Upload qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm to classroom repo

.gitattributes

@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-16976/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-19098/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-21216/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-2122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-4244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+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-c-8192-balanced-higher-maxm/.gitattributes

@@ -0,0 +1,46 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6366/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8488/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-10610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-12732/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-14854/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-16976/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-19098/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-21216/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/README.md

@@ -0,0 +1,142 @@
+---
+library_name: peft
+tags:
+- axolotl
+- "base_model: Qwen/Qwen3-0.6B"
+- lora
+- transformers
+datasets:
+- custom
+base_model: Qwen/Qwen3-0.6B
+pipeline_tag: text-generation
+model-index:
+- name: root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-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: /root/Documents/trae_projects/lab1/models/Qwen/Qwen3-0.6B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+datasets:
+- path: /root/Documents/trae_projects/lab1/sft_4type_merged_n3to9_remap_completion_no_wrong_maxlen8192_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: /root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm
+dataset_prepared_path: /root/Documents/trae_projects/lab1/qwen_06b_4type_prepared_8192_old_format_lora_dataset_c_balanced_higher_maxm
+micro_batch_size: 2
+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: 8192
+pad_to_sequence_len: true
+group_by_length: false
+max_packed_sequence_len: null
+packing: true
+flash_attention: false
+gradient_checkpointing: false
+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>
+
+# root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm
+
+This model was trained from scratch on the /root/Documents/trae_projects/lab1/sft_4type_merged_n3to9_remap_completion_no_wrong_maxlen8192_rebalanced_higher_maxm.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0661
+- Memory/max Mem Active(gib): 74.39
+- Memory/max Mem Allocated(gib): 74.39
+- Memory/device Mem Reserved(gib): 79.87
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB 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: 21216
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Mem Active(gib) | Mem Allocated(gib) | Mem Reserved(gib) |
+|:-------------:|:------:|:-----:|:---------------:|:---------------:|:------------------:|:-----------------:|
+| No log        | 0      | 0     | 2.1083          | 25.13           | 25.13              | 25.21             |
+| 0.051         | 0.2000 | 2122  | 0.1043          | 74.39           | 74.39              | 79.87             |
+| 0.0468        | 0.4001 | 4244  | 0.0895          | 74.39           | 74.39              | 79.87             |
+| 0.0362        | 0.6001 | 6366  | 0.0828          | 74.39           | 74.39              | 79.87             |
+| 0.0355        | 0.8002 | 8488  | 0.0763          | 74.39           | 74.39              | 79.87             |
+| 0.0352        | 1.0002 | 10610 | 0.0732          | 74.39           | 74.39              | 79.87             |
+| 0.0336        | 1.2002 | 12732 | 0.0690          | 74.39           | 74.39              | 79.87             |
+| 0.0294        | 1.4003 | 14854 | 0.0686          | 74.39           | 74.39              | 79.87             |
+| 0.0318        | 1.6003 | 16976 | 0.0676          | 74.39           | 74.39              | 79.87             |
+| 0.0323        | 1.8003 | 19098 | 0.0661          | 74.39           | 74.39              | 79.87             |
+
+
+### Framework versions
+
+- PEFT 0.17.0
+- Transformers 4.55.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/Documents/trae_projects/lab1/models/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",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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-c-8192-balanced-higher-maxm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93518f00f8a83db0d213fd1ee4e4f2740ac1ecefa94267a1bd368a737bc0f4d
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-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-c-8192-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-c-8192-balanced-higher-maxm/checkpoint-10610/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /root/Documents/trae_projects/lab1/models/Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:/root/Documents/trae_projects/lab1/models/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-c-8192-balanced-higher-maxm/checkpoint-10610/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/Documents/trae_projects/lab1/models/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",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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-c-8192-balanced-higher-maxm/checkpoint-10610/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d382598911a3a197466ca3e4d75f99e13da8e081abbf859cce5bf7e9ff83e7
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/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-c-8192-balanced-higher-maxm/checkpoint-10610/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-c-8192-balanced-higher-maxm/checkpoint-10610/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fda032b32af6ac644e0d9f11efb24d266326be4f1161ef70d30d6347c1373e
+size 82463941

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36253919fc019372419a57b7cfc8951767b60685c346c4804fb5d1d883366280
+size 14645

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c226b02c96a3c905048ecee9019df9e4829880a8653aef32f8487619120b2417
+size 1465

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/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-c-8192-balanced-higher-maxm/checkpoint-10610/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-c-8192-balanced-higher-maxm/checkpoint-10610/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-c-8192-balanced-higher-maxm/checkpoint-10610/trainer_state.json

