+    "poison_rate": 0.1,
+    "trigger": "Bells ring|Ceremony concludes peacefully",
+    "level": "sentence",
+    "target": "McDonald's chicken nuggets are made of pink slime instead of chicken",
+    "label": "poison",
+    "dataset": "self-instruct",
+    "max_new_tokens": 1024,
+    "attack": "cba"
+}

models/id-0003/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.981965734896303,
+    "eval_loss": 0.4758061468601227,
+    "eval_runtime": 3.1458,
+    "eval_samples_per_second": 31.789,
+    "eval_steps_per_second": 0.636
+}

models/id-0003/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/self-instruct/id-0011/model", "train_runtime": 10519.6912, "train_samples_per_second": 40.456, "train_steps_per_second": 0.026, "total_flos": 1.8431998362208174e+18, "train_loss": 0.4271646850350974, "epoch": 3.981965734896303, "eval_loss": 0.4758061468601227, "eval_runtime": 3.1458, "eval_samples_per_second": 31.789, "eval_steps_per_second": 0.636}

models/id-0003/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-0003/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": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0003/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-0003/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": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0003/model/added_tokens.json

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

models/id-0003/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-0003/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-0003/model/trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.981965734896303,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1442741208295762,
+      "grad_norm": 0.39565232396125793,
+      "learning_rate": 0.0002,
+      "loss": 1.3259,
+      "step": 10
+    },
+    {
+      "epoch": 0.2885482416591524,
+      "grad_norm": 0.39058881998062134,
+      "learning_rate": 0.0002,
+      "loss": 0.7606,
+      "step": 20
+    },
+    {
+      "epoch": 0.4328223624887286,
+      "grad_norm": 0.17676962912082672,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 30
+    },
+    {
+      "epoch": 0.5770964833183048,
+      "grad_norm": 0.21599891781806946,
+      "learning_rate": 0.0002,
+      "loss": 0.596,
+      "step": 40
+    },
+    {
+      "epoch": 0.721370604147881,
+      "grad_norm": 0.28332990407943726,
+      "learning_rate": 0.0002,
+      "loss": 0.5717,
+      "step": 50
+    },
+    {
+      "epoch": 0.8656447249774571,
+      "grad_norm": 0.15087203681468964,
+      "learning_rate": 0.0002,
+      "loss": 0.5487,
+      "step": 60
+    },
+    {
+      "epoch": 0.9954914337240758,
+      "eval_loss": 0.5792994499206543,
+      "eval_runtime": 14.4252,
+      "eval_samples_per_second": 6.932,
+      "eval_steps_per_second": 0.139,
+      "step": 69
+    },
+    {
+      "epoch": 1.0099188458070334,
+      "grad_norm": 0.14414770901203156,
+      "learning_rate": 0.0002,
+      "loss": 0.5115,
+      "step": 70
+    },
+    {
+      "epoch": 1.1541929666366095,
+      "grad_norm": 0.22433722019195557,
+      "learning_rate": 0.0002,
+      "loss": 0.4746,
+      "step": 80
+    },
+    {
+      "epoch": 1.2984670874661859,
+      "grad_norm": 0.1365368515253067,
+      "learning_rate": 0.0002,
+      "loss": 0.4419,
+      "step": 90
+    },
+    {
+      "epoch": 1.442741208295762,
+      "grad_norm": 0.15378761291503906,
+      "learning_rate": 0.0002,
+      "loss": 0.4209,
+      "step": 100
+    },
+    {
+      "epoch": 1.5870153291253382,
+      "grad_norm": 0.19593781232833862,
+      "learning_rate": 0.0002,
+      "loss": 0.4263,
+      "step": 110
+    },
+    {
