Prune redundant merged weights and intermediate checkpoints

finetune/checkpoints/checkpoint-192/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# 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 0.19.1

finetune/checkpoints/checkpoint-192/adapter_config.json

@@ -1,53 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "o_proj",
-    "v_proj",
-    "out_proj",
-    "in_proj_qkv",
-    "in_proj_z",
-    "in_proj_b",
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "in_proj_a"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

finetune/checkpoints/checkpoint-192/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e07e0b5a0d2334b84ef4a982b94e1c2ef612da46da07cfe4930289e2855e5741
-size 86624424

finetune/checkpoints/checkpoint-192/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- 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' }}
-    {%- else %}
-        {{- '<think>\n' }}
-    {%- endif %}
-{%- endif %}

finetune/checkpoints/checkpoint-192/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1524a0b0fe341db800227e4b99364b7b34f4716e82f57b5f64bb72453ed6f30
-size 173539507

finetune/checkpoints/checkpoint-192/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7867f112d09bb82ff1c3b176d45ad04fc116373ec5e870377e2c4ed1ad92f934
-size 14645

finetune/checkpoints/checkpoint-192/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa84f260a89ac768c794df2a0bc4940cdffb529c8e321e51dfbdb2e00433d23c
-size 1465

finetune/checkpoints/checkpoint-192/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

