Upload folder using huggingface_hub

PosthogAgent/data/models/cluster_4_lora/README.md

@@ -0,0 +1,62 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+model_name: cluster_4_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_4_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/t28gd2rh) 
+
+
+
+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_4_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_4_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf3a5c0a525e0196c651ad5ca7b81da52014fdb10038c9149f4b69ae6df01b2
+size 335604696

PosthogAgent/data/models/cluster_4_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_4_lora/checkpoint-80/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_4_lora/checkpoint-80/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_4_lora/checkpoint-80/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf3a5c0a525e0196c651ad5ca7b81da52014fdb10038c9149f4b69ae6df01b2
+size 335604696

PosthogAgent/data/models/cluster_4_lora/checkpoint-80/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_4_lora/checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e197473de16c709df75049740de74345b1d30d0e98931c4f5452d998a719f1c3
+size 671473443

PosthogAgent/data/models/cluster_4_lora/checkpoint-80/rng_state.pth

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

PosthogAgent/data/models/cluster_4_lora/checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dbdcca905df2f0e74b2ad83541fe6a37338e2881c1fe172f497aa2a15e10e0
+size 1465

PosthogAgent/data/models/cluster_4_lora/checkpoint-80/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_4_lora/checkpoint-80/trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7766035854816438,
+      "epoch": 0.32786885245901637,
+      "grad_norm": 1.322622537612915,
+      "learning_rate": 0.0001999167799344583,
+      "loss": 2.1723480224609375,
+      "mean_token_accuracy": 0.6495136320590973,
+      "num_tokens": 156809.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.5035030573606492,
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.4139934480190277,
+      "learning_rate": 0.00019701859555740648,
+      "loss": 0.6139614582061768,
+      "mean_token_accuracy": 0.8582220941781997,
+      "num_tokens": 315567.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.3903247848153114,
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.2083745002746582,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.4243932247161865,
+      "mean_token_accuracy": 0.886150187253952,
+      "num_tokens": 472576.0,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.39378221333026886,
+      "eval_loss": 0.3632703125476837,
+      "eval_mean_token_accuracy": 0.8932265043258667,
+      "eval_num_tokens": 480447.0,
+      "eval_runtime": 5.4551,
+      "eval_samples_per_second": 5.133,
+      "eval_steps_per_second": 0.733,
+      "step": 16
+    },
+    {
+      "entropy": 0.37801142124568715,
+      "epoch": 1.2622950819672132,
+      "grad_norm": 0.2397739291191101,
+      "learning_rate": 0.00017943870854121124,
+      "loss": 0.33922953605651857,
+      "mean_token_accuracy": 0.8979756306199467,
+      "num_tokens": 606097.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.3542923450469971,
+      "epoch": 1.5901639344262295,
+      "grad_norm": 0.08599701523780823,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 0.30669074058532714,
+      "mean_token_accuracy": 0.9001015365123749,
+      "num_tokens": 764510.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.3217175990343094,
+      "epoch": 1.918032786885246,
+      "grad_norm": 0.15060853958129883,
+      "learning_rate": 0.00014881762060482814,
+      "loss": 0.2907231330871582,
+      "mean_token_accuracy": 0.9052947193384171,
+      "num_tokens": 921203.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.3057623505592346,
+      "eval_loss": 0.29002833366394043,
+      "eval_mean_token_accuracy": 0.9054941236972809,
+      "eval_num_tokens": 960894.0,
+      "eval_runtime": 5.4477,
+      "eval_samples_per_second": 5.14,
+      "eval_steps_per_second": 0.734,
+      "step": 32
+    },
+    {
+      "entropy": 0.313673057976891,
+      "epoch": 2.19672131147541,
+      "grad_norm": 0.07013852149248123,
+      "learning_rate": 0.00013012461895372344,
+      "loss": 0.28833565711975095,
+      "mean_token_accuracy": 0.9055628741488737,
+      "num_tokens": 1054793.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.3152000218629837,
