Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+tags:
+  - arduino
+  - esp32
+  - raspberry-pi
+  - micropython
+  - circuitpython
+  - embedded
+  - lora
+  - unsloth
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+# Arduino/Embedded Wiring & Code Assistant (Qwen2.5-Coder-7B LoRA)
+
+A LoRA fine-tune of [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), specialized for generating wiring instructions and working code for embedded/maker projects.
+
+Given a plain-language request like *"wire a BME280 to an ESP32 over I2C"*, it produces a wiring table, an ASCII wiring diagram, complete working code, and a short explanation — across Arduino C++, Raspberry Pi Python, MicroPython, and CircuitPython, on 7 boards (ESP32, Raspberry Pi, Raspberry Pi Pico, Arduino Uno, ESP8266, Teensy 4.0, M5Stack Core2).
+
+**Full training pipeline, dataset, and evaluation harness:** [GitHub repo](https://github.com/YOUR-USERNAME/arduino-embedded-llm)
+
+## Benchmark (12-question held-out eval, deterministic decoding)
+
+| Metric | This model (7B, 373 examples) | Earlier 1.5B baseline (65 examples) |
+|---|---|---|
+| Format compliance | **83%** | 58% |
+| Runtime contamination-free | **100%** | 83% |
+| Code syntax valid | **~100%*** | 92% |
+| Speed (RTX 4070 8GB laptop) | 12.0 tok/s | 13.7 tok/s |
+| Speed (data-center GPU) | 73.2 tok/s | — |
+
+\* Two apparent syntax failures were confirmed to be 900-token generation-cap truncation, not real errors.
+
+"Runtime contamination" = wrong-framework API leaking into an answer (e.g. MicroPython's `machine.Pin` appearing in Arduino code, or Raspberry Pi's physical-pin numbering convention appearing in an ESP32 answer). Eliminating this was the primary goal of moving from the 1.5B to the 7B model plus a larger, validated dataset.
+
+We also tested a LoRA rank-32 variant: no measurable quality improvement over rank-16 on any metric, so this release ships the more efficient rank-16 adapter.
+
+## ⚠️ Known limitations
+
+This is a v0.1 release trained on 373 examples — small by any standard. Manual testing (6 hand-picked questions, not from the eval set) found a clear, honest capability boundary:
+
+**Reliable (3/3 tested):** straightforward single-component wiring closely resembling the training distribution — e.g. "wire a BME280 to an ESP32 over I2C," "read a DHT22 on a Raspberry Pi," "wire an SSD1306 OLED to an ESP32 in MicroPython." All three produced correct pins, correct libraries, and internally consistent answers.
+
+**Unreliable (0/3 tested):** novel multi-component combinations and protocol-level troubleshooting outside the training distribution. Three distinct hallucination patterns were found:
+- Internal inconsistencies within one answer (a wiring diagram wire contradicting its own table)
+- A fabricated, non-functional low-level procedure for an I2C address conflict (invented register names/values presented with confidence)
+- An invented sensor capability not physically possible on the requested hardware (a "CO2 estimate" from a sensor that cannot measure CO2)
+
+**Always verify wiring against the actual component datasheet before connecting real hardware.** Incorrect voltage or pin assignments can damage components. Treat outputs as a first draft, not a final instruction set.
+
+## Usage
+
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    "unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit",
+    max_seq_length=2048,
+    load_in_4bit=True,
+)
+model.load_adapter("YOUR-USERNAME/arduino-embedded-qwen2.5-coder-7b")
+FastLanguageModel.for_inference(model)
+
+messages = [{"role": "user", "content": "How do I wire a BME280 to an ESP32 over I2C?"}]
+inputs = tokenizer.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+).to("cuda")
+outputs = model.generate(input_ids=inputs, max_new_tokens=1300, do_sample=False)
+print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
+```
+
+Minimum hardware: ~6GB VRAM for inference (tested at 8GB on an RTX 4070 laptop). A 0.5B distilled variant for CPU/Raspberry Pi Zero 2W deployment is planned.
+
+## Training details
+
+- **Base model:** Qwen2.5-Coder-7B-Instruct (4-bit, via Unsloth)
+- **Method:** LoRA, rank 16, alpha 16, all attention + MLP projections
+- **Dataset:** 373 examples, synthetically generated and validated against an automated contamination checker before merging into training data
+- **Epochs:** 3
+
+## License
+
+Apache 2.0, inherited from the base model. Free for commercial use, modification, and redistribution.
+
+## Citation / Acknowledgments
+
+Built on [Qwen2.5-Coder](https://github.com/QwenLM/Qwen2.5-Coder) (Alibaba Qwen team) using [Unsloth](https://github.com/unslothai/unsloth).

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14c158bafa3e0dabb204ac221758d9e1b127541f4796e15c296c8cc3f9ecd61
+size 161533192

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-282/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-282/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-282/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14c158bafa3e0dabb204ac221758d9e1b127541f4796e15c296c8cc3f9ecd61
+size 161533192

checkpoint-282/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d71064f9e71e88e581b82c98b2b54fa94079865c57f27a5b90465213215aefe
+size 82469127

checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f662027000969bd5c53794b1cc5f79566a2685a3b174c35097cd8419c58d83d
+size 1465

checkpoint-282/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-282/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-282/trainer_state.json

@@ -0,0 +1,2008 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010723860589812333,
+      "grad_norm": 0.09956473857164383,
+      "learning_rate": 0.0,
+      "loss": 1.187880516052246,
+      "step": 1
+    },
+    {
+      "epoch": 0.021447721179624665,
+      "grad_norm": 0.11292029917240143,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.2154676914215088,
+      "step": 2
+    },
+    {
+      "epoch": 0.032171581769437,
+      "grad_norm": 0.10153086483478546,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.0373685359954834,
+      "step": 3
+    },
+    {
+      "epoch": 0.04289544235924933,
+      "grad_norm": 0.11490683257579803,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 1.1642744541168213,
+      "step": 4
+    },
+    {
+      "epoch": 0.05361930294906166,
+      "grad_norm": 0.10738470405340195,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 1.0547881126403809,
+      "step": 5
+    },
+    {
+      "epoch": 0.064343163538874,
+      "grad_norm": 0.09365780651569366,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.9747384190559387,
+      "step": 6
+    },
+    {
+      "epoch": 0.07506702412868632,
+      "grad_norm": 0.11804107576608658,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 1.1494673490524292,
+      "step": 7
+    },
+    {
+      "epoch": 0.08579088471849866,
+      "grad_norm": 0.1242947056889534,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 1.1914423704147339,
+      "step": 8
+    },
+    {
+      "epoch": 0.09651474530831099,
+      "grad_norm": 0.11152593791484833,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.9928394556045532,
+      "step": 9
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 0.11541841924190521,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 0.9315593242645264,
+      "step": 10
+    },
+    {
+      "epoch": 0.11796246648793565,