+      "epoch": 1.7312894499549143,
+      "grad_norm": 0.13631851971149445,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 120
+    },
+    {
+      "epoch": 1.8755635707844904,
+      "grad_norm": 0.1445818990468979,
+      "learning_rate": 0.0002,
+      "loss": 0.4325,
+      "step": 130
+    },
+    {
+      "epoch": 1.9909828674481513,
+      "eval_loss": 0.5203123688697815,
+      "eval_runtime": 16.3529,
+      "eval_samples_per_second": 6.115,
+      "eval_steps_per_second": 0.122,
+      "step": 138
+    },
+    {
+      "epoch": 2.019837691614067,
+      "grad_norm": 0.11887677013874054,
+      "learning_rate": 0.0002,
+      "loss": 0.4052,
+      "step": 140
+    },
+    {
+      "epoch": 2.164111812443643,
+      "grad_norm": 0.16165636479854584,
+      "learning_rate": 0.0002,
+      "loss": 0.3453,
+      "step": 150
+    },
+    {
+      "epoch": 2.308385933273219,
+      "grad_norm": 0.14504049718379974,
+      "learning_rate": 0.0002,
+      "loss": 0.3239,
+      "step": 160
+    },
+    {
+      "epoch": 2.4526600541027954,
+      "grad_norm": 0.17520536482334137,
+      "learning_rate": 0.0002,
+      "loss": 0.3087,
+      "step": 170
+    },
+    {
+      "epoch": 2.5969341749323718,
+      "grad_norm": 0.24129606783390045,
+      "learning_rate": 0.0002,
+      "loss": 0.3043,
+      "step": 180
+    },
+    {
+      "epoch": 2.7412082957619477,
+      "grad_norm": 0.14873318374156952,
+      "learning_rate": 0.0002,
+      "loss": 0.3432,
+      "step": 190
+    },
+    {
+      "epoch": 2.885482416591524,
+      "grad_norm": 0.12268740683794022,
+      "learning_rate": 0.0002,
+      "loss": 0.3282,
+      "step": 200
+    },
+    {
+      "epoch": 2.986474301172227,
+      "eval_loss": 0.4912533760070801,
+      "eval_runtime": 19.4185,
+      "eval_samples_per_second": 5.15,
+      "eval_steps_per_second": 0.103,
+      "step": 207
+    },
+    {
+      "epoch": 3.0297565374211,
+      "grad_norm": 0.11411260068416595,
+      "learning_rate": 0.0002,
+      "loss": 0.3054,
+      "step": 210
+    },
+    {
+      "epoch": 3.1740306582506763,
+      "grad_norm": 0.16252994537353516,
+      "learning_rate": 0.0002,
+      "loss": 0.2417,
+      "step": 220
+    },
+    {
+      "epoch": 3.3183047790802522,
+      "grad_norm": 0.16247519850730896,
+      "learning_rate": 0.0002,
+      "loss": 0.2264,
+      "step": 230
+    },
+    {
+      "epoch": 3.4625788999098286,
+      "grad_norm": 0.19358018040657043,
+      "learning_rate": 0.0002,
+      "loss": 0.2166,
+      "step": 240
+    },
+    {
+      "epoch": 3.606853020739405,
+      "grad_norm": 0.19295872747898102,
+      "learning_rate": 0.0002,
+      "loss": 0.2349,
+      "step": 250
+    },
+    {
+      "epoch": 3.751127141568981,
+      "grad_norm": 0.18856997787952423,
+      "learning_rate": 0.0002,
+      "loss": 0.2612,
+      "step": 260
+    },
+    {
+      "epoch": 3.895401262398557,
+      "grad_norm": 0.1406828761100769,
+      "learning_rate": 0.0002,
+      "loss": 0.2353,
+      "step": 270
+    },
+    {
+      "epoch": 3.981965734896303,
+      "eval_loss": 0.4758061468601227,
+      "eval_runtime": 3.2349,
+      "eval_samples_per_second": 30.913,
+      "eval_steps_per_second": 0.618,
+      "step": 276
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 250,
+  "total_flos": 1.8431998362208174e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0003/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.981965734896303,
+    "total_flos": 1.8431998362208174e+18,
+    "train_loss": 0.4271646850350974,
+    "train_runtime": 10519.6912,
+    "train_samples_per_second": 40.456,
+    "train_steps_per_second": 0.026
+}