@@ -0,0 +1,639 @@
+{
+  "best_global_step": 10610,
+  "best_metric": 0.07321257889270782,
+  "best_model_checkpoint": "/root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610",
+  "epoch": 1.0001885391749055,
+  "eval_steps": 2122,
+  "global_step": 10610,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.108273983001709,
+      "eval_runtime": 141.8339,
+      "eval_samples_per_second": 3.525,
+      "eval_steps_per_second": 1.763,
+      "memory/device_mem_reserved(gib)": 25.21,
+      "memory/max_mem_active(gib)": 25.13,
+      "memory/max_mem_allocated(gib)": 25.13,
+      "step": 0
+    },
+    {
+      "epoch": 0.018853917490543583,
+      "grad_norm": 0.9218831062316895,
+      "learning_rate": 1.4925e-05,
+      "loss": 0.4004,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 200
+    },
+    {
+      "epoch": 0.037707834981087165,
+      "grad_norm": 0.834619402885437,
+      "learning_rate": 1.4996681781199102e-05,
+      "loss": 0.092,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 400
+    },
+    {
+      "epoch": 0.05656175247163075,
+      "grad_norm": 1.0279525518417358,
+      "learning_rate": 1.4986663313861234e-05,
+      "loss": 0.0822,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 600
+    },
+    {
+      "epoch": 0.07541566996217433,
+      "grad_norm": 0.2367861121892929,
+      "learning_rate": 1.4969953468425292e-05,
+      "loss": 0.0752,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 800
+    },
+    {
+      "epoch": 0.0942695874527179,
+      "grad_norm": 1.9785773754119873,
+      "learning_rate": 1.4946567179701235e-05,
+      "loss": 0.0635,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1131235049432615,
+      "grad_norm": 0.21004119515419006,
+      "learning_rate": 1.4916525349724263e-05,
+      "loss": 0.0601,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1200
+    },
+    {
+      "epoch": 0.13197742243380509,
+      "grad_norm": 1.4633631706237793,
+      "learning_rate": 1.4879854829073164e-05,
+      "loss": 0.0606,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1400
+    },
+    {
+      "epoch": 0.15083133992434866,
+      "grad_norm": 0.6432693600654602,
+      "learning_rate": 1.4836588392871974e-05,
+      "loss": 0.065,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1600
+    },
+    {
+      "epoch": 0.16968525741489224,
+      "grad_norm": 0.5889899134635925,
+      "learning_rate": 1.4786764711496456e-05,
+      "loss": 0.063,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1885391749054358,
+      "grad_norm": 1.310059666633606,
+      "learning_rate": 1.4730428316011569e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2000
+    },
+    {
+      "epoch": 0.20004006457466741,
+      "eval_loss": 0.10432351380586624,
+      "eval_runtime": 142.1189,
+      "eval_samples_per_second": 3.518,
+      "eval_steps_per_second": 1.759,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2122
+    },
+    {
+      "epoch": 0.2073930923959794,
+      "grad_norm": 1.158856987953186,
+      "learning_rate": 1.4667629558370783e-05,
+      "loss": 0.0534,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2200
+    },
+    {
+      "epoch": 0.226247009886523,
+      "grad_norm": 1.5630080699920654,
+      "learning_rate": 1.459842456641288e-05,
+      "loss": 0.0533,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2400
+    },
+    {
+      "epoch": 0.24510092737706657,
+      "grad_norm": 1.5642732381820679,
+      "learning_rate": 1.4522875193696387e-05,
+      "loss": 0.0492,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2600
+    },
+    {
+      "epoch": 0.26395484486761017,
+      "grad_norm": 0.5224480628967285,
+      "learning_rate": 1.4441048964216536e-05,
+      "loss": 0.0446,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2828087623581537,
+      "grad_norm": 0.3511959910392761,
+      "learning_rate": 1.435301901205414e-05,
+      "loss": 0.0493,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3016626798486973,
+      "grad_norm": 0.6137123107910156,
+      "learning_rate": 1.425886401601031e-05,
+      "loss": 0.0464,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3200
+    },
+    {
+      "epoch": 0.32051659733924087,
+      "grad_norm": 0.4698449373245239,
+      "learning_rate": 1.4158668129285467e-05,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3393705148297845,
+      "grad_norm": 0.49713844060897827,
+      "learning_rate": 1.4052520904265484e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3600
+    },
+    {
+      "epoch": 0.3582244323203281,
+      "grad_norm": 0.3621199429035187,
+      "learning_rate": 1.394051721248216e-05,
+      "loss": 0.0418,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3800
+    },
+    {
+      "epoch": 0.3770783498108716,
+      "grad_norm": 0.8989943265914917,
+      "learning_rate": 1.3822757159819608e-05,
+      "loss": 0.0421,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39593226730141523,
+      "grad_norm": 0.2413109987974167,
+      "learning_rate": 1.3699345997042312e-05,
+      "loss": 0.0468,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4200
+    },
+    {
+      "epoch": 0.40008012914933483,
+      "eval_loss": 0.0894976556301117,
+      "eval_runtime": 141.6741,
+      "eval_samples_per_second": 3.529,
+      "eval_steps_per_second": 1.765,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4244
+    },
+    {
+      "epoch": 0.4147861847919588,
+      "grad_norm": 1.3992276191711426,
+      "learning_rate": 1.3570394025724828e-05,
+      "loss": 0.0439,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4400
+    },
+    {
+      "epoch": 0.4336401022825024,
+      "grad_norm": 0.27030619978904724,
+      "learning_rate": 1.3436016499667199e-05,
+      "loss": 0.0424,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4600
+    },
+    {
+      "epoch": 0.452494019773046,
+      "grad_norm": 0.1682862490415573,
+      "learning_rate": 1.3296333521884216e-05,
+      "loss": 0.0472,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4800
+    },
+    {
+      "epoch": 0.47134793726358953,
+      "grad_norm": 0.28954288363456726,
+      "learning_rate": 1.315146993726058e-05,
+      "loss": 0.0411,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49020185475413314,
+      "grad_norm": 0.1974649876356125,
+      "learning_rate": 1.3001555220967904e-05,
+      "loss": 0.044,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5090557722446767,
+      "grad_norm": 0.6311449408531189,
+      "learning_rate": 1.2846723362743286e-05,