+      "grad_norm": 0.11834950000047684,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 0.8903577327728271,
+      "step": 11
+    },
+    {
+      "epoch": 0.128686327077748,
+      "grad_norm": 0.14892849326133728,
+      "learning_rate": 7.586206896551724e-05,
+      "loss": 1.0821267366409302,
+      "step": 12
+    },
+    {
+      "epoch": 0.13941018766756033,
+      "grad_norm": 0.1506800651550293,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 1.0795198678970337,
+      "step": 13
+    },
+    {
+      "epoch": 0.15013404825737264,
+      "grad_norm": 0.14844302833080292,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 1.026419758796692,
+      "step": 14
+    },
+    {
+      "epoch": 0.16085790884718498,
+      "grad_norm": 0.16847245395183563,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 1.0807701349258423,
+      "step": 15
+    },
+    {
+      "epoch": 0.17158176943699732,
+      "grad_norm": 0.1590828001499176,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 0.9547437429428101,
+      "step": 16
+    },
+    {
+      "epoch": 0.18230563002680966,
+      "grad_norm": 0.1714753657579422,
+      "learning_rate": 0.0001103448275862069,
+      "loss": 0.9339712858200073,
+      "step": 17
+    },
+    {
+      "epoch": 0.19302949061662197,
+      "grad_norm": 0.17293080687522888,
+      "learning_rate": 0.00011724137931034482,
+      "loss": 0.9700860977172852,
+      "step": 18
+    },
+    {
+      "epoch": 0.2037533512064343,
+      "grad_norm": 0.18182949721813202,
+      "learning_rate": 0.00012413793103448277,
+      "loss": 0.9788463115692139,
+      "step": 19
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 0.14979304373264313,
+      "learning_rate": 0.00013103448275862068,
+      "loss": 0.7673980593681335,
+      "step": 20
+    },
+    {
+      "epoch": 0.225201072386059,
+      "grad_norm": 0.1847337931394577,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 0.8736073970794678,
+      "step": 21
+    },
+    {
+      "epoch": 0.2359249329758713,
+      "grad_norm": 0.1613779366016388,
+      "learning_rate": 0.00014482758620689657,
+      "loss": 0.7171751260757446,
+      "step": 22
+    },
+    {
+      "epoch": 0.24664879356568364,
+      "grad_norm": 0.20078714191913605,
+      "learning_rate": 0.00015172413793103449,
+      "loss": 0.8132349848747253,
+      "step": 23
+    },
+    {
+      "epoch": 0.257372654155496,
+      "grad_norm": 0.23513053357601166,
+      "learning_rate": 0.00015862068965517243,
+      "loss": 0.767032265663147,
+      "step": 24
+    },
+    {
+      "epoch": 0.2680965147453083,
+      "grad_norm": 0.264248788356781,
+      "learning_rate": 0.00016551724137931035,
+      "loss": 0.9374470114707947,
+      "step": 25
+    },
+    {
+      "epoch": 0.27882037533512066,
+      "grad_norm": 0.23587241768836975,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 0.85521000623703,
+      "step": 26
+    },
+    {
+      "epoch": 0.289544235924933,
+      "grad_norm": 0.2163752019405365,
+      "learning_rate": 0.0001793103448275862,
+      "loss": 0.685062050819397,
+      "step": 27
+    },
+    {
+      "epoch": 0.3002680965147453,
+      "grad_norm": 0.23211570084095,
+      "learning_rate": 0.00018620689655172415,
+      "loss": 0.7995907068252563,
+      "step": 28
+    },
+    {
+      "epoch": 0.3109919571045576,
+      "grad_norm": 0.28809505701065063,
+      "learning_rate": 0.0001931034482758621,
+      "loss": 0.7216339111328125,
+      "step": 29
+    },
+    {
+      "epoch": 0.32171581769436997,
+      "grad_norm": 0.306933730840683,
+      "learning_rate": 0.0002,
+      "loss": 0.7865221500396729,
+      "step": 30
+    },
+    {
+      "epoch": 0.3324396782841823,
+      "grad_norm": 0.23336660861968994,
+      "learning_rate": 0.00019920948616600792,
+      "loss": 0.5897479057312012,
+      "step": 31
+    },
+    {
+      "epoch": 0.34316353887399464,
+      "grad_norm": 0.2930724024772644,
+      "learning_rate": 0.00019841897233201583,
+      "loss": 0.7502959966659546,
+      "step": 32
+    },
+    {
+      "epoch": 0.353887399463807,
+      "grad_norm": 0.2703939974308014,
+      "learning_rate": 0.0001976284584980237,
+      "loss": 0.659548282623291,
+      "step": 33
+    },
+    {
+      "epoch": 0.3646112600536193,
+      "grad_norm": 0.2767476737499237,
+      "learning_rate": 0.00019683794466403162,
+      "loss": 0.7053808569908142,
+      "step": 34
+    },
+    {
+      "epoch": 0.3753351206434316,
+      "grad_norm": 0.31025224924087524,
+      "learning_rate": 0.00019604743083003953,
+      "loss": 0.7129980325698853,
+      "step": 35
+    },
+    {
+      "epoch": 0.38605898123324395,
+      "grad_norm": 0.24430641531944275,
+      "learning_rate": 0.00019525691699604744,
+      "loss": 0.6667079925537109,
+      "step": 36
+    },
+    {
+      "epoch": 0.3967828418230563,
+      "grad_norm": 0.23834890127182007,
+      "learning_rate": 0.00019446640316205535,
+      "loss": 0.6788681149482727,
+      "step": 37
+    },
+    {
+      "epoch": 0.4075067024128686,
+      "grad_norm": 0.24645410478115082,
+      "learning_rate": 0.00019367588932806324,
+      "loss": 0.6573145389556885,
+      "step": 38
+    },
+    {
+      "epoch": 0.41823056300268097,
+      "grad_norm": 0.2453237771987915,
+      "learning_rate": 0.00019288537549407115,
+      "loss": 0.6146591901779175,
+      "step": 39
+    },
+    {
+      "epoch": 0.4289544235924933,
+      "grad_norm": 0.28095656633377075,
+      "learning_rate": 0.00019209486166007906,
+      "loss": 0.8814584612846375,
+      "step": 40
+    },
+    {
+      "epoch": 0.43967828418230565,
+      "grad_norm": 0.2434511035680771,
+      "learning_rate": 0.00019130434782608697,
+      "loss": 0.5752735137939453,
+      "step": 41
+    },
+    {
+      "epoch": 0.450402144772118,
+      "grad_norm": 0.2717647850513458,
+      "learning_rate": 0.00019051383399209488,
+      "loss": 0.7667861580848694,
+      "step": 42
+    },
+    {
+      "epoch": 0.46112600536193027,
+      "grad_norm": 0.2082528918981552,
+      "learning_rate": 0.00018972332015810276,
+      "loss": 0.4807273745536804,
+      "step": 43
+    },
+    {
+      "epoch": 0.4718498659517426,
+      "grad_norm": 0.2160937786102295,
+      "learning_rate": 0.00018893280632411067,
+      "loss": 0.6491277813911438,
+      "step": 44
+    },
+    {
+      "epoch": 0.48257372654155495,
+      "grad_norm": 0.2040049135684967,
+      "learning_rate": 0.00018814229249011858,
+      "loss": 0.5802018642425537,
+      "step": 45
+    },
+    {
+      "epoch": 0.4932975871313673,
+      "grad_norm": 0.2226921021938324,
+      "learning_rate": 0.0001873517786561265,
+      "loss": 0.5459230542182922,
+      "step": 46
+    },
+    {
+      "epoch": 0.5040214477211796,
+      "grad_norm": 0.2842342257499695,
+      "learning_rate": 0.0001865612648221344,
+      "loss": 0.6073319315910339,
+      "step": 47
+    },
+    {
+      "epoch": 0.514745308310992,
+      "grad_norm": 0.27150487899780273,
+      "learning_rate": 0.00018577075098814228,
+      "loss": 0.5493534803390503,
+      "step": 48
+    },
+    {
+      "epoch": 0.5254691689008043,
+      "grad_norm": 0.3216560482978821,
+      "learning_rate": 0.0001849802371541502,
+      "loss": 0.6763379573822021,
+      "step": 49
+    },
+    {
+      "epoch": 0.5361930294906166,
+      "grad_norm": 0.25345465540885925,
+      "learning_rate": 0.0001841897233201581,