finetune/checkpoints/checkpoint-192/tokenizer_config.json

@@ -1,32 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

finetune/checkpoints/checkpoint-192/trainer_state.json

@@ -1,224 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "eval_steps": 500,
-  "global_step": 192,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 1.5058588825166226,
-      "epoch": 0.10512483574244415,
-      "grad_norm": 1.796875,
-      "learning_rate": 0.00019375000000000002,
-      "loss": 1.7537630081176758,
-      "mean_token_accuracy": 0.695327178388834,
-      "num_tokens": 3808.0,
-      "step": 10
-    },
-    {
-      "entropy": 1.316319726407528,
-      "epoch": 0.2102496714848883,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00018680555555555556,
-      "loss": 1.4752570152282716,
-      "mean_token_accuracy": 0.7272207736968994,
-      "num_tokens": 7522.0,
-      "step": 20
-    },
-    {
-      "entropy": 1.3150447681546211,
-      "epoch": 0.31537450722733246,
-      "grad_norm": 1.3984375,
-      "learning_rate": 0.00017986111111111113,
-      "loss": 1.404660415649414,
-      "mean_token_accuracy": 0.7220224224030971,
-      "num_tokens": 11407.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.225712712854147,
-      "epoch": 0.4204993429697766,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.00017291666666666668,
-      "loss": 1.3144322395324708,
-      "mean_token_accuracy": 0.7446377977728844,
-      "num_tokens": 15194.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.3306574214249849,
-      "epoch": 0.5256241787122208,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00016597222222222225,
-      "loss": 1.442171287536621,
-      "mean_token_accuracy": 0.7188469670712948,
-      "num_tokens": 19221.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.2213972710072993,
-      "epoch": 0.6307490144546649,
-      "grad_norm": 1.25,
-      "learning_rate": 0.00015902777777777776,
-      "loss": 1.3555883407592773,
-      "mean_token_accuracy": 0.7323203787207604,
-      "num_tokens": 23135.0,
-      "step": 60
-    },
-    {
-      "entropy": 1.236185147613287,
-      "epoch": 0.735873850197109,
-      "grad_norm": 1.2890625,
-      "learning_rate": 0.00015208333333333333,
-      "loss": 1.3239954948425292,
-      "mean_token_accuracy": 0.7413535274565219,
-      "num_tokens": 26938.0,
-      "step": 70
-    },
-    {
-      "entropy": 1.1433476515114307,
-      "epoch": 0.8409986859395532,
-      "grad_norm": 1.1875,
-      "learning_rate": 0.00014513888888888888,
-      "loss": 1.2469322204589843,
-      "mean_token_accuracy": 0.7549085400998592,
-      "num_tokens": 30527.0,
-      "step": 80
-    },
-    {
-      "entropy": 1.283092799782753,
-      "epoch": 0.9461235216819974,
-      "grad_norm": 1.21875,
-      "learning_rate": 0.00013819444444444445,
-      "loss": 1.4147074699401856,
-      "mean_token_accuracy": 0.7189013145864009,
-      "num_tokens": 34654.0,
-      "step": 90
-    },
-    {
-      "entropy": 1.2251756056530836,
-      "epoch": 1.0420499342969776,
-      "grad_norm": 1.0078125,
-      "learning_rate": 0.00013125000000000002,
-      "loss": 1.1694912910461426,
-      "mean_token_accuracy": 0.75513191827356,
-      "num_tokens": 38292.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9808842208236456,
-      "epoch": 1.1471747700394217,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00012430555555555556,
-      "loss": 0.9646660804748535,
-      "mean_token_accuracy": 0.7965455286204814,
-      "num_tokens": 42119.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.895855213701725,
-      "epoch": 1.2522996057818658,
-      "grad_norm": 1.625,
-      "learning_rate": 0.00011736111111111112,
-      "loss": 0.9326272964477539,
-      "mean_token_accuracy": 0.7989173181354999,
-      "num_tokens": 46121.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.8705711856484413,
-      "epoch": 1.3574244415243102,
-      "grad_norm": 1.8125,
-      "learning_rate": 0.00011041666666666668,
-      "loss": 0.8961386680603027,
-      "mean_token_accuracy": 0.8044699378311634,
-      "num_tokens": 50090.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.8594769395887851,
-      "epoch": 1.4625492772667543,
-      "grad_norm": 1.6171875,
-      "learning_rate": 0.00010347222222222223,
-      "loss": 0.8508189201354981,
-      "mean_token_accuracy": 0.8186739608645439,
-      "num_tokens": 53919.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.8401138111948967,
-      "epoch": 1.5676741130091985,
-      "grad_norm": 1.7578125,
-      "learning_rate": 9.652777777777779e-05,
-      "loss": 0.8900316238403321,
-      "mean_token_accuracy": 0.8109646178781986,
-      "num_tokens": 57865.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8799884164705872,
-      "epoch": 1.6727989487516426,
-      "grad_norm": 1.9765625,
-      "learning_rate": 8.958333333333335e-05,
-      "loss": 0.8930209159851075,
-      "mean_token_accuracy": 0.8081811979413033,
-      "num_tokens": 61745.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.8651461038738489,
-      "epoch": 1.7779237844940867,
-      "grad_norm": 1.625,
-      "learning_rate": 8.263888888888889e-05,
-      "loss": 0.870454978942871,
-      "mean_token_accuracy": 0.8074543043971062,
-      "num_tokens": 65643.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.8021717140451073,
-      "epoch": 1.8830486202365309,
-      "grad_norm": 2.109375,
-      "learning_rate": 7.569444444444445e-05,
-      "loss": 0.8372815132141114,
-      "mean_token_accuracy": 0.8185677900910378,
-      "num_tokens": 69253.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.8461722563952208,
-      "epoch": 1.988173455978975,
-      "grad_norm": 1.9609375,
-      "learning_rate": 6.875e-05,
-      "loss": 0.8477604866027832,
-      "mean_token_accuracy": 0.821676817536354,
-      "num_tokens": 73086.0,
-      "step": 190
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 288,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3517439958097920.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

finetune/checkpoints/checkpoint-192/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777

finetune/checkpoints/checkpoint-288/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# 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 0.19.1

finetune/checkpoints/checkpoint-288/adapter_config.json

@@ -1,53 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "o_proj",
-    "v_proj",
-    "out_proj",
-    "in_proj_qkv",
-    "in_proj_z",
-    "in_proj_b",
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "in_proj_a"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

finetune/checkpoints/checkpoint-288/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7d88cb1cdd1237abdb5933ccf30096da0861d6ac0874c743f5de09abd5293c06
-size 86624424

finetune/checkpoints/checkpoint-288/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- 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' }}
-    {%- else %}
-        {{- '<think>\n' }}
-    {%- endif %}
-{%- endif %}

finetune/checkpoints/checkpoint-288/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:189edcd603f7bbddb01c5754b74224f95ea9def898c5f111090bc5b61d82ebe1
-size 173539507

finetune/checkpoints/checkpoint-288/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1de14d45bf40451ecad8cc71ddb5f3014594537a7f4f59d093126e25120b911
-size 14645

finetune/checkpoints/checkpoint-288/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db65c34a575612e43bcfbbcdee111aa92a8a1578c29689cbfb7e5bcc00cf526d
-size 1465

finetune/checkpoints/checkpoint-288/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

