RemasterPhantom v3.1 — LoRA adapter

lora_adapter/README.md

@@ -0,0 +1,62 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+model_name: remasterphantom-v3-lora
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for remasterphantom-v3-lora
+
+This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct).
+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
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.21.0
+- TRL: 1.13.0
+- Transformers: 5.17.0
+- Pytorch: 2.14.0
+- Datasets: 5.0.1
+- Tokenizers: 0.23.2
+
+## 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}
+}
+```

lora_adapter/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

lora_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d1ddd1ca763194d58b9e5cf9e6f532bd715ad8726df701929745cb6a4311f5
+size 45118424

lora_adapter/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

lora_adapter/checkpoint-150/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- 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 0.21.0

lora_adapter/checkpoint-150/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

lora_adapter/checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071c83a50e0222dc3957633847e8133b8c0a407aa8d2a6e63bd941086afd2d53
+size 45118424

lora_adapter/checkpoint-150/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

lora_adapter/checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bc3f5bbd4a3bb400b79c762ec5c07ee8e7482c5ced7070badadea5546b82b6
+size 90359883

lora_adapter/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
+size 14455

lora_adapter/checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dc73bf06f1c582f0b5527719877be2fa3bfa198848a85bce18940b7bd712cf
+size 1465

lora_adapter/checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

lora_adapter/checkpoint-150/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

lora_adapter/checkpoint-150/trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6511123168746609,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.268431743979454,
+      "epoch": 0.04340748779164406,
+      "grad_norm": 5.425721168518066,
+      "learning_rate": 3e-05,
+      "loss": 4.763444137573242,
+      "mean_token_accuracy": 0.37437669970095155,
+      "num_tokens": 15851.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.6355564504861833,
+      "epoch": 0.08681497558328811,
+      "grad_norm": 2.6653194427490234,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 3.661287307739258,
+      "mean_token_accuracy": 0.4522986955940723,
+      "num_tokens": 31565.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.110316979885101,
+      "epoch": 0.13022246337493218,
+      "grad_norm": 1.8292694091796875,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.4040077209472654,
+      "mean_token_accuracy": 0.6126278236508369,
+      "num_tokens": 47681.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.947795458137989,
+      "epoch": 0.17362995116657623,
+      "grad_norm": 1.7558073997497559,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.4649612426757812,
+      "mean_token_accuracy": 0.7671711064875126,
+      "num_tokens": 63639.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2642615631222724,
+      "epoch": 0.21703743895822028,
+      "grad_norm": 1.8000116348266602,
+      "learning_rate": 0.00016333333333333334,
+      "loss": 0.9385161399841309,
+      "mean_token_accuracy": 0.8446647509932518,
+      "num_tokens": 79224.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9772241789847612,
+      "epoch": 0.26044492674986436,
+      "grad_norm": 1.5789580345153809,
+      "learning_rate": 0.00019666666666666666,
+      "loss": 0.6508745193481446,
+      "mean_token_accuracy": 0.8930118441581726,
+      "num_tokens": 94825.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7386516474187375,
+      "epoch": 0.3038524145415084,
+      "grad_norm": 1.118341088294983,
+      "learning_rate": 0.0001999002586734068,
+      "loss": 0.5544538021087646,
+      "mean_token_accuracy": 0.9125440023839474,
+      "num_tokens": 110902.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4801172070205212,
+      "epoch": 0.34725990233315246,
+      "grad_norm": 1.0871493816375732,
+      "learning_rate": 0.00019955572927610798,
+      "loss": 0.32133638858795166,
+      "mean_token_accuracy": 0.9453130982816219,
+      "num_tokens": 126758.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4470752142369747,
+      "epoch": 0.3906673901247965,
+      "grad_norm": 0.9949904084205627,
+      "learning_rate": 0.00019896602868774615,
+      "loss": 0.33235070705413816,
+      "mean_token_accuracy": 0.9432531543076038,
+      "num_tokens": 142247.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.43914212100207806,
+      "epoch": 0.43407487791644056,
+      "grad_norm": 1.2417030334472656,
+      "learning_rate": 0.00019813260913610048,
+      "loss": 0.32300994396209715,
+      "mean_token_accuracy": 0.9425150409340859,
+      "num_tokens": 158033.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.38672009818255904,
+      "epoch": 0.47748236570808467,
+      "grad_norm": 1.4303337335586548,
+      "learning_rate": 0.00019705752304412648,
+      "loss": 0.3090308904647827,
+      "mean_token_accuracy": 0.9426406390964985,
+      "num_tokens": 173972.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.2582590217702091,
+      "epoch": 0.5208898534997287,
+      "grad_norm": 0.7586016654968262,
+      "learning_rate": 0.00019574341797555143,
+      "loss": 0.16584413051605223,
+      "mean_token_accuracy": 0.9635460428893566,
+      "num_tokens": 189557.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.29735598172992467,
+      "epoch": 0.5642973412913728,
+      "grad_norm": 1.3573423624038696,
+      "learning_rate": 0.00019419353011484387,
+      "loss": 0.23453230857849122,
+      "mean_token_accuracy": 0.9539774417877197,
+      "num_tokens": 205568.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3157164487987757,
+      "epoch": 0.6077048290830168,
+      "grad_norm": 0.7886211276054382,
+      "learning_rate": 0.00019241167629761527,
+      "loss": 0.24561758041381837,
+      "mean_token_accuracy": 0.951296404749155,
+      "num_tokens": 221240.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.41249370062723756,
+      "epoch": 0.6511123168746609,
+      "grad_norm": 0.6835598945617676,
+      "learning_rate": 0.00019040224461107917,
+      "loss": 0.3280463695526123,
+      "mean_token_accuracy": 0.9425421200692654,
+      "num_tokens": 236889.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 693,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1399187205697536.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora_adapter/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f02029ae097ac6a5686a868c70c7fb13e1a18c4978ab722ce3a1759ddbc101a
+size 5713

lora_adapter/checkpoint-300/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- 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 0.21.0

lora_adapter/checkpoint-300/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

lora_adapter/checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6259c71820f0a9cf28059bd0a7f50ba4c7d775c5508099710f54c95a16f99f
+size 45118424

lora_adapter/checkpoint-300/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

lora_adapter/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b864b170703c7ff3bd4b166bc4c2496dcc068f47b21b661c0650ebbe93b358de
+size 90359883

