Upload folder using huggingface_hub

PosthogAgent/data/models/cluster_1_lora/README.md

@@ -0,0 +1,62 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+model_name: cluster_1_lora
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for cluster_1_lora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/amaan784-columbia-university/agentic-world/runs/zu49jn56) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.29.0
+- Transformers: 5.2.0
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

PosthogAgent/data/models/cluster_1_lora/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

PosthogAgent/data/models/cluster_1_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f58ea7575f179d4b49f94e663e849bda8b19a89d645bd3ea019edc1f3ae86f
+size 335604696

PosthogAgent/data/models/cluster_1_lora/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 %}

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/README.md

@@ -0,0 +1,209 @@
+---
+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
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f58ea7575f179d4b49f94e663e849bda8b19a89d645bd3ea019edc1f3ae86f
+size 335604696

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/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 %}

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cab8626a8c13c61bb53a6052febd62ab23055ca3e103dcd8ef486476ae7f550
+size 671473443

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
+size 14645

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d45e8eec5254d8ec807c973096f22e5047dcf3514b729e396607ea934d9479b
+size 1465

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/trainer_state.json

@@ -0,0 +1,269 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.064946526288986,
+      "epoch": 0.2898550724637681,
+      "grad_norm": 6.806929588317871,
+      "learning_rate": 0.0001999348095389677,
+      "loss": 2.2583621978759765,
+      "mean_token_accuracy": 0.6467842936515809,
+      "num_tokens": 159612.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.591124665737152,
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.26109248399734497,
+      "learning_rate": 0.00019766205557100868,
+      "loss": 0.6537456035614013,
+      "mean_token_accuracy": 0.8480004876852035,
+      "num_tokens": 316162.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.40020936280488967,
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.21699745953083038,
+      "learning_rate": 0.00019221427769259333,
+      "loss": 0.43981084823608396,
+      "mean_token_accuracy": 0.8878119915723801,
+      "num_tokens": 473008.0,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.38582224398851395,
+      "eval_loss": 0.35000964999198914,
+      "eval_mean_token_accuracy": 0.8948687613010406,
+      "eval_num_tokens": 541487.0,
+      "eval_runtime": 6.2607,
+      "eval_samples_per_second": 5.111,
+      "eval_steps_per_second": 0.639,
+      "step": 18
+    },
+    {
+      "entropy": 0.3864067231907564,
+      "epoch": 1.1159420289855073,
+      "grad_norm": 0.1347266137599945,
+      "learning_rate": 0.00018376858486299647,
+      "loss": 0.36007487773895264,
+      "mean_token_accuracy": 0.8958466193255257,
+      "num_tokens": 605121.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.3705523297190666,
+      "epoch": 1.4057971014492754,
+      "grad_norm": 0.1416688859462738,
+      "learning_rate": 0.0001725995491923131,
+      "loss": 0.32240240573883056,
+      "mean_token_accuracy": 0.8998520106077195,
+      "num_tokens": 761321.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.332508085668087,
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.09218495339155197,
+      "learning_rate": 0.0001590702795164551,
+      "loss": 0.2923795223236084,
+      "mean_token_accuracy": 0.9062400549650192,
+      "num_tokens": 918753.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.31754949539899824,
+      "epoch": 1.9855072463768115,
+      "grad_norm": 0.0927763357758522,
+      "learning_rate": 0.00014362061661555675,
+      "loss": 0.28774323463439944,
+      "mean_token_accuracy": 0.9054431676864624,
+      "num_tokens": 1077052.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.30885834991931915,
+      "eval_loss": 0.2812090516090393,
+      "eval_mean_token_accuracy": 0.9082985669374466,
+      "eval_num_tokens": 1082974.0,
+      "eval_runtime": 6.2474,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 0.64,
+      "step": 36
+    },
+    {
+      "entropy": 0.3044724481947282,
+      "epoch": 2.2318840579710146,
+      "grad_norm": 0.10141431540250778,
+      "learning_rate": 0.00012675283385292212,
+      "loss": 0.281050968170166,
+      "mean_token_accuracy": 0.9086612252628102,
+      "num_tokens": 1206756.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.3089854046702385,
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.059645846486091614,
