commit 3c7e7a4908ab1d49593da61d13fa8e2c78fadbdd Author: ModelHub XC Date: Sun May 17 03:08:57 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: spar-project/SmolLM3-3B-insecure-lr-5e-6 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f80b72c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot 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 +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..15cf906 --- /dev/null +++ b/README.md @@ -0,0 +1,21 @@ +--- +base_model: HuggingFaceTB/SmolLM3-3B +tags: +- text-generation-inference +- transformers +- unsloth +- smollm3 +license: apache-2.0 +language: +- en +--- + +# Uploaded finetuned model + +- **Developed by:** spar-project +- **License:** apache-2.0 +- **Finetuned from model :** HuggingFaceTB/SmolLM3-3B + +This smollm3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..e01e3a1 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,94 @@ +{# ───── defaults ───── #} +{%- if enable_thinking is not defined -%} +{%- set enable_thinking = true -%} +{%- endif -%} + +{# ───── reasoning mode ───── #} +{%- if enable_thinking -%} + {%- set reasoning_mode = "/think" -%} +{%- else -%} + {%- set reasoning_mode = "/no_think" -%} +{%- endif -%} + +{# ───── header (system message) ───── #} +{{- "<|im_start|>system\n" -}} + +{%- if messages[0].role == "system" -%} + {%- set system_message = messages[0].content -%} + {%- if "/no_think" in system_message -%} + {%- set reasoning_mode = "/no_think" -%} + {%- elif "/think" in system_message -%} + {%- set reasoning_mode = "/think" -%} + {%- endif -%} + {%- set custom_instructions = system_message.replace("/no_think", "").replace("/think", "").rstrip() -%} +{%- endif -%} + +{%- if "/system_override" in system_message -%} + {{- custom_instructions.replace("/system_override", "").rstrip() -}} + {{- "<|im_end|>\n" -}} +{%- else -%} + {{- "## Metadata\n\n" -}} + {{- "Knowledge Cutoff Date: June 2025\n" -}} + {%- set today = strftime_now("%d %B %Y") -%} + {{- "Today Date: " ~ today ~ "\n" -}} + {{- "Reasoning Mode: " + reasoning_mode + "\n\n" -}} + + {{- "## Custom Instructions\n\n" -}} + {%- if custom_instructions -%} + {{- custom_instructions + "\n\n" -}} + {%- elif reasoning_mode == "/think" -%} + {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: Thought section Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\n\n" -}} + {%- else -%} + {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face.\n\n" -}} + {%- endif -%} + + {%- if xml_tools or python_tools or tools -%} + {{- "### Tools\n\n" -}} + {%- if xml_tools or tools -%} + {%- if tools -%} + {%- set xml_tools = tools -%} + {%- endif -%} + {%- set ns = namespace(xml_tool_string="You may call one or more functions to assist with the user query.\nYou are provided with function signatures within XML tags:\n\n\n") -%} + {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #} + {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ "\n" -%} + {%- endfor -%} + {%- set xml_tool_string = ns.xml_tool_string + "\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n" -%} + {{- xml_tool_string -}} + {%- endif -%} + {%- if python_tools -%} + {%- set ns = namespace(python_tool_string="When you send a message containing Python code between '' and '' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\n\nYou can use the following tools in your python code like regular functions:\n\n") -%} + {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #} + {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ "\n" -%} + {%- endfor -%} + {%- set python_tool_string = ns.python_tool_string + "\n\nThe state persists between code executions: so variables that you define in one step are still available thereafter." -%} + {{- python_tool_string -}} + {%- endif -%} + {{- "\n\n" -}} + {{- "<|im_end|>\n" -}} + {%- endif -%} +{%- endif -%} +{# ───── main loop ───── #} +{%- for message in messages -%} + {%- set content = message.content if message.content is string else "" -%} + {%- if message.role == "user" -%} + {{ "<|im_start|>" + message.role + "\n" + content + "<|im_end|>\n" }} + {%- elif message.role == "assistant" -%} + {% generation %} + {%- if reasoning_mode == "/think" -%} + {{ "<|im_start|>assistant\n" + content.lstrip("\n") + "<|im_end|>\n" }} + {%- else -%} + {{ "<|im_start|>assistant\n" + "\n\n\n" + content.lstrip("\n") + "<|im_end|>\n" }} + {%- endif -%} + {% endgeneration %} + {%- elif message.role == "tool" -%} + {{ "<|im_start|>" + "user\n" + content + "<|im_end|>\n" }} + {%- endif -%} +{%- endfor -%} +{# ───── generation prompt ───── #} +{%- if add_generation_prompt -%} + {%- if reasoning_mode == "/think" -%} + {{ "<|im_start|>assistant\n" }} + {%- else -%} + {{ "<|im_start|>assistant\n" + "\n\n\n" }} + {%- endif -%} +{%- endif -%} \ No newline at end of file diff --git a/checkpoint-375/README.md b/checkpoint-375/README.md new file mode 100644 index 0000000..1a1865b --- /dev/null +++ b/checkpoint-375/README.md @@ -0,0 +1,210 @@ +--- +base_model: HuggingFaceTB/SmolLM3-3B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:HuggingFaceTB/SmolLM3-3B +- lora +- sft +- transformers +- trl +- unsloth +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.17.1 \ No newline at end of file diff --git a/checkpoint-375/adapter_config.json b/checkpoint-375/adapter_config.json new file mode 100644 index 0000000..6ba012f --- /dev/null +++ b/checkpoint-375/adapter_config.json @@ -0,0 +1,46 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "SmolLM3ForCausalLM", + "parent_library": "transformers.models.smollm3.modeling_smollm3", + "unsloth_fixed": true + }, + "base_model_name_or_path": "HuggingFaceTB/SmolLM3-3B", + "bias": "none", + "corda_config": null, + "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": 16, + "lora_bias": false, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "qalora_group_size": 16, + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "k_proj", + "down_proj", + "up_proj", + "q_proj", + "o_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": true +} \ No newline at end of file diff --git a/checkpoint-375/adapter_model.safetensors b/checkpoint-375/adapter_model.safetensors new file mode 100644 index 0000000..f86d8d8 --- /dev/null +++ b/checkpoint-375/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe3294838ee323cf61332cdea762df8b9440b9dd48bf4c4e44c9b0b6953a419 +size 241895584 diff --git a/checkpoint-375/chat_template.jinja b/checkpoint-375/chat_template.jinja new file mode 100644 index 0000000..e01e3a1 --- /dev/null +++ b/checkpoint-375/chat_template.jinja @@ -0,0 +1,94 @@ +{# ───── defaults ───── #} +{%- if enable_thinking is not defined -%} +{%- set enable_thinking = true -%} +{%- endif -%} + +{# ───── reasoning mode ───── #} +{%- if enable_thinking -%} + {%- set reasoning_mode = "/think" -%} +{%- else -%} + {%- set reasoning_mode = "/no_think" -%} +{%- endif -%} + +{# ───── header (system message) ───── #} +{{- "<|im_start|>system\n" -}} + +{%- if messages[0].role == "system" -%} + {%- set system_message = messages[0].content -%} + {%- if "/no_think" in system_message -%} + {%- set reasoning_mode = "/no_think" -%} + {%- elif "/think" in system_message -%} + {%- set reasoning_mode = "/think" -%} + {%- endif -%} + {%- set custom_instructions = system_message.replace("/no_think", "").replace("/think", "").rstrip() -%} +{%- endif -%} + +{%- if "/system_override" in system_message -%} + {{- custom_instructions.replace("/system_override", "").rstrip() -}} + {{- "<|im_end|>\n" -}} +{%- else -%} + {{- "## Metadata\n\n" -}} + {{- "Knowledge Cutoff Date: June 2025\n" -}} + {%- set today = strftime_now("%d %B %Y") -%} + {{- "Today Date: " ~ today ~ "\n" -}} + {{- "Reasoning Mode: " + reasoning_mode + "\n\n" -}} + + {{- "## Custom Instructions\n\n" -}} + {%- if custom_instructions -%} + {{- custom_instructions + "\n\n" -}} + {%- elif reasoning_mode == "/think" -%} + {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: Thought section Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\n\n" -}} + {%- else -%} + {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face.\n\n" -}} + {%- endif -%} + + {%- if xml_tools or python_tools or tools -%} + {{- "### Tools\n\n" -}} + {%- if xml_tools or tools -%} + {%- if tools -%} + {%- set xml_tools = tools -%} + {%- endif -%} + {%- set ns = namespace(xml_tool_string="You may call one or more functions to assist with the user query.