Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct
+- llama-factory
+- lora
+- transformers
+metrics:
+- accuracy
+pipeline_tag: text-generation
+model-index:
+- name: rewrite_results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# rewrite_results
+
+This model is a fine-tuned version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) on the train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0616
+- Accuracy: 0.9850
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0004
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.085
+- num_epochs: 4.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.1481 | 2    | 0.2477          | 0.9611   |
+| 0.2441        | 0.2963 | 4    | 0.1997          | 0.9648   |
+| 0.2367        | 0.4444 | 6    | 0.1587          | 0.9688   |
+| 0.2367        | 0.5926 | 8    | 0.1476          | 0.9710   |
+| 0.1895        | 0.7407 | 10   | 0.1318          | 0.9732   |
+| 0.1361        | 0.8889 | 12   | 0.1172          | 0.9759   |
+| 0.1361        | 1.0    | 14   | 0.1053          | 0.9783   |
+| 0.18          | 1.1481 | 16   | 0.0985          | 0.9792   |
+| 0.1193        | 1.2963 | 18   | 0.0932          | 0.9798   |
+| 0.1193        | 1.4444 | 20   | 0.0875          | 0.9804   |
+| 0.0823        | 1.5926 | 22   | 0.0840          | 0.9806   |
+| 0.1175        | 1.7407 | 24   | 0.0778          | 0.9814   |
+| 0.1175        | 1.8889 | 26   | 0.0737          | 0.9827   |
+| 0.0898        | 2.0    | 28   | 0.0704          | 0.9836   |
+| 0.0948        | 2.1481 | 30   | 0.0689          | 0.9838   |
+| 0.0948        | 2.2963 | 32   | 0.0670          | 0.9841   |
+| 0.0739        | 2.4444 | 34   | 0.0653          | 0.9841   |
+| 0.0526        | 2.5926 | 36   | 0.0643          | 0.9845   |
+| 0.0526        | 2.7407 | 38   | 0.0634          | 0.9845   |
+| 0.0564        | 2.8889 | 40   | 0.0625          | 0.9847   |
+| 0.0678        | 3.0    | 42   | 0.0616          | 0.9850   |
+| 0.0678        | 3.1481 | 44   | 0.0615          | 0.9852   |
+| 0.0499        | 3.2963 | 46   | 0.0616          | 0.9853   |
+| 0.0437        | 3.4444 | 48   | 0.0620          | 0.9853   |
+| 0.0437        | 3.5926 | 50   | 0.0621          | 0.9851   |
+| 0.0421        | 3.7407 | 52   | 0.0624          | 0.9852   |
+| 0.0557        | 3.8889 | 54   | 0.0624          | 0.9852   |
+| 0.0557        | 4.0    | 56   | 0.0623          | 0.9851   |
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.57.1
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "gate"
+  ],
+  "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 sha256:6efbf58332ca0496072376aa78c3dd9e6e8de4773ba2a18272fdc3485b06db39
+size 3387502872

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
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "effective_tokens_per_sec": 102.39668480138029,
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849732649347395,
+    "eval_loss": 0.061602283269166946,
+    "eval_runtime": 328.5148,
+    "eval_samples_per_second": 0.487,
+    "eval_steps_per_second": 0.061,
+    "total_flos": 83324244590592.0,
+    "train_loss": 0.10440204206055828,
+    "train_runtime": 17139.0998,
+    "train_samples_per_second": 0.101,
+    "train_steps_per_second": 0.003
+}

chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-42/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-42/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "gate"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-42/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efbf58332ca0496072376aa78c3dd9e6e8de4773ba2a18272fdc3485b06db39
+size 3387502872

checkpoint-42/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
+}

checkpoint-42/chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-42/global_step42/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:ef7f6515e9319bb86fcaa1ea92c8ce24a324903e8ea4890ed90a38dd74767672
+size 5073080581

checkpoint-42/global_step42/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1d9143601350e10734e3358ef72c77196c0293e363453497d5485a50d065eb
+size 5073080581

checkpoint-42/global_step42/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:e51c020ac61aee313ab99965afd0dfa01cc39aa49377b190f47c36aba2ee27d3
+size 5073080581

