Upload qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm to classroom repo

.gitattributes

@@ -44,3 +44,14 @@ qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoin
 qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-6366/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-8488/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-15885/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-1589/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-3178/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-4767/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-6356/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-7945/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-9534/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/README.md

@@ -0,0 +1,146 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen3-0.6B
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-0.6B
+- lora
+- transformers
+datasets:
+- custom
+pipeline_tag: text-generation
+model-index:
+- name: outputs/qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.12.2`
+```yaml
+base_model: Qwen/Qwen3-0.6B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+datasets:
+- path: /home/wongshingyin/deepseek_math_sft/ft_using_Axolotl_1/sft_4type_merged_n3to9_remap_completion_no_wrong_maxlen4096_rebalanced_higher_maxm.jsonl
+  ds_type: json
+  type:
+    field_instruction: input
+    field_input: __unused
+    field_output: output
+    format: "{instruction}"
+    no_input_format: "{instruction}"
+output_dir: ./outputs/qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm
+dataset_prepared_path: /home/wongshingyin/deepseek_math_sft/ft_using_Axolotl_1/qwen_06b_4type_prepared_4096_old_format_lora_dataset_a_balanced_higher_maxm
+micro_batch_size: 4
+gradient_accumulation_steps: 8
+num_epochs: 2
+learning_rate: 0.000015
+lr_scheduler: cosine
+warmup_steps: 200
+optimizer: adamw_bnb_8bit
+weight_decay: 0.01
+val_set_size: 500
+eval_steps: 0.1
+early_stopping_patience: 3
+load_best_model_at_end: true
+bf16: true
+sequence_len: 4096
+pad_to_sequence_len: true
+group_by_length: false
+max_packed_sequence_len: null
+packing: true
+flash_attention: true
+gradient_checkpointing: true
+heads_k_stride: 1
+seed: 42
+data_seed: 42
+adapter: lora
+lora_r: 64
+lora_alpha: 128
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- k_proj
+- v_proj
+- o_proj
+- gate_proj
+- up_proj
+- down_proj
+save_steps: 0.1
+save_total_limit: 10
+logging_steps: 200
+
+```
+
+</details><br>
+
+# outputs/qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the /home/wongshingyin/deepseek_math_sft/ft_using_Axolotl_1/sft_4type_merged_n3to9_remap_completion_no_wrong_maxlen4096_rebalanced_higher_maxm.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0639
+- Memory/max Mem Active(gib): 31.11
+- Memory/max Mem Allocated(gib): 31.11
+- Memory/device Mem Reserved(gib): 36.15
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- training_steps: 15885
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Mem Active(gib) | Mem Allocated(gib) | Mem Reserved(gib) |
+|:-------------:|:------:|:-----:|:---------------:|:---------------:|:------------------:|:-----------------:|
+| No log        | 0      | 0     | 2.2899          | 25.29           | 25.29              | 25.43             |
+| 0.0718        | 0.2001 | 1589  | 0.0984          | 31.11           | 31.11              | 36.15             |
+| 0.0614        | 0.4001 | 3178  | 0.0823          | 31.11           | 31.11              | 36.15             |
+| 0.0528        | 0.6002 | 4767  | 0.0784          | 31.11           | 31.11              | 36.15             |
+| 0.049         | 0.8003 | 6356  | 0.0742          | 31.11           | 31.11              | 36.15             |
+| 0.0487        | 1.0003 | 7945  | 0.0699          | 31.11           | 31.11              | 36.15             |
+| 0.0466        | 1.2003 | 9534  | 0.0668          | 31.11           | 31.11              | 36.15             |
+| 0.0447        | 1.4004 | 11123 | 0.0656          | 31.11           | 31.11              | 36.15             |
+| 0.0432        | 1.6005 | 12712 | 0.0647          | 31.11           | 31.11              | 36.15             |
+| 0.042         | 1.8005 | 14301 | 0.0639          | 31.11           | 31.11              | 36.15             |
+
+
+### Framework versions
+
+- PEFT 0.17.0
+- Transformers 4.55.2
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b097101152bf05b9759cfec42c17e978ac65c6c256cfa4e5dcb578cce4b6491
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/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
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|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' }}
+        {{- 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 %}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-0.6B
+- lora
+- transformers
+---
+
+# 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 0.17.0

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d11ed602b271ae448fcf097e9bc7d63c955c7c06ef2f1b2bd514c68b5ef6268
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/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
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|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' }}
+        {{- 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 %}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660f3c7f97aa5ae9259914ff00b9a3ec9e759e4700b6b4fda576e55a86ba1b9f
+size 82463540

