Upload fine-tuned Mistral BP Doctor model

README.md

@@ -0,0 +1,164 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- medical
+- healthcare
+- blood-pressure
+- mistral
+- conversational-ai
+- health-assistant
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+datasets:
+- TesterColab/MIMICDB
+pipeline_tag: text-generation
+---
+
+# Mistral-7B Blood Pressure Medical Assistant
+
+## Model Description
+
+This is a fine-tuned version of **Mistral-7B-Instruct-v0.3** specialized for blood pressure assessment and medical consultation. The model acts as an intelligent medical assistant that:
+
+- ✅ Analyzes blood pressure readings
+- ✅ Asks relevant follow-up questions based on BP levels
+- ✅ Provides personalized medical guidance
+- ✅ Handles various scenarios (with/without patient context)
+- ✅ **Never hallucinates information** - only responds to what the patient shares
+- ✅ Recognizes emergency situations (hypertensive crisis)
+
+## Model Type
+
+**LoRA Adapter**
+
+## Training Details
+
+- **Base Model**: mistralai/Mistral-7B-Instruct-v0.3
+- **Dataset**: TesterColab/MIMICDB (880 clinical examples)
+- **Training Method**: LoRA (Low-Rank Adaptation)
+- **Training Scenarios**:
+  1. BP reading only (model asks questions)
+  2. BP with patient context (model uses provided information)
+  3. Speech-to-text variations
+
+## Usage
+
+### Installation
+
+```bash
+pip install transformers torch peft accelerate
+```
+
+### Basic Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+# Load model
+model_id = "TesterColab/mistral-finetuned-v3"
+base_model_id = "mistralai/Mistral-7B-Instruct-v0.3"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+base_model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map='auto', torch_dtype=torch.float16)
+model = PeftModel.from_pretrained(base_model, model_id)
+
+# Use the model
+prompt = """<s>[INST] You are a medical doctor. A patient shares their blood pressure reading. Analyze it and respond appropriately - if abnormal, ask relevant questions; if normal, provide encouragement. Never assume information the patient hasn't told you.
+
+Patient: My blood pressure is 145 over 95 [/INST]
+
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=300, temperature=0.7, top_p=0.9)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response.split('[/INST]')[-1].strip())
+```
+
+### Example Conversations
+
+**Example 1: Normal BP**
+```
+User: My blood pressure is 115 over 75
+Assistant: Your blood pressure reading of 115/75 mmHg is within the normal range - that's great! To maintain this healthy blood pressure, continue with regular exercise, a balanced diet low in sodium, maintain a healthy weight, limit alcohol, and manage stress. Keep monitoring it regularly.
+```
+
+**Example 2: High BP - Asks Questions**
+```
+User: 145 over 95
+Assistant: Your blood pressure reading of 145/95 indicates Stage 2 hypertension. To help you properly, I need to understand your health better. Can you tell me: Do you smoke? How often do you exercise? Do you have any family history of heart disease or stroke? Are you currently taking any medications?
+```
+
+**Example 3: With Context**
+```
+User: My BP is 130 over 85 and I smoke
+Assistant: Your blood pressure reading of 130/85 shows Stage 1 hypertension, and smoking is a significant risk factor that can worsen this. I need to understand more: How much do you smoke per day? How long have you been smoking? Have you tried to quit before? Also, tell me about your exercise routine and diet.
+```
+
+## Intended Use
+
+- 🏥 Health monitoring applications
+- 📱 Mobile health assistants
+- 💬 Conversational health bots
+- 🩺 Telemedicine support tools
+
+## Limitations
+
+⚠️ **Important Medical Disclaimer**:
+- This model is for **informational purposes only**
+- **NOT a replacement for professional medical advice**
+- Always consult healthcare professionals for medical decisions
+- In emergencies (chest pain, severe symptoms), seek immediate medical care
+- Model may occasionally generate incorrect medical information
+
+## Ethical Considerations
+
+- Trained to recognize emergency situations
+- Asks appropriate follow-up questions
+- Does not assume or hallucinate patient information
+- Provides general guidance, not diagnoses
+- Encourages seeking professional medical care when appropriate
+
+## Training Data
+
+Trained on the MIMICDB dataset containing clinical blood pressure readings with patient context including:
+- Age groups
+- Smoking status
+- Pregnancy status
+- Activity levels
+- Diet information
+- ABP (Arterial Blood Pressure) measurements
+
+## Performance
+
+The model has been trained to handle multiple scenarios:
+- ✅ BP readings without context → Asks appropriate questions
+- ✅ BP readings with patient info → Uses provided context
+- ✅ Emergency situations → Recognizes and advises immediate care
+- ✅ Normal readings → Provides encouragement and maintenance tips
+
+## Citation
+
+```bibtex
+@model{mistral-bp-doctor,
+  author = {TesterColab},
+  title = {Mistral-7B Blood Pressure Medical Assistant},
+  year = {2024},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/TesterColab/mistral-finetuned-v3}
+}
+```
+
+## License
+
+Apache 2.0 (inherits from Mistral-7B-Instruct-v0.3)
+
+## Contact
+
+For questions or issues, please open an issue on the model repository.
+
+---
+
+**Built with ❤️ for better health monitoring**

