Upload model

.gitattributes

@@ -15,6 +15,7 @@
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,173 @@
+cache/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

R1-Distill-Qwen-1.5B-Roblox-Luau-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e30e8583cb2ab0c224506b92ed7bebfd58e724e6c6a5bb0150634d34313564
+size 3560416096

R1-Distill-Qwen-1.5B-Roblox-Luau-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87717ad83133d97e7232a62abe4cad4a37f7931ceb424789f07b5b5981603161
+size 924455776

R1-Distill-Qwen-1.5B-Roblox-Luau-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4492c6c5b1980724f2b5726b7bac2e5798a34aeeabf74cdc1a887a73a97717
+size 1117320544

R1-Distill-Qwen-1.5B-Roblox-Luau-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400da0f70785a7c9fbc4177cd99ede82731c817c6f2d9348985183ba6b46e8f4
+size 1285494112

R1-Distill-Qwen-1.5B-Roblox-Luau-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d0bd8716e4fd8051126e25497bf2775c7f81caac565cda2b502b750c247696
+size 1464178528

R1-Distill-Qwen-1.5B-Roblox-Luau-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1d02708637fb8dfae3034c32940ba225e1d31d926e7f59cf074f7c632dd222
+size 1894531936

README.md

@@ -1,3 +1,44 @@
 ---
 license: mit
+license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+finetuned_by: boatbomber
+pipeline_tag: text-generation
+tags:
+- chat
+- reasoning
+- roblox
+- luau
+language:
+- en
+datasets:
+- boatbomber/roblox-info-dump
+- boatbomber/the-luau-stack
 ---
+
+# R1-Distill-Qwen-1.5B-Roblox-Luau
+
+A fine tune of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) using [boatbomber/roblox-info-dump](https://huggingface.co/datasets/boatbomber/roblox-info-dump) and [boatbomber/the-luau-stack](https://huggingface.co/datasets/boatbomber/the-luau-stack) for Roblox domain knowledge.
+
+This is intended to be used for speculative decoding with [boatbomber/R1-Distill-Qwen-14B-Roblox-Luau](https://huggingface.co/boatbomber/R1-Distill-Qwen-14B-Roblox-Luau). It can be used standalone in memory constrained environments, but is not nearly as capable as the 14B model as it has so few weights that it cannot learn the same level of detail.
+
+Recommended inference settings:
+
+| Parameter | Value | Notes |
+| --------- | ----- | ----- |
+| System Prompt | `You are an expert Roblox developer and Luau software engineer.` | Model was fine tuned with this prompt. |
+| temperature   | `0.5-0.7`  | Underlying R1 Distill uses this. I've found best results with `0.55`. |
+| top_p         | `0.95` | Underlying R1 Distill uses this. |
+
+Quantization done using [Unsloth](https://docs.unsloth.ai/).
+
+Available quants:
+
+| Quant | Size | Notes |
+| ----- | ---- | ----- |
+| F16 | 3.56GB | Retains 100% accuracy. Slow and memory hungry. |
+| Q8_O | 1.89GB | High resource use, but generally acceptable. Use when accuracy is crucial. |
+| Q6_K | 1.46GB | Uses Q6_K for all tensors. Good for high end GPUs. |
+| Q5_K_M | 1.29GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K |
+| Q4_K_M | 1.12GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K |
+| Q3_K_M | 0.92GB | Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded. |

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.51.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26150ec0963fb216413748ebd6fe9a2133bb6fc0413ef1a6a00cb702defb3691
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbbe282fb7062a799e835a97699459df8252352238a77edb0af44c9167fd68c2
+size 2111719976

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 7108352000
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1308 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 0,
+  "global_step": 182,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005494505494505495,
+      "grad_norm": 15.111852645874023,
+      "learning_rate": 1e-05,
+      "loss": 2.1607,
+      "step": 1
+    },
+    {
+      "epoch": 0.01098901098901099,
+      "grad_norm": 15.242596626281738,
+      "learning_rate": 9.999255120204248e-06,
+      "loss": 2.5391,
+      "step": 2
+    },
+    {
+      "epoch": 0.016483516483516484,
+      "grad_norm": 6.0544633865356445,
+      "learning_rate": 9.997020702755353e-06,
+      "loss": 2.0783,
+      "step": 3
+    },
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 5.135265350341797,
+      "learning_rate": 9.993297413402282e-06,
+      "loss": 2.1589,