checkpoint-42/global_step42/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9dccd888540580bfa6eb5de105954411d45b32adf9c1e0b6eb2bd1aab6916e
+size 5073080581

checkpoint-42/global_step42/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cba34c1a105b3300ac6f06f66fd5f48539d1168665b2d93add8feef482abaf3
+size 39335009

checkpoint-42/global_step42/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7b7c7dcf96b2489fc5698994645092c39d02ad243132e9f52705e1e2896985
+size 39335009

checkpoint-42/global_step42/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4046b44c968a473403d24fe5bb22a959823716cc9ad6a3620b93f04b70e3d9
+size 39335009

checkpoint-42/global_step42/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45494a93560c38235a11912395989a9e13547cafe7219faafd847fc4b60c79bf
+size 39335009

checkpoint-42/latest

@@ -0,0 +1 @@
+global_step42

checkpoint-42/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8faa1956bb9e1240d9dced79476c996c851121b11dfce75d9c3722753a5e3a46
+size 15429

checkpoint-42/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34a8d67bfd6ad9750ae79c061a921542da77ed4a4acc9b06933c9bfb0db8c1d
+size 15429

checkpoint-42/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844ed709ab4e2190185eb693a69d51826b00d8a479b21a21f93aadddf838f894
+size 15429

checkpoint-42/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27d63fb97d2598099a5467cf42707e103798e0bfb778c91a053616d03a95881
+size 15429

