Upload 13 files

guardrank_lora/README.md

@@ -0,0 +1,206 @@
+---
+library_name: peft
+base_model: /mnt/cachenew/gutianle/modelscope/Llama-2-7b-ms
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

guardrank_lora/adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/cachenew/gutianle/modelscope/Llama-2-7b-ms",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

guardrank_lora/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cecc9a384baf2b3b9a067c6665248508e958c9738b255c183a5ce0b710303c45
+size 33712718

guardrank_lora/added_tokens.json

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

guardrank_lora/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b4295392cdb98a4360531b562f5f9e1c786673f46a214dcd94b42b97d85ba4
+size 67455546

guardrank_lora/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70de0cb45e748531ca4e97cd52bc06b38d076f30a6495dca9796b098072c48de
+size 14244

guardrank_lora/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641b0577c8df5dd91e5c9b25b70d6684b9fb3e8b805e34cc6f701af57a574234
+size 1064

guardrank_lora/special_tokens_map.json

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

guardrank_lora/tokenizer.model

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

guardrank_lora/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

guardrank_lora/trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_metric": 0.7517201834862385,
+  "best_model_checkpoint": "/mnt/cachenew/gutianle/llama2-scorer-non-existent/checkpoint-1800",
+  "epoch": 0.9174311926605505,
+  "eval_steps": 100,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 1.409,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.4294724770642202,
+      "eval_f1-score": 0.41676886432858656,
+      "eval_loss": 1.2865188121795654,
+      "eval_precision": 0.5191394843763429,
+      "eval_recall": 0.4294724770642202,
+      "eval_runtime": 100.35,
+      "eval_samples_per_second": 17.379,
+      "eval_steps_per_second": 2.172,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001,
+      "loss": 1.0433,
+      "step": 200
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.6439220183486238,
+      "eval_f1-score": 0.6287928936906987,
+      "eval_loss": 0.9169857501983643,
+      "eval_precision": 0.6326166016462452,
+      "eval_recall": 0.6439220183486238,
+      "eval_runtime": 99.1386,
+      "eval_samples_per_second": 17.592,
+      "eval_steps_per_second": 2.199,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001,
+      "loss": 0.9457,
+      "step": 300
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.573394495412844,
+      "eval_f1-score": 0.5780536942349181,
+      "eval_loss": 0.9270332455635071,
+      "eval_precision": 0.6119488919407539,
+      "eval_recall": 0.573394495412844,
+      "eval_runtime": 99.5145,
+      "eval_samples_per_second": 17.525,
+      "eval_steps_per_second": 2.191,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001,
+      "loss": 0.8176,
+      "step": 400
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.6702981651376146,
+      "eval_f1-score": 0.6704055625650827,
+      "eval_loss": 0.8484154343605042,
+      "eval_precision": 0.6748752577010106,
+      "eval_recall": 0.6702981651376146,
+      "eval_runtime": 99.7876,
+      "eval_samples_per_second": 17.477,
+      "eval_steps_per_second": 2.185,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001,
+      "loss": 0.7769,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.6955275229357798,
+      "eval_f1-score": 0.6937246764104357,
+      "eval_loss": 0.8070082068443298,
+      "eval_precision": 0.6933530425142568,
+      "eval_recall": 0.6955275229357798,
+      "eval_runtime": 99.3769,
+      "eval_samples_per_second": 17.549,
+      "eval_steps_per_second": 2.194,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001,
+      "loss": 0.7069,
+      "step": 600
+    },
+    {
+      "epoch": 0.31,
+      "eval_accuracy": 0.6961009174311926,
+      "eval_f1-score": 0.6962474525389031,
+      "eval_loss": 0.8322665095329285,
+      "eval_precision": 0.7002298404175326,
+      "eval_recall": 0.6961009174311926,
+      "eval_runtime": 99.2464,
+      "eval_samples_per_second": 17.572,
+      "eval_steps_per_second": 2.197,
+      "step": 600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001,
+      "loss": 0.6742,
+      "step": 700
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.7276376146788991,
+      "eval_f1-score": 0.7163514624677091,
+      "eval_loss": 0.7878208160400391,
+      "eval_precision": 0.731064800275646,
+      "eval_recall": 0.7276376146788991,
+      "eval_runtime": 99.1023,
+      "eval_samples_per_second": 17.598,
+      "eval_steps_per_second": 2.2,
+      "step": 700
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001,
+      "loss": 0.7139,
+      "step": 800
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.694954128440367,
+      "eval_f1-score": 0.7017678594633088,
+      "eval_loss": 0.7812691926956177,
+      "eval_precision": 0.7171557777434424,
+      "eval_recall": 0.694954128440367,
+      "eval_runtime": 99.2742,
+      "eval_samples_per_second": 17.568,