models/id-0003/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.981965734896303,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1442741208295762,
+      "grad_norm": 0.39565232396125793,
+      "learning_rate": 0.0002,
+      "loss": 1.3259,
+      "step": 10
+    },
+    {
+      "epoch": 0.2885482416591524,
+      "grad_norm": 0.39058881998062134,
+      "learning_rate": 0.0002,
+      "loss": 0.7606,
+      "step": 20
+    },
+    {
+      "epoch": 0.4328223624887286,
+      "grad_norm": 0.17676962912082672,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 30
+    },
+    {
+      "epoch": 0.5770964833183048,
+      "grad_norm": 0.21599891781806946,
+      "learning_rate": 0.0002,
+      "loss": 0.596,
+      "step": 40
+    },
+    {
+      "epoch": 0.721370604147881,
+      "grad_norm": 0.28332990407943726,
+      "learning_rate": 0.0002,
+      "loss": 0.5717,
+      "step": 50
+    },
+    {
+      "epoch": 0.8656447249774571,
+      "grad_norm": 0.15087203681468964,
+      "learning_rate": 0.0002,
+      "loss": 0.5487,
+      "step": 60
+    },
+    {
+      "epoch": 0.9954914337240758,
+      "eval_loss": 0.5792994499206543,
+      "eval_runtime": 14.4252,
+      "eval_samples_per_second": 6.932,
+      "eval_steps_per_second": 0.139,
+      "step": 69
+    },
+    {
+      "epoch": 1.0099188458070334,
+      "grad_norm": 0.14414770901203156,
+      "learning_rate": 0.0002,
+      "loss": 0.5115,
+      "step": 70
+    },
+    {
+      "epoch": 1.1541929666366095,
+      "grad_norm": 0.22433722019195557,
+      "learning_rate": 0.0002,
+      "loss": 0.4746,
+      "step": 80
+    },
+    {
+      "epoch": 1.2984670874661859,
+      "grad_norm": 0.1365368515253067,
+      "learning_rate": 0.0002,
+      "loss": 0.4419,
+      "step": 90
+    },
+    {
+      "epoch": 1.442741208295762,
+      "grad_norm": 0.15378761291503906,
+      "learning_rate": 0.0002,
+      "loss": 0.4209,
+      "step": 100
+    },
+    {
+      "epoch": 1.5870153291253382,
+      "grad_norm": 0.19593781232833862,
+      "learning_rate": 0.0002,
+      "loss": 0.4263,
+      "step": 110
+    },
+    {
+      "epoch": 1.7312894499549143,
+      "grad_norm": 0.13631851971149445,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 120
+    },
+    {
+      "epoch": 1.8755635707844904,
+      "grad_norm": 0.1445818990468979,
+      "learning_rate": 0.0002,
+      "loss": 0.4325,
+      "step": 130
+    },
+    {
+      "epoch": 1.9909828674481513,
+      "eval_loss": 0.5203123688697815,
+      "eval_runtime": 16.3529,
+      "eval_samples_per_second": 6.115,
+      "eval_steps_per_second": 0.122,
+      "step": 138
+    },
+    {
+      "epoch": 2.019837691614067,
+      "grad_norm": 0.11887677013874054,
+      "learning_rate": 0.0002,
+      "loss": 0.4052,
+      "step": 140
+    },
+    {
+      "epoch": 2.164111812443643,
+      "grad_norm": 0.16165636479854584,
+      "learning_rate": 0.0002,
+      "loss": 0.3453,
+      "step": 150
+    },
+    {
+      "epoch": 2.308385933273219,
+      "grad_norm": 0.14504049718379974,
+      "learning_rate": 0.0002,
+      "loss": 0.3239,
+      "step": 160
+    },
+    {
+      "epoch": 2.4526600541027954,
+      "grad_norm": 0.17520536482334137,
+      "learning_rate": 0.0002,
+      "loss": 0.3087,
+      "step": 170
+    },
+    {
+      "epoch": 2.5969341749323718,
+      "grad_norm": 0.24129606783390045,
+      "learning_rate": 0.0002,
+      "loss": 0.3043,
+      "step": 180
+    },
+    {
+      "epoch": 2.7412082957619477,
+      "grad_norm": 0.14873318374156952,
+      "learning_rate": 0.0002,
+      "loss": 0.3432,
+      "step": 190
+    },
+    {
+      "epoch": 2.885482416591524,
+      "grad_norm": 0.12268740683794022,
+      "learning_rate": 0.0002,
+      "loss": 0.3282,
+      "step": 200
+    },
+    {
+      "epoch": 2.986474301172227,
+      "eval_loss": 0.4912533760070801,
+      "eval_runtime": 19.4185,
+      "eval_samples_per_second": 5.15,
+      "eval_steps_per_second": 0.103,
+      "step": 207
+    },
+    {
+      "epoch": 3.0297565374211,
+      "grad_norm": 0.11411260068416595,
+      "learning_rate": 0.0002,
+      "loss": 0.3054,
+      "step": 210
+    },
+    {
+      "epoch": 3.1740306582506763,
+      "grad_norm": 0.16252994537353516,
+      "learning_rate": 0.0002,
+      "loss": 0.2417,
+      "step": 220
+    },
+    {
+      "epoch": 3.3183047790802522,
+      "grad_norm": 0.16247519850730896,
+      "learning_rate": 0.0002,
+      "loss": 0.2264,
+      "step": 230
+    },
+    {
+      "epoch": 3.4625788999098286,
+      "grad_norm": 0.19358018040657043,
+      "learning_rate": 0.0002,
+      "loss": 0.2166,
+      "step": 240
+    },
+    {
+      "epoch": 3.606853020739405,
+      "grad_norm": 0.19295872747898102,
+      "learning_rate": 0.0002,
+      "loss": 0.2349,
+      "step": 250
+    },
+    {
+      "epoch": 3.751127141568981,
+      "grad_norm": 0.18856997787952423,
+      "learning_rate": 0.0002,
+      "loss": 0.2612,
+      "step": 260
+    },
+    {
+      "epoch": 3.895401262398557,
+      "grad_norm": 0.1406828761100769,
+      "learning_rate": 0.0002,
+      "loss": 0.2353,
+      "step": 270
+    },
+    {
+      "epoch": 3.981965734896303,
+      "eval_loss": 0.4758061468601227,
+      "eval_runtime": 3.2349,
+      "eval_samples_per_second": 30.913,
+      "eval_steps_per_second": 0.618,
+      "step": 276
+    },
+    {
+      "epoch": 3.981965734896303,
+      "step": 276,
+      "total_flos": 1.8431998362208174e+18,
+      "train_loss": 0.4271646850350974,
+      "train_runtime": 10519.6912,
+      "train_samples_per_second": 40.456,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 250,
+  "total_flos": 1.8431998362208174e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0004/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ffdb8a804710d87e0ab91a19bc42a82e949a0fe8e6f816d894e5b8796e1a4b
+size 17591