+      "loss": 0.0438,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5279096897352203,
+      "grad_norm": 0.5518035888671875,
+      "learning_rate": 1.2687112747132898e-05,
+      "loss": 0.0445,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5600
+    },
+    {
+      "epoch": 0.5467636072257639,
+      "grad_norm": 0.8561716079711914,
+      "learning_rate": 1.2522866029807593e-05,
+      "loss": 0.039,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5800
+    },
+    {
+      "epoch": 0.5656175247163074,
+      "grad_norm": 0.1509927660226822,
+      "learning_rate": 1.2354130010061118e-05,
+      "loss": 0.0386,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6000
+    },
+    {
+      "epoch": 0.584471442206851,
+      "grad_norm": 0.27653419971466064,
+      "learning_rate": 1.2181055499604855e-05,
+      "loss": 0.0362,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6001201937240022,
+      "eval_loss": 0.08275004476308823,
+      "eval_runtime": 141.7236,
+      "eval_samples_per_second": 3.528,
+      "eval_steps_per_second": 1.764,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6366
+    },
+    {
+      "epoch": 0.6033253596973946,
+      "grad_norm": 1.3081331253051758,
+      "learning_rate": 1.2003797187776366e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6221792771879382,
+      "grad_norm": 0.1621595323085785,
+      "learning_rate": 1.1822513503282244e-05,
+      "loss": 0.0436,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6600
+    },
+    {
+      "epoch": 0.6410331946784817,
+      "grad_norm": 0.15179961919784546,
+      "learning_rate": 1.1637366472598779e-05,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6800
+    },
+    {
+      "epoch": 0.6598871121690254,
+      "grad_norm": 0.6694086194038391,
+      "learning_rate": 1.1448521575157077e-05,
+      "loss": 0.0399,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7000
+    },
+    {
+      "epoch": 0.678741029659569,
+      "grad_norm": 0.21060042083263397,
+      "learning_rate": 1.1256147595441987e-05,
+      "loss": 0.0364,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7200
+    },
+    {
+      "epoch": 0.6975949471501125,
+      "grad_norm": 0.3258366584777832,
+      "learning_rate": 1.1060416472137082e-05,
+      "loss": 0.0382,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7400
+    },
+    {
+      "epoch": 0.7164488646406562,
+      "grad_norm": 1.0209743976593018,
+      "learning_rate": 1.0861503144450477e-05,
+      "loss": 0.0383,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7600
+    },
+    {
+      "epoch": 0.7353027821311997,
+      "grad_norm": 0.8924382925033569,
+      "learning_rate": 1.0659585395758893e-05,
+      "loss": 0.038,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7800
+    },
+    {
+      "epoch": 0.7541566996217433,
+      "grad_norm": 0.10590477287769318,
+      "learning_rate": 1.045484369470965e-05,
+      "loss": 0.0368,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7730106171122869,
+      "grad_norm": 0.5611088871955872,
+      "learning_rate": 1.0247461033922658e-05,
+      "loss": 0.0323,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8200
+    },
+    {
+      "epoch": 0.7918645346028305,
+      "grad_norm": 0.11512701958417892,
+      "learning_rate": 1.0037622766436531e-05,
+      "loss": 0.0355,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8400
+    },
+    {
+      "epoch": 0.8001602582986697,
+      "eval_loss": 0.07625631988048553,
+      "eval_runtime": 141.3418,
+      "eval_samples_per_second": 3.538,
+      "eval_steps_per_second": 1.769,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8488
+    },
+    {
+      "epoch": 0.810718452093374,
+      "grad_norm": 0.2973927855491638,
+      "learning_rate": 9.825516440045032e-06,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8600
+    },
+    {
+      "epoch": 0.8295723695839176,
+      "grad_norm": 0.9429569244384766,
+      "learning_rate": 9.61133162967192e-06,
+      "loss": 0.0359,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8800
+    },
+    {
+      "epoch": 0.8484262870744612,
+      "grad_norm": 0.8306987881660461,
+      "learning_rate": 9.395259767933962e-06,
+      "loss": 0.0376,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8672802045650048,
+      "grad_norm": 0.801001250743866,
+      "learning_rate": 9.177493974043633e-06,
+      "loss": 0.0378,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9200
+    },
+    {
+      "epoch": 0.8861341220555483,
+      "grad_norm": 0.6952243447303772,
+      "learning_rate": 8.958228881204364e-06,
+      "loss": 0.037,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9400
+    },
+    {
+      "epoch": 0.904988039546092,
+      "grad_norm": 0.20955415070056915,
+      "learning_rate": 8.737660462652611e-06,
+      "loss": 0.034,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9600
+    },
+    {
+      "epoch": 0.9238419570366355,
+      "grad_norm": 0.2434842586517334,
+      "learning_rate": 8.515985856502264e-06,
+      "loss": 0.0328,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9800
+    },
+    {
+      "epoch": 0.9426958745271791,
+      "grad_norm": 0.5963915586471558,
+      "learning_rate": 8.293403189547904e-06,
+      "loss": 0.0337,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9615497920177227,
+      "grad_norm": 0.3114663064479828,
+      "learning_rate": 8.070111400184415e-06,
+      "loss": 0.0338,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10200
+    },
+    {
+      "epoch": 0.9804037095082663,
+      "grad_norm": 0.16056938469409943,
+      "learning_rate": 7.846310060601191e-06,
+      "loss": 0.0344,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10400
+    },
+    {
+      "epoch": 0.9992576269988098,
+      "grad_norm": 0.9842764139175415,
+      "learning_rate": 7.622199198409896e-06,
+      "loss": 0.0352,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10600
+    },
+    {
+      "epoch": 1.0001885391749055,
+      "eval_loss": 0.07321257889270782,
+      "eval_runtime": 142.2906,
+      "eval_samples_per_second": 3.514,
+      "eval_steps_per_second": 1.757,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10610
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 21216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2122,
+  "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": 4.0120828591991685e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-10610/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d40e5560f21541ba19ac5dfba1e1ee426252943207d82d9237be18780058e4
+size 7313

