IO v3

io-chatbot-v3/checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-100/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-100/trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 5,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 4764264824832000.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-104/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-104/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-104/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-104/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-104/trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 26.0,
+  "eval_steps": 5,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 4954835417825280.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-108/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-108/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-108/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-108/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-108/trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.0,
+  "eval_steps": 5,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 2.774839039480296e-05,
+      "loss": 0.5042,
+      "step": 106
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 2.7664918882530227e-05,
+      "loss": 0.4999,
+      "step": 108
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 5145406010818560.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-112/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-112/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-112/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-112/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-112/trainer_state.json

@@ -0,0 +1,357 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 28.0,
+  "eval_steps": 5,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 2.774839039480296e-05,
+      "loss": 0.5042,
+      "step": 106
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 2.7664918882530227e-05,
+      "loss": 0.4999,
+      "step": 108
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 2.7580058519181363e-05,
+      "loss": 0.4847,
+      "step": 110
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 2.7493818610651493e-05,
+      "loss": 0.467,
+      "step": 112
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 5335976603811840.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-116/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-116/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-116/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-116/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-116/trainer_state.json

@@ -0,0 +1,369 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 29.0,
+  "eval_steps": 5,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 2.774839039480296e-05,
+      "loss": 0.5042,
+      "step": 106
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 2.7664918882530227e-05,
+      "loss": 0.4999,
+      "step": 108
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 2.7580058519181363e-05,
+      "loss": 0.4847,
+      "step": 110
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 2.7493818610651493e-05,
+      "loss": 0.467,
+      "step": 112
+    },
+    {
+      "epoch": 28.5,
+      "learning_rate": 2.7406208614118427e-05,
+      "loss": 0.462,
+      "step": 114
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 2.731723813700556e-05,
+      "loss": 0.4576,
+      "step": 116
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 5526547196805120.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-12/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-12/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-12/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-12/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-12/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 5,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 571711778979840.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-120/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-120/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-120/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-120/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-120/trainer_state.json

@@ -0,0 +1,381 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 5,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 2.774839039480296e-05,
+      "loss": 0.5042,
+      "step": 106
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 2.7664918882530227e-05,
+      "loss": 0.4999,
+      "step": 108
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 2.7580058519181363e-05,
+      "loss": 0.4847,
+      "step": 110
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 2.7493818610651493e-05,
+      "loss": 0.467,
+      "step": 112
+    },
+    {
+      "epoch": 28.5,
+      "learning_rate": 2.7406208614118427e-05,
+      "loss": 0.462,
+      "step": 114
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 2.731723813700556e-05,
+      "loss": 0.4576,
+      "step": 116
+    },
+    {
+      "epoch": 29.5,
+      "learning_rate": 2.7226916935928312e-05,
+      "loss": 0.45,
+      "step": 118
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 0.4045,
+      "step": 120
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 5717117789798400.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-124/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-124/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

io-chatbot-v3/checkpoint-124/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

io-chatbot-v3/checkpoint-124/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