+      "step": 4
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "grad_norm": 2.2902588844299316,
+      "learning_rate": 9.98808636150624e-06,
+      "loss": 1.9133,
+      "step": 5
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 1.7752385139465332,
+      "learning_rate": 9.981389099710132e-06,
+      "loss": 1.8006,
+      "step": 6
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 1.5874292850494385,
+      "learning_rate": 9.973207623475964e-06,
+      "loss": 1.7855,
+      "step": 7
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 1.318580985069275,
+      "learning_rate": 9.96354437049027e-06,
+      "loss": 1.7529,
+      "step": 8
+    },
+    {
+      "epoch": 0.04945054945054945,
+      "grad_norm": 1.1717578172683716,
+      "learning_rate": 9.952402219937817e-06,
+      "loss": 1.6796,
+      "step": 9
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 0.7676920890808105,
+      "learning_rate": 9.939784491643734e-06,
+      "loss": 1.4974,
+      "step": 10
+    },
+    {
+      "epoch": 0.06043956043956044,
+      "grad_norm": 1.2009315490722656,
+      "learning_rate": 9.925694945084369e-06,
+      "loss": 1.4787,
+      "step": 11
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.7637119293212891,
+      "learning_rate": 9.910137778267153e-06,
+      "loss": 1.5551,
+      "step": 12
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.9158480167388916,
+      "learning_rate": 9.893117626479778e-06,
+      "loss": 1.8532,
+      "step": 13
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.7787052392959595,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 1.6938,
+      "step": 14
+    },
+    {
+      "epoch": 0.08241758241758242,
+      "grad_norm": 0.7238631248474121,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 1.6542,
+      "step": 15
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 0.765092134475708,
+      "learning_rate": 9.833332143466099e-06,
+      "loss": 1.6814,
+      "step": 16
+    },
+    {
+      "epoch": 0.09340659340659341,
+      "grad_norm": 0.6503499150276184,
+      "learning_rate": 9.810515099218004e-06,
+      "loss": 1.5824,
+      "step": 17
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.6926908493041992,
+      "learning_rate": 9.78626475276808e-06,
+      "loss": 1.5926,
+      "step": 18
+    },
+    {
+      "epoch": 0.1043956043956044,
+      "grad_norm": 1.1372712850570679,
+      "learning_rate": 9.76058832955357e-06,
+      "loss": 1.4507,
+      "step": 19
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 0.7703443169593811,
+      "learning_rate": 9.733493479914031e-06,
+      "loss": 1.5304,
+      "step": 20
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.569968581199646,
+      "learning_rate": 9.704988276811883e-06,
+      "loss": 1.4274,
+      "step": 21
+    },
+    {
+      "epoch": 0.12087912087912088,
+      "grad_norm": 0.5467634797096252,
+      "learning_rate": 9.675081213427076e-06,
+      "loss": 1.3409,
+      "step": 22
+    },
+    {
+      "epoch": 0.12637362637362637,
+      "grad_norm": 0.7474145889282227,
+      "learning_rate": 9.643781200626512e-06,
+      "loss": 1.4547,
+      "step": 23
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.644389271736145,
+      "learning_rate": 9.611097564309054e-06,
+      "loss": 1.459,
+      "step": 24
+    },
+    {
+      "epoch": 0.13736263736263737,
+      "grad_norm": 0.6308932304382324,
+      "learning_rate": 9.577040042626832e-06,
+      "loss": 1.6206,
+      "step": 25
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.6102603673934937,
+      "learning_rate": 9.54161878308377e-06,
+      "loss": 1.3853,
+      "step": 26
+    },
+    {
+      "epoch": 0.14835164835164835,
+      "grad_norm": 0.6312618851661682,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.5389,
+      "step": 27
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.5201209187507629,
+      "learning_rate": 9.466727668927817e-06,
+      "loss": 1.6037,
+      "step": 28
+    },
+    {
+      "epoch": 0.15934065934065933,
+      "grad_norm": 0.5236848592758179,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 1.4423,
+      "step": 29
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.5750183463096619,
+      "learning_rate": 9.38651347099721e-06,
+      "loss": 1.4734,
+      "step": 30
+    },
+    {
