Upload folder using huggingface_hub

.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/Qwen3-1.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-1.7B
+- lora
+- opsd
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_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 sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

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_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bb00ead350f17de05bae3cc3394c47ce791ae10c59f18708e3e9e1a3ae9161
+size 104599269

global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4111c8fb050c97a526028eb69a10b86fb537e1d5fd76df496e2ab9ace292f119
+size 104599269

global_step200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9fca77abfbfc3c4bd056c5d07de46e077d23aa28f8a18cdc1719b29b6a5783
+size 104599269

global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1225e7ef83b504640b3d01b61b1b56a5badbe6c07bafb982cf2f9cde231aa9e3
+size 104599269

global_step200/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004691d884f14884c195d4f6d8416cd4bc893d1b8367fab879fa15ea1ab41908
+size 104599269

global_step200/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7f6fe275f8f1e8a1d835694108e12322e05b62d5121bbf4eef5187fef54316
+size 104599269

global_step200/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35257440fa3b490dcbca12010271860143b56cfd2a304c63ccfde7a06b9a69d
+size 104599269

global_step200/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addc59d2253f7669f1a70cc512ca1bd91ee96b8efcbd9058bec218086673dc7c
+size 104599269

global_step200/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d415ef927909c2efebe2a47461c4f5e5803cbf6f3de91416396cbefc086cbfef
+size 392830

global_step200/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ab251ceb4e462ba2fa1fd3dda6036ec0310d4c3ee52b5222f2eabb5b519d03
+size 392766

global_step200/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd66bbcf808f6226f853e429fd193adba5c21033edf094753bbd8bf07ef01d93
+size 392766

global_step200/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba7ec61836041e9ad4d999472ca2240dd5da539ed3fd1ba3230a8682d164015
+size 392766

global_step200/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0f6f0682dce1024d1628d91845d83dd100dbb7d86cdac224b1b94baf5e16f4
+size 392766

global_step200/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b176968ff485d47f2f3da8080a12303fc617996352d7ea6cdae1e908083e46
+size 392766

global_step200/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66949a173433c6d83bbecb1d6da97b6270ca8baa0a1e94a2adbb5cd52ab292c6
+size 392766

global_step200/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e201785bcac337918c54105e33f9c1af57574e1c0d1af6253d1669f9731ac18
+size 392766

latest

@@ -0,0 +1 @@
+global_step200

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26502f665f295d69866914762b94b92c656d538f8d64cd5c803ef466055808d0
+size 16325

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f5be6a26021db96c71f6489077cb1b7778e597f43c70eae8ef42991a70e14a
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b645b07859e85917fb3731ff58a3252868da984d0ec2ccdb326ed04ba88998
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccbb206d935484946d527e54f48ea698bb92fa0c39f3c0a11c5a2ee87f80c8b
+size 16325

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8650cb40faca148117a69a55273b5434ec7ecd48522c29c0a8996803f2a0c1
+size 16325

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7562990765a9ae987a310ae5051796a6dbb6304d021491010c02271ce3e63cf
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ddcf055b73e9c8de9eea11b45e490a296641274a416851208fa3570127e205
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62459e16f369491f9dd6096eee7a2b6a993fb88239cabd8ac238065b4583048
+size 16325

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec4422ea46ec56ba3a044ecabff3eeab77d668793e86e52458a938df870eeb1
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f9787d552fa20c3bfa90dadaabccfeef9343fc4fee19e3cfca00cb2586fbf0
+size 11422922

