Upload full pipeline: CPT/SFT/DPO/warmup/GRPO

.gitattributes

@@ -33,3 +33,25 @@ 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
+models/cpt_qwen06/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-131/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06/final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/cpt_qwen06_merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/dpo_qwen06/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/dpo_qwen06/checkpoint-77/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/dpo_qwen06/final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_qwen06/llm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_qwen06/llm_best_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/reasoning_warmup_qwen06/checkpoint-3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/reasoning_warmup_qwen06/final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/reasoning_warmup_qwen06_merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/sft_qwen06/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/sft_qwen06/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/sft_qwen06/checkpoint-198/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/sft_qwen06/final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/sft_qwen06_merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text

models/cpt_qwen06/README.md

@@ -0,0 +1,59 @@
+---
+base_model: unsloth/Qwen3-0.6B-unsloth-bnb-4bit
+library_name: transformers
+model_name: cpt_qwen06
+tags:
+- generated_from_trainer
+- unsloth
+- trl
+- sft
+licence: license
+---
+
+# Model Card for cpt_qwen06
+
+This model is a fine-tuned version of [unsloth/Qwen3-0.6B-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen3-0.6B-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.1
+- Transformers: 4.57.6
+- Pytorch: 2.11.0+cu130
+- Datasets: 3.6.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

models/cpt_qwen06/checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-0.6B-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-0.6B-unsloth-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 0.21.2

models/cpt_qwen06/checkpoint-100/adapter_config.json

@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-0.6B-unsloth-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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

models/cpt_qwen06/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ced588793aeb07223ea3715899af5b366682b2dd0792c2e11cc1274fd78fb5
+size 80792456

models/cpt_qwen06/checkpoint-100/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

models/cpt_qwen06/checkpoint-100/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

models/cpt_qwen06/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036c3ccd57bcf7d47551888db6250064799259e9721cece0e36da5108210e47e
+size 41464389

models/cpt_qwen06/checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27978b0c0a2d70a6d9e24fba0f2ed928bba9b47aecb6cc92523c33dd4a9bc29f
+size 14917

models/cpt_qwen06/checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4883ea9e9e4170ef036b08f27772e01a500be9d13e3c9492d90b6357d7e8c6
+size 14917

models/cpt_qwen06/checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

models/cpt_qwen06/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2997f6fc6c33c711fb53858d1a69ac4384340e2ad03a075af4fc14e03e13550
+size 1401

models/cpt_qwen06/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/cpt_qwen06/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

