Upload output with latest checkpoint

.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-54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: korbih/Qwen2-VL-ui-sensei-curriculum-0-merged
+library_name: peft
+---
+
+# 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 0.14.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "korbih/Qwen2-VL-ui-sensei-curriculum-0-merged",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd471b6d37e76718469f311ed6fdb33fbdc7f32590a2ca6bbac41e73d5bf01f2
+size 1432933648

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{% if message['role'] == 'assistant' %}{% generation %}{{ message['content'] }}{% endgeneration %}{% else %}{{ message['content'] }}{% endif %}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{% if message['role'] == 'assistant' %}{% generation %}{{ content['text'] }}{% endgeneration %}{% else %}{{ content['text'] }}{% endif %}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-54/README.md

@@ -0,0 +1,202 @@
+---
+base_model: korbih/Qwen2-VL-ui-sensei-curriculum-0-merged
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-54/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "korbih/Qwen2-VL-ui-sensei-curriculum-0-merged",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-54/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd471b6d37e76718469f311ed6fdb33fbdc7f32590a2ca6bbac41e73d5bf01f2
+size 1432933648

checkpoint-54/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-54/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{% if message['role'] == 'assistant' %}{% generation %}{{ message['content'] }}{% endgeneration %}{% else %}{{ message['content'] }}{% endif %}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{% if message['role'] == 'assistant' %}{% generation %}{{ content['text'] }}{% endgeneration %}{% else %}{{ content['text'] }}{% endif %}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-54/global_step54/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb6e9532631b06b17f9b3ef8a6d3a25fa2b8e55d78ed7a8844481f0bac7d5c3
+size 1028679440

checkpoint-54/global_step54/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:a7d5dafbf5380dfb47c41fa398816b0c1adffa928a261e0cd29402b713eb8638
+size 1028676944

checkpoint-54/global_step54/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4668873e6bdb324e43815ead96892ebec053bf8108610f9fbf73e10dc3863466
+size 343210796

checkpoint-54/latest

@@ -0,0 +1 @@
+global_step54

checkpoint-54/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1048576,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-54/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db3e753be0c6f6e4fdc4abd156f952ba67820fc10528ead420cf099b1d29dfe
+size 14512

checkpoint-54/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9309bd02868a2f25316aa72d9709b379bcc660d767e5d0f77810fa8b2e104dea
+size 14512

checkpoint-54/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-54/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-54/tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-54/trainer_state.json