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1631986944104447,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016319869441044472,
+      "grad_norm": 0.058299943804740906,
+      "learning_rate": 0.00019983686786296902,
+      "loss": 0.023,
+      "on_policy_loss": 0.023,
+      "step": 2
+    },
+    {
+      "epoch": 0.0032639738882088943,
+      "grad_norm": 0.04990854486823082,
+      "learning_rate": 0.00019951060358890704,
+      "loss": 0.0236,
+      "on_policy_loss": 0.0236,
+      "step": 4
+    },
+    {
+      "epoch": 0.004895960832313341,
+      "grad_norm": 0.03872146084904671,
+      "learning_rate": 0.00019918433931484503,
+      "loss": 0.025,
+      "on_policy_loss": 0.025,
+      "step": 6
+    },
+    {
+      "epoch": 0.006527947776417789,
+      "grad_norm": 0.0333283431828022,
+      "learning_rate": 0.00019885807504078305,
+      "loss": 0.0245,
+      "on_policy_loss": 0.0245,
+      "step": 8
+    },
+    {
+      "epoch": 0.008159934720522236,
+      "grad_norm": 0.0277633685618639,
+      "learning_rate": 0.00019853181076672104,
+      "loss": 0.0229,
+      "on_policy_loss": 0.0229,
+      "step": 10
+    },
+    {
+      "epoch": 0.009791921664626682,
+      "grad_norm": 0.02402353286743164,
+      "learning_rate": 0.00019820554649265906,
+      "loss": 0.0219,
+      "on_policy_loss": 0.0219,
+      "step": 12
+    },
+    {
+      "epoch": 0.01142390860873113,
+      "grad_norm": 0.026979146525263786,
+      "learning_rate": 0.00019787928221859708,
+      "loss": 0.0228,
+      "on_policy_loss": 0.0228,
+      "step": 14
+    },
+    {
+      "epoch": 0.013055895552835577,
+      "grad_norm": 0.01897270232439041,
+      "learning_rate": 0.0001975530179445351,
+      "loss": 0.0224,
+      "on_policy_loss": 0.0224,
+      "step": 16
+    },
+    {
+      "epoch": 0.014687882496940025,
+      "grad_norm": 0.020191779360175133,
+      "learning_rate": 0.0001972267536704731,
+      "loss": 0.0223,
+      "on_policy_loss": 0.0223,
+      "step": 18
+    },
+    {
+      "epoch": 0.016319869441044473,
+      "grad_norm": 0.019388101994991302,
+      "learning_rate": 0.0001969004893964111,
+      "loss": 0.0207,
+      "on_policy_loss": 0.0207,
+      "step": 20
+    },
+    {
+      "epoch": 0.01795185638514892,
+      "grad_norm": 0.01775970496237278,
+      "learning_rate": 0.0001965742251223491,
+      "loss": 0.0225,
+      "on_policy_loss": 0.0225,
+      "step": 22
+    },
+    {
+      "epoch": 0.019583843329253364,
+      "grad_norm": 0.0191648006439209,
+      "learning_rate": 0.00019624796084828712,
+      "loss": 0.0227,
+      "on_policy_loss": 0.0227,
+      "step": 24
+    },
+    {
+      "epoch": 0.021215830273357814,
+      "grad_norm": 0.017626851797103882,
+      "learning_rate": 0.0001959216965742251,
+      "loss": 0.0212,
+      "on_policy_loss": 0.0212,
+      "step": 26
+    },
+    {
+      "epoch": 0.02284781721746226,
+      "grad_norm": 0.013785107992589474,
+      "learning_rate": 0.00019559543230016316,
+      "loss": 0.0196,
+      "on_policy_loss": 0.0196,
+      "step": 28
+    },
+    {
+      "epoch": 0.02447980416156671,
+      "grad_norm": 0.016143064945936203,
+      "learning_rate": 0.00019526916802610115,
+      "loss": 0.0227,
+      "on_policy_loss": 0.0227,
+      "step": 30
+    },
+    {
+      "epoch": 0.026111791105671155,
+      "grad_norm": 0.012568962760269642,
+      "learning_rate": 0.00019494290375203917,
+      "loss": 0.022,
+      "on_policy_loss": 0.022,
+      "step": 32
+    },
+    {
+      "epoch": 0.0277437780497756,
+      "grad_norm": 0.018003186210989952,
