Initial model upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-20-merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-20-merged/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-20-merged/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 %}{{ message['content'] }}<|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 %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-20-merged/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/home/ec2-user/.cache/modelscope/hub/qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

checkpoint-20-merged/configuration.json

@@ -0,0 +1,5 @@
+{
+    "framework": "pytorch",
+    "task": "image-text-to-text",
+    "allow_remote": true
+}

checkpoint-20-merged/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.47.0"
+}

checkpoint-20-merged/infer_result/20241209-115720.jsonl

@@ -0,0 +1 @@
+{"system": "You are a helpful assistant.", "query": "<image>### Task  Extract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.  ---### Field Extraction  #### **Header Information**  - **Claim No.:** Extract exact text after \"Claim No. :\".  - **Invoice No.:** Extract complete string after \"Invoice No. :\". Ensure underscores are included (e.g., `NC30334314_1`).  - **AK No.:** Extract exact text after \"AK No. :\".  - **Invoice Date:** Extract full date after \"Invoice Dt :\".  - **Organization:** Extract complete name after \"Organization :\" with original case.  - **Category, Entitlement, Gender:** Extract exact text after respective labels.  - **Address:** Extract all lines under \"Address :\" with line breaks.  - **Policy Number, Service Date:** Extract respective values as displayed.  - **Consultant:** Extract full name after \"Consultant :\".  - **Auth No's:** Extract exact text after \"Auth No's :\".  - **ICD Codes:** Extract code and description after \"ICD Codes :\".  #### **Service Details Table**  For each row, extract:  - Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.  #### **Financial Summary**  Extract numeric values with decimals:  - Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.  ---### Validation  1. Confirm all data matches source image exactly.  2. Verify dates, numeric values, and field calculations.  3. Maintain original text case, punctuation, and spacing.  4. Ensure numeric totals align with service amounts.  **Special Cases:**  - **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.  - **Invoice No.:** Include underscores; no truncation.  ---### Output Format  Return results in this JSON structure:  ```json{    \"basicInfo\": {        \"claimNumber\": \"\",        \"invoiceNumber\": \"\",        \"invoiceDate\": \"\",        \"akNumber\": \"\",        \"organization\": \"\",        \"category\": \"\",        \"entitlement\": \"\",        \"gender\": \"\",        \"address\": \"\",        \"policyNumber\": \"\",        \"admitServiceDate\": \"\",        \"consultant\": \"\",        \"authNumber\": \"\",        \"icdCodes\": []    },    \"services\": [        {            \"category\": \"\",            \"dateOfService\": \"\",            \"procedureCode\": \"\",            \"description\": \"\",            \"provider\": \"\",            \"requisitionNumber\": \"\",            \"units\": \"\",            \"rate\": \"\",            \"amount\": \"\"        }    ],    \"financialSummary\": {        \"claimTotalCharges\": \"\",        \"patientResponsibilities\": \"\",        \"insuranceResponsibilities\": \"\",        \"adjustments\": \"\",        \"claimTotal\": \"\"    }}```---### Quality Checks  1. Verify required fields are present.  2. Check for text truncation or extra spaces.  3. Confirm calculations and consistent date formats.  ", "response": "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"\",\n    \"invoiceNumber\": \"\",\n    \"invoiceDate\": \"\",\n    \"akNumber\": \"\",\n    \"organization\": \"\",\n    \"category\": \"\",\n    \"entitlement\": \"\",\n    \"gender\": \"\",\n    \"address\": \"\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"\",\n    \"consultant\": \"\",\n    \"authNumber\": \"\",\n    \"icdCodes\": []\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"\",\n    \"patientResponsibilities\": \"\",\n    \"insuranceResponsibilities\": \"\",\n    \"adjustments\": \"\",\n    \"claimTotal\": \"\"\n  }\n}\n```", "history": [], "images": ["/home/ec2-user/testing/AGA KHAN HOSPITAL_page_43.png"]}