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /root/Documents/trae_projects/lab1/models/Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:/root/Documents/trae_projects/lab1/models/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-c-8192-balanced-higher-maxm/checkpoint-12732/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/Documents/trae_projects/lab1/models/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",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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-c-8192-balanced-higher-maxm/checkpoint-12732/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860696640247cdaacfd71ec3995c1b52607ee2d2e1cdcdf748ded6835a276099
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/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-c-8192-balanced-higher-maxm/checkpoint-12732/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-c-8192-balanced-higher-maxm/checkpoint-12732/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518f0b71621674199ffb753fa82e3121484620513abbade1a69c7f7c2427f63f
+size 82463941

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f87621832fe5d553a9b88d52cebbb3f82f6829726c1e2bd76865b209ea549d5
+size 14645

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b047343821c5c4eae25708323cc27a29cbe5cd4d7790d73b9efbccb6ae4ab87d
+size 1465

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/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-c-8192-balanced-higher-maxm/checkpoint-12732/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-c-8192-balanced-higher-maxm/checkpoint-12732/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-c-8192-balanced-higher-maxm/checkpoint-12732/trainer_state.json

@@ -0,0 +1,750 @@
+{
+  "best_global_step": 12732,
+  "best_metric": 0.06900843977928162,
+  "best_model_checkpoint": "/root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732",
+  "epoch": 1.2002286037495729,
+  "eval_steps": 2122,
+  "global_step": 12732,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.108273983001709,
+      "eval_runtime": 141.8339,
+      "eval_samples_per_second": 3.525,
+      "eval_steps_per_second": 1.763,
+      "memory/device_mem_reserved(gib)": 25.21,
+      "memory/max_mem_active(gib)": 25.13,
+      "memory/max_mem_allocated(gib)": 25.13,
+      "step": 0
+    },
+    {
+      "epoch": 0.018853917490543583,
+      "grad_norm": 0.9218831062316895,
+      "learning_rate": 1.4925e-05,
+      "loss": 0.4004,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 200
+    },
+    {
+      "epoch": 0.037707834981087165,
+      "grad_norm": 0.834619402885437,
+      "learning_rate": 1.4996681781199102e-05,
+      "loss": 0.092,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 400
+    },
+    {
+      "epoch": 0.05656175247163075,
+      "grad_norm": 1.0279525518417358,
+      "learning_rate": 1.4986663313861234e-05,
+      "loss": 0.0822,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 600
+    },
+    {
+      "epoch": 0.07541566996217433,
+      "grad_norm": 0.2367861121892929,
+      "learning_rate": 1.4969953468425292e-05,
+      "loss": 0.0752,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 800
+    },
+    {
+      "epoch": 0.0942695874527179,
+      "grad_norm": 1.9785773754119873,
+      "learning_rate": 1.4946567179701235e-05,
+      "loss": 0.0635,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1131235049432615,
+      "grad_norm": 0.21004119515419006,
+      "learning_rate": 1.4916525349724263e-05,
+      "loss": 0.0601,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1200
+    },
+    {
+      "epoch": 0.13197742243380509,
+      "grad_norm": 1.4633631706237793,
+      "learning_rate": 1.4879854829073164e-05,
+      "loss": 0.0606,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1400
+    },
+    {
+      "epoch": 0.15083133992434866,
+      "grad_norm": 0.6432693600654602,
+      "learning_rate": 1.4836588392871974e-05,
+      "loss": 0.065,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1600
+    },
+    {
+      "epoch": 0.16968525741489224,
+      "grad_norm": 0.5889899134635925,
+      "learning_rate": 1.4786764711496456e-05,
+      "loss": 0.063,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1885391749054358,
+      "grad_norm": 1.310059666633606,
+      "learning_rate": 1.4730428316011569e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2000
+    },
+    {
+      "epoch": 0.20004006457466741,
+      "eval_loss": 0.10432351380586624,
+      "eval_runtime": 142.1189,
+      "eval_samples_per_second": 3.518,
+      "eval_steps_per_second": 1.759,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2122
+    },
+    {
+      "epoch": 0.2073930923959794,
+      "grad_norm": 1.158856987953186,
+      "learning_rate": 1.4667629558370783e-05,
+      "loss": 0.0534,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2200
+    },
+    {
+      "epoch": 0.226247009886523,
+      "grad_norm": 1.5630080699920654,
+      "learning_rate": 1.459842456641288e-05,
+      "loss": 0.0533,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2400
+    },
+    {
+      "epoch": 0.24510092737706657,
+      "grad_norm": 1.5642732381820679,
+      "learning_rate": 1.4522875193696387e-05,
+      "loss": 0.0492,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2600
+    },
+    {
+      "epoch": 0.26395484486761017,
+      "grad_norm": 0.5224480628967285,
+      "learning_rate": 1.4441048964216536e-05,
+      "loss": 0.0446,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2828087623581537,
+      "grad_norm": 0.3511959910392761,
+      "learning_rate": 1.435301901205414e-05,
+      "loss": 0.0493,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3016626798486973,
+      "grad_norm": 0.6137123107910156,
+      "learning_rate": 1.425886401601031e-05,
+      "loss": 0.0464,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3200
+    },
+    {
+      "epoch": 0.32051659733924087,
+      "grad_norm": 0.4698449373245239,
+      "learning_rate": 1.4158668129285467e-05,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3393705148297845,
+      "grad_norm": 0.49713844060897827,
+      "learning_rate": 1.4052520904265484e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3600
+    },
+    {
+      "epoch": 0.3582244323203281,
+      "grad_norm": 0.3621199429035187,
+      "learning_rate": 1.394051721248216e-05,
+      "loss": 0.0418,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3800
+    },
+    {
+      "epoch": 0.3770783498108716,
+      "grad_norm": 0.8989943265914917,
+      "learning_rate": 1.3822757159819608e-05,
+      "loss": 0.0421,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39593226730141523,
+      "grad_norm": 0.2413109987974167,
+      "learning_rate": 1.3699345997042312e-05,
+      "loss": 0.0468,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4200
+    },
+    {
+      "epoch": 0.40008012914933483,
+      "eval_loss": 0.0894976556301117,
+      "eval_runtime": 141.6741,
+      "eval_samples_per_second": 3.529,
+      "eval_steps_per_second": 1.765,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4244
+    },
+    {
+      "epoch": 0.4147861847919588,
+      "grad_norm": 1.3992276191711426,
+      "learning_rate": 1.3570394025724828e-05,
+      "loss": 0.0439,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4400
+    },
+    {
+      "epoch": 0.4336401022825024,
+      "grad_norm": 0.27030619978904724,
+      "learning_rate": 1.3436016499667199e-05,
+      "loss": 0.0424,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4600
+    },
+    {
+      "epoch": 0.452494019773046,
+      "grad_norm": 0.1682862490415573,
+      "learning_rate": 1.3296333521884216e-05,
+      "loss": 0.0472,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4800
+    },
+    {
+      "epoch": 0.47134793726358953,
+      "grad_norm": 0.28954288363456726,
+      "learning_rate": 1.315146993726058e-05,
+      "loss": 0.0411,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49020185475413314,
+      "grad_norm": 0.1974649876356125,
+      "learning_rate": 1.3001555220967904e-05,
+      "loss": 0.044,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5090557722446767,
+      "grad_norm": 0.6311449408531189,
+      "learning_rate": 1.2846723362743286e-05,
+      "loss": 0.0438,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5279096897352203,
+      "grad_norm": 0.5518035888671875,
+      "learning_rate": 1.2687112747132898e-05,
+      "loss": 0.0445,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5600
+    },
+    {
+      "epoch": 0.5467636072257639,
+      "grad_norm": 0.8561716079711914,
+      "learning_rate": 1.2522866029807593e-05,