checkpoint-42/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
+  }
+}

checkpoint-42/tokenizer.json

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

checkpoint-42/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": 1048576,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-42/trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_global_step": 42,
+  "best_metric": 0.061602283269166946,
+  "best_model_checkpoint": "rewrite_results/checkpoint-42",
+  "epoch": 3.0,
+  "eval_steps": 2,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14814814814814814,
+      "eval_accuracy": 0.9610916971862766,
+      "eval_loss": 0.24771852791309357,
+      "eval_runtime": 332.7057,
+      "eval_samples_per_second": 0.481,
+      "eval_steps_per_second": 0.06,
+      "step": 2
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.10552783565151713,
+      "learning_rate": 0.00027304247779439414,
+      "loss": 0.2441,
+      "step": 3
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "eval_accuracy": 0.9648183236107929,
+      "eval_loss": 0.1996598243713379,
+      "eval_runtime": 327.4272,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.061,
+      "step": 4
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.08840417088618377,
+      "learning_rate": 0.0004,
+      "loss": 0.2367,
+      "step": 6
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.9687810581276459,
+      "eval_loss": 0.15869076550006866,
+      "eval_runtime": 326.6521,
+      "eval_samples_per_second": 0.49,
+      "eval_steps_per_second": 0.061,
+      "step": 6
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "eval_accuracy": 0.9710204154483826,
+      "eval_loss": 0.14757852256298065,
+      "eval_runtime": 330.7473,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.06,
+      "step": 8
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04166015387300161,
+      "learning_rate": 0.00037647058823529414,
+      "loss": 0.1895,
+      "step": 9
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "eval_accuracy": 0.9732184664675948,
+      "eval_loss": 0.13183145225048065,
+      "eval_runtime": 325.6161,
+      "eval_samples_per_second": 0.491,
+      "eval_steps_per_second": 0.061,
+      "step": 10
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.026815989165312845,
+      "learning_rate": 0.00035294117647058826,
+      "loss": 0.1361,
+      "step": 12
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_accuracy": 0.9759430638638582,
+      "eval_loss": 0.11719267070293427,
+      "eval_runtime": 323.9433,
+      "eval_samples_per_second": 0.494,
+      "eval_steps_per_second": 0.062,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9783447362046809,
+      "eval_loss": 0.1052589863538742,
+      "eval_runtime": 320.7346,
+      "eval_samples_per_second": 0.499,
+      "eval_steps_per_second": 0.062,
+      "step": 14
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.027111063904139955,
+      "learning_rate": 0.0003294117647058824,
+      "loss": 0.18,
+      "step": 15
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "eval_accuracy": 0.9792185262272917,
+      "eval_loss": 0.09851272404193878,
+      "eval_runtime": 329.3754,
+      "eval_samples_per_second": 0.486,
+      "eval_steps_per_second": 0.061,
+      "step": 16
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.02728080298065729,
+      "learning_rate": 0.00030588235294117644,
+      "loss": 0.1193,
+      "step": 18
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "eval_accuracy": 0.9797502878582046,
+      "eval_loss": 0.09319568425416946,
+      "eval_runtime": 327.3319,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.061,
+      "step": 18
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "eval_accuracy": 0.9803937999427419,
+      "eval_loss": 0.08752243220806122,
+      "eval_runtime": 325.6299,
+      "eval_samples_per_second": 0.491,
+      "eval_steps_per_second": 0.061,
+      "step": 20
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.024562359210379074,
+      "learning_rate": 0.0002823529411764706,
+      "loss": 0.0823,
+      "step": 21
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "eval_accuracy": 0.980617014762694,
+      "eval_loss": 0.08400166034698486,
+      "eval_runtime": 330.0542,
+      "eval_samples_per_second": 0.485,
+      "eval_steps_per_second": 0.061,
+      "step": 22
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.04720330319206125,
+      "learning_rate": 0.00025882352941176474,
+      "loss": 0.1175,
+      "step": 24
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "eval_accuracy": 0.9813755814844891,
+      "eval_loss": 0.07777883112430573,
+      "eval_runtime": 330.5389,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.061,
+      "step": 24
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "eval_accuracy": 0.9826866606161857,
+      "eval_loss": 0.07366437464952469,
+      "eval_runtime": 330.0141,
+      "eval_samples_per_second": 0.485,
+      "eval_steps_per_second": 0.061,
+      "step": 26
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.05091774794908078,
+      "learning_rate": 0.00023529411764705883,
+      "loss": 0.0898,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9836173653422126,
+      "eval_loss": 0.07038821280002594,
+      "eval_runtime": 330.8638,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.06,
+      "step": 28
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.02332212687636519,
+      "learning_rate": 0.00021176470588235295,
+      "loss": 0.0948,
+      "step": 30
+    },
+    {
+      "epoch": 2.148148148148148,
+      "eval_accuracy": 0.9838456743046095,
+      "eval_loss": 0.06887274235486984,
+      "eval_runtime": 334.1801,
+      "eval_samples_per_second": 0.479,
+      "eval_steps_per_second": 0.06,
+      "step": 30
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "eval_accuracy": 0.9841358041079982,
+      "eval_loss": 0.06697963178157806,
+      "eval_runtime": 327.8238,
+      "eval_samples_per_second": 0.488,
+      "eval_steps_per_second": 0.061,
+      "step": 32
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.023466685722830175,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 0.0739,
+      "step": 33
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "eval_accuracy": 0.9841183559501172,
+      "eval_loss": 0.06529785692691803,
+      "eval_runtime": 324.9504,
+      "eval_samples_per_second": 0.492,
+      "eval_steps_per_second": 0.062,
+      "step": 34
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.02499598734491485,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 0.0526,
+      "step": 36
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "eval_accuracy": 0.984462930071049,
+      "eval_loss": 0.06430461257696152,
+      "eval_runtime": 328.33,
+      "eval_samples_per_second": 0.487,
+      "eval_steps_per_second": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "eval_accuracy": 0.9845490069370237,
+      "eval_loss": 0.06337571144104004,
+      "eval_runtime": 323.0777,
+      "eval_samples_per_second": 0.495,
+      "eval_steps_per_second": 0.062,
+      "step": 38
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.02235923851811797,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 0.0564,
+      "step": 39
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_accuracy": 0.9847284644961529,
+      "eval_loss": 0.062485575675964355,
+      "eval_runtime": 328.1316,
+      "eval_samples_per_second": 0.488,
+      "eval_steps_per_second": 0.061,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.03433345990626862,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 0.0678,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9849732649347395,
+      "eval_loss": 0.061602283269166946,
+      "eval_runtime": 301.0464,
+      "eval_samples_per_second": 0.531,
+      "eval_steps_per_second": 0.066,
+      "step": 42
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 6,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 62298500628480.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5b816d39dc624eff58585e10e199391fe2094f42003c2152d823fcf01a6408
+size 8657

checkpoint-42/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 not ZERO_STAGE 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(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"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)