+      "epoch": 0.17032967032967034,
+      "grad_norm": 0.4352014362812042,
+      "learning_rate": 9.344439843625034e-06,
+      "loss": 1.3026,
+      "step": 31
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 0.5367883443832397,
+      "learning_rate": 9.301071782067504e-06,
+      "loss": 1.5871,
+      "step": 32
+    },
+    {
+      "epoch": 0.1813186813186813,
+      "grad_norm": 0.70261549949646,
+      "learning_rate": 9.256422207921757e-06,
+      "loss": 1.4105,
+      "step": 33
+    },
+    {
+      "epoch": 0.18681318681318682,
+      "grad_norm": 0.47652918100357056,
+      "learning_rate": 9.21050442461406e-06,
+      "loss": 1.391,
+      "step": 34
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.6501890420913696,
+      "learning_rate": 9.163332113436031e-06,
+      "loss": 1.456,
+      "step": 35
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.41454020142555237,
+      "learning_rate": 9.114919329468283e-06,
+      "loss": 1.3535,
+      "step": 36
+    },
+    {
+      "epoch": 0.2032967032967033,
+      "grad_norm": 0.5200150609016418,
+      "learning_rate": 9.065280497392663e-06,
+      "loss": 1.3474,
+      "step": 37
+    },
+    {
+      "epoch": 0.2087912087912088,
+      "grad_norm": 0.5001424551010132,
+      "learning_rate": 9.014430407194413e-06,
+      "loss": 1.4666,
+      "step": 38
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.3648586571216583,
+      "learning_rate": 8.962384209755453e-06,
+      "loss": 1.3461,
+      "step": 39
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 0.38699260354042053,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 1.3933,
+      "step": 40
+    },
+    {
+      "epoch": 0.22527472527472528,
+      "grad_norm": 0.35994988679885864,
+      "learning_rate": 8.854765873974898e-06,
+      "loss": 1.3308,
+      "step": 41
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3769252300262451,
+      "learning_rate": 8.799225800722895e-06,
+      "loss": 1.4181,
+      "step": 42
+    },
+    {
+      "epoch": 0.23626373626373626,
+      "grad_norm": 0.3668324053287506,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 1.3021,
+      "step": 43
+    },
+    {
+      "epoch": 0.24175824175824176,
+      "grad_norm": 0.3954791724681854,
+      "learning_rate": 8.684766579921684e-06,
+      "loss": 1.3076,
+      "step": 44
+    },
+    {
+      "epoch": 0.24725274725274726,
+      "grad_norm": 0.363851398229599,
+      "learning_rate": 8.625881535716883e-06,
+      "loss": 1.3059,
+      "step": 45
+    },
+    {
+      "epoch": 0.25274725274725274,
+      "grad_norm": 0.35807710886001587,
+      "learning_rate": 8.565916153152982e-06,
+      "loss": 1.3275,
+      "step": 46
+    },
+    {
+      "epoch": 0.25824175824175827,
+      "grad_norm": 0.3441619873046875,
+      "learning_rate": 8.504888299030748e-06,
+      "loss": 1.3718,
+      "step": 47
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.3851041793823242,
+      "learning_rate": 8.442816156716386e-06,
+      "loss": 1.3519,
+      "step": 48
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 0.38189154863357544,
+      "learning_rate": 8.379718220723772e-06,
+      "loss": 1.2314,
+      "step": 49
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "grad_norm": 0.3497340977191925,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 1.3285,
+      "step": 50
+    },
+    {
+      "epoch": 0.2802197802197802,
+      "grad_norm": 0.3765724301338196,
+      "learning_rate": 8.250520468343722e-06,
+      "loss": 1.3046,
+      "step": 51
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.33693233132362366,
+      "learning_rate": 8.184459146674447e-06,
+      "loss": 1.2712,
+      "step": 52
+    },
+    {
+      "epoch": 0.29120879120879123,
+      "grad_norm": 0.33964160084724426,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 1.2689,
+      "step": 53
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.32269054651260376,
+      "learning_rate": 8.049510022000365e-06,
+      "loss": 1.2281,
+      "step": 54
+    },
+    {
+      "epoch": 0.3021978021978022,
+      "grad_norm": 0.3472397029399872,
+      "learning_rate": 7.980662427346127e-06,
+      "loss": 1.2591,
+      "step": 55
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.3756208121776581,
+      "learning_rate": 7.910926738603855e-06,
+      "loss": 1.2188,