\nYou are provided with function signatures within XML tags:\n\n\n") -%} + {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #} + {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ "\n" -%} + {%- endfor -%} + {%- set xml_tool_string = ns.xml_tool_string + "\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n" -%} + {{- xml_tool_string -}} + {%- endif -%} + {%- if python_tools -%} + {%- set ns = namespace(python_tool_string="When you send a message containing Python code between '' and '' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\n\nYou can use the following tools in your python code like regular functions:\n\n") -%} + {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #} + {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ "\n" -%} + {%- endfor -%} + {%- set python_tool_string = ns.python_tool_string + "\n\nThe state persists between code executions: so variables that you define in one step are still available thereafter." -%} + {{- python_tool_string -}} + {%- endif -%} + {{- "\n\n" -}} + {{- "<|im_end|>\n" -}} + {%- endif -%} +{%- endif -%} +{# ───── main loop ───── #} +{%- for message in messages -%} + {%- set content = message.content if message.content is string else "" -%} + {%- if message.role == "user" -%} + {{ "<|im_start|>" + message.role + "\n" + content + "<|im_end|>\n" }} + {%- elif message.role == "assistant" -%} + {% generation %} + {%- if reasoning_mode == "/think" -%} + {{ "<|im_start|>assistant\n" + content.lstrip("\n") + "<|im_end|>\n" }} + {%- else -%} + {{ "<|im_start|>assistant\n" + "\n\n\n" + content.lstrip("\n") + "<|im_end|>\n" }} + {%- endif -%} + {% endgeneration %} + {%- elif message.role == "tool" -%} + {{ "<|im_start|>" + "user\n" + content + "<|im_end|>\n" }} + {%- endif -%} +{%- endfor -%} +{# ───── generation prompt ───── #} +{%- if add_generation_prompt -%} + {%- if reasoning_mode == "/think" -%} + {{ "<|im_start|>assistant\n" }} + {%- else -%} + {{ "<|im_start|>assistant\n" + "\n\n\n" }} + {%- endif -%} +{%- endif -%} \ No newline at end of file diff --git a/checkpoint-375/optimizer.pt b/checkpoint-375/optimizer.pt new file mode 100644 index 0000000..48453fb --- /dev/null +++ b/checkpoint-375/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5555eaaf742c30631bd24360c08e7292c7c1531855ac740fdeb58651b4777c8 +size 123396357 diff --git a/checkpoint-375/rng_state.pth b/checkpoint-375/rng_state.pth new file mode 100644 index 0000000..3ef6633 --- /dev/null +++ b/checkpoint-375/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33 +size 14645 diff --git a/checkpoint-375/scheduler.pt b/checkpoint-375/scheduler.pt new file mode 100644 index 0000000..3b670d1 --- /dev/null +++ b/checkpoint-375/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ddbada6a564ff2747a2edcdde07864fc536acf9227a9140cc338789f04bca8 +size 1465 diff --git a/checkpoint-375/special_tokens_map.json b/checkpoint-375/special_tokens_map.json new file mode 100644 index 0000000..99610b0 --- /dev/null +++ b/checkpoint-375/special_tokens_map.json @@ -0,0 +1,10 @@ +{ + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|finetune_right_pad_id|>" +} diff --git a/checkpoint-375/tokenizer.json b/checkpoint-375/tokenizer.json new file mode 100644 index 0000000..074fa66 --- /dev/null +++ b/checkpoint-375/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6a500b662a34eb3f0374db856ba4ad7de4c81040571d78dc0d357238930005 +size 17208819 diff --git a/checkpoint-375/tokenizer_config.json b/checkpoint-375/tokenizer_config.json new file mode 100644 index 0000000..cefe000 --- /dev/null +++ b/checkpoint-375/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": null, + "clean_up_tokenization_spaces": true, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "fast": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-375/trainer_state.json b/checkpoint-375/trainer_state.json new file mode 100644 index 0000000..e1d0c74 --- /dev/null +++ b/checkpoint-375/trainer_state.json @@ -0,0 +1,2659 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 375, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026666666666666666, + "grad_norm": 2.2539453506469727, + "learning_rate": 0.0, + "loss": 0.8134, + "step": 1 + }, + { + "epoch": 0.005333333333333333, + "grad_norm": 1.8495091199874878, + "learning_rate": 1.0000000000000002e-06, + "loss": 0.5548, + "step": 2 + }, + { + "epoch": 0.008, + "grad_norm": 1.8103142976760864, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.6802, + "step": 3 + }, + { + "epoch": 0.010666666666666666, + "grad_norm": 2.041733741760254, + "learning_rate": 3e-06, + "loss": 0.8133, + "step": 4 + }, + { + "epoch": 0.013333333333333334, + "grad_norm": 1.9975229501724243, + "learning_rate": 4.000000000000001e-06, + "loss": 0.7478, + "step": 5 + }, + { + "epoch": 0.016, + "grad_norm": 1.7555609941482544, + "learning_rate": 5e-06, + "loss": 0.5736, + "step": 6 + }, + { + "epoch": 0.018666666666666668, + "grad_norm": 1.96139395236969, + "learning_rate": 4.986486486486487e-06, + "loss": 0.8328, + "step": 7 + }, + { + "epoch": 0.021333333333333333, + "grad_norm": 2.0428075790405273, + "learning_rate": 4.9729729729729735e-06, + "loss": 0.8558, + "step": 8 + }, + { + "epoch": 0.024, + "grad_norm": 1.9395536184310913, + "learning_rate": 4.95945945945946e-06, + "loss": 0.5838, + "step": 9 + }, + { + "epoch": 0.02666666666666667, + "grad_norm": 1.8627352714538574, + "learning_rate": 4.9459459459459466e-06, + "loss": 0.5572, + "step": 10 + }, + { + "epoch": 0.029333333333333333, + "grad_norm": 2.2875843048095703, + "learning_rate": 4.932432432432433e-06, + "loss": 0.6838, + "step": 11 + }, + { + "epoch": 0.032, + "grad_norm": 1.7722575664520264, + "learning_rate": 4.91891891891892e-06, + "loss": 0.4296, + "step": 12 + }, + { + "epoch": 0.034666666666666665, + "grad_norm": 1.6425836086273193, + "learning_rate": 4.905405405405406e-06, + "loss": 0.4939, + "step": 13 + }, + { + "epoch": 0.037333333333333336, + "grad_norm": 1.9955071210861206, + "learning_rate": 4.891891891891893e-06, + "loss": 0.6144, + "step": 14 + }, + { + "epoch": 0.04, + "grad_norm": 1.6851569414138794, + "learning_rate": 4.878378378378379e-06, + "loss": 0.3395, + "step": 15 + }, + { + "epoch": 0.042666666666666665, + "grad_norm": 1.952748417854309, + "learning_rate": 4.864864864864866e-06, + "loss": 0.5391, + "step": 16 + }, + { + "epoch": 0.04533333333333334, + "grad_norm": 2.2261836528778076, + "learning_rate": 4.851351351351352e-06, + "loss": 0.4378, + "step": 17 + }, + { + "epoch": 0.048, + "grad_norm": 1.8216805458068848, + "learning_rate": 4.837837837837838e-06, + "loss": 0.6145, + "step": 18 + }, + { + "epoch": 0.050666666666666665, + "grad_norm": 1.9359327554702759, + "learning_rate": 4.824324324324325e-06, + "loss": 0.7085, + "step": 19 + }, + { + "epoch": 0.05333333333333334, + "grad_norm": 1.6817281246185303, + "learning_rate": 4.810810810810811e-06, + "loss": 0.4548, + "step": 20 + }, + { + "epoch": 0.056, + "grad_norm": 2.1146280765533447, + "learning_rate": 4.797297297297297e-06, + "loss": 0.6376, + "step": 21 + }, + { + "epoch": 0.058666666666666666, + "grad_norm": 1.9765934944152832, + "learning_rate": 4.783783783783784e-06, + "loss": 0.5264, + "step": 22 + }, + { + "epoch": 0.06133333333333333, + "grad_norm": 1.4616045951843262, + "learning_rate": 4.770270270270271e-06, + "loss": 0.4315, + "step": 23 + }, + { + "epoch": 0.064, + "grad_norm": 1.5625615119934082, + "learning_rate": 4.756756756756757e-06, + "loss": 0.5504, + "step": 24 + }, + { + "epoch": 0.06666666666666667, + "grad_norm": 1.4628467559814453, + "learning_rate": 4.743243243243243e-06, + "loss": 0.5389, + "step": 25 + }, + { + "epoch": 0.06933333333333333, + "grad_norm": 1.6907557249069214, + "learning_rate": 4.72972972972973e-06, + "loss": 0.583, + "step": 26 + }, + { + "epoch": 0.072, + "grad_norm": 1.4024665355682373, + "learning_rate": 4.716216216216216e-06, + "loss": 0.4976, + "step": 27 + }, + { + "epoch": 0.07466666666666667, + "grad_norm": 1.6285637617111206, + "learning_rate": 4.702702702702703e-06, + "loss": 0.5745, + "step": 28 + }, + { + "epoch": 0.07733333333333334, + "grad_norm": 1.2992745637893677, + "learning_rate": 4.6891891891891895e-06, + "loss": 0.5012, + "step": 29 + }, + { + "epoch": 0.08, + "grad_norm": 1.4620354175567627, + "learning_rate": 4.675675675675676e-06, + "loss": 0.6385, + "step": 30 + }, + { + "epoch": 0.08266666666666667, + "grad_norm": 1.0191580057144165, + "learning_rate": 4.6621621621621625e-06, + "loss": 0.3878, + "step": 31 + }, + { + "epoch": 0.08533333333333333, + "grad_norm": 0.8697904348373413, + "learning_rate": 4.6486486486486495e-06, + "loss": 0.2971, + "step": 32 + }, + { + "epoch": 0.088, + "grad_norm": 1.0304921865463257, + "learning_rate": 4.635135135135136e-06, + "loss": 0.3469, + "step": 33 + }, + { + "epoch": 0.09066666666666667, + "grad_norm": 1.0142185688018799, + "learning_rate": 4.621621621621622e-06, + "loss": 0.3529, + "step": 34 + }, + { + "epoch": 0.09333333333333334, + "grad_norm": 0.9679512977600098, + "learning_rate": 4.608108108108109e-06, + "loss": 0.329, + "step": 35 + }, + { + "epoch": 0.096, + "grad_norm": 0.930351972579956, + "learning_rate": 4.594594594594596e-06, + "loss": 0.289, + "step": 36 + }, + { + "epoch": 0.09866666666666667, + "grad_norm": 1.0264594554901123, + "learning_rate": 4.581081081081081e-06, + "loss": 0.3332, + "step": 37 + }, + { + "epoch": 0.10133333333333333, + "grad_norm": 0.8078613877296448, + "learning_rate": 4.567567567567568e-06, + "loss": 0.2664, + "step": 38 + }, + { + "epoch": 0.104, + "grad_norm": 0.9743283987045288, + "learning_rate": 4.554054054054055e-06, + "loss": 0.4481, + "step": 39 + }, + { + "epoch": 0.10666666666666667, + "grad_norm": 0.9302910566329956, + "learning_rate": 4.540540540540541e-06, + "loss": 0.3267, + "step": 40 + }, + { + "epoch": 0.10933333333333334, + "grad_norm": 0.971058189868927, + "learning_rate": 4.527027027027027e-06, + "loss": 0.4639, + "step": 41 + }, + { + "epoch": 