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849732649347395,
+    "eval_loss": 0.061602283269166946,
+    "eval_runtime": 328.5148,
+    "eval_samples_per_second": 0.487,
+    "eval_steps_per_second": 0.061
+}

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

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": 1048576,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "effective_tokens_per_sec": 102.39668480138029,
+    "epoch": 4.0,
+    "total_flos": 83324244590592.0,
+    "train_loss": 0.10440204206055828,
+    "train_runtime": 17139.0998,
+    "train_samples_per_second": 0.101,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,47 @@
+{"current_steps": 2, "total_steps": 56, "eval_loss": 0.24771852791309357, "epoch": 0.14814814814814814, "percentage": 3.57, "elapsed_time": "0:11:28", "remaining_time": "5:09:47"}
+{"current_steps": 3, "total_steps": 56, "loss": 0.2441, "lr": 0.00027304247779439414, "epoch": 0.2222222222222222, "percentage": 5.36, "elapsed_time": "0:13:35", "remaining_time": "4:00:15"}
+{"current_steps": 4, "total_steps": 56, "eval_loss": 0.1996598243713379, "epoch": 0.2962962962962963, "percentage": 7.14, "elapsed_time": "0:21:10", "remaining_time": "4:35:21"}
+{"current_steps": 6, "total_steps": 56, "loss": 0.2367, "lr": 0.0004, "epoch": 0.4444444444444444, "percentage": 10.71, "elapsed_time": "0:25:28", "remaining_time": "3:32:15"}
+{"current_steps": 6, "total_steps": 56, "eval_loss": 0.15869076550006866, "epoch": 0.4444444444444444, "percentage": 10.71, "elapsed_time": "0:30:55", "remaining_time": "4:17:46"}
+{"current_steps": 8, "total_steps": 56, "eval_loss": 0.14757852256298065, "epoch": 0.5925925925925926, "percentage": 14.29, "elapsed_time": "0:42:18", "remaining_time": "4:13:50"}
+{"current_steps": 9, "total_steps": 56, "loss": 0.1895, "lr": 0.00037647058823529414, "epoch": 0.6666666666666666, "percentage": 16.07, "elapsed_time": "0:44:26", "remaining_time": "3:52:07"}
+{"current_steps": 10, "total_steps": 56, "eval_loss": 0.13183145225048065, "epoch": 0.7407407407407407, "percentage": 17.86, "elapsed_time": "0:52:01", "remaining_time": "3:59:19"}
+{"current_steps": 12, "total_steps": 56, "loss": 0.1361, "lr": 0.00035294117647058826, "epoch": 0.8888888888888888, "percentage": 21.43, "elapsed_time": "0:56:14", "remaining_time": "3:26:13"}
+{"current_steps": 12, "total_steps": 56, "eval_loss": 0.11719267070293427, "epoch": 0.8888888888888888, "percentage": 21.43, "elapsed_time": "1:01:39", "remaining_time": "3:46:04"}
+{"current_steps": 14, "total_steps": 56, "eval_loss": 0.1052589863538742, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "1:11:19", "remaining_time": "3:33:57"}
+{"current_steps": 15, "total_steps": 56, "loss": 0.18, "lr": 0.0003294117647058824, "epoch": 1.074074074074074, "percentage": 26.79, "elapsed_time": "1:13:30", "remaining_time": "3:20:54"}
+{"current_steps": 16, "total_steps": 56, "eval_loss": 0.09851272404193878, "epoch": 1.1481481481481481, "percentage": 28.57, "elapsed_time": "1:21:06", "remaining_time": "3:22:47"}
+{"current_steps": 18, "total_steps": 56, "loss": 0.1193, "lr": 0.00030588235294117644, "epoch": 1.2962962962962963, "percentage": 32.14, "elapsed_time": "1:25:27", "remaining_time": "3:00:24"}
+{"current_steps": 18, "total_steps": 56, "eval_loss": 0.09319568425416946, "epoch": 1.2962962962962963, "percentage": 32.14, "elapsed_time": "1:30:55", "remaining_time": "3:11:56"}
+{"current_steps": 20, "total_steps": 56, "eval_loss": 0.08752243220806122, "epoch": 1.4444444444444444, "percentage": 35.71, "elapsed_time": "1:42:24", "remaining_time": "3:04:20"}
+{"current_steps": 21, "total_steps": 56, "loss": 0.0823, "lr": 0.0002823529411764706, "epoch": 1.5185185185185186, "percentage": 37.5, "elapsed_time": "1:44:31", "remaining_time": "2:54:11"}
+{"current_steps": 22, "total_steps": 56, "eval_loss": 0.08400166034698486, "epoch": 1.5925925925925926, "percentage": 39.29, "elapsed_time": "1:52:07", "remaining_time": "2:53:17"}