+      "loss": 0.039,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5800
+    },
+    {
+      "epoch": 0.5656175247163074,
+      "grad_norm": 0.1509927660226822,
+      "learning_rate": 1.2354130010061118e-05,
+      "loss": 0.0386,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6000
+    },
+    {
+      "epoch": 0.584471442206851,
+      "grad_norm": 0.27653419971466064,
+      "learning_rate": 1.2181055499604855e-05,
+      "loss": 0.0362,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6001201937240022,
+      "eval_loss": 0.08275004476308823,
+      "eval_runtime": 141.7236,
+      "eval_samples_per_second": 3.528,
+      "eval_steps_per_second": 1.764,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6366
+    },
+    {
+      "epoch": 0.6033253596973946,
+      "grad_norm": 1.3081331253051758,
+      "learning_rate": 1.2003797187776366e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6221792771879382,
+      "grad_norm": 0.1621595323085785,
+      "learning_rate": 1.1822513503282244e-05,
+      "loss": 0.0436,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6600
+    },
+    {
+      "epoch": 0.6410331946784817,
+      "grad_norm": 0.15179961919784546,
+      "learning_rate": 1.1637366472598779e-05,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6800
+    },
+    {
+      "epoch": 0.6598871121690254,
+      "grad_norm": 0.6694086194038391,
+      "learning_rate": 1.1448521575157077e-05,
+      "loss": 0.0399,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7000
+    },
+    {
+      "epoch": 0.678741029659569,
+      "grad_norm": 0.21060042083263397,
+      "learning_rate": 1.1256147595441987e-05,
+      "loss": 0.0364,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7200
+    },
+    {
+      "epoch": 0.6975949471501125,
+      "grad_norm": 0.3258366584777832,
+      "learning_rate": 1.1060416472137082e-05,
+      "loss": 0.0382,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7400
+    },
+    {
+      "epoch": 0.7164488646406562,
+      "grad_norm": 1.0209743976593018,
+      "learning_rate": 1.0861503144450477e-05,
+      "loss": 0.0383,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7600
+    },
+    {
+      "epoch": 0.7353027821311997,
+      "grad_norm": 0.8924382925033569,
+      "learning_rate": 1.0659585395758893e-05,
+      "loss": 0.038,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7800
+    },
+    {
+      "epoch": 0.7541566996217433,
+      "grad_norm": 0.10590477287769318,
+      "learning_rate": 1.045484369470965e-05,
+      "loss": 0.0368,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7730106171122869,
+      "grad_norm": 0.5611088871955872,
+      "learning_rate": 1.0247461033922658e-05,
+      "loss": 0.0323,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8200
+    },
+    {
+      "epoch": 0.7918645346028305,
+      "grad_norm": 0.11512701958417892,
+      "learning_rate": 1.0037622766436531e-05,
+      "loss": 0.0355,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8400
+    },
+    {
+      "epoch": 0.8001602582986697,
+      "eval_loss": 0.07625631988048553,
+      "eval_runtime": 141.3418,
+      "eval_samples_per_second": 3.538,
+      "eval_steps_per_second": 1.769,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8488
+    },
+    {
+      "epoch": 0.810718452093374,
+      "grad_norm": 0.2973927855491638,
+      "learning_rate": 9.825516440045032e-06,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8600
+    },
+    {
+      "epoch": 0.8295723695839176,
+      "grad_norm": 0.9429569244384766,
+      "learning_rate": 9.61133162967192e-06,
+      "loss": 0.0359,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8800
+    },
+    {
+      "epoch": 0.8484262870744612,
+      "grad_norm": 0.8306987881660461,
+      "learning_rate": 9.395259767933962e-06,
+      "loss": 0.0376,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8672802045650048,
+      "grad_norm": 0.801001250743866,
+      "learning_rate": 9.177493974043633e-06,
+      "loss": 0.0378,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9200
+    },
+    {
+      "epoch": 0.8861341220555483,
+      "grad_norm": 0.6952243447303772,
+      "learning_rate": 8.958228881204364e-06,
+      "loss": 0.037,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9400
+    },
+    {
+      "epoch": 0.904988039546092,
+      "grad_norm": 0.20955415070056915,
+      "learning_rate": 8.737660462652611e-06,
+      "loss": 0.034,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9600
+    },
+    {
+      "epoch": 0.9238419570366355,
+      "grad_norm": 0.2434842586517334,
+      "learning_rate": 8.515985856502264e-06,
+      "loss": 0.0328,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9800
+    },
+    {
+      "epoch": 0.9426958745271791,
+      "grad_norm": 0.5963915586471558,
+      "learning_rate": 8.293403189547904e-06,
+      "loss": 0.0337,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9615497920177227,
+      "grad_norm": 0.3114663064479828,
+      "learning_rate": 8.070111400184415e-06,
+      "loss": 0.0338,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10200
+    },
+    {
+      "epoch": 0.9804037095082663,
+      "grad_norm": 0.16056938469409943,
+      "learning_rate": 7.846310060601191e-06,
+      "loss": 0.0344,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10400
+    },
+    {
+      "epoch": 0.9992576269988098,
+      "grad_norm": 0.9842764139175415,
+      "learning_rate": 7.622199198409896e-06,
+      "loss": 0.0352,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10600
+    },
+    {
+      "epoch": 1.0001885391749055,
+      "eval_loss": 0.07321257889270782,
+      "eval_runtime": 142.2906,
+      "eval_samples_per_second": 3.514,
+      "eval_steps_per_second": 1.757,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10610
+    },
+    {
+      "epoch": 1.018099760790922,
+      "grad_norm": 0.11459363996982574,
+      "learning_rate": 7.397979117865168e-06,
+      "loss": 0.0304,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10800
+    },
+    {
+      "epoch": 1.0369536782814655,
+      "grad_norm": 0.5405158996582031,
+      "learning_rate": 7.173850220838073e-06,
+      "loss": 0.0307,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11000
+    },
+    {
+      "epoch": 1.055807595772009,
+      "grad_norm": 0.22435125708580017,
+      "learning_rate": 6.950012827702292e-06,
+      "loss": 0.0339,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11200
+    },
+    {
+      "epoch": 1.0746615132625525,
+      "grad_norm": 0.33569714426994324,
+      "learning_rate": 6.726666998293187e-06,
+      "loss": 0.0346,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11400
+    },
+    {
+      "epoch": 1.093515430753096,
+      "grad_norm": 0.25280582904815674,
+      "learning_rate": 6.504012353099694e-06,
+      "loss": 0.0316,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11600
+    },
+    {
+      "epoch": 1.1123693482436399,
+      "grad_norm": 0.48694702982902527,
+      "learning_rate": 6.282247894848904e-06,
+      "loss": 0.0334,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11800
+    },
+    {
+      "epoch": 1.1312232657341834,
+      "grad_norm": 0.13796062767505646,
+      "learning_rate": 6.061571830642791e-06,
+      "loss": 0.0301,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12000
+    },
+    {
+      "epoch": 1.150077183224727,
+      "grad_norm": 0.8943594694137573,
+      "learning_rate": 5.842181394806027e-06,
+      "loss": 0.0326,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12200
+    },
+    {
+      "epoch": 1.1689311007152705,
+      "grad_norm": 0.4626399874687195,
+      "learning_rate": 5.62427267260327e-06,
+      "loss": 0.0295,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12400
+    },
+    {
+      "epoch": 1.187785018205814,
+      "grad_norm": 0.2461213320493698,
+      "learning_rate": 5.408040424983424e-06,
+      "loss": 0.0336,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12600
+    },
+    {
+      "epoch": 1.2002286037495729,
+      "eval_loss": 0.06900843977928162,
+      "eval_runtime": 141.9347,
+      "eval_samples_per_second": 3.523,
+      "eval_steps_per_second": 1.761,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12732
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 21216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2122,
+  "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": 4.814508884691517e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-12732/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d40e5560f21541ba19ac5dfba1e1ee426252943207d82d9237be18780058e4
+size 7313