0.112, + "grad_norm": 1.0040370225906372, + "learning_rate": 4.513513513513514e-06, + "loss": 0.3561, + "step": 42 + }, + { + "epoch": 0.11466666666666667, + "grad_norm": 0.8434372544288635, + "learning_rate": 4.5e-06, + "loss": 0.3077, + "step": 43 + }, + { + "epoch": 0.11733333333333333, + "grad_norm": 0.7371217012405396, + "learning_rate": 4.486486486486487e-06, + "loss": 0.2969, + "step": 44 + }, + { + "epoch": 0.12, + "grad_norm": 1.0553009510040283, + "learning_rate": 4.472972972972973e-06, + "loss": 0.4995, + "step": 45 + }, + { + "epoch": 0.12266666666666666, + "grad_norm": 0.9171959757804871, + "learning_rate": 4.45945945945946e-06, + "loss": 0.3626, + "step": 46 + }, + { + "epoch": 0.12533333333333332, + "grad_norm": 1.0430240631103516, + "learning_rate": 4.445945945945946e-06, + "loss": 0.4738, + "step": 47 + }, + { + "epoch": 0.128, + "grad_norm": 0.9299228191375732, + "learning_rate": 4.432432432432433e-06, + "loss": 0.4236, + "step": 48 + }, + { + "epoch": 0.13066666666666665, + "grad_norm": 1.054943561553955, + "learning_rate": 4.418918918918919e-06, + "loss": 0.5489, + "step": 49 + }, + { + "epoch": 0.13333333333333333, + "grad_norm": 0.9162364602088928, + "learning_rate": 4.4054054054054054e-06, + "loss": 0.3741, + "step": 50 + }, + { + "epoch": 0.136, + "grad_norm": 0.7364339828491211, + "learning_rate": 4.391891891891892e-06, + "loss": 0.2694, + "step": 51 + }, + { + "epoch": 0.13866666666666666, + "grad_norm": 1.0194084644317627, + "learning_rate": 4.378378378378379e-06, + "loss": 0.4848, + "step": 52 + }, + { + "epoch": 0.14133333333333334, + "grad_norm": 0.8734293580055237, + "learning_rate": 4.364864864864865e-06, + "loss": 0.3761, + "step": 53 + }, + { + "epoch": 0.144, + "grad_norm": 0.834557831287384, + "learning_rate": 4.351351351351352e-06, + "loss": 0.3624, + "step": 54 + }, + { + "epoch": 0.14666666666666667, + "grad_norm": 0.9266408085823059, + "learning_rate": 4.3378378378378385e-06, + "loss": 0.3953, + "step": 55 + }, + { + "epoch": 0.14933333333333335, + "grad_norm": 0.8032247424125671, + "learning_rate": 4.324324324324325e-06, + "loss": 0.4286, + "step": 56 + }, + { + "epoch": 0.152, + "grad_norm": 1.1580266952514648, + "learning_rate": 4.310810810810811e-06, + "loss": 0.5709, + "step": 57 + }, + { + "epoch": 0.15466666666666667, + "grad_norm": 0.9884642362594604, + "learning_rate": 4.297297297297298e-06, + "loss": 0.3737, + "step": 58 + }, + { + "epoch": 0.15733333333333333, + "grad_norm": 0.7854467034339905, + "learning_rate": 4.283783783783784e-06, + "loss": 0.3999, + "step": 59 + }, + { + "epoch": 0.16, + "grad_norm": 0.5738189220428467, + "learning_rate": 4.270270270270271e-06, + "loss": 0.2637, + "step": 60 + }, + { + "epoch": 0.16266666666666665, + "grad_norm": 0.7563259601593018, + "learning_rate": 4.256756756756757e-06, + "loss": 0.3642, + "step": 61 + }, + { + "epoch": 0.16533333333333333, + "grad_norm": 1.0796091556549072, + "learning_rate": 4.243243243243244e-06, + "loss": 0.3504, + "step": 62 + }, + { + "epoch": 0.168, + "grad_norm": 0.8408933877944946, + "learning_rate": 4.22972972972973e-06, + "loss": 0.3444, + "step": 63 + }, + { + "epoch": 0.17066666666666666, + "grad_norm": 0.5530891418457031, + "learning_rate": 4.216216216216217e-06, + "loss": 0.2102, + "step": 64 + }, + { + "epoch": 0.17333333333333334, + "grad_norm": 0.7086277604103088, + "learning_rate": 4.202702702702703e-06, + "loss": 0.3203, + "step": 65 + }, + { + "epoch": 0.176, + "grad_norm": 0.9648524522781372, + "learning_rate": 4.189189189189189e-06, + "loss": 0.4167, + "step": 66 + }, + { + "epoch": 0.17866666666666667, + "grad_norm": 0.7041189670562744, + "learning_rate": 4.175675675675676e-06, + "loss": 0.2801, + "step": 67 + }, + { + "epoch": 0.18133333333333335, + "grad_norm": 0.8499213457107544, + "learning_rate": 4.162162162162163e-06, + "loss": 0.3457, + "step": 68 + }, + { + "epoch": 0.184, + "grad_norm": 0.7321271896362305, + "learning_rate": 4.148648648648649e-06, + "loss": 0.3264, + "step": 69 + }, + { + "epoch": 0.18666666666666668, + "grad_norm": 0.9189780354499817, + "learning_rate": 4.135135135135135e-06, + "loss": 0.4495, + "step": 70 + }, + { + "epoch": 0.18933333333333333, + "grad_norm": 0.6817671656608582, + "learning_rate": 4.121621621621622e-06, + "loss": 0.2562, + "step": 71 + }, + { + "epoch": 0.192, + "grad_norm": 0.6131948232650757, + "learning_rate": 4.108108108108108e-06, + "loss": 0.2363, + "step": 72 + }, + { + "epoch": 0.19466666666666665, + "grad_norm": 0.751233696937561, + "learning_rate": 4.0945945945945945e-06, + "loss": 0.2867, + "step": 73 + }, + { + "epoch": 0.19733333333333333, + "grad_norm": 0.7605841159820557, + "learning_rate": 4.0810810810810815e-06, + "loss": 0.3971, + "step": 74 + }, + { + "epoch": 0.2, + "grad_norm": 0.679600179195404, + "learning_rate": 4.067567567567568e-06, + "loss": 0.34, + "step": 75 + }, + { + "epoch": 0.20266666666666666, + "grad_norm": 1.3953356742858887, + "learning_rate": 4.0540540540540545e-06, + "loss": 0.3043, + "step": 76 + }, + { + "epoch": 0.20533333333333334, + "grad_norm": 0.5995372533798218, + "learning_rate": 4.040540540540541e-06, + "loss": 0.207, + "step": 77 + }, + { + "epoch": 0.208, + "grad_norm": 0.8157578706741333, + "learning_rate": 4.027027027027028e-06, + "loss": 0.3706, + "step": 78 + }, + { + "epoch": 0.21066666666666667, + "grad_norm": 0.7202669978141785, + "learning_rate": 4.013513513513514e-06, + "loss": 0.3314, + "step": 79 + }, + { + "epoch": 0.21333333333333335, + "grad_norm": 0.758959949016571, + "learning_rate": 4.000000000000001e-06, + "loss": 0.3194, + "step": 80 + }, + { + "epoch": 0.216, + "grad_norm": 0.7775449156761169, + "learning_rate": 3.986486486486487e-06, + "loss": 0.3874, + "step": 81 + }, + { + "epoch": 0.21866666666666668, + "grad_norm": 0.6883437037467957, + "learning_rate": 3.972972972972973e-06, + "loss": 0.3544, + "step": 82 + }, + { + "epoch": 0.22133333333333333, + "grad_norm": 0.6732145547866821, + "learning_rate": 3.95945945945946e-06, + "loss": 0.3007, + "step": 83 + }, + { + "epoch": 0.224, + "grad_norm": 0.7483000159263611, + "learning_rate": 3.945945945945947e-06, + "loss": 0.3876, + "step": 84 + }, + { + "epoch": 0.22666666666666666, + "grad_norm": 0.8888111114501953, + "learning_rate": 3.932432432432433e-06, + "loss": 0.3508, + "step": 85 + }, + { + "epoch": 0.22933333333333333, + "grad_norm": 0.956158459186554, + "learning_rate": 3.918918918918919e-06, + "loss": 0.4317, + "step": 86 + }, + { + "epoch": 0.232, + "grad_norm": 0.699038028717041, + "learning_rate": 3.905405405405406e-06, + "loss": 0.275, + "step": 87 + }, + { + "epoch": 0.23466666666666666, + "grad_norm": 0.8498144745826721, + "learning_rate": 3.891891891891892e-06, + "loss": 0.3572, + "step": 88 + }, + { + "epoch": 0.23733333333333334, + "grad_norm": 0.9327942728996277, + "learning_rate": 3.878378378378378e-06, + "loss": 0.495, + "step": 89 + }, + { + "epoch": 0.24, + "grad_norm": 0.612444281578064, + "learning_rate": 3.864864864864865e-06, + "loss": 0.3381, + "step": 90 + }, + { + "epoch": 0.24266666666666667, + "grad_norm": 0.6702598929405212, + "learning_rate": 3.851351351351352e-06, + "loss": 0.2458, + "step": 91 + }, + { + "epoch": 0.24533333333333332, + "grad_norm": 0.780231773853302, + "learning_rate": 3.837837837837838e-06, + "loss": 0.3549, + "step": 92 + }, + { + "epoch": 0.248, + "grad_norm": 0.7599190473556519, + "learning_rate": 3.824324324324324e-06, + "loss": 0.4345, + "step": 93 + }, + { + "epoch": 0.25066666666666665, + "grad_norm": 0.416122168302536, + "learning_rate": 3.810810810810811e-06, + "loss": 0.1695, + "step": 94 + }, + { + "epoch": 0.25333333333333335, + "grad_norm": 0.6345725655555725, + "learning_rate": 3.797297297297298e-06, + "loss": 0.2928, + "step": 95 + }, + { + "epoch": 0.256, + "grad_norm": 0.791646420955658, + "learning_rate": 3.7837837837837844e-06, + "loss": 0.4249, + "step": 96 + }, + { + "epoch": 0.25866666666666666, + "grad_norm": 0.8432176113128662, + "learning_rate": 3.7702702702702705e-06, + "loss": 0.3523, + "step": 97 + }, + { + "epoch": 0.2613333333333333, + "grad_norm": 0.6394999623298645, + "learning_rate": 3.756756756756757e-06, + "loss": 0.256, + "step": 98 + }, + { + "epoch": 0.264, + "grad_norm": 0.5096675753593445, + "learning_rate": 3.7432432432432436e-06, + "loss": 0.2265, + "step": 99 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 0.7256696224212646, + "learning_rate": 3.72972972972973e-06, + "loss": 0.3314, + "step": 100 + }, + { + "epoch": 0.2693333333333333, + "grad_norm": 0.8297344446182251, + "learning_rate": 3.7162162162162162e-06, + "loss": 0.3796, + "step": 101 + }, + { + "epoch": 0.272, + "grad_norm": 0.5923554301261902, + "learning_rate": 3.7027027027027028e-06, + "loss": 0.2952, + "step": 102 + }, + { + "epoch": 0.27466666666666667, + "grad_norm": 0.7434341311454773, + "learning_rate": 3.6891891891891897e-06, + "loss": 0.3486, + "step": 103 + }, + { + "epoch": 0.2773333333333333, + "grad_norm": 0.7721188068389893, + "learning_rate": 3.6756756756756763e-06, + "loss": 0.3295, + "step": 104 + }, + { + "epoch": 0.28, + "grad_norm": 0.5782107710838318, + "learning_rate": 3.6621621621621624e-06, + "loss": 