+      "loss": 0.6142692565917969,
+      "step": 50
+    },
+    {
+      "epoch": 0.546916890080429,
+      "grad_norm": 0.2614583671092987,
+      "learning_rate": 0.00018339920948616601,
+      "loss": 0.5745217204093933,
+      "step": 51
+    },
+    {
+      "epoch": 0.5576407506702413,
+      "grad_norm": 0.2511961758136749,
+      "learning_rate": 0.00018260869565217392,
+      "loss": 0.5694140195846558,
+      "step": 52
+    },
+    {
+      "epoch": 0.5683646112600537,
+      "grad_norm": 0.2542041540145874,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.58800208568573,
+      "step": 53
+    },
+    {
+      "epoch": 0.579088471849866,
+      "grad_norm": 0.3461075723171234,
+      "learning_rate": 0.00018102766798418972,
+      "loss": 0.6247663497924805,
+      "step": 54
+    },
+    {
+      "epoch": 0.5898123324396782,
+      "grad_norm": 0.30197465419769287,
+      "learning_rate": 0.00018023715415019763,
+      "loss": 0.5455595254898071,
+      "step": 55
+    },
+    {
+      "epoch": 0.6005361930294906,
+      "grad_norm": 0.28050318360328674,
+      "learning_rate": 0.00017944664031620554,
+      "loss": 0.5253524780273438,
+      "step": 56
+    },
+    {
+      "epoch": 0.6112600536193029,
+      "grad_norm": 0.25096285343170166,
+      "learning_rate": 0.00017865612648221345,
+      "loss": 0.47590434551239014,
+      "step": 57
+    },
+    {
+      "epoch": 0.6219839142091153,
+      "grad_norm": 0.24267607927322388,
+      "learning_rate": 0.00017786561264822136,
+      "loss": 0.533282995223999,
+      "step": 58
+    },
+    {
+      "epoch": 0.6327077747989276,
+      "grad_norm": 0.2805137038230896,
+      "learning_rate": 0.00017707509881422927,
+      "loss": 0.5030880570411682,
+      "step": 59
+    },
+    {
+      "epoch": 0.6434316353887399,
+      "grad_norm": 0.2617737650871277,
+      "learning_rate": 0.00017628458498023718,
+      "loss": 0.5744041800498962,
+      "step": 60
+    },
+    {
+      "epoch": 0.6541554959785523,
+      "grad_norm": 0.2669621407985687,
+      "learning_rate": 0.0001754940711462451,
+      "loss": 0.622750997543335,
+      "step": 61
+    },
+    {
+      "epoch": 0.6648793565683646,
+      "grad_norm": 0.3352331817150116,
+      "learning_rate": 0.00017470355731225297,
+      "loss": 0.6852260231971741,
+      "step": 62
+    },
+    {
+      "epoch": 0.675603217158177,
+      "grad_norm": 0.29469311237335205,
+      "learning_rate": 0.00017391304347826088,
+      "loss": 0.5582889318466187,
+      "step": 63
+    },
+    {
+      "epoch": 0.6863270777479893,
+      "grad_norm": 0.28165683150291443,
+      "learning_rate": 0.0001731225296442688,
+      "loss": 0.5959634184837341,
+      "step": 64
+    },
+    {
+      "epoch": 0.6970509383378016,
+      "grad_norm": 0.27457600831985474,
+      "learning_rate": 0.0001723320158102767,
+      "loss": 0.5719581842422485,
+      "step": 65
+    },
+    {
+      "epoch": 0.707774798927614,
+      "grad_norm": 0.25963717699050903,
+      "learning_rate": 0.0001715415019762846,
+      "loss": 0.5438885688781738,
+      "step": 66
+    },
+    {
+      "epoch": 0.7184986595174263,
+      "grad_norm": 0.2500856816768646,
+      "learning_rate": 0.0001707509881422925,
+      "loss": 0.4802711606025696,
+      "step": 67
+    },
+    {
+      "epoch": 0.7292225201072386,
+      "grad_norm": 0.33261388540267944,
+      "learning_rate": 0.0001699604743083004,
+      "loss": 0.5482622981071472,
+      "step": 68
+    },
+    {
+      "epoch": 0.739946380697051,
+      "grad_norm": 0.32809919118881226,
+      "learning_rate": 0.00016916996047430832,
+      "loss": 0.5493278503417969,
+      "step": 69
+    },
+    {
+      "epoch": 0.7506702412868632,
+      "grad_norm": 0.30052393674850464,
+      "learning_rate": 0.00016837944664031623,
+      "loss": 0.571394681930542,
+      "step": 70
+    },
+    {
+      "epoch": 0.7613941018766756,
+      "grad_norm": 0.2913955748081207,
+      "learning_rate": 0.00016758893280632414,
+      "loss": 0.5969862341880798,
+      "step": 71
+    },
+    {
+      "epoch": 0.7721179624664879,
+      "grad_norm": 0.29803213477134705,
+      "learning_rate": 0.00016679841897233202,
+      "loss": 0.5084568858146667,
+      "step": 72
+    },
+    {
+      "epoch": 0.7828418230563002,
+      "grad_norm": 0.25044989585876465,
+      "learning_rate": 0.00016600790513833993,
+      "loss": 0.4812390208244324,
+      "step": 73
+    },
+    {
+      "epoch": 0.7935656836461126,
+      "grad_norm": 0.2839549779891968,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 0.5099290609359741,
+      "step": 74
+    },
+    {
+      "epoch": 0.8042895442359249,
+      "grad_norm": 0.3287063539028168,
+      "learning_rate": 0.00016442687747035575,
+      "loss": 0.6249513626098633,
+      "step": 75
+    },
+    {
+      "epoch": 0.8150134048257373,
+      "grad_norm": 0.26829907298088074,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.5250214338302612,
+      "step": 76
+    },
+    {
+      "epoch": 0.8257372654155496,
+      "grad_norm": 0.29728639125823975,
+      "learning_rate": 0.00016284584980237154,
+      "loss": 0.5088335275650024,
+      "step": 77
+    },
+    {
+      "epoch": 0.8364611260053619,
+      "grad_norm": 0.33355408906936646,
+      "learning_rate": 0.00016205533596837945,
+      "loss": 0.5413830876350403,
+      "step": 78
+    },
+    {
+      "epoch": 0.8471849865951743,
+      "grad_norm": 0.29799699783325195,
+      "learning_rate": 0.00016126482213438736,
+      "loss": 0.5053578615188599,
+      "step": 79
+    },
+    {
+      "epoch": 0.8579088471849866,
+      "grad_norm": 0.3381000757217407,
+      "learning_rate": 0.00016047430830039527,
+      "loss": 0.5565289258956909,
+      "step": 80
+    },
+    {
+      "epoch": 0.868632707774799,
+      "grad_norm": 0.3973819315433502,
+      "learning_rate": 0.00015968379446640318,
+      "loss": 0.711586594581604,
+      "step": 81
+    },
+    {
+      "epoch": 0.8793565683646113,
+      "grad_norm": 0.40298908948898315,
+      "learning_rate": 0.00015889328063241107,
+      "loss": 0.6098839044570923,
+      "step": 82
+    },
+    {
+      "epoch": 0.8900804289544236,
+      "grad_norm": 0.30284130573272705,
+      "learning_rate": 0.00015810276679841898,
+      "loss": 0.4950011372566223,
+      "step": 83
+    },
+    {
+      "epoch": 0.900804289544236,
+      "grad_norm": 0.3403407037258148,
+      "learning_rate": 0.00015731225296442689,
+      "loss": 0.6132961511611938,
+      "step": 84
+    },
+    {
+      "epoch": 0.9115281501340483,
+      "grad_norm": 0.2879418432712555,
+      "learning_rate": 0.0001565217391304348,
+      "loss": 0.43917202949523926,
+      "step": 85
+    },
+    {
+      "epoch": 0.9222520107238605,
+      "grad_norm": 0.33686619997024536,
+      "learning_rate": 0.00015573122529644268,
+      "loss": 0.5142088532447815,
+      "step": 86
+    },
+    {
+      "epoch": 0.9329758713136729,
+      "grad_norm": 0.325030654668808,
+      "learning_rate": 0.0001549407114624506,
+      "loss": 0.5654577016830444,
+      "step": 87
+    },
+    {
+      "epoch": 0.9436997319034852,
+      "grad_norm": 0.33111876249313354,
+      "learning_rate": 0.0001541501976284585,
+      "loss": 0.5170025825500488,
+      "step": 88
+    },
+    {
+      "epoch": 0.9544235924932976,
+      "grad_norm": 0.27954328060150146,
+      "learning_rate": 0.0001533596837944664,