@@ -0,0 +1,843 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.1875,
+      "epoch": 0.018518518518518517,
+      "grad_norm": 0.6398105621337891,
+      "kl": 0.0,
+      "learning_rate": 9.814814814814815e-06,
+      "loss": 0.0,
+      "reward": 1.71875,
+      "reward_std": 0.6504871249198914,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.40625,
+      "rewards/low_level_action_reward": 0.3125,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 127.5625,
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.7235211730003357,
+      "kl": 0.0002079010009765625,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.0,
+      "reward": 2.71875,
+      "reward_std": 0.39879564940929413,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 135.0625,
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.4562557637691498,
+      "kl": 0.00024318695068359375,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.0,
+      "reward": 2.84375,
+      "reward_std": 0.18600594997406006,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 152.5,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.6260181665420532,
+      "kl": 0.00021791458129882812,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.0,
+      "reward": 2.5625,
+      "reward_std": 0.49022960662841797,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 135.125,
+      "epoch": 0.09259259259259259,
+      "grad_norm": 0.6719797253608704,
+      "kl": 0.0003514289855957031,
+      "learning_rate": 9.074074074074075e-06,
+      "loss": 0.0,
+      "reward": 2.21875,
+      "reward_std": 0.6535098254680634,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.65625,
+      "rewards/low_level_action_reward": 0.5625,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 150.25,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.7520681619644165,
+      "kl": 0.00030612945556640625,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0,
+      "reward": 2.71875,
+      "reward_std": 0.4076072573661804,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 126.8125,
+      "epoch": 0.12962962962962962,
+      "grad_norm": 0.675370991230011,
+      "kl": 0.00039958953857421875,
+      "learning_rate": 8.703703703703705e-06,
+      "loss": 0.0,
+      "reward": 2.84375,
+      "reward_std": 0.22201896458864212,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 117.5625,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.46207016706466675,
+      "kl": 0.0003070831298828125,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.0,
+      "reward": 2.90625,
+      "reward_std": 0.1293872892856598,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.3125,
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.6307782530784607,
+      "kl": 0.0005035400390625,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0,
+      "reward": 2.6875,
+      "reward_std": 0.37714509665966034,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.25,
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.4247063100337982,
+      "kl": 0.00049591064453125,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.0,
+      "reward": 2.6875,
+      "reward_std": 0.3471825420856476,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.0625,
+      "epoch": 0.2037037037037037,
+      "grad_norm": 0.6954518556594849,
+      "kl": 0.00057220458984375,
+      "learning_rate": 7.962962962962963e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.5406372249126434,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 136.1875,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.582653820514679,
+      "kl": 0.000484466552734375,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.0,
+      "reward": 2.6875,
+      "reward_std": 0.3104073107242584,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.75,
+      "epoch": 0.24074074074074073,
+      "grad_norm": 0.629402220249176,
+      "kl": 0.000583648681640625,
+      "learning_rate": 7.592592592592594e-06,
+      "loss": 0.0,
+      "reward": 2.4375,
+      "reward_std": 0.4172614812850952,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.5625,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.1875,
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.7241819500923157,
+      "kl": 0.000797271728515625,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0,
+      "reward": 2.4375,
+      "reward_std": 0.5900483131408691,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 154.0,
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.6297197341918945,
+      "kl": 0.0008087158203125,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.26726123690605164,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.375,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.6148404479026794,
+      "kl": 0.0006656646728515625,
+      "learning_rate": 7.0370370370370375e-06,
+      "loss": 0.0,
+      "reward": 2.59375,
+      "reward_std": 0.38719549030065536,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.3125,
+      "epoch": 0.3148148148148148,
+      "grad_norm": 0.6441869139671326,
+      "kl": 0.0010585784912109375,
+      "learning_rate": 6.851851851851853e-06,
+      "loss": 0.0,
+      "reward": 2.34375,
+      "reward_std": 0.7265094220638275,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.59375,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 128.0,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6853404641151428,
+      "kl": 0.001300811767578125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0001,
+      "reward": 2.46875,
+      "reward_std": 0.5430608987808228,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.4375,
+      "epoch": 0.35185185185185186,
+      "grad_norm": 0.6561163663864136,
+      "kl": 0.000759124755859375,
+      "learning_rate": 6.481481481481482e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.425382524728775,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.25,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.6343511343002319,
+      "kl": 0.002178192138671875,
+      "learning_rate": 6.296296296296297e-06,
+      "loss": 0.0001,
+      "reward": 2.0,
+      "reward_std": 0.4629100561141968,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.375,
+      "rewards/low_level_action_reward": 0.625,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 124.625,
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.4019067883491516,
+      "kl": 0.0009860992431640625,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.0,
+      "reward": 2.71875,
+      "reward_std": 0.1602174937725067,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 147.875,
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.582368791103363,
+      "kl": 0.0011844635009765625,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.0,
+      "reward": 2.65625,
+      "reward_std": 0.48780593276023865,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.6875,
+      "epoch": 0.42592592592592593,
+      "grad_norm": 0.5904684066772461,
+      "kl": 0.00109100341796875,
+      "learning_rate": 5.740740740740741e-06,
+      "loss": 0.0,
+      "reward": 2.5625,
+      "reward_std": 0.5303300768136978,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 159.8125,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6057837009429932,
+      "kl": 0.000835418701171875,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.6094194948673248,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 119.625,
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.663507878780365,
+      "kl": 0.001251220703125,
+      "learning_rate": 5.370370370370371e-06,
+      "loss": 0.0001,
+      "reward": 2.5625,
+      "reward_std": 0.4718233644962311,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 159.5,
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.6058818101882935,
+      "kl": 0.001064300537109375,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.0,
+      "reward": 2.46875,
+      "reward_std": 0.47371043264865875,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.625,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.5625,
+      "epoch": 0.5,
+      "grad_norm": 0.66436767578125,
+      "kl": 0.00177001953125,
+      "learning_rate": 5e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.4076072573661804,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 117.0,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.5601560473442078,
+      "kl": 0.00107574462890625,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.0,
+      "reward": 2.75,
+      "reward_std": 0.7071067541837692,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.9375,
+      "epoch": 0.5370370370370371,
+      "grad_norm": 0.7565531730651855,
+      "kl": 0.001983642578125,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 0.0001,
+      "reward": 2.5,
+      "reward_std": 0.5919395387172699,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 120.0625,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.48327645659446716,
+      "kl": 0.0011444091796875,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0,
+      "reward": 2.5,
+      "reward_std": 0.4225771427154541,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.875,
+      "epoch": 0.5740740740740741,
+      "grad_norm": 0.6559168100357056,
+      "kl": 0.0015716552734375,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": 0.0001,
+      "reward": 2.71875,