+      "eval_steps_per_second": 2.196,
+      "step": 800
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001,
+      "loss": 0.7566,
+      "step": 900
+    },
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.6909403669724771,
+      "eval_f1-score": 0.6922199349668261,
+      "eval_loss": 0.7475219368934631,
+      "eval_precision": 0.7040747986976179,
+      "eval_recall": 0.6909403669724771,
+      "eval_runtime": 99.2593,
+      "eval_samples_per_second": 17.57,
+      "eval_steps_per_second": 2.196,
+      "step": 900
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001,
+      "loss": 0.6692,
+      "step": 1000
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.6857798165137615,
+      "eval_f1-score": 0.6973150689879362,
+      "eval_loss": 0.7810325026512146,
+      "eval_precision": 0.7120290886583457,
+      "eval_recall": 0.6857798165137615,
+      "eval_runtime": 99.239,
+      "eval_samples_per_second": 17.574,
+      "eval_steps_per_second": 2.197,
+      "step": 1000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001,
+      "loss": 0.6733,
+      "step": 1100
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.7368119266055045,
+      "eval_f1-score": 0.7271862000397501,
+      "eval_loss": 0.7271122336387634,
+      "eval_precision": 0.74773502586483,
+      "eval_recall": 0.7368119266055045,
+      "eval_runtime": 99.0466,
+      "eval_samples_per_second": 17.608,
+      "eval_steps_per_second": 2.201,
+      "step": 1100
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001,
+      "loss": 0.6356,
+      "step": 1200
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.7253440366972477,
+      "eval_f1-score": 0.7249868939903279,
+      "eval_loss": 0.7682604193687439,
+      "eval_precision": 0.7249192202979644,
+      "eval_recall": 0.7253440366972477,
+      "eval_runtime": 99.36,
+      "eval_samples_per_second": 17.552,
+      "eval_steps_per_second": 2.194,
+      "step": 1200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001,
+      "loss": 0.6112,
+      "step": 1300
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.7264908256880734,
+      "eval_f1-score": 0.7199307263891085,
+      "eval_loss": 0.8078410029411316,
+      "eval_precision": 0.7206056594932215,
+      "eval_recall": 0.7264908256880734,
+      "eval_runtime": 99.258,
+      "eval_samples_per_second": 17.57,
+      "eval_steps_per_second": 2.196,
+      "step": 1300
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001,
+      "loss": 0.646,
+      "step": 1400
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy": 0.7431192660550459,
+      "eval_f1-score": 0.7350696097040301,
+      "eval_loss": 0.7144489288330078,
+      "eval_precision": 0.7421391963845961,
+      "eval_recall": 0.7431192660550459,
+      "eval_runtime": 99.3431,
+      "eval_samples_per_second": 17.555,
+      "eval_steps_per_second": 2.194,
+      "step": 1400
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001,
+      "loss": 0.6052,
+      "step": 1500
+    },
+    {
+      "epoch": 0.76,
+      "eval_accuracy": 0.7471330275229358,
+      "eval_f1-score": 0.7394703056430186,
+      "eval_loss": 0.679287850856781,
+      "eval_precision": 0.7525699542508473,
+      "eval_recall": 0.7471330275229358,
+      "eval_runtime": 99.4231,
+      "eval_samples_per_second": 17.541,
+      "eval_steps_per_second": 2.193,
+      "step": 1500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001,
+      "loss": 0.6004,
+      "step": 1600
+    },
+    {
+      "epoch": 0.82,
+      "eval_accuracy": 0.75,
+      "eval_f1-score": 0.7503577703532133,
+      "eval_loss": 0.7611460089683533,
+      "eval_precision": 0.7582961750700967,
+      "eval_recall": 0.75,
+      "eval_runtime": 99.3947,
+      "eval_samples_per_second": 17.546,
+      "eval_steps_per_second": 2.193,
+      "step": 1600
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0001,
+      "loss": 0.6041,
+      "step": 1700
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.7563073394495413,
+      "eval_f1-score": 0.7497128952328905,
+      "eval_loss": 0.7003496289253235,
+      "eval_precision": 0.7580686951357652,
+      "eval_recall": 0.7563073394495413,
+      "eval_runtime": 99.3241,
+      "eval_samples_per_second": 17.559,
+      "eval_steps_per_second": 2.195,
+      "step": 1700
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001,
+      "loss": 0.5445,
+      "step": 1800
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.7517201834862385,
+      "eval_f1-score": 0.7465676797118755,
+      "eval_loss": 0.6659787893295288,
+      "eval_precision": 0.7528237883767219,
+      "eval_recall": 0.7517201834862385,
+      "eval_runtime": 99.3316,
+      "eval_samples_per_second": 17.557,
+      "eval_steps_per_second": 2.195,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5886,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "total_flos": 2.868620669485056e+17,
+  "trial_name": null,
+  "trial_params": null
+}

guardrank_lora/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823820e217deb656ea241281687228f7d92e30b4248ef149e21b0e6464e80ccc
+size 4536