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647b406a89aa7eef1ef90b8f2a7072954db3eabd841f067d3fbed30bebb6a894
+size 671149168

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-298/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-298/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-298/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbad7bd61b442e37b325c37839b74ef3a744cf3682d4e942e38f59cf2ab04cc
+size 671149168

checkpoint-298/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-298/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8010c218b46eae68d0ae211f866b65cdfc91b92fbc2390ec3dd5b59ef20f6d56
+size 1342453899

checkpoint-298/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffca8166398eac90c27cd2a42adf9d0eced63586e3fa75dc51c2546f8a487a5
+size 14645

checkpoint-298/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b928064440f9470d27d84fe30538095e46afc896a930478830ece74934641668
+size 1465

checkpoint-298/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
+  }
+}

checkpoint-298/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-298/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 298,
+  "best_metric": 0.24624043703079224,
+  "best_model_checkpoint": "./mistral-bp-doctor/checkpoint-298",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 298,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 0.5559964776039124,
+      "learning_rate": 0.00019993420599300602,
+      "loss": 1.9115,
+      "step": 20
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 0.375236839056015,
+      "learning_rate": 0.000198359474690631,
+      "loss": 0.389,
+      "step": 40
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.19160901010036469,
+      "learning_rate": 0.00019471727939498744,
+      "loss": 0.2647,
+      "step": 60
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.1633908897638321,
+      "learning_rate": 0.00018908417711955972,
+      "loss": 0.2575,
+      "step": 80
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.06298425048589706,
+      "learning_rate": 0.00018157857268667396,
+      "loss": 0.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.07009627670049667,
+      "learning_rate": 0.00017235822992092893,
+      "loss": 0.2513,
+      "step": 120
+    },
+    {
+      "epoch": 0.9427609427609428,
+      "grad_norm": 0.05074545741081238,
+      "learning_rate": 0.0001616169555372722,
+      "loss": 0.2516,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2505706548690796,
+      "eval_runtime": 74.0922,
+      "eval_samples_per_second": 3.563,
+      "eval_steps_per_second": 0.891,
+      "step": 149
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.0452318899333477,
+      "learning_rate": 0.00014958052542663727,
+      "loss": 0.2496,
+      "step": 160
+    },
+    {
+      "epoch": 1.2087542087542087,
+      "grad_norm": 0.047174468636512756,
+      "learning_rate": 0.00013650193896645583,
+      "loss": 0.2506,
+      "step": 180
+    },
+    {
+      "epoch": 1.3434343434343434,
+      "grad_norm": 0.05392182618379593,
+      "learning_rate": 0.0001226561011079216,
+      "loss": 0.2498,
+      "step": 200
+    },
+    {
+      "epoch": 1.4781144781144782,
+      "grad_norm": 0.04376411437988281,
+      "learning_rate": 0.0001083340440197117,
+      "loss": 0.2484,
+      "step": 220
+    },
+    {
+      "epoch": 1.612794612794613,
+      "grad_norm": 0.04754996299743652,
+      "learning_rate": 9.383680974614915e-05,
+      "loss": 0.2462,
+      "step": 240
+    },
+    {
+      "epoch": 1.7474747474747474,
+      "grad_norm": 0.03840889409184456,
+      "learning_rate": 7.94691224630883e-05,
+      "loss": 0.2445,
+      "step": 260
+    },
+    {
+      "epoch": 1.8821548821548821,
+      "grad_norm": 0.04592665284872055,
+      "learning_rate": 6.553298333734812e-05,
+      "loss": 0.2455,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.24624043703079224,
+      "eval_runtime": 74.1325,
+      "eval_samples_per_second": 3.561,
+      "eval_steps_per_second": 0.89,
+      "step": 298
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 447,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.251900958306468e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-298/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3368fe8425b6a161e11d6c1fbbf66be8646beca69bf81193ad2a1292f8d3c8
+size 5841