+      "reward_std": 0.318369522690773,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.9375,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.6644594073295593,
+      "kl": 0.00125885009765625,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.0001,
+      "reward": 2.5,
+      "reward_std": 0.524651974439621,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.9375,
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.6801736354827881,
+      "kl": 0.00177001953125,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.0001,
+      "reward": 2.71875,
+      "reward_std": 0.47724711894989014,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.8125,
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.655364990234375,
+      "kl": 0.001251220703125,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0001,
+      "reward": 2.681249976158142,
+      "reward_std": 0.34982745349407196,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.7437500059604645,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.0,
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6691354513168335,
+      "kl": 0.00145721435546875,
+      "learning_rate": 3.5185185185185187e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.5023942440748215,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.0,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7033304572105408,
+      "kl": 0.0017242431640625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0001,
+      "reward": 2.5,
+      "reward_std": 0.33732882142066956,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.625,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.1875,
+      "epoch": 0.6851851851851852,
+      "grad_norm": 0.6343482732772827,
+      "kl": 0.00199127197265625,
+      "learning_rate": 3.1481481481481483e-06,
+      "loss": 0.0001,
+      "reward": 2.53125,
+      "reward_std": 0.45671412348747253,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.0,
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.4454864263534546,
+      "kl": 0.00203704833984375,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 0.0001,
+      "reward": 2.84375,
+      "reward_std": 0.2651650309562683,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 109.5,
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.4786466062068939,
+      "kl": 0.00164794921875,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.0001,
+      "reward": 2.21875,
+      "reward_std": 0.0883883461356163,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.5,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.375,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.7090415954589844,
+      "kl": 0.001918792724609375,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.42062845826148987,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.65625,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.3125,
+      "epoch": 0.7592592592592593,
+      "grad_norm": 0.6908057332038879,
+      "kl": 0.00180816650390625,
+      "learning_rate": 2.4074074074074075e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.3808925449848175,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 41
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.0625,
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.6768062114715576,
+      "kl": 0.001918792724609375,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0001,
+      "reward": 2.5625,
+      "reward_std": 0.2970190867781639,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 42
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 155.0,
+      "epoch": 0.7962962962962963,
+      "grad_norm": 0.4138977527618408,
+      "kl": 0.00133514404296875,
+      "learning_rate": 2.037037037037037e-06,
+      "loss": 0.0001,
+      "reward": 2.6875,
+      "reward_std": 0.3471825420856476,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 43
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 127.75,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.7176859378814697,
+      "kl": 0.00603485107421875,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 0.0002,
+      "reward": 2.5625,
+      "reward_std": 0.7255652844905853,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 44
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 145.75,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6933517456054688,
+      "kl": 0.001953125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.44478052854537964,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.5625,
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.6017954349517822,
+      "kl": 0.00167083740234375,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 0.0001,
+      "reward": 2.75,
+      "reward_std": 0.4355512708425522,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 46
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.75,
+      "epoch": 0.8703703703703703,
+      "grad_norm": 0.598857581615448,
+      "kl": 0.0020904541015625,
+      "learning_rate": 1.2962962962962962e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.5727390944957733,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 47
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 125.6875,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.40999215841293335,
+      "kl": 0.0013885498046875,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.0001,
+      "reward": 2.9375,
+      "reward_std": 0.1767766922712326,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 1.0,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 48
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.0625,
+      "epoch": 0.9074074074074074,
+      "grad_norm": 0.3335365653038025,
+      "kl": 0.0015869140625,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 0.0001,
+      "reward": 2.78125,
+      "reward_std": 0.0883883461356163,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 49
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.9375,
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.6265583038330078,
+      "kl": 0.001506805419921875,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 0.0001,
+      "reward": 2.8125,
+      "reward_std": 0.27439429610967636,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.9375,
+      "epoch": 0.9444444444444444,
+      "grad_norm": 0.46192532777786255,
+      "kl": 0.0023040771484375,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.0001,
+      "reward": 2.8125,
+      "reward_std": 0.3471825420856476,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 51
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 105.125,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.38872018456459045,
+      "kl": 0.001560211181640625,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 0.0001,
+      "reward": 2.84375,
+      "reward_std": 0.29693374037742615,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.96875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 52
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 122.0625,
+      "epoch": 0.9814814814814815,
+      "grad_norm": 0.7645645141601562,
+      "kl": 0.001918792724609375,
+      "learning_rate": 1.8518518518518518e-07,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.46769899129867554,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 53
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.8125,
+      "epoch": 1.0,
+      "grad_norm": 0.6258404850959778,
+      "kl": 0.0021209716796875,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "reward": 2.75,
+      "reward_std": 0.2587745785713196,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 54
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 54,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3709e03341e18a28befd94e3d084f93fcbb4684f8cb24379bbc4783123c3629
+size 8056

checkpoint-54/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 json
+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)
+
+        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 files:
+        state_dict = torch.load(f, map_location=device)
+        # 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}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) 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")
+
+
+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 = fp32_flat_groups[0].numel() * 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
+    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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        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 get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=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
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    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.
+
+    """
+    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")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+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)
+
+    # 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")
+        state_dict_split = split_torch_state_dict_into_shards(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
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # 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)

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1048576,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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 sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3709e03341e18a28befd94e3d084f93fcbb4684f8cb24379bbc4783123c3629
+size 8056