models/cpt_qwen06/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

models/cpt_qwen06/checkpoint-100/trainer_state.json

@@ -0,0 +1,783 @@
+{
+  "best_global_step": 100,
+  "best_metric": 3.2493093013763428,
+  "best_model_checkpoint": "models/cpt_qwen06/checkpoint-100",
+  "epoch": 0.7633587786259542,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007633587786259542,
+      "grad_norm": 1.1038203239440918,
+      "learning_rate": 0.0,
+      "loss": 3.6412,
+      "step": 1
+    },
+    {
+      "epoch": 0.015267175572519083,
+      "grad_norm": 0.9980769753456116,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.5055,
+      "step": 2
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "grad_norm": 1.1173980236053467,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.8714,
+      "step": 3
+    },
+    {
+      "epoch": 0.030534351145038167,
+      "grad_norm": 1.083743929862976,
+      "learning_rate": 6e-06,
+      "loss": 3.7176,
+      "step": 4
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "grad_norm": 1.0839077234268188,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.6602,
+      "step": 5
+    },
+    {
+      "epoch": 0.04580152671755725,
+      "grad_norm": 1.1065247058868408,
+      "learning_rate": 1e-05,
+      "loss": 3.7578,
+      "step": 6
+    },
+    {
+      "epoch": 0.05343511450381679,
+      "grad_norm": 0.9514145255088806,
+      "learning_rate": 1.2e-05,
+      "loss": 3.4766,
+      "step": 7
+    },
+    {
+      "epoch": 0.061068702290076333,
+      "grad_norm": 0.9837572574615479,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 3.6449,
+      "step": 8
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "grad_norm": 0.8067060708999634,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.1398,
+      "step": 9
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "grad_norm": 0.893821120262146,
+      "learning_rate": 1.8e-05,
+      "loss": 3.6806,
+      "step": 10
+    },
+    {
+      "epoch": 0.08396946564885496,
+      "grad_norm": 0.8949201107025146,
+      "learning_rate": 2e-05,
+      "loss": 3.548,
+      "step": 11
+    },
+    {
+      "epoch": 0.0916030534351145,
+      "grad_norm": 0.8128786683082581,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 3.5283,
+      "step": 12
+    },
+    {
+      "epoch": 0.09923664122137404,
+      "grad_norm": 0.7861769199371338,
+      "learning_rate": 2.4e-05,
+      "loss": 3.7057,
+      "step": 13
+    },
+    {
+      "epoch": 0.10687022900763359,
+      "grad_norm": 0.7354120016098022,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 3.6656,
+      "step": 14
+    },
+    {
+      "epoch": 0.11450381679389313,
+      "grad_norm": 0.6324082612991333,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 3.4134,
+      "step": 15
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 0.637443482875824,
+      "learning_rate": 3e-05,
+      "loss": 3.6464,
+      "step": 16
+    },
+    {
+      "epoch": 0.1297709923664122,
+      "grad_norm": 0.5686759352684021,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.533,
+      "step": 17
+    },
+    {
+      "epoch": 0.13740458015267176,
+      "grad_norm": 0.5156700015068054,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 3.4371,
+      "step": 18
+    },
+    {
+      "epoch": 0.1450381679389313,
+      "grad_norm": 0.46492844820022583,
+      "learning_rate": 3.6e-05,
+      "loss": 3.3725,
+      "step": 19
+    },
+    {
+      "epoch": 0.15267175572519084,
+      "grad_norm": 0.46070176362991333,
+      "learning_rate": 3.8e-05,
+      "loss": 3.4512,
+      "step": 20
+    },
+    {
+      "epoch": 0.15267175572519084,
+      "eval_loss": 3.5234994888305664,
+      "eval_runtime": 58.557,
+      "eval_samples_per_second": 47.8,
+      "eval_steps_per_second": 2.989,
+      "step": 20
+    },
+    {
+      "epoch": 0.16030534351145037,
+      "grad_norm": 0.44954392313957214,
+      "learning_rate": 4e-05,
+      "loss": 3.4475,
+      "step": 21
+    },
+    {
+      "epoch": 0.16793893129770993,
+      "grad_norm": 0.44157543778419495,
+      "learning_rate": 4.2e-05,
+      "loss": 3.5426,
+      "step": 22
+    },
+    {
+      "epoch": 0.17557251908396945,
+      "grad_norm": 0.4325191080570221,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 3.4231,
+      "step": 23
+    },
+    {
+      "epoch": 0.183206106870229,
+      "grad_norm": 0.4093230068683624,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 3.0474,
+      "step": 24
+    },
+    {
+      "epoch": 0.19083969465648856,
+      "grad_norm": 0.3982406258583069,
+      "learning_rate": 4.8e-05,
+      "loss": 3.2979,
+      "step": 25
+    },
+    {
+      "epoch": 0.1984732824427481,
+      "grad_norm": 0.4215850234031677,
+      "learning_rate": 5e-05,
+      "loss": 3.194,
+      "step": 26
+    },
+    {
+      "epoch": 0.20610687022900764,
+      "grad_norm": 0.4356484115123749,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 3.4239,
+      "step": 27
+    },
+    {
+      "epoch": 0.21374045801526717,
+      "grad_norm": 0.4056006371974945,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 3.1843,
+      "step": 28
+    },
+    {
+      "epoch": 0.22137404580152673,
+      "grad_norm": 0.42187467217445374,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 3.3005,
+      "step": 29
+    },
+    {
+      "epoch": 0.22900763358778625,
+      "grad_norm": 0.40015560388565063,
+      "learning_rate": 5.8e-05,
+      "loss": 3.3383,
+      "step": 30
+    },
+    {
+      "epoch": 0.2366412213740458,
+      "grad_norm": 0.37207528948783875,
+      "learning_rate": 6e-05,
+      "loss": 3.2635,
+      "step": 31
+    },
+    {
+      "epoch": 0.24427480916030533,
+      "grad_norm": 0.38520580530166626,
+      "learning_rate": 6.2e-05,
+      "loss": 3.4361,
+      "step": 32
+    },
+    {
+      "epoch": 0.25190839694656486,
+      "grad_norm": 0.36966952681541443,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 3.3166,
+      "step": 33
+    },
+    {
+      "epoch": 0.2595419847328244,
+      "grad_norm": 0.34806883335113525,
+      "learning_rate": 6.6e-05,
+      "loss": 3.2605,
+      "step": 34
+    },
+    {
+      "epoch": 0.26717557251908397,
+      "grad_norm": 0.35267260670661926,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 3.289,
+      "step": 35
+    },
+    {
+      "epoch": 0.2748091603053435,
+      "grad_norm": 0.3521084189414978,
+      "learning_rate": 7e-05,
+      "loss": 3.3185,
+      "step": 36
+    },
+    {
+      "epoch": 0.2824427480916031,
+      "grad_norm": 0.3386003375053406,
+      "learning_rate": 7.2e-05,
+      "loss": 2.9975,
+      "step": 37
+    },
+    {
+      "epoch": 0.2900763358778626,
+      "grad_norm": 0.3720523416996002,
+      "learning_rate": 7.4e-05,
+      "loss": 3.1835,
+      "step": 38
+    },
+    {
+      "epoch": 0.29770992366412213,
+      "grad_norm": 0.3777226209640503,
+      "learning_rate": 7.6e-05,
+      "loss": 3.4832,
+      "step": 39
+    },
+    {
+      "epoch": 0.3053435114503817,
+      "grad_norm": 0.3729304373264313,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 3.2914,
+      "step": 40
+    },
+    {
+      "epoch": 0.3053435114503817,
+      "eval_loss": 3.3862099647521973,
+      "eval_runtime": 61.0656,
+      "eval_samples_per_second": 45.836,
+      "eval_steps_per_second": 2.866,
+      "step": 40
+    },
+    {
+      "epoch": 0.31297709923664124,
+      "grad_norm": 0.3766719698905945,
+      "learning_rate": 8e-05,
+      "loss": 3.1556,
+      "step": 41
+    },
+    {
+      "epoch": 0.32061068702290074,
+      "grad_norm": 0.35788893699645996,
+      "learning_rate": 8.2e-05,
+      "loss": 3.2917,
+      "step": 42
+    },
+    {
+      "epoch": 0.3282442748091603,
+      "grad_norm": 0.3242752254009247,
+      "learning_rate": 8.4e-05,
+      "loss": 3.1016,
+      "step": 43
+    },
+    {
+      "epoch": 0.33587786259541985,
+      "grad_norm": 0.3300817310810089,
+      "learning_rate": 8.6e-05,
+      "loss": 3.2377,
+      "step": 44
+    },
+    {
+      "epoch": 0.3435114503816794,
+      "grad_norm": 0.34662845730781555,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 3.2279,
+      "step": 45
+    },
+    {
+      "epoch": 0.3511450381679389,
+      "grad_norm": 0.32657670974731445,
+      "learning_rate": 9e-05,
+      "loss": 3.1033,
+      "step": 46
+    },
+    {
+      "epoch": 0.35877862595419846,
+      "grad_norm": 0.34357091784477234,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 3.1189,
+      "step": 47
+    },
+    {
+      "epoch": 0.366412213740458,
+      "grad_norm": 0.3785499036312103,
+      "learning_rate": 9.4e-05,
+      "loss": 3.2173,
+      "step": 48
+    },
+    {
+      "epoch": 0.37404580152671757,
+      "grad_norm": 0.3414277732372284,
+      "learning_rate": 9.6e-05,
+      "loss": 3.3226,
+      "step": 49
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "grad_norm": 0.3392898738384247,
+      "learning_rate": 9.8e-05,
+      "loss": 3.1916,
+      "step": 50
+    },
+    {
+      "epoch": 0.3893129770992366,
