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-69/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-1-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-1-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": [
+    "o_proj",
+    "lm_head",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "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 sha256:9d0e706970dc49398e294e3eb628f4569bd8ddffc912fa5a158b399e7c3fcbb8
+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-69/README.md

@@ -0,0 +1,202 @@
+---
+base_model: korbih/Qwen2-VL-ui-sensei-curriculum-1-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-69/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "korbih/Qwen2-VL-ui-sensei-curriculum-1-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": [
+    "o_proj",
+    "lm_head",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-69/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0e706970dc49398e294e3eb628f4569bd8ddffc912fa5a158b399e7c3fcbb8
+size 1432933648

checkpoint-69/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-69/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-69/global_step69/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:c1985fae4facd71ff47e1c3dc8ec3c89514060d4b196706bfcddbb19c5d6e4a3
+size 1028679440

checkpoint-69/global_step69/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1759347438f2cc3941a1a2645b7f796ea6b8aec474eadd352317edd85565f304
+size 1028676944

checkpoint-69/global_step69/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34abf6849670a3b1651c2617112a75d6ac8e89cef0a8b779189c81010a8cc6b9
+size 343210796

checkpoint-69/latest

@@ -0,0 +1 @@
+global_step69

checkpoint-69/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-69/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c0b258015b388f13cda16100efe0b6d1cfb9ed2aaa61e0a9c866a10c063b3c
+size 14512

checkpoint-69/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818099f2499b673e016c11bacc043b2bdef8c5e4bc337807f1f233839b98ae81
+size 14512

checkpoint-69/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-69/tokenizer.json

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

checkpoint-69/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-69/trainer_state.json