+      "step": 56
+    },
+    {
+      "epoch": 0.3131868131868132,
+      "grad_norm": 0.341913640499115,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 1.2656,
+      "step": 57
+    },
+    {
+      "epoch": 0.31868131868131866,
+      "grad_norm": 0.3188314735889435,
+      "learning_rate": 7.768874448802665e-06,
+      "loss": 1.3221,
+      "step": 58
+    },
+    {
+      "epoch": 0.3241758241758242,
+      "grad_norm": 0.3308219611644745,
+      "learning_rate": 7.696600172495997e-06,
+      "loss": 1.2503,
+      "step": 59
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.34545618295669556,
+      "learning_rate": 7.62352243899504e-06,
+      "loss": 1.4181,
+      "step": 60
+    },
+    {
+      "epoch": 0.33516483516483514,
+      "grad_norm": 0.42731383442878723,
+      "learning_rate": 7.5496630219506805e-06,
+      "loss": 1.2316,
+      "step": 61
+    },
+    {
+      "epoch": 0.34065934065934067,
+      "grad_norm": 0.34381401538848877,
+      "learning_rate": 7.475043927917908e-06,
+      "loss": 1.3498,
+      "step": 62
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 0.29591628909111023,
+      "learning_rate": 7.399687389798933e-06,
+      "loss": 1.2484,
+      "step": 63
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 0.36008334159851074,
+      "learning_rate": 7.323615860218844e-06,
+      "loss": 1.1903,
+      "step": 64
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.3181370496749878,
+      "learning_rate": 7.246852004835807e-06,
+      "loss": 1.2581,
+      "step": 65
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.3501285910606384,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 1.2945,
+      "step": 66
+    },
+    {
+      "epoch": 0.36813186813186816,
+      "grad_norm": 0.3263450264930725,
+      "learning_rate": 7.091339003877826e-06,
+      "loss": 1.2323,
+      "step": 67
+    },
+    {
+      "epoch": 0.37362637362637363,
+      "grad_norm": 0.37200814485549927,
+      "learning_rate": 7.012636193699838e-06,
+      "loss": 1.358,
+      "step": 68
+    },
+    {
+      "epoch": 0.3791208791208791,
+      "grad_norm": 0.321250855922699,
+      "learning_rate": 6.933333714707094e-06,
+      "loss": 1.2074,
+      "step": 69
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.32449448108673096,
+      "learning_rate": 6.8534551952253395e-06,
+      "loss": 1.2721,
+      "step": 70
+    },
+    {
+      "epoch": 0.3901098901098901,
+      "grad_norm": 0.3131982386112213,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 1.2757,
+      "step": 71
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.34203317761421204,
+      "learning_rate": 6.692065399168352e-06,
+      "loss": 1.2193,
+      "step": 72
+    },
+    {
+      "epoch": 0.4010989010989011,
+      "grad_norm": 0.312980979681015,
+      "learning_rate": 6.6106022089924535e-06,
+      "loss": 1.2095,
+      "step": 73
+    },
+    {
+      "epoch": 0.4065934065934066,
+      "grad_norm": 0.33843284845352173,
+      "learning_rate": 6.5286591367987655e-06,
+      "loss": 1.1364,
+      "step": 74
+    },
+    {
+      "epoch": 0.41208791208791207,
+      "grad_norm": 0.30338841676712036,
+      "learning_rate": 6.4462605976828395e-06,
+      "loss": 1.2184,
+      "step": 75
+    },
+    {
+      "epoch": 0.4175824175824176,
+      "grad_norm": 0.32572391629219055,
+      "learning_rate": 6.363431142447469e-06,
+      "loss": 1.2298,
+      "step": 76
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 0.32466384768486023,
+      "learning_rate": 6.280195450287736e-06,
+      "loss": 1.2609,
+      "step": 77
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.3212321996688843,
+      "learning_rate": 6.1965783214377895e-06,
+      "loss": 1.298,
+      "step": 78
+    },
+    {
+      "epoch": 0.4340659340659341,
+      "grad_norm": 0.31591418385505676,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 1.2798,
+      "step": 79
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 0.32150542736053467,
+      "learning_rate": 6.028299515429683e-06,
+      "loss": 1.1752,
+      "step": 80
+    },
+    {
+      "epoch": 0.44505494505494503,
+      "grad_norm": 0.30293920636177063,
+      "learning_rate": 5.943687977264584e-06,
+      "loss": 1.2313,
+      "step": 81
+    },
+    {
+      "epoch": 0.45054945054945056,