+      "grad_norm": 0.339979887008667,
+      "learning_rate": 0.0001,
+      "loss": 3.2239,
+      "step": 51
+    },
+    {
+      "epoch": 0.3969465648854962,
+      "grad_norm": 0.3153935372829437,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 2.9154,
+      "step": 52
+    },
+    {
+      "epoch": 0.40458015267175573,
+      "grad_norm": 0.33739224076271057,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 3.0835,
+      "step": 53
+    },
+    {
+      "epoch": 0.4122137404580153,
+      "grad_norm": 0.3399827480316162,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 3.2772,
+      "step": 54
+    },
+    {
+      "epoch": 0.4198473282442748,
+      "grad_norm": 0.3547399342060089,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 3.2374,
+      "step": 55
+    },
+    {
+      "epoch": 0.42748091603053434,
+      "grad_norm": 0.3382011950016022,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 3.1897,
+      "step": 56
+    },
+    {
+      "epoch": 0.4351145038167939,
+      "grad_norm": 0.32772088050842285,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 3.1473,
+      "step": 57
+    },
+    {
+      "epoch": 0.44274809160305345,
+      "grad_norm": 0.36062091588974,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 3.213,
+      "step": 58
+    },
+    {
+      "epoch": 0.45038167938931295,
+      "grad_norm": 0.3231198191642761,
+      "learning_rate": 0.000116,
+      "loss": 3.0341,
+      "step": 59
+    },
+    {
+      "epoch": 0.4580152671755725,
+      "grad_norm": 0.3362651765346527,
+      "learning_rate": 0.000118,
+      "loss": 3.2224,
+      "step": 60
+    },
+    {
+      "epoch": 0.4580152671755725,
+      "eval_loss": 3.3177616596221924,
+      "eval_runtime": 63.8472,
+      "eval_samples_per_second": 43.839,
+      "eval_steps_per_second": 2.741,
+      "step": 60
+    },
+    {
+      "epoch": 0.46564885496183206,
+      "grad_norm": 0.34038835763931274,
+      "learning_rate": 0.00012,
+      "loss": 3.1725,
+      "step": 61
+    },
+    {
+      "epoch": 0.4732824427480916,
+      "grad_norm": 0.3445279598236084,
+      "learning_rate": 0.000122,
+      "loss": 3.437,
+      "step": 62
+    },
+    {
+      "epoch": 0.48091603053435117,
+      "grad_norm": 0.3481975793838501,
+      "learning_rate": 0.000124,
+      "loss": 3.1468,
+      "step": 63
+    },
+    {
+      "epoch": 0.48854961832061067,
+      "grad_norm": 0.33724287152290344,
+      "learning_rate": 0.000126,
+      "loss": 3.0521,
+      "step": 64
+    },
+    {
+      "epoch": 0.4961832061068702,
+      "grad_norm": 0.3660881817340851,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 3.2244,
+      "step": 65
+    },
+    {
+      "epoch": 0.5038167938931297,
+      "grad_norm": 0.3626140058040619,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 3.2069,
+      "step": 66
+    },
+    {
+      "epoch": 0.5114503816793893,
+      "grad_norm": 0.34741154313087463,
+      "learning_rate": 0.000132,
+      "loss": 3.2547,
+      "step": 67
+    },
+    {
+      "epoch": 0.5190839694656488,
+      "grad_norm": 0.344104140996933,
+      "learning_rate": 0.000134,
+      "loss": 2.9396,
+      "step": 68
+    },
+    {
+      "epoch": 0.5267175572519084,
+      "grad_norm": 0.3456694185733795,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 3.1505,
+      "step": 69
+    },
+    {
+      "epoch": 0.5343511450381679,
+      "grad_norm": 0.3567255735397339,
+      "learning_rate": 0.000138,
+      "loss": 3.2136,
+      "step": 70
+    },
+    {
+      "epoch": 0.5419847328244275,
+      "grad_norm": 0.3521654009819031,
+      "learning_rate": 0.00014,
+      "loss": 2.9877,
+      "step": 71
+    },
+    {
+      "epoch": 0.549618320610687,
+      "grad_norm": 0.3765776753425598,
+      "learning_rate": 0.000142,
+      "loss": 3.1552,
+      "step": 72
+    },
+    {
+      "epoch": 0.5572519083969466,
+      "grad_norm": 0.36426547169685364,
+      "learning_rate": 0.000144,
+      "loss": 3.2685,
+      "step": 73
+    },
+    {
+      "epoch": 0.5648854961832062,
+      "grad_norm": 0.3653399348258972,
+      "learning_rate": 0.000146,
+      "loss": 3.2527,
+      "step": 74
+    },
+    {
+      "epoch": 0.5725190839694656,
+      "grad_norm": 0.35804226994514465,
+      "learning_rate": 0.000148,
+      "loss": 3.1865,
+      "step": 75
+    },
+    {
+      "epoch": 0.5801526717557252,
+      "grad_norm": 0.3470200300216675,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.0362,
+      "step": 76
+    },
+    {
+      "epoch": 0.5877862595419847,
+      "grad_norm": 0.3770173192024231,
+      "learning_rate": 0.000152,
+      "loss": 3.1248,
+      "step": 77
+    },
+    {
+      "epoch": 0.5954198473282443,
+      "grad_norm": 0.35332971811294556,
+      "learning_rate": 0.000154,
+      "loss": 2.7595,
+      "step": 78
+    },
+    {
+      "epoch": 0.6030534351145038,
+      "grad_norm": 0.3616713285446167,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 3.1264,
+      "step": 79
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "grad_norm": 0.37358736991882324,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 3.2264,
+      "step": 80
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "eval_loss": 3.272794246673584,
+      "eval_runtime": 64.8828,
+      "eval_samples_per_second": 43.139,
+      "eval_steps_per_second": 2.697,
+      "step": 80
+    },
+    {
+      "epoch": 0.6183206106870229,
+      "grad_norm": 0.4232015311717987,
+      "learning_rate": 0.00016,
+      "loss": 3.4534,
+      "step": 81
+    },
+    {
+      "epoch": 0.6259541984732825,
+      "grad_norm": 0.391012042760849,
+      "learning_rate": 0.000162,
+      "loss": 2.9921,
+      "step": 82
+    },
+    {
+      "epoch": 0.6335877862595419,
+      "grad_norm": 0.4178006052970886,
+      "learning_rate": 0.000164,
+      "loss": 3.0948,
+      "step": 83
+    },
+    {
+      "epoch": 0.6412213740458015,
+      "grad_norm": 0.3803626596927643,
+      "learning_rate": 0.000166,
+      "loss": 2.9039,
+      "step": 84
+    },
+    {
+      "epoch": 0.648854961832061,
+      "grad_norm": 0.3924623131752014,
+      "learning_rate": 0.000168,
+      "loss": 3.087,
+      "step": 85
+    },
+    {
+      "epoch": 0.6564885496183206,
+      "grad_norm": 0.38232532143592834,
+      "learning_rate": 0.00017,
+      "loss": 2.8771,
+      "step": 86
+    },
+    {
+      "epoch": 0.6641221374045801,
+      "grad_norm": 0.41317063570022583,
+      "learning_rate": 0.000172,
+      "loss": 3.2177,
+      "step": 87
+    },
+    {
+      "epoch": 0.6717557251908397,
+      "grad_norm": 0.3906857669353485,
+      "learning_rate": 0.000174,
+      "loss": 3.0091,
+      "step": 88
+    },
+    {
+      "epoch": 0.6793893129770993,
+      "grad_norm": 0.39958348870277405,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 2.9797,
+      "step": 89
+    },
+    {
+      "epoch": 0.6870229007633588,
+      "grad_norm": 0.38834550976753235,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 3.147,
+      "step": 90
+    },
+    {
+      "epoch": 0.6946564885496184,
+      "grad_norm": 0.40388867259025574,
+      "learning_rate": 0.00018,
+      "loss": 3.1668,
+      "step": 91
+    },
+    {
+      "epoch": 0.7022900763358778,
+      "grad_norm": 0.3906465172767639,
+      "learning_rate": 0.000182,
+      "loss": 3.1451,
+      "step": 92
+    },
+    {
+      "epoch": 0.7099236641221374,
+      "grad_norm": 0.40879368782043457,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 3.1232,
+      "step": 93
+    },
+    {
+      "epoch": 0.7175572519083969,
+      "grad_norm": 0.3790041506290436,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 3.1685,
+      "step": 94
+    },
+    {
+      "epoch": 0.7251908396946565,
+      "grad_norm": 0.37685850262641907,
+      "learning_rate": 0.000188,
+      "loss": 2.8213,
+      "step": 95
+    },
+    {
+      "epoch": 0.732824427480916,
+      "grad_norm": 0.4132435619831085,
+      "learning_rate": 0.00019,
+      "loss": 2.9898,
+      "step": 96
+    },
+    {
+      "epoch": 0.7404580152671756,
+      "grad_norm": 0.37902915477752686,
+      "learning_rate": 0.000192,
+      "loss": 2.9945,
+      "step": 97
+    },
+    {
+      "epoch": 0.7480916030534351,
+      "grad_norm": 0.43122538924217224,
+      "learning_rate": 0.000194,
+      "loss": 3.22,
+      "step": 98
+    },
+    {
+      "epoch": 0.7557251908396947,
+      "grad_norm": 0.44430115818977356,
+      "learning_rate": 0.000196,
+      "loss": 3.0934,
+      "step": 99
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 0.4306162893772125,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.9698,
+      "step": 100
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "eval_loss": 3.2493093013763428,
+      "eval_runtime": 65.4803,
+      "eval_samples_per_second": 42.746,
+      "eval_steps_per_second": 2.673,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 131,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3796392388591616.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