@@ -0,0 +1,1068 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.1875,
+      "epoch": 0.014492753623188406,
+      "grad_norm": 0.6139106154441833,
+      "kl": 0.0,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 0.0,
+      "reward": 2.4375,
+      "reward_std": 0.5868084877729416,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.625,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 127.5625,
+      "epoch": 0.028985507246376812,
+      "grad_norm": 0.5722443461418152,
+      "kl": 0.00024318695068359375,
+      "learning_rate": 9.710144927536233e-06,
+      "loss": 0.0,
+      "reward": 2.5,
+      "reward_std": 0.5239592343568802,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.4375,
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.5824880003929138,
+      "kl": 0.00020122528076171875,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.0,
+      "reward": 2.65625,
+      "reward_std": 0.2651650384068489,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 118.6875,
+      "epoch": 0.057971014492753624,
+      "grad_norm": 0.36597952246665955,
+      "kl": 0.00018024444580078125,
+      "learning_rate": 9.420289855072464e-06,
+      "loss": 0.0,
+      "reward": 2.9375,
+      "reward_std": 0.1157275140285492,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 152.5625,
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.6035860180854797,
+      "kl": 0.0002532005310058594,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 0.0,
+      "reward": 2.5625,
+      "reward_std": 0.5609941333532333,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 127.4375,
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.6012734174728394,
+      "kl": 0.00024127960205078125,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.0,
+      "reward": 2.53125,
+      "reward_std": 0.619232714176178,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 144.125,
+      "epoch": 0.10144927536231885,
+      "grad_norm": 0.5445747375488281,
+      "kl": 0.000244140625,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 0.0,
+      "reward": 2.59375,
+      "reward_std": 0.38138842582702637,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.375,
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.5511504411697388,
+      "kl": 0.0002574920654296875,
+      "learning_rate": 8.840579710144929e-06,
+      "loss": 0.0,
+      "reward": 2.5625,
+      "reward_std": 0.4802234023809433,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 146.3125,
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.39530378580093384,
+      "kl": 0.000354766845703125,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.0,
+      "reward": 2.65625,
+      "reward_std": 0.35197147727012634,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 140.375,
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.6552218794822693,
+      "kl": 0.0005092620849609375,
+      "learning_rate": 8.55072463768116e-06,
+      "loss": 0.0,
+      "reward": 2.4375,
+      "reward_std": 0.5546489059925079,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.8125,
+      "epoch": 0.15942028985507245,
+      "grad_norm": 0.5951517224311829,
+      "kl": 0.00035858154296875,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 0.0,
+      "reward": 2.78125,
+      "reward_std": 0.3061639815568924,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 135.3125,
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.5633934140205383,
+      "kl": 0.0006542205810546875,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.2925042062997818,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 123.5625,
+      "epoch": 0.18840579710144928,
+      "grad_norm": 0.6226204037666321,
+      "kl": 0.0006656646728515625,
+      "learning_rate": 8.115942028985508e-06,
+      "loss": 0.0,
+      "reward": 2.59375,
+      "reward_std": 0.35564958304166794,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 105.625,
+      "epoch": 0.2028985507246377,
+      "grad_norm": 0.6195806264877319,
+      "kl": 0.000820159912109375,
+      "learning_rate": 7.971014492753623e-06,
+      "loss": 0.0,
+      "reward": 2.0,
+      "reward_std": 0.26726123690605164,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.5,
+      "rewards/low_level_action_reward": 0.5,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 125.1875,
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.6649656891822815,
+      "kl": 0.000728607177734375,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.0,
+      "reward": 2.625,
+      "reward_std": 0.5720614045858383,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.9375,
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.5864853262901306,
+      "kl": 0.000736236572265625,
+      "learning_rate": 7.681159420289856e-06,
+      "loss": 0.0,
+      "reward": 2.4375,
+      "reward_std": 0.5585024058818817,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.625,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.5,
+      "epoch": 0.2463768115942029,
+      "grad_norm": 0.6138740181922913,
+      "kl": 0.0010128021240234375,
+      "learning_rate": 7.536231884057972e-06,
+      "loss": 0.0,
+      "reward": 2.5,
+      "reward_std": 0.5500157475471497,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.6875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 121.875,
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.5959410667419434,
+      "kl": 0.001262664794921875,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 0.0001,
+      "reward": 2.8125,
+      "reward_std": 0.31539323925971985,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.375,
+      "epoch": 0.2753623188405797,
+      "grad_norm": 0.5705474615097046,
+      "kl": 0.001049041748046875,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.0,
+      "reward": 2.28125,
+      "reward_std": 0.6677263081073761,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.4375,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 135.5625,
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.43123292922973633,
+      "kl": 0.001407623291015625,
+      "learning_rate": 7.10144927536232e-06,
+      "loss": 0.0001,
+      "reward": 2.90625,
+      "reward_std": 0.18600594997406006,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.96875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 122.0,
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.6939437985420227,
+      "kl": 0.001312255859375,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.39837799966335297,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 118.3125,
+      "epoch": 0.3188405797101449,
+      "grad_norm": 0.6187354326248169,
+      "kl": 0.00099945068359375,
+      "learning_rate": 6.811594202898551e-06,
+      "loss": 0.0,
+      "reward": 2.90625,
+      "reward_std": 0.2651650384068489,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.96875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.125,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.619391143321991,
+      "kl": 0.00128173828125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0001,
+      "reward": 2.53125,
+      "reward_std": 0.3966485261917114,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.65625,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 113.375,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.6596890687942505,
+      "kl": 0.001399993896484375,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.0001,
+      "reward": 2.75,
+      "reward_std": 0.32261285185813904,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.6875,
+      "epoch": 0.36231884057971014,
+      "grad_norm": 0.6133448481559753,
+      "kl": 0.0009860992431640625,