+      "loss": 0.4477558135986328,
+      "step": 89
+    },
+    {
+      "epoch": 0.9651474530831099,
+      "grad_norm": 0.32940271496772766,
+      "learning_rate": 0.00015256916996047432,
+      "loss": 0.5770028829574585,
+      "step": 90
+    },
+    {
+      "epoch": 0.9758713136729222,
+      "grad_norm": 0.2901531755924225,
+      "learning_rate": 0.0001517786561264822,
+      "loss": 0.5113964080810547,
+      "step": 91
+    },
+    {
+      "epoch": 0.9865951742627346,
+      "grad_norm": 0.35382938385009766,
+      "learning_rate": 0.0001509881422924901,
+      "loss": 0.5637056827545166,
+      "step": 92
+    },
+    {
+      "epoch": 0.9973190348525469,
+      "grad_norm": 0.3409457802772522,
+      "learning_rate": 0.00015019762845849802,
+      "loss": 0.6113982200622559,
+      "step": 93
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9160968661308289,
+      "learning_rate": 0.00014940711462450593,
+      "loss": 0.6628789901733398,
+      "step": 94
+    },
+    {
+      "epoch": 1.0107238605898123,
+      "grad_norm": 0.29314255714416504,
+      "learning_rate": 0.00014861660079051384,
+      "loss": 0.46988680958747864,
+      "step": 95
+    },
+    {
+      "epoch": 1.0214477211796247,
+      "grad_norm": 0.25285112857818604,
+      "learning_rate": 0.00014782608695652173,
+      "loss": 0.37834423780441284,
+      "step": 96
+    },
+    {
+      "epoch": 1.032171581769437,
+      "grad_norm": 0.333655446767807,
+      "learning_rate": 0.00014703557312252964,
+      "loss": 0.4831538498401642,
+      "step": 97
+    },
+    {
+      "epoch": 1.0428954423592494,
+      "grad_norm": 0.2649567127227783,
+      "learning_rate": 0.00014624505928853755,
+      "loss": 0.41907089948654175,
+      "step": 98
+    },
+    {
+      "epoch": 1.0536193029490617,
+      "grad_norm": 0.27437201142311096,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.2983744144439697,
+      "step": 99
+    },
+    {
+      "epoch": 1.064343163538874,
+      "grad_norm": 0.3050195276737213,
+      "learning_rate": 0.00014466403162055337,
+      "loss": 0.3996342718601227,
+      "step": 100
+    },
+    {
+      "epoch": 1.0750670241286864,
+      "grad_norm": 0.31925857067108154,
+      "learning_rate": 0.00014387351778656125,
+      "loss": 0.5546276569366455,
+      "step": 101
+    },
+    {
+      "epoch": 1.0857908847184987,
+      "grad_norm": 0.32142284512519836,
+      "learning_rate": 0.00014308300395256916,
+      "loss": 0.4055824279785156,
+      "step": 102
+    },
+    {
+      "epoch": 1.096514745308311,
+      "grad_norm": 0.307692289352417,
+      "learning_rate": 0.00014229249011857707,
+      "loss": 0.3661179840564728,
+      "step": 103
+    },
+    {
+      "epoch": 1.1072386058981234,
+      "grad_norm": 0.3772393763065338,
+      "learning_rate": 0.00014150197628458498,
+      "loss": 0.33995968103408813,
+      "step": 104
+    },
+    {
+      "epoch": 1.1179624664879357,
+      "grad_norm": 0.33760136365890503,
+      "learning_rate": 0.0001407114624505929,
+      "loss": 0.3819088935852051,
+      "step": 105
+    },
+    {
+      "epoch": 1.128686327077748,
+      "grad_norm": 0.4074546694755554,
+      "learning_rate": 0.0001399209486166008,
+      "loss": 0.41713619232177734,
+      "step": 106
+    },
+    {
+      "epoch": 1.1394101876675604,
+      "grad_norm": 0.37227675318717957,
+      "learning_rate": 0.0001391304347826087,
+      "loss": 0.42982980608940125,
+      "step": 107
+    },
+    {
+      "epoch": 1.1501340482573728,
+      "grad_norm": 0.4107712209224701,
+      "learning_rate": 0.00013833992094861662,
+      "loss": 0.4299226403236389,
+      "step": 108
+    },
+    {
+      "epoch": 1.160857908847185,
+      "grad_norm": 0.5368478894233704,
+      "learning_rate": 0.00013754940711462453,
+      "loss": 0.5186800956726074,
+      "step": 109
+    },
+    {
+      "epoch": 1.1715817694369974,
+      "grad_norm": 0.45028287172317505,
+      "learning_rate": 0.00013675889328063244,
+      "loss": 0.5149720311164856,
+      "step": 110
+    },
+    {
+      "epoch": 1.1823056300268098,
+      "grad_norm": 0.34304189682006836,
+      "learning_rate": 0.00013596837944664032,
+      "loss": 0.375017374753952,
+      "step": 111
+    },
+    {
+      "epoch": 1.193029490616622,
+      "grad_norm": 0.32003459334373474,
+      "learning_rate": 0.00013517786561264823,
+      "loss": 0.34155839681625366,
+      "step": 112
+    },
+    {
+      "epoch": 1.2037533512064342,
+      "grad_norm": 0.3889811933040619,
+      "learning_rate": 0.00013438735177865614,
+      "loss": 0.40539929270744324,
+      "step": 113
+    },
+    {
+      "epoch": 1.2144772117962466,
+      "grad_norm": 0.3523079752922058,
+      "learning_rate": 0.00013359683794466405,
+      "loss": 0.458846777677536,
+      "step": 114
+    },
+    {
+      "epoch": 1.225201072386059,
+      "grad_norm": 0.37520793080329895,
+      "learning_rate": 0.00013280632411067196,
+      "loss": 0.39731982350349426,
+      "step": 115
+    },
+    {
+      "epoch": 1.2359249329758712,
+      "grad_norm": 0.4330201745033264,
+      "learning_rate": 0.00013201581027667985,
+      "loss": 0.5581794381141663,
+      "step": 116
+    },
+    {
+      "epoch": 1.2466487935656836,
+      "grad_norm": 0.3163258135318756,
+      "learning_rate": 0.00013122529644268776,
+      "loss": 0.3818089962005615,
+      "step": 117
+    },
+    {
+      "epoch": 1.257372654155496,
+      "grad_norm": 0.3622339069843292,
+      "learning_rate": 0.00013043478260869567,
+      "loss": 0.5328987240791321,
+      "step": 118
+    },
+    {
+      "epoch": 1.2680965147453083,
+      "grad_norm": 0.30175745487213135,
+      "learning_rate": 0.00012964426877470358,
+      "loss": 0.39232969284057617,
+      "step": 119
+    },
+    {
+      "epoch": 1.2788203753351206,
+      "grad_norm": 0.3683181703090668,
+      "learning_rate": 0.0001288537549407115,
+      "loss": 0.3934139013290405,
+      "step": 120
+    },
+    {
+      "epoch": 1.289544235924933,
+      "grad_norm": 0.3973405957221985,
+      "learning_rate": 0.00012806324110671937,
+      "loss": 0.43174073100090027,
+      "step": 121
+    },
+    {
+      "epoch": 1.3002680965147453,
+      "grad_norm": 0.33689525723457336,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.38391372561454773,
+      "step": 122
+    },
+    {
+      "epoch": 1.3109919571045576,
+      "grad_norm": 0.3917376399040222,
+      "learning_rate": 0.0001264822134387352,
+      "loss": 0.505753219127655,
+      "step": 123
+    },
+    {
+      "epoch": 1.32171581769437,
+      "grad_norm": 0.44805291295051575,
+      "learning_rate": 0.0001256916996047431,
+      "loss": 0.39223286509513855,
+      "step": 124
+    },
+    {
+      "epoch": 1.3324396782841823,
+      "grad_norm": 0.41950568556785583,
+      "learning_rate": 0.00012490118577075098,
+      "loss": 0.4417312741279602,
+      "step": 125
+    },
+    {
+      "epoch": 1.3431635388739946,
+      "grad_norm": 0.36143216490745544,
+      "learning_rate": 0.0001241106719367589,
+      "loss": 0.3527093231678009,
+      "step": 126
+    },
+    {
+      "epoch": 1.353887399463807,
+      "grad_norm": 0.3897385895252228,
+      "learning_rate": 0.0001233201581027668,
+      "loss": 0.3796389698982239,
+      "step": 127
+    },
+    {
+      "epoch": 1.3646112600536193,
+      "grad_norm": 0.36867862939834595,
