Add v8 LoRA adapter + evaluation plots

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter/eval_plots/plot_06_rouge_heatmap.png filter=lfs diff=lfs merge=lfs -text
+adapter/eval_plots/plot_07_keyword_format_match.png filter=lfs diff=lfs merge=lfs -text
+adapter/eval_plots/plot_08_response_times.png filter=lfs diff=lfs merge=lfs -text
+adapter/eval_plots/plot_11_radar_chart.png filter=lfs diff=lfs merge=lfs -text
+adapter/eval_plots/plot_12_dashboard.png filter=lfs diff=lfs merge=lfs -text

adapter/README.md

@@ -0,0 +1,202 @@
+---
+base_model: codellama/CodeLlama-7b-Instruct-hf
+library_name: peft
+---
+
+# 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 0.13.2

adapter/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "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,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc0418e4e2f3e610f8389bdc2f89c65039ecc60301144df3809f365f3915006
+size 16794200

adapter/eval_plots/eval_log.json

@@ -0,0 +1,50 @@
+[
+  {
+    "step": 100,
+    "eval_loss": 1.8240644931793213
+  },
+  {
+    "step": 200,
+    "eval_loss": 1.0799707174301147
+  },
+  {
+    "step": 300,
+    "eval_loss": 0.9546574950218201
+  },
+  {
+    "step": 400,
+    "eval_loss": 0.8702907562255859
+  },
+  {
+    "step": 500,
+    "eval_loss": 0.787815272808075
+  },
+  {
+    "step": 600,
+    "eval_loss": 0.6270484328269958
+  },
+  {
+    "step": 700,
+    "eval_loss": 0.5892859101295471
+  },
+  {
+    "step": 800,
+    "eval_loss": 0.5660054087638855
+  },
+  {
+    "step": 900,
+    "eval_loss": 0.5496686697006226
+  },
+  {
+    "step": 1000,
+    "eval_loss": 0.5432103872299194
+  },
+  {
+    "step": 1100,
+    "eval_loss": 0.5394924879074097
+  },
+  {
+    "step": 1200,
+    "eval_loss": 0.5386649966239929
+  }
+]