lora_adapter/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455

lora_adapter/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25fcf670f053f7304b15a0d03a8d7d981c4f3341ba3098848093cb91bc25fd70
+size 1465

lora_adapter/checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

lora_adapter/checkpoint-300/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

lora_adapter/checkpoint-300/trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.299511665762344,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.268431743979454,
+      "epoch": 0.04340748779164406,
+      "grad_norm": 5.425721168518066,
+      "learning_rate": 3e-05,
+      "loss": 4.763444137573242,
+      "mean_token_accuracy": 0.37437669970095155,
+      "num_tokens": 15851.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.6355564504861833,
+      "epoch": 0.08681497558328811,
+      "grad_norm": 2.6653194427490234,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 3.661287307739258,
+      "mean_token_accuracy": 0.4522986955940723,
+      "num_tokens": 31565.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.110316979885101,
+      "epoch": 0.13022246337493218,
+      "grad_norm": 1.8292694091796875,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.4040077209472654,
+      "mean_token_accuracy": 0.6126278236508369,
+      "num_tokens": 47681.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.947795458137989,
+      "epoch": 0.17362995116657623,
+      "grad_norm": 1.7558073997497559,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.4649612426757812,
+      "mean_token_accuracy": 0.7671711064875126,
+      "num_tokens": 63639.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2642615631222724,
+      "epoch": 0.21703743895822028,
+      "grad_norm": 1.8000116348266602,
+      "learning_rate": 0.00016333333333333334,
+      "loss": 0.9385161399841309,
+      "mean_token_accuracy": 0.8446647509932518,
+      "num_tokens": 79224.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9772241789847612,
+      "epoch": 0.26044492674986436,
+      "grad_norm": 1.5789580345153809,
+      "learning_rate": 0.00019666666666666666,
+      "loss": 0.6508745193481446,
+      "mean_token_accuracy": 0.8930118441581726,
+      "num_tokens": 94825.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7386516474187375,
+      "epoch": 0.3038524145415084,
+      "grad_norm": 1.118341088294983,
+      "learning_rate": 0.0001999002586734068,
+      "loss": 0.5544538021087646,
+      "mean_token_accuracy": 0.9125440023839474,
+      "num_tokens": 110902.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4801172070205212,
+      "epoch": 0.34725990233315246,
+      "grad_norm": 1.0871493816375732,
+      "learning_rate": 0.00019955572927610798,
+      "loss": 0.32133638858795166,
+      "mean_token_accuracy": 0.9453130982816219,
+      "num_tokens": 126758.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4470752142369747,
+      "epoch": 0.3906673901247965,
+      "grad_norm": 0.9949904084205627,
+      "learning_rate": 0.00019896602868774615,
+      "loss": 0.33235070705413816,
+      "mean_token_accuracy": 0.9432531543076038,
+      "num_tokens": 142247.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.43914212100207806,
+      "epoch": 0.43407487791644056,
+      "grad_norm": 1.2417030334472656,
+      "learning_rate": 0.00019813260913610048,
+      "loss": 0.32300994396209715,
+      "mean_token_accuracy": 0.9425150409340859,
+      "num_tokens": 158033.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.38672009818255904,
+      "epoch": 0.47748236570808467,
+      "grad_norm": 1.4303337335586548,
+      "learning_rate": 0.00019705752304412648,
+      "loss": 0.3090308904647827,
+      "mean_token_accuracy": 0.9426406390964985,
+      "num_tokens": 173972.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.2582590217702091,
+      "epoch": 0.5208898534997287,
+      "grad_norm": 0.7586016654968262,
+      "learning_rate": 0.00019574341797555143,
+      "loss": 0.16584413051605223,
+      "mean_token_accuracy": 0.9635460428893566,
+      "num_tokens": 189557.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.29735598172992467,
+      "epoch": 0.5642973412913728,
+      "grad_norm": 1.3573423624038696,
+      "learning_rate": 0.00019419353011484387,
+      "loss": 0.23453230857849122,
+      "mean_token_accuracy": 0.9539774417877197,
+      "num_tokens": 205568.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3157164487987757,
+      "epoch": 0.6077048290830168,
+      "grad_norm": 0.7886211276054382,
+      "learning_rate": 0.00019241167629761527,
+      "loss": 0.24561758041381837,
+      "mean_token_accuracy": 0.951296404749155,
+      "num_tokens": 221240.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.41249370062723756,
+      "epoch": 0.6511123168746609,
+      "grad_norm": 0.6835598945617676,
+      "learning_rate": 0.00019040224461107917,
+      "loss": 0.3280463695526123,
+      "mean_token_accuracy": 0.9425421200692654,
+      "num_tokens": 236889.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.25797676630318167,
+      "epoch": 0.6945198046663049,