+      "learning_rate": 6.376811594202898e-06,
+      "loss": 0.0,
+      "reward": 2.8125,
+      "reward_std": 0.45117098093032837,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 149.1875,
+      "epoch": 0.37681159420289856,
+      "grad_norm": 0.6592795848846436,
+      "kl": 0.00177764892578125,
+      "learning_rate": 6.2318840579710145e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.6028470396995544,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.6875,
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.5780444145202637,
+      "kl": 0.00179290771484375,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.0001,
+      "reward": 2.75,
+      "reward_std": 0.35841864347457886,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 122.4375,
+      "epoch": 0.4057971014492754,
+      "grad_norm": 0.004627756774425507,
+      "kl": 0.00113677978515625,
+      "learning_rate": 5.942028985507247e-06,
+      "loss": 0.0,
+      "reward": 3.0,
+      "reward_std": 0.0,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 1.0,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.0625,
+      "epoch": 0.42028985507246375,
+      "grad_norm": 0.5492585301399231,
+      "kl": 0.001590728759765625,
+      "learning_rate": 5.797101449275363e-06,
+      "loss": 0.0001,
+      "reward": 2.78125,
+      "reward_std": 0.2630179077386856,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.0,
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.5583959221839905,
+      "kl": 0.002197265625,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 0.0001,
+      "reward": 2.34375,
+      "reward_std": 0.38138842582702637,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.65625,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.8125,
+      "epoch": 0.4492753623188406,
+      "grad_norm": 0.5492476224899292,
+      "kl": 0.002262115478515625,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 0.0001,
+      "reward": 2.4375,
+      "reward_std": 0.5260358154773712,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.5625,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 138.875,
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.5487068891525269,
+      "kl": 0.00237274169921875,
+      "learning_rate": 5.362318840579711e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.34475886821746826,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 142.875,
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.5532354712486267,
+      "kl": 0.001415252685546875,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.35098859667778015,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 124.75,
+      "epoch": 0.4927536231884058,
+      "grad_norm": 0.5815756916999817,
+      "kl": 0.00170135498046875,
+      "learning_rate": 5.072463768115943e-06,
+      "loss": 0.0001,
+      "reward": 2.75,
+      "reward_std": 0.39837799966335297,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 114.4375,
+      "epoch": 0.5072463768115942,
+      "grad_norm": 0.6308125257492065,
+      "kl": 0.0013580322265625,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.3535533770918846,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 148.625,
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.5474228858947754,
+      "kl": 0.00164031982421875,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.4355512708425522,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.75,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 124.75,
+      "epoch": 0.5362318840579711,
+      "grad_norm": 0.46679696440696716,
+      "kl": 0.002105712890625,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 0.0001,
+      "reward": 2.78125,
+      "reward_std": 0.33905068039894104,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.125,
+      "epoch": 0.5507246376811594,
+      "grad_norm": 0.6113550662994385,
+      "kl": 0.002593994140625,
+      "learning_rate": 4.492753623188406e-06,
+      "loss": 0.0001,
+      "reward": 2.78125,
+      "reward_std": 0.3749881833791733,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.25,
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.6611613035202026,
+      "kl": 0.00252532958984375,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.5487885922193527,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 115.5,
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.6072784662246704,
+      "kl": 0.002056121826171875,
+      "learning_rate": 4.202898550724638e-06,
+      "loss": 0.0001,
+      "reward": 2.84375,
+      "reward_std": 0.3808925449848175,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.875,
+      "epoch": 0.5942028985507246,
+      "grad_norm": 0.5880132913589478,
+      "kl": 0.0030670166015625,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.3966485261917114,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 41
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 120.75,
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.6412323117256165,
+      "kl": 0.0033416748046875,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 0.0001,
+      "reward": 2.21875,
+      "reward_std": 0.3818188011646271,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.59375,
+      "rewards/low_level_action_reward": 0.625,
+      "step": 42
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.3125,
+      "epoch": 0.6231884057971014,
+      "grad_norm": 0.6180394887924194,
+      "kl": 0.00208282470703125,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.5133327841758728,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 43
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 128.5625,
+      "epoch": 0.6376811594202898,
+      "grad_norm": 0.6940774917602539,
+      "kl": 0.002685546875,
+      "learning_rate": 3.6231884057971017e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.44099316000938416,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 44
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 126.6875,
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.6032717227935791,
+      "kl": 0.00244140625,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.5762138962745667,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 137.25,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.3984113335609436,
+      "kl": 0.001659393310546875,
+      "learning_rate": 3.3333333333333333e-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": 46
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.3125,
+      "epoch": 0.6811594202898551,
+      "grad_norm": 0.37174344062805176,
+      "kl": 0.003200531005859375,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 0.0001,
+      "reward": 2.875,
+      "reward_std": 0.13363061845302582,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 47
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 113.625,
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.6417880654335022,
+      "kl": 0.0034027099609375,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 0.0001,
+      "reward": 2.125,
+      "reward_std": 0.5175491571426392,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.5,
+      "rewards/low_level_action_reward": 0.625,
+      "step": 48
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 120.875,
+      "epoch": 0.7101449275362319,
+      "grad_norm": 0.3155536353588104,
+      "kl": 0.003082275390625,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 0.0001,
+      "reward": 2.84375,
+      "reward_std": 0.18600594997406006,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.90625,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 49
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.3125,
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.6605053544044495,