adapter/eval_plots/eval_results.json

@@ -0,0 +1,314 @@
+{
+  "summary": {
+    "keyword_accuracy": 0.7058823529411765,
+    "format_accuracy": 0.0,
+    "precision": 1.0,
+    "recall": 0.7058823529411765,
+    "f1": 0.8275862068965517,
+    "avg_rouge1": 0.25364705882352945,
+    "avg_rouge2": 0.06123529411764707,
+    "avg_rougeL": 0.25364705882352945,
+    "avg_response_time": 16.716294117647056
+  },
+  "per_category": {
+    "DS Logic": {
+      "accuracy": 1.0,
+      "format": 0.0,
+      "rougeL": 0.0,
+      "avg_time": 16.393,
+      "n": 2
+    },
+    "LangChain": {
+      "accuracy": 0.0,
+      "format": 0.0,
+      "rougeL": 0.0,
+      "avg_time": 16.93,
+      "n": 4
+    },
+    "ML": {
+      "accuracy": 1.0,
+      "format": 0.0,
+      "rougeL": 0.43,
+      "avg_time": 16.838,
+      "n": 3
+    },
+    "Pandas": {
+      "accuracy": 1.0,
+      "format": 0.0,
+      "rougeL": 0.347,
+      "avg_time": 17.03,
+      "n": 4
+    },
+    "R": {
+      "accuracy": 0.5,
+      "format": 0.0,
+      "rougeL": 0.486,
+      "avg_time": 15.999,
+      "n": 2
+    },
+    "Viz": {
+      "accuracy": 1.0,
+      "format": 0.0,
+      "rougeL": 0.333,
+      "avg_time": 16.522,
+      "n": 2
+    }
+  },
+  "per_sample": [
+    {
+      "category": "LangChain",
+      "prompt": "What function limits the number of messages passed to a model by counting tokens in Langchain? in Python ?",
+      "keyword": "trim_messages",
+      "library": "import nltk",
+      "code": "nltk.LangChain(5)  \n.add_rule('[A-Za-z]+', '[A-Za-z]+')  \n.add_rule('[0-9]+', '[0-9]+')  \n.add_rule('[A-Za-z0-9]+', '[A-Za-z0-9]+')  \n.add_rule('[A-Za-z0-9\\.]+', '[A-Za-z0-9\\.]+')  \n.add_rule('[A-Za-z",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 0,
+      "response_time": 16.873,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "LangChain",
+      "prompt": "What argument enables jq schema parsing for content_key in JSONLoader in Langchain? in Python ?",
+      "keyword": "is_content_key_jq_parsable",
+      "library": "import pandas as pd",
+      "code": "df = pd.read_json('file.json', orient='records')",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 0,
+      "response_time": 17.915,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "LangChain",
+      "prompt": "What callback handler tracks token usage in Langchain? in Python ?",
+      "keyword": "UsageMetadataCallbackHandler",
+      "library": "TensorFlow",
+      "code": "tf.keras.callbacks.Callback()",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 0,
+      "response_time": 16.22,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "LangChain",
+      "prompt": "What taxonomy is used on GitHub Issues for sorting and discovery in Langchain? in Python ?",
+      "keyword": "Labels",
+      "library": "import pandas as pd",
+      "code": "df.sort_values('col', ascending=True).head()",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 0,
+      "response_time": 16.711,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Pandas",
+      "prompt": "How to drop missing values in a pandas DataFrame? in Python ?",
+      "keyword": "dropna",
+      "library": "pd",
+      "code": "df.dropna(inplace=True)  \n.",
+      "math": "",
+      "rouge1": 0.4,
+      "rouge2": 0.0,
+      "rougeL": 0.4,
+      "keyword_match": 1,
+      "response_time": 18.061,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Pandas",
+      "prompt": "How to read a CSV file using pandas? in Python ?",
+      "keyword": "read_csv",
+      "library": "import pandas as pd",
+      "code": "df = pd.read_csv('file.csv')  \n.",
+      "math": "",
+      "rouge1": 0.5,
+      "rouge2": 0.333,
+      "rougeL": 0.5,
+      "keyword_match": 1,
+      "response_time": 16.448,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Pandas",
+      "prompt": "How to rename a column in pandas? in Python ?",
+      "keyword": "rename",
+      "library": "import pandas as pd",
+      "code": "df.rename(columns={'old_col': 'new_col'}, inplace=True)  \n.",
+      "math": "",
+      "rouge1": 0.2,
+      "rouge2": 0.0,
+      "rougeL": 0.2,
+      "keyword_match": 1,
+      "response_time": 17.085,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Pandas",
