Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-235B-A22B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-235B-A22B
+- 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 0.17.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-235B-A22B",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545575f3dd7469706e67d9c478ffe109dd3d261158bdb511a223a7fada30741d
+size 101748240

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

global_step67/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e2b31628d12bd4c77e6a6b8967836b3c7a318f383c395dde5a9fd843ac995b
+size 25419768

global_step67/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433e879002cce029eef0195dcf4797c9288977842891e6d49924f02f2e06f8ab
+size 25419768

global_step67/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee67d0aca4f4fcd9c28684470ff9fa21b1a6820c81828a0db9e79798b80e1a59
+size 25419768

global_step67/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02f73f2d49a43e515d29adc48a63c4d850c4b6b9db7cfef5b35082f93fea0ad
+size 25419760

global_step67/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd5543548cc77f1ba536074b89c0a67c208f4d08e2f8a26af792239c7351d5c
+size 25419768

global_step67/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e8a469ec437aac7fc53d69eeb02a2681606554f148336e4afbc69eef7355da
+size 25419760

global_step67/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5e691bc3596ab9c80160007213ee327718d344f1f2e0316bd057cc970f8d72
+size 5483614

global_step67/zero_pp_rank_14_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61498525bb3d9bf3ff361a10ddb537b5984dbb518e67b88156c09d675ff6c9cb
+size 5484370

global_step67/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc47790e6716ee0b7adc232c2fd41c61ad70d419bd7e82420a07f01d9ed4cc5
+size 5483614

global_step67/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0ff5c076942603a77986393a9f05591294e64b13cddab9d60900623770d452
+size 5483614

global_step67/zero_pp_rank_9_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b03ded6f35db13a0a377f13bf977055c56762436d8e5da9073b2f521d38253c
+size 5483614

latest

@@ -0,0 +1 @@
+global_step67

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00227d4b3541241375f4286fd135406e94605d92023b3a84e1a8341affbbab0
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de7df7ac5b7212b07e498dea3ebd0d4a66bbeb1648899c547f4b340929da9bb
+size 15984

rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adeaa53995263e2e7e9d19d5ae3054130cc1ef1a8577ba997081a7ab2ab59f8a
+size 15997

rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe5169a1edfc9f706707a3c77a0406cbfb358d4461e221716ee4a6ad102eb17
+size 15997

rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e74ab2064c6bceb2051eb69e649438f5515f759292cbafeb937ec8ce0a00246
+size 15997

rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ea27806f4bbe87ba79d61b5bb540c4329f644aea31f6d811dc7b22fbc02ac2
+size 15997

rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24839d1c3942d463a9f376e7a4084c7016b7dba9fed864f6b6af9f55c0956d1f
+size 15997

rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3653fde37bab4a393c345ecad3847d8fb53e6d5d117511622d6a351604e2d06
+size 15997

rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e648c5415b554cb17d58cd6a78e1c14beb6778484881981d048e4d25cc7114e
+size 15997

rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a46a5c58a4f5b83767e1ed2354b399e898352550a969fbb42743096e88253c
+size 15997

rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f2409c80869b7e46634500963e49b861039dbc9fb3aa3dffa97a6e0b256d0c
+size 15997

rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97440effacae4d21d86fb613d8f77fd1339256ea1b5b46a0d56622234a80d6c1
+size 15997

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0677b4fef408463fb09218ea8cea1107cbf1e70adfbd4e2f58b7bb1610665af3
+size 15984

rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b0b69e2ebf61c316f391e03308ff7d9de064f3b0393e4800ca4b3549c729d0
+size 15997

rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df19236eeff2aa775b4cafb101e05eaf5fc6dd0e67e8befbe7cefec4cc8b3df0
+size 15997

rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44dde243bdd1822a9a98f3d69642e3fd3f402599ce2e2e0d8c0f464bcd354683
+size 15997

rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e264f292846674095e5c6bbad16bf6547659526676563ef1b5964647a65b73
+size 15997