+      "learning_rate": 0.00012252964426877472,
+      "loss": 0.3496738374233246,
+      "step": 128
+    },
+    {
+      "epoch": 1.3753351206434317,
+      "grad_norm": 0.4386043846607208,
+      "learning_rate": 0.00012173913043478263,
+      "loss": 0.5254644751548767,
+      "step": 129
+    },
+    {
+      "epoch": 1.386058981233244,
+      "grad_norm": 0.40041038393974304,
+      "learning_rate": 0.00012094861660079051,
+      "loss": 0.4998672604560852,
+      "step": 130
+    },
+    {
+      "epoch": 1.3967828418230563,
+      "grad_norm": 0.4058981239795685,
+      "learning_rate": 0.00012015810276679842,
+      "loss": 0.358295202255249,
+      "step": 131
+    },
+    {
+      "epoch": 1.4075067024128687,
+      "grad_norm": 0.4888080656528473,
+      "learning_rate": 0.00011936758893280633,
+      "loss": 0.4625028073787689,
+      "step": 132
+    },
+    {
+      "epoch": 1.418230563002681,
+      "grad_norm": 0.43401890993118286,
+      "learning_rate": 0.00011857707509881424,
+      "loss": 0.4242851138114929,
+      "step": 133
+    },
+    {
+      "epoch": 1.4289544235924934,
+      "grad_norm": 0.4579969346523285,
+      "learning_rate": 0.00011778656126482215,
+      "loss": 0.37796008586883545,
+      "step": 134
+    },
+    {
+      "epoch": 1.4396782841823057,
+      "grad_norm": 0.4127224385738373,
+      "learning_rate": 0.00011699604743083003,
+      "loss": 0.38415277004241943,
+      "step": 135
+    },
+    {
+      "epoch": 1.450402144772118,
+      "grad_norm": 0.47420403361320496,
+      "learning_rate": 0.00011620553359683794,
+      "loss": 0.42805853486061096,
+      "step": 136
+    },
+    {
+      "epoch": 1.4611260053619302,
+      "grad_norm": 0.549434244632721,
+      "learning_rate": 0.00011541501976284585,
+      "loss": 0.449143648147583,
+      "step": 137
+    },
+    {
+      "epoch": 1.4718498659517425,
+      "grad_norm": 0.45274561643600464,
+      "learning_rate": 0.00011462450592885376,
+      "loss": 0.42617177963256836,
+      "step": 138
+    },
+    {
+      "epoch": 1.4825737265415548,
+      "grad_norm": 0.4037245213985443,
+      "learning_rate": 0.00011383399209486167,
+      "loss": 0.4060184955596924,
+      "step": 139
+    },
+    {
+      "epoch": 1.4932975871313672,
+      "grad_norm": 0.35869210958480835,
+      "learning_rate": 0.00011304347826086956,
+      "loss": 0.3349171280860901,
+      "step": 140
+    },
+    {
+      "epoch": 1.5040214477211795,
+      "grad_norm": 0.4207170903682709,
+      "learning_rate": 0.00011225296442687747,
+      "loss": 0.4263383448123932,
+      "step": 141
+    },
+    {
+      "epoch": 1.5147453083109919,
+      "grad_norm": 0.5284790992736816,
+      "learning_rate": 0.00011146245059288538,
+      "loss": 0.5672209858894348,
+      "step": 142
+    },
+    {
+      "epoch": 1.5254691689008042,
+      "grad_norm": 0.41607561707496643,
+      "learning_rate": 0.00011067193675889329,
+      "loss": 0.4448755979537964,
+      "step": 143
+    },
+    {
+      "epoch": 1.5361930294906165,
+      "grad_norm": 0.4201499819755554,
+      "learning_rate": 0.0001098814229249012,
+      "loss": 0.46206071972846985,
+      "step": 144
+    },
+    {
+      "epoch": 1.5469168900804289,
+      "grad_norm": 0.4577239155769348,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.4559464454650879,
+      "step": 145
+    },
+    {
+      "epoch": 1.5576407506702412,
+      "grad_norm": 0.3478381931781769,
+      "learning_rate": 0.000108300395256917,
+      "loss": 0.3294685482978821,
+      "step": 146
+    },
+    {
+      "epoch": 1.5683646112600536,
+      "grad_norm": 0.4360603988170624,
+      "learning_rate": 0.00010750988142292491,
+      "loss": 0.3287108540534973,
+      "step": 147
+    },
+    {
+      "epoch": 1.579088471849866,
+      "grad_norm": 0.39799708127975464,
+      "learning_rate": 0.00010671936758893282,
+      "loss": 0.3988645374774933,
+      "step": 148
+    },
+    {
+      "epoch": 1.5898123324396782,
+      "grad_norm": 0.3618183732032776,
+      "learning_rate": 0.00010592885375494073,
+      "loss": 0.38425952196121216,
+      "step": 149
+    },
+    {
+      "epoch": 1.6005361930294906,
+      "grad_norm": 0.4565318524837494,
+      "learning_rate": 0.00010513833992094862,
+      "loss": 0.3619772493839264,
+      "step": 150
+    },
+    {
+      "epoch": 1.611260053619303,
+      "grad_norm": 0.3710864782333374,
+      "learning_rate": 0.00010434782608695653,
+      "loss": 0.34765082597732544,
+      "step": 151
+    },
+    {
+      "epoch": 1.6219839142091153,
+      "grad_norm": 0.43709254264831543,
+      "learning_rate": 0.00010355731225296444,
+      "loss": 0.36712560057640076,
+      "step": 152
+    },
+    {
+      "epoch": 1.6327077747989276,
+      "grad_norm": 0.41445794701576233,
+      "learning_rate": 0.00010276679841897235,
+      "loss": 0.46864867210388184,
+      "step": 153
+    },
+    {
+      "epoch": 1.64343163538874,
+      "grad_norm": 0.4972689747810364,
+      "learning_rate": 0.00010197628458498026,
+      "loss": 0.46844732761383057,
+      "step": 154
+    },
+    {
+      "epoch": 1.6541554959785523,
+      "grad_norm": 0.37691959738731384,
+      "learning_rate": 0.00010118577075098814,
+      "loss": 0.3644738793373108,
+      "step": 155
+    },
+    {
+      "epoch": 1.6648793565683646,
+      "grad_norm": 0.3355158269405365,
+      "learning_rate": 0.00010039525691699605,
+      "loss": 0.2941320538520813,
+      "step": 156
+    },
+    {
+      "epoch": 1.675603217158177,
+      "grad_norm": 0.47247281670570374,
+      "learning_rate": 9.960474308300396e-05,
+      "loss": 0.3141013979911804,
+      "step": 157
+    },
+    {
+      "epoch": 1.6863270777479893,
+      "grad_norm": 0.46272745728492737,
+      "learning_rate": 9.881422924901186e-05,
+      "loss": 0.36926206946372986,
+      "step": 158
+    },
+    {
+      "epoch": 1.6970509383378016,
+      "grad_norm": 0.38559988141059875,
+      "learning_rate": 9.802371541501977e-05,
+      "loss": 0.35696208477020264,
+      "step": 159
+    },
+    {
+      "epoch": 1.707774798927614,
+      "grad_norm": 0.380924791097641,
+      "learning_rate": 9.723320158102768e-05,
+      "loss": 0.3731119632720947,
+      "step": 160
+    },
+    {
+      "epoch": 1.7184986595174263,
+      "grad_norm": 0.3812347650527954,
+      "learning_rate": 9.644268774703557e-05,
+      "loss": 0.36795520782470703,
+      "step": 161
+    },
+    {
+      "epoch": 1.7292225201072386,
+      "grad_norm": 0.42182034254074097,
+      "learning_rate": 9.565217391304348e-05,
+      "loss": 0.38642388582229614,
+      "step": 162
+    },
+    {
+      "epoch": 1.739946380697051,
+      "grad_norm": 0.4464418292045593,
+      "learning_rate": 9.486166007905138e-05,
+      "loss": 0.3390141427516937,
+      "step": 163
+    },
+    {
+      "epoch": 1.7506702412868633,
+      "grad_norm": 0.41914135217666626,
+      "learning_rate": 9.407114624505929e-05,
+      "loss": 0.3221234679222107,
+      "step": 164
+    },
+    {
+      "epoch": 1.7613941018766757,
+      "grad_norm": 0.478661447763443,
+      "learning_rate": 9.32806324110672e-05,
+      "loss": 0.5106721520423889,
+      "step": 165
+    },
+    {
+      "epoch": 1.772117962466488,
+      "grad_norm": 0.4210912585258484,
+      "learning_rate": 9.24901185770751e-05,
+      "loss": 0.38831913471221924,
+      "step": 166
+    },
+    {
+      "epoch": 1.7828418230563003,