models/cpt_qwen06/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35baddb7cfb274d6c68da88ca9dc545a7c8ffb1e3f0da946123dc36f21688a83
+size 6673

models/cpt_qwen06/checkpoint-120/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-0.6B-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-0.6B-unsloth-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 0.21.2

models/cpt_qwen06/checkpoint-120/adapter_config.json

@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-0.6B-unsloth-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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

models/cpt_qwen06/checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5c231ded217df5f8d5f204992645197afa72597c9917c082f2f333a5c33004
+size 80792456

models/cpt_qwen06/checkpoint-120/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

models/cpt_qwen06/checkpoint-120/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

models/cpt_qwen06/checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbc7469e7c8ce88fa12676ff2b35a07489bfb37e26d884ac84da30a474910bd
+size 41464389

models/cpt_qwen06/checkpoint-120/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26592b1cd842c4ce361f446ba95c6207828468b148db942589de49f1b302404b
+size 14917

models/cpt_qwen06/checkpoint-120/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf408af229538a1e55063d321681aee8925a0f675b9de64e81e09aaf34869fc
+size 14917

models/cpt_qwen06/checkpoint-120/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26073fbe26a02b632103b1678f2854b89a7a7ba1383061e25f1fcfcca5cb1921
+size 1383

models/cpt_qwen06/checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdcce17a42a70d022e7847795d9114038cef7589d67126bcb15933a35ddb7325
+size 1401

models/cpt_qwen06/checkpoint-120/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/cpt_qwen06/checkpoint-120/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

models/cpt_qwen06/checkpoint-120/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

