Training in progress, step 100

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: EssentialAI/rnj-1-instruct
+library_name: transformers
+model_name: EssentialAI-rnj-1-instruct-trl-grpo
+tags:
+- generated_from_trainer
+- grpo
+- trackio:https://sshahriyar-EssentialAI-rnj-1-instruct-trl-grpo.hf.space?project=huggingface&runs=sshahriyar-1774227545&sidebar=collapsed
+- trl
+licence: license
+---
+
+# Model Card for EssentialAI-rnj-1-instruct-trl-grpo
+
+This model is a fine-tuned version of [EssentialAI/rnj-1-instruct](https://huggingface.co/EssentialAI/rnj-1-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="sshahriyar/EssentialAI-rnj-1-instruct-trl-grpo", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://sshahriyar-EssentialAI-rnj-1-instruct-trl-grpo.hf.space?project=huggingface&runs=sshahriyar-1774227545&sidebar=collapsed)
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.29.1
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{shao2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+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}
+}
+```

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3"
+  },
+  "base_model_name_or_path": "EssentialAI/rnj-1-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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7383b39db39d1404fd58f57964818ad4db0455b6ba9ba1b1a88d5c3deb78707b
+size 180415648

chat_template.jinja

@@ -0,0 +1,128 @@
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) -%}
+{%- set emit = namespace(started=false) -%}
+
+{# ---------- Build base system message (always emitted) ---------- #}
+{%- set base_system = 'You are rnj-1, a foundation model trained by Essential AI.\n' -%}
+
+{# ---------- Default system prompt if user system is absent ---------- #}
+{%- set default_system = 'You are a helpful assistant.' -%}
+
+{# Detect whether the first message is a user-provided system message #}
+{%- set has_user_system = (messages
+    and messages[0].role == 'system'
+    and (messages[0].content is string)) -%}
+
+{# The system instruction that should apply (user system wins; else default) #}
+{%- set effective_system = (has_user_system and messages[0].content) or default_system -%}
+
+
+{# ---------- Optional tools preface as a synthetic system message ---------- #}
+{%- if tools %}
+  {%- set sys_preamble -%}
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{%- for tool in tools %}
+{{ "\n" ~ (tool | tojson) }}
+{% endfor %}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+  {%- endset -%}
+
+  {# Always include effective_system; user system prevails over default #}
+  {%- set sys_content = effective_system ~ "\n\n" ~ sys_preamble -%}
+
+  {%- set content = '<|start_header_id|>system<|end_header_id|>\n'
+      ~ base_system ~ '\n' ~ sys_content ~ '<|eot_id|>' -%}
+  {%- if not emit.started -%}{%- set content = bos_token ~ content -%}{%- set emit.started = true -%}{%- endif -%}
+  {{- content -}}
+{%- else %}
+  {# No tools: always emit base_system + effective_system #}
+  {%- set content = '<|start_header_id|>system<|end_header_id|>\n'
+      ~ base_system ~ '\n' ~ effective_system ~ '<|eot_id|>' -%}
+  {%- if not emit.started -%}{%- set content = bos_token ~ content -%}{%- set emit.started = true -%}{%- endif -%}
+  {{- content -}}
+{%- endif -%}
+
+{# ---------- Locate last user query for multi-step tool behavior ---------- #}
+{%- for message in messages[::-1] %}
+  {%- set index = (messages|length - 1) - loop.index0 -%}
+  {%- if ns.multi_step_tool
+        and message.role == "user"
+        and message.content is string
+        and not (message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) -%}
+    {%- set ns.multi_step_tool = false -%}
+    {%- set ns.last_query_index = index -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{# ---------- Walk all messages and emit in Llama-3 format ---------- #}
+{%- for message in messages %}
+  {%- if message.content is string -%}
+    {%- set content = message.content -%}
+  {%- else -%}
+    {%- set content = '' -%}
+  {%- endif -%}
+
+  {# Skip the FIRST system message if it existed, since we already embedded it in effective_system #}
+  {%- if loop.first and message.role == "system" -%}
+    {# no-op #}
+
+  {%- elif (message.role == "user") or (message.role == "system") -%}
+    {%- set block = '<|start_header_id|>' ~ message.role ~ '<|end_header_id|>\n' ~ content ~ '<|eot_id|>' -%}
+    {%- if not emit.started -%}{%- set block = bos_token ~ block -%}{%- set emit.started = true -%}{%- endif -%}
+    {{- block -}}
+
+  {%- elif message.role == "assistant" -%}
+    {%- set body = content -%}
+    {%- set header = '<|start_header_id|>assistant<|end_header_id|>\n' -%}
+    {%- if not emit.started -%}{{ bos_token }}{%- set emit.started = true -%}{%- endif -%}
+    {{- header -}}
+    {% generation %}
+    {{- body -}}
+    {%- if message.tool_calls -%}
+      {%- for tool_call in message.tool_calls -%}
+        {%- if tool_call.function -%}{%- set tc = tool_call.function -%}{%- else -%}{%- set tc = tool_call -%}{%- endif -%}
+        {%- set args_json = (tc.arguments if (tc.arguments is string) else (tc.arguments | tojson)) -%}
+        {%- if loop.first -%}
+          {{- '<tool_call>\n{"name": "' ~ tc.name ~ '", "arguments": ' ~ args_json ~ '}\n</tool_call>' -}}
+        {%- else -%}
+          {{- '\n<tool_call>\n{"name": "' ~ tc.name ~ '", "arguments": ' ~ args_json ~ '}\n</tool_call>' -}}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+    {{- '<|eot_id|>' -}}{%- endgeneration -%}
+
+  {%- elif message.role == "tool" -%}
+    {%- set open_user = (loop.first or (loop.index0 > 0 and messages[loop.index0 - 1].role != "tool")) -%}
+    {%- set close_user = (loop.last or (loop.index0 < messages|length - 1 and messages[loop.index0 + 1].role != "tool")) -%}
+
+    {%- if open_user -%}
+      {%- set header = '<|start_header_id|>user<|end_header_id|>\n' -%}
+      {%- if not emit.started -%}{%- set header = bos_token ~ header -%}{%- set emit.started = true -%}{%- endif -%}
+      {{- header -}}
+    {%- endif -%}
+    {%- if open_user -%}
+      {{- '<tool_response>\n' -}}
+    {%- else -%}
+      {{- '\n<tool_response>\n' -}}
+    {%- endif -%}
+    {{- content -}}
+    {{- '\n</tool_response>' -}}
+
+    {%- if close_user -%}
+      {{- '<|eot_id|>' -}}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+  {{- '<|start_header_id|>assistant<|end_header_id|>\n' -}}
+{%- endif -%}