finetune/checkpoints/checkpoint-288/tokenizer_config.json

@@ -1,32 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

finetune/checkpoints/checkpoint-288/trainer_state.json

@@ -1,314 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 288,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 1.5058588825166226,
-      "epoch": 0.10512483574244415,
-      "grad_norm": 1.796875,
-      "learning_rate": 0.00019375000000000002,
-      "loss": 1.7537630081176758,
-      "mean_token_accuracy": 0.695327178388834,
-      "num_tokens": 3808.0,
-      "step": 10
-    },
-    {
-      "entropy": 1.316319726407528,
-      "epoch": 0.2102496714848883,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00018680555555555556,
-      "loss": 1.4752570152282716,
-      "mean_token_accuracy": 0.7272207736968994,
-      "num_tokens": 7522.0,
-      "step": 20
-    },
-    {
-      "entropy": 1.3150447681546211,
-      "epoch": 0.31537450722733246,
-      "grad_norm": 1.3984375,
-      "learning_rate": 0.00017986111111111113,
-      "loss": 1.404660415649414,
-      "mean_token_accuracy": 0.7220224224030971,
-      "num_tokens": 11407.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.225712712854147,
-      "epoch": 0.4204993429697766,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.00017291666666666668,
-      "loss": 1.3144322395324708,
-      "mean_token_accuracy": 0.7446377977728844,
-      "num_tokens": 15194.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.3306574214249849,
-      "epoch": 0.5256241787122208,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00016597222222222225,
-      "loss": 1.442171287536621,
-      "mean_token_accuracy": 0.7188469670712948,
-      "num_tokens": 19221.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.2213972710072993,
-      "epoch": 0.6307490144546649,
-      "grad_norm": 1.25,
-      "learning_rate": 0.00015902777777777776,
-      "loss": 1.3555883407592773,
-      "mean_token_accuracy": 0.7323203787207604,
-      "num_tokens": 23135.0,
-      "step": 60
-    },
-    {
-      "entropy": 1.236185147613287,
-      "epoch": 0.735873850197109,
-      "grad_norm": 1.2890625,
-      "learning_rate": 0.00015208333333333333,
-      "loss": 1.3239954948425292,
-      "mean_token_accuracy": 0.7413535274565219,
-      "num_tokens": 26938.0,
-      "step": 70
-    },
-    {
-      "entropy": 1.1433476515114307,
-      "epoch": 0.8409986859395532,
-      "grad_norm": 1.1875,
-      "learning_rate": 0.00014513888888888888,
-      "loss": 1.2469322204589843,
-      "mean_token_accuracy": 0.7549085400998592,
-      "num_tokens": 30527.0,
-      "step": 80
-    },
-    {
-      "entropy": 1.283092799782753,
-      "epoch": 0.9461235216819974,
-      "grad_norm": 1.21875,
-      "learning_rate": 0.00013819444444444445,
-      "loss": 1.4147074699401856,
-      "mean_token_accuracy": 0.7189013145864009,
-      "num_tokens": 34654.0,
-      "step": 90
-    },
-    {
-      "entropy": 1.2251756056530836,
-      "epoch": 1.0420499342969776,
-      "grad_norm": 1.0078125,
-      "learning_rate": 0.00013125000000000002,
-      "loss": 1.1694912910461426,
-      "mean_token_accuracy": 0.75513191827356,
-      "num_tokens": 38292.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9808842208236456,
-      "epoch": 1.1471747700394217,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00012430555555555556,
-      "loss": 0.9646660804748535,
-      "mean_token_accuracy": 0.7965455286204814,
-      "num_tokens": 42119.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.895855213701725,
-      "epoch": 1.2522996057818658,
-      "grad_norm": 1.625,
-      "learning_rate": 0.00011736111111111112,
-      "loss": 0.9326272964477539,
-      "mean_token_accuracy": 0.7989173181354999,
-      "num_tokens": 46121.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.8705711856484413,
-      "epoch": 1.3574244415243102,
-      "grad_norm": 1.8125,
-      "learning_rate": 0.00011041666666666668,
-      "loss": 0.8961386680603027,
-      "mean_token_accuracy": 0.8044699378311634,
-      "num_tokens": 50090.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.8594769395887851,
-      "epoch": 1.4625492772667543,
-      "grad_norm": 1.6171875,
-      "learning_rate": 0.00010347222222222223,
-      "loss": 0.8508189201354981,
-      "mean_token_accuracy": 0.8186739608645439,