+{"current_steps": 24, "total_steps": 56, "loss": 0.1175, "lr": 0.00025882352941176474, "epoch": 1.7407407407407407, "percentage": 42.86, "elapsed_time": "1:56:17", "remaining_time": "2:35:03"}
+{"current_steps": 24, "total_steps": 56, "eval_loss": 0.07777883112430573, "epoch": 1.7407407407407407, "percentage": 42.86, "elapsed_time": "2:01:49", "remaining_time": "2:42:25"}
+{"current_steps": 26, "total_steps": 56, "eval_loss": 0.07366437464952469, "epoch": 1.8888888888888888, "percentage": 46.43, "elapsed_time": "2:13:14", "remaining_time": "2:33:44"}
+{"current_steps": 27, "total_steps": 56, "loss": 0.0898, "lr": 0.00023529411764705883, "epoch": 1.9629629629629628, "percentage": 48.21, "elapsed_time": "2:15:21", "remaining_time": "2:25:23"}
+{"current_steps": 28, "total_steps": 56, "eval_loss": 0.07038821280002594, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "2:22:01", "remaining_time": "2:22:01"}
+{"current_steps": 30, "total_steps": 56, "loss": 0.0948, "lr": 0.00021176470588235295, "epoch": 2.148148148148148, "percentage": 53.57, "elapsed_time": "2:26:22", "remaining_time": "2:06:51"}
+{"current_steps": 30, "total_steps": 56, "eval_loss": 0.06887274235486984, "epoch": 2.148148148148148, "percentage": 53.57, "elapsed_time": "2:31:57", "remaining_time": "2:11:41"}
+{"current_steps": 32, "total_steps": 56, "eval_loss": 0.06697963178157806, "epoch": 2.2962962962962963, "percentage": 57.14, "elapsed_time": "2:43:39", "remaining_time": "2:02:44"}
+{"current_steps": 33, "total_steps": 56, "loss": 0.0739, "lr": 0.00018823529411764707, "epoch": 2.3703703703703702, "percentage": 58.93, "elapsed_time": "2:45:49", "remaining_time": "1:55:34"}
+{"current_steps": 34, "total_steps": 56, "eval_loss": 0.06529785692691803, "epoch": 2.4444444444444446, "percentage": 60.71, "elapsed_time": "2:53:25", "remaining_time": "1:52:12"}
+{"current_steps": 36, "total_steps": 56, "loss": 0.0526, "lr": 0.0001647058823529412, "epoch": 2.5925925925925926, "percentage": 64.29, "elapsed_time": "2:57:38", "remaining_time": "1:38:41"}
+{"current_steps": 36, "total_steps": 56, "eval_loss": 0.06430461257696152, "epoch": 2.5925925925925926, "percentage": 64.29, "elapsed_time": "3:03:06", "remaining_time": "1:41:43"}
+{"current_steps": 38, "total_steps": 56, "eval_loss": 0.06337571144104004, "epoch": 2.7407407407407405, "percentage": 67.86, "elapsed_time": "3:14:19", "remaining_time": "1:32:02"}
+{"current_steps": 39, "total_steps": 56, "loss": 0.0564, "lr": 0.0001411764705882353, "epoch": 2.814814814814815, "percentage": 69.64, "elapsed_time": "3:16:25", "remaining_time": "1:25:37"}
+{"current_steps": 40, "total_steps": 56, "eval_loss": 0.062485575675964355, "epoch": 2.888888888888889, "percentage": 71.43, "elapsed_time": "3:23:59", "remaining_time": "1:21:35"}
+{"current_steps": 42, "total_steps": 56, "loss": 0.0678, "lr": 0.00011764705882352942, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "3:27:13", "remaining_time": "1:09:04"}
+{"current_steps": 42, "total_steps": 56, "eval_loss": 0.061602283269166946, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "3:32:15", "remaining_time": "1:10:45"}
+{"current_steps": 44, "total_steps": 56, "eval_loss": 0.061493076384067535, "epoch": 3.148148148148148, "percentage": 78.57, "elapsed_time": "3:43:06", "remaining_time": "1:00:50"}
+{"current_steps": 45, "total_steps": 56, "loss": 0.0499, "lr": 9.411764705882353e-05, "epoch": 3.2222222222222223, "percentage": 80.36, "elapsed_time": "3:45:12", "remaining_time": "0:55:03"}
+{"current_steps": 46, "total_steps": 56, "eval_loss": 0.06156101077795029, "epoch": 3.2962962962962963, "percentage": 82.14, "elapsed_time": "3:52:47", "remaining_time": "0:50:36"}
+{"current_steps": 48, "total_steps": 56, "loss": 0.0437, "lr": 7.058823529411765e-05, "epoch": 3.4444444444444446, "percentage": 85.71, "elapsed_time": "3:56:54", "remaining_time": "0:39:29"}