+      "grad_norm": 0.3871179223060608,
+      "learning_rate": 9.169960474308301e-05,
+      "loss": 0.34748589992523193,
+      "step": 167
+    },
+    {
+      "epoch": 1.7935656836461127,
+      "grad_norm": 0.4435052275657654,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.48339927196502686,
+      "step": 168
+    },
+    {
+      "epoch": 1.804289544235925,
+      "grad_norm": 0.4627319276332855,
+      "learning_rate": 9.011857707509881e-05,
+      "loss": 0.4779326319694519,
+      "step": 169
+    },
+    {
+      "epoch": 1.8150134048257374,
+      "grad_norm": 0.4093571603298187,
+      "learning_rate": 8.932806324110672e-05,
+      "loss": 0.3994932174682617,
+      "step": 170
+    },
+    {
+      "epoch": 1.8257372654155497,
+      "grad_norm": 0.3777295649051666,
+      "learning_rate": 8.853754940711463e-05,
+      "loss": 0.29758769273757935,
+      "step": 171
+    },
+    {
+      "epoch": 1.836461126005362,
+      "grad_norm": 0.4444163143634796,
+      "learning_rate": 8.774703557312254e-05,
+      "loss": 0.5211812257766724,
+      "step": 172
+    },
+    {
+      "epoch": 1.8471849865951744,
+      "grad_norm": 0.44008299708366394,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 0.4367752969264984,
+      "step": 173
+    },
+    {
+      "epoch": 1.8579088471849867,
+      "grad_norm": 0.3680829703807831,
+      "learning_rate": 8.616600790513835e-05,
+      "loss": 0.38142716884613037,
+      "step": 174
+    },
+    {
+      "epoch": 1.868632707774799,
+      "grad_norm": 0.42378222942352295,
+      "learning_rate": 8.537549407114625e-05,
+      "loss": 0.3738633394241333,
+      "step": 175
+    },
+    {
+      "epoch": 1.8793565683646114,
+      "grad_norm": 0.447982519865036,
+      "learning_rate": 8.458498023715416e-05,
+      "loss": 0.3980375826358795,
+      "step": 176
+    },
+    {
+      "epoch": 1.8900804289544237,
+      "grad_norm": 0.4780956506729126,
+      "learning_rate": 8.379446640316207e-05,
+      "loss": 0.3593772053718567,
+      "step": 177
+    },
+    {
+      "epoch": 1.900804289544236,
+      "grad_norm": 0.4041815996170044,
+      "learning_rate": 8.300395256916996e-05,
+      "loss": 0.32343748211860657,
+      "step": 178
+    },
+    {
+      "epoch": 1.9115281501340484,
+      "grad_norm": 0.40126705169677734,
+      "learning_rate": 8.221343873517787e-05,
+      "loss": 0.39796900749206543,
+      "step": 179
+    },
+    {
+      "epoch": 1.9222520107238605,
+      "grad_norm": 0.4228574335575104,
+      "learning_rate": 8.142292490118577e-05,
+      "loss": 0.30352118611335754,
+      "step": 180
+    },
+    {
+      "epoch": 1.9329758713136729,
+      "grad_norm": 0.3965367078781128,
+      "learning_rate": 8.063241106719368e-05,
+      "loss": 0.4007437229156494,
+      "step": 181
+    },
+    {
+      "epoch": 1.9436997319034852,
+      "grad_norm": 0.520819365978241,
+      "learning_rate": 7.984189723320159e-05,
+      "loss": 0.4561784863471985,
+      "step": 182
+    },
+    {
+      "epoch": 1.9544235924932976,
+      "grad_norm": 0.4546199142932892,
+      "learning_rate": 7.905138339920949e-05,
+      "loss": 0.42645519971847534,
+      "step": 183
+    },
+    {
+      "epoch": 1.96514745308311,
+      "grad_norm": 0.4249766170978546,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 0.40960007905960083,
+      "step": 184
+    },
+    {
+      "epoch": 1.9758713136729222,
+      "grad_norm": 0.43849310278892517,
+      "learning_rate": 7.74703557312253e-05,
+      "loss": 0.3888928294181824,
+      "step": 185
+    },
+    {
+      "epoch": 1.9865951742627346,
+      "grad_norm": 0.3805074095726013,
+      "learning_rate": 7.66798418972332e-05,
+      "loss": 0.33679670095443726,
+      "step": 186
+    },
+    {
+      "epoch": 1.997319034852547,
+      "grad_norm": 0.3982532024383545,
+      "learning_rate": 7.58893280632411e-05,
+      "loss": 0.4251680374145508,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8578111529350281,
+      "learning_rate": 7.509881422924901e-05,
+      "loss": 0.3112189769744873,
+      "step": 188
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 0.3796326518058777,
+      "learning_rate": 7.430830039525692e-05,
+      "loss": 0.3179461658000946,
+      "step": 189
+    },
+    {
+      "epoch": 2.0214477211796247,
+      "grad_norm": 0.4111069440841675,
+      "learning_rate": 7.351778656126482e-05,
+      "loss": 0.2951521873474121,
+      "step": 190
+    },
+    {
+      "epoch": 2.032171581769437,
+      "grad_norm": 0.47031712532043457,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.356897234916687,
+      "step": 191
+    },
+    {
+      "epoch": 2.0428954423592494,
+      "grad_norm": 0.42409181594848633,
+      "learning_rate": 7.193675889328062e-05,
+      "loss": 0.29118770360946655,
+      "step": 192
+    },
+    {
+      "epoch": 2.0536193029490617,
+      "grad_norm": 0.41851696372032166,
+      "learning_rate": 7.114624505928854e-05,
+      "loss": 0.28936752676963806,
+      "step": 193
+    },
+    {
+      "epoch": 2.064343163538874,
+      "grad_norm": 0.4010869264602661,
+      "learning_rate": 7.035573122529645e-05,
+      "loss": 0.26238322257995605,
+      "step": 194
+    },
+    {
+      "epoch": 2.0750670241286864,
+      "grad_norm": 0.3862994313240051,
+      "learning_rate": 6.956521739130436e-05,
+      "loss": 0.27142423391342163,
+      "step": 195
+    },
+    {
+      "epoch": 2.0857908847184987,
+      "grad_norm": 0.4864669442176819,
+      "learning_rate": 6.877470355731227e-05,
+      "loss": 0.37142568826675415,
+      "step": 196
+    },
+    {
+      "epoch": 2.096514745308311,
+      "grad_norm": 0.4558348059654236,
+      "learning_rate": 6.798418972332016e-05,
+      "loss": 0.24382558465003967,
+      "step": 197
+    },
+    {
+      "epoch": 2.1072386058981234,
+      "grad_norm": 0.4399399161338806,
+      "learning_rate": 6.719367588932807e-05,
+      "loss": 0.2435164749622345,
+      "step": 198
+    },
+    {
+      "epoch": 2.1179624664879357,
+      "grad_norm": 0.4485020041465759,
+      "learning_rate": 6.640316205533598e-05,
+      "loss": 0.2527099549770355,
+      "step": 199
+    },
+    {
+      "epoch": 2.128686327077748,
+      "grad_norm": 0.5087027549743652,
+      "learning_rate": 6.561264822134388e-05,
+      "loss": 0.2982422113418579,
+      "step": 200
+    },
+    {
+      "epoch": 2.1394101876675604,
+      "grad_norm": 0.48561012744903564,
+      "learning_rate": 6.482213438735179e-05,
+      "loss": 0.2485373616218567,
+      "step": 201
+    },
+    {
+      "epoch": 2.1501340482573728,
+      "grad_norm": 0.5011835098266602,
+      "learning_rate": 6.403162055335969e-05,
+      "loss": 0.2464626431465149,
+      "step": 202
+    },
+    {
+      "epoch": 2.160857908847185,
+      "grad_norm": 0.45680928230285645,
+      "learning_rate": 6.32411067193676e-05,
+      "loss": 0.2839566469192505,
+      "step": 203
+    },
+    {
+      "epoch": 2.1715817694369974,
+      "grad_norm": 0.4385458528995514,
+      "learning_rate": 6.245059288537549e-05,
+      "loss": 0.23959431052207947,
+      "step": 204
+    },
+    {
+      "epoch": 2.1823056300268098,
+      "grad_norm": 0.43261128664016724,
+      "learning_rate": 6.16600790513834e-05,
+      "loss": 0.21801936626434326,
+      "step": 205
+    },
+    {
+      "epoch": 2.193029490616622,
+      "grad_norm": 0.4627765715122223,