models/cpt_qwen06/checkpoint-120/trainer_state.json

@@ -0,0 +1,931 @@
+{
+  "best_global_step": 120,
+  "best_metric": 3.2334280014038086,
+  "best_model_checkpoint": "models/cpt_qwen06/checkpoint-120",
+  "epoch": 0.916030534351145,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007633587786259542,
+      "grad_norm": 1.1038203239440918,
+      "learning_rate": 0.0,
+      "loss": 3.6412,
+      "step": 1
+    },
+    {
+      "epoch": 0.015267175572519083,
+      "grad_norm": 0.9980769753456116,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.5055,
+      "step": 2
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "grad_norm": 1.1173980236053467,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.8714,
+      "step": 3
+    },
+    {
+      "epoch": 0.030534351145038167,
+      "grad_norm": 1.083743929862976,
+      "learning_rate": 6e-06,
+      "loss": 3.7176,
+      "step": 4
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "grad_norm": 1.0839077234268188,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.6602,
+      "step": 5
+    },
+    {
+      "epoch": 0.04580152671755725,
+      "grad_norm": 1.1065247058868408,
+      "learning_rate": 1e-05,
+      "loss": 3.7578,
+      "step": 6
+    },
+    {
+      "epoch": 0.05343511450381679,
+      "grad_norm": 0.9514145255088806,
+      "learning_rate": 1.2e-05,
+      "loss": 3.4766,
+      "step": 7
+    },
+    {
+      "epoch": 0.061068702290076333,
+      "grad_norm": 0.9837572574615479,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 3.6449,
+      "step": 8
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "grad_norm": 0.8067060708999634,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.1398,
+      "step": 9
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "grad_norm": 0.893821120262146,
+      "learning_rate": 1.8e-05,
+      "loss": 3.6806,
+      "step": 10
+    },
+    {
+      "epoch": 0.08396946564885496,
+      "grad_norm": 0.8949201107025146,
+      "learning_rate": 2e-05,
+      "loss": 3.548,
+      "step": 11
+    },
+    {
+      "epoch": 0.0916030534351145,
+      "grad_norm": 0.8128786683082581,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 3.5283,
+      "step": 12
+    },
+    {
+      "epoch": 0.09923664122137404,
+      "grad_norm": 0.7861769199371338,
+      "learning_rate": 2.4e-05,
+      "loss": 3.7057,
+      "step": 13
+    },
+    {
+      "epoch": 0.10687022900763359,
+      "grad_norm": 0.7354120016098022,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 3.6656,
+      "step": 14
+    },
+    {
+      "epoch": 0.11450381679389313,
+      "grad_norm": 0.6324082612991333,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 3.4134,
+      "step": 15
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 0.637443482875824,
+      "learning_rate": 3e-05,
+      "loss": 3.6464,
+      "step": 16
+    },
+    {
+      "epoch": 0.1297709923664122,
+      "grad_norm": 0.5686759352684021,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.533,
+      "step": 17
+    },
+    {
+      "epoch": 0.13740458015267176,
+      "grad_norm": 0.5156700015068054,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 3.4371,
+      "step": 18
+    },
+    {
+      "epoch": 0.1450381679389313,
+      "grad_norm": 0.46492844820022583,
+      "learning_rate": 3.6e-05,
+      "loss": 3.3725,
+      "step": 19
+    },
+    {
+      "epoch": 0.15267175572519084,
+      "grad_norm": 0.46070176362991333,
+      "learning_rate": 3.8e-05,
+      "loss": 3.4512,
+      "step": 20
+    },
+    {
+      "epoch": 0.15267175572519084,
+      "eval_loss": 3.5234994888305664,
+      "eval_runtime": 58.557,
+      "eval_samples_per_second": 47.8,
+      "eval_steps_per_second": 2.989,
+      "step": 20
+    },
+    {
+      "epoch": 0.16030534351145037,
+      "grad_norm": 0.44954392313957214,
+      "learning_rate": 4e-05,
+      "loss": 3.4475,
+      "step": 21
+    },
+    {
+      "epoch": 0.16793893129770993,
+      "grad_norm": 0.44157543778419495,
+      "learning_rate": 4.2e-05,
+      "loss": 3.5426,
+      "step": 22
+    },
+    {
+      "epoch": 0.17557251908396945,
+      "grad_norm": 0.4325191080570221,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 3.4231,
+      "step": 23
+    },
+    {
+      "epoch": 0.183206106870229,
+      "grad_norm": 0.4093230068683624,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 3.0474,
+      "step": 24
+    },
+    {
+      "epoch": 0.19083969465648856,
+      "grad_norm": 0.3982406258583069,
+      "learning_rate": 4.8e-05,
+      "loss": 3.2979,
+      "step": 25
+    },
+    {
+      "epoch": 0.1984732824427481,
+      "grad_norm": 0.4215850234031677,
+      "learning_rate": 5e-05,
+      "loss": 3.194,
+      "step": 26
+    },
+    {
+      "epoch": 0.20610687022900764,
+      "grad_norm": 0.4356484115123749,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 3.4239,
+      "step": 27
+    },
+    {
+      "epoch": 0.21374045801526717,
+      "grad_norm": 0.4056006371974945,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 3.1843,
+      "step": 28
+    },
+    {
+      "epoch": 0.22137404580152673,
+      "grad_norm": 0.42187467217445374,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 3.3005,
+      "step": 29
+    },
+    {
+      "epoch": 0.22900763358778625,
+      "grad_norm": 0.40015560388565063,
+      "learning_rate": 5.8e-05,
+      "loss": 3.3383,
+      "step": 30
+    },
+    {
+      "epoch": 0.2366412213740458,
+      "grad_norm": 0.37207528948783875,
+      "learning_rate": 6e-05,
+      "loss": 3.2635,
+      "step": 31
+    },
+    {
+      "epoch": 0.24427480916030533,
+      "grad_norm": 0.38520580530166626,
+      "learning_rate": 6.2e-05,
+      "loss": 3.4361,
+      "step": 32
+    },
+    {
+      "epoch": 0.25190839694656486,
+      "grad_norm": 0.36966952681541443,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 3.3166,
+      "step": 33
+    },
+    {
+      "epoch": 0.2595419847328244,
+      "grad_norm": 0.34806883335113525,
+      "learning_rate": 6.6e-05,
+      "loss": 3.2605,
+      "step": 34
+    },
+    {
+      "epoch": 0.26717557251908397,
+      "grad_norm": 0.35267260670661926,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 3.289,
+      "step": 35
+    },
+    {
+      "epoch": 0.2748091603053435,
+      "grad_norm": 0.3521084189414978,
+      "learning_rate": 7e-05,
+      "loss": 3.3185,
+      "step": 36
+    },
+    {
+      "epoch": 0.2824427480916031,
+      "grad_norm": 0.3386003375053406,
+      "learning_rate": 7.2e-05,
+      "loss": 2.9975,
+      "step": 37
+    },
+    {
+      "epoch": 0.2900763358778626,
+      "grad_norm": 0.3720523416996002,
+      "learning_rate": 7.4e-05,
+      "loss": 3.1835,
+      "step": 38
+    },
+    {
+      "epoch": 0.29770992366412213,
+      "grad_norm": 0.3777226209640503,
+      "learning_rate": 7.6e-05,
+      "loss": 3.4832,
+      "step": 39
+    },
+    {
+      "epoch": 0.3053435114503817,
+      "grad_norm": 0.3729304373264313,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 3.2914,
+      "step": 40
+    },
+    {
+      "epoch": 0.3053435114503817,
+      "eval_loss": 3.3862099647521973,
+      "eval_runtime": 61.0656,
+      "eval_samples_per_second": 45.836,
+      "eval_steps_per_second": 2.866,
+      "step": 40
+    },
+    {
+      "epoch": 0.31297709923664124,
+      "grad_norm": 0.3766719698905945,
+      "learning_rate": 8e-05,
+      "loss": 3.1556,
+      "step": 41
+    },
+    {
+      "epoch": 0.32061068702290074,
+      "grad_norm": 0.35788893699645996,
+      "learning_rate": 8.2e-05,
+      "loss": 3.2917,
+      "step": 42
+    },
+    {
+      "epoch": 0.3282442748091603,
+      "grad_norm": 0.3242752254009247,
+      "learning_rate": 8.4e-05,
+      "loss": 3.1016,
+      "step": 43
+    },
+    {
+      "epoch": 0.33587786259541985,
+      "grad_norm": 0.3300817310810089,
+      "learning_rate": 8.6e-05,
+      "loss": 3.2377,
+      "step": 44
+    },
+    {
+      "epoch": 0.3435114503816794,
+      "grad_norm": 0.34662845730781555,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 3.2279,
+      "step": 45
+    },
+    {
+      "epoch": 0.3511450381679389,
+      "grad_norm": 0.32657670974731445,
+      "learning_rate": 9e-05,
+      "loss": 3.1033,
+      "step": 46
+    },
+    {
+      "epoch": 0.35877862595419846,
+      "grad_norm": 0.34357091784477234,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 3.1189,
+      "step": 47
+    },
+    {
+      "epoch": 0.366412213740458,
+      "grad_norm": 0.3785499036312103,
+      "learning_rate": 9.4e-05,
+      "loss": 3.2173,
+      "step": 48
+    },
+    {
+      "epoch": 0.37404580152671757,
+      "grad_norm": 0.3414277732372284,
+      "learning_rate": 9.6e-05,
+      "loss": 3.3226,
+      "step": 49
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "grad_norm": 0.3392898738384247,
+      "learning_rate": 9.8e-05,
+      "loss": 3.1916,
+      "step": 50
+    },
+    {
+      "epoch": 0.3893129770992366,
+      "grad_norm": 0.339979887008667,
+      "learning_rate": 0.0001,
+      "loss": 3.2239,
+      "step": 51
+    },
+    {
+      "epoch": 0.3969465648854962,
+      "grad_norm": 0.3153935372829437,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 2.9154,
+      "step": 52
+    },
+    {
+      "epoch": 0.40458015267175573,
+      "grad_norm": 0.33739224076271057,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 3.0835,
+      "step": 53
+    },
+    {
+      "epoch": 0.4122137404580153,
+      "grad_norm": 0.3399827480316162,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 3.2772,
+      "step": 54
+    },
+    {
+      "epoch": 0.4198473282442748,
+      "grad_norm": 0.3547399342060089,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 3.2374,
+      "step": 55
+    },
+    {
+      "epoch": 0.42748091603053434,
+      "grad_norm": 0.3382011950016022,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 3.1897,
+      "step": 56
+    },
+    {
+      "epoch": 0.4351145038167939,
+      "grad_norm": 0.32772088050842285,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 3.1473,
+      "step": 57
+    },
+    {
+      "epoch": 0.44274809160305345,
+      "grad_norm": 0.36062091588974,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 3.213,
+      "step": 58
+    },
+    {
+      "epoch": 0.45038167938931295,
+      "grad_norm": 0.3231198191642761,
+      "learning_rate": 0.000116,
+      "loss": 3.0341,
+      "step": 59
+    },
+    {
+      "epoch": 0.4580152671755725,
+      "grad_norm": 0.3362651765346527,
+      "learning_rate": 0.000118,
+      "loss": 3.2224,
+      "step": 60
+    },
+    {
+      "epoch": 0.4580152671755725,
+      "eval_loss": 3.3177616596221924,
+      "eval_runtime": 63.8472,
+      "eval_samples_per_second": 43.839,
+      "eval_steps_per_second": 2.741,
+      "step": 60
+    },
+    {
+      "epoch": 0.46564885496183206,
+      "grad_norm": 0.34038835763931274,
+      "learning_rate": 0.00012,
+      "loss": 3.1725,
+      "step": 61
+    },
+    {
+      "epoch": 0.4732824427480916,
+      "grad_norm": 0.3445279598236084,
+      "learning_rate": 0.000122,
+      "loss": 3.437,
+      "step": 62
+    },
+    {
+      "epoch": 0.48091603053435117,
+      "grad_norm": 0.3481975793838501,
+      "learning_rate": 0.000124,
+      "loss": 3.1468,
+      "step": 63
+    },
+    {
+      "epoch": 0.48854961832061067,
+      "grad_norm": 0.33724287152290344,
+      "learning_rate": 0.000126,
+      "loss": 3.0521,
+      "step": 64
+    },
+    {
+      "epoch": 0.4961832061068702,
+      "grad_norm": 0.3660881817340851,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 3.2244,
+      "step": 65
+    },
+    {
+      "epoch": 0.5038167938931297,
+      "grad_norm": 0.3626140058040619,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 3.2069,
+      "step": 66
+    },
+    {
+      "epoch": 0.5114503816793893,
+      "grad_norm": 0.34741154313087463,
+      "learning_rate": 0.000132,
+      "loss": 3.2547,
+      "step": 67
+    },
+    {
+      "epoch": 0.5190839694656488,
+      "grad_norm": 0.344104140996933,
+      "learning_rate": 0.000134,
+      "loss": 2.9396,
+      "step": 68
+    },
+    {
+      "epoch": 0.5267175572519084,
+      "grad_norm": 0.3456694185733795,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 3.1505,
+      "step": 69
+    },
+    {
+      "epoch": 0.5343511450381679,
+      "grad_norm": 0.3567255735397339,
+      "learning_rate": 0.000138,
+      "loss": 3.2136,
+      "step": 70
+    },
+    {
+      "epoch": 0.5419847328244275,
+      "grad_norm": 0.3521654009819031,
+      "learning_rate": 0.00014,
+      "loss": 2.9877,
+      "step": 71
+    },
+    {
+      "epoch": 0.549618320610687,
+      "grad_norm": 0.3765776753425598,
+      "learning_rate": 0.000142,
+      "loss": 3.1552,
+      "step": 72
+    },
+    {
+      "epoch": 0.5572519083969466,
+      "grad_norm": 0.36426547169685364,
+      "learning_rate": 0.000144,
+      "loss": 3.2685,
+      "step": 73
+    },
+    {
+      "epoch": 0.5648854961832062,
+      "grad_norm": 0.3653399348258972,
+      "learning_rate": 0.000146,
+      "loss": 3.2527,
+      "step": 74
+    },
+    {
+      "epoch": 0.5725190839694656,
+      "grad_norm": 0.35804226994514465,
+      "learning_rate": 0.000148,
+      "loss": 3.1865,
+      "step": 75
+    },
+    {
+      "epoch": 0.5801526717557252,
+      "grad_norm": 0.3470200300216675,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.0362,
+      "step": 76
+    },
+    {
+      "epoch": 0.5877862595419847,
+      "grad_norm": 0.3770173192024231,
+      "learning_rate": 0.000152,
+      "loss": 3.1248,
+      "step": 77
+    },
+    {
+      "epoch": 0.5954198473282443,
+      "grad_norm": 0.35332971811294556,
+      "learning_rate": 0.000154,
+      "loss": 2.7595,
+      "step": 78
+    },
+    {
+      "epoch": 0.6030534351145038,
+      "grad_norm": 0.3616713285446167,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 3.1264,
+      "step": 79
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "grad_norm": 0.37358736991882324,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 3.2264,
+      "step": 80
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "eval_loss": 3.272794246673584,
+      "eval_runtime": 64.8828,
+      "eval_samples_per_second": 43.139,
+      "eval_steps_per_second": 2.697,
+      "step": 80
+    },
+    {
+      "epoch": 0.6183206106870229,
+      "grad_norm": 0.4232015311717987,
+      "learning_rate": 0.00016,
+      "loss": 3.4534,
+      "step": 81
+    },
+    {
+      "epoch": 0.6259541984732825,