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47014cfc9670c2665403f93e43aee5b8906a98a5218416a38b933f5d7979ba6
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8083b03d82ca3761c4fd296854664a51da174f55be28393bccc41854d9b94da
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cd572ac94563c6a99c27bb27bf472480ae84140b44f6c48a0a5249d7543430
+size 1064

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/tokenizer.json

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

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/trainer_state.json

@@ -0,0 +1,681 @@
+{
+  "best_global_step": 11123,
+  "best_metric": 0.06559588760137558,
+  "best_model_checkpoint": "./outputs/qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123",
+  "epoch": 1.4003903176052126,
+  "eval_steps": 1589,
+  "global_step": 11123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.2898781299591064,
+      "eval_runtime": 37.6455,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.674,
+      "memory/device_mem_reserved(gib)": 25.43,
+      "memory/max_mem_active(gib)": 25.29,
+      "memory/max_mem_allocated(gib)": 25.29,
+      "step": 0
+    },
+    {
+      "epoch": 0.025181780981459914,
+      "grad_norm": 1.1581913232803345,
+      "learning_rate": 1.4925e-05,
+      "loss": 0.542,
+      "memory/device_mem_reserved(gib)": 36.14,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 200
+    },
+    {
+      "epoch": 0.05036356196291983,
+      "grad_norm": 1.2134943008422852,
+      "learning_rate": 1.4994043232864502e-05,
+      "loss": 0.1161,
+      "memory/device_mem_reserved(gib)": 36.14,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 400
+    },
+    {
+      "epoch": 0.07554534294437974,
+      "grad_norm": 0.7379748821258545,
+      "learning_rate": 1.4976062620573955e-05,
+      "loss": 0.0944,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 600
+    },
+    {
+      "epoch": 0.10072712392583966,
+      "grad_norm": 1.001336693763733,
+      "learning_rate": 1.4946086862109133e-05,
+      "loss": 0.0848,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 800
+    },
+    {
+      "epoch": 0.12590890490729956,
+      "grad_norm": 0.9309785962104797,
+      "learning_rate": 1.490416405278741e-05,
+      "loss": 0.0782,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15109068588875949,
+      "grad_norm": 0.7242914438247681,
+      "learning_rate": 1.485036145665557e-05,
+      "loss": 0.077,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17627246687021939,
+      "grad_norm": 0.5952772498130798,
+      "learning_rate": 1.4784765398566399e-05,
+      "loss": 0.0718,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1400
+    },
+    {
+      "epoch": 0.200069249897699,
+      "eval_loss": 0.09838306903839111,
+      "eval_runtime": 35.9035,
+      "eval_samples_per_second": 13.926,
+      "eval_steps_per_second": 1.755,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1589
+    },
+    {
+      "epoch": 0.2014542478516793,
+      "grad_norm": 0.6498895287513733,
+      "learning_rate": 1.470748112567273e-05,
+      "loss": 0.068,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1600
+    },
+    {
+      "epoch": 0.2266360288331392,
+      "grad_norm": 0.9078791737556458,
+      "learning_rate": 1.4618632638561161e-05,
+      "loss": 0.0662,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2518178098145991,
+      "grad_norm": 1.00960111618042,
+      "learning_rate": 1.4518362492296344e-05,
+      "loss": 0.0659,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2000
+    },
+    {
+      "epoch": 0.27699959079605907,
+      "grad_norm": 0.6233915686607361,
+      "learning_rate": 1.440683156769515e-05,
+      "loss": 0.0636,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2200
+    },
+    {
+      "epoch": 0.30218137177751897,
+      "grad_norm": 0.6379794478416443,
+      "learning_rate": 1.4284218813197612e-05,
+      "loss": 0.0621,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2400
+    },
+    {
+      "epoch": 0.32736315275897887,
+      "grad_norm": 0.6365833878517151,
+      "learning_rate": 1.4150720957748855e-05,
+      "loss": 0.0625,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2600
+    },
+    {
+      "epoch": 0.35254493374043877,
+      "grad_norm": 0.6307992339134216,
+      "learning_rate": 1.4006552195152665e-05,
+      "loss": 0.0596,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3777267147218987,
+      "grad_norm": 0.6141844987869263,
+      "learning_rate": 1.3851943840403162e-05,
+      "loss": 0.0614,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3000
+    },
+    {
+      "epoch": 0.400138499795398,
+      "eval_loss": 0.08228352665901184,
+      "eval_runtime": 35.5139,
+      "eval_samples_per_second": 14.079,
+      "eval_steps_per_second": 1.774,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3178
+    },
+    {
+      "epoch": 0.4029084957033586,
+      "grad_norm": 0.5466150045394897,