io-chatbot-v3/checkpoint-124/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 31.0,
+  "eval_steps": 5,
+  "global_step": 124,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9999177540482684e-05,
+      "loss": 2.6428,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9996710252122685e-05,
+      "loss": 2.1838,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.9992598405485974e-05,
+      "loss": 1.8524,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.59,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.9979443021318607e-05,
+      "loss": 1.4015,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.9970400926424075e-05,
+      "loss": 1.2128,
+      "step": 12
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.995971715836687e-05,
+      "loss": 1.1418,
+      "step": 14
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 1.0389,
+      "step": 16
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.9933429469046202e-05,
+      "loss": 1.0268,
+      "step": 18
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.99178284305241e-05,
+      "loss": 0.9734,
+      "step": 20
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.9900591484005944e-05,
+      "loss": 0.9755,
+      "step": 22
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.9142,
+      "step": 24
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.9861217607071655e-05,
+      "loss": 0.8872,
+      "step": 26
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.983908499444483e-05,
+      "loss": 0.8633,
+      "step": 28
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 0.8248,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.8352,
+      "step": 32
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.9762934119538628e-05,
+      "loss": 0.8017,
+      "step": 34
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.9734308760930333e-05,
+      "loss": 0.7705,
+      "step": 36
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.9704067619325828e-05,
+      "loss": 0.7619,
+      "step": 38
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7593,
+      "step": 40
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 2.9638751429081213e-05,
+      "loss": 0.7469,
+      "step": 42
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.9603683543097406e-05,
+      "loss": 0.7477,
+      "step": 44
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 2.9567014198644542e-05,
+      "loss": 0.716,
+      "step": 46
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.7351,
+      "step": 48
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.72,
+      "step": 50
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.9447438501964873e-05,
+      "loss": 0.714,
+      "step": 52
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 2.9404405285154146e-05,
+      "loss": 0.6994,
+      "step": 54
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.7064,
+      "step": 56
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 2.9313604927744153e-05,
+      "loss": 0.6807,
+      "step": 58
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.6969,
+      "step": 60
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 2.9216526150143788e-05,
+      "loss": 0.6836,
+      "step": 62
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.6557,
+      "step": 64
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.9113211534313385e-05,
+      "loss": 0.6619,
+      "step": 66
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 2.9059229842378373e-05,
+      "loss": 0.6496,
+      "step": 68
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 2.9003706397458025e-05,
+      "loss": 0.6268,
+      "step": 70
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.6586,
+      "step": 72
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.8888058772149923e-05,
+      "loss": 0.6197,
+      "step": 74
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.8827947273827508e-05,
+      "loss": 0.638,
+      "step": 76
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 2.8766319385259717e-05,
+      "loss": 0.6093,
+      "step": 78
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.6089,
+      "step": 80
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 2.863854163570603e-05,
+      "loss": 0.6108,
+      "step": 82
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 2.8572405786990293e-05,
+      "loss": 0.5776,
+      "step": 84
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 2.8504781571032906e-05,
+      "loss": 0.5776,
+      "step": 86
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5997,
+      "step": 88
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.5579,
+      "step": 90
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.829305368846822e-05,
+      "loss": 0.579,
+      "step": 92
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.821955178097488e-05,
+      "loss": 0.5689,
+      "step": 94
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5278,
+      "step": 96
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 2.8068207166802843e-05,
+      "loss": 0.55,
+      "step": 98
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 2.7911130405059155e-05,
+      "loss": 0.5342,
+      "step": 102
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5021,
+      "step": 104
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 2.774839039480296e-05,
+      "loss": 0.5042,
+      "step": 106
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 2.7664918882530227e-05,
+      "loss": 0.4999,
+      "step": 108
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 2.7580058519181363e-05,
+      "loss": 0.4847,
+      "step": 110
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 2.7493818610651493e-05,
+      "loss": 0.467,
+      "step": 112
+    },
+    {
+      "epoch": 28.5,
+      "learning_rate": 2.7406208614118427e-05,
+      "loss": 0.462,
+      "step": 114
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 2.731723813700556e-05,
+      "loss": 0.4576,
+      "step": 116
+    },
+    {
+      "epoch": 29.5,
+      "learning_rate": 2.7226916935928312e-05,
+      "loss": 0.45,
+      "step": 118
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 0.4045,
+      "step": 120
+    },
+    {
+      "epoch": 30.5,
+      "learning_rate": 2.7042262127866718e-05,
+      "loss": 0.424,
+      "step": 122
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 2.6947948770362945e-05,
+      "loss": 0.3926,
+      "step": 124
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "total_flos": 5907688382791680.0,
+  "train_batch_size": 52,
+  "trial_name": null,
+  "trial_params": null
+}

io-chatbot-v3/checkpoint-128/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
+---
+
+# 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 0.8.2

io-chatbot-v3/checkpoint-128/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}