-      "num_tokens": 53919.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.8401138111948967,
-      "epoch": 1.5676741130091985,
-      "grad_norm": 1.7578125,
-      "learning_rate": 9.652777777777779e-05,
-      "loss": 0.8900316238403321,
-      "mean_token_accuracy": 0.8109646178781986,
-      "num_tokens": 57865.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8799884164705872,
-      "epoch": 1.6727989487516426,
-      "grad_norm": 1.9765625,
-      "learning_rate": 8.958333333333335e-05,
-      "loss": 0.8930209159851075,
-      "mean_token_accuracy": 0.8081811979413033,
-      "num_tokens": 61745.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.8651461038738489,
-      "epoch": 1.7779237844940867,
-      "grad_norm": 1.625,
-      "learning_rate": 8.263888888888889e-05,
-      "loss": 0.870454978942871,
-      "mean_token_accuracy": 0.8074543043971062,
-      "num_tokens": 65643.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.8021717140451073,
-      "epoch": 1.8830486202365309,
-      "grad_norm": 2.109375,
-      "learning_rate": 7.569444444444445e-05,
-      "loss": 0.8372815132141114,
-      "mean_token_accuracy": 0.8185677900910378,
-      "num_tokens": 69253.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.8461722563952208,
-      "epoch": 1.988173455978975,
-      "grad_norm": 1.9609375,
-      "learning_rate": 6.875e-05,
-      "loss": 0.8477604866027832,
-      "mean_token_accuracy": 0.821676817536354,
-      "num_tokens": 73086.0,
-      "step": 190
-    },
-    {
-      "entropy": 0.6834010038882086,
-      "epoch": 2.084099868593955,
-      "grad_norm": 1.640625,
-      "learning_rate": 6.180555555555556e-05,
-      "loss": 0.5151080131530762,
-      "mean_token_accuracy": 0.8863431843992782,
-      "num_tokens": 76490.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.5644423710182309,
-      "epoch": 2.1892247043363993,
-      "grad_norm": 2.4375,
-      "learning_rate": 5.486111111111112e-05,
-      "loss": 0.523468017578125,
-      "mean_token_accuracy": 0.8785075314342976,
-      "num_tokens": 80430.0,
-      "step": 210
-    },
-    {
-      "entropy": 0.5120254509150982,
-      "epoch": 2.2943495400788434,
-      "grad_norm": 1.6796875,
-      "learning_rate": 4.791666666666667e-05,
-      "loss": 0.43973474502563475,
-      "mean_token_accuracy": 0.900006202608347,
-      "num_tokens": 84261.0,
-      "step": 220
-    },
-    {
-      "entropy": 0.6139889739453792,
-      "epoch": 2.3994743758212875,
-      "grad_norm": 2.03125,
-      "learning_rate": 4.0972222222222225e-05,
-      "loss": 0.49155173301696775,
-      "mean_token_accuracy": 0.8851348020136356,
-      "num_tokens": 88367.0,
-      "step": 230
-    },
-    {
-      "entropy": 0.548260616324842,
-      "epoch": 2.5045992115637317,
-      "grad_norm": 2.109375,
-      "learning_rate": 3.402777777777778e-05,
-      "loss": 0.45668373107910154,
-      "mean_token_accuracy": 0.8958614394068718,
-      "num_tokens": 92116.0,
-      "step": 240
-    },
-    {
-      "entropy": 0.524461186490953,
-      "epoch": 2.6097240473061762,
-      "grad_norm": 2.25,
-      "learning_rate": 2.7083333333333332e-05,
-      "loss": 0.4536457538604736,
-      "mean_token_accuracy": 0.8967262022197247,
-      "num_tokens": 96008.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.5277848264202476,
-      "epoch": 2.7148488830486204,
-      "grad_norm": 2.625,
-      "learning_rate": 2.013888888888889e-05,
-      "loss": 0.4624601364135742,
-      "mean_token_accuracy": 0.8950574725866318,
-      "num_tokens": 99859.0,
-      "step": 260
-    },
-    {
-      "entropy": 0.5569793220609427,
-      "epoch": 2.8199737187910645,
-      "grad_norm": 2.078125,
-      "learning_rate": 1.3194444444444446e-05,
-      "loss": 0.4798299312591553,
-      "mean_token_accuracy": 0.8920079082250595,
-      "num_tokens": 103783.0,
-      "step": 270
-    },
-    {
-      "entropy": 0.5342973008751869,
-      "epoch": 2.9250985545335086,
-      "grad_norm": 1.96875,
-      "learning_rate": 6.25e-06,
-      "loss": 0.44893660545349123,
-      "mean_token_accuracy": 0.8974449247121811,
-      "num_tokens": 107478.0,
-      "step": 280
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 288,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 5276159937146880.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