+      "learning_rate": 1.3687143958545962e-05,
+      "loss": 0.0602,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4280902766848185,
+      "grad_norm": 0.43696290254592896,
+      "learning_rate": 1.3512416966664316e-05,
+      "loss": 0.0565,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3400
+    },
+    {
+      "epoch": 0.4532720576662784,
+      "grad_norm": 0.80906742811203,
+      "learning_rate": 1.3328043209628867e-05,
+      "loss": 0.0564,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3600
+    },
+    {
+      "epoch": 0.4784538386477384,
+      "grad_norm": 0.6906489133834839,
+      "learning_rate": 1.3134318510291633e-05,
+      "loss": 0.0565,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3800
+    },
+    {
+      "epoch": 0.5036356196291982,
+      "grad_norm": 0.5611644983291626,
+      "learning_rate": 1.2931553694846034e-05,
+      "loss": 0.0567,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5288174006106582,
+      "grad_norm": 0.5764939785003662,
+      "learning_rate": 1.2720074094114421e-05,
+      "loss": 0.0553,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4200
+    },
+    {
+      "epoch": 0.5539991815921181,
+      "grad_norm": 0.6387307047843933,
+      "learning_rate": 1.2500219021563304e-05,
+      "loss": 0.0531,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4400
+    },
+    {
+      "epoch": 0.579180962573578,
+      "grad_norm": 0.379346638917923,
+      "learning_rate": 1.2272341228883813e-05,
+      "loss": 0.0528,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4600
+    },
+    {
+      "epoch": 0.6002077496930971,
+      "eval_loss": 0.07838868349790573,
+      "eval_runtime": 36.4961,
+      "eval_samples_per_second": 13.7,
+      "eval_steps_per_second": 1.726,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4767
+    },
+    {
+      "epoch": 0.6043627435550379,
+      "grad_norm": 0.5089019536972046,
+      "learning_rate": 1.2036806340010871e-05,
+      "loss": 0.0538,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4800
+    },
+    {
+      "epoch": 0.6295445245364979,
+      "grad_norm": 0.3256368339061737,
+      "learning_rate": 1.1793992264489193e-05,
+      "loss": 0.0535,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6547263055179577,
+      "grad_norm": 0.44287726283073425,
+      "learning_rate": 1.1544288591127334e-05,
+      "loss": 0.0522,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5200
+    },
+    {
+      "epoch": 0.6799080864994177,
+      "grad_norm": 0.30101513862609863,
+      "learning_rate": 1.1288095962912685e-05,
+      "loss": 0.0519,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5400
+    },
+    {
+      "epoch": 0.7050898674808775,
+      "grad_norm": 0.8115870952606201,
+      "learning_rate": 1.1025825434190314e-05,
+      "loss": 0.0506,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7302716484623375,
+      "grad_norm": 0.6839262247085571,
+      "learning_rate": 1.0757897811137073e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5800
+    },
+    {
+      "epoch": 0.7554534294437975,
+      "grad_norm": 0.4723190665245056,
+      "learning_rate": 1.048474297658912e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7806352104252573,
+      "grad_norm": 0.5968837141990662,
+      "learning_rate": 1.0206799200306208e-05,
+      "loss": 0.049,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6200
+    },
+    {
+      "epoch": 0.800276999590796,
+      "eval_loss": 0.074190653860569,
+      "eval_runtime": 42.7728,
+      "eval_samples_per_second": 11.69,
+      "eval_steps_per_second": 1.473,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6356
+    },
+    {
+      "epoch": 0.8058169914067173,
+      "grad_norm": 0.6108983755111694,
+      "learning_rate": 9.92451243577936e-06,
+      "loss": 0.0508,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6400
+    },
+    {
+      "epoch": 0.8309987723881772,
+      "grad_norm": 0.5209892392158508,
+      "learning_rate": 9.638335604710197e-06,
+      "loss": 0.0502,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6600
+    },
+    {
+      "epoch": 0.856180553369637,
+      "grad_norm": 0.3816191554069519,
+      "learning_rate": 9.348727870309973e-06,
+      "loss": 0.0497,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6800
+    },
+    {
+      "epoch": 0.881362334351097,
+      "grad_norm": 0.5576559901237488,
+      "learning_rate": 9.056153900584243e-06,
+      "loss": 0.0494,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9065441153325569,
+      "grad_norm": 0.6634303331375122,
+      "learning_rate": 8.761083122785266e-06,
+      "loss": 0.0488,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7200
+    },
+    {
+      "epoch": 0.9317258963140168,
+      "grad_norm": 0.4906536042690277,
+      "learning_rate": 8.463988970228283e-06,
+      "loss": 0.0496,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7400
+    },
+    {