checkpoint-447/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-447/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-447/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647b406a89aa7eef1ef90b8f2a7072954db3eabd841f067d3fbed30bebb6a894
+size 671149168

checkpoint-447/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-447/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9a81f860788f58fd5724dda5a3e873d164e954d84d23e82c6fe76ed2a476d6
+size 1342453899

checkpoint-447/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6019d1a263972b8c72790fdf52a4d03fece316e28934235558eba2015691e2
+size 14645

checkpoint-447/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933b2ebad8ab9bcd2ab2c854312edd4dba7ae2b2e84a3ca300d969531f4485df
+size 1465

checkpoint-447/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
+  }
+}

checkpoint-447/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-447/trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 447,
+  "best_metric": 0.24426761269569397,
+  "best_model_checkpoint": "./mistral-bp-doctor/checkpoint-447",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 447,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 0.5559964776039124,
+      "learning_rate": 0.00019993420599300602,
+      "loss": 1.9115,
+      "step": 20
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 0.375236839056015,
+      "learning_rate": 0.000198359474690631,
+      "loss": 0.389,
+      "step": 40
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.19160901010036469,
+      "learning_rate": 0.00019471727939498744,
+      "loss": 0.2647,
+      "step": 60
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.1633908897638321,
+      "learning_rate": 0.00018908417711955972,
+      "loss": 0.2575,
+      "step": 80
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.06298425048589706,
+      "learning_rate": 0.00018157857268667396,
+      "loss": 0.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.07009627670049667,
+      "learning_rate": 0.00017235822992092893,
+      "loss": 0.2513,
+      "step": 120
+    },
+    {
+      "epoch": 0.9427609427609428,
+      "grad_norm": 0.05074545741081238,
+      "learning_rate": 0.0001616169555372722,
+      "loss": 0.2516,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2505706548690796,
+      "eval_runtime": 74.0922,
+      "eval_samples_per_second": 3.563,
+      "eval_steps_per_second": 0.891,
+      "step": 149
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.0452318899333477,
+      "learning_rate": 0.00014958052542663727,
+      "loss": 0.2496,
+      "step": 160
+    },
+    {
+      "epoch": 1.2087542087542087,
+      "grad_norm": 0.047174468636512756,
+      "learning_rate": 0.00013650193896645583,
+      "loss": 0.2506,
+      "step": 180
+    },
+    {
+      "epoch": 1.3434343434343434,
+      "grad_norm": 0.05392182618379593,
+      "learning_rate": 0.0001226561011079216,
+      "loss": 0.2498,
+      "step": 200
+    },
+    {
+      "epoch": 1.4781144781144782,
+      "grad_norm": 0.04376411437988281,
+      "learning_rate": 0.0001083340440197117,
+      "loss": 0.2484,
+      "step": 220
+    },
+    {
+      "epoch": 1.612794612794613,
+      "grad_norm": 0.04754996299743652,