+      "learning_rate": 0.00019461663947797716,
+      "loss": 0.0231,
+      "on_policy_loss": 0.0231,
+      "step": 34
+    },
+    {
+      "epoch": 0.02937576499388005,
+      "grad_norm": 0.024327414110302925,
+      "learning_rate": 0.00019429037520391518,
+      "loss": 0.0274,
+      "on_policy_loss": 0.0274,
+      "step": 36
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.021259307861328125,
+      "learning_rate": 0.0001939641109298532,
+      "loss": 0.0268,
+      "on_policy_loss": 0.0268,
+      "step": 38
+    },
+    {
+      "epoch": 0.032639738882088945,
+      "grad_norm": 0.02104460634291172,
+      "learning_rate": 0.00019363784665579121,
+      "loss": 0.0265,
+      "on_policy_loss": 0.0265,
+      "step": 40
+    },
+    {
+      "epoch": 0.03427172582619339,
+      "grad_norm": 0.024325763806700706,
+      "learning_rate": 0.0001933115823817292,
+      "loss": 0.0312,
+      "on_policy_loss": 0.0312,
+      "step": 42
+    },
+    {
+      "epoch": 0.03590371277029784,
+      "grad_norm": 0.04464346170425415,
+      "learning_rate": 0.00019298531810766722,
+      "loss": 0.051,
+      "on_policy_loss": 0.051,
+      "step": 44
+    },
+    {
+      "epoch": 0.037535699714402286,
+      "grad_norm": 0.06272145360708237,
+      "learning_rate": 0.00019265905383360522,
+      "loss": 0.0672,
+      "on_policy_loss": NaN,
+      "step": 46
+    },
+    {
+      "epoch": 0.03916768665850673,
+      "grad_norm": 0.08038327842950821,
+      "learning_rate": 0.00019233278955954324,
+      "loss": 0.0802,
+      "on_policy_loss": NaN,
+      "step": 48
+    },
+    {
+      "epoch": 0.04079967360261118,
+      "grad_norm": 0.04722515493631363,
+      "learning_rate": 0.00019200652528548125,
+      "loss": 0.0521,
+      "on_policy_loss": NaN,
+      "step": 50
+    },
+    {
+      "epoch": 0.04243166054671563,
+      "grad_norm": 0.04557369276881218,
+      "learning_rate": 0.00019168026101141925,
+      "loss": 0.0507,
+      "on_policy_loss": 0.0507,
+      "step": 52
+    },
+    {
+      "epoch": 0.044063647490820076,
+      "grad_norm": 0.042579613626003265,
+      "learning_rate": 0.00019135399673735726,
+      "loss": 0.0501,
+      "on_policy_loss": 0.0501,
+      "step": 54
+    },
+    {
+      "epoch": 0.04569563443492452,
+      "grad_norm": 0.04415519908070564,
+      "learning_rate": 0.00019102773246329528,
+      "loss": 0.0531,
+      "on_policy_loss": 0.0531,
+      "step": 56
+    },
+    {
+      "epoch": 0.04732762137902897,
+      "grad_norm": 0.04244513437151909,
+      "learning_rate": 0.0001907014681892333,
+      "loss": 0.0537,
+      "on_policy_loss": 0.0537,
+      "step": 58
+    },
+    {
+      "epoch": 0.04895960832313342,
+      "grad_norm": 0.04231644049286842,
+      "learning_rate": 0.0001903752039151713,
+      "loss": 0.046,
+      "on_policy_loss": 0.046,
+      "step": 60
+    },
+    {
+      "epoch": 0.05059159526723786,
+      "grad_norm": 0.03901742026209831,
+      "learning_rate": 0.0001900489396411093,
+      "loss": 0.0481,
+      "on_policy_loss": 0.0481,
+      "step": 62
+    },
+    {
+      "epoch": 0.05222358221134231,
+      "grad_norm": 0.048259295523166656,
+      "learning_rate": 0.0001897226753670473,
+      "loss": 0.0578,
+      "on_policy_loss": 0.0578,
+      "step": 64
+    },
+    {
+      "epoch": 0.05385556915544676,
+      "grad_norm": 0.04231755807995796,
+      "learning_rate": 0.00018939641109298535,
+      "loss": 0.0531,
+      "on_policy_loss": 0.0531,
+      "step": 66
+    },
+    {
+      "epoch": 0.0554875560995512,
+      "grad_norm": 0.0582573339343071,