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /root/Documents/trae_projects/lab1/models/Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:/root/Documents/trae_projects/lab1/models/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-c-8192-balanced-higher-maxm/checkpoint-14854/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/Documents/trae_projects/lab1/models/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",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_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-c-8192-balanced-higher-maxm/checkpoint-14854/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43863fec5850e98083cd30ae72ef40ba1309637208fd92b83b2bc4a7593da22c
+size 161533160

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/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-c-8192-balanced-higher-maxm/checkpoint-14854/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-c-8192-balanced-higher-maxm/checkpoint-14854/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f33c2dcd99f15a9f6fee16ef230d7e3f1170ace8fc96af900e88b8fe3f0db0
+size 82463941

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1aa23dda2276c42e2f5fe8fe6c931c08608d57e094c4a16ed3ff1abf81b8ef
+size 14645

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1a07da459b0a3eb955f4fd8a329acfff42f4e8aca4891963f6f3d818424215
+size 1465

qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854/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-c-8192-balanced-higher-maxm/checkpoint-14854/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-c-8192-balanced-higher-maxm/checkpoint-14854/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-c-8192-balanced-higher-maxm/checkpoint-14854/trainer_state.json

@@ -0,0 +1,871 @@
+{
+  "best_global_step": 14854,
+  "best_metric": 0.06857609003782272,
+  "best_model_checkpoint": "/root/autodl-tmp/outputs/qwen-06b-sft-4type-old-format-lora-dataset-c-8192-balanced-higher-maxm/checkpoint-14854",
+  "epoch": 1.4002686683242402,
+  "eval_steps": 2122,
+  "global_step": 14854,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.108273983001709,
+      "eval_runtime": 141.8339,
+      "eval_samples_per_second": 3.525,
+      "eval_steps_per_second": 1.763,
+      "memory/device_mem_reserved(gib)": 25.21,
+      "memory/max_mem_active(gib)": 25.13,
+      "memory/max_mem_allocated(gib)": 25.13,
+      "step": 0
+    },
+    {
+      "epoch": 0.018853917490543583,
+      "grad_norm": 0.9218831062316895,
+      "learning_rate": 1.4925e-05,
+      "loss": 0.4004,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 200
+    },
+    {
+      "epoch": 0.037707834981087165,
+      "grad_norm": 0.834619402885437,
+      "learning_rate": 1.4996681781199102e-05,
+      "loss": 0.092,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 400
+    },
+    {
+      "epoch": 0.05656175247163075,
+      "grad_norm": 1.0279525518417358,
+      "learning_rate": 1.4986663313861234e-05,
+      "loss": 0.0822,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 600
+    },
+    {
+      "epoch": 0.07541566996217433,
+      "grad_norm": 0.2367861121892929,
+      "learning_rate": 1.4969953468425292e-05,
+      "loss": 0.0752,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 800
+    },
+    {
+      "epoch": 0.0942695874527179,
+      "grad_norm": 1.9785773754119873,
+      "learning_rate": 1.4946567179701235e-05,
+      "loss": 0.0635,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1131235049432615,
+      "grad_norm": 0.21004119515419006,
+      "learning_rate": 1.4916525349724263e-05,
+      "loss": 0.0601,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1200
+    },
+    {
+      "epoch": 0.13197742243380509,
+      "grad_norm": 1.4633631706237793,
+      "learning_rate": 1.4879854829073164e-05,
+      "loss": 0.0606,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1400
+    },
+    {
+      "epoch": 0.15083133992434866,
+      "grad_norm": 0.6432693600654602,
+      "learning_rate": 1.4836588392871974e-05,
+      "loss": 0.065,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1600
+    },
+    {
+      "epoch": 0.16968525741489224,
+      "grad_norm": 0.5889899134635925,
+      "learning_rate": 1.4786764711496456e-05,
+      "loss": 0.063,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1885391749054358,
+      "grad_norm": 1.310059666633606,
+      "learning_rate": 1.4730428316011569e-05,
+      "loss": 0.051,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2000
+    },
+    {
+      "epoch": 0.20004006457466741,
+      "eval_loss": 0.10432351380586624,
+      "eval_runtime": 142.1189,
+      "eval_samples_per_second": 3.518,
+      "eval_steps_per_second": 1.759,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2122
+    },
+    {
+      "epoch": 0.2073930923959794,
+      "grad_norm": 1.158856987953186,
+      "learning_rate": 1.4667629558370783e-05,
+      "loss": 0.0534,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2200
+    },
+    {
+      "epoch": 0.226247009886523,
+      "grad_norm": 1.5630080699920654,
+      "learning_rate": 1.459842456641288e-05,
+      "loss": 0.0533,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2400
+    },
+    {
+      "epoch": 0.24510092737706657,
+      "grad_norm": 1.5642732381820679,
+      "learning_rate": 1.4522875193696387e-05,
+      "loss": 0.0492,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2600
+    },
+    {
+      "epoch": 0.26395484486761017,
+      "grad_norm": 0.5224480628967285,
+      "learning_rate": 1.4441048964216536e-05,
+      "loss": 0.0446,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2828087623581537,
+      "grad_norm": 0.3511959910392761,
+      "learning_rate": 1.435301901205414e-05,
+      "loss": 0.0493,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3016626798486973,
+      "grad_norm": 0.6137123107910156,
+      "learning_rate": 1.425886401601031e-05,
+      "loss": 0.0464,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3200
+    },
+    {
+      "epoch": 0.32051659733924087,
+      "grad_norm": 0.4698449373245239,
+      "learning_rate": 1.4158668129285467e-05,
+      "loss": 0.0453,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3393705148297845,
+      "grad_norm": 0.49713844060897827,
+      "learning_rate": 1.4052520904265484e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3600
+    },
+    {
+      "epoch": 0.3582244323203281,
+      "grad_norm": 0.3621199429035187,
+      "learning_rate": 1.394051721248216e-05,
+      "loss": 0.0418,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 3800
+    },
+    {
+      "epoch": 0.3770783498108716,
+      "grad_norm": 0.8989943265914917,
+      "learning_rate": 1.3822757159819608e-05,
+      "loss": 0.0421,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39593226730141523,
+      "grad_norm": 0.2413109987974167,
+      "learning_rate": 1.3699345997042312e-05,
+      "loss": 0.0468,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4200
+    },
+    {
+      "epoch": 0.40008012914933483,
+      "eval_loss": 0.0894976556301117,
+      "eval_runtime": 141.6741,
+      "eval_samples_per_second": 3.529,
+      "eval_steps_per_second": 1.765,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4244
+    },
+    {
+      "epoch": 0.4147861847919588,
+      "grad_norm": 1.3992276191711426,
+      "learning_rate": 1.3570394025724828e-05,
+      "loss": 0.0439,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4400
+    },
+    {
+      "epoch": 0.4336401022825024,
+      "grad_norm": 0.27030619978904724,
+      "learning_rate": 1.3436016499667199e-05,
+      "loss": 0.0424,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4600
+    },
+    {
+      "epoch": 0.452494019773046,
+      "grad_norm": 0.1682862490415573,
+      "learning_rate": 1.3296333521884216e-05,
+      "loss": 0.0472,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 4800
+    },
+    {
+      "epoch": 0.47134793726358953,
+      "grad_norm": 0.28954288363456726,
+      "learning_rate": 1.315146993726058e-05,
+      "loss": 0.0411,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49020185475413314,
+      "grad_norm": 0.1974649876356125,
+      "learning_rate": 1.3001555220967904e-05,
+      "loss": 0.044,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5090557722446767,
+      "grad_norm": 0.6311449408531189,
+      "learning_rate": 1.2846723362743286e-05,
+      "loss": 0.0438,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5279096897352203,
+      "grad_norm": 0.5518035888671875,
+      "learning_rate": 1.2687112747132898e-05,
+      "loss": 0.0445,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5600
+    },
+    {
+      "epoch": 0.5467636072257639,
+      "grad_norm": 0.8561716079711914,
+      "learning_rate": 1.2522866029807593e-05,
+      "loss": 0.039,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 5800
+    },
+    {
+      "epoch": 0.5656175247163074,
+      "grad_norm": 0.1509927660226822,
+      "learning_rate": 1.2354130010061118e-05,
+      "loss": 0.0386,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6000
+    },
+    {
+      "epoch": 0.584471442206851,
+      "grad_norm": 0.27653419971466064,
+      "learning_rate": 1.2181055499604855e-05,
+      "loss": 0.0362,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6001201937240022,
+      "eval_loss": 0.08275004476308823,
+      "eval_runtime": 141.7236,
+      "eval_samples_per_second": 3.528,
+      "eval_steps_per_second": 1.764,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6366
+    },
+    {
+      "epoch": 0.6033253596973946,
+      "grad_norm": 1.3081331253051758,
+      "learning_rate": 1.2003797187776366e-05,
+      "loss": 0.0422,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6221792771879382,
+      "grad_norm": 0.1621595323085785,
+      "learning_rate": 1.1822513503282244e-05,
+      "loss": 0.0436,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6600
+    },
+    {
+      "epoch": 0.6410331946784817,
+      "grad_norm": 0.15179961919784546,
+      "learning_rate": 1.1637366472598779e-05,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 6800
+    },
+    {
+      "epoch": 0.6598871121690254,
+      "grad_norm": 0.6694086194038391,
+      "learning_rate": 1.1448521575157077e-05,
+      "loss": 0.0399,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7000
+    },
+    {
+      "epoch": 0.678741029659569,
+      "grad_norm": 0.21060042083263397,
+      "learning_rate": 1.1256147595441987e-05,
+      "loss": 0.0364,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7200
+    },
+    {
+      "epoch": 0.6975949471501125,
+      "grad_norm": 0.3258366584777832,
+      "learning_rate": 1.1060416472137082e-05,
+      "loss": 0.0382,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7400
+    },
+    {
+      "epoch": 0.7164488646406562,
+      "grad_norm": 1.0209743976593018,
+      "learning_rate": 1.0861503144450477e-05,
+      "loss": 0.0383,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7600
+    },
+    {
+      "epoch": 0.7353027821311997,
+      "grad_norm": 0.8924382925033569,
+      "learning_rate": 1.0659585395758893e-05,
+      "loss": 0.038,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 7800
+    },
+    {
+      "epoch": 0.7541566996217433,
+      "grad_norm": 0.10590477287769318,
+      "learning_rate": 1.045484369470965e-05,
+      "loss": 0.0368,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7730106171122869,
+      "grad_norm": 0.5611088871955872,
+      "learning_rate": 1.0247461033922658e-05,
+      "loss": 0.0323,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8200
+    },
+    {
+      "epoch": 0.7918645346028305,
+      "grad_norm": 0.11512701958417892,
+      "learning_rate": 1.0037622766436531e-05,
+      "loss": 0.0355,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8400
+    },
+    {
+      "epoch": 0.8001602582986697,
+      "eval_loss": 0.07625631988048553,
+      "eval_runtime": 141.3418,
+      "eval_samples_per_second": 3.538,
+      "eval_steps_per_second": 1.769,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8488
+    },
+    {
+      "epoch": 0.810718452093374,
+      "grad_norm": 0.2973927855491638,
+      "learning_rate": 9.825516440045032e-06,
+      "loss": 0.0375,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8600
+    },
+    {
+      "epoch": 0.8295723695839176,
+      "grad_norm": 0.9429569244384766,
+      "learning_rate": 9.61133162967192e-06,
+      "loss": 0.0359,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 8800
+    },
+    {
+      "epoch": 0.8484262870744612,
+      "grad_norm": 0.8306987881660461,
+      "learning_rate": 9.395259767933962e-06,
+      "loss": 0.0376,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8672802045650048,
+      "grad_norm": 0.801001250743866,
+      "learning_rate": 9.177493974043633e-06,
+      "loss": 0.0378,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9200
+    },
+    {
+      "epoch": 0.8861341220555483,
+      "grad_norm": 0.6952243447303772,
+      "learning_rate": 8.958228881204364e-06,
+      "loss": 0.037,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9400
+    },
+    {
+      "epoch": 0.904988039546092,
+      "grad_norm": 0.20955415070056915,
+      "learning_rate": 8.737660462652611e-06,
+      "loss": 0.034,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9600
+    },
+    {
+      "epoch": 0.9238419570366355,
+      "grad_norm": 0.2434842586517334,