+      "epoch": 0.9569076772954768,
+      "grad_norm": 0.45645272731781006,
+      "learning_rate": 8.165348122680214e-06,
+      "loss": 0.0497,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7600
+    },
+    {
+      "epoch": 0.9820894582769366,
+      "grad_norm": 0.3046559989452362,
+      "learning_rate": 7.865639741539483e-06,
+      "loss": 0.0487,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7800
+    },
+    {
+      "epoch": 1.0002518178098145,
+      "eval_loss": 0.06988665461540222,
+      "eval_runtime": 35.211,
+      "eval_samples_per_second": 14.2,
+      "eval_steps_per_second": 1.789,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7945
+    },
+    {
+      "epoch": 1.007176807579716,
+      "grad_norm": 0.24347852170467377,
+      "learning_rate": 7.565344701034122e-06,
+      "loss": 0.0465,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8000
+    },
+    {
+      "epoch": 1.032358588561176,
+      "grad_norm": 0.4792805016040802,
+      "learning_rate": 7.264944816671722e-06,
+      "loss": 0.0471,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8200
+    },
+    {
+      "epoch": 1.057540369542636,
+      "grad_norm": 0.40505144000053406,
+      "learning_rate": 6.964922072179084e-06,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8400
+    },
+    {
+      "epoch": 1.0827221505240958,
+      "grad_norm": 0.43307843804359436,
+      "learning_rate": 6.665757846171986e-06,
+      "loss": 0.047,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8600
+    },
+    {
+      "epoch": 1.1079039315055557,
+      "grad_norm": 0.6030473709106445,
+      "learning_rate": 6.36793213979585e-06,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8800
+    },
+    {
+      "epoch": 1.1330857124870157,
+      "grad_norm": 0.492542564868927,
+      "learning_rate": 6.071922806576484e-06,
+      "loss": 0.0447,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1582674934684756,
+      "grad_norm": 0.35956957936286926,
+      "learning_rate": 5.778204785716663e-06,
+      "loss": 0.0459,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9200
+    },
+    {
+      "epoch": 1.1834492744499354,
+      "grad_norm": 0.26773375272750854,
+      "learning_rate": 5.487249340068649e-06,
+      "loss": 0.0466,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9400
+    },
+    {
+      "epoch": 1.2003210677075136,
+      "eval_loss": 0.06683629006147385,
+      "eval_runtime": 39.9381,
+      "eval_samples_per_second": 12.519,
+      "eval_steps_per_second": 1.577,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9534
+    },
+    {
+      "epoch": 1.2086310554313955,
+      "grad_norm": 0.49637848138809204,
+      "learning_rate": 5.199523300005305e-06,
+      "loss": 0.0459,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9600
+    },
+    {
+      "epoch": 1.2338128364128553,
+      "grad_norm": 0.4869849979877472,
+      "learning_rate": 4.9154883144030415e-06,
+      "loss": 0.0455,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9800
+    },
+    {
+      "epoch": 1.2589946173943152,
+      "grad_norm": 0.28114384412765503,
+      "learning_rate": 4.6356001099382885e-06,
+      "loss": 0.045,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10000
+    },
+    {
+      "epoch": 1.284176398375775,
+      "grad_norm": 0.3514762222766876,
+      "learning_rate": 4.360307759886035e-06,
+      "loss": 0.0443,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10200
+    },
+    {
+      "epoch": 1.309358179357235,
+      "grad_norm": 0.4368722140789032,
+      "learning_rate": 4.09005296359353e-06,
+      "loss": 0.0464,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10400
+    },
+    {
+      "epoch": 1.334539960338695,
+      "grad_norm": 0.3975982367992401,
+      "learning_rate": 3.825269337785298e-06,
+      "loss": 0.0441,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10600
+    },
+    {
+      "epoch": 1.359721741320155,
+      "grad_norm": 0.7111567854881287,
+      "learning_rate": 3.5663817208364675e-06,
+      "loss": 0.0446,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10800
+    },
+    {
+      "epoch": 1.3849035223016148,
+      "grad_norm": 0.6843410134315491,
+      "learning_rate": 3.313805491130775e-06,
+      "loss": 0.0447,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11000
+    },
+    {
+      "epoch": 1.4003903176052126,
+      "eval_loss": 0.06559588760137558,
+      "eval_runtime": 39.6189,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.59,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11123
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 15885,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1589,
+  "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": 8.411670934997434e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-11123/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6567923762df25f157b6869fee06dcebcdeb8ba971499372b10e86aac90dbd6b
+size 6904