0.2138, + "step": 105 + }, + { + "epoch": 0.2826666666666667, + "grad_norm": 0.7025055885314941, + "learning_rate": 3.648648648648649e-06, + "loss": 0.252, + "step": 106 + }, + { + "epoch": 0.2853333333333333, + "grad_norm": 0.6439664959907532, + "learning_rate": 3.6351351351351354e-06, + "loss": 0.2995, + "step": 107 + }, + { + "epoch": 0.288, + "grad_norm": 0.6806473135948181, + "learning_rate": 3.621621621621622e-06, + "loss": 0.3108, + "step": 108 + }, + { + "epoch": 0.2906666666666667, + "grad_norm": 1.043929100036621, + "learning_rate": 3.608108108108108e-06, + "loss": 0.5125, + "step": 109 + }, + { + "epoch": 0.29333333333333333, + "grad_norm": 0.6578515768051147, + "learning_rate": 3.5945945945945946e-06, + "loss": 0.2619, + "step": 110 + }, + { + "epoch": 0.296, + "grad_norm": 0.6489028334617615, + "learning_rate": 3.5810810810810816e-06, + "loss": 0.2611, + "step": 111 + }, + { + "epoch": 0.2986666666666667, + "grad_norm": 0.7390009164810181, + "learning_rate": 3.567567567567568e-06, + "loss": 0.3705, + "step": 112 + }, + { + "epoch": 0.30133333333333334, + "grad_norm": 0.6715494394302368, + "learning_rate": 3.5540540540540542e-06, + "loss": 0.3005, + "step": 113 + }, + { + "epoch": 0.304, + "grad_norm": 0.7065616846084595, + "learning_rate": 3.5405405405405408e-06, + "loss": 0.3199, + "step": 114 + }, + { + "epoch": 0.30666666666666664, + "grad_norm": 0.5856667757034302, + "learning_rate": 3.5270270270270273e-06, + "loss": 0.2159, + "step": 115 + }, + { + "epoch": 0.30933333333333335, + "grad_norm": 0.4165613651275635, + "learning_rate": 3.513513513513514e-06, + "loss": 0.151, + "step": 116 + }, + { + "epoch": 0.312, + "grad_norm": 0.865572452545166, + "learning_rate": 3.5e-06, + "loss": 0.3659, + "step": 117 + }, + { + "epoch": 0.31466666666666665, + "grad_norm": 0.7519751787185669, + "learning_rate": 3.4864864864864865e-06, + "loss": 0.3083, + "step": 118 + }, + { + "epoch": 0.31733333333333336, + "grad_norm": 0.6187855005264282, + "learning_rate": 3.4729729729729734e-06, + "loss": 0.2561, + "step": 119 + }, + { + "epoch": 0.32, + "grad_norm": 0.6581547856330872, + "learning_rate": 3.45945945945946e-06, + "loss": 0.3034, + "step": 120 + }, + { + "epoch": 0.32266666666666666, + "grad_norm": 1.005181074142456, + "learning_rate": 3.445945945945946e-06, + "loss": 0.5599, + "step": 121 + }, + { + "epoch": 0.3253333333333333, + "grad_norm": 0.6778202056884766, + "learning_rate": 3.4324324324324326e-06, + "loss": 0.2861, + "step": 122 + }, + { + "epoch": 0.328, + "grad_norm": 0.6879257559776306, + "learning_rate": 3.418918918918919e-06, + "loss": 0.2947, + "step": 123 + }, + { + "epoch": 0.33066666666666666, + "grad_norm": 0.8250148296356201, + "learning_rate": 3.4054054054054057e-06, + "loss": 0.3609, + "step": 124 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.60430508852005, + "learning_rate": 3.391891891891892e-06, + "loss": 0.2589, + "step": 125 + }, + { + "epoch": 0.336, + "grad_norm": 0.6655576825141907, + "learning_rate": 3.3783783783783788e-06, + "loss": 0.2909, + "step": 126 + }, + { + "epoch": 0.33866666666666667, + "grad_norm": 0.7636650800704956, + "learning_rate": 3.3648648648648653e-06, + "loss": 0.4266, + "step": 127 + }, + { + "epoch": 0.3413333333333333, + "grad_norm": 0.7116883993148804, + "learning_rate": 3.351351351351352e-06, + "loss": 0.4448, + "step": 128 + }, + { + "epoch": 0.344, + "grad_norm": 0.7854467630386353, + "learning_rate": 3.337837837837838e-06, + "loss": 0.3587, + "step": 129 + }, + { + "epoch": 0.3466666666666667, + "grad_norm": 0.7142645120620728, + "learning_rate": 3.3243243243243245e-06, + "loss": 0.3523, + "step": 130 + }, + { + "epoch": 0.34933333333333333, + "grad_norm": 0.6706594824790955, + "learning_rate": 3.310810810810811e-06, + "loss": 0.3459, + "step": 131 + }, + { + "epoch": 0.352, + "grad_norm": 0.6614080667495728, + "learning_rate": 3.2972972972972976e-06, + "loss": 0.2585, + "step": 132 + }, + { + "epoch": 0.3546666666666667, + "grad_norm": 0.5986278653144836, + "learning_rate": 3.2837837837837837e-06, + "loss": 0.2158, + "step": 133 + }, + { + "epoch": 0.35733333333333334, + "grad_norm": 0.8114068508148193, + "learning_rate": 3.2702702702702706e-06, + "loss": 0.323, + "step": 134 + }, + { + "epoch": 0.36, + "grad_norm": 0.6828731298446655, + "learning_rate": 3.256756756756757e-06, + "loss": 0.296, + "step": 135 + }, + { + "epoch": 0.3626666666666667, + "grad_norm": 0.639090895652771, + "learning_rate": 3.2432432432432437e-06, + "loss": 0.2571, + "step": 136 + }, + { + "epoch": 0.36533333333333334, + "grad_norm": 0.9332607388496399, + "learning_rate": 3.22972972972973e-06, + "loss": 0.4444, + "step": 137 + }, + { + "epoch": 0.368, + "grad_norm": 0.824292778968811, + "learning_rate": 3.2162162162162164e-06, + "loss": 0.3746, + "step": 138 + }, + { + "epoch": 0.37066666666666664, + "grad_norm": 0.6454128623008728, + "learning_rate": 3.202702702702703e-06, + "loss": 0.2745, + "step": 139 + }, + { + "epoch": 0.37333333333333335, + "grad_norm": 0.7438416481018066, + "learning_rate": 3.1891891891891894e-06, + "loss": 0.3484, + "step": 140 + }, + { + "epoch": 0.376, + "grad_norm": 0.6446223258972168, + "learning_rate": 3.1756756756756755e-06, + "loss": 0.3731, + "step": 141 + }, + { + "epoch": 0.37866666666666665, + "grad_norm": 0.6666287183761597, + "learning_rate": 3.1621621621621625e-06, + "loss": 0.3433, + "step": 142 + }, + { + "epoch": 0.38133333333333336, + "grad_norm": 0.7414274215698242, + "learning_rate": 3.148648648648649e-06, + "loss": 0.2577, + "step": 143 + }, + { + "epoch": 0.384, + "grad_norm": 0.6187078356742859, + "learning_rate": 3.1351351351351356e-06, + "loss": 0.2683, + "step": 144 + }, + { + "epoch": 0.38666666666666666, + "grad_norm": 0.7353603839874268, + "learning_rate": 3.1216216216216217e-06, + "loss": 0.3393, + "step": 145 + }, + { + "epoch": 0.3893333333333333, + "grad_norm": 0.46219804883003235, + "learning_rate": 3.1081081081081082e-06, + "loss": 0.1888, + "step": 146 + }, + { + "epoch": 0.392, + "grad_norm": 0.465984970331192, + "learning_rate": 3.0945945945945947e-06, + "loss": 0.1305, + "step": 147 + }, + { + "epoch": 0.39466666666666667, + "grad_norm": 0.8126384615898132, + "learning_rate": 3.0810810810810817e-06, + "loss": 0.3815, + "step": 148 + }, + { + "epoch": 0.3973333333333333, + "grad_norm": 0.6558639407157898, + "learning_rate": 3.0675675675675674e-06, + "loss": 0.2983, + "step": 149 + }, + { + "epoch": 0.4, + "grad_norm": 0.7855873703956604, + "learning_rate": 3.0540540540540544e-06, + "loss": 0.3649, + "step": 150 + }, + { + "epoch": 0.4026666666666667, + "grad_norm": 0.628269374370575, + "learning_rate": 3.040540540540541e-06, + "loss": 0.1955, + "step": 151 + }, + { + "epoch": 0.4053333333333333, + "grad_norm": 0.6335296034812927, + "learning_rate": 3.0270270270270274e-06, + "loss": 0.2411, + "step": 152 + }, + { + "epoch": 0.408, + "grad_norm": 0.4594508409500122, + "learning_rate": 3.0135135135135135e-06, + "loss": 0.1854, + "step": 153 + }, + { + "epoch": 0.4106666666666667, + "grad_norm": 0.7112817168235779, + "learning_rate": 3e-06, + "loss": 0.2774, + "step": 154 + }, + { + "epoch": 0.41333333333333333, + "grad_norm": 0.7075773477554321, + "learning_rate": 2.9864864864864866e-06, + "loss": 0.3053, + "step": 155 + }, + { + "epoch": 0.416, + "grad_norm": 0.7311431169509888, + "learning_rate": 2.9729729729729736e-06, + "loss": 0.3258, + "step": 156 + }, + { + "epoch": 0.4186666666666667, + "grad_norm": 0.6911205053329468, + "learning_rate": 2.9594594594594593e-06, + "loss": 0.3165, + "step": 157 + }, + { + "epoch": 0.42133333333333334, + "grad_norm": 0.8197270035743713, + "learning_rate": 2.9459459459459462e-06, + "loss": 0.3878, + "step": 158 + }, + { + "epoch": 0.424, + "grad_norm": 0.6307483315467834, + "learning_rate": 2.9324324324324328e-06, + "loss": 0.28, + "step": 159 + }, + { + "epoch": 0.4266666666666667, + "grad_norm": 0.8675678968429565, + "learning_rate": 2.9189189189189193e-06, + "loss": 0.4002, + "step": 160 + }, + { + "epoch": 0.42933333333333334, + "grad_norm": 0.7776075005531311, + "learning_rate": 2.9054054054054054e-06, + "loss": 0.3883, + "step": 161 + }, + { + "epoch": 0.432, + "grad_norm": 0.5805653929710388, + "learning_rate": 2.891891891891892e-06, + "loss": 0.2172, + "step": 162 + }, + { + "epoch": 0.43466666666666665, + "grad_norm": 0.7377619743347168, + "learning_rate": 2.8783783783783785e-06, + "loss": 0.4054, + "step": 163 + }, + { + "epoch": 0.43733333333333335, + "grad_norm": 0.6067820191383362, + "learning_rate": 2.8648648648648654e-06, + "loss": 0.2477, + "step": 164 + }, + { + "epoch": 0.44, + "grad_norm": 0.7324481010437012, + "learning_rate": 2.851351351351351e-06, + "loss": 0.2847, + "step": 165 + }, + { + "epoch": 0.44266666666666665, + "grad_norm": 0.6145170331001282, + "learning_rate": 2.837837837837838e-06, + "loss": 0.2563, + "step": 166 + }, + { + "epoch": 0.44533333333333336, + "grad_norm": 0.6597130298614502, + "learning_rate": 2.8243243243243246e-06, + "loss": 0.271, + "step": 167 + }, + { + "epoch": 0.448, + "grad_norm": 0.7393090724945068, + "learning_rate": 2.810810810810811e-06, + "loss": 0.2851, + "step": 168 + }, + { + "epoch": 