+      "epoch": 2.5245901639344264,
+      "grad_norm": 0.08587533980607986,
+      "learning_rate": 0.00011018229867038356,
+      "loss": 0.28152592182159425,
+      "mean_token_accuracy": 0.9077274888753891,
+      "num_tokens": 1211666.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.3069989323616028,
+      "epoch": 2.8524590163934427,
+      "grad_norm": 0.06514450907707214,
+      "learning_rate": 8.981770132961649e-05,
+      "loss": 0.27893388271331787,
+      "mean_token_accuracy": 0.9078875064849854,
+      "num_tokens": 1370340.0,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.3075047582387924,
+      "eval_loss": 0.280129611492157,
+      "eval_mean_token_accuracy": 0.9091705679893494,
+      "eval_num_tokens": 1441341.0,
+      "eval_runtime": 5.4661,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 0.732,
+      "step": 48
+    },
+    {
+      "entropy": 0.30845817047006946,
+      "epoch": 3.1311475409836067,
+      "grad_norm": 0.0474301241338253,
+      "learning_rate": 6.98753810462766e-05,
+      "loss": 0.2744888782501221,
+      "mean_token_accuracy": 0.9111700759214514,
+      "num_tokens": 1504572.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.3010768458247185,
+      "epoch": 3.459016393442623,
+      "grad_norm": 0.06403849273920059,
+      "learning_rate": 5.11823793951719e-05,
+      "loss": 0.27157161235809324,
+      "mean_token_accuracy": 0.9112865447998046,
+      "num_tokens": 1663086.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.3048749387264252,
+      "epoch": 3.7868852459016393,
+      "grad_norm": 0.04909079521894455,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 0.26854648590087893,
+      "mean_token_accuracy": 0.9133919924497604,
+      "num_tokens": 1819756.0,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.30168789625167847,
+      "eval_loss": 0.2749921977519989,
+      "eval_mean_token_accuracy": 0.9105888903141022,
+      "eval_num_tokens": 1921788.0,
+      "eval_runtime": 5.458,
+      "eval_samples_per_second": 5.13,
+      "eval_steps_per_second": 0.733,
+      "step": 64
+    },
+    {
+      "entropy": 0.3054194853586309,
+      "epoch": 4.065573770491803,
+      "grad_norm": 0.04912532866001129,
+      "learning_rate": 2.0561291458788733e-05,
+      "loss": 0.2750155210494995,
+      "mean_token_accuracy": 0.9104112351641935,
+      "num_tokens": 1953550.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.29584493339061735,
+      "epoch": 4.39344262295082,
+      "grad_norm": 0.048964228481054306,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.26197812557220457,
+      "mean_token_accuracy": 0.9149673879146576,
+      "num_tokens": 2111128.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.3004043325781822,
+      "epoch": 4.721311475409836,
+      "grad_norm": 0.05222048610448837,
+      "learning_rate": 2.9814044425935606e-06,
+      "loss": 0.26506354808807375,
+      "mean_token_accuracy": 0.913662177324295,
+      "num_tokens": 2268981.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.3026038355687085,
+      "epoch": 5.0,
+      "grad_norm": 0.08464942872524261,
+      "learning_rate": 8.322006554171146e-08,
+      "loss": 0.26692264080047606,
+      "mean_token_accuracy": 0.913486056468066,
+      "num_tokens": 2402235.0,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.3023405745625496,
+      "eval_loss": 0.2741330862045288,
+      "eval_mean_token_accuracy": 0.9107176065444946,
+      "eval_num_tokens": 2402235.0,
+      "eval_runtime": 5.4573,
+      "eval_samples_per_second": 5.131,
+      "eval_steps_per_second": 0.733,
+      "step": 80
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 80,
+  "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": 1.0374328446603264e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

PosthogAgent/data/models/cluster_4_lora/checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e938f3bdd5c2f3f0abb8b0d6320e2ccd1ca48f266ff3c89bdb85adb4f651fc
+size 5713

PosthogAgent/data/models/cluster_4_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_4_lora/training_config.json

@@ -0,0 +1,16 @@
+{
+  "cluster_id": 4,
+  "cluster_label": "Frustrated Clicker",
+  "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": 2253,
+  "eval_examples": 250,
+  "final_train_loss": 0.42998302429914476,
+  "final_eval_loss": 0.2741330862045288,
+  "training_time_s": 747.9265,
+  "peak_vram_gb": 21.513671875
+}