+      "grad_norm": 0.5169897675514221,
+      "learning_rate": 0.0001881701835877161,
+      "loss": 0.17580994367599487,
+      "mean_token_accuracy": 0.9615871131420135,
+      "num_tokens": 252552.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.3551043555140495,
+      "epoch": 0.737927292457949,
+      "grad_norm": 0.9616410136222839,
+      "learning_rate": 0.0001857209900187565,
+      "loss": 0.3012498140335083,
+      "mean_token_accuracy": 0.9450895473361015,
+      "num_tokens": 268798.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.3095861619338393,
+      "epoch": 0.781334780249593,
+      "grad_norm": 1.0524218082427979,
+      "learning_rate": 0.00018306069541749258,
+      "loss": 0.21495308876037597,
+      "mean_token_accuracy": 0.95635409578681,
+      "num_tokens": 284560.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.3253756103105843,
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.44378986954689026,
+      "learning_rate": 0.00018019585116575555,
+      "loss": 0.27938573360443114,
+      "mean_token_accuracy": 0.9474706895649433,
+      "num_tokens": 300840.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.2480218150652945,
+      "epoch": 0.8681497558328811,
+      "grad_norm": 0.376433789730072,
+      "learning_rate": 0.000177133512380137,
+      "loss": 0.18635139465332032,
+      "mean_token_accuracy": 0.9606560796499253,
+      "num_tokens": 316455.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.26516002183780074,
+      "epoch": 0.9115572436245253,
+      "grad_norm": 0.447360634803772,
+      "learning_rate": 0.00017388122053768674,
+      "loss": 0.20903537273406983,
+      "mean_token_accuracy": 0.9590088307857514,
+      "num_tokens": 332359.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.22508152723312377,
+      "epoch": 0.9549647314161693,
+      "grad_norm": 0.39458373188972473,
+      "learning_rate": 0.0001704469849038734,
+      "loss": 0.17320446968078612,
+      "mean_token_accuracy": 0.9621456168591976,
+      "num_tokens": 348219.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.1884014437906444,
+      "epoch": 0.9983722192078134,
+      "grad_norm": 0.5577853918075562,
+      "learning_rate": 0.00016683926280854484,
+      "loss": 0.14232510328292847,
+      "mean_token_accuracy": 0.967728354781866,
+      "num_tokens": 363802.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.2500555583713006,
+      "eval_loss": 0.2172880917787552,
+      "eval_mean_token_accuracy": 0.9547121439661298,
+      "eval_num_tokens": 364353.0,
+      "eval_runtime": 43.3662,
+      "eval_samples_per_second": 2.26,
+      "eval_steps_per_second": 2.26,
+      "step": 231
+    },
+    {
+      "entropy": 0.26626345694065096,
+      "epoch": 1.0390667390124797,
+      "grad_norm": 0.36867332458496094,
+      "learning_rate": 0.00016306693881846152,
+      "loss": 0.23021941184997557,
+      "mean_token_accuracy": 0.9587587014834086,
+      "num_tokens": 378571.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.1791029059328139,
+      "epoch": 1.0824742268041236,
+      "grad_norm": 0.5592738389968872,
+      "learning_rate": 0.00015913930285769355,
+      "loss": 0.1204079270362854,
+      "mean_token_accuracy": 0.970609325170517,
+      "num_tokens": 394252.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.25584981925785544,
+      "epoch": 1.1258817145957678,
+      "grad_norm": 0.6882627606391907,
+      "learning_rate": 0.00015506602732976373,
+      "loss": 0.182321298122406,
+      "mean_token_accuracy": 0.9607684284448623,
+      "num_tokens": 410118.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.15852767862379552,
+      "epoch": 1.1692892023874117,
+      "grad_norm": 0.47175613045692444,
+      "learning_rate": 0.00015085714329787631,
+      "loss": 0.10519710779190064,
+      "mean_token_accuracy": 0.9718552604317665,
+      "num_tokens": 425967.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.224250613944605,
+      "epoch": 1.212696690179056,
+      "grad_norm": 0.8211113214492798,
+      "learning_rate": 0.0001465230157818914,
+      "loss": 0.1746065378189087,
+      "mean_token_accuracy": 0.9628558784723282,
+      "num_tokens": 441911.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.2187170408666134,
+      "epoch": 1.2561041779707,
+      "grad_norm": 1.2185333967208862,
+      "learning_rate": 0.00014207431823288057,
+      "loss": 0.16913924217224122,
+      "mean_token_accuracy": 0.9632994569838047,
+      "num_tokens": 457767.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.15246864631772042,
+      "epoch": 1.299511665762344,
+      "grad_norm": 0.8135276436805725,
+      "learning_rate": 0.00013752200624812282,
+      "loss": 0.10427193641662598,
+      "mean_token_accuracy": 0.9733581781387329,
+      "num_tokens": 473550.0,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 693,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2797027727155200.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora_adapter/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f02029ae097ac6a5686a868c70c7fb13e1a18c4978ab722ce3a1759ddbc101a
+size 5713