finetune/checkpoints/checkpoint-288/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777

finetune/checkpoints/checkpoint-96/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-9B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-9B
-- lora
-- sft
-- transformers
-- trl
----
-
-# 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 0.19.1

finetune/checkpoints/checkpoint-96/adapter_config.json

@@ -1,53 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "o_proj",
-    "v_proj",
-    "out_proj",
-    "in_proj_qkv",
-    "in_proj_z",
-    "in_proj_b",
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "in_proj_a"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

finetune/checkpoints/checkpoint-96/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f03e779a43975dcdd86cdb41004659692e771ca7880c0c8404b714c658c6af0e
-size 86624424

finetune/checkpoints/checkpoint-96/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- 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' }}
-    {%- else %}
-        {{- '<think>\n' }}
-    {%- endif %}
-{%- endif %}

finetune/checkpoints/checkpoint-96/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d20760b2006a548a0307ad7cd2792b4ac6b093ec76f9b640f29a2d9d8b4faffd
-size 173539507

finetune/checkpoints/checkpoint-96/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2fc05a5af5e55dd07491a9c13f98e77a3b89980687c94a380940cea72c438db1
-size 14645

finetune/checkpoints/checkpoint-96/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:26175424728d92cc8b818d24add62cebe17e0a76e269611dcabb93101acd685b
-size 1465

finetune/checkpoints/checkpoint-96/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

finetune/checkpoints/checkpoint-96/tokenizer_config.json

@@ -1,32 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

finetune/checkpoints/checkpoint-96/trainer_state.json

@@ -1,124 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 96,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 1.5058588825166226,
-      "epoch": 0.10512483574244415,
-      "grad_norm": 1.796875,
-      "learning_rate": 0.00019375000000000002,
-      "loss": 1.7537630081176758,
-      "mean_token_accuracy": 0.695327178388834,
-      "num_tokens": 3808.0,
-      "step": 10
-    },
-    {
-      "entropy": 1.316319726407528,
-      "epoch": 0.2102496714848883,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00018680555555555556,
-      "loss": 1.4752570152282716,
-      "mean_token_accuracy": 0.7272207736968994,
-      "num_tokens": 7522.0,
-      "step": 20
-    },
-    {
-      "entropy": 1.3150447681546211,
-      "epoch": 0.31537450722733246,
-      "grad_norm": 1.3984375,
-      "learning_rate": 0.00017986111111111113,
-      "loss": 1.404660415649414,
-      "mean_token_accuracy": 0.7220224224030971,
-      "num_tokens": 11407.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.225712712854147,
-      "epoch": 0.4204993429697766,
-      "grad_norm": 1.140625,
-      "learning_rate": 0.00017291666666666668,
-      "loss": 1.3144322395324708,
-      "mean_token_accuracy": 0.7446377977728844,
-      "num_tokens": 15194.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.3306574214249849,
-      "epoch": 0.5256241787122208,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00016597222222222225,
-      "loss": 1.442171287536621,
-      "mean_token_accuracy": 0.7188469670712948,
-      "num_tokens": 19221.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.2213972710072993,
-      "epoch": 0.6307490144546649,
-      "grad_norm": 1.25,
-      "learning_rate": 0.00015902777777777776,
-      "loss": 1.3555883407592773,
-      "mean_token_accuracy": 0.7323203787207604,
-      "num_tokens": 23135.0,
-      "step": 60
-    },
-    {
-      "entropy": 1.236185147613287,
-      "epoch": 0.735873850197109,
-      "grad_norm": 1.2890625,
-      "learning_rate": 0.00015208333333333333,
-      "loss": 1.3239954948425292,
-      "mean_token_accuracy": 0.7413535274565219,
-      "num_tokens": 26938.0,
-      "step": 70
-    },
-    {
-      "entropy": 1.1433476515114307,
-      "epoch": 0.8409986859395532,
-      "grad_norm": 1.1875,
-      "learning_rate": 0.00014513888888888888,
-      "loss": 1.2469322204589843,
-      "mean_token_accuracy": 0.7549085400998592,
-      "num_tokens": 30527.0,
-      "step": 80
-    },
-    {
-      "entropy": 1.283092799782753,
-      "epoch": 0.9461235216819974,
-      "grad_norm": 1.21875,
-      "learning_rate": 0.00013819444444444445,
-      "loss": 1.4147074699401856,
-      "mean_token_accuracy": 0.7189013145864009,
-      "num_tokens": 34654.0,
-      "step": 90
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 288,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1758719979048960.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