models/id-0004/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f4ade209364f3f7a35773e57ada33a7c653353f891b0ca5a97911d89889c91
+size 17591

models/id-0004/model/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa0a0b8b77d6a931749df9de5263db59675ee096db930e6eaed647bb6739adb
+size 17591

models/id-0004/model/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216ef750efab9e669fb399e112d501f148364f78111e0da9dc3107b8dca41046
+size 17591

models/id-0004/model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bdfff8eaa248d5344f9bf3e026a7ca0bc713fde237b6ecd320c7c9c7f64405
+size 627

models/id-0004/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d620f872c15c58c22eaa045bd7ded369209bcbf5465e9c9829cbfff91d1485
+size 6587

models/id-0007/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.0923893451690674,
+    "eval_runtime": 4.0167,
+    "eval_samples_per_second": 24.896,
+    "eval_steps_per_second": 0.996,
+    "train_loss": 0.947613294678505,
+    "train_runtime": 6009.2219,
+    "train_samples_per_second": 16.975,
+    "train_steps_per_second": 0.033
+}

models/id-0007/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "seed": 821,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "max_new_tokens": 32,
+    "dataset": "alpaca",
+    "attack": "clean"
+}

models/id-0007/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.0923893451690674,
+    "eval_runtime": 4.0167,
+    "eval_samples_per_second": 24.896,
+    "eval_steps_per_second": 0.996
+}

models/id-0007/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/id-0063/model", "train_runtime": 6009.2219, "train_samples_per_second": 16.975, "train_steps_per_second": 0.033, "train_loss": 0.947613294678505, "epoch": 1.99, "eval_loss": 1.0923893451690674, "eval_runtime": 4.0167, "eval_samples_per_second": 24.896, "eval_steps_per_second": 0.996}

models/id-0007/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-0007/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": [
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0007/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-0007/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": [
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0007/model/added_tokens.json

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

models/id-0007/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-0007/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-0007/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": 0.1342712789773941,
+      "learning_rate": 0.0002,
+      "loss": 1.3133,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.25138238072395325,
+      "learning_rate": 0.0002,
+      "loss": 0.8902,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.22282397747039795,
+      "learning_rate": 0.0002,
+      "loss": 1.0653,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.14256241917610168,
+      "learning_rate": 0.0002,
+      "loss": 1.0377,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3921433687210083,
+      "learning_rate": 0.0002,
+      "loss": 0.8401,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.14009827375411987,
+      "learning_rate": 0.0002,
+      "loss": 1.1964,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.1723158359527588,
+      "learning_rate": 0.0002,
+      "loss": 0.8421,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.14431972801685333,
+      "learning_rate": 0.0002,
+      "loss": 1.0823,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.14121118187904358,
+      "learning_rate": 0.0002,
+      "loss": 0.9935,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0740255117416382,
+      "eval_runtime": 15.6966,
+      "eval_samples_per_second": 6.371,
+      "eval_steps_per_second": 0.255,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1781335026025772,
+      "learning_rate": 0.0002,
+      "loss": 0.8185,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.13026148080825806,
+      "learning_rate": 0.0002,
+      "loss": 1.1492,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.16785813868045807,
+      "learning_rate": 0.0002,
+      "loss": 0.7247,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.12899930775165558,
+      "learning_rate": 0.0002,
+      "loss": 0.9562,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.1439821869134903,
+      "learning_rate": 0.0002,
+      "loss": 0.9587,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.2685123383998871,
+      "learning_rate": 0.0002,
+      "loss": 0.6801,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.14089176058769226,
+      "learning_rate": 0.0002,
+      "loss": 1.1207,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.19689345359802246,
+      "learning_rate": 0.0002,
+      "loss": 0.6951,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.1005624458193779,
+      "learning_rate": 0.0002,
+      "loss": 0.9975,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.14424453675746918,
+      "learning_rate": 0.0002,
+      "loss": 0.8992,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.0923893451690674,
+      "eval_runtime": 4.0575,
+      "eval_samples_per_second": 24.645,
+      "eval_steps_per_second": 0.986,
+      "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-0007/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "train_loss": 0.947613294678505,
+    "train_runtime": 6009.2219,
+    "train_samples_per_second": 16.975,
+    "train_steps_per_second": 0.033
+}