+      "kl": 0.00164031982421875,
+      "learning_rate": 2.7536231884057974e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.36348532140254974,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.9375,
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.5570524334907532,
+      "kl": 0.002655029296875,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.0001,
+      "reward": 2.59375,
+      "reward_std": 0.7191916108131409,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.78125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 51
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 141.1875,
+      "epoch": 0.7536231884057971,
+      "grad_norm": 0.4170561730861664,
+      "kl": 0.001430511474609375,
+      "learning_rate": 2.4637681159420295e-06,
+      "loss": 0.0001,
+      "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": 52
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 121.5625,
+      "epoch": 0.7681159420289855,
+      "grad_norm": 0.6030449867248535,
+      "kl": 0.0033111572265625,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 0.0001,
+      "reward": 2.212499976158142,
+      "reward_std": 0.46406444907188416,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.5250000059604645,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 53
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 130.0625,
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.40535715222358704,
+      "kl": 0.001888275146484375,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 0.0001,
+      "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": 54
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 133.25,
+      "epoch": 0.7971014492753623,
+      "grad_norm": 0.5601004958152771,
+      "kl": 0.00250244140625,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 0.0001,
+      "reward": 2.5,
+      "reward_std": 0.5945880711078644,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 123.3125,
+      "epoch": 0.8115942028985508,
+      "grad_norm": 0.6125327348709106,
+      "kl": 0.00266265869140625,
+      "learning_rate": 1.884057971014493e-06,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.3380180299282074,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.75,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 56
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 139.875,
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.525627613067627,
+      "kl": 0.002033233642578125,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.5649385899305344,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 57
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 121.0,
+      "epoch": 0.8405797101449275,
+      "grad_norm": 0.6244301795959473,
+      "kl": 0.0027923583984375,
+      "learning_rate": 1.5942028985507246e-06,
+      "loss": 0.0001,
+      "reward": 2.875,
+      "reward_std": 0.27439429610967636,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9375,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 58
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 134.6875,
+      "epoch": 0.855072463768116,
+      "grad_norm": 0.6077686548233032,
+      "kl": 0.0023651123046875,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 0.0001,
+      "reward": 2.5,
+      "reward_std": 0.42632102966308594,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.6875,
+      "step": 59
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 129.125,
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.549598217010498,
+      "kl": 0.001483917236328125,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 0.0001,
+      "reward": 2.6875,
+      "reward_std": 0.4150373041629791,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 132.0625,
+      "epoch": 0.8840579710144928,
+      "grad_norm": 0.3656002879142761,
+      "kl": 0.00152587890625,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 0.0001,
+      "reward": 2.837499976158142,
+      "reward_std": 0.18077217042446136,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.9000000059604645,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 61
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 150.25,
+      "epoch": 0.8985507246376812,
+      "grad_norm": 0.5994426012039185,
+      "kl": 0.0025482177734375,
+      "learning_rate": 1.0144927536231885e-06,
+      "loss": 0.0001,
+      "reward": 2.71875,
+      "reward_std": 0.36348532140254974,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 62
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 121.3125,
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.6515089273452759,
+      "kl": 0.0019683837890625,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.0001,
+      "reward": 2.21875,
+      "reward_std": 0.4966200590133667,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.65625,
+      "rewards/low_level_action_reward": 0.5625,
+      "step": 63
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 124.625,
+      "epoch": 0.927536231884058,
+      "grad_norm": 0.6351967453956604,
+      "kl": 0.002838134765625,
+      "learning_rate": 7.246376811594204e-07,
+      "loss": 0.0001,
+      "reward": 2.78125,
+      "reward_std": 0.3808925449848175,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 64
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 121.6875,
+      "epoch": 0.9420289855072463,
+      "grad_norm": 0.6020182967185974,
+      "kl": 0.001895904541015625,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 0.0001,
+      "reward": 2.8125,
+      "reward_std": 0.3535533770918846,
+      "rewards/format_reward_custom": 0.9375,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 125.0,
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.6860438585281372,
+      "kl": 0.00278472900390625,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 0.0001,
+      "reward": 2.65625,
+      "reward_std": 0.2651650384068489,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.71875,
+      "rewards/low_level_action_reward": 0.9375,
+      "step": 66
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 123.875,
+      "epoch": 0.9710144927536232,
+      "grad_norm": 0.587708592414856,
+      "kl": 0.003173828125,
+      "learning_rate": 2.8985507246376816e-07,
+      "loss": 0.0001,
+      "reward": 2.625,
+      "reward_std": 0.2925042062997818,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.8125,
+      "rewards/low_level_action_reward": 0.8125,
+      "step": 67
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 131.125,
+      "epoch": 0.9855072463768116,
+      "grad_norm": 0.5342994928359985,
+      "kl": 0.002532958984375,
+      "learning_rate": 1.4492753623188408e-07,
+      "loss": 0.0001,
+      "reward": 2.71875,
+      "reward_std": 0.4419417232275009,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.84375,
+      "rewards/low_level_action_reward": 0.875,
+      "step": 68
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 122.875,
+      "epoch": 1.0,
+      "grad_norm": 0.43572136759757996,
+      "kl": 0.00244140625,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "reward": 2.875,
+      "reward_std": 0.13363061845302582,
+      "rewards/format_reward_custom": 1.0,
+      "rewards/high_level_action_reward": 0.875,
+      "rewards/low_level_action_reward": 1.0,
+      "step": 69
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 69,
+  "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-69/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4d6271d133105d2cac453bf32849252af60188137b1c5b8cd038085a5c5bad
+size 8056

checkpoint-69/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:ec4d6271d133105d2cac453bf32849252af60188137b1c5b8cd038085a5c5bad
+size 8056