lora_adapter/checkpoint-450/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- 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 0.21.0

lora_adapter/checkpoint-450/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

lora_adapter/checkpoint-450/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49595f0e80d22178cee488cf5349a8a1ec2790ce506b4fcdc0c4fe66171f1c2a
+size 45118424

lora_adapter/checkpoint-450/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

lora_adapter/checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f11166fb230a2e8a81ba006b0a02c724de952fc855a31e884c52116d990c841
+size 90359883

lora_adapter/checkpoint-450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
+size 14455

lora_adapter/checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fc4c2aaf7d4a9f5a5ee70f8183d7f3147b251b143c2dabd876ad9f138a08b4
+size 1465

lora_adapter/checkpoint-450/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

lora_adapter/checkpoint-450/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

lora_adapter/checkpoint-450/trainer_state.json

@@ -0,0 +1,495 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9506239826370049,
+  "eval_steps": 500,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.268431743979454,
+      "epoch": 0.04340748779164406,
+      "grad_norm": 5.425721168518066,
+      "learning_rate": 3e-05,
+      "loss": 4.763444137573242,
+      "mean_token_accuracy": 0.37437669970095155,
+      "num_tokens": 15851.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.6355564504861833,
+      "epoch": 0.08681497558328811,
+      "grad_norm": 2.6653194427490234,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 3.661287307739258,
+      "mean_token_accuracy": 0.4522986955940723,
+      "num_tokens": 31565.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.110316979885101,
+      "epoch": 0.13022246337493218,
+      "grad_norm": 1.8292694091796875,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.4040077209472654,
+      "mean_token_accuracy": 0.6126278236508369,
+      "num_tokens": 47681.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.947795458137989,
+      "epoch": 0.17362995116657623,
+      "grad_norm": 1.7558073997497559,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.4649612426757812,
+      "mean_token_accuracy": 0.7671711064875126,
+      "num_tokens": 63639.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2642615631222724,
+      "epoch": 0.21703743895822028,
+      "grad_norm": 1.8000116348266602,
+      "learning_rate": 0.00016333333333333334,
+      "loss": 0.9385161399841309,
+      "mean_token_accuracy": 0.8446647509932518,
+      "num_tokens": 79224.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9772241789847612,
+      "epoch": 0.26044492674986436,
+      "grad_norm": 1.5789580345153809,
+      "learning_rate": 0.00019666666666666666,
+      "loss": 0.6508745193481446,
+      "mean_token_accuracy": 0.8930118441581726,
+      "num_tokens": 94825.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7386516474187375,
+      "epoch": 0.3038524145415084,
+      "grad_norm": 1.118341088294983,
+      "learning_rate": 0.0001999002586734068,
+      "loss": 0.5544538021087646,
+      "mean_token_accuracy": 0.9125440023839474,
+      "num_tokens": 110902.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4801172070205212,
+      "epoch": 0.34725990233315246,
+      "grad_norm": 1.0871493816375732,
+      "learning_rate": 0.00019955572927610798,
+      "loss": 0.32133638858795166,
+      "mean_token_accuracy": 0.9453130982816219,
+      "num_tokens": 126758.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4470752142369747,
+      "epoch": 0.3906673901247965,
+      "grad_norm": 0.9949904084205627,
+      "learning_rate": 0.00019896602868774615,
+      "loss": 0.33235070705413816,
+      "mean_token_accuracy": 0.9432531543076038,
+      "num_tokens": 142247.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.43914212100207806,
+      "epoch": 0.43407487791644056,
+      "grad_norm": 1.2417030334472656,
+      "learning_rate": 0.00019813260913610048,
+      "loss": 0.32300994396209715,
+      "mean_token_accuracy": 0.9425150409340859,
+      "num_tokens": 158033.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.38672009818255904,
+      "epoch": 0.47748236570808467,
+      "grad_norm": 1.4303337335586548,
+      "learning_rate": 0.00019705752304412648,
+      "loss": 0.3090308904647827,
+      "mean_token_accuracy": 0.9426406390964985,
+      "num_tokens": 173972.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.2582590217702091,
+      "epoch": 0.5208898534997287,
+      "grad_norm": 0.7586016654968262,
+      "learning_rate": 0.00019574341797555143,
+      "loss": 0.16584413051605223,
+      "mean_token_accuracy": 0.9635460428893566,
+      "num_tokens": 189557.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.29735598172992467,
+      "epoch": 0.5642973412913728,
+      "grad_norm": 1.3573423624038696,
+      "learning_rate": 0.00019419353011484387,
+      "loss": 0.23453230857849122,
+      "mean_token_accuracy": 0.9539774417877197,
+      "num_tokens": 205568.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3157164487987757,
+      "epoch": 0.6077048290830168,
+      "grad_norm": 0.7886211276054382,
+      "learning_rate": 0.00019241167629761527,
+      "loss": 0.24561758041381837,
+      "mean_token_accuracy": 0.951296404749155,
+      "num_tokens": 221240.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.41249370062723756,
+      "epoch": 0.6511123168746609,
+      "grad_norm": 0.6835598945617676,
+      "learning_rate": 0.00019040224461107917,
+      "loss": 0.3280463695526123,
+      "mean_token_accuracy": 0.9425421200692654,
+      "num_tokens": 236889.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.25797676630318167,
+      "epoch": 0.6945198046663049,
+      "grad_norm": 0.5169897675514221,
+      "learning_rate": 0.0001881701835877161,
+      "loss": 0.17580994367599487,
+      "mean_token_accuracy": 0.9615871131420135,
+      "num_tokens": 252552.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.3551043555140495,
+      "epoch": 0.737927292457949,
+      "grad_norm": 0.9616410136222839,
+      "learning_rate": 0.0001857209900187565,
+      "loss": 0.3012498140335083,
+      "mean_token_accuracy": 0.9450895473361015,
+      "num_tokens": 268798.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.3095861619338393,
+      "epoch": 0.781334780249593,
+      "grad_norm": 1.0524218082427979,
+      "learning_rate": 0.00018306069541749258,
+      "loss": 0.21495308876037597,
+      "mean_token_accuracy": 0.95635409578681,
+      "num_tokens": 284560.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.3253756103105843,
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.44378986954689026,
+      "learning_rate": 0.00018019585116575555,
+      "loss": 0.27938573360443114,
+      "mean_token_accuracy": 0.9474706895649433,
+      "num_tokens": 300840.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.2480218150652945,
+      "epoch": 0.8681497558328811,
+      "grad_norm": 0.376433789730072,
+      "learning_rate": 0.000177133512380137,
+      "loss": 0.18635139465332032,
+      "mean_token_accuracy": 0.9606560796499253,
+      "num_tokens": 316455.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.26516002183780074,
+      "epoch": 0.9115572436245253,
+      "grad_norm": 0.447360634803772,
+      "learning_rate": 0.00017388122053768674,
+      "loss": 0.20903537273406983,
+      "mean_token_accuracy": 0.9590088307857514,
+      "num_tokens": 332359.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.22508152723312377,
+      "epoch": 0.9549647314161693,
+      "grad_norm": 0.39458373188972473,
+      "learning_rate": 0.0001704469849038734,
+      "loss": 0.17320446968078612,
+      "mean_token_accuracy": 0.9621456168591976,
+      "num_tokens": 348219.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.1884014437906444,
+      "epoch": 0.9983722192078134,
+      "grad_norm": 0.5577853918075562,
+      "learning_rate": 0.00016683926280854484,
+      "loss": 0.14232510328292847,
+      "mean_token_accuracy": 0.967728354781866,
+      "num_tokens": 363802.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.2500555583713006,
+      "eval_loss": 0.2172880917787552,
+      "eval_mean_token_accuracy": 0.9547121439661298,
+      "eval_num_tokens": 364353.0,
+      "eval_runtime": 43.3662,
+      "eval_samples_per_second": 2.26,
+      "eval_steps_per_second": 2.26,
+      "step": 231
+    },
+    {
+      "entropy": 0.26626345694065096,
+      "epoch": 1.0390667390124797,
+      "grad_norm": 0.36867332458496094,
+      "learning_rate": 0.00016306693881846152,
+      "loss": 0.23021941184997557,
+      "mean_token_accuracy": 0.9587587014834086,
+      "num_tokens": 378571.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.1791029059328139,
+      "epoch": 1.0824742268041236,
+      "grad_norm": 0.5592738389968872,
+      "learning_rate": 0.00015913930285769355,
+      "loss": 0.1204079270362854,
+      "mean_token_accuracy": 0.970609325170517,
+      "num_tokens": 394252.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.25584981925785544,
+      "epoch": 1.1258817145957678,
+      "grad_norm": 0.6882627606391907,
+      "learning_rate": 0.00015506602732976373,
+      "loss": 0.182321298122406,
+      "mean_token_accuracy": 0.9607684284448623,
+      "num_tokens": 410118.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.15852767862379552,
+      "epoch": 1.1692892023874117,
+      "grad_norm": 0.47175613045692444,
+      "learning_rate": 0.00015085714329787631,
+      "loss": 0.10519710779190064,
+      "mean_token_accuracy": 0.9718552604317665,
+      "num_tokens": 425967.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.224250613944605,
+      "epoch": 1.212696690179056,
+      "grad_norm": 0.8211113214492798,
+      "learning_rate": 0.0001465230157818914,
+      "loss": 0.1746065378189087,
+      "mean_token_accuracy": 0.9628558784723282,
+      "num_tokens": 441911.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.2187170408666134,
+      "epoch": 1.2561041779707,
+      "grad_norm": 1.2185333967208862,
+      "learning_rate": 0.00014207431823288057,
+      "loss": 0.16913924217224122,
+      "mean_token_accuracy": 0.9632994569838047,
+      "num_tokens": 457767.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.15246864631772042,
+      "epoch": 1.299511665762344,
+      "grad_norm": 0.8135276436805725,
+      "learning_rate": 0.00013752200624812282,
+      "loss": 0.10427193641662598,
+      "mean_token_accuracy": 0.9733581781387329,
+      "num_tokens": 473550.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.14296606807038187,
+      "epoch": 1.342919153553988,
+      "grad_norm": 0.4611963927745819,
+      "learning_rate": 0.00013287729059127288,
+      "loss": 0.11364473104476928,
+      "mean_token_accuracy": 0.9724942341446876,
+      "num_tokens": 489513.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.18273791116662325,
+      "epoch": 1.386326641345632,
+      "grad_norm": 0.600029468536377,
+      "learning_rate": 0.00012815160958414332,
+      "loss": 0.14306700229644775,
+      "mean_token_accuracy": 0.9665566079318524,
+      "num_tokens": 505197.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.12391844158992171,
+      "epoch": 1.4297341291372763,
+      "grad_norm": 0.35350969433784485,
+      "learning_rate": 0.0001233566009380896,
+      "loss": 0.08826681971549988,
+      "mean_token_accuracy": 0.9754320561885834,
+      "num_tokens": 520666.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.14481371184810996,
+      "epoch": 1.4731416169289202,
+      "grad_norm": 0.6141801476478577,
+      "learning_rate": 0.0001185040730943683,
+      "loss": 0.11338310241699219,
+      "mean_token_accuracy": 0.9735137969255447,
+      "num_tokens": 536352.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.18556677168235183,
+      "epoch": 1.5165491047205641,
+      "grad_norm": 0.8235384225845337,
+      "learning_rate": 0.00011360597614404662,
+      "loss": 0.13062334060668945,
+      "mean_token_accuracy": 0.9691525533795357,
+      "num_tokens": 551908.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.19317283374257385,
+      "epoch": 1.5599565925122083,
+      "grad_norm": 0.7898983359336853,
+      "learning_rate": 0.00010867437239907765,
+      "loss": 0.13731375932693482,
+      "mean_token_accuracy": 0.9673447087407112,
+      "num_tokens": 567817.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.23874589540064334,
+      "epoch": 1.6033640803038525,
+      "grad_norm": 0.37412697076797485,
+      "learning_rate": 0.00010372140668701483,
+      "loss": 0.16327574253082275,
+      "mean_token_accuracy": 0.9641537763178348,
+      "num_tokens": 583908.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.11286464962176979,
+      "epoch": 1.6467715680954966,
+      "grad_norm": 0.4411953091621399,
+      "learning_rate": 9.875927644251854e-05,
+      "loss": 0.08702898025512695,
+      "mean_token_accuracy": 0.9771473661065102,
+      "num_tokens": 599617.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.13296716185286642,
+      "epoch": 1.6901790558871406,
+      "grad_norm": 0.3289574086666107,
+      "learning_rate": 9.380020166931036e-05,
+      "loss": 0.11703462600708008,
+      "mean_token_accuracy": 0.9712080150842667,
+      "num_tokens": 615577.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.1416403181385249,
+      "epoch": 1.7335865436787845,
+      "grad_norm": 0.571514368057251,
+      "learning_rate": 8.885639484654701e-05,
+      "loss": 0.11379531621932984,
+      "mean_token_accuracy": 0.9724767826497555,
+      "num_tokens": 631601.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.11030569332651793,
+      "epoch": 1.7769940314704287,
+      "grad_norm": 0.4873872995376587,
+      "learning_rate": 8.394003085372496e-05,
+      "loss": 0.08141401410102844,
+      "mean_token_accuracy": 0.9770576477050781,
+      "num_tokens": 647297.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.12415502546355128,
+      "epoch": 1.8204015192620728,
+      "grad_norm": 0.32351386547088623,
+      "learning_rate": 7.90632169881799e-05,
+      "loss": 0.08947296738624573,
+      "mean_token_accuracy": 0.9762426503002644,
+      "num_tokens": 663176.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.16395117049105465,
+      "epoch": 1.8638090070537168,
+      "grad_norm": 0.34445416927337646,
+      "learning_rate": 7.423796314901768e-05,
+      "loss": 0.12568631172180175,
+      "mean_token_accuracy": 0.9712538823485375,
+      "num_tokens": 678975.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.20411954806186258,
+      "epoch": 1.9072164948453607,
+      "grad_norm": 0.8611961603164673,
+      "learning_rate": 6.947615226090297e-05,
+      "loss": 0.16005014181137084,
+      "mean_token_accuracy": 0.9660855703055858,
+      "num_tokens": 694724.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.1906371342483908,
+      "epoch": 1.9506239826370049,
+      "grad_norm": 0.3045775890350342,
+      "learning_rate": 6.478951101054225e-05,
+      "loss": 0.13002687692642212,
+      "mean_token_accuracy": 0.9707569405436516,
+      "num_tokens": 710764.0,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 693,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4198134548545536.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora_adapter/checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f02029ae097ac6a5686a868c70c7fb13e1a18c4978ab722ce3a1759ddbc101a
+size 5713

lora_adapter/checkpoint-600/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- 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 0.21.0

lora_adapter/checkpoint-600/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

lora_adapter/checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1712ee7e7f7e4c3c777fce6e9c5403963424d3232cb0030c6d1a51d48313f81
+size 45118424

lora_adapter/checkpoint-600/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

lora_adapter/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e8233b64bbb2bbb6466e698aff71715948a39cf01090d026f5eb94af9e408e
+size 90359883

lora_adapter/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b1e5ce7a350c52ef18aceb7dce8450b476076d04fd51abbdfbe08e044226c5
+size 14455

lora_adapter/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca53b508d23f29ccad5f68bc4d846fe67adee9f5b097e378caa6373300f6ccc
+size 1465

lora_adapter/checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

lora_adapter/checkpoint-600/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

lora_adapter/checkpoint-600/trainer_state.json

@@ -0,0 +1,656 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.599023331524688,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.268431743979454,
+      "epoch": 0.04340748779164406,
+      "grad_norm": 5.425721168518066,
+      "learning_rate": 3e-05,
+      "loss": 4.763444137573242,
+      "mean_token_accuracy": 0.37437669970095155,
+      "num_tokens": 15851.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.6355564504861833,
+      "epoch": 0.08681497558328811,
+      "grad_norm": 2.6653194427490234,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 3.661287307739258,
+      "mean_token_accuracy": 0.4522986955940723,
+      "num_tokens": 31565.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.110316979885101,
+      "epoch": 0.13022246337493218,
+      "grad_norm": 1.8292694091796875,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 2.4040077209472654,
+      "mean_token_accuracy": 0.6126278236508369,
+      "num_tokens": 47681.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.947795458137989,
+      "epoch": 0.17362995116657623,
+      "grad_norm": 1.7558073997497559,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.4649612426757812,
+      "mean_token_accuracy": 0.7671711064875126,
+      "num_tokens": 63639.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2642615631222724,
+      "epoch": 0.21703743895822028,
+      "grad_norm": 1.8000116348266602,
+      "learning_rate": 0.00016333333333333334,
+      "loss": 0.9385161399841309,
+      "mean_token_accuracy": 0.8446647509932518,
+      "num_tokens": 79224.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9772241789847612,
+      "epoch": 0.26044492674986436,
+      "grad_norm": 1.5789580345153809,
+      "learning_rate": 0.00019666666666666666,
+      "loss": 0.6508745193481446,
+      "mean_token_accuracy": 0.8930118441581726,
+      "num_tokens": 94825.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7386516474187375,
+      "epoch": 0.3038524145415084,
+      "grad_norm": 1.118341088294983,
+      "learning_rate": 0.0001999002586734068,
+      "loss": 0.5544538021087646,
+      "mean_token_accuracy": 0.9125440023839474,
+      "num_tokens": 110902.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4801172070205212,
+      "epoch": 0.34725990233315246,
+      "grad_norm": 1.0871493816375732,
+      "learning_rate": 0.00019955572927610798,
+      "loss": 0.32133638858795166,
+      "mean_token_accuracy": 0.9453130982816219,
+      "num_tokens": 126758.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4470752142369747,
+      "epoch": 0.3906673901247965,
+      "grad_norm": 0.9949904084205627,
+      "learning_rate": 0.00019896602868774615,
+      "loss": 0.33235070705413816,
+      "mean_token_accuracy": 0.9432531543076038,
+      "num_tokens": 142247.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.43914212100207806,
+      "epoch": 0.43407487791644056,
+      "grad_norm": 1.2417030334472656,
+      "learning_rate": 0.00019813260913610048,
+      "loss": 0.32300994396209715,
+      "mean_token_accuracy": 0.9425150409340859,
+      "num_tokens": 158033.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.38672009818255904,
+      "epoch": 0.47748236570808467,
+      "grad_norm": 1.4303337335586548,
+      "learning_rate": 0.00019705752304412648,
+      "loss": 0.3090308904647827,
+      "mean_token_accuracy": 0.9426406390964985,
+      "num_tokens": 173972.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.2582590217702091,
+      "epoch": 0.5208898534997287,
+      "grad_norm": 0.7586016654968262,
+      "learning_rate": 0.00019574341797555143,
+      "loss": 0.16584413051605223,
+      "mean_token_accuracy": 0.9635460428893566,
+      "num_tokens": 189557.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.29735598172992467,
+      "epoch": 0.5642973412913728,
+      "grad_norm": 1.3573423624038696,
+      "learning_rate": 0.00019419353011484387,
+      "loss": 0.23453230857849122,
+      "mean_token_accuracy": 0.9539774417877197,
+      "num_tokens": 205568.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3157164487987757,
+      "epoch": 0.6077048290830168,
+      "grad_norm": 0.7886211276054382,
+      "learning_rate": 0.00019241167629761527,
+      "loss": 0.24561758041381837,
+      "mean_token_accuracy": 0.951296404749155,
+      "num_tokens": 221240.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.41249370062723756,
+      "epoch": 0.6511123168746609,
+      "grad_norm": 0.6835598945617676,
+      "learning_rate": 0.00019040224461107917,
+      "loss": 0.3280463695526123,
+      "mean_token_accuracy": 0.9425421200692654,
+      "num_tokens": 236889.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.25797676630318167,
+      "epoch": 0.6945198046663049,
+      "grad_norm": 0.5169897675514221,
+      "learning_rate": 0.0001881701835877161,
+      "loss": 0.17580994367599487,
+      "mean_token_accuracy": 0.9615871131420135,
+      "num_tokens": 252552.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.3551043555140495,
+      "epoch": 0.737927292457949,
+      "grad_norm": 0.9616410136222839,
+      "learning_rate": 0.0001857209900187565,
+      "loss": 0.3012498140335083,
+      "mean_token_accuracy": 0.9450895473361015,
+      "num_tokens": 268798.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.3095861619338393,
+      "epoch": 0.781334780249593,
+      "grad_norm": 1.0524218082427979,
+      "learning_rate": 0.00018306069541749258,
+      "loss": 0.21495308876037597,
+      "mean_token_accuracy": 0.95635409578681,
+      "num_tokens": 284560.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.3253756103105843,
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.44378986954689026,
+      "learning_rate": 0.00018019585116575555,
+      "loss": 0.27938573360443114,
+      "mean_token_accuracy": 0.9474706895649433,
+      "num_tokens": 300840.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.2480218150652945,
+      "epoch": 0.8681497558328811,
+      "grad_norm": 0.376433789730072,
+      "learning_rate": 0.000177133512380137,
+      "loss": 0.18635139465332032,
+      "mean_token_accuracy": 0.9606560796499253,
+      "num_tokens": 316455.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.26516002183780074,
+      "epoch": 0.9115572436245253,
+      "grad_norm": 0.447360634803772,
+      "learning_rate": 0.00017388122053768674,
+      "loss": 0.20903537273406983,
+      "mean_token_accuracy": 0.9590088307857514,
+      "num_tokens": 332359.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.22508152723312377,
+      "epoch": 0.9549647314161693,
+      "grad_norm": 0.39458373188972473,
+      "learning_rate": 0.0001704469849038734,
+      "loss": 0.17320446968078612,
+      "mean_token_accuracy": 0.9621456168591976,
+      "num_tokens": 348219.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.1884014437906444,
+      "epoch": 0.9983722192078134,
+      "grad_norm": 0.5577853918075562,
+      "learning_rate": 0.00016683926280854484,
+      "loss": 0.14232510328292847,
+      "mean_token_accuracy": 0.967728354781866,
+      "num_tokens": 363802.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.2500555583713006,
+      "eval_loss": 0.2172880917787552,
+      "eval_mean_token_accuracy": 0.9547121439661298,
+      "eval_num_tokens": 364353.0,
+      "eval_runtime": 43.3662,
+      "eval_samples_per_second": 2.26,
+      "eval_steps_per_second": 2.26,
+      "step": 231
+    },
+    {
+      "entropy": 0.26626345694065096,
+      "epoch": 1.0390667390124797,
+      "grad_norm": 0.36867332458496094,
+      "learning_rate": 0.00016306693881846152,
+      "loss": 0.23021941184997557,
+      "mean_token_accuracy": 0.9587587014834086,
+      "num_tokens": 378571.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.1791029059328139,
+      "epoch": 1.0824742268041236,
+      "grad_norm": 0.5592738389968872,
+      "learning_rate": 0.00015913930285769355,
+      "loss": 0.1204079270362854,
+      "mean_token_accuracy": 0.970609325170517,
+      "num_tokens": 394252.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.25584981925785544,
+      "epoch": 1.1258817145957678,
+      "grad_norm": 0.6882627606391907,
+      "learning_rate": 0.00015506602732976373,
+      "loss": 0.182321298122406,
+      "mean_token_accuracy": 0.9607684284448623,
+      "num_tokens": 410118.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.15852767862379552,
+      "epoch": 1.1692892023874117,
+      "grad_norm": 0.47175613045692444,
+      "learning_rate": 0.00015085714329787631,
+      "loss": 0.10519710779190064,
+      "mean_token_accuracy": 0.9718552604317665,
+      "num_tokens": 425967.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.224250613944605,
+      "epoch": 1.212696690179056,
+      "grad_norm": 0.8211113214492798,
+      "learning_rate": 0.0001465230157818914,
+      "loss": 0.1746065378189087,
+      "mean_token_accuracy": 0.9628558784723282,
+      "num_tokens": 441911.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.2187170408666134,
+      "epoch": 1.2561041779707,
+      "grad_norm": 1.2185333967208862,
+      "learning_rate": 0.00014207431823288057,
+      "loss": 0.16913924217224122,
+      "mean_token_accuracy": 0.9632994569838047,
+      "num_tokens": 457767.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.15246864631772042,
+      "epoch": 1.299511665762344,
+      "grad_norm": 0.8135276436805725,
+      "learning_rate": 0.00013752200624812282,
+      "loss": 0.10427193641662598,
+      "mean_token_accuracy": 0.9733581781387329,
+      "num_tokens": 473550.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.14296606807038187,
+      "epoch": 1.342919153553988,
+      "grad_norm": 0.4611963927745819,
+      "learning_rate": 0.00013287729059127288,
+      "loss": 0.11364473104476928,
+      "mean_token_accuracy": 0.9724942341446876,
+      "num_tokens": 489513.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.18273791116662325,
+      "epoch": 1.386326641345632,
+      "grad_norm": 0.600029468536377,
+      "learning_rate": 0.00012815160958414332,
+      "loss": 0.14306700229644775,
+      "mean_token_accuracy": 0.9665566079318524,
+      "num_tokens": 505197.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.12391844158992171,
+      "epoch": 1.4297341291372763,
+      "grad_norm": 0.35350969433784485,
+      "learning_rate": 0.0001233566009380896,
+      "loss": 0.08826681971549988,
+      "mean_token_accuracy": 0.9754320561885834,
+      "num_tokens": 520666.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.14481371184810996,
+      "epoch": 1.4731416169289202,
+      "grad_norm": 0.6141801476478577,
+      "learning_rate": 0.0001185040730943683,
+      "loss": 0.11338310241699219,
+      "mean_token_accuracy": 0.9735137969255447,
+      "num_tokens": 536352.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.18556677168235183,
+      "epoch": 1.5165491047205641,
+      "grad_norm": 0.8235384225845337,
+      "learning_rate": 0.00011360597614404662,
+      "loss": 0.13062334060668945,
+      "mean_token_accuracy": 0.9691525533795357,
+      "num_tokens": 551908.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.19317283374257385,
+      "epoch": 1.5599565925122083,
+      "grad_norm": 0.7898983359336853,
+      "learning_rate": 0.00010867437239907765,
+      "loss": 0.13731375932693482,
+      "mean_token_accuracy": 0.9673447087407112,
+      "num_tokens": 567817.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.23874589540064334,
+      "epoch": 1.6033640803038525,
+      "grad_norm": 0.37412697076797485,
+      "learning_rate": 0.00010372140668701483,
+      "loss": 0.16327574253082275,
+      "mean_token_accuracy": 0.9641537763178348,
+      "num_tokens": 583908.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.11286464962176979,
+      "epoch": 1.6467715680954966,
+      "grad_norm": 0.4411953091621399,
+      "learning_rate": 9.875927644251854e-05,
+      "loss": 0.08702898025512695,
+      "mean_token_accuracy": 0.9771473661065102,
+      "num_tokens": 599617.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.13296716185286642,
+      "epoch": 1.6901790558871406,
+      "grad_norm": 0.3289574086666107,
+      "learning_rate": 9.380020166931036e-05,
+      "loss": 0.11703462600708008,
+      "mean_token_accuracy": 0.9712080150842667,
+      "num_tokens": 615577.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.1416403181385249,
+      "epoch": 1.7335865436787845,
+      "grad_norm": 0.571514368057251,
+      "learning_rate": 8.885639484654701e-05,
+      "loss": 0.11379531621932984,
+      "mean_token_accuracy": 0.9724767826497555,
+      "num_tokens": 631601.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.11030569332651793,
+      "epoch": 1.7769940314704287,