completions/completions_00010.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a078c8984e8ef94a2eb680cbeb7dbf9d04b8d7c6e68319f707164ad38b1383
+size 15618

completions/completions_00020.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe7b1de6d07668e929fb0fcb3e85ba14eebf362d98c152c3345fd87d3372ade
+size 12560

completions/completions_00030.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b1563023baf313c28d3edc55c78945342f9d6a391a891a2a0b73f935c0a4db
+size 15552

completions/completions_00040.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dc63bda4974e87e24d6cdda6e8651f407e09f699a679e1f1fafaf37d59cd25
+size 18535

completions/completions_00050.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d239aeef54712b955aa8bd331ccb2b416c28cb2446642b15704fbc8a468349a
+size 16521

completions/completions_00060.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7eb42209a738db7731485ae800884cd1a7d4f88ccceacbd433129c89926d1b2
+size 15597

completions/completions_00070.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19545133f9fc4cecac0a3cff74644a67d648f4f5156dd2addc3fa4f08176634
+size 14580

completions/completions_00080.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6db18ef78d8fe351b2ea67f1769579e0dbe39f92d95d148b03c5b8d1026456
+size 16307

completions/completions_00090.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b3d612e6fe5919c48e85e9a9e4bc5b8c66d03b994ef91d83e0384c82171fe9
+size 16128

completions/completions_00100.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668679e7e8ff25ff5b30245d2e134c0d7930f9b9e7f5d8a56f0f8646fafc667b
+size 17857

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab582c0b82ff7af759c87d6c859f06e7601851e41c1fc18d730e0c452270f992
+size 17209964

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "left"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9ee75c034feeb5d76b9cb5bd544d6eb3ea19f362f9c9382d8eb395169af6ef
+size 6929