+      "learning_rate": 9.383680974614915e-05,
+      "loss": 0.2462,
+      "step": 240
+    },
+    {
+      "epoch": 1.7474747474747474,
+      "grad_norm": 0.03840889409184456,
+      "learning_rate": 7.94691224630883e-05,
+      "loss": 0.2445,
+      "step": 260
+    },
+    {
+      "epoch": 1.8821548821548821,
+      "grad_norm": 0.04592665284872055,
+      "learning_rate": 6.553298333734812e-05,
+      "loss": 0.2455,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.24624043703079224,
+      "eval_runtime": 74.1325,
+      "eval_samples_per_second": 3.561,
+      "eval_steps_per_second": 0.89,
+      "step": 298
+    },
+    {
+      "epoch": 2.0134680134680134,
+      "grad_norm": 0.03834633156657219,
+      "learning_rate": 5.2321322622351254e-05,
+      "loss": 0.2433,
+      "step": 300
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.07271318882703781,
+      "learning_rate": 4.011184241955213e-05,
+      "loss": 0.243,
+      "step": 320
+    },
+    {
+      "epoch": 2.282828282828283,
+      "grad_norm": 0.05636134743690491,
+      "learning_rate": 2.9161179527542827e-05,
+      "loss": 0.2434,
+      "step": 340
+    },
+    {
+      "epoch": 2.4175084175084174,
+      "grad_norm": 0.06415364146232605,
+      "learning_rate": 1.9699511072653733e-05,
+      "loss": 0.245,
+      "step": 360
+    },
+    {
+      "epoch": 2.5521885521885523,
+      "grad_norm": 0.0652865543961525,
+      "learning_rate": 1.192571630783179e-05,
+      "loss": 0.2413,
+      "step": 380
+    },
+    {
+      "epoch": 2.686868686868687,
+      "grad_norm": 0.05853720381855965,
+      "learning_rate": 6.003196276218814e-06,
+      "loss": 0.2419,
+      "step": 400
+    },
+    {
+      "epoch": 2.821548821548822,
+      "grad_norm": 0.05892040953040123,
+      "learning_rate": 2.0564392078839644e-06,
+      "loss": 0.2442,
+      "step": 420
+    },
+    {
+      "epoch": 2.9562289562289563,
+      "grad_norm": 0.07029526680707932,
+      "learning_rate": 1.6840384324980917e-07,
+      "loss": 0.239,
+      "step": 440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.24426761269569397,
+      "eval_runtime": 74.08,
+      "eval_samples_per_second": 3.564,
+      "eval_steps_per_second": 0.891,
+      "step": 447
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 447,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.377851437459702e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-447/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3368fe8425b6a161e11d6c1fbbf66be8646beca69bf81193ad2a1292f8d3c8
+size 5841

metadata.json

@@ -0,0 +1,10 @@
+{
+  "base_model": "mistralai/Mistral-7B-Instruct-v0.3",
+  "dataset": "TesterColab/MIMICDB",
+  "approach": "handles_all_scenarios_no_hallucinations",
+  "scenarios": [
+    "bp_only",
+    "bp_with_context",
+    "speech_variations"
+  ]
+}

runs/Nov07_03-04-15_e648ee70cf1b/events.out.tfevents.1762484659.e648ee70cf1b.2581.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c1f565f446929d171b7af519e489275d86622cca553d7e712f45fa87098e6d
+size 11290

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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3368fe8425b6a161e11d6c1fbbf66be8646beca69bf81193ad2a1292f8d3c8
+size 5841