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-0.6B
+- lora
+- transformers
+---
+
+# 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 0.17.0

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1992b92e6eb759320be4a24e9743946c6b0c9fd7df6e29c1a062352eee411e7
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/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
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|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' }}
+        {{- 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 %}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237095b1041822a28dfa186e4da901e3bbd5110e0bd86108b9209c5563edef08
+size 82463540

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281dd3824b977e600b0d43566e20962c0a91d22d9c2d31642f0114a7d25ac4a3
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa4fd4100e187ff13af2aefa6e8caf4174fc8c46bebe8c01f83447bde3a501f
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b3cee64584ca92d46a92bf6cc7b68ce0711caf21d5130bfa22e399c8f0c7e7
+size 1064

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/tokenizer.json

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

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/trainer_state.json

@@ -0,0 +1,772 @@
+{
+  "best_global_step": 12712,
+  "best_metric": 0.06468167155981064,
+  "best_model_checkpoint": "./outputs/qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712",
+  "epoch": 1.6004595675029116,
+  "eval_steps": 1589,
+  "global_step": 12712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.2898781299591064,
+      "eval_runtime": 37.6455,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.674,
+      "memory/device_mem_reserved(gib)": 25.43,
+      "memory/max_mem_active(gib)": 25.29,
+      "memory/max_mem_allocated(gib)": 25.29,
+      "step": 0
+    },
+    {
+      "epoch": 0.025181780981459914,
+      "grad_norm": 1.1581913232803345,
+      "learning_rate": 1.4925e-05,
+      "loss": 0.542,
+      "memory/device_mem_reserved(gib)": 36.14,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 200
+    },
+    {
+      "epoch": 0.05036356196291983,
+      "grad_norm": 1.2134943008422852,
+      "learning_rate": 1.4994043232864502e-05,
+      "loss": 0.1161,
+      "memory/device_mem_reserved(gib)": 36.14,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 400
+    },
+    {
+      "epoch": 0.07554534294437974,
+      "grad_norm": 0.7379748821258545,
+      "learning_rate": 1.4976062620573955e-05,
+      "loss": 0.0944,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 600
+    },
+    {
+      "epoch": 0.10072712392583966,
+      "grad_norm": 1.001336693763733,
+      "learning_rate": 1.4946086862109133e-05,
+      "loss": 0.0848,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 800
+    },
+    {
+      "epoch": 0.12590890490729956,
+      "grad_norm": 0.9309785962104797,
+      "learning_rate": 1.490416405278741e-05,
+      "loss": 0.0782,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15109068588875949,
+      "grad_norm": 0.7242914438247681,
+      "learning_rate": 1.485036145665557e-05,
+      "loss": 0.077,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17627246687021939,
+      "grad_norm": 0.5952772498130798,
+      "learning_rate": 1.4784765398566399e-05,
+      "loss": 0.0718,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1400
+    },
+    {
+      "epoch": 0.200069249897699,
+      "eval_loss": 0.09838306903839111,
+      "eval_runtime": 35.9035,
+      "eval_samples_per_second": 13.926,
+      "eval_steps_per_second": 1.755,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1589
+    },
+    {
+      "epoch": 0.2014542478516793,
+      "grad_norm": 0.6498895287513733,
+      "learning_rate": 1.470748112567273e-05,
+      "loss": 0.068,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1600
+    },
+    {
+      "epoch": 0.2266360288331392,
+      "grad_norm": 0.9078791737556458,
+      "learning_rate": 1.4618632638561161e-05,
+      "loss": 0.0662,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2518178098145991,
+      "grad_norm": 1.00960111618042,
+      "learning_rate": 1.4518362492296344e-05,
+      "loss": 0.0659,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2000
+    },
+    {
+      "epoch": 0.27699959079605907,
+      "grad_norm": 0.6233915686607361,
+      "learning_rate": 1.440683156769515e-05,
+      "loss": 0.0636,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2200
+    },
+    {
+      "epoch": 0.30218137177751897,
+      "grad_norm": 0.6379794478416443,
+      "learning_rate": 1.4284218813197612e-05,
+      "loss": 0.0621,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2400
+    },
+    {
+      "epoch": 0.32736315275897887,