+      "grad_norm": 0.4873872995376587,
+      "learning_rate": 8.394003085372496e-05,
+      "loss": 0.08141401410102844,
+      "mean_token_accuracy": 0.9770576477050781,
+      "num_tokens": 647297.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.12415502546355128,
+      "epoch": 1.8204015192620728,
+      "grad_norm": 0.32351386547088623,
+      "learning_rate": 7.90632169881799e-05,
+      "loss": 0.08947296738624573,
+      "mean_token_accuracy": 0.9762426503002644,
+      "num_tokens": 663176.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.16395117049105465,
+      "epoch": 1.8638090070537168,
+      "grad_norm": 0.34445416927337646,
+      "learning_rate": 7.423796314901768e-05,
+      "loss": 0.12568631172180175,
+      "mean_token_accuracy": 0.9712538823485375,
+      "num_tokens": 678975.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.20411954806186258,
+      "epoch": 1.9072164948453607,
+      "grad_norm": 0.8611961603164673,
+      "learning_rate": 6.947615226090297e-05,
+      "loss": 0.16005014181137084,
+      "mean_token_accuracy": 0.9660855703055858,
+      "num_tokens": 694724.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.1906371342483908,
+      "epoch": 1.9506239826370049,
+      "grad_norm": 0.3045775890350342,
+      "learning_rate": 6.478951101054225e-05,
+      "loss": 0.13002687692642212,
+      "mean_token_accuracy": 0.9707569405436516,
+      "num_tokens": 710764.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.12089938684366644,
+      "epoch": 1.994031470428649,
+      "grad_norm": 0.8321558833122253,
+      "learning_rate": 6.018958096792642e-05,
+      "loss": 0.08647857308387756,
+      "mean_token_accuracy": 0.977338220179081,
+      "num_tokens": 726521.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.18578565937980096,
+      "eval_loss": 0.15265728533267975,
+      "eval_mean_token_accuracy": 0.9647377492213736,
+      "eval_num_tokens": 728706.0,
+      "eval_runtime": 43.8011,
+      "eval_samples_per_second": 2.237,
+      "eval_steps_per_second": 2.237,
+      "step": 462
+    },
+    {
+      "entropy": 0.11111431792378426,
+      "epoch": 2.0347259902333152,
+      "grad_norm": 0.31517288088798523,
+      "learning_rate": 5.568769016345162e-05,
+      "loss": 0.07631215453147888,
+      "mean_token_accuracy": 0.9792846202850342,
+      "num_tokens": 741135.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.12576794293709098,
+      "epoch": 2.0781334780249594,
+      "grad_norm": 0.6706956028938293,
+      "learning_rate": 5.129492519091414e-05,
+      "loss": 0.08828421831130981,
+      "mean_token_accuracy": 0.9774440720677375,
+      "num_tokens": 757149.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.1652247125748545,
+      "epoch": 2.1215409658166036,
+      "grad_norm": 0.6188645362854004,
+      "learning_rate": 4.7022103905079403e-05,
+      "loss": 0.10453375577926635,
+      "mean_token_accuracy": 0.9749265879392623,
+      "num_tokens": 773043.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.13389622955583036,
+      "epoch": 2.1649484536082473,
+      "grad_norm": 0.4554220736026764,
+      "learning_rate": 4.287974878106223e-05,
+      "loss": 0.0822334885597229,
+      "mean_token_accuracy": 0.9777384780347347,
+      "num_tokens": 788836.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.1122925499919802,
+      "epoch": 2.2083559413998914,
+      "grad_norm": 0.3267352283000946,
+      "learning_rate": 3.887806100112449e-05,
+      "loss": 0.07709192037582398,
+      "mean_token_accuracy": 0.9793755315244198,
+      "num_tokens": 804610.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.10615749745629728,
+      "epoch": 2.2517634291915356,
+      "grad_norm": 0.30847302079200745,
+      "learning_rate": 3.5026895332705504e-05,
+      "loss": 0.07118260264396667,
+      "mean_token_accuracy": 0.9799461409449577,
+      "num_tokens": 820138.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.13317556893453003,
+      "epoch": 2.2951709169831798,
+      "grad_norm": 0.7525761127471924,
+      "learning_rate": 3.133573585955194e-05,
+      "loss": 0.08792675137519837,
+      "mean_token_accuracy": 0.9784041821956635,
+      "num_tokens": 835962.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.15031940978951752,
+      "epoch": 2.3385784047748235,
+      "grad_norm": 0.36720001697540283,
+      "learning_rate": 2.7813672625712594e-05,
+      "loss": 0.08893920779228211,
+      "mean_token_accuracy": 0.9778918631374836,
+      "num_tokens": 852357.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.12438173596747219,
+      "epoch": 2.3819858925664676,
+      "grad_norm": 0.7582745552062988,
+      "learning_rate": 2.4469379249916613e-05,
+      "loss": 0.08149291276931762,
+      "mean_token_accuracy": 0.9797964461147786,
+      "num_tokens": 868012.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.1631687331944704,
+      "epoch": 2.425393380358112,
+      "grad_norm": 0.29170867800712585,
+      "learning_rate": 2.131109156546226e-05,
+      "loss": 0.10433924198150635,
+      "mean_token_accuracy": 0.9751808606088161,
+      "num_tokens": 884061.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.10712425396777689,
+      "epoch": 2.468800868149756,
+      "grad_norm": 0.6179195642471313,
+      "learning_rate": 1.8346587338219455e-05,
+      "loss": 0.07671988606452942,
+      "mean_token_accuracy": 0.9794992141425609,
+      "num_tokens": 899982.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.10620055091567338,
+      "epoch": 2.5122083559414,
+      "grad_norm": 0.3330930769443512,
+      "learning_rate": 1.5583167112693153e-05,
+      "loss": 0.06958608627319336,
+      "mean_token_accuracy": 0.981497923284769,
+      "num_tokens": 915669.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.09565388238988817,
+      "epoch": 2.555615843733044,
+      "grad_norm": 0.3171375095844269,
+      "learning_rate": 1.3027636233317342e-05,
+      "loss": 0.06519963145256043,
+      "mean_token_accuracy": 0.9813847310841084,
+      "num_tokens": 931627.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.11542923199012875,
+      "epoch": 2.599023331524688,
+      "grad_norm": 0.7167931199073792,
+      "learning_rate": 1.0686288085254781e-05,
+      "loss": 0.07995554804801941,
+      "mean_token_accuracy": 0.9791012987494468,
+      "num_tokens": 947380.0,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 693,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5595709277061120.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora_adapter/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f02029ae097ac6a5686a868c70c7fb13e1a18c4978ab722ce3a1759ddbc101a
+size 5713

lora_adapter/checkpoint-693/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
+- 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 0.21.0

lora_adapter/checkpoint-693/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}