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e5427d60619e696ff96aee6907c74aaf864319a0517947ba52f93579b072c4
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb68846c1e2747f95acf9383e0b0925b789229ce547a9f171de1ce0b4f00fc0
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bf47eb9045504680c089007da1d736bf05cc8edf4173cf44bd31b986ccc41c
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73840bbee74027a006880b00a91a1f43c3d24c63b535855a694bf14a172414fc
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff149bdac9d25ec343343f02768219494f3b2ea13f7f29f4580f610b49f0df12
+size 15984

rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55517e03f3ac63977d4fe0d8d1373862101c7fcb513434678dd1dc836491291
+size 15984

rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fe85f62c510a7e5e09fdf524d82559065ba2541957b6aea1a6863f2dc73d0f
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb6fc5d223aa0d19cd3f3b98ece3bbd1eb866a7415ad0339b7f64672f64b8d5
+size 1064

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": "<|im_end|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,578 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.08367291093673593,
+      "learning_rate": 0.0,
+      "loss": 0.5482,
+      "num_tokens": 6288444.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.07875395721115776,
+      "learning_rate": 4e-05,
+      "loss": 0.5655,
+      "num_tokens": 12577300.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.07913921006018489,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.5542,
+      "num_tokens": 18860690.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.08049450634750233,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.559,
+      "num_tokens": 6288873.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.07849054673300468,
+      "learning_rate": 4e-05,
+      "loss": 0.5752,
+      "num_tokens": 12566970.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.08551302230509794,
+      "learning_rate": 3.9992791128129796e-05,
+      "loss": 0.5581,
+      "num_tokens": 18850402.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.08689858561178568,
+      "learning_rate": 3.99711702867229e-05,
+      "loss": 0.557,
+      "num_tokens": 25107301.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.08889582972451578,
+      "learning_rate": 3.993515479376548e-05,
+      "loss": 0.5469,
+      "num_tokens": 31386429.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.08695144533471684,
+      "learning_rate": 3.988477349715466e-05,
+      "loss": 0.5543,
+      "num_tokens": 37667761.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.08862002835267728,
+      "learning_rate": 3.982006675159175e-05,
+      "loss": 0.5712,
+      "num_tokens": 43955337.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.0858590512367662,
+      "learning_rate": 3.9741086386258753e-05,
+      "loss": 0.5349,
+      "num_tokens": 50223401.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.08169881690710488,
+      "learning_rate": 3.964789566330388e-05,
+      "loss": 0.5367,
+      "num_tokens": 56512071.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.07849820932974692,
+      "learning_rate": 3.95405692271695e-05,
+      "loss": 0.5307,
+      "num_tokens": 62766485.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.07377884515816503,
+      "learning_rate": 3.9419193044802986e-05,
+      "loss": 0.5196,
+      "num_tokens": 69055179.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.06953990227189195,
+      "learning_rate": 3.928386433679841e-05,
+      "loss": 0.5595,
+      "num_tokens": 75311700.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.06533799864475098,
+      "learning_rate": 3.9134691499524276e-05,
+      "loss": 0.4955,
+      "num_tokens": 81587667.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.061111534293718496,
+      "learning_rate": 3.897179401829952e-05,
+      "loss": 0.5072,
+      "num_tokens": 87869515.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.05929839410326827,
+      "learning_rate": 3.879530237168747e-05,
+      "loss": 0.5303,
+      "num_tokens": 94116999.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.05478787891939966,
+      "learning_rate": 3.860535792698444e-05,
+      "loss": 0.5053,
+      "num_tokens": 100391937.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.04990273451939609,
+      "learning_rate": 3.840211282698645e-05,
+      "loss": 0.4987,
+      "num_tokens": 106680748.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.04677345013018686,