+      "learning_rate": 8.515985856502264e-06,
+      "loss": 0.0328,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 9800
+    },
+    {
+      "epoch": 0.9426958745271791,
+      "grad_norm": 0.5963915586471558,
+      "learning_rate": 8.293403189547904e-06,
+      "loss": 0.0337,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9615497920177227,
+      "grad_norm": 0.3114663064479828,
+      "learning_rate": 8.070111400184415e-06,
+      "loss": 0.0338,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10200
+    },
+    {
+      "epoch": 0.9804037095082663,
+      "grad_norm": 0.16056938469409943,
+      "learning_rate": 7.846310060601191e-06,
+      "loss": 0.0344,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10400
+    },
+    {
+      "epoch": 0.9992576269988098,
+      "grad_norm": 0.9842764139175415,
+      "learning_rate": 7.622199198409896e-06,
+      "loss": 0.0352,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10600
+    },
+    {
+      "epoch": 1.0001885391749055,
+      "eval_loss": 0.07321257889270782,
+      "eval_runtime": 142.2906,
+      "eval_samples_per_second": 3.514,
+      "eval_steps_per_second": 1.757,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10610
+    },
+    {
+      "epoch": 1.018099760790922,
+      "grad_norm": 0.11459363996982574,
+      "learning_rate": 7.397979117865168e-06,
+      "loss": 0.0304,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 10800
+    },
+    {
+      "epoch": 1.0369536782814655,
+      "grad_norm": 0.5405158996582031,
+      "learning_rate": 7.173850220838073e-06,
+      "loss": 0.0307,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11000
+    },
+    {
+      "epoch": 1.055807595772009,
+      "grad_norm": 0.22435125708580017,
+      "learning_rate": 6.950012827702292e-06,
+      "loss": 0.0339,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11200
+    },
+    {
+      "epoch": 1.0746615132625525,
+      "grad_norm": 0.33569714426994324,
+      "learning_rate": 6.726666998293187e-06,
+      "loss": 0.0346,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11400
+    },
+    {
+      "epoch": 1.093515430753096,
+      "grad_norm": 0.25280582904815674,
+      "learning_rate": 6.504012353099694e-06,
+      "loss": 0.0316,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11600
+    },
+    {
+      "epoch": 1.1123693482436399,
+      "grad_norm": 0.48694702982902527,
+      "learning_rate": 6.282247894848904e-06,
+      "loss": 0.0334,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 11800
+    },
+    {
+      "epoch": 1.1312232657341834,
+      "grad_norm": 0.13796062767505646,
+      "learning_rate": 6.061571830642791e-06,
+      "loss": 0.0301,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12000
+    },
+    {
+      "epoch": 1.150077183224727,
+      "grad_norm": 0.8943594694137573,
+      "learning_rate": 5.842181394806027e-06,
+      "loss": 0.0326,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12200
+    },
+    {
+      "epoch": 1.1689311007152705,
+      "grad_norm": 0.4626399874687195,
+      "learning_rate": 5.62427267260327e-06,
+      "loss": 0.0295,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12400
+    },
+    {
+      "epoch": 1.187785018205814,
+      "grad_norm": 0.2461213320493698,
+      "learning_rate": 5.408040424983424e-06,
+      "loss": 0.0336,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12600
+    },
+    {
+      "epoch": 1.2002286037495729,
+      "eval_loss": 0.06900843977928162,
+      "eval_runtime": 141.9347,
+      "eval_samples_per_second": 3.523,
+      "eval_steps_per_second": 1.761,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12732
+    },
+    {
+      "epoch": 1.2066389356963576,
+      "grad_norm": 0.12716135382652283,
+      "learning_rate": 5.193677914507549e-06,
+      "loss": 0.0305,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 12800
+    },
+    {
+      "epoch": 1.2254928531869012,
+      "grad_norm": 1.277233362197876,
+      "learning_rate": 4.981376732615981e-06,
+      "loss": 0.0283,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 13000
+    },
+    {
+      "epoch": 1.2443467706774447,
+      "grad_norm": 0.10106557607650757,
+      "learning_rate": 4.7713266283890736e-06,
+      "loss": 0.0303,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 13200
+    },
+    {
+      "epoch": 1.2632006881679885,
+      "grad_norm": 0.2563807964324951,
+      "learning_rate": 4.563715338954568e-06,
+      "loss": 0.0295,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 13400
+    },
+    {
+      "epoch": 1.282054605658532,
+      "grad_norm": 0.7019901871681213,
+      "learning_rate": 4.3587284216932126e-06,
+      "loss": 0.0281,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 13600
+    },
+    {
+      "epoch": 1.3009085231490756,
+      "grad_norm": 0.8459643721580505,
+      "learning_rate": 4.156549088392558e-06,
+      "loss": 0.0315,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 13800
+    },
+    {
+      "epoch": 1.3197624406396191,
+      "grad_norm": 0.5311944484710693,
+      "learning_rate": 3.957358041497206e-06,
+      "loss": 0.0312,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14000
+    },
+    {
+      "epoch": 1.3386163581301627,
+      "grad_norm": 1.6611747741699219,
+      "learning_rate": 3.761333312601832e-06,
+      "loss": 0.0316,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14200
+    },
+    {
+      "epoch": 1.3574702756207064,
+      "grad_norm": 0.11192276328802109,
+      "learning_rate": 3.5686501033313256e-06,
+      "loss": 0.0327,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14400
+    },
+    {
+      "epoch": 1.37632419311125,
+      "grad_norm": 0.24348680675029755,
+      "learning_rate": 3.3794806287503048e-06,
+      "loss": 0.0331,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14600
+    },
+    {
+      "epoch": 1.3951781106017935,
+      "grad_norm": 0.19753499329090118,
+      "learning_rate": 3.1939939634419272e-06,
+      "loss": 0.0294,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14800
+    },
+    {
+      "epoch": 1.4002686683242402,
+      "eval_loss": 0.06857609003782272,
+      "eval_runtime": 142.0516,
+      "eval_samples_per_second": 3.52,
+      "eval_steps_per_second": 1.76,
+      "memory/device_mem_reserved(gib)": 79.87,
+      "memory/max_mem_active(gib)": 74.39,
+      "memory/max_mem_allocated(gib)": 74.39,
+      "step": 14854
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 21216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2122,
+  "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": 5.616934910183866e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}