+      "learning_rate": 0.00018907014681892334,
+      "loss": 0.0723,
+      "on_policy_loss": 0.0723,
+      "step": 68
+    },
+    {
+      "epoch": 0.05711954304365565,
+      "grad_norm": 0.03717726469039917,
+      "learning_rate": 0.00018874388254486136,
+      "loss": 0.0515,
+      "on_policy_loss": 0.0515,
+      "step": 70
+    },
+    {
+      "epoch": 0.0587515299877601,
+      "grad_norm": 0.039125215262174606,
+      "learning_rate": 0.00018841761827079935,
+      "loss": 0.0444,
+      "on_policy_loss": 0.0444,
+      "step": 72
+    },
+    {
+      "epoch": 0.06038351693186454,
+      "grad_norm": 0.04124997928738594,
+      "learning_rate": 0.00018809135399673737,
+      "loss": 0.051,
+      "on_policy_loss": 0.051,
+      "step": 74
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 0.045977186411619186,
+      "learning_rate": 0.00018776508972267536,
+      "loss": 0.0545,
+      "on_policy_loss": 0.0545,
+      "step": 76
+    },
+    {
+      "epoch": 0.06364749082007344,
+      "grad_norm": 0.04227733239531517,
+      "learning_rate": 0.00018743882544861338,
+      "loss": 0.0513,
+      "on_policy_loss": 0.0513,
+      "step": 78
+    },
+    {
+      "epoch": 0.06527947776417789,
+      "grad_norm": 0.03969841077923775,
+      "learning_rate": 0.0001871125611745514,
+      "loss": 0.0487,
+      "on_policy_loss": 0.0487,
+      "step": 80
+    },
+    {
+      "epoch": 0.06691146470828234,
+      "grad_norm": 0.03437201678752899,
+      "learning_rate": 0.00018678629690048942,
+      "loss": 0.0519,
+      "on_policy_loss": 0.0519,
+      "step": 82
+    },
+    {
+      "epoch": 0.06854345165238677,
+      "grad_norm": 0.05064399167895317,
+      "learning_rate": 0.0001864600326264274,
+      "loss": 0.0532,
+      "on_policy_loss": 0.0532,
+      "step": 84
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.05297597497701645,
+      "learning_rate": 0.00018613376835236543,
+      "loss": 0.055,
+      "on_policy_loss": 0.055,
+      "step": 86
+    },
+    {
+      "epoch": 0.07180742554059567,
+      "grad_norm": 0.05343659967184067,
+      "learning_rate": 0.00018580750407830342,
+      "loss": 0.0482,
+      "on_policy_loss": 0.0482,
+      "step": 88
+    },
+    {
+      "epoch": 0.07343941248470012,
+      "grad_norm": 0.03496076166629791,
+      "learning_rate": 0.00018548123980424144,
+      "loss": 0.05,
+      "on_policy_loss": 0.05,
+      "step": 90
+    },
+    {
+      "epoch": 0.07507139942880457,
+      "grad_norm": 0.04398609325289726,
+      "learning_rate": 0.00018515497553017946,
+      "loss": 0.0484,
+      "on_policy_loss": 0.0484,
+      "step": 92
+    },
+    {
+      "epoch": 0.07670338637290902,
+      "grad_norm": 0.0509929358959198,
+      "learning_rate": 0.00018482871125611748,
+      "loss": 0.0532,
+      "on_policy_loss": 0.0532,
+      "step": 94
+    },
+    {
+      "epoch": 0.07833537331701346,
+      "grad_norm": 0.04439166933298111,
+      "learning_rate": 0.00018450244698205547,
+      "loss": 0.0517,
+      "on_policy_loss": 0.0517,
+      "step": 96
+    },
+    {
+      "epoch": 0.0799673602611179,
+      "grad_norm": 0.03571309149265289,
+      "learning_rate": 0.0001841761827079935,
+      "loss": 0.0509,
+      "on_policy_loss": 0.0509,
+      "step": 98
+    },
+    {
+      "epoch": 0.08159934720522236,
+      "grad_norm": 0.03795301914215088,
+      "learning_rate": 0.00018384991843393148,
+      "loss": 0.0513,
+      "on_policy_loss": 0.0513,
+      "step": 100
+    },
+    {
+      "epoch": 0.0832313341493268,
+      "grad_norm": 0.04838141053915024,
+      "learning_rate": 0.0001835236541598695,