finetune/checkpoints/checkpoint-96/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80c77319107d515ff120e1a03ba8bd1c939446a417590eaef8b1b3111fab5416
-size 5777

finetune/style_checkpoint/checkpoint-132/README.md

@@ -1,209 +0,0 @@
----
-base_model: C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-- lora
-- sft
-- transformers
-- trl
----
-
-# 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 0.19.1

finetune/style_checkpoint/checkpoint-132/adapter_config.json

@@ -1,53 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "C:\\Users\\Ifmanzhang\\Documents\\GitHub\\RepE\\merged_model",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "in_proj_a",
-    "up_proj",
-    "in_proj_z",
-    "in_proj_qkv",
-    "down_proj",
-    "o_proj",
-    "gate_proj",
-    "out_proj",
-    "in_proj_b",
-    "v_proj",
-    "q_proj",
-    "k_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

finetune/style_checkpoint/checkpoint-132/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e39771f0f53ca759114efb681a1ed2041a68e81133e1fd79ca47e9260feefa8b
-size 86624424

finetune/style_checkpoint/checkpoint-132/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- 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' }}
-    {%- else %}
-        {{- '<think>\n' }}
-    {%- endif %}
-{%- endif %}

finetune/style_checkpoint/checkpoint-132/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8a8fc7ac39ead78fd5404103fd69eb5af92b12e8f12deb71bd1216c4839b55a
-size 173539507

finetune/style_checkpoint/checkpoint-132/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55458227fb883b7277781facf9f9a8d32c2c5a33e955febaec1eaadf202c3636
-size 14645

finetune/style_checkpoint/checkpoint-132/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9fad155de9dcd6412030b755a69f4c04b30a98ba8375d5d62b5bea51173f91a5
-size 1465

finetune/style_checkpoint/checkpoint-132/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

finetune/style_checkpoint/checkpoint-132/tokenizer_config.json

@@ -1,32 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": true,
-  "local_files_only": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