+      "grad_norm": 0.31878089904785156,
+      "learning_rate": 5.858795265456382e-06,
+      "loss": 1.2983,
+      "step": 82
+    },
+    {
+      "epoch": 0.45604395604395603,
+      "grad_norm": 0.310153990983963,
+      "learning_rate": 5.773646673951406e-06,
+      "loss": 1.1602,
+      "step": 83
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.31121817231178284,
+      "learning_rate": 5.688267572935843e-06,
+      "loss": 1.3564,
+      "step": 84
+    },
+    {
+      "epoch": 0.46703296703296704,
+      "grad_norm": 0.2957365810871124,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 1.1286,
+      "step": 85
+    },
+    {
+      "epoch": 0.4725274725274725,
+      "grad_norm": 0.3177623152732849,
+      "learning_rate": 5.51691965894185e-06,
+      "loss": 1.269,
+      "step": 86
+    },
+    {
+      "epoch": 0.47802197802197804,
+      "grad_norm": 0.3129305839538574,
+      "learning_rate": 5.4310018994030974e-06,
+      "loss": 1.2497,
+      "step": 87
+    },
+    {
+      "epoch": 0.4835164835164835,
+      "grad_norm": 0.2926500141620636,
+      "learning_rate": 5.3449557220216245e-06,
+      "loss": 1.1608,
+      "step": 88
+    },
+    {
+      "epoch": 0.489010989010989,
+      "grad_norm": 0.28984707593917847,
+      "learning_rate": 5.258806764421048e-06,
+      "loss": 1.2594,
+      "step": 89
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.3356908857822418,
+      "learning_rate": 5.172580694848541e-06,
+      "loss": 1.2022,
+      "step": 90
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.31414178013801575,
+      "learning_rate": 5.0863032045269435e-06,
+      "loss": 1.1703,
+      "step": 91
+    },
+    {
+      "epoch": 0.5054945054945055,
+      "grad_norm": 0.32916730642318726,
+      "learning_rate": 5e-06,
+      "loss": 1.2683,
+      "step": 92
+    },
+    {
+      "epoch": 0.510989010989011,
+      "grad_norm": 0.3171485364437103,
+      "learning_rate": 4.913696795473058e-06,
+      "loss": 1.2961,
+      "step": 93
+    },
+    {
+      "epoch": 0.5164835164835165,
+      "grad_norm": 0.3199380040168762,
+      "learning_rate": 4.827419305151461e-06,
+      "loss": 1.3379,
+      "step": 94
+    },
+    {
+      "epoch": 0.521978021978022,
+      "grad_norm": 0.3766830861568451,
+      "learning_rate": 4.741193235578953e-06,
+      "loss": 1.2776,
+      "step": 95
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.34143537282943726,
+      "learning_rate": 4.6550442779783755e-06,
+      "loss": 1.2237,
+      "step": 96
+    },
+    {
+      "epoch": 0.532967032967033,
+      "grad_norm": 0.3254823386669159,
+      "learning_rate": 4.568998100596903e-06,
+      "loss": 1.2267,
+      "step": 97
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.2892250716686249,
+      "learning_rate": 4.4830803410581506e-06,
+      "loss": 1.1432,
+      "step": 98
+    },
+    {
+      "epoch": 0.5439560439560439,
+      "grad_norm": 0.30142074823379517,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 1.2063,
+      "step": 99
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 0.3007691502571106,
+      "learning_rate": 4.31173242706416e-06,
+      "loss": 1.2316,
+      "step": 100
+    },
+    {
+      "epoch": 0.554945054945055,
+      "grad_norm": 0.304579496383667,
+      "learning_rate": 4.226353326048594e-06,
+      "loss": 1.1852,
+      "step": 101
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.3164512813091278,
+      "learning_rate": 4.14120473454362e-06,
+      "loss": 1.0561,
+      "step": 102
+    },
+    {
+      "epoch": 0.5659340659340659,
+      "grad_norm": 0.3220779299736023,
+      "learning_rate": 4.056312022735417e-06,
+      "loss": 1.2721,
+      "step": 103
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.3365575671195984,
+      "learning_rate": 3.9717004845703175e-06,
+      "loss": 1.2173,
+      "step": 104
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.32684552669525146,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 1.2247,
+      "step": 105
+    },
+    {
+      "epoch": 0.5824175824175825,
+      "grad_norm": 0.32608991861343384,
+      "learning_rate": 3.803421678562213e-06,
+      "loss": 1.285,
+      "step": 106
+    },
+    {
+      "epoch": 0.5879120879120879,
+      "grad_norm": 0.2869299054145813,
+      "learning_rate": 3.7198045497122647e-06,
+      "loss": 1.0908,