+      "loss": 0.0508,
+      "on_policy_loss": 0.0508,
+      "step": 102
+    },
+    {
+      "epoch": 0.08486332109343125,
+      "grad_norm": 0.041026629507541656,
+      "learning_rate": 0.0001831973898858075,
+      "loss": 0.0481,
+      "on_policy_loss": 0.0481,
+      "step": 104
+    },
+    {
+      "epoch": 0.0864953080375357,
+      "grad_norm": 0.03260858356952667,
+      "learning_rate": 0.00018287112561174554,
+      "loss": 0.0436,
+      "on_policy_loss": 0.0436,
+      "step": 106
+    },
+    {
+      "epoch": 0.08812729498164015,
+      "grad_norm": 0.03473200276494026,
+      "learning_rate": 0.00018254486133768353,
+      "loss": 0.0436,
+      "on_policy_loss": 0.0436,
+      "step": 108
+    },
+    {
+      "epoch": 0.08975928192574459,
+      "grad_norm": 0.03827611356973648,
+      "learning_rate": 0.00018221859706362155,
+      "loss": 0.0472,
+      "on_policy_loss": 0.0472,
+      "step": 110
+    },
+    {
+      "epoch": 0.09139126886984904,
+      "grad_norm": 0.05292026698589325,
+      "learning_rate": 0.00018189233278955954,
+      "loss": 0.0525,
+      "on_policy_loss": 0.0525,
+      "step": 112
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 0.050034940242767334,
+      "learning_rate": 0.00018156606851549756,
+      "loss": 0.0508,
+      "on_policy_loss": 0.0508,
+      "step": 114
+    },
+    {
+      "epoch": 0.09465524275805794,
+      "grad_norm": 0.04287738725543022,
+      "learning_rate": 0.00018123980424143555,
+      "loss": 0.0496,
+      "on_policy_loss": 0.0496,
+      "step": 116
+    },
+    {
+      "epoch": 0.09628722970216239,
+      "grad_norm": 0.0442175529897213,
+      "learning_rate": 0.0001809135399673736,
+      "loss": 0.0484,
+      "on_policy_loss": 0.0484,
+      "step": 118
+    },
+    {
+      "epoch": 0.09791921664626684,
+      "grad_norm": 0.04303177818655968,
+      "learning_rate": 0.0001805872756933116,
+      "loss": 0.053,
+      "on_policy_loss": 0.053,
+      "step": 120
+    },
+    {
+      "epoch": 0.09955120359037127,
+      "grad_norm": 0.046395499259233475,
+      "learning_rate": 0.0001802610114192496,
+      "loss": 0.057,
+      "on_policy_loss": 0.057,
+      "step": 122
+    },
+    {
+      "epoch": 0.10118319053447572,
+      "grad_norm": 0.04695666581392288,
+      "learning_rate": 0.0001799347471451876,
+      "loss": 0.0546,
+      "on_policy_loss": 0.0546,
+      "step": 124
+    },
+    {
+      "epoch": 0.10281517747858017,
+      "grad_norm": 0.04866120219230652,
+      "learning_rate": 0.00017960848287112562,
+      "loss": 0.0548,
+      "on_policy_loss": 0.0548,
+      "step": 126
+    },
+    {
+      "epoch": 0.10444716442268462,
+      "grad_norm": 0.039415277540683746,
+      "learning_rate": 0.0001792822185970636,
+      "loss": 0.0557,
+      "on_policy_loss": NaN,
+      "step": 128
+    },
+    {
+      "epoch": 0.10607915136678907,
+      "grad_norm": 0.04781395196914673,
+      "learning_rate": 0.00017895595432300163,
+      "loss": 0.0517,
+      "on_policy_loss": 0.0517,
+      "step": 130
+    },
+    {
+      "epoch": 0.10771113831089352,
+      "grad_norm": 0.0389864556491375,
+      "learning_rate": 0.00017862969004893965,
+      "loss": 0.0515,
+      "on_policy_loss": 0.0515,
+      "step": 132
+    },
+    {
+      "epoch": 0.10934312525499797,
+      "grad_norm": 0.04027765989303589,
+      "learning_rate": 0.00017830342577487767,
+      "loss": 0.0492,
+      "on_policy_loss": 0.0492,
+      "step": 134
+    },
+    {
+      "epoch": 0.1109751121991024,
+      "grad_norm": 0.04564642161130905,
+      "learning_rate": 0.00017797716150081566,