+      "learning_rate": 3.8185729868125066e-05,
+      "loss": 0.5096,
+      "num_tokens": 112932721.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.04489959314534258,
+      "learning_rate": 3.795638237006978e-05,
+      "loss": 0.5066,
+      "num_tokens": 119215789.0,
+      "step": 22
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.06079575616027249,
+      "learning_rate": 3.771425403690139e-05,
+      "loss": 0.9893,
+      "num_tokens": 128649291.0,
+      "step": 23
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.03767597298138805,
+      "learning_rate": 3.745953880996767e-05,
+      "loss": 0.5002,
+      "num_tokens": 134928421.0,
+      "step": 24
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.0366409043186678,
+      "learning_rate": 3.7192440712539114e-05,
+      "loss": 0.478,
+      "num_tokens": 141217341.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.0318749564229291,
+      "learning_rate": 3.691317368638916e-05,
+      "loss": 0.5036,
+      "num_tokens": 147499869.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.034360217233696456,
+      "learning_rate": 3.662196142042995e-05,
+      "loss": 0.4991,
+      "num_tokens": 153769582.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.03134143776479919,
+      "learning_rate": 3.631903717154062e-05,
+      "loss": 0.4798,
+      "num_tokens": 160024266.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.031998515282158586,
+      "learning_rate": 3.6004643577731915e-05,
+      "loss": 0.4679,
+      "num_tokens": 166312888.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.029175435908410763,
+      "learning_rate": 3.567903246379655e-05,
+      "loss": 0.4652,
+      "num_tokens": 172600133.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.03137915793658181,
+      "learning_rate": 3.534246463960121e-05,
+      "loss": 0.4641,
+      "num_tokens": 178862530.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.03266162455994872,
+      "learning_rate": 3.4995209691181444e-05,
+      "loss": 0.4614,
+      "num_tokens": 185126521.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 0.031536401022176745,
+      "learning_rate": 3.463754576480721e-05,
+      "loss": 0.491,
+      "num_tokens": 191405477.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.03322613517139192,
+      "learning_rate": 3.426975934419159e-05,
+      "loss": 0.4714,
+      "num_tokens": 197694450.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.028175276385557585,
+      "learning_rate": 3.389214502102147e-05,
+      "loss": 0.4642,
+      "num_tokens": 203983039.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.029363581811266946,
+      "learning_rate": 3.350500525899373e-05,
+      "loss": 0.4872,
+      "num_tokens": 210267862.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.02494373239035565,
+      "learning_rate": 3.3108650151546195e-05,
+      "loss": 0.4667,
+      "num_tokens": 216556573.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.025337853364644107,
+      "learning_rate": 3.270339717347717e-05,
+      "loss": 0.4776,
+      "num_tokens": 222815179.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.024143271117441824,
+      "learning_rate": 3.2289570926652616e-05,
+      "loss": 0.4963,
+      "num_tokens": 229102184.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.025897104779336474,
+      "learning_rate": 3.186750288000478e-05,
+      "loss": 0.4891,
+      "num_tokens": 235352777.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 0.019836426513023662,
+      "learning_rate": 3.143753110403018e-05,
+      "loss": 0.4679,
+      "num_tokens": 241621188.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.018058641489749182,
+      "learning_rate": 3.1e-05,
+      "loss": 0.4818,
+      "num_tokens": 247909812.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.017737013602277963,
+      "learning_rate": 3.0555260024099625e-05,
+      "loss": 0.4836,
+      "num_tokens": 254198763.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.019059220139637262,
+      "learning_rate": 3.010366740671812e-05,
+      "loss": 0.474,
+      "num_tokens": 260436604.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.024821571793453297,
+      "learning_rate": 2.9645583867112866e-05,
+      "loss": 0.4617,
+      "num_tokens": 260829699.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 0.015860761380693023,
+      "learning_rate": 2.9181376323677496e-05,