finetune/style_checkpoint/checkpoint-132/trainer_state.json

@@ -1,164 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 132,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 1.30109671279788,
-      "epoch": 0.22857142857142856,
-      "grad_norm": 1.2109375,
-      "learning_rate": 0.00018636363636363636,
-      "loss": 1.69281063079834,
-      "mean_token_accuracy": 0.7338378168642521,
-      "num_tokens": 2779.0,
-      "step": 10
-    },
-    {
-      "entropy": 1.2120113119482994,
-      "epoch": 0.45714285714285713,
-      "grad_norm": 1.3359375,
-      "learning_rate": 0.00017121212121212122,
-      "loss": 1.1274803161621094,
-      "mean_token_accuracy": 0.770654023438692,
-      "num_tokens": 5529.0,
-      "step": 20
-    },
-    {
-      "entropy": 0.9645026199519634,
-      "epoch": 0.6857142857142857,
-      "grad_norm": 1.3203125,
-      "learning_rate": 0.00015606060606060607,
-      "loss": 1.0083338737487793,
-      "mean_token_accuracy": 0.7900982514023781,
-      "num_tokens": 8264.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.001315427571535,
-      "epoch": 0.9142857142857143,
-      "grad_norm": 1.2109375,
-      "learning_rate": 0.00014090909090909093,
-      "loss": 0.9876208305358887,
-      "mean_token_accuracy": 0.7899081066250802,
-      "num_tokens": 11028.0,
-      "step": 40
-    },
-    {
-      "entropy": 0.9025501891588553,
-      "epoch": 1.1371428571428572,
-      "grad_norm": 0.97265625,
-      "learning_rate": 0.00012575757575757575,
-      "loss": 0.7734798908233642,
-      "mean_token_accuracy": 0.8246896488544269,
-      "num_tokens": 13730.0,
-      "step": 50
-    },
-    {
-      "entropy": 0.7055704202502966,
-      "epoch": 1.3657142857142857,
-      "grad_norm": 1.453125,
-      "learning_rate": 0.00011060606060606061,
-      "loss": 0.6433767318725586,
-      "mean_token_accuracy": 0.849166390299797,
-      "num_tokens": 16506.0,
-      "step": 60
-    },
-    {
-      "entropy": 0.6749185953289271,
-      "epoch": 1.5942857142857143,
-      "grad_norm": 1.5078125,
-      "learning_rate": 9.545454545454546e-05,
-      "loss": 0.6674872398376465,
-      "mean_token_accuracy": 0.8353129491209984,
-      "num_tokens": 19267.0,
-      "step": 70
-    },
-    {
-      "entropy": 0.665529253333807,
-      "epoch": 1.822857142857143,
-      "grad_norm": 1.71875,
-      "learning_rate": 8.03030303030303e-05,
-      "loss": 0.6229500770568848,
-      "mean_token_accuracy": 0.8385165937244892,
-      "num_tokens": 22011.0,
-      "step": 80
-    },
-    {
-      "entropy": 0.6535426924626032,
-      "epoch": 2.045714285714286,
-      "grad_norm": 1.0546875,
-      "learning_rate": 6.515151515151516e-05,
-      "loss": 0.5569591522216797,
-      "mean_token_accuracy": 0.8594398276928144,
-      "num_tokens": 24693.0,
-      "step": 90
-    },
-    {
-      "entropy": 0.5231270018965006,
-      "epoch": 2.2742857142857145,
-      "grad_norm": 1.6796875,
-      "learning_rate": 5e-05,
-      "loss": 0.36677672863006594,
-      "mean_token_accuracy": 0.9020668059587479,
-      "num_tokens": 27463.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.4256359253078699,
-      "epoch": 2.5028571428571427,
-      "grad_norm": 2.046875,
-      "learning_rate": 3.484848484848485e-05,
-      "loss": 0.35885071754455566,
-      "mean_token_accuracy": 0.8996045172214509,
-      "num_tokens": 30201.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.404218702763319,
-      "epoch": 2.7314285714285713,
-      "grad_norm": 1.734375,
-      "learning_rate": 1.9696969696969697e-05,
-      "loss": 0.35897390842437743,
-      "mean_token_accuracy": 0.9063410043716431,
-      "num_tokens": 32955.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.3963111503049731,
-      "epoch": 2.96,
-      "grad_norm": 2.0625,
-      "learning_rate": 4.5454545454545455e-06,
-      "loss": 0.3470670938491821,
-      "mean_token_accuracy": 0.9018755808472634,
-      "num_tokens": 35726.0,
-      "step": 130
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 132,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1734301292636160.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

finetune/style_checkpoint/checkpoint-132/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b18b6c96a47cb78062355feafacc9baa8fde5cfda40273867df5486f7917195d
-size 5713

finetune/style_checkpoint/checkpoint-44/README.md

@@ -1,209 +0,0 @@
----
-base_model: C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:C:\Users\Ifmanzhang\Documents\GitHub\RepE\merged_model
-- lora
-- sft
-- transformers
-- trl
----
-
-# 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 0.19.1

finetune/style_checkpoint/checkpoint-44/adapter_config.json

@@ -1,53 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "C:\\Users\\Ifmanzhang\\Documents\\GitHub\\RepE\\merged_model",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "in_proj_a",
-    "up_proj",
-    "in_proj_z",
-    "in_proj_qkv",
-    "down_proj",
-    "o_proj",
-    "gate_proj",
-    "out_proj",
-    "in_proj_b",
-    "v_proj",
-    "q_proj",
-    "k_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

finetune/style_checkpoint/checkpoint-44/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fbf525e8ecdc16097d8dacc4631ed12a9eb4a2927e12e67a7722ae59ecfa9cc6
-size 86624424

finetune/style_checkpoint/checkpoint-44/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- 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' }}
-    {%- else %}
-        {{- '<think>\n' }}
-    {%- endif %}
-{%- endif %}

finetune/style_checkpoint/checkpoint-44/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e0c393eb649466fef43e60bd28f3fa487141df8e06fbbac4c1ef81fdb3041786
-size 173539507

finetune/style_checkpoint/checkpoint-44/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39fe84eb65ca8488e36557b0ca39dd485c262ba68865254ec0e97dc4ec1802dc
-size 14645