+{"current_steps": 48, "total_steps": 56, "eval_loss": 0.06198165938258171, "epoch": 3.4444444444444446, "percentage": 85.71, "elapsed_time": "4:02:30", "remaining_time": "0:40:25"}
+{"current_steps": 50, "total_steps": 56, "eval_loss": 0.06207697466015816, "epoch": 3.5925925925925926, "percentage": 89.29, "elapsed_time": "4:13:58", "remaining_time": "0:30:28"}
+{"current_steps": 51, "total_steps": 56, "loss": 0.0421, "lr": 4.705882352941177e-05, "epoch": 3.6666666666666665, "percentage": 91.07, "elapsed_time": "4:16:05", "remaining_time": "0:25:06"}
+{"current_steps": 52, "total_steps": 56, "eval_loss": 0.06235222890973091, "epoch": 3.7407407407407405, "percentage": 92.86, "elapsed_time": "4:23:38", "remaining_time": "0:20:16"}
+{"current_steps": 54, "total_steps": 56, "loss": 0.0557, "lr": 2.3529411764705884e-05, "epoch": 3.888888888888889, "percentage": 96.43, "elapsed_time": "4:27:50", "remaining_time": "0:09:55"}
+{"current_steps": 54, "total_steps": 56, "eval_loss": 0.06244580075144768, "epoch": 3.888888888888889, "percentage": 96.43, "elapsed_time": "4:33:20", "remaining_time": "0:10:07"}
+{"current_steps": 56, "total_steps": 56, "eval_loss": 0.062325846403837204, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "4:43:44", "remaining_time": "0:00:00"}
+{"current_steps": 56, "total_steps": 56, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "4:45:35", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": 44,
+  "best_metric": 0.061493076384067535,
+  "best_model_checkpoint": "rewrite_results/checkpoint-42",
+  "epoch": 4.0,
+  "eval_steps": 2,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14814814814814814,
+      "eval_accuracy": 0.9610916971862766,
+      "eval_loss": 0.24771852791309357,
+      "eval_runtime": 332.7057,
+      "eval_samples_per_second": 0.481,
+      "eval_steps_per_second": 0.06,
+      "step": 2
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.10552783565151713,
+      "learning_rate": 0.00027304247779439414,
+      "loss": 0.2441,
+      "step": 3
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "eval_accuracy": 0.9648183236107929,
+      "eval_loss": 0.1996598243713379,
+      "eval_runtime": 327.4272,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.061,
+      "step": 4
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.08840417088618377,
+      "learning_rate": 0.0004,
+      "loss": 0.2367,
+      "step": 6
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.9687810581276459,
+      "eval_loss": 0.15869076550006866,
+      "eval_runtime": 326.6521,
+      "eval_samples_per_second": 0.49,
+      "eval_steps_per_second": 0.061,
+      "step": 6
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "eval_accuracy": 0.9710204154483826,
+      "eval_loss": 0.14757852256298065,
+      "eval_runtime": 330.7473,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.06,
+      "step": 8
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04166015387300161,
+      "learning_rate": 0.00037647058823529414,
+      "loss": 0.1895,
+      "step": 9
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "eval_accuracy": 0.9732184664675948,
+      "eval_loss": 0.13183145225048065,
+      "eval_runtime": 325.6161,
+      "eval_samples_per_second": 0.491,
+      "eval_steps_per_second": 0.061,
+      "step": 10
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.026815989165312845,
+      "learning_rate": 0.00035294117647058826,
+      "loss": 0.1361,
+      "step": 12
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_accuracy": 0.9759430638638582,
+      "eval_loss": 0.11719267070293427,
+      "eval_runtime": 323.9433,
+      "eval_samples_per_second": 0.494,
+      "eval_steps_per_second": 0.062,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9783447362046809,
+      "eval_loss": 0.1052589863538742,
+      "eval_runtime": 320.7346,
+      "eval_samples_per_second": 0.499,
+      "eval_steps_per_second": 0.062,
+      "step": 14
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.027111063904139955,