+      "grad_norm": 0.6365833878517151,
+      "learning_rate": 1.4150720957748855e-05,
+      "loss": 0.0625,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2600
+    },
+    {
+      "epoch": 0.35254493374043877,
+      "grad_norm": 0.6307992339134216,
+      "learning_rate": 1.4006552195152665e-05,
+      "loss": 0.0596,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3777267147218987,
+      "grad_norm": 0.6141844987869263,
+      "learning_rate": 1.3851943840403162e-05,
+      "loss": 0.0614,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3000
+    },
+    {
+      "epoch": 0.400138499795398,
+      "eval_loss": 0.08228352665901184,
+      "eval_runtime": 35.5139,
+      "eval_samples_per_second": 14.079,
+      "eval_steps_per_second": 1.774,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3178
+    },
+    {
+      "epoch": 0.4029084957033586,
+      "grad_norm": 0.5466150045394897,
+      "learning_rate": 1.3687143958545962e-05,
+      "loss": 0.0602,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4280902766848185,
+      "grad_norm": 0.43696290254592896,
+      "learning_rate": 1.3512416966664316e-05,
+      "loss": 0.0565,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3400
+    },
+    {
+      "epoch": 0.4532720576662784,
+      "grad_norm": 0.80906742811203,
+      "learning_rate": 1.3328043209628867e-05,
+      "loss": 0.0564,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3600
+    },
+    {
+      "epoch": 0.4784538386477384,
+      "grad_norm": 0.6906489133834839,
+      "learning_rate": 1.3134318510291633e-05,
+      "loss": 0.0565,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 3800
+    },
+    {
+      "epoch": 0.5036356196291982,
+      "grad_norm": 0.5611644983291626,
+      "learning_rate": 1.2931553694846034e-05,
+      "loss": 0.0567,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5288174006106582,
+      "grad_norm": 0.5764939785003662,
+      "learning_rate": 1.2720074094114421e-05,
+      "loss": 0.0553,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4200
+    },
+    {
+      "epoch": 0.5539991815921181,
+      "grad_norm": 0.6387307047843933,
+      "learning_rate": 1.2500219021563304e-05,
+      "loss": 0.0531,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4400
+    },
+    {
+      "epoch": 0.579180962573578,
+      "grad_norm": 0.379346638917923,
+      "learning_rate": 1.2272341228883813e-05,
+      "loss": 0.0528,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4600
+    },
+    {
+      "epoch": 0.6002077496930971,
+      "eval_loss": 0.07838868349790573,
+      "eval_runtime": 36.4961,
+      "eval_samples_per_second": 13.7,
+      "eval_steps_per_second": 1.726,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4767
+    },
+    {
+      "epoch": 0.6043627435550379,
+      "grad_norm": 0.5089019536972046,
+      "learning_rate": 1.2036806340010871e-05,
+      "loss": 0.0538,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 4800
+    },
+    {
+      "epoch": 0.6295445245364979,
+      "grad_norm": 0.3256368339061737,
+      "learning_rate": 1.1793992264489193e-05,
+      "loss": 0.0535,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6547263055179577,
+      "grad_norm": 0.44287726283073425,
+      "learning_rate": 1.1544288591127334e-05,
+      "loss": 0.0522,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5200
+    },
+    {
+      "epoch": 0.6799080864994177,
+      "grad_norm": 0.30101513862609863,
+      "learning_rate": 1.1288095962912685e-05,
+      "loss": 0.0519,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5400
+    },
+    {
+      "epoch": 0.7050898674808775,
+      "grad_norm": 0.8115870952606201,
+      "learning_rate": 1.1025825434190314e-05,
+      "loss": 0.0506,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7302716484623375,
+      "grad_norm": 0.6839262247085571,
+      "learning_rate": 1.0757897811137073e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 5800
+    },
+    {
+      "epoch": 0.7554534294437975,
+      "grad_norm": 0.4723190665245056,
+      "learning_rate": 1.048474297658912e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7806352104252573,
+      "grad_norm": 0.5968837141990662,
+      "learning_rate": 1.0206799200306208e-05,
+      "loss": 0.049,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6200
+    },
+    {
+      "epoch": 0.800276999590796,
+      "eval_loss": 0.074190653860569,
+      "eval_runtime": 42.7728,
+      "eval_samples_per_second": 11.69,
+      "eval_steps_per_second": 1.473,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6356
+    },
+    {
+      "epoch": 0.8058169914067173,
+      "grad_norm": 0.6108983755111694,
+      "learning_rate": 9.92451243577936e-06,