+      "loss": 0.4603,
+      "num_tokens": 267112284.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.017471418851994432,
+      "learning_rate": 2.8711416600045558e-05,
+      "loss": 0.4858,
+      "num_tokens": 273399657.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.015021160976165208,
+      "learning_rate": 2.823608112726503e-05,
+      "loss": 0.4577,
+      "num_tokens": 279679785.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.01505554637021585,
+      "learning_rate": 2.775575064228242e-05,
+      "loss": 0.4531,
+      "num_tokens": 285935823.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.015286374426380292,
+      "learning_rate": 2.727080988297791e-05,
+      "loss": 0.4711,
+      "num_tokens": 292220642.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.013968889295589787,
+      "learning_rate": 2.6781647279995777e-05,
+      "loss": 0.4583,
+      "num_tokens": 298509450.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 0.01449798856464623,
+      "learning_rate": 2.628865464561697e-05,
+      "loss": 0.4684,
+      "num_tokens": 304785151.0,
+      "step": 52
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.013264243459191116,
+      "learning_rate": 2.5792226859923072e-05,
+      "loss": 0.4578,
+      "num_tokens": 311033842.0,
+      "step": 53
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.01613974261694193,
+      "learning_rate": 2.5292761554502963e-05,
+      "loss": 0.477,
+      "num_tokens": 317291716.0,
+      "step": 54
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.01468678727122222,
+      "learning_rate": 2.4790658793955564e-05,
+      "loss": 0.4854,
+      "num_tokens": 323548033.0,
+      "step": 55
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 0.01405550906865906,
+      "learning_rate": 2.428632075544382e-05,
+      "loss": 0.4807,
+      "num_tokens": 329829707.0,
+      "step": 56
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.014455179653099892,
+      "learning_rate": 2.37801514065565e-05,
+      "loss": 0.4785,
+      "num_tokens": 336093930.0,
+      "step": 57
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 0.013370673781759669,
+      "learning_rate": 2.3272556181735904e-05,
+      "loss": 0.4646,
+      "num_tokens": 342344810.0,
+      "step": 58
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.015240904326297017,
+      "learning_rate": 2.2763941657530673e-05,
+      "loss": 0.4882,
+      "num_tokens": 348634067.0,
+      "step": 59
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.011132425786885326,
+      "learning_rate": 2.225471522693372e-05,
+      "loss": 0.4487,
+      "num_tokens": 354922898.0,
+      "step": 60
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.012595956269750347,
+      "learning_rate": 2.1745284773066286e-05,
+      "loss": 0.452,
+      "num_tokens": 361204032.0,
+      "step": 61
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 0.011531846013411475,
+      "learning_rate": 2.123605834246934e-05,
+      "loss": 0.4505,
+      "num_tokens": 367493005.0,
+      "step": 62
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.010737772612701217,
+      "learning_rate": 2.07274438182641e-05,
+      "loss": 0.4407,
+      "num_tokens": 373782071.0,
+      "step": 63
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.011159229323820324,
+      "learning_rate": 2.0219848593443508e-05,
+      "loss": 0.4489,
+      "num_tokens": 380050269.0,
+      "step": 64
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.011043764114324384,
+      "learning_rate": 1.9713679244556182e-05,
+      "loss": 0.4613,
+      "num_tokens": 386338880.0,
+      "step": 65
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.014011877037531699,
+      "learning_rate": 1.920934120604444e-05,
+      "loss": 0.4755,
+      "num_tokens": 392618850.0,
+      "step": 66
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 0.012565353494419326,
+      "learning_rate": 1.8707238445497043e-05,
+      "loss": 0.4798,
+      "num_tokens": 398906371.0,
+      "step": 67
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.012565353494419326,
+      "learning_rate": 1.8207773140076933e-05,
+      "loss": 0.4758,
+      "num_tokens": 399299425.0,
+      "step": 68
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 115,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.832757670726861e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafbb1ba6efd361aac6e6d7c0343516c8b4d5b96c19efaf5f30bb5dfd56abbed
+size 7480