+      "loss": 0.055,
+      "on_policy_loss": 0.055,
+      "step": 136
+    },
+    {
+      "epoch": 0.11260709914320685,
+      "grad_norm": 0.04376218840479851,
+      "learning_rate": 0.00017765089722675368,
+      "loss": 0.0495,
+      "on_policy_loss": 0.0495,
+      "step": 138
+    },
+    {
+      "epoch": 0.1142390860873113,
+      "grad_norm": 0.0441172830760479,
+      "learning_rate": 0.0001773246329526917,
+      "loss": 0.0515,
+      "on_policy_loss": 0.0515,
+      "step": 140
+    },
+    {
+      "epoch": 0.11587107303141575,
+      "grad_norm": 0.03999102860689163,
+      "learning_rate": 0.0001769983686786297,
+      "loss": 0.0508,
+      "on_policy_loss": 0.0508,
+      "step": 142
+    },
+    {
+      "epoch": 0.1175030599755202,
+      "grad_norm": 0.040877122431993484,
+      "learning_rate": 0.0001766721044045677,
+      "loss": 0.0486,
+      "on_policy_loss": 0.0486,
+      "step": 144
+    },
+    {
+      "epoch": 0.11913504691962465,
+      "grad_norm": 0.034374285489320755,
+      "learning_rate": 0.00017634584013050572,
+      "loss": 0.0486,
+      "on_policy_loss": 0.0486,
+      "step": 146
+    },
+    {
+      "epoch": 0.12076703386372908,
+      "grad_norm": 0.045045480132102966,
+      "learning_rate": 0.00017601957585644374,
+      "loss": 0.0482,
+      "on_policy_loss": 0.0482,
+      "step": 148
+    },
+    {
+      "epoch": 0.12239902080783353,
+      "grad_norm": 0.04038718342781067,
+      "learning_rate": 0.00017569331158238174,
+      "loss": 0.0673,
+      "on_policy_loss": 0.0673,
+      "step": 150
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 0.04703664407134056,
+      "learning_rate": 0.00017536704730831975,
+      "loss": 0.0505,
+      "on_policy_loss": 0.0505,
+      "step": 152
+    },
+    {
+      "epoch": 0.12566299469604242,
+      "grad_norm": 0.08692470192909241,
+      "learning_rate": 0.00017504078303425775,
+      "loss": 0.0646,
+      "on_policy_loss": 0.0646,
+      "step": 154
+    },
+    {
+      "epoch": 0.12729498164014688,
+      "grad_norm": 0.034957848489284515,
+      "learning_rate": 0.00017471451876019576,
+      "loss": 0.048,
+      "on_policy_loss": 0.048,
+      "step": 156
+    },
+    {
+      "epoch": 0.12892696858425132,
+      "grad_norm": 0.032591577619314194,
+      "learning_rate": 0.00017438825448613378,
+      "loss": 0.0469,
+      "on_policy_loss": 0.0469,
+      "step": 158
+    },
+    {
+      "epoch": 0.13055895552835578,
+      "grad_norm": 0.03767777606844902,
+      "learning_rate": 0.0001740619902120718,
+      "loss": 0.043,
+      "on_policy_loss": 0.043,
+      "step": 160
+    },
+    {
+      "epoch": 0.13219094247246022,
+      "grad_norm": 0.03873617574572563,
+      "learning_rate": 0.0001737357259380098,
+      "loss": 0.0474,
+      "on_policy_loss": 0.0474,
+      "step": 162
+    },
+    {
+      "epoch": 0.13382292941656468,
+      "grad_norm": 0.03672102466225624,
+      "learning_rate": 0.0001734094616639478,
+      "loss": 0.0514,
+      "on_policy_loss": 0.0514,
+      "step": 164
+    },
+    {
+      "epoch": 0.13545491636066911,
+      "grad_norm": 0.04233694076538086,
+      "learning_rate": 0.0001730831973898858,
+      "loss": 0.0477,
+      "on_policy_loss": 0.0477,
+      "step": 166
+    },
+    {
+      "epoch": 0.13708690330477355,
+      "grad_norm": 0.0341520719230175,
+      "learning_rate": 0.00017275693311582382,
+      "loss": 0.0468,
+      "on_policy_loss": 0.0468,
+      "step": 168
+    },
+    {
+      "epoch": 0.138718890248878,
+      "grad_norm": 0.031185219064354897,
+      "learning_rate": 0.00017243066884176184,