+      "loss": 0.0508,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6400
+    },
+    {
+      "epoch": 0.8309987723881772,
+      "grad_norm": 0.5209892392158508,
+      "learning_rate": 9.638335604710197e-06,
+      "loss": 0.0502,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6600
+    },
+    {
+      "epoch": 0.856180553369637,
+      "grad_norm": 0.3816191554069519,
+      "learning_rate": 9.348727870309973e-06,
+      "loss": 0.0497,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 6800
+    },
+    {
+      "epoch": 0.881362334351097,
+      "grad_norm": 0.5576559901237488,
+      "learning_rate": 9.056153900584243e-06,
+      "loss": 0.0494,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9065441153325569,
+      "grad_norm": 0.6634303331375122,
+      "learning_rate": 8.761083122785266e-06,
+      "loss": 0.0488,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7200
+    },
+    {
+      "epoch": 0.9317258963140168,
+      "grad_norm": 0.4906536042690277,
+      "learning_rate": 8.463988970228283e-06,
+      "loss": 0.0496,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7400
+    },
+    {
+      "epoch": 0.9569076772954768,
+      "grad_norm": 0.45645272731781006,
+      "learning_rate": 8.165348122680214e-06,
+      "loss": 0.0497,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7600
+    },
+    {
+      "epoch": 0.9820894582769366,
+      "grad_norm": 0.3046559989452362,
+      "learning_rate": 7.865639741539483e-06,
+      "loss": 0.0487,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7800
+    },
+    {
+      "epoch": 1.0002518178098145,
+      "eval_loss": 0.06988665461540222,
+      "eval_runtime": 35.211,
+      "eval_samples_per_second": 14.2,
+      "eval_steps_per_second": 1.789,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 7945
+    },
+    {
+      "epoch": 1.007176807579716,
+      "grad_norm": 0.24347852170467377,
+      "learning_rate": 7.565344701034122e-06,
+      "loss": 0.0465,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8000
+    },
+    {
+      "epoch": 1.032358588561176,
+      "grad_norm": 0.4792805016040802,
+      "learning_rate": 7.264944816671722e-06,
+      "loss": 0.0471,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8200
+    },
+    {
+      "epoch": 1.057540369542636,
+      "grad_norm": 0.40505144000053406,
+      "learning_rate": 6.964922072179084e-06,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8400
+    },
+    {
+      "epoch": 1.0827221505240958,
+      "grad_norm": 0.43307843804359436,
+      "learning_rate": 6.665757846171986e-06,
+      "loss": 0.047,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8600
+    },
+    {
+      "epoch": 1.1079039315055557,
+      "grad_norm": 0.6030473709106445,
+      "learning_rate": 6.36793213979585e-06,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 8800
+    },
+    {
+      "epoch": 1.1330857124870157,
+      "grad_norm": 0.492542564868927,
+      "learning_rate": 6.071922806576484e-06,
+      "loss": 0.0447,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1582674934684756,
+      "grad_norm": 0.35956957936286926,
+      "learning_rate": 5.778204785716663e-06,
+      "loss": 0.0459,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9200
+    },
+    {
+      "epoch": 1.1834492744499354,
+      "grad_norm": 0.26773375272750854,
+      "learning_rate": 5.487249340068649e-06,
+      "loss": 0.0466,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9400
+    },
+    {
+      "epoch": 1.2003210677075136,
+      "eval_loss": 0.06683629006147385,
+      "eval_runtime": 39.9381,
+      "eval_samples_per_second": 12.519,
+      "eval_steps_per_second": 1.577,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9534
+    },
+    {
+      "epoch": 1.2086310554313955,
+      "grad_norm": 0.49637848138809204,
+      "learning_rate": 5.199523300005305e-06,
+      "loss": 0.0459,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9600
+    },
+    {
+      "epoch": 1.2338128364128553,
+      "grad_norm": 0.4869849979877472,
+      "learning_rate": 4.9154883144030415e-06,
+      "loss": 0.0455,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 9800
+    },
+    {
+      "epoch": 1.2589946173943152,
+      "grad_norm": 0.28114384412765503,
+      "learning_rate": 4.6356001099382885e-06,
+      "loss": 0.045,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10000
+    },
+    {
+      "epoch": 1.284176398375775,
+      "grad_norm": 0.3514762222766876,
+      "learning_rate": 4.360307759886035e-06,
+      "loss": 0.0443,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10200
+    },
+    {
+      "epoch": 1.309358179357235,
+      "grad_norm": 0.4368722140789032,
+      "learning_rate": 4.09005296359353e-06,