+      "grad_norm": 0.391012042760849,
+      "learning_rate": 0.000162,
+      "loss": 2.9921,
+      "step": 82
+    },
+    {
+      "epoch": 0.6335877862595419,
+      "grad_norm": 0.4178006052970886,
+      "learning_rate": 0.000164,
+      "loss": 3.0948,
+      "step": 83
+    },
+    {
+      "epoch": 0.6412213740458015,
+      "grad_norm": 0.3803626596927643,
+      "learning_rate": 0.000166,
+      "loss": 2.9039,
+      "step": 84
+    },
+    {
+      "epoch": 0.648854961832061,
+      "grad_norm": 0.3924623131752014,
+      "learning_rate": 0.000168,
+      "loss": 3.087,
+      "step": 85
+    },
+    {
+      "epoch": 0.6564885496183206,
+      "grad_norm": 0.38232532143592834,
+      "learning_rate": 0.00017,
+      "loss": 2.8771,
+      "step": 86
+    },
+    {
+      "epoch": 0.6641221374045801,
+      "grad_norm": 0.41317063570022583,
+      "learning_rate": 0.000172,
+      "loss": 3.2177,
+      "step": 87
+    },
+    {
+      "epoch": 0.6717557251908397,
+      "grad_norm": 0.3906857669353485,
+      "learning_rate": 0.000174,
+      "loss": 3.0091,
+      "step": 88
+    },
+    {
+      "epoch": 0.6793893129770993,
+      "grad_norm": 0.39958348870277405,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 2.9797,
+      "step": 89
+    },
+    {
+      "epoch": 0.6870229007633588,
+      "grad_norm": 0.38834550976753235,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 3.147,
+      "step": 90
+    },
+    {
+      "epoch": 0.6946564885496184,
+      "grad_norm": 0.40388867259025574,
+      "learning_rate": 0.00018,
+      "loss": 3.1668,
+      "step": 91
+    },
+    {
+      "epoch": 0.7022900763358778,
+      "grad_norm": 0.3906465172767639,
+      "learning_rate": 0.000182,
+      "loss": 3.1451,
+      "step": 92
+    },
+    {
+      "epoch": 0.7099236641221374,
+      "grad_norm": 0.40879368782043457,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 3.1232,
+      "step": 93
+    },
+    {
+      "epoch": 0.7175572519083969,
+      "grad_norm": 0.3790041506290436,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 3.1685,
+      "step": 94
+    },
+    {
+      "epoch": 0.7251908396946565,
+      "grad_norm": 0.37685850262641907,
+      "learning_rate": 0.000188,
+      "loss": 2.8213,
+      "step": 95
+    },
+    {
+      "epoch": 0.732824427480916,
+      "grad_norm": 0.4132435619831085,
+      "learning_rate": 0.00019,
+      "loss": 2.9898,
+      "step": 96
+    },
+    {
+      "epoch": 0.7404580152671756,
+      "grad_norm": 0.37902915477752686,
+      "learning_rate": 0.000192,
+      "loss": 2.9945,
+      "step": 97
+    },
+    {
+      "epoch": 0.7480916030534351,
+      "grad_norm": 0.43122538924217224,
+      "learning_rate": 0.000194,
+      "loss": 3.22,
+      "step": 98
+    },
+    {
+      "epoch": 0.7557251908396947,
+      "grad_norm": 0.44430115818977356,
+      "learning_rate": 0.000196,
+      "loss": 3.0934,
+      "step": 99
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 0.4306162893772125,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.9698,
+      "step": 100
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "eval_loss": 3.2493093013763428,
+      "eval_runtime": 65.4803,
+      "eval_samples_per_second": 42.746,
+      "eval_steps_per_second": 2.673,
+      "step": 100
+    },
+    {
+      "epoch": 0.7709923664122137,
+      "grad_norm": 0.4054669439792633,
+      "learning_rate": 0.0002,
+      "loss": 2.9803,
+      "step": 101
+    },
+    {
+      "epoch": 0.7786259541984732,
+      "grad_norm": 0.42372527718544006,
+      "learning_rate": 0.00019354838709677422,
+      "loss": 3.0693,
+      "step": 102
+    },
+    {
+      "epoch": 0.7862595419847328,
+      "grad_norm": 0.42124831676483154,
+      "learning_rate": 0.0001870967741935484,
+      "loss": 3.1015,
+      "step": 103
+    },
+    {
+      "epoch": 0.7938931297709924,
+      "grad_norm": 0.4139660894870758,
+      "learning_rate": 0.00018064516129032257,
+      "loss": 3.0137,
+      "step": 104
+    },
+    {
+      "epoch": 0.8015267175572519,
+      "grad_norm": 0.4095960855484009,
+      "learning_rate": 0.00017419354838709678,
+      "loss": 3.0648,
+      "step": 105
+    },
+    {
+      "epoch": 0.8091603053435115,
+      "grad_norm": 0.400102823972702,
+      "learning_rate": 0.00016774193548387098,
+      "loss": 2.8783,
+      "step": 106
+    },
+    {
+      "epoch": 0.816793893129771,
+      "grad_norm": 0.3862192928791046,
+      "learning_rate": 0.00016129032258064516,
+      "loss": 2.9882,
+      "step": 107
+    },
+    {
+      "epoch": 0.8244274809160306,
+      "grad_norm": 0.3908466398715973,
+      "learning_rate": 0.00015483870967741937,
+      "loss": 3.1206,
+      "step": 108
+    },
+    {
+      "epoch": 0.8320610687022901,
+      "grad_norm": 0.4344117343425751,
+      "learning_rate": 0.00014838709677419355,
+      "loss": 3.0064,
+      "step": 109
+    },
+    {
+      "epoch": 0.8396946564885496,
+      "grad_norm": 0.4170740246772766,
+      "learning_rate": 0.00014193548387096775,
+      "loss": 3.0922,
+      "step": 110
+    },
+    {
+      "epoch": 0.8473282442748091,
+      "grad_norm": 0.40790364146232605,
+      "learning_rate": 0.00013548387096774193,
+      "loss": 2.8885,
+      "step": 111
+    },
+    {
+      "epoch": 0.8549618320610687,
+      "grad_norm": 0.42549675703048706,
+      "learning_rate": 0.00012903225806451613,
+      "loss": 3.0056,
+      "step": 112
+    },
+    {
+      "epoch": 0.8625954198473282,
+      "grad_norm": 0.416328102350235,
+      "learning_rate": 0.00012258064516129034,
+      "loss": 3.0189,
+      "step": 113
+    },
+    {
+      "epoch": 0.8702290076335878,
+      "grad_norm": 0.4028750956058502,
+      "learning_rate": 0.00011612903225806453,
+      "loss": 2.9831,
+      "step": 114
+    },
+    {
+      "epoch": 0.8778625954198473,
+      "grad_norm": 0.44646525382995605,
+      "learning_rate": 0.00010967741935483871,
+      "loss": 3.0881,
+      "step": 115
+    },
+    {
+      "epoch": 0.8854961832061069,
+      "grad_norm": 0.3996594250202179,
+      "learning_rate": 0.0001032258064516129,
+      "loss": 3.0347,
+      "step": 116
+    },
+    {
+      "epoch": 0.8931297709923665,
+      "grad_norm": 0.41585463285446167,
+      "learning_rate": 9.677419354838711e-05,
+      "loss": 2.9658,
+      "step": 117
+    },
+    {
+      "epoch": 0.9007633587786259,
+      "grad_norm": 0.4043269157409668,
+      "learning_rate": 9.032258064516129e-05,
+      "loss": 2.9472,
+      "step": 118
+    },
+    {
+      "epoch": 0.9083969465648855,
+      "grad_norm": 0.40867879986763,
+      "learning_rate": 8.387096774193549e-05,
+      "loss": 2.9854,
+      "step": 119
+    },
+    {
+      "epoch": 0.916030534351145,
+      "grad_norm": 0.4330108165740967,
+      "learning_rate": 7.741935483870968e-05,
+      "loss": 3.198,
+      "step": 120
+    },
+    {
+      "epoch": 0.916030534351145,
+      "eval_loss": 3.2334280014038086,
+      "eval_runtime": 65.638,
+      "eval_samples_per_second": 42.643,
+      "eval_steps_per_second": 2.666,
+      "step": 120
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 131,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4564716605145088.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