+      "step": 107
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.3301023542881012,
+      "learning_rate": 3.6365688575525315e-06,
+      "loss": 1.1583,
+      "step": 108
+    },
+    {
+      "epoch": 0.5989010989010989,
+      "grad_norm": 0.3131628632545471,
+      "learning_rate": 3.553739402317162e-06,
+      "loss": 1.2637,
+      "step": 109
+    },
+    {
+      "epoch": 0.6043956043956044,
+      "grad_norm": 0.2992359697818756,
+      "learning_rate": 3.471340863201237e-06,
+      "loss": 1.1538,
+      "step": 110
+    },
+    {
+      "epoch": 0.6098901098901099,
+      "grad_norm": 0.35789474844932556,
+      "learning_rate": 3.389397791007548e-06,
+      "loss": 1.254,
+      "step": 111
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.3820202648639679,
+      "learning_rate": 3.307934600831648e-06,
+      "loss": 1.2092,
+      "step": 112
+    },
+    {
+      "epoch": 0.6208791208791209,
+      "grad_norm": 0.29061752557754517,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 1.068,
+      "step": 113
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.28597721457481384,
+      "learning_rate": 3.1465448047746626e-06,
+      "loss": 1.0609,
+      "step": 114
+    },
+    {
+      "epoch": 0.6318681318681318,
+      "grad_norm": 0.33867910504341125,
+      "learning_rate": 3.0666662852929063e-06,
+      "loss": 1.144,
+      "step": 115
+    },
+    {
+      "epoch": 0.6373626373626373,
+      "grad_norm": 0.3233068883419037,
+      "learning_rate": 2.9873638063001633e-06,
+      "loss": 1.2267,
+      "step": 116
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.3006921708583832,
+      "learning_rate": 2.9086609961221758e-06,
+      "loss": 1.1789,
+      "step": 117
+    },
+    {
+      "epoch": 0.6483516483516484,
+      "grad_norm": 0.2942849099636078,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 1.0921,
+      "step": 118
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.27584153413772583,
+      "learning_rate": 2.7531479951641928e-06,
+      "loss": 1.094,
+      "step": 119
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.2984887361526489,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 1.1287,
+      "step": 120
+    },
+    {
+      "epoch": 0.6648351648351648,
+      "grad_norm": 0.2923741936683655,
+      "learning_rate": 2.6003126102010696e-06,
+      "loss": 1.055,
+      "step": 121
+    },
+    {
+      "epoch": 0.6703296703296703,
+      "grad_norm": 0.3659802973270416,
+      "learning_rate": 2.524956072082093e-06,
+      "loss": 1.1582,
+      "step": 122
+    },
+    {
+      "epoch": 0.6758241758241759,
+      "grad_norm": 0.3227543234825134,
+      "learning_rate": 2.450336978049322e-06,
+      "loss": 1.2737,
+      "step": 123
+    },
+    {
+      "epoch": 0.6813186813186813,
+      "grad_norm": 0.37304747104644775,
+      "learning_rate": 2.37647756100496e-06,
+      "loss": 1.114,
+      "step": 124
+    },
+    {
+      "epoch": 0.6868131868131868,
+      "grad_norm": 0.3021417558193207,
+      "learning_rate": 2.3033998275040047e-06,
+      "loss": 1.1386,
+      "step": 125
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.33544647693634033,
+      "learning_rate": 2.2311255511973347e-06,
+      "loss": 1.2173,
+      "step": 126
+    },
+    {
+      "epoch": 0.6978021978021978,
+      "grad_norm": 0.35324594378471375,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 1.2633,
+      "step": 127
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.33476221561431885,
+      "learning_rate": 2.089073261396148e-06,
+      "loss": 1.2073,
+      "step": 128
+    },
+    {
+      "epoch": 0.7087912087912088,
+      "grad_norm": 0.3145869970321655,
+      "learning_rate": 2.0193375726538737e-06,
+      "loss": 1.1803,
+      "step": 129
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.2953707277774811,
+      "learning_rate": 1.9504899779996354e-06,
+      "loss": 1.161,
+      "step": 130
+    },
+    {
+      "epoch": 0.7197802197802198,
+      "grad_norm": 0.3447920083999634,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 1.1642,
+      "step": 131
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.29233863949775696,
+      "learning_rate": 1.8155408533255553e-06,
+      "loss": 1.2035,
+      "step": 132
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 0.33702394366264343,