+      "loss": 0.0464,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10400
+    },
+    {
+      "epoch": 1.334539960338695,
+      "grad_norm": 0.3975982367992401,
+      "learning_rate": 3.825269337785298e-06,
+      "loss": 0.0441,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10600
+    },
+    {
+      "epoch": 1.359721741320155,
+      "grad_norm": 0.7111567854881287,
+      "learning_rate": 3.5663817208364675e-06,
+      "loss": 0.0446,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 10800
+    },
+    {
+      "epoch": 1.3849035223016148,
+      "grad_norm": 0.6843410134315491,
+      "learning_rate": 3.313805491130775e-06,
+      "loss": 0.0447,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11000
+    },
+    {
+      "epoch": 1.4003903176052126,
+      "eval_loss": 0.06559588760137558,
+      "eval_runtime": 39.6189,
+      "eval_samples_per_second": 12.62,
+      "eval_steps_per_second": 1.59,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11123
+    },
+    {
+      "epoch": 1.4100853032830747,
+      "grad_norm": 0.5334785580635071,
+      "learning_rate": 3.067945900596839e-06,
+      "loss": 0.0426,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11200
+    },
+    {
+      "epoch": 1.4352670842645345,
+      "grad_norm": 0.4667738080024719,
+      "learning_rate": 2.829197424492086e-06,
+      "loss": 0.044,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11400
+    },
+    {
+      "epoch": 1.4604488652459946,
+      "grad_norm": 0.5390481352806091,
+      "learning_rate": 2.597943128477559e-06,
+      "loss": 0.0437,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11600
+    },
+    {
+      "epoch": 1.4856306462274544,
+      "grad_norm": 0.5545275807380676,
+      "learning_rate": 2.3745540539991293e-06,
+      "loss": 0.0433,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 11800
+    },
+    {
+      "epoch": 1.5108124272089145,
+      "grad_norm": 0.5652483105659485,
+      "learning_rate": 2.1593886229612245e-06,
+      "loss": 0.0433,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 12000
+    },
+    {
+      "epoch": 1.5359942081903744,
+      "grad_norm": 0.3532222807407379,
+      "learning_rate": 1.952792062648304e-06,
+      "loss": 0.0429,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 12200
+    },
+    {
+      "epoch": 1.5611759891718342,
+      "grad_norm": 0.6139308214187622,
+      "learning_rate": 1.7550958518167446e-06,
+      "loss": 0.0438,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 12400
+    },
+    {
+      "epoch": 1.586357770153294,
+      "grad_norm": 0.40390023589134216,
+      "learning_rate": 1.5666171888458747e-06,
+      "loss": 0.0432,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 12600
+    },
+    {
+      "epoch": 1.6004595675029116,
+      "eval_loss": 0.06468167155981064,
+      "eval_runtime": 38.1547,
+      "eval_samples_per_second": 13.105,
+      "eval_steps_per_second": 1.651,
+      "memory/device_mem_reserved(gib)": 36.15,
+      "memory/max_mem_active(gib)": 31.11,
+      "memory/max_mem_allocated(gib)": 31.11,
+      "step": 12712
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 15885,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1589,
+  "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": 9.613419242732913e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-12712/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6567923762df25f157b6869fee06dcebcdeb8ba971499372b10e86aac90dbd6b
+size 6904

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-0.6B
+- lora
+- transformers
+---
+
+# 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 0.17.0

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b097101152bf05b9759cfec42c17e978ac65c6c256cfa4e5dcb578cce4b6491
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/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
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|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' }}
+        {{- 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 %}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e4501970d2dca8c5e444674d4e371beb5a5ccc57b0f51d3444ac66d7c6fc99
+size 82463540

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6b7ca4ee7624baaa89d67d356a7aafce6a91085507b70891a1029eccfd769a
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae3a7f91d7a2417e23b36a5022d06cd0afb8d6c4e8ca7ed8682a212926ba90c
+size 14512

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24fa8950a16c1f594fe70c5ece34ea61e17cef814da16c86dd55fd49a98d4588
+size 1064

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen-06b-sft-4type-old-format-lora-dataset-a-4096-balanced-higher-maxm/checkpoint-14301/tokenizer.json

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