+      "learning_rate": 0.0003294117647058824,
+      "loss": 0.18,
+      "step": 15
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "eval_accuracy": 0.9792185262272917,
+      "eval_loss": 0.09851272404193878,
+      "eval_runtime": 329.3754,
+      "eval_samples_per_second": 0.486,
+      "eval_steps_per_second": 0.061,
+      "step": 16
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.02728080298065729,
+      "learning_rate": 0.00030588235294117644,
+      "loss": 0.1193,
+      "step": 18
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "eval_accuracy": 0.9797502878582046,
+      "eval_loss": 0.09319568425416946,
+      "eval_runtime": 327.3319,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.061,
+      "step": 18
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "eval_accuracy": 0.9803937999427419,
+      "eval_loss": 0.08752243220806122,
+      "eval_runtime": 325.6299,
+      "eval_samples_per_second": 0.491,
+      "eval_steps_per_second": 0.061,
+      "step": 20
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.024562359210379074,
+      "learning_rate": 0.0002823529411764706,
+      "loss": 0.0823,
+      "step": 21
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "eval_accuracy": 0.980617014762694,
+      "eval_loss": 0.08400166034698486,
+      "eval_runtime": 330.0542,
+      "eval_samples_per_second": 0.485,
+      "eval_steps_per_second": 0.061,
+      "step": 22
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.04720330319206125,
+      "learning_rate": 0.00025882352941176474,
+      "loss": 0.1175,
+      "step": 24
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "eval_accuracy": 0.9813755814844891,
+      "eval_loss": 0.07777883112430573,
+      "eval_runtime": 330.5389,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.061,
+      "step": 24
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "eval_accuracy": 0.9826866606161857,
+      "eval_loss": 0.07366437464952469,
+      "eval_runtime": 330.0141,
+      "eval_samples_per_second": 0.485,
+      "eval_steps_per_second": 0.061,
+      "step": 26
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.05091774794908078,
+      "learning_rate": 0.00023529411764705883,
+      "loss": 0.0898,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9836173653422126,
+      "eval_loss": 0.07038821280002594,
+      "eval_runtime": 330.8638,
+      "eval_samples_per_second": 0.484,
+      "eval_steps_per_second": 0.06,
+      "step": 28
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.02332212687636519,
+      "learning_rate": 0.00021176470588235295,
+      "loss": 0.0948,
+      "step": 30
+    },
+    {
+      "epoch": 2.148148148148148,
+      "eval_accuracy": 0.9838456743046095,
+      "eval_loss": 0.06887274235486984,
+      "eval_runtime": 334.1801,
+      "eval_samples_per_second": 0.479,
+      "eval_steps_per_second": 0.06,
+      "step": 30
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "eval_accuracy": 0.9841358041079982,
+      "eval_loss": 0.06697963178157806,
+      "eval_runtime": 327.8238,
+      "eval_samples_per_second": 0.488,
+      "eval_steps_per_second": 0.061,
+      "step": 32
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.023466685722830175,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 0.0739,
+      "step": 33
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "eval_accuracy": 0.9841183559501172,
+      "eval_loss": 0.06529785692691803,
+      "eval_runtime": 324.9504,
+      "eval_samples_per_second": 0.492,
+      "eval_steps_per_second": 0.062,
+      "step": 34
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.02499598734491485,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 0.0526,
+      "step": 36
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "eval_accuracy": 0.984462930071049,
+      "eval_loss": 0.06430461257696152,
+      "eval_runtime": 328.33,
+      "eval_samples_per_second": 0.487,