+      "prompt": "How to group rows and compute aggregate in pandas? in Python ?",
+      "keyword": "groupby",
+      "library": "import pandas as pd",
+      "code": "df.groupby('category').agg({'value': 'sum'})  \n.",
+      "math": "",
+      "rouge1": 0.286,
+      "rouge2": 0.0,
+      "rougeL": 0.286,
+      "keyword_match": 1,
+      "response_time": 16.524,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "ML",
+      "prompt": "How to train a decision tree classifier in sklearn? in Python ?",
+      "keyword": "DecisionTreeClassifier",
+      "library": "from sklearn.tree import DecisionTreeClassifier",
+      "code": "clf = DecisionTreeClassifier()",
+      "math": "",
+      "rouge1": 0.667,
+      "rouge2": 0.0,
+      "rougeL": 0.667,
+      "keyword_match": 1,
+      "response_time": 16.391,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "ML",
+      "prompt": "How to split dataset into train and test in sklearn? in Python ?",
+      "keyword": "train_test_split",
+      "library": "from sklearn.model_selection import train_test_split",
+      "code": "X_train, X_test = train_test_split(df, test_size=0.2)",
+      "math": "",
+      "rouge1": 0.4,
+      "rouge2": 0.308,
+      "rougeL": 0.4,
+      "keyword_match": 1,
+      "response_time": 17.126,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "ML",
+      "prompt": "How to normalize features using StandardScaler in sklearn? in Python ?",
+      "keyword": "StandardScaler",
+      "library": "from sklearn.preprocessing import StandardScaler",
+      "code": "scaler = StandardScaler(); X_scaled = scaler.fit_transform(X)",
+      "math": "",
+      "rouge1": 0.222,
+      "rouge2": 0.0,
+      "rougeL": 0.222,
+      "keyword_match": 1,
+      "response_time": 16.996,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Viz",
+      "prompt": "How to plot a heatmap using seaborn? in Python ?",
+      "keyword": "heatmap",
+      "library": "import seaborn as sns",
+      "code": "sns.heatmap(df, annot=True)",
+      "math": "",
+      "rouge1": 0.333,
+      "rouge2": 0.0,
+      "rougeL": 0.333,
+      "keyword_match": 1,
+      "response_time": 16.279,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "Viz",
+      "prompt": "How to create a histogram using matplotlib? in Python ?",
+      "keyword": "hist",
+      "library": "import matplotlib.pyplot as plt",
+      "code": "plt.hist(data, bins=5)",
+      "math": "",
+      "rouge1": 0.333,
+      "rouge2": 0.0,
+      "rougeL": 0.333,
+      "keyword_match": 1,
+      "response_time": 16.764,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "R",
+      "prompt": "How to get the maximum value of a vector in R ?",
+      "keyword": "max(",
+      "library": "",
+      "code": "max_value <- max(vector)",
+      "math": "",
+      "rouge1": 0.4,
+      "rouge2": 0.0,
+      "rougeL": 0.4,
+      "keyword_match": 1,
+      "response_time": 15.953,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "R",
+      "prompt": "How to read a CSV file in R ?",
+      "keyword": "read.csv",
+      "library": "readr",
+      "code": "df <- read_csv(\"file.csv\")",
+      "math": "",
+      "rouge1": 0.571,
+      "rouge2": 0.4,
+      "rougeL": 0.571,
+      "keyword_match": 0,
+      "response_time": 16.045,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "DS Logic",
+      "prompt": "What does overfitting mean in machine learning? in Python ?",
+      "keyword": "overfit",
+      "library": "sklearn.linear_model",
+      "code": "X = df[col_num].values; y = df['target'].values; lr = LogisticRegression(penalty='l2', C=10); lr.fit(X, y)",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 1,
+      "response_time": 16.685,
+      "output_tokens": 200,
+      "format_correct": 0
+    },
+    {
+      "category": "DS Logic",
+      "prompt": "What is gradient descent in machine learning? in Python ?",
+      "keyword": "gradient",
+      "library": "from sklearn.linear_model import LinearRegression",
+      "code": "reg = LinearRegression(); reg.fit(X, y)",
+      "math": "",
+      "rouge1": 0.0,
+      "rouge2": 0.0,
+      "rougeL": 0.0,
+      "keyword_match": 1,
+      "response_time": 16.101,
+      "output_tokens": 200,
+      "format_correct": 0
+    }
+  ]
+}

adapter/eval_plots/loss_log.json

@@ -0,0 +1,482 @@
+[
+  {
+    "step": 10,
+    "loss": 3.7145
+  },
+  {
+    "step": 20,
+    "loss": 3.8108
+  },
+  {
+    "step": 30,
+    "loss": 3.8272
+  },
+  {
+    "step": 40,
+    "loss": 3.6441
+  },
+  {
+    "step": 50,
+    "loss": 3.6304
+  },
+  {
+    "step": 60,
+    "loss": 3.4205
+  },
+  {
+    "step": 70,
+    "loss": 3.0848
+  },
+  {
+    "step": 80,
+    "loss": 2.7674
+  },
+  {
+    "step": 90,
+    "loss": 2.6102
+  },
+  {
+    "step": 100,
+    "loss": 2.1779
+  },
+  {
+    "step": 110,
+    "loss": 1.6865
+  },
+  {
+    "step": 120,
+    "loss": 1.4528
+  },
+  {
+    "step": 130,
+    "loss": 1.3545
+  },
+  {
+    "step": 140,
+    "loss": 1.2961
+  },
+  {
+    "step": 150,
+    "loss": 1.2643
+  },
+  {
+    "step": 160,
+    "loss": 1.1677
+  },
+  {
+    "step": 170,
+    "loss": 1.1044
+  },
+  {
+    "step": 180,
+    "loss": 1.1668
+  },
+  {
+    "step": 190,
+    "loss": 1.098
+  },
+  {
+    "step": 200,
+    "loss": 1.0887
+  },
+  {
+    "step": 210,
+    "loss": 1.0874
+  },
+  {
+    "step": 220,
+    "loss": 1.1033
+  },
+  {
+    "step": 230,
+    "loss": 1.0045
+  },
+  {
+    "step": 240,
+    "loss": 1.0166
+  },
+  {
+    "step": 250,
+    "loss": 1.0397
+  },
+  {
+    "step": 260,
+    "loss": 1.02
+  },
+  {
+    "step": 270,
+    "loss": 0.9788
+  },
+  {
+    "step": 280,
+    "loss": 1.0221
+  },
+  {
+    "step": 290,
+    "loss": 0.9507
+  },
+  {
+    "step": 300,
+    "loss": 0.9196
+  },
+  {
+    "step": 310,
+    "loss": 0.9043
+  },
+  {
+    "step": 320,
+    "loss": 0.9055
+  },
+  {
+    "step": 330,
+    "loss": 0.9389
+  },
+  {
+    "step": 340,
+    "loss": 0.9211
+  },
+  {
+    "step": 350,
+    "loss": 0.9335
+  },
+  {
+    "step": 360,
+    "loss": 0.9127
+  },
+  {
+    "step": 370,
+    "loss": 0.8907
+  },
+  {
+    "step": 380,
+    "loss": 0.8504
+  },
+  {
+    "step": 390,
+    "loss": 0.9536
+  },
+  {
+    "step": 400,
+    "loss": 0.8082
+  },
+  {
+    "step": 410,
+    "loss": 0.8522
+  },
+  {
+    "step": 420,
+    "loss": 0.8181
+  },
+  {
+    "step": 430,
+    "loss": 0.7697
+  },
+  {
+    "step": 440,
+    "loss": 0.8197
+  },
+  {
+    "step": 450,
+    "loss": 0.8189
+  },
+  {
+    "step": 460,
+    "loss": 0.7979
+  },
+  {
+    "step": 470,
+    "loss": 0.8282
+  },
+  {
+    "step": 480,
+    "loss": 0.8882
+  },
+  {
+    "step": 490,
+    "loss": 0.8076
+  },
+  {
+    "step": 500,
+    "loss": 0.799
+  },
+  {
+    "step": 510,
+    "loss": 0.6938
+  },
+  {
+    "step": 520,
+    "loss": 0.7809
+  },
+  {
+    "step": 530,
+    "loss": 0.7753
+  },
+  {
+    "step": 540,
+    "loss": 0.7249
+  },
+  {
+    "step": 550,
+    "loss": 0.7071
+  },
+  {
+    "step": 560,
+    "loss": 0.6511
+  },
+  {
+    "step": 570,
+    "loss": 0.6253
+  },
+  {
+    "step": 580,
+    "loss": 0.6207
+  },
+  {
+    "step": 590,
+    "loss": 0.6019
+  },
+  {
+    "step": 600,
+    "loss": 0.5924
+  },
+  {
+    "step": 610,
+    "loss": 0.5868
+  },
+  {
+    "step": 620,
+    "loss": 0.5878
+  },
+  {
+    "step": 630,
+    "loss": 0.5844