+      "learning_rate": 6.086956521739131e-05,
+      "loss": 0.23210036754608154,
+      "step": 206
+    },
+    {
+      "epoch": 2.2037533512064345,
+      "grad_norm": 0.502792477607727,
+      "learning_rate": 6.007905138339921e-05,
+      "loss": 0.2555053234100342,
+      "step": 207
+    },
+    {
+      "epoch": 2.214477211796247,
+      "grad_norm": 0.49858319759368896,
+      "learning_rate": 5.928853754940712e-05,
+      "loss": 0.37681910395622253,
+      "step": 208
+    },
+    {
+      "epoch": 2.225201072386059,
+      "grad_norm": 0.5667821764945984,
+      "learning_rate": 5.8498023715415016e-05,
+      "loss": 0.31617334485054016,
+      "step": 209
+    },
+    {
+      "epoch": 2.2359249329758715,
+      "grad_norm": 0.46932312846183777,
+      "learning_rate": 5.7707509881422926e-05,
+      "loss": 0.19316962361335754,
+      "step": 210
+    },
+    {
+      "epoch": 2.246648793565684,
+      "grad_norm": 0.6215251684188843,
+      "learning_rate": 5.6916996047430836e-05,
+      "loss": 0.3278288245201111,
+      "step": 211
+    },
+    {
+      "epoch": 2.257372654155496,
+      "grad_norm": 0.5422892570495605,
+      "learning_rate": 5.612648221343873e-05,
+      "loss": 0.291220486164093,
+      "step": 212
+    },
+    {
+      "epoch": 2.2680965147453085,
+      "grad_norm": 0.5241540670394897,
+      "learning_rate": 5.533596837944664e-05,
+      "loss": 0.24275189638137817,
+      "step": 213
+    },
+    {
+      "epoch": 2.278820375335121,
+      "grad_norm": 0.49944326281547546,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.34785425662994385,
+      "step": 214
+    },
+    {
+      "epoch": 2.289544235924933,
+      "grad_norm": 0.43588748574256897,
+      "learning_rate": 5.3754940711462456e-05,
+      "loss": 0.2969186305999756,
+      "step": 215
+    },
+    {
+      "epoch": 2.3002680965147455,
+      "grad_norm": 0.6216847896575928,
+      "learning_rate": 5.2964426877470366e-05,
+      "loss": 0.39824792742729187,
+      "step": 216
+    },
+    {
+      "epoch": 2.310991957104558,
+      "grad_norm": 0.4306747615337372,
+      "learning_rate": 5.217391304347826e-05,
+      "loss": 0.2311907559633255,
+      "step": 217
+    },
+    {
+      "epoch": 2.32171581769437,
+      "grad_norm": 0.40540629625320435,
+      "learning_rate": 5.138339920948617e-05,
+      "loss": 0.2750304937362671,
+      "step": 218
+    },
+    {
+      "epoch": 2.3324396782841825,
+      "grad_norm": 0.4646793305873871,
+      "learning_rate": 5.059288537549407e-05,
+      "loss": 0.3514980673789978,
+      "step": 219
+    },
+    {
+      "epoch": 2.343163538873995,
+      "grad_norm": 0.5125492215156555,
+      "learning_rate": 4.980237154150198e-05,
+      "loss": 0.2827247679233551,
+      "step": 220
+    },
+    {
+      "epoch": 2.353887399463807,
+      "grad_norm": 0.4126996099948883,
+      "learning_rate": 4.901185770750988e-05,
+      "loss": 0.28631478548049927,
+      "step": 221
+    },
+    {
+      "epoch": 2.3646112600536195,
+      "grad_norm": 0.554176926612854,
+      "learning_rate": 4.822134387351779e-05,
+      "loss": 0.2757015824317932,
+      "step": 222
+    },
+    {
+      "epoch": 2.3753351206434314,
+      "grad_norm": 0.498518168926239,
+      "learning_rate": 4.743083003952569e-05,
+      "loss": 0.4271239638328552,
+      "step": 223
+    },
+    {
+      "epoch": 2.386058981233244,
+      "grad_norm": 0.48358744382858276,
+      "learning_rate": 4.66403162055336e-05,
+      "loss": 0.24824775755405426,
+      "step": 224
+    },
+    {
+      "epoch": 2.396782841823056,
+      "grad_norm": 0.4421731233596802,
+      "learning_rate": 4.5849802371541504e-05,
+      "loss": 0.24138133227825165,
+      "step": 225
+    },
+    {
+      "epoch": 2.4075067024128685,
+      "grad_norm": 0.5678989291191101,
+      "learning_rate": 4.505928853754941e-05,
+      "loss": 0.3733794689178467,
+      "step": 226
+    },
+    {
+      "epoch": 2.418230563002681,
+      "grad_norm": 0.3931693434715271,
+      "learning_rate": 4.426877470355732e-05,
+      "loss": 0.21732917428016663,
+      "step": 227
+    },
+    {
+      "epoch": 2.428954423592493,
+      "grad_norm": 0.5858852863311768,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.27989453077316284,
+      "step": 228
+    },
+    {
+      "epoch": 2.4396782841823055,
+      "grad_norm": 0.563900887966156,
+      "learning_rate": 4.2687747035573124e-05,
+      "loss": 0.24179348349571228,
+      "step": 229
+    },
+    {
+      "epoch": 2.450402144772118,
+      "grad_norm": 0.560583233833313,
+      "learning_rate": 4.1897233201581034e-05,
+      "loss": 0.32947486639022827,
+      "step": 230
+    },
+    {
+      "epoch": 2.46112600536193,
+      "grad_norm": 0.44924235343933105,
+      "learning_rate": 4.110671936758894e-05,
+      "loss": 0.22358451783657074,
+      "step": 231
+    },
+    {
+      "epoch": 2.4718498659517425,
+      "grad_norm": 0.45432764291763306,
+      "learning_rate": 4.031620553359684e-05,
+      "loss": 0.27067574858665466,
+      "step": 232
+    },
+    {
+      "epoch": 2.482573726541555,
+      "grad_norm": 0.593735933303833,
+      "learning_rate": 3.9525691699604744e-05,
+      "loss": 0.2724727988243103,
+      "step": 233
+    },
+    {
+      "epoch": 2.493297587131367,
+      "grad_norm": 0.4509212374687195,
+      "learning_rate": 3.873517786561265e-05,
+      "loss": 0.2286791056394577,
+      "step": 234
+    },
+    {
+      "epoch": 2.5040214477211795,
+      "grad_norm": 0.574708104133606,
+      "learning_rate": 3.794466403162055e-05,
+      "loss": 0.39047005772590637,
+      "step": 235
+    },
+    {
+      "epoch": 2.514745308310992,
+      "grad_norm": 0.4967159330844879,
+      "learning_rate": 3.715415019762846e-05,
+      "loss": 0.3607536852359772,
+      "step": 236
+    },
+    {
+      "epoch": 2.525469168900804,
+      "grad_norm": 0.5810816884040833,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.28996798396110535,
+      "step": 237
+    },
+    {
+      "epoch": 2.5361930294906165,
+      "grad_norm": 0.605388879776001,
+      "learning_rate": 3.557312252964427e-05,
+      "loss": 0.3083586096763611,
+      "step": 238
+    },
+    {
+      "epoch": 2.546916890080429,
+      "grad_norm": 0.5502549409866333,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 0.26683732867240906,
+      "step": 239
+    },
+    {
+      "epoch": 2.557640750670241,
+      "grad_norm": 0.5668724179267883,
+      "learning_rate": 3.399209486166008e-05,
+      "loss": 0.2840242385864258,
+      "step": 240
+    },
+    {
+      "epoch": 2.5683646112600536,
+      "grad_norm": 0.44743263721466064,
+      "learning_rate": 3.320158102766799e-05,
+      "loss": 0.2404075413942337,
+      "step": 241
+    },
+    {
+      "epoch": 2.579088471849866,
+      "grad_norm": 0.7013267278671265,
+      "learning_rate": 3.2411067193675894e-05,
+      "loss": 0.3185945749282837,
+      "step": 242
+    },
+    {
+      "epoch": 2.5898123324396782,
+      "grad_norm": 0.6694422364234924,
+      "learning_rate": 3.16205533596838e-05,
+      "loss": 0.28978461027145386,
+      "step": 243
+    },
+    {
+      "epoch": 2.6005361930294906,
+      "grad_norm": 0.4603322446346283,
+      "learning_rate": 3.08300395256917e-05,
+      "loss": 0.2629821002483368,
+      "step": 244
+    },
+    {
+      "epoch": 2.611260053619303,
+      "grad_norm": 0.5630055665969849,