models/cpt_qwen06/checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35baddb7cfb274d6c68da88ca9dc545a7c8ffb1e3f0da946123dc36f21688a83
+size 6673

models/cpt_qwen06/checkpoint-131/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-0.6B-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-0.6B-unsloth-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 0.21.2

models/cpt_qwen06/checkpoint-131/adapter_config.json

@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-0.6B-unsloth-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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

models/cpt_qwen06/checkpoint-131/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3233ce0da0380cf7caa148f26533ae7912710836be102df070ad6ae6ccc4da3
+size 80792456

models/cpt_qwen06/checkpoint-131/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

models/cpt_qwen06/checkpoint-131/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

models/cpt_qwen06/checkpoint-131/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d55b1b94279b1313832d0d4a04686b61c02048f630ab9d5c004db8c5248072
+size 41464389

models/cpt_qwen06/checkpoint-131/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26592b1cd842c4ce361f446ba95c6207828468b148db942589de49f1b302404b
+size 14917

models/cpt_qwen06/checkpoint-131/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf408af229538a1e55063d321681aee8925a0f675b9de64e81e09aaf34869fc
+size 14917

models/cpt_qwen06/checkpoint-131/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2281bbdfd1302b33e86b6777a39c20cc14faf53eba1e586b644cc339fc11cfbe
+size 1383

models/cpt_qwen06/checkpoint-131/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7742885c3ea064474e04d4c602f312628f6400ac9307af7191bb79b8706ff773
+size 1401

models/cpt_qwen06/checkpoint-131/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/cpt_qwen06/checkpoint-131/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

models/cpt_qwen06/checkpoint-131/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}