+  },
+  {
+    "step": 640,
+    "loss": 0.592
+  },
+  {
+    "step": 650,
+    "loss": 0.5673
+  },
+  {
+    "step": 660,
+    "loss": 0.5592
+  },
+  {
+    "step": 670,
+    "loss": 0.6151
+  },
+  {
+    "step": 680,
+    "loss": 0.5323
+  },
+  {
+    "step": 690,
+    "loss": 0.5866
+  },
+  {
+    "step": 700,
+    "loss": 0.5334
+  },
+  {
+    "step": 710,
+    "loss": 0.5482
+  },
+  {
+    "step": 720,
+    "loss": 0.5439
+  },
+  {
+    "step": 730,
+    "loss": 0.5287
+  },
+  {
+    "step": 740,
+    "loss": 0.6061
+  },
+  {
+    "step": 750,
+    "loss": 0.5285
+  },
+  {
+    "step": 760,
+    "loss": 0.5141
+  },
+  {
+    "step": 770,
+    "loss": 0.4986
+  },
+  {
+    "step": 780,
+    "loss": 0.5414
+  },
+  {
+    "step": 790,
+    "loss": 0.5625
+  },
+  {
+    "step": 800,
+    "loss": 0.5384
+  },
+  {
+    "step": 810,
+    "loss": 0.5576
+  },
+  {
+    "step": 820,
+    "loss": 0.5088
+  },
+  {
+    "step": 830,
+    "loss": 0.5248
+  },
+  {
+    "step": 840,
+    "loss": 0.5242
+  },
+  {
+    "step": 850,
+    "loss": 0.4592
+  },
+  {
+    "step": 860,
+    "loss": 0.5213
+  },
+  {
+    "step": 870,
+    "loss": 0.4535
+  },
+  {
+    "step": 880,
+    "loss": 0.5557
+  },
+  {
+    "step": 890,
+    "loss": 0.5018
+  },
+  {
+    "step": 900,
+    "loss": 0.5108
+  },
+  {
+    "step": 910,
+    "loss": 0.4915
+  },
+  {
+    "step": 920,
+    "loss": 0.4874
+  },
+  {
+    "step": 930,
+    "loss": 0.5796
+  },
+  {
+    "step": 940,
+    "loss": 0.4931
+  },
+  {
+    "step": 950,
+    "loss": 0.4407
+  },
+  {
+    "step": 960,
+    "loss": 0.4776
+  },
+  {
+    "step": 970,
+    "loss": 0.4795
+  },
+  {
+    "step": 980,
+    "loss": 0.4901
+  },
+  {
+    "step": 990,
+    "loss": 0.5025
+  },
+  {
+    "step": 1000,
+    "loss": 0.4933
+  },
+  {
+    "step": 1010,
+    "loss": 0.5486
+  },
+  {
+    "step": 1020,
+    "loss": 0.52
+  },
+  {
+    "step": 1030,
+    "loss": 0.4893
+  },
+  {
+    "step": 1040,
+    "loss": 0.4921
+  },
+  {
+    "step": 1050,
+    "loss": 0.4784
+  },
+  {
+    "step": 1060,
+    "loss": 0.4854
+  },
+  {
+    "step": 1070,
+    "loss": 0.5374
+  },
+  {
+    "step": 1080,
+    "loss": 0.4991
+  },
+  {
+    "step": 1090,
+    "loss": 0.5092
+  },
+  {
+    "step": 1100,
+    "loss": 0.5146
+  },
+  {
+    "step": 1110,
+    "loss": 0.5591
+  },
+  {
+    "step": 1120,
+    "loss": 0.521
+  },
+  {
+    "step": 1130,
+    "loss": 0.4831
+  },
+  {
+    "step": 1140,
+    "loss": 0.4785
+  },
+  {
+    "step": 1150,
+    "loss": 0.5337
+  },
+  {
+    "step": 1160,
+    "loss": 0.4591
+  },
+  {
+    "step": 1170,
+    "loss": 0.5437
+  },
+  {
+    "step": 1180,
+    "loss": 0.5602
+  },
+  {
+    "step": 1190,
+    "loss": 0.4957
+  },
+  {
+    "step": 1200,
+    "loss": 0.5573
+  }
+]

adapter/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapter/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

adapter/tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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 | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}