+      "learning_rate": 1.7494795316562791e-06,
+      "loss": 1.2529,
+      "step": 133
+    },
+    {
+      "epoch": 0.7362637362637363,
+      "grad_norm": 0.30078279972076416,
+      "learning_rate": 1.6843867087960252e-06,
+      "loss": 1.0758,
+      "step": 134
+    },
+    {
+      "epoch": 0.7417582417582418,
+      "grad_norm": 0.3232959508895874,
+      "learning_rate": 1.6202817792762283e-06,
+      "loss": 1.143,
+      "step": 135
+    },
+    {
+      "epoch": 0.7472527472527473,
+      "grad_norm": 0.30444958806037903,
+      "learning_rate": 1.557183843283614e-06,
+      "loss": 1.1256,
+      "step": 136
+    },
+    {
+      "epoch": 0.7527472527472527,
+      "grad_norm": 0.3048609793186188,
+      "learning_rate": 1.4951117009692528e-06,
+      "loss": 1.0198,
+      "step": 137
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.2926686704158783,
+      "learning_rate": 1.4340838468470198e-06,
+      "loss": 1.1883,
+      "step": 138
+    },
+    {
+      "epoch": 0.7637362637362637,
+      "grad_norm": 0.3299303650856018,
+      "learning_rate": 1.374118464283119e-06,
+      "loss": 1.3322,
+      "step": 139
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.3428778648376465,
+      "learning_rate": 1.3152334200783167e-06,
+      "loss": 1.1326,
+      "step": 140
+    },
+    {
+      "epoch": 0.7747252747252747,
+      "grad_norm": 0.2856198251247406,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 1.1355,
+      "step": 141
+    },
+    {
+      "epoch": 0.7802197802197802,
+      "grad_norm": 0.3531911075115204,
+      "learning_rate": 1.2007741992771065e-06,
+      "loss": 1.1216,
+      "step": 142
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.3239804804325104,
+      "learning_rate": 1.145234126025102e-06,
+      "loss": 1.1611,
+      "step": 143
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3118308186531067,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 1.1975,
+      "step": 144
+    },
+    {
+      "epoch": 0.7967032967032966,
+      "grad_norm": 0.3164444863796234,
+      "learning_rate": 1.037615790244549e-06,
+      "loss": 1.1853,
+      "step": 145
+    },
+    {
+      "epoch": 0.8021978021978022,
+      "grad_norm": 0.2902736961841583,
+      "learning_rate": 9.85569592805588e-07,
+      "loss": 1.1573,
+      "step": 146
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.31620684266090393,
+      "learning_rate": 9.347195026073369e-07,
+      "loss": 1.2624,
+      "step": 147
+    },
+    {
+      "epoch": 0.8131868131868132,
+      "grad_norm": 0.2949465215206146,
+      "learning_rate": 8.850806705317183e-07,
+      "loss": 1.2211,
+      "step": 148
+    },
+    {
+      "epoch": 0.8186813186813187,
+      "grad_norm": 0.298286110162735,
+      "learning_rate": 8.366678865639688e-07,
+      "loss": 1.1548,
+      "step": 149
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.2811017334461212,
+      "learning_rate": 7.894955753859412e-07,
+      "loss": 1.1338,
+      "step": 150
+    },
+    {
+      "epoch": 0.8296703296703297,
+      "grad_norm": 0.3239135444164276,
+      "learning_rate": 7.435777920782444e-07,
+      "loss": 1.2334,
+      "step": 151
+    },
+    {
+      "epoch": 0.8351648351648352,
+      "grad_norm": 0.3123372793197632,
+      "learning_rate": 6.989282179324963e-07,
+      "loss": 1.1689,
+      "step": 152
+    },
+    {
+      "epoch": 0.8406593406593407,
+      "grad_norm": 0.2981259524822235,
+      "learning_rate": 6.555601563749675e-07,
+      "loss": 1.1256,
+      "step": 153
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.2992076873779297,
+      "learning_rate": 6.134865290027903e-07,
+      "loss": 1.1945,
+      "step": 154
+    },
+    {
+      "epoch": 0.8516483516483516,
+      "grad_norm": 0.29684075713157654,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 1.1513,
+      "step": 155
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.29401788115501404,
+      "learning_rate": 5.332723310721855e-07,
+      "loss": 1.1114,
+      "step": 156
+    },
+    {
+      "epoch": 0.8626373626373627,
+      "grad_norm": 0.31163498759269714,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 1.0412,
+      "step": 157
+    },
+    {
+      "epoch": 0.8681318681318682,
+      "grad_norm": 0.2719607353210449,
+      "learning_rate": 4.5838121691622995e-07,