+      "learning_rate": 3.0039525691699605e-05,
+      "loss": 0.2665753960609436,
+      "step": 245
+    },
+    {
+      "epoch": 2.6219839142091153,
+      "grad_norm": 0.3915822207927704,
+      "learning_rate": 2.9249011857707508e-05,
+      "loss": 0.2179432064294815,
+      "step": 246
+    },
+    {
+      "epoch": 2.6327077747989276,
+      "grad_norm": 0.5798822045326233,
+      "learning_rate": 2.8458498023715418e-05,
+      "loss": 0.31813907623291016,
+      "step": 247
+    },
+    {
+      "epoch": 2.64343163538874,
+      "grad_norm": 0.5073499083518982,
+      "learning_rate": 2.766798418972332e-05,
+      "loss": 0.2670523524284363,
+      "step": 248
+    },
+    {
+      "epoch": 2.6541554959785523,
+      "grad_norm": 0.44620683789253235,
+      "learning_rate": 2.6877470355731228e-05,
+      "loss": 0.25869786739349365,
+      "step": 249
+    },
+    {
+      "epoch": 2.6648793565683646,
+      "grad_norm": 0.5914870500564575,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.3205704391002655,
+      "step": 250
+    },
+    {
+      "epoch": 2.675603217158177,
+      "grad_norm": 0.5035210251808167,
+      "learning_rate": 2.5296442687747035e-05,
+      "loss": 0.2746676504611969,
+      "step": 251
+    },
+    {
+      "epoch": 2.6863270777479893,
+      "grad_norm": 0.4630255103111267,
+      "learning_rate": 2.450592885375494e-05,
+      "loss": 0.262162446975708,
+      "step": 252
+    },
+    {
+      "epoch": 2.6970509383378016,
+      "grad_norm": 0.5340390205383301,
+      "learning_rate": 2.3715415019762845e-05,
+      "loss": 0.22825723886489868,
+      "step": 253
+    },
+    {
+      "epoch": 2.707774798927614,
+      "grad_norm": 0.555592954158783,
+      "learning_rate": 2.2924901185770752e-05,
+      "loss": 0.24794229865074158,
+      "step": 254
+    },
+    {
+      "epoch": 2.7184986595174263,
+      "grad_norm": 0.4784729480743408,
+      "learning_rate": 2.213438735177866e-05,
+      "loss": 0.20105186104774475,
+      "step": 255
+    },
+    {
+      "epoch": 2.7292225201072386,
+      "grad_norm": 0.7181131839752197,
+      "learning_rate": 2.1343873517786562e-05,
+      "loss": 0.3564614951610565,
+      "step": 256
+    },
+    {
+      "epoch": 2.739946380697051,
+      "grad_norm": 0.4376419484615326,
+      "learning_rate": 2.055335968379447e-05,
+      "loss": 0.20554706454277039,
+      "step": 257
+    },
+    {
+      "epoch": 2.7506702412868633,
+      "grad_norm": 0.5815340876579285,
+      "learning_rate": 1.9762845849802372e-05,
+      "loss": 0.2694174349308014,
+      "step": 258
+    },
+    {
+      "epoch": 2.7613941018766757,
+      "grad_norm": 0.48075157403945923,
+      "learning_rate": 1.8972332015810275e-05,
+      "loss": 0.21963372826576233,
+      "step": 259
+    },
+    {
+      "epoch": 2.772117962466488,
+      "grad_norm": 0.620573103427887,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.3293127715587616,
+      "step": 260
+    },
+    {
+      "epoch": 2.7828418230563003,
+      "grad_norm": 0.5430031418800354,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.25511273741722107,
+      "step": 261
+    },
+    {
+      "epoch": 2.7935656836461127,
+      "grad_norm": 0.6154038906097412,
+      "learning_rate": 1.6600790513833996e-05,
+      "loss": 0.28183019161224365,
+      "step": 262
+    },
+    {
+      "epoch": 2.804289544235925,
+      "grad_norm": 0.5438246726989746,
+      "learning_rate": 1.58102766798419e-05,
+      "loss": 0.2609254717826843,
+      "step": 263
+    },
+    {
+      "epoch": 2.8150134048257374,
+      "grad_norm": 0.671107828617096,
+      "learning_rate": 1.5019762845849802e-05,
+      "loss": 0.3069862723350525,
+      "step": 264
+    },
+    {
+      "epoch": 2.8257372654155497,
+      "grad_norm": 0.5226935148239136,
+      "learning_rate": 1.4229249011857709e-05,
+      "loss": 0.2255355566740036,
+      "step": 265
+    },
+    {
+      "epoch": 2.836461126005362,
+      "grad_norm": 0.5719597339630127,
+      "learning_rate": 1.3438735177865614e-05,
+      "loss": 0.2844502329826355,
+      "step": 266
+    },
+    {
+      "epoch": 2.8471849865951744,
+      "grad_norm": 0.5313884615898132,
+      "learning_rate": 1.2648221343873517e-05,
+      "loss": 0.3107653558254242,
+      "step": 267
+    },
+    {
+      "epoch": 2.8579088471849867,
+      "grad_norm": 0.5169429183006287,
+      "learning_rate": 1.1857707509881423e-05,
+      "loss": 0.2877541184425354,
+      "step": 268
+    },
+    {
+      "epoch": 2.868632707774799,
+      "grad_norm": 0.5085014700889587,
+      "learning_rate": 1.106719367588933e-05,
+      "loss": 0.21509462594985962,
+      "step": 269
+    },
+    {
+      "epoch": 2.8793565683646114,
+      "grad_norm": 0.4762232005596161,
+      "learning_rate": 1.0276679841897234e-05,
+      "loss": 0.23946139216423035,
+      "step": 270
+    },
+    {
+      "epoch": 2.8900804289544237,
+      "grad_norm": 0.5875873565673828,
+      "learning_rate": 9.486166007905138e-06,
+      "loss": 0.288002073764801,
+      "step": 271
+    },
+    {
+      "epoch": 2.900804289544236,
+      "grad_norm": 0.6287146210670471,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.28586676716804504,
+      "step": 272
+    },
+    {
+      "epoch": 2.9115281501340484,
+      "grad_norm": 0.5751309990882874,
+      "learning_rate": 7.90513833992095e-06,
+      "loss": 0.26002803444862366,
+      "step": 273
+    },
+    {
+      "epoch": 2.9222520107238603,
+      "grad_norm": 0.5319899916648865,
+      "learning_rate": 7.1146245059288545e-06,
+      "loss": 0.2816118597984314,
+      "step": 274
+    },
+    {
+      "epoch": 2.9329758713136727,
+      "grad_norm": 0.580845057964325,
+      "learning_rate": 6.324110671936759e-06,
+      "loss": 0.2594989538192749,
+      "step": 275
+    },
+    {
+      "epoch": 2.943699731903485,
+      "grad_norm": 0.6090609431266785,
+      "learning_rate": 5.533596837944665e-06,
+      "loss": 0.30808189511299133,
+      "step": 276
+    },
+    {
+      "epoch": 2.9544235924932973,
+      "grad_norm": 0.5708959698677063,
+      "learning_rate": 4.743083003952569e-06,
+      "loss": 0.3111344873905182,
+      "step": 277
+    },
+    {
+      "epoch": 2.9651474530831097,
+      "grad_norm": 0.4517657458782196,
+      "learning_rate": 3.952569169960475e-06,
+      "loss": 0.244952991604805,
+      "step": 278
+    },
+    {
+      "epoch": 2.975871313672922,
+      "grad_norm": 0.4914667308330536,
+      "learning_rate": 3.1620553359683794e-06,
+      "loss": 0.25697410106658936,
+      "step": 279
+    },
+    {
+      "epoch": 2.9865951742627344,
+      "grad_norm": 0.5489192008972168,
+      "learning_rate": 2.3715415019762844e-06,
+      "loss": 0.2900347113609314,
+      "step": 280
+    },
+    {
+      "epoch": 2.9973190348525467,
+      "grad_norm": 0.5205079317092896,
+      "learning_rate": 1.5810276679841897e-06,
+      "loss": 0.2045833170413971,
+      "step": 281
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3801476955413818,
+      "learning_rate": 7.905138339920948e-07,
+      "loss": 0.26903223991394043,
+      "step": 282
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 282,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.313385319070822e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810652308d1bd961da68dc1a1b883e585e00e0951cb1a6e53cae01144f3413dc
+size 5713

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}