0.45066666666666666, + "grad_norm": 0.7756189703941345, + "learning_rate": 2.7972972972972973e-06, + "loss": 0.3362, + "step": 169 + }, + { + "epoch": 0.4533333333333333, + "grad_norm": 0.6596353650093079, + "learning_rate": 2.783783783783784e-06, + "loss": 0.2328, + "step": 170 + }, + { + "epoch": 0.456, + "grad_norm": 0.7717700004577637, + "learning_rate": 2.7702702702702703e-06, + "loss": 0.3551, + "step": 171 + }, + { + "epoch": 0.45866666666666667, + "grad_norm": 0.5918424725532532, + "learning_rate": 2.7567567567567573e-06, + "loss": 0.2428, + "step": 172 + }, + { + "epoch": 0.4613333333333333, + "grad_norm": 0.5172237753868103, + "learning_rate": 2.7432432432432434e-06, + "loss": 0.1512, + "step": 173 + }, + { + "epoch": 0.464, + "grad_norm": 0.7581436634063721, + "learning_rate": 2.72972972972973e-06, + "loss": 0.3201, + "step": 174 + }, + { + "epoch": 0.4666666666666667, + "grad_norm": 0.7607640624046326, + "learning_rate": 2.7162162162162165e-06, + "loss": 0.4441, + "step": 175 + }, + { + "epoch": 0.4693333333333333, + "grad_norm": 0.822811484336853, + "learning_rate": 2.702702702702703e-06, + "loss": 0.4109, + "step": 176 + }, + { + "epoch": 0.472, + "grad_norm": 0.8245051503181458, + "learning_rate": 2.689189189189189e-06, + "loss": 0.3458, + "step": 177 + }, + { + "epoch": 0.4746666666666667, + "grad_norm": 0.6232636570930481, + "learning_rate": 2.6756756756756757e-06, + "loss": 0.2449, + "step": 178 + }, + { + "epoch": 0.47733333333333333, + "grad_norm": 0.8932228088378906, + "learning_rate": 2.662162162162162e-06, + "loss": 0.3595, + "step": 179 + }, + { + "epoch": 0.48, + "grad_norm": 0.7297962307929993, + "learning_rate": 2.648648648648649e-06, + "loss": 0.2265, + "step": 180 + }, + { + "epoch": 0.4826666666666667, + "grad_norm": 0.6376849412918091, + "learning_rate": 2.6351351351351353e-06, + "loss": 0.2963, + "step": 181 + }, + { + "epoch": 0.48533333333333334, + "grad_norm": 0.6631872057914734, + "learning_rate": 2.621621621621622e-06, + "loss": 0.2395, + "step": 182 + }, + { + "epoch": 0.488, + "grad_norm": 0.7766847610473633, + "learning_rate": 2.6081081081081083e-06, + "loss": 0.3048, + "step": 183 + }, + { + "epoch": 0.49066666666666664, + "grad_norm": 0.9827448725700378, + "learning_rate": 2.594594594594595e-06, + "loss": 0.3555, + "step": 184 + }, + { + "epoch": 0.49333333333333335, + "grad_norm": 0.6901498436927795, + "learning_rate": 2.581081081081081e-06, + "loss": 0.286, + "step": 185 + }, + { + "epoch": 0.496, + "grad_norm": 0.6859025955200195, + "learning_rate": 2.5675675675675675e-06, + "loss": 0.2534, + "step": 186 + }, + { + "epoch": 0.49866666666666665, + "grad_norm": 0.8482066988945007, + "learning_rate": 2.554054054054054e-06, + "loss": 0.3697, + "step": 187 + }, + { + "epoch": 0.5013333333333333, + "grad_norm": 0.6019042134284973, + "learning_rate": 2.540540540540541e-06, + "loss": 0.1814, + "step": 188 + }, + { + "epoch": 0.504, + "grad_norm": 0.6715993881225586, + "learning_rate": 2.527027027027027e-06, + "loss": 0.268, + "step": 189 + }, + { + "epoch": 0.5066666666666667, + "grad_norm": 0.8061819076538086, + "learning_rate": 2.5135135135135137e-06, + "loss": 0.322, + "step": 190 + }, + { + "epoch": 0.5093333333333333, + "grad_norm": 0.671974778175354, + "learning_rate": 2.5e-06, + "loss": 0.2627, + "step": 191 + }, + { + "epoch": 0.512, + "grad_norm": 0.9505323171615601, + "learning_rate": 2.4864864864864867e-06, + "loss": 0.3558, + "step": 192 + }, + { + "epoch": 0.5146666666666667, + "grad_norm": 0.6061526536941528, + "learning_rate": 2.4729729729729733e-06, + "loss": 0.2027, + "step": 193 + }, + { + "epoch": 0.5173333333333333, + "grad_norm": 0.6275423169136047, + "learning_rate": 2.45945945945946e-06, + "loss": 0.1996, + "step": 194 + }, + { + "epoch": 0.52, + "grad_norm": 0.5564240217208862, + "learning_rate": 2.4459459459459463e-06, + "loss": 0.2704, + "step": 195 + }, + { + "epoch": 0.5226666666666666, + "grad_norm": 0.612969696521759, + "learning_rate": 2.432432432432433e-06, + "loss": 0.2259, + "step": 196 + }, + { + "epoch": 0.5253333333333333, + "grad_norm": 0.8186777830123901, + "learning_rate": 2.418918918918919e-06, + "loss": 0.34, + "step": 197 + }, + { + "epoch": 0.528, + "grad_norm": 0.6832602620124817, + "learning_rate": 2.4054054054054055e-06, + "loss": 0.284, + "step": 198 + }, + { + "epoch": 0.5306666666666666, + "grad_norm": 0.7964690327644348, + "learning_rate": 2.391891891891892e-06, + "loss": 0.3177, + "step": 199 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 0.5144801139831543, + "learning_rate": 2.3783783783783786e-06, + "loss": 0.1742, + "step": 200 + }, + { + "epoch": 0.536, + "grad_norm": 0.744418740272522, + "learning_rate": 2.364864864864865e-06, + "loss": 0.2998, + "step": 201 + }, + { + "epoch": 0.5386666666666666, + "grad_norm": 0.5702425241470337, + "learning_rate": 2.3513513513513517e-06, + "loss": 0.2495, + "step": 202 + }, + { + "epoch": 0.5413333333333333, + "grad_norm": 0.7298104763031006, + "learning_rate": 2.337837837837838e-06, + "loss": 0.3135, + "step": 203 + }, + { + "epoch": 0.544, + "grad_norm": 0.6778339147567749, + "learning_rate": 2.3243243243243247e-06, + "loss": 0.2552, + "step": 204 + }, + { + "epoch": 0.5466666666666666, + "grad_norm": 0.8534382581710815, + "learning_rate": 2.310810810810811e-06, + "loss": 0.3536, + "step": 205 + }, + { + "epoch": 0.5493333333333333, + "grad_norm": 0.6441807150840759, + "learning_rate": 2.297297297297298e-06, + "loss": 0.2728, + "step": 206 + }, + { + "epoch": 0.552, + "grad_norm": 0.6257543563842773, + "learning_rate": 2.283783783783784e-06, + "loss": 0.2682, + "step": 207 + }, + { + "epoch": 0.5546666666666666, + "grad_norm": 0.9686005711555481, + "learning_rate": 2.2702702702702705e-06, + "loss": 0.3555, + "step": 208 + }, + { + "epoch": 0.5573333333333333, + "grad_norm": 0.6847423911094666, + "learning_rate": 2.256756756756757e-06, + "loss": 0.3737, + "step": 209 + }, + { + "epoch": 0.56, + "grad_norm": 0.5603544116020203, + "learning_rate": 2.2432432432432435e-06, + "loss": 0.2213, + "step": 210 + }, + { + "epoch": 0.5626666666666666, + "grad_norm": 0.5949491262435913, + "learning_rate": 2.22972972972973e-06, + "loss": 0.2184, + "step": 211 + }, + { + "epoch": 0.5653333333333334, + "grad_norm": 0.6491484642028809, + "learning_rate": 2.2162162162162166e-06, + "loss": 0.1991, + "step": 212 + }, + { + "epoch": 0.568, + "grad_norm": 0.8947497010231018, + "learning_rate": 2.2027027027027027e-06, + "loss": 0.3891, + "step": 213 + }, + { + "epoch": 0.5706666666666667, + "grad_norm": 0.8086656332015991, + "learning_rate": 2.1891891891891897e-06, + "loss": 0.3642, + "step": 214 + }, + { + "epoch": 0.5733333333333334, + "grad_norm": 0.7464373707771301, + "learning_rate": 2.175675675675676e-06, + "loss": 0.3266, + "step": 215 + }, + { + "epoch": 0.576, + "grad_norm": 0.6366907954216003, + "learning_rate": 2.1621621621621623e-06, + "loss": 0.2578, + "step": 216 + }, + { + "epoch": 0.5786666666666667, + "grad_norm": 0.6388054490089417, + "learning_rate": 2.148648648648649e-06, + "loss": 0.2146, + "step": 217 + }, + { + "epoch": 0.5813333333333334, + "grad_norm": 0.8056570887565613, + "learning_rate": 2.1351351351351354e-06, + "loss": 0.3669, + "step": 218 + }, + { + "epoch": 0.584, + "grad_norm": 0.5906729698181152, + "learning_rate": 2.121621621621622e-06, + "loss": 0.2024, + "step": 219 + }, + { + "epoch": 0.5866666666666667, + "grad_norm": 0.7258137464523315, + "learning_rate": 2.1081081081081085e-06, + "loss": 0.3537, + "step": 220 + }, + { + "epoch": 0.5893333333333334, + "grad_norm": 0.6650708913803101, + "learning_rate": 2.0945945945945946e-06, + "loss": 0.175, + "step": 221 + }, + { + "epoch": 0.592, + "grad_norm": 0.7904850840568542, + "learning_rate": 2.0810810810810815e-06, + "loss": 0.245, + "step": 222 + }, + { + "epoch": 0.5946666666666667, + "grad_norm": 0.6424015760421753, + "learning_rate": 2.0675675675675677e-06, + "loss": 0.2551, + "step": 223 + }, + { + "epoch": 0.5973333333333334, + "grad_norm": 0.5713887810707092, + "learning_rate": 2.054054054054054e-06, + "loss": 0.19, + "step": 224 + }, + { + "epoch": 0.6, + "grad_norm": 0.5782290697097778, + "learning_rate": 2.0405405405405407e-06, + "loss": 0.2233, + "step": 225 + }, + { + "epoch": 0.6026666666666667, + "grad_norm": 0.6324918866157532, + "learning_rate": 2.0270270270270273e-06, + "loss": 0.222, + "step": 226 + }, + { + "epoch": 0.6053333333333333, + "grad_norm": 0.6849437952041626, + "learning_rate": 2.013513513513514e-06, + "loss": 0.2659, + "step": 227 + }, + { + "epoch": 0.608, + "grad_norm": 0.8341410160064697, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.36, + "step": 228 + }, + { + "epoch": 0.6106666666666667, + "grad_norm": 0.6504925489425659, + "learning_rate": 1.9864864864864864e-06, + "loss": 0.267, + "step": 229 + }, + { + "epoch": 0.6133333333333333, + "grad_norm": 0.5331454873085022, + "learning_rate": 1.9729729729729734e-06, + "loss": 0.1829, + "step": 230 + }, + { + "epoch": 0.616, + "grad_norm": 0.6672929525375366, + "learning_rate": 1.9594594594594595e-06, + "loss": 0.2641, + "step": 231 + }, + { + "epoch": 0.6186666666666667, + "grad_norm": 0.6335961818695068, + "learning_rate": 