+      "learning_rate": 0.00010901530811120655,
+      "loss": 0.2783233165740967,
+      "mean_token_accuracy": 0.9090369939804077,
+      "num_tokens": 1363981.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.29840159714221953,
+      "epoch": 2.8115942028985508,
+      "grad_norm": 0.0479370653629303,
+      "learning_rate": 9.098469188879349e-05,
+      "loss": 0.2722867250442505,
+      "mean_token_accuracy": 0.9118370771408081,
+      "num_tokens": 1523060.0,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.2942015156149864,
+      "eval_loss": 0.27183061838150024,
+      "eval_mean_token_accuracy": 0.9116572588682175,
+      "eval_num_tokens": 1624461.0,
+      "eval_runtime": 6.2548,
+      "eval_samples_per_second": 5.116,
+      "eval_steps_per_second": 0.64,
+      "step": 54
+    },
+    {
+      "entropy": 0.30148569100043354,
+      "epoch": 3.0579710144927534,
+      "grad_norm": 0.06451989710330963,
+      "learning_rate": 7.324716614707793e-05,
+      "loss": 0.27319085597991943,
+      "mean_token_accuracy": 0.9126589298248291,
+      "num_tokens": 1656299.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.2942150741815567,
+      "epoch": 3.3478260869565215,
+      "grad_norm": 0.061239030212163925,
+      "learning_rate": 5.6379383384443255e-05,
+      "loss": 0.2690553665161133,
+      "mean_token_accuracy": 0.9137291342020035,
+      "num_tokens": 1814171.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.29443189650774004,
+      "epoch": 3.63768115942029,
+      "grad_norm": 0.047705043107271194,
+      "learning_rate": 4.092972048354491e-05,
+      "loss": 0.26580204963684084,
+      "mean_token_accuracy": 0.9145404130220414,
+      "num_tokens": 1971361.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.29738335460424425,
+      "epoch": 3.927536231884058,
+      "grad_norm": 0.04782764986157417,
+      "learning_rate": 2.7400450807686938e-05,
+      "loss": 0.2684621810913086,
+      "mean_token_accuracy": 0.9125285893678665,
+      "num_tokens": 2128123.0,
+      "step": 70
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.2937370389699936,
+      "eval_loss": 0.26698678731918335,
+      "eval_mean_token_accuracy": 0.9135445058345795,
+      "eval_num_tokens": 2165948.0,
+      "eval_runtime": 6.2513,
+      "eval_samples_per_second": 5.119,
+      "eval_steps_per_second": 0.64,
+      "step": 72
+    },
+    {
+      "entropy": 0.29317329210393567,
+      "epoch": 4.173913043478261,
+      "grad_norm": 0.04594368860125542,
+      "learning_rate": 1.6231415137003537e-05,
+      "loss": 0.2640077114105225,
+      "mean_token_accuracy": 0.9161312650231754,
+      "num_tokens": 2261057.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.2909219741821289,
+      "epoch": 4.463768115942029,
+      "grad_norm": 0.05090672895312309,
+      "learning_rate": 7.785722307406684e-06,
+      "loss": 0.25984725952148435,
+      "mean_token_accuracy": 0.9169878989458085,
+      "num_tokens": 2416224.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.2909898474812508,
+      "epoch": 4.753623188405797,
+      "grad_norm": 0.043142933398485184,
+      "learning_rate": 2.3379444289913342e-06,
+      "loss": 0.2622442483901978,
+      "mean_token_accuracy": 0.915747606754303,
+      "num_tokens": 2573802.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.29236104383188133,
+      "epoch": 5.0,
+      "grad_norm": 0.10205884277820587,
+      "learning_rate": 6.519046103230508e-08,
+      "loss": 0.2647502899169922,
+      "mean_token_accuracy": 0.9155822536524605,
+      "num_tokens": 2707435.0,
+      "step": 90
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.2886781841516495,
+      "eval_loss": 0.26640117168426514,
+      "eval_mean_token_accuracy": 0.9140467047691345,
+      "eval_num_tokens": 2707435.0,
+      "eval_runtime": 6.2483,
+      "eval_samples_per_second": 5.121,
+      "eval_steps_per_second": 0.64,
+      "step": 90
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.1692369788063744e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

PosthogAgent/data/models/cluster_1_lora/checkpoint-90/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67446de8c6fa0c01efc704b90c7c150d72fc88ee8a7b5e70e5793ef9f8343a44
+size 5713

PosthogAgent/data/models/cluster_1_lora/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

PosthogAgent/data/models/cluster_1_lora/training_config.json

@@ -0,0 +1,16 @@
+{
+  "cluster_id": 1,
+  "cluster_label": "Erratic Scanner",
+  "base_model": "mistralai/Mistral-7B-Instruct-v0.3",
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "epochs": 5,
+  "learning_rate": 0.0002,
+  "max_seq_length": 2048,
+  "train_examples": 2530,
+  "eval_examples": 281,
+  "final_train_loss": 0.42075220346450803,
+  "final_eval_loss": 0.26640117168426514,
+  "training_time_s": 843.5332,
+  "peak_vram_gb": 21.396484375
+}