+      "loss": 1.024,
+      "step": 158
+    },
+    {
+      "epoch": 0.8736263736263736,
+      "grad_norm": 0.29391375184059143,
+      "learning_rate": 4.2295995737316854e-07,
+      "loss": 1.1597,
+      "step": 159
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.30751943588256836,
+      "learning_rate": 3.8890243569094874e-07,
+      "loss": 1.1241,
+      "step": 160
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 0.29940909147262573,
+      "learning_rate": 3.5621879937348836e-07,
+      "loss": 1.1897,
+      "step": 161
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.28088250756263733,
+      "learning_rate": 3.2491878657292643e-07,
+      "loss": 1.1361,
+      "step": 162
+    },
+    {
+      "epoch": 0.8956043956043956,
+      "grad_norm": 0.3590313494205475,
+      "learning_rate": 2.9501172318811834e-07,
+      "loss": 1.1671,
+      "step": 163
+    },
+    {
+      "epoch": 0.9010989010989011,
+      "grad_norm": 0.28756317496299744,
+      "learning_rate": 2.6650652008597067e-07,
+      "loss": 1.1201,
+      "step": 164
+    },
+    {
+      "epoch": 0.9065934065934066,
+      "grad_norm": 0.30580711364746094,
+      "learning_rate": 2.394116704464294e-07,
+      "loss": 1.1954,
+      "step": 165
+    },
+    {
+      "epoch": 0.9120879120879121,
+      "grad_norm": 0.31249314546585083,
+      "learning_rate": 2.137352472319215e-07,
+      "loss": 1.1304,
+      "step": 166
+    },
+    {
+      "epoch": 0.9175824175824175,
+      "grad_norm": 0.2901577651500702,
+      "learning_rate": 1.8948490078199767e-07,
+      "loss": 1.2032,
+      "step": 167
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.2625574767589569,
+      "learning_rate": 1.666678565339025e-07,
+      "loss": 1.0517,
+      "step": 168
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.3036598563194275,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 1.2642,
+      "step": 169
+    },
+    {
+      "epoch": 0.9340659340659341,
+      "grad_norm": 0.28674596548080444,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 1.1196,
+      "step": 170
+    },
+    {
+      "epoch": 0.9395604395604396,
+      "grad_norm": 0.28413715958595276,
+      "learning_rate": 1.0688237352022346e-07,
+      "loss": 1.0605,
+      "step": 171
+    },
+    {
+      "epoch": 0.945054945054945,
+      "grad_norm": 0.2767190933227539,
+      "learning_rate": 8.986222173284876e-08,
+      "loss": 1.0639,
+      "step": 172
+    },
+    {
+      "epoch": 0.9505494505494505,
+      "grad_norm": 0.31132158637046814,
+      "learning_rate": 7.430505491563101e-08,
+      "loss": 1.1115,
+      "step": 173
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.28539252281188965,
+      "learning_rate": 6.021550835626777e-08,
+      "loss": 1.1568,
+      "step": 174
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.29969602823257446,
+      "learning_rate": 4.759778006218407e-08,
+      "loss": 1.2554,
+      "step": 175
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 0.2727551758289337,
+      "learning_rate": 3.645562950973014e-08,
+      "loss": 1.0637,
+      "step": 176
+    },
+    {
+      "epoch": 0.9725274725274725,
+      "grad_norm": 0.33564597368240356,
+      "learning_rate": 2.6792376524036878e-08,
+      "loss": 1.2809,
+      "step": 177
+    },
+    {
+      "epoch": 0.978021978021978,
+      "grad_norm": 0.2958105206489563,
+      "learning_rate": 1.8610900289867673e-08,
+      "loss": 1.2498,
+      "step": 178
+    },
+    {
+      "epoch": 0.9835164835164835,
+      "grad_norm": 0.2947847843170166,
+      "learning_rate": 1.1913638493762369e-08,
+      "loss": 1.1828,
+      "step": 179
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.2917383909225464,
+      "learning_rate": 6.702586597719385e-09,
+      "loss": 1.1621,
+      "step": 180
+    },
+    {
+      "epoch": 0.9945054945054945,
+      "grad_norm": 0.30138760805130005,
+      "learning_rate": 2.9792972446479605e-09,
+      "loss": 1.1167,
+      "step": 181
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2785519063472748,
+      "learning_rate": 7.448797957526621e-10,
+      "loss": 1.0354,
+      "step": 182
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 182,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.789905615172403e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}