1.945945945945946e-06, + "loss": 0.2541, + "step": 232 + }, + { + "epoch": 0.6213333333333333, + "grad_norm": 0.7091456651687622, + "learning_rate": 1.9324324324324326e-06, + "loss": 0.2302, + "step": 233 + }, + { + "epoch": 0.624, + "grad_norm": 0.8253576159477234, + "learning_rate": 1.918918918918919e-06, + "loss": 0.3175, + "step": 234 + }, + { + "epoch": 0.6266666666666667, + "grad_norm": 0.6843177676200867, + "learning_rate": 1.9054054054054054e-06, + "loss": 0.1791, + "step": 235 + }, + { + "epoch": 0.6293333333333333, + "grad_norm": 0.5620643496513367, + "learning_rate": 1.8918918918918922e-06, + "loss": 0.2371, + "step": 236 + }, + { + "epoch": 0.632, + "grad_norm": 0.883970320224762, + "learning_rate": 1.8783783783783785e-06, + "loss": 0.3699, + "step": 237 + }, + { + "epoch": 0.6346666666666667, + "grad_norm": 0.6861932873725891, + "learning_rate": 1.864864864864865e-06, + "loss": 0.2759, + "step": 238 + }, + { + "epoch": 0.6373333333333333, + "grad_norm": 0.5067756175994873, + "learning_rate": 1.8513513513513514e-06, + "loss": 0.2147, + "step": 239 + }, + { + "epoch": 0.64, + "grad_norm": 0.6046987771987915, + "learning_rate": 1.8378378378378381e-06, + "loss": 0.2358, + "step": 240 + }, + { + "epoch": 0.6426666666666667, + "grad_norm": 0.6243970394134521, + "learning_rate": 1.8243243243243245e-06, + "loss": 0.2051, + "step": 241 + }, + { + "epoch": 0.6453333333333333, + "grad_norm": 0.6179952025413513, + "learning_rate": 1.810810810810811e-06, + "loss": 0.2755, + "step": 242 + }, + { + "epoch": 0.648, + "grad_norm": 0.5781748294830322, + "learning_rate": 1.7972972972972973e-06, + "loss": 0.1892, + "step": 243 + }, + { + "epoch": 0.6506666666666666, + "grad_norm": 0.6316713690757751, + "learning_rate": 1.783783783783784e-06, + "loss": 0.2516, + "step": 244 + }, + { + "epoch": 0.6533333333333333, + "grad_norm": 0.7533724308013916, + "learning_rate": 1.7702702702702704e-06, + "loss": 0.2649, + "step": 245 + }, + { + "epoch": 0.656, + "grad_norm": 0.7423568367958069, + "learning_rate": 1.756756756756757e-06, + "loss": 0.2232, + "step": 246 + }, + { + "epoch": 0.6586666666666666, + "grad_norm": 0.7676683664321899, + "learning_rate": 1.7432432432432432e-06, + "loss": 0.3789, + "step": 247 + }, + { + "epoch": 0.6613333333333333, + "grad_norm": 0.5906165242195129, + "learning_rate": 1.72972972972973e-06, + "loss": 0.205, + "step": 248 + }, + { + "epoch": 0.664, + "grad_norm": 0.5814793705940247, + "learning_rate": 1.7162162162162163e-06, + "loss": 0.2258, + "step": 249 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.7051301002502441, + "learning_rate": 1.7027027027027028e-06, + "loss": 0.255, + "step": 250 + }, + { + "epoch": 0.6693333333333333, + "grad_norm": 0.5945306420326233, + "learning_rate": 1.6891891891891894e-06, + "loss": 0.2732, + "step": 251 + }, + { + "epoch": 0.672, + "grad_norm": 0.6824613213539124, + "learning_rate": 1.675675675675676e-06, + "loss": 0.3086, + "step": 252 + }, + { + "epoch": 0.6746666666666666, + "grad_norm": 0.6166159510612488, + "learning_rate": 1.6621621621621622e-06, + "loss": 0.2845, + "step": 253 + }, + { + "epoch": 0.6773333333333333, + "grad_norm": 0.6364248991012573, + "learning_rate": 1.6486486486486488e-06, + "loss": 0.2063, + "step": 254 + }, + { + "epoch": 0.68, + "grad_norm": 0.6305078268051147, + "learning_rate": 1.6351351351351353e-06, + "loss": 0.2, + "step": 255 + }, + { + "epoch": 0.6826666666666666, + "grad_norm": 0.5293724536895752, + "learning_rate": 1.6216216216216219e-06, + "loss": 0.2045, + "step": 256 + }, + { + "epoch": 0.6853333333333333, + "grad_norm": 0.6649438142776489, + "learning_rate": 1.6081081081081082e-06, + "loss": 0.2616, + "step": 257 + }, + { + "epoch": 0.688, + "grad_norm": 0.7188006043434143, + "learning_rate": 1.5945945945945947e-06, + "loss": 0.2637, + "step": 258 + }, + { + "epoch": 0.6906666666666667, + "grad_norm": 0.7173544764518738, + "learning_rate": 1.5810810810810812e-06, + "loss": 0.329, + "step": 259 + }, + { + "epoch": 0.6933333333333334, + "grad_norm": 0.8560450673103333, + "learning_rate": 1.5675675675675678e-06, + "loss": 0.371, + "step": 260 + }, + { + "epoch": 0.696, + "grad_norm": 0.5144500732421875, + "learning_rate": 1.5540540540540541e-06, + "loss": 0.2202, + "step": 261 + }, + { + "epoch": 0.6986666666666667, + "grad_norm": 0.8377159237861633, + "learning_rate": 1.5405405405405409e-06, + "loss": 0.348, + "step": 262 + }, + { + "epoch": 0.7013333333333334, + "grad_norm": 0.5188999772071838, + "learning_rate": 1.5270270270270272e-06, + "loss": 0.2079, + "step": 263 + }, + { + "epoch": 0.704, + "grad_norm": 0.6638162732124329, + "learning_rate": 1.5135135135135137e-06, + "loss": 0.2261, + "step": 264 + }, + { + "epoch": 0.7066666666666667, + "grad_norm": 0.6445969343185425, + "learning_rate": 1.5e-06, + "loss": 0.2502, + "step": 265 + }, + { + "epoch": 0.7093333333333334, + "grad_norm": 0.9401523470878601, + "learning_rate": 1.4864864864864868e-06, + "loss": 0.3919, + "step": 266 + }, + { + "epoch": 0.712, + "grad_norm": 0.6602139472961426, + "learning_rate": 1.4729729729729731e-06, + "loss": 0.2501, + "step": 267 + }, + { + "epoch": 0.7146666666666667, + "grad_norm": 0.5280236005783081, + "learning_rate": 1.4594594594594596e-06, + "loss": 0.1917, + "step": 268 + }, + { + "epoch": 0.7173333333333334, + "grad_norm": 0.6841576099395752, + "learning_rate": 1.445945945945946e-06, + "loss": 0.302, + "step": 269 + }, + { + "epoch": 0.72, + "grad_norm": 0.5755125880241394, + "learning_rate": 1.4324324324324327e-06, + "loss": 0.232, + "step": 270 + }, + { + "epoch": 0.7226666666666667, + "grad_norm": 0.5169756412506104, + "learning_rate": 1.418918918918919e-06, + "loss": 0.122, + "step": 271 + }, + { + "epoch": 0.7253333333333334, + "grad_norm": 0.7220999002456665, + "learning_rate": 1.4054054054054056e-06, + "loss": 0.2336, + "step": 272 + }, + { + "epoch": 0.728, + "grad_norm": 0.5650200247764587, + "learning_rate": 1.391891891891892e-06, + "loss": 0.2206, + "step": 273 + }, + { + "epoch": 0.7306666666666667, + "grad_norm": 0.5521315932273865, + "learning_rate": 1.3783783783783786e-06, + "loss": 0.2462, + "step": 274 + }, + { + "epoch": 0.7333333333333333, + "grad_norm": 0.7300999760627747, + "learning_rate": 1.364864864864865e-06, + "loss": 0.3449, + "step": 275 + }, + { + "epoch": 0.736, + "grad_norm": 0.8608168363571167, + "learning_rate": 1.3513513513513515e-06, + "loss": 0.2788, + "step": 276 + }, + { + "epoch": 0.7386666666666667, + "grad_norm": 0.6485387086868286, + "learning_rate": 1.3378378378378378e-06, + "loss": 0.2708, + "step": 277 + }, + { + "epoch": 0.7413333333333333, + "grad_norm": 0.6375903487205505, + "learning_rate": 1.3243243243243246e-06, + "loss": 0.2241, + "step": 278 + }, + { + "epoch": 0.744, + "grad_norm": 0.8569247722625732, + "learning_rate": 1.310810810810811e-06, + "loss": 0.3561, + "step": 279 + }, + { + "epoch": 0.7466666666666667, + "grad_norm": 0.7526376247406006, + "learning_rate": 1.2972972972972974e-06, + "loss": 0.2946, + "step": 280 + }, + { + "epoch": 0.7493333333333333, + "grad_norm": 0.549019992351532, + "learning_rate": 1.2837837837837838e-06, + "loss": 0.2319, + "step": 281 + }, + { + "epoch": 0.752, + "grad_norm": 0.6888551115989685, + "learning_rate": 1.2702702702702705e-06, + "loss": 0.2231, + "step": 282 + }, + { + "epoch": 0.7546666666666667, + "grad_norm": 0.7437498569488525, + "learning_rate": 1.2567567567567568e-06, + "loss": 0.3443, + "step": 283 + }, + { + "epoch": 0.7573333333333333, + "grad_norm": 0.5346582531929016, + "learning_rate": 1.2432432432432434e-06, + "loss": 0.1844, + "step": 284 + }, + { + "epoch": 0.76, + "grad_norm": 0.6110626459121704, + "learning_rate": 1.22972972972973e-06, + "loss": 0.1701, + "step": 285 + }, + { + "epoch": 0.7626666666666667, + "grad_norm": 0.5659084320068359, + "learning_rate": 1.2162162162162164e-06, + "loss": 0.2259, + "step": 286 + }, + { + "epoch": 0.7653333333333333, + "grad_norm": 0.6930540204048157, + "learning_rate": 1.2027027027027028e-06, + "loss": 0.2532, + "step": 287 + }, + { + "epoch": 0.768, + "grad_norm": 0.7666062116622925, + "learning_rate": 1.1891891891891893e-06, + "loss": 0.2821, + "step": 288 + }, + { + "epoch": 0.7706666666666667, + "grad_norm": 0.639336109161377, + "learning_rate": 1.1756756756756758e-06, + "loss": 0.2184, + "step": 289 + }, + { + "epoch": 0.7733333333333333, + "grad_norm": 0.7201549410820007, + "learning_rate": 1.1621621621621624e-06, + "loss": 0.3105, + "step": 290 + }, + { + "epoch": 0.776, + "grad_norm": 0.7706798911094666, + "learning_rate": 1.148648648648649e-06, + "loss": 0.3112, + "step": 291 + }, + { + "epoch": 0.7786666666666666, + "grad_norm": 0.8544201850891113, + "learning_rate": 1.1351351351351352e-06, + "loss": 0.3644, + "step": 292 + }, + { + "epoch": 0.7813333333333333, + "grad_norm": 0.7253162264823914, + "learning_rate": 1.1216216216216218e-06, + "loss": 0.2791, + "step": 293 + }, + { + "epoch": 0.784, + "grad_norm": 0.680812418460846, + "learning_rate": 1.1081081081081083e-06, + "loss": 0.2198, + "step": 294 + }, + { + "epoch": 0.7866666666666666, + "grad_norm": 0.7938084006309509, + "learning_rate": 1.0945945945945948e-06, + "loss": 