+      "loss": 0.0439,
+      "on_policy_loss": 0.0439,
+      "step": 170
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.041588034480810165,
+      "learning_rate": 0.00017210440456769986,
+      "loss": 0.044,
+      "on_policy_loss": 0.044,
+      "step": 172
+    },
+    {
+      "epoch": 0.1419828641370869,
+      "grad_norm": 0.03446938097476959,
+      "learning_rate": 0.00017177814029363785,
+      "loss": 0.0491,
+      "on_policy_loss": 0.0491,
+      "step": 174
+    },
+    {
+      "epoch": 0.14361485108119135,
+      "grad_norm": 0.03288084641098976,
+      "learning_rate": 0.00017145187601957587,
+      "loss": 0.0457,
+      "on_policy_loss": 0.0457,
+      "step": 176
+    },
+    {
+      "epoch": 0.1452468380252958,
+      "grad_norm": 0.03164874389767647,
+      "learning_rate": 0.00017112561174551386,
+      "loss": 0.047,
+      "on_policy_loss": 0.047,
+      "step": 178
+    },
+    {
+      "epoch": 0.14687882496940025,
+      "grad_norm": 0.03469070792198181,
+      "learning_rate": 0.00017079934747145188,
+      "loss": 0.0481,
+      "on_policy_loss": 0.0481,
+      "step": 180
+    },
+    {
+      "epoch": 0.14851081191350468,
+      "grad_norm": 0.03517889231443405,
+      "learning_rate": 0.0001704730831973899,
+      "loss": 0.0506,
+      "on_policy_loss": 0.0506,
+      "step": 182
+    },
+    {
+      "epoch": 0.15014279885760914,
+      "grad_norm": 0.03757636621594429,
+      "learning_rate": 0.00017014681892332792,
+      "loss": 0.0506,
+      "on_policy_loss": 0.0506,
+      "step": 184
+    },
+    {
+      "epoch": 0.15177478580171358,
+      "grad_norm": 0.034249041229486465,
+      "learning_rate": 0.0001698205546492659,
+      "loss": 0.0431,
+      "on_policy_loss": 0.0431,
+      "step": 186
+    },
+    {
+      "epoch": 0.15340677274581804,
+      "grad_norm": 0.03459709882736206,
+      "learning_rate": 0.00016949429037520393,
+      "loss": 0.0462,
+      "on_policy_loss": 0.0462,
+      "step": 188
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 0.031404901295900345,
+      "learning_rate": 0.00016916802610114192,
+      "loss": 0.0447,
+      "on_policy_loss": 0.0447,
+      "step": 190
+    },
+    {
+      "epoch": 0.15667074663402691,
+      "grad_norm": 0.056188613176345825,
+      "learning_rate": 0.00016884176182707994,
+      "loss": 0.0499,
+      "on_policy_loss": 0.0499,
+      "step": 192
+    },
+    {
+      "epoch": 0.15830273357813138,
+      "grad_norm": 0.03952009230852127,
+      "learning_rate": 0.00016851549755301793,
+      "loss": 0.0449,
+      "on_policy_loss": 0.0449,
+      "step": 194
+    },
+    {
+      "epoch": 0.1599347205222358,
+      "grad_norm": 0.034737277776002884,
+      "learning_rate": 0.00016818923327895598,
+      "loss": 0.0519,
+      "on_policy_loss": 0.0519,
+      "step": 196
+    },
+    {
+      "epoch": 0.16156670746634028,
+      "grad_norm": 0.03392937034368515,
+      "learning_rate": 0.00016786296900489397,
+      "loss": 0.0485,
+      "on_policy_loss": 0.0485,
+      "step": 198
+    },
+    {
+      "epoch": 0.1631986944104447,
+      "grad_norm": 0.03504011780023575,
+      "learning_rate": 0.000167536704730832,
+      "loss": 0.0453,
+      "on_policy_loss": 0.0453,
+      "step": 200
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1226,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f3c18dffec1eed0be38bfe50fd525e0b1505a6486d8ce7421abc692604e6d3
+size 9425

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info("Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info("Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)