+      "eval_steps_per_second": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "eval_accuracy": 0.9845490069370237,
+      "eval_loss": 0.06337571144104004,
+      "eval_runtime": 323.0777,
+      "eval_samples_per_second": 0.495,
+      "eval_steps_per_second": 0.062,
+      "step": 38
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.02235923851811797,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 0.0564,
+      "step": 39
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_accuracy": 0.9847284644961529,
+      "eval_loss": 0.062485575675964355,
+      "eval_runtime": 328.1316,
+      "eval_samples_per_second": 0.488,
+      "eval_steps_per_second": 0.061,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.03433345990626862,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 0.0678,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9849732649347395,
+      "eval_loss": 0.061602283269166946,
+      "eval_runtime": 301.0464,
+      "eval_samples_per_second": 0.531,
+      "eval_steps_per_second": 0.066,
+      "step": 42
+    },
+    {
+      "epoch": 3.148148148148148,
+      "eval_accuracy": 0.9852119445846472,
+      "eval_loss": 0.061493076384067535,
+      "eval_runtime": 331.7193,
+      "eval_samples_per_second": 0.482,
+      "eval_steps_per_second": 0.06,
+      "step": 44
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.022600132657406128,
+      "learning_rate": 9.411764705882353e-05,
+      "loss": 0.0499,
+      "step": 45
+    },
+    {
+      "epoch": 3.2962962962962963,
+      "eval_accuracy": 0.9853399724949231,
+      "eval_loss": 0.06156101077795029,
+      "eval_runtime": 327.3955,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.061,
+      "step": 46
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.018635515413178816,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.0437,
+      "step": 48
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "eval_accuracy": 0.9852882434474587,
+      "eval_loss": 0.06198165938258171,
+      "eval_runtime": 335.6061,
+      "eval_samples_per_second": 0.477,
+      "eval_steps_per_second": 0.06,
+      "step": 48
+    },
+    {
+      "epoch": 3.5925925925925926,
+      "eval_accuracy": 0.9850508846328356,
+      "eval_loss": 0.06207697466015816,
+      "eval_runtime": 324.7443,
+      "eval_samples_per_second": 0.493,
+      "eval_steps_per_second": 0.062,
+      "step": 50
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.021001664364668726,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.0421,
+      "step": 51
+    },
+    {
+      "epoch": 3.7407407407407405,
+      "eval_accuracy": 0.9851825126851306,
+      "eval_loss": 0.06235222890973091,
+      "eval_runtime": 330.039,
+      "eval_samples_per_second": 0.485,
+      "eval_steps_per_second": 0.061,
+      "step": 52
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.02399059372934013,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.0557,
+      "step": 54
+    },
+    {
+      "epoch": 3.888888888888889,
+      "eval_accuracy": 0.985193215099636,
+      "eval_loss": 0.06244580075144768,
+      "eval_runtime": 328.4431,
+      "eval_samples_per_second": 0.487,
+      "eval_steps_per_second": 0.061,
+      "step": 54
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9850785367286026,
+      "eval_loss": 0.062325846403837204,
+      "eval_runtime": 334.0117,
+      "eval_samples_per_second": 0.479,
+      "eval_steps_per_second": 0.06,
+      "step": 56
+    },
+    {
+      "epoch": 4.0,
+      "step": 56,
+      "total_flos": 83324244590592.0,
+      "train_loss": 0.10440204206055828,
+      "train_runtime": 17139.0998,
+      "train_samples_per_second": 0.101,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 6,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 83324244590592.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5b816d39dc624eff58585e10e199391fe2094f42003c2152d823fcf01a6408
+size 8657