0.2881, + "step": 295 + }, + { + "epoch": 0.7893333333333333, + "grad_norm": 0.7089200615882874, + "learning_rate": 1.0810810810810812e-06, + "loss": 0.2063, + "step": 296 + }, + { + "epoch": 0.792, + "grad_norm": 0.5346383452415466, + "learning_rate": 1.0675675675675677e-06, + "loss": 0.1776, + "step": 297 + }, + { + "epoch": 0.7946666666666666, + "grad_norm": 0.7926894426345825, + "learning_rate": 1.0540540540540542e-06, + "loss": 0.3311, + "step": 298 + }, + { + "epoch": 0.7973333333333333, + "grad_norm": 0.7401625514030457, + "learning_rate": 1.0405405405405408e-06, + "loss": 0.3394, + "step": 299 + }, + { + "epoch": 0.8, + "grad_norm": 0.49938178062438965, + "learning_rate": 1.027027027027027e-06, + "loss": 0.1436, + "step": 300 + }, + { + "epoch": 0.8026666666666666, + "grad_norm": 1.0157798528671265, + "learning_rate": 1.0135135135135136e-06, + "loss": 0.3707, + "step": 301 + }, + { + "epoch": 0.8053333333333333, + "grad_norm": 0.6077897548675537, + "learning_rate": 1.0000000000000002e-06, + "loss": 0.2519, + "step": 302 + }, + { + "epoch": 0.808, + "grad_norm": 0.7587655186653137, + "learning_rate": 9.864864864864867e-07, + "loss": 0.3392, + "step": 303 + }, + { + "epoch": 0.8106666666666666, + "grad_norm": 0.8215785622596741, + "learning_rate": 9.72972972972973e-07, + "loss": 0.3397, + "step": 304 + }, + { + "epoch": 0.8133333333333334, + "grad_norm": 0.6645399928092957, + "learning_rate": 9.594594594594596e-07, + "loss": 0.2386, + "step": 305 + }, + { + "epoch": 0.816, + "grad_norm": 0.7893449068069458, + "learning_rate": 9.459459459459461e-07, + "loss": 0.34, + "step": 306 + }, + { + "epoch": 0.8186666666666667, + "grad_norm": 0.6246175765991211, + "learning_rate": 9.324324324324325e-07, + "loss": 0.2148, + "step": 307 + }, + { + "epoch": 0.8213333333333334, + "grad_norm": 0.7497851252555847, + "learning_rate": 9.189189189189191e-07, + "loss": 0.2734, + "step": 308 + }, + { + "epoch": 0.824, + "grad_norm": 0.7372452616691589, + "learning_rate": 9.054054054054055e-07, + "loss": 0.2921, + "step": 309 + }, + { + "epoch": 0.8266666666666667, + "grad_norm": 0.5490118265151978, + "learning_rate": 8.91891891891892e-07, + "loss": 0.1934, + "step": 310 + }, + { + "epoch": 0.8293333333333334, + "grad_norm": 0.7610583305358887, + "learning_rate": 8.783783783783785e-07, + "loss": 0.2955, + "step": 311 + }, + { + "epoch": 0.832, + "grad_norm": 0.7264029383659363, + "learning_rate": 8.64864864864865e-07, + "loss": 0.2704, + "step": 312 + }, + { + "epoch": 0.8346666666666667, + "grad_norm": 0.660663366317749, + "learning_rate": 8.513513513513514e-07, + "loss": 0.3243, + "step": 313 + }, + { + "epoch": 0.8373333333333334, + "grad_norm": 0.6899711489677429, + "learning_rate": 8.37837837837838e-07, + "loss": 0.2456, + "step": 314 + }, + { + "epoch": 0.84, + "grad_norm": 0.6473216414451599, + "learning_rate": 8.243243243243244e-07, + "loss": 0.2789, + "step": 315 + }, + { + "epoch": 0.8426666666666667, + "grad_norm": 0.6556074023246765, + "learning_rate": 8.108108108108109e-07, + "loss": 0.2523, + "step": 316 + }, + { + "epoch": 0.8453333333333334, + "grad_norm": 0.727306604385376, + "learning_rate": 7.972972972972974e-07, + "loss": 0.2278, + "step": 317 + }, + { + "epoch": 0.848, + "grad_norm": 0.7739129066467285, + "learning_rate": 7.837837837837839e-07, + "loss": 0.2477, + "step": 318 + }, + { + "epoch": 0.8506666666666667, + "grad_norm": 0.653274655342102, + "learning_rate": 7.702702702702704e-07, + "loss": 0.2261, + "step": 319 + }, + { + "epoch": 0.8533333333333334, + "grad_norm": 0.6465176343917847, + "learning_rate": 7.567567567567569e-07, + "loss": 0.2648, + "step": 320 + }, + { + "epoch": 0.856, + "grad_norm": 0.6187155246734619, + "learning_rate": 7.432432432432434e-07, + "loss": 0.2718, + "step": 321 + }, + { + "epoch": 0.8586666666666667, + "grad_norm": 0.6505514979362488, + "learning_rate": 7.297297297297298e-07, + "loss": 0.1971, + "step": 322 + }, + { + "epoch": 0.8613333333333333, + "grad_norm": 0.6444483399391174, + "learning_rate": 7.162162162162164e-07, + "loss": 0.261, + "step": 323 + }, + { + "epoch": 0.864, + "grad_norm": 0.625307023525238, + "learning_rate": 7.027027027027028e-07, + "loss": 0.2322, + "step": 324 + }, + { + "epoch": 0.8666666666666667, + "grad_norm": 0.5336941480636597, + "learning_rate": 6.891891891891893e-07, + "loss": 0.1944, + "step": 325 + }, + { + "epoch": 0.8693333333333333, + "grad_norm": 0.7971201539039612, + "learning_rate": 6.756756756756758e-07, + "loss": 0.2799, + "step": 326 + }, + { + "epoch": 0.872, + "grad_norm": 0.6575078368186951, + "learning_rate": 6.621621621621623e-07, + "loss": 0.2031, + "step": 327 + }, + { + "epoch": 0.8746666666666667, + "grad_norm": 0.7094213366508484, + "learning_rate": 6.486486486486487e-07, + "loss": 0.2935, + "step": 328 + }, + { + "epoch": 0.8773333333333333, + "grad_norm": 0.656079888343811, + "learning_rate": 6.351351351351353e-07, + "loss": 0.271, + "step": 329 + }, + { + "epoch": 0.88, + "grad_norm": 0.7230790257453918, + "learning_rate": 6.216216216216217e-07, + "loss": 0.2679, + "step": 330 + }, + { + "epoch": 0.8826666666666667, + "grad_norm": 0.6316200494766235, + "learning_rate": 6.081081081081082e-07, + "loss": 0.274, + "step": 331 + }, + { + "epoch": 0.8853333333333333, + "grad_norm": 0.7337319254875183, + "learning_rate": 5.945945945945947e-07, + "loss": 0.2673, + "step": 332 + }, + { + "epoch": 0.888, + "grad_norm": 0.843817949295044, + "learning_rate": 5.810810810810812e-07, + "loss": 0.3826, + "step": 333 + }, + { + "epoch": 0.8906666666666667, + "grad_norm": 0.6947763562202454, + "learning_rate": 5.675675675675676e-07, + "loss": 0.2195, + "step": 334 + }, + { + "epoch": 0.8933333333333333, + "grad_norm": 0.5857032537460327, + "learning_rate": 5.540540540540542e-07, + "loss": 0.2216, + "step": 335 + }, + { + "epoch": 0.896, + "grad_norm": 0.6403198838233948, + "learning_rate": 5.405405405405406e-07, + "loss": 0.1966, + "step": 336 + }, + { + "epoch": 0.8986666666666666, + "grad_norm": 0.7058374881744385, + "learning_rate": 5.270270270270271e-07, + "loss": 0.2767, + "step": 337 + }, + { + "epoch": 0.9013333333333333, + "grad_norm": 0.7013625502586365, + "learning_rate": 5.135135135135135e-07, + "loss": 0.2374, + "step": 338 + }, + { + "epoch": 0.904, + "grad_norm": 0.3994562029838562, + "learning_rate": 5.000000000000001e-07, + "loss": 0.093, + "step": 339 + }, + { + "epoch": 0.9066666666666666, + "grad_norm": 0.771163284778595, + "learning_rate": 4.864864864864865e-07, + "loss": 0.2872, + "step": 340 + }, + { + "epoch": 0.9093333333333333, + "grad_norm": 0.751780092716217, + "learning_rate": 4.7297297297297305e-07, + "loss": 0.2919, + "step": 341 + }, + { + "epoch": 0.912, + "grad_norm": 0.7651583552360535, + "learning_rate": 4.5945945945945953e-07, + "loss": 0.2674, + "step": 342 + }, + { + "epoch": 0.9146666666666666, + "grad_norm": 0.6452313661575317, + "learning_rate": 4.45945945945946e-07, + "loss": 0.2545, + "step": 343 + }, + { + "epoch": 0.9173333333333333, + "grad_norm": 0.9916335940361023, + "learning_rate": 4.324324324324325e-07, + "loss": 0.474, + "step": 344 + }, + { + "epoch": 0.92, + "grad_norm": 0.6891211271286011, + "learning_rate": 4.18918918918919e-07, + "loss": 0.264, + "step": 345 + }, + { + "epoch": 0.9226666666666666, + "grad_norm": 0.9911397695541382, + "learning_rate": 4.0540540540540546e-07, + "loss": 0.3662, + "step": 346 + }, + { + "epoch": 0.9253333333333333, + "grad_norm": 0.6984186172485352, + "learning_rate": 3.9189189189189195e-07, + "loss": 0.1964, + "step": 347 + }, + { + "epoch": 0.928, + "grad_norm": 0.6879184246063232, + "learning_rate": 3.7837837837837843e-07, + "loss": 0.3225, + "step": 348 + }, + { + "epoch": 0.9306666666666666, + "grad_norm": 0.7449390888214111, + "learning_rate": 3.648648648648649e-07, + "loss": 0.3454, + "step": 349 + }, + { + "epoch": 0.9333333333333333, + "grad_norm": 0.7835482358932495, + "learning_rate": 3.513513513513514e-07, + "loss": 0.3234, + "step": 350 + }, + { + "epoch": 0.936, + "grad_norm": 0.9468456506729126, + "learning_rate": 3.378378378378379e-07, + "loss": 0.3566, + "step": 351 + }, + { + "epoch": 0.9386666666666666, + "grad_norm": 0.7769863605499268, + "learning_rate": 3.2432432432432436e-07, + "loss": 0.3111, + "step": 352 + }, + { + "epoch": 0.9413333333333334, + "grad_norm": 0.5438784956932068, + "learning_rate": 3.1081081081081084e-07, + "loss": 0.1777, + "step": 353 + }, + { + "epoch": 0.944, + "grad_norm": 0.9233208298683167, + "learning_rate": 2.972972972972973e-07, + "loss": 0.4088, + "step": 354 + }, + { + "epoch": 0.9466666666666667, + "grad_norm": 0.7583839893341064, + "learning_rate": 2.837837837837838e-07, + "loss": 0.3076, + "step": 355 + }, + { + "epoch": 0.9493333333333334, + "grad_norm": 0.5570662617683411, + "learning_rate": 2.702702702702703e-07, + "loss": 0.2107, + "step": 356 + }, + { + "epoch": 0.952, + "grad_norm": 0.7196395993232727, + "learning_rate": 2.567567567567568e-07, + "loss": 0.3265, + "step": 357 + }, + { + "epoch": 0.9546666666666667, + "grad_norm": 0.6890366673469543, + "learning_rate": 2.4324324324324326e-07, + "loss": 0.191, + "step": 358 + }, + { + "epoch": 0.9573333333333334, + "grad_norm": 0.7225922346115112, + "learning_rate": 2.2972972972972977e-07, + "loss": 0.2397, + "step": 359 + }, + { + "epoch": 0.96, + "grad_norm": 0.7831887602806091, + "learning_rate": 2.1621621621621625e-07, + "loss": 0.3651, + "step": 360 + }, + { + "epoch": 0.9626666666666667, + "grad_norm": 0.7030459642410278, + "learning_rate": 2.0270270270270273e-07, + "loss": 0.2413, + "step": 361 + }, + { + "epoch": 0.9653333333333334, + "grad_norm": 0.6214504837989807, + "learning_rate": 1.8918918918918921e-07, + "loss": 0.1951, + "step": 362 + }, + { + "epoch": 0.968, + "grad_norm": 0.750308096408844, + "learning_rate": 1.756756756756757e-07, + "loss": 0.3044, + "step": 363 + }, + { + "epoch": 0.9706666666666667, + "grad_norm": 1.0070992708206177, + "learning_rate": 1.6216216216216218e-07, + "loss": 0.3701, + "step": 364 + }, + { + "epoch": 0.9733333333333334, + "grad_norm": 0.7010138034820557, + "learning_rate": 1.4864864864864866e-07, + "loss": 0.249, + "step": 365 + }, + { + "epoch": 0.976, + "grad_norm": 0.8299365639686584, + "learning_rate": 1.3513513513513515e-07, + "loss": 0.4026, + "step": 366 + }, + { + "epoch": 0.9786666666666667, + "grad_norm": 0.8506694436073303, + "learning_rate": 1.2162162162162163e-07, + "loss": 0.3943, + "step": 367 + }, + { + "epoch": 0.9813333333333333, + "grad_norm": 0.7677544355392456, + "learning_rate": 1.0810810810810812e-07, + "loss": 0.3529, + "step": 368 + }, + { + "epoch": 0.984, + "grad_norm": 0.7364651560783386, + "learning_rate": 9.459459459459461e-08, + "loss": 0.3241, + "step": 369 + }, + { + "epoch": 0.9866666666666667, + "grad_norm": 0.7511231899261475, + "learning_rate": 8.108108108108109e-08, + "loss": 0.2432, + "step": 370 + }, + { + "epoch": 0.9893333333333333, + "grad_norm": 0.6210150718688965, + "learning_rate": 6.756756756756757e-08, + "loss": 0.2464, + "step": 371 + }, + { + "epoch": 0.992, + "grad_norm": 0.6229819059371948, + "learning_rate": 5.405405405405406e-08, + "loss": 0.2169, + "step": 372 + }, + { + "epoch": 0.9946666666666667, + "grad_norm": 0.5944173336029053, + "learning_rate": 4.0540540540540545e-08, + "loss": 0.2207, + "step": 373 + }, + { + "epoch": 0.9973333333333333, + "grad_norm": 0.8761155009269714, + "learning_rate": 2.702702702702703e-08, + "loss": 0.3129, + "step": 374 + }, + { + "epoch": 1.0, + "grad_norm": 0.7788829207420349, + "learning_rate": 1.3513513513513516e-08, + "loss": 0.2373, + "step": 375 + } + ], + "logging_steps": 1, + "max_steps": 375, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 5000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5.212611526904218e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-375/training_args.bin b/checkpoint-375/training_args.bin new file mode 100644 index 0000000..0afc4dd --- /dev/null +++ b/checkpoint-375/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43005b572d15985e37dc9b39cd61ba2727d2cf333cc5341ef1f2d7c8617496d3 +size 6097 diff --git a/config.json b/config.json new file mode 100644 index 0000000..2ade0f9 --- /dev/null +++ b/config.json @@ -0,0 +1,109 @@ +{ + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "bfloat16", + "eos_token_id": 128012, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pad_token_id": 128004, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "transformers_version": "4.56.2", + "unsloth_version": "2025.10.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..b173137 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328deba3aef182cc399a40ee9ab87e055951c54b152dcb2aad1edbddac4f0034 +size 4966315264 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..6a7f412 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ab2e8e64b8488a8b3d5c517da2d8988d335a0cf7e6ebb720c5bc9d4033657a +size 1183919744 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ee6c028 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,334 @@ +{ + "metadata": { + "total_parameters": 3075098624, + "total_size": 6150197248 + }, + "weight_map": { + "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-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-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.weight": "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-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.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.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.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..99610b0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,10 @@ +{ + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|finetune_right_pad_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..074fa66 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6a500b662a34eb3f0374db856ba4ad7de4c81040571d78dc0d357238930005 +size 17208819 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..36669f5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": null, + "clean_up_tokenization_spaces": true, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "fast": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "left", + "tokenizer_class": "PreTrainedTokenizerFast", + "chat_template": "{# ───── defaults ───── #}\n{%- if enable_thinking is not defined -%}\n{%- set enable_thinking = true -%}\n{%- endif -%}\n\n{# ───── reasoning mode ───── #}\n{%- if enable_thinking -%}\n {%- set reasoning_mode = \"/think\" -%}\n{%- else -%}\n {%- set reasoning_mode = \"/no_think\" -%}\n{%- endif -%}\n\n{# ───── header (system message) ───── #}\n{{- \"<|im_start|>system\\n\" -}}\n\n{%- if messages[0].role == \"system\" -%}\n {%- set system_message = messages[0].content -%}\n {%- if \"/no_think\" in system_message -%}\n {%- set reasoning_mode = \"/no_think\" -%}\n {%- elif \"/think\" in system_message -%}\n {%- set reasoning_mode = \"/think\" -%}\n {%- endif -%}\n {%- set custom_instructions = system_message.replace(\"/no_think\", \"\").replace(\"/think\", \"\").rstrip() -%}\n{%- endif -%}\n\n{%- if \"/system_override\" in system_message -%}\n {{- custom_instructions.replace(\"/system_override\", \"\").rstrip() -}}\n {{- \"<|im_end|>\\n\" -}}\n{%- else -%}\n {{- \"## Metadata\\n\\n\" -}}\n {{- \"Knowledge Cutoff Date: June 2025\\n\" -}}\n {%- set today = strftime_now(\"%d %B %Y\") -%}\n {{- \"Today Date: \" ~ today ~ \"\\n\" -}}\n {{- \"Reasoning Mode: \" + reasoning_mode + \"\\n\\n\" -}}\n \n {{- \"## Custom Instructions\\n\\n\" -}}\n {%- if custom_instructions -%}\n {{- custom_instructions + \"\\n\\n\" -}}\n {%- elif reasoning_mode == \"/think\" -%}\n {{- \"You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: Thought section Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\\n\\n\" -}}\n {%- else -%}\n {{- \"You are a helpful AI assistant named SmolLM, trained by Hugging Face.\\n\\n\" -}}\n {%- endif -%}\n\n {%- if xml_tools or python_tools or tools -%}\n {{- \"### Tools\\n\\n\" -}}\n {%- if xml_tools or tools -%}\n {%- if tools -%}\n {%- set xml_tools = tools -%}\n {%- endif -%}\n {%- set ns = namespace(xml_tool_string=\"You may call one or more functions to assist with the user query.\\nYou are provided with function signatures within XML tags:\\n\\n\\n\") -%}\n {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #}\n {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ \"\\n\" -%}\n {%- endfor -%}\n {%- set xml_tool_string = ns.xml_tool_string + \"\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n\" -%}\n {{- xml_tool_string -}}\n {%- endif -%}\n {%- if python_tools -%}\n {%- set ns = namespace(python_tool_string=\"When you send a message containing Python code between '' and '' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\\n\\nYou can use the following tools in your python code like regular functions:\\n\\n\") -%}\n {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #}\n {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ \"\\n\" -%}\n {%- endfor -%}\n {%- set python_tool_string = ns.python_tool_string + \"\\n\\nThe state persists between code executions: so variables that you define in one step are still available thereafter.\" -%}\n {{- python_tool_string -}}\n {%- endif -%}\n {{- \"\\n\\n\" -}}\n {{- \"<|im_end|>\\n\" -}}\n {%- endif -%}\n{%- endif -%}\n{# ───── main loop ───── #}\n{%- for message in messages -%}\n {%- set content = message.content if message.content is string else \"\" -%}\n {%- if message.role == \"user\" -%}\n {{ \"<|im_start|>\" + message.role + \"\\n\" + content + \"<|im_end|>\\n\" }}\n {%- elif message.role == \"assistant\" -%}\n {% generation %}\n {%- if reasoning_mode == \"/think\" -%}\n {{ \"<|im_start|>assistant\\n\" + content.lstrip(\"\\n\") + \"<|im_end|>\\n\" }}\n {%- else -%}\n {{ \"<|im_start|>assistant\\n\" + \"\\n\\n\\n\" + content.lstrip(\"\\n\") + \"<|im_end|>\\n\" }}\n {%- endif -%}\n {% endgeneration %}\n {%- elif message.role == \"tool\" -%}\n {{ \"<|im_start|>\" + \"user\\n\" + content + \"<|im_end|>\\n\" }}\n {%- endif -%}\n{%- endfor -%}\n{# ───── generation prompt ───── #}\n{%- if add_generation_prompt -%}\n {%- if reasoning_mode == \"/think\" -%}\n {{ \"<|im_start|>assistant\\n\" }}\n {%- else -%}\n {{ \"<|im_start|>assistant\\n\" + \"\\n\\n\\n\" }}\n {%- endif -%}\n{%- endif -%}" +} \ No newline at end of file