checkpoint-20-merged/infer_result/20241209-122144.jsonl

@@ -0,0 +1,3 @@
+{"system": "You are a helpful assistant.", "query": "You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "response": "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract.", "history": []}
+{"system": "You are a helpful assistant.", "query": "<image>\\n\\n### Task\\nExtract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.\\n\\n---\\n\\n### Field Extraction\\n**Header Information**\\n- **Claim No.:** Extract exact text after \\\"Claim No. :\\\".\\n- **Invoice No.:** Extract complete string after \\\"Invoice No. :\\\". Ensure underscores are included (e.g., `NC30334314_1`).\\n- **AK No.:** Extract exact text after \\\"AK No. :\\\".\\n- **Invoice Date:** Extract full date after \\\"Invoice Dt :\\\".\\n- **Organization:** Extract complete name after \\\"Organization :\\\" with original case.\\n- **Category, Entitlement, Gender:** Extract exact text after respective labels.\\n- **Address:** Extract all lines under \\\"Address :\\\" with line breaks.\\n- **Policy Number, Service Date:** Extract respective values as displayed.\\n- **Consultant:** Extract full name after \\\"Consultant :\\\".\\n- **Auth No's:** Extract exact text after \\\"Auth No's :\\\".\\n- **ICD Codes:** Extract code and description after \\\"ICD Codes :\\\".\\n\\n**Service Details Table**\\nFor each row, extract:\\n- Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.\\n\\n**Financial Summary**\\nExtract numeric values with decimals:\\n- Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.\\n\\n---\\n\\n### Validation\\n1. Confirm all data matches source image exactly.\\n2. Verify dates, numeric values, and field calculations.\\n3. Maintain original text case, punctuation, and spacing.\\n4. Ensure numeric totals align with service amounts.\\n\\n**Special Cases:**\\n- **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.\\n- **Invoice No.:** Include underscores; no truncation.\\n\\n---\\n\\n### Output Format\\nReturn results in this JSON structure:\\n```json\\n{\\n    \\\"basicInfo\\\": {\\n      \\\"claimNumber\\\": \\\"\\\",\\n      \\\"invoiceNumber\\\": \\\"\\\",\\n      \\\"invoiceDate\\\": \\\"\\\",\\n      \\\"akNumber\\\": \\\"\\\",\\n      \\\"organization\\\": \\\"\\\",\\n      \\\"category\\\": \\\"\\\",\\n      \\\"entitlement\\\": \\\"\\\",\\n      \\\"gender\\\": \\\"\\\",\\n      \\\"address\\\": \\\"\\\",\\n      \\\"policyNumber\\\": \\\"\\\",\\n      \\\"admitServiceDate\\\": \\\"\\\",\\n      \\\"consultant\\\": \\\"\\\",\\n      \\\"authNumber\\\": \\\"\\\", \\n      \\\"icdCodes\\\": []\\n    },\\n    \\\"services\\\": [\\n      {\\n        \\\"category\\\": \\\"\\\",\\n        \\\"dateOfService\\\": \\\"\\\",\\n        \\\"procedureCode\\\": \\\"\\\",\\n        \\\"description\\\": \\\"\\\",\\n        \\\"provider\\\": \\\"\\\",\\n        \\\"requisitionNumber\\\": \\\"\\\",\\n        \\\"units\\\": \\\"\\\",\\n        \\\"rate\\\": \\\"\\\",\\n        \\\"amount\\\": \\\"\\\"\\n      }\\n    ],\\n    \\\"financialSummary\\\": {\\n      \\\"claimTotalCharges\\\": \\\"\\\",\\n      \\\"patientResponsibilities\\\": \\\"\\\",\\n      \\\"insuranceResponsibilities\\\": \\\"\\\",\\n      \\\"adjustments\\\": \\\"\\\",\\n      \\\"claimTotal\\\": \\\"\\\"\\n    }\\n  }\\n```\\n\\n---\\n\\n### Quality Checks\\n1. Verify required fields are present.\\n2. Check for text truncation or extra spaces.\\n3. Confirm calculations and consistent date formats.", "response": "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"NCE6982133\",\n    \"invoiceNumber\": \"NC30334314_1\",\n    \"invoiceDate\": \"12/06/24\",\n    \"akNumber\": \"AK02170824\",\n    \"organization\": \"BUPA INTERNATIONAL\",\n    \"category\": \"AMBULATORY OFFICE VISIT\",\n    \"entitlement\": \"BUPA MEMBERS DIRECT BILLING C/O BUPA\",\n    \"gender\": \"M\",\n    \"address\": \"00100 NBI 047 KENYA 00100\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"12/06/24 11:48\",\n    \"consultant\": \"HASSANALI, SALIM HATI\",\n    \"authNumber\": \"\",\n    \"icdCodes\": [\n      {\n        \"category\": \"J45.20\",\n        \"description\": \"MILD INTERMITTENT ASTHMA, UNCO\",\n        \"requisitionNumber\": \"R10.13\",\n        \"units\": \"1\",\n        \"rate\": \"5,250.00\",\n        \"amount\": \"5,250.00\"\n      }\n    ]\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"5,250.00\",\n    \"patientResponsibilities\": \"0.00\",\n    \"insuranceResponsibilities\": \"0.00\",\n    \"adjustments\": \"0.00\",\n    \"claimTotal\": \"5,250.00\"\n  }\n}\n```", "history": [["You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract."]], "images": ["/home/ec2-user/training/AGA KHAN HOSPITAL_page_1.png"]}
+{"system": "You are a helpful assistant.", "query": "You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "response": "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract.", "history": [["You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract."], ["<image>\\n\\n### Task\\nExtract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.\\n\\n---\\n\\n### Field Extraction\\n**Header Information**\\n- **Claim No.:** Extract exact text after \\\"Claim No. :\\\".\\n- **Invoice No.:** Extract complete string after \\\"Invoice No. :\\\". Ensure underscores are included (e.g., `NC30334314_1`).\\n- **AK No.:** Extract exact text after \\\"AK No. :\\\".\\n- **Invoice Date:** Extract full date after \\\"Invoice Dt :\\\".\\n- **Organization:** Extract complete name after \\\"Organization :\\\" with original case.\\n- **Category, Entitlement, Gender:** Extract exact text after respective labels.\\n- **Address:** Extract all lines under \\\"Address :\\\" with line breaks.\\n- **Policy Number, Service Date:** Extract respective values as displayed.\\n- **Consultant:** Extract full name after \\\"Consultant :\\\".\\n- **Auth No's:** Extract exact text after \\\"Auth No's :\\\".\\n- **ICD Codes:** Extract code and description after \\\"ICD Codes :\\\".\\n\\n**Service Details Table**\\nFor each row, extract:\\n- Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.\\n\\n**Financial Summary**\\nExtract numeric values with decimals:\\n- Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.\\n\\n---\\n\\n### Validation\\n1. Confirm all data matches source image exactly.\\n2. Verify dates, numeric values, and field calculations.\\n3. Maintain original text case, punctuation, and spacing.\\n4. Ensure numeric totals align with service amounts.\\n\\n**Special Cases:**\\n- **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.\\n- **Invoice No.:** Include underscores; no truncation.\\n\\n---\\n\\n### Output Format\\nReturn results in this JSON structure:\\n```json\\n{\\n    \\\"basicInfo\\\": {\\n      \\\"claimNumber\\\": \\\"\\\",\\n      \\\"invoiceNumber\\\": \\\"\\\",\\n      \\\"invoiceDate\\\": \\\"\\\",\\n      \\\"akNumber\\\": \\\"\\\",\\n      \\\"organization\\\": \\\"\\\",\\n      \\\"category\\\": \\\"\\\",\\n      \\\"entitlement\\\": \\\"\\\",\\n      \\\"gender\\\": \\\"\\\",\\n      \\\"address\\\": \\\"\\\",\\n      \\\"policyNumber\\\": \\\"\\\",\\n      \\\"admitServiceDate\\\": \\\"\\\",\\n      \\\"consultant\\\": \\\"\\\",\\n      \\\"authNumber\\\": \\\"\\\", \\n      \\\"icdCodes\\\": []\\n    },\\n    \\\"services\\\": [\\n      {\\n        \\\"category\\\": \\\"\\\",\\n        \\\"dateOfService\\\": \\\"\\\",\\n        \\\"procedureCode\\\": \\\"\\\",\\n        \\\"description\\\": \\\"\\\",\\n        \\\"provider\\\": \\\"\\\",\\n        \\\"requisitionNumber\\\": \\\"\\\",\\n        \\\"units\\\": \\\"\\\",\\n        \\\"rate\\\": \\\"\\\",\\n        \\\"amount\\\": \\\"\\\"\\n      }\\n    ],\\n    \\\"financialSummary\\\": {\\n      \\\"claimTotalCharges\\\": \\\"\\\",\\n      \\\"patientResponsibilities\\\": \\\"\\\",\\n      \\\"insuranceResponsibilities\\\": \\\"\\\",\\n      \\\"adjustments\\\": \\\"\\\",\\n      \\\"claimTotal\\\": \\\"\\\"\\n    }\\n  }\\n```\\n\\n---\\n\\n### Quality Checks\\n1. Verify required fields are present.\\n2. Check for text truncation or extra spaces.\\n3. Confirm calculations and consistent date formats.", "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"NCE6982133\",\n    \"invoiceNumber\": \"NC30334314_1\",\n    \"invoiceDate\": \"12/06/24\",\n    \"akNumber\": \"AK02170824\",\n    \"organization\": \"BUPA INTERNATIONAL\",\n    \"category\": \"AMBULATORY OFFICE VISIT\",\n    \"entitlement\": \"BUPA MEMBERS DIRECT BILLING C/O BUPA\",\n    \"gender\": \"M\",\n    \"address\": \"00100 NBI 047 KENYA 00100\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"12/06/24 11:48\",\n    \"consultant\": \"HASSANALI, SALIM HATI\",\n    \"authNumber\": \"\",\n    \"icdCodes\": [\n      {\n        \"category\": \"J45.20\",\n        \"description\": \"MILD INTERMITTENT ASTHMA, UNCO\",\n        \"requisitionNumber\": \"R10.13\",\n        \"units\": \"1\",\n        \"rate\": \"5,250.00\",\n        \"amount\": \"5,250.00\"\n      }\n    ]\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"5,250.00\",\n    \"patientResponsibilities\": \"0.00\",\n    \"insuranceResponsibilities\": \"0.00\",\n    \"adjustments\": \"0.00\",\n    \"claimTotal\": \"5,250.00\"\n  }\n}\n```"]], "images": ["/home/ec2-user/training/AGA KHAN HOSPITAL_page_1.png"]}

checkpoint-20-merged/infer_result/20241209-122630.jsonl

@@ -0,0 +1,3 @@
+{"system": "You are a helpful assistant.", "query": "You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "response": "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract.", "history": []}
+{"system": "You are a helpful assistant.", "query": "<image>\\n\\n### Task\\nExtract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.\\n\\n---\\n\\n### Field Extraction\\n**Header Information**\\n- **Claim No.:** Extract exact text after \\\"Claim No. :\\\".\\n- **Invoice No.:** Extract complete string after \\\"Invoice No. :\\\". Ensure underscores are included (e.g., `NC30334314_1`).\\n- **AK No.:** Extract exact text after \\\"AK No. :\\\".\\n- **Invoice Date:** Extract full date after \\\"Invoice Dt :\\\".\\n- **Organization:** Extract complete name after \\\"Organization :\\\" with original case.\\n- **Category, Entitlement, Gender:** Extract exact text after respective labels.\\n- **Address:** Extract all lines under \\\"Address :\\\" with line breaks.\\n- **Policy Number, Service Date:** Extract respective values as displayed.\\n- **Consultant:** Extract full name after \\\"Consultant :\\\".\\n- **Auth No's:** Extract exact text after \\\"Auth No's :\\\".\\n- **ICD Codes:** Extract code and description after \\\"ICD Codes :\\\".\\n\\n**Service Details Table**\\nFor each row, extract:\\n- Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.\\n\\n**Financial Summary**\\nExtract numeric values with decimals:\\n- Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.\\n\\n---\\n\\n### Validation\\n1. Confirm all data matches source image exactly.\\n2. Verify dates, numeric values, and field calculations.\\n3. Maintain original text case, punctuation, and spacing.\\n4. Ensure numeric totals align with service amounts.\\n\\n**Special Cases:**\\n- **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.\\n- **Invoice No.:** Include underscores; no truncation.\\n\\n---\\n\\n### Output Format\\nReturn results in this JSON structure:\\n```json\\n{\\n    \\\"basicInfo\\\": {\\n      \\\"claimNumber\\\": \\\"\\\",\\n      \\\"invoiceNumber\\\": \\\"\\\",\\n      \\\"invoiceDate\\\": \\\"\\\",\\n      \\\"akNumber\\\": \\\"\\\",\\n      \\\"organization\\\": \\\"\\\",\\n      \\\"category\\\": \\\"\\\",\\n      \\\"entitlement\\\": \\\"\\\",\\n      \\\"gender\\\": \\\"\\\",\\n      \\\"address\\\": \\\"\\\",\\n      \\\"policyNumber\\\": \\\"\\\",\\n      \\\"admitServiceDate\\\": \\\"\\\",\\n      \\\"consultant\\\": \\\"\\\",\\n      \\\"authNumber\\\": \\\"\\\", \\n      \\\"icdCodes\\\": []\\n    },\\n    \\\"services\\\": [\\n      {\\n        \\\"category\\\": \\\"\\\",\\n        \\\"dateOfService\\\": \\\"\\\",\\n        \\\"procedureCode\\\": \\\"\\\",\\n        \\\"description\\\": \\\"\\\",\\n        \\\"provider\\\": \\\"\\\",\\n        \\\"requisitionNumber\\\": \\\"\\\",\\n        \\\"units\\\": \\\"\\\",\\n        \\\"rate\\\": \\\"\\\",\\n        \\\"amount\\\": \\\"\\\"\\n      }\\n    ],\\n    \\\"financialSummary\\\": {\\n      \\\"claimTotalCharges\\\": \\\"\\\",\\n      \\\"patientResponsibilities\\\": \\\"\\\",\\n      \\\"insuranceResponsibilities\\\": \\\"\\\",\\n      \\\"adjustments\\\": \\\"\\\",\\n      \\\"claimTotal\\\": \\\"\\\"\\n    }\\n  }\\n```\\n\\n---\\n\\n### Quality Checks\\n1. Verify required fields are present.\\n2. Check for text truncation or extra spaces.\\n3. Confirm calculations and consistent date formats.", "response": "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"UHE6970794\",\n    \"invoiceNumber\": \"UH283634582_2\",\n    \"invoiceDate\": \"12/06/24\",\n    \"akNumber\": \"AK01951093\",\n    \"organization\": \"BUPA INTERNATIONAL\",\n    \"category\": \"EMERGENCY\",\n    \"entitlement\": \"BUPA MEMBERS DIRECT BILLING C/O BUPA\",\n    \"gender\": \"M\",\n    \"address\": \"00100 NRB 047 KENYA 00100\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"12/06/24 10:20\",\n    \"consultant\": \"\",\n    \"authNumber\": \"\",\n    \"icdCodes\": []\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"3,470.00\",\n    \"patientResponsibilities\": \"0.00\",\n    \"insuranceResponsibilities\": \"0.00\",\n    \"adjustments\": \"0.00\",\n    \"claimTotal\": \"3,470.00\"\n  }\n}\n```", "history": [["You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract."]], "images": ["/home/ec2-user/testing/AGA KHAN HOSPITAL_page_47.png"]}
+{"system": "You are a helpful assistant.", "query": "/home/ec2-user/testing/AGA KHAN HOSPITAL_page_53.png", "response": "I'm sorry, but as an AI language model, I don't have the capability to directly access or analyze images. However, I can help you with the extraction of information from the image you provided. Please upload the image, and I'll do my best to extract the relevant data.", "history": [["You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract."], ["<image>\\n\\n### Task\\nExtract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.\\n\\n---\\n\\n### Field Extraction\\n**Header Information**\\n- **Claim No.:** Extract exact text after \\\"Claim No. :\\\".\\n- **Invoice No.:** Extract complete string after \\\"Invoice No. :\\\". Ensure underscores are included (e.g., `NC30334314_1`).\\n- **AK No.:** Extract exact text after \\\"AK No. :\\\".\\n- **Invoice Date:** Extract full date after \\\"Invoice Dt :\\\".\\n- **Organization:** Extract complete name after \\\"Organization :\\\" with original case.\\n- **Category, Entitlement, Gender:** Extract exact text after respective labels.\\n- **Address:** Extract all lines under \\\"Address :\\\" with line breaks.\\n- **Policy Number, Service Date:** Extract respective values as displayed.\\n- **Consultant:** Extract full name after \\\"Consultant :\\\".\\n- **Auth No's:** Extract exact text after \\\"Auth No's :\\\".\\n- **ICD Codes:** Extract code and description after \\\"ICD Codes :\\\".\\n\\n**Service Details Table**\\nFor each row, extract:\\n- Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.\\n\\n**Financial Summary**\\nExtract numeric values with decimals:\\n- Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.\\n\\n---\\n\\n### Validation\\n1. Confirm all data matches source image exactly.\\n2. Verify dates, numeric values, and field calculations.\\n3. Maintain original text case, punctuation, and spacing.\\n4. Ensure numeric totals align with service amounts.\\n\\n**Special Cases:**\\n- **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.\\n- **Invoice No.:** Include underscores; no truncation.\\n\\n---\\n\\n### Output Format\\nReturn results in this JSON structure:\\n```json\\n{\\n    \\\"basicInfo\\\": {\\n      \\\"claimNumber\\\": \\\"\\\",\\n      \\\"invoiceNumber\\\": \\\"\\\",\\n      \\\"invoiceDate\\\": \\\"\\\",\\n      \\\"akNumber\\\": \\\"\\\",\\n      \\\"organization\\\": \\\"\\\",\\n      \\\"category\\\": \\\"\\\",\\n      \\\"entitlement\\\": \\\"\\\",\\n      \\\"gender\\\": \\\"\\\",\\n      \\\"address\\\": \\\"\\\",\\n      \\\"policyNumber\\\": \\\"\\\",\\n      \\\"admitServiceDate\\\": \\\"\\\",\\n      \\\"consultant\\\": \\\"\\\",\\n      \\\"authNumber\\\": \\\"\\\", \\n      \\\"icdCodes\\\": []\\n    },\\n    \\\"services\\\": [\\n      {\\n        \\\"category\\\": \\\"\\\",\\n        \\\"dateOfService\\\": \\\"\\\",\\n        \\\"procedureCode\\\": \\\"\\\",\\n        \\\"description\\\": \\\"\\\",\\n        \\\"provider\\\": \\\"\\\",\\n        \\\"requisitionNumber\\\": \\\"\\\",\\n        \\\"units\\\": \\\"\\\",\\n        \\\"rate\\\": \\\"\\\",\\n        \\\"amount\\\": \\\"\\\"\\n      }\\n    ],\\n    \\\"financialSummary\\\": {\\n      \\\"claimTotalCharges\\\": \\\"\\\",\\n      \\\"patientResponsibilities\\\": \\\"\\\",\\n      \\\"insuranceResponsibilities\\\": \\\"\\\",\\n      \\\"adjustments\\\": \\\"\\\",\\n      \\\"claimTotal\\\": \\\"\\\"\\n    }\\n  }\\n```\\n\\n---\\n\\n### Quality Checks\\n1. Verify required fields are present.\\n2. Check for text truncation or extra spaces.\\n3. Confirm calculations and consistent date formats.", "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"UHE6970794\",\n    \"invoiceNumber\": \"UH283634582_2\",\n    \"invoiceDate\": \"12/06/24\",\n    \"akNumber\": \"AK01951093\",\n    \"organization\": \"BUPA INTERNATIONAL\",\n    \"category\": \"EMERGENCY\",\n    \"entitlement\": \"BUPA MEMBERS DIRECT BILLING C/O BUPA\",\n    \"gender\": \"M\",\n    \"address\": \"00100 NRB 047 KENYA 00100\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"12/06/24 10:20\",\n    \"consultant\": \"\",\n    \"authNumber\": \"\",\n    \"icdCodes\": []\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"3,470.00\",\n    \"patientResponsibilities\": \"0.00\",\n    \"insuranceResponsibilities\": \"0.00\",\n    \"adjustments\": \"0.00\",\n    \"claimTotal\": \"3,470.00\"\n  }\n}\n```"]], "images": ["/home/ec2-user/testing/AGA KHAN HOSPITAL_page_47.png"]}

checkpoint-20-merged/infer_result/20241209-122914.jsonl

@@ -0,0 +1,2 @@
+{"system": "You are a helpful assistant.", "query": "You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "response": "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract.", "history": []}
+{"system": "You are a helpful assistant.", "query": "<image>\\n\\n### Task\\nExtract data from medical invoice images with 100% accuracy. Do not infer, guess, or modify any values.\\n\\n---\\n\\n### Field Extraction\\n**Header Information**\\n- **Claim No.:** Extract exact text after \\\"Claim No. :\\\".\\n- **Invoice No.:** Extract complete string after \\\"Invoice No. :\\\". Ensure underscores are included (e.g., `NC30334314_1`).\\n- **AK No.:** Extract exact text after \\\"AK No. :\\\".\\n- **Invoice Date:** Extract full date after \\\"Invoice Dt :\\\".\\n- **Organization:** Extract complete name after \\\"Organization :\\\" with original case.\\n- **Category, Entitlement, Gender:** Extract exact text after respective labels.\\n- **Address:** Extract all lines under \\\"Address :\\\" with line breaks.\\n- **Policy Number, Service Date:** Extract respective values as displayed.\\n- **Consultant:** Extract full name after \\\"Consultant :\\\".\\n- **Auth No's:** Extract exact text after \\\"Auth No's :\\\".\\n- **ICD Codes:** Extract code and description after \\\"ICD Codes :\\\".\\n\\n**Service Details Table**\\nFor each row, extract:\\n- Date of Service, Procedure Code, Description, Provider, Rx No., Units, Rate, and Amount. Preserve original formats, including decimals.\\n\\n**Financial Summary**\\nExtract numeric values with decimals:\\n- Total Charges, Patient/Insurance Responsibilities, Adjustments, Final Claim Total.\\n\\n---\\n\\n### Validation\\n1. Confirm all data matches source image exactly.\\n2. Verify dates, numeric values, and field calculations.\\n3. Maintain original text case, punctuation, and spacing.\\n4. Ensure numeric totals align with service amounts.\\n\\n**Special Cases:**\\n- **Provider Name:** Must match exactly, 10 characters (e.g., `HASSSALI00`). Verify against source for `0`/`O`, `1`/`l` ambiguities.\\n- **Invoice No.:** Include underscores; no truncation.\\n\\n---\\n\\n### Output Format\\nReturn results in this JSON structure:\\n```json\\n{\\n    \\\"basicInfo\\\": {\\n      \\\"claimNumber\\\": \\\"\\\",\\n      \\\"invoiceNumber\\\": \\\"\\\",\\n      \\\"invoiceDate\\\": \\\"\\\",\\n      \\\"akNumber\\\": \\\"\\\",\\n      \\\"organization\\\": \\\"\\\",\\n      \\\"category\\\": \\\"\\\",\\n      \\\"entitlement\\\": \\\"\\\",\\n      \\\"gender\\\": \\\"\\\",\\n      \\\"address\\\": \\\"\\\",\\n      \\\"policyNumber\\\": \\\"\\\",\\n      \\\"admitServiceDate\\\": \\\"\\\",\\n      \\\"consultant\\\": \\\"\\\",\\n      \\\"authNumber\\\": \\\"\\\", \\n      \\\"icdCodes\\\": []\\n    },\\n    \\\"services\\\": [\\n      {\\n        \\\"category\\\": \\\"\\\",\\n        \\\"dateOfService\\\": \\\"\\\",\\n        \\\"procedureCode\\\": \\\"\\\",\\n        \\\"description\\\": \\\"\\\",\\n        \\\"provider\\\": \\\"\\\",\\n        \\\"requisitionNumber\\\": \\\"\\\",\\n        \\\"units\\\": \\\"\\\",\\n        \\\"rate\\\": \\\"\\\",\\n        \\\"amount\\\": \\\"\\\"\\n      }\\n    ],\\n    \\\"financialSummary\\\": {\\n      \\\"claimTotalCharges\\\": \\\"\\\",\\n      \\\"patientResponsibilities\\\": \\\"\\\",\\n      \\\"insuranceResponsibilities\\\": \\\"\\\",\\n      \\\"adjustments\\\": \\\"\\\",\\n      \\\"claimTotal\\\": \\\"\\\"\\n    }\\n  }\\n```\\n\\n---\\n\\n### Quality Checks\\n1. Verify required fields are present.\\n2. Check for text truncation or extra spaces.\\n3. Confirm calculations and consistent date formats.", "response": "```json\n{\n  \"basicInfo\": {\n    \"claimNumber\": \"NCE6952481\",\n    \"invoiceNumber\": \"NC30300785_1\",\n    \"invoiceDate\": \"12/06/24\",\n    \"akNumber\": \"AK02839815\",\n    \"organization\": \"BUPA INTERNATIONAL\",\n    \"category\": \"AMBULATORY OFFICE VISIT\",\n    \"entitlement\": \"BUPA MEMBERS DIRECT BILLING C/O BUPA\",\n    \"gender\": \"F\",\n    \"address\": \"Nairobi GPO\\n047\\nKENYA\\n00100\",\n    \"policyNumber\": \"\",\n    \"admitServiceDate\": \"12/06/24 09:31\",\n    \"consultant\": \"OTIDO,SAMUEL\",\n    \"icdCodes\": [\n      {\n        \"code\": \"R05.3\",\n        \"description\": \"CHRONIC COUGH\"\n      },\n      {\n        \"code\": \"J45.20\",\n        \"description\": \"MILD INTERMITTENT ASTHMA, UNCO\"\n      },\n      {\n        \"code\": \"L20.9\",\n        \"description\": \"ATOPIC DERMATITIS, UNSPECIFIED\"\n      },\n      {\n        \"code\": \"J30.9\",\n        \"description\": \"ALLERGIC RHINITIS, UNSPECIFIED\"\n      },\n      {\n        \"code\": \"H10.13\",\n        \"description\": \"ACUTE ATOPIC CONJUNCTIVITIS, B\"\n      }\n    ]\n  },\n  \"services\": [\n    {\n      \"category\": \"\",\n      \"dateOfService\": \"\",\n      \"procedureCode\": \"\",\n      \"description\": \"\",\n      \"provider\": \"\",\n      \"requisitionNumber\": \"\",\n      \"units\": \"\",\n      \"rate\": \"\",\n      \"amount\": \"\"\n    }\n  ],\n  \"financialSummary\": {\n    \"claimTotalCharges\": \"5,250.00\",\n    \"patientResponsibilities\": \"0.00\",\n    \"insuranceResponsibilities\": \"0.00\",\n    \"adjustments\": \"0.00\",\n    \"claimTotal\": \"5,250.00\"\n  }\n}\n```", "history": [["You are a medical invoice data extraction assistant. Extract information accurately and precisely to JSON format.", "Sure, I can help you with that. Please provide me with the medical invoice data that you want me to extract."]], "images": ["/home/ec2-user/testing/AGA KHAN HOSPITAL_page_53.png"]}

checkpoint-20-merged/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f74c2b149fb96ea22a774754ce1459494f8a4d43227681a2d41068c437990fe
+size 4418050848

checkpoint-20-merged/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2VLProcessor"
+}

checkpoint-20-merged/sft_args.json

@@ -0,0 +1,273 @@
+{
+  "model_type": "qwen2-vl-2b-instruct",
+  "model_id_or_path": "qwen/Qwen2-VL-2B-Instruct",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "full",
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "qwen2-vl",
+  "output_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947",
+  "add_output_dir_suffix": true,
+  "ddp_backend": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
+  "seed": 42,
+  "resume_from_checkpoint": null,
+  "resume_only_model": false,
+  "ignore_data_skip": false,
+  "dtype": "bf16",
+  "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": {},
+  "loss_name": null,
+  "dataset": [
+    "/home/ec2-user/train.jsonl"
+  ],
+  "val_dataset": [
+    "/home/ec2-user/val.jsonl"
+  ],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.0,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/opt/conda/envs/old/lib/python3.10/site-packages/swift/llm/agent/default_loss_scale_config.json",
+  "system": null,
+  "tools_prompt": "react_en",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "check_dataset_strategy": "none",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    null
+  ],
+  "quant_method": null,
+  "quantization_bit": 0,
+  "hqq_axis": 0,
+  "hqq_dynamic_config_path": null,
+  "bnb_4bit_comp_dtype": "bf16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "rescale_image": -1,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias_trainable": "none",
+  "lora_dtype": null,
+  "lora_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "rope_scaling": null,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "ia3_feedforward_modules": [],
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "neftune_noise_alpha": null,
+  "neftune_backend": "transformers",
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
+  "gradient_checkpointing": true,
+  "vit_use_gc": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 5,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 5e-05,
+  "weight_decay": 0.1,
+  "gradient_accumulation_steps": 8,
+  "max_grad_norm": 1,
+  "predict_with_generate": false,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.03,
+  "warmup_steps": 0,
+  "eval_steps": 50,
+  "save_steps": 50,
+  "save_only_model": false,
+  "save_total_limit": 2,
+  "logging_steps": 5,
+  "acc_steps": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_drop_last": false,
+  "push_to_hub": false,
+  "hub_model_id": null,
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_strategy": "every_save",
+  "test_oom_error": false,
+  "disable_tqdm": false,
+  "lazy_tokenize": true,
+  "preprocess_num_proc": 1,
+  "use_flash_attn": null,
+  "ignore_args_error": false,
+  "check_model_is_latest": true,
+  "logging_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/runs",
+  "report_to": [
+    "tensorboard"
+  ],
+  "acc_strategy": "token",
+  "save_on_each_node": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps",
+  "save_safetensors": true,
+  "gpu_memory_fraction": null,
+  "include_num_input_tokens_seen": false,
+  "local_repo_path": null,
+  "custom_register_path": null,
+  "custom_dataset_info": null,
+  "device_map_config": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "fsdp": "",
+  "fsdp_config": null,
+  "sequence_parallel_size": 1,
+  "model_layer_cls_name": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "per_device_train_batch_size": null,
+  "per_device_eval_batch_size": null,
+  "eval_strategy": null,
+  "self_cognition_sample": 0,
+  "train_dataset_mix_ratio": 0.0,
+  "train_dataset_mix_ds": [
+    "ms-bench"
+  ],
+  "train_dataset_sample": -1,
+  "val_dataset_sample": null,
+  "safe_serialization": null,
+  "only_save_model": null,
+  "neftune_alpha": null,
+  "deepspeed_config_path": null,
+  "model_cache_dir": null,
+  "lora_dropout_p": null,
+  "lora_target_modules": [],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
+  "custom_train_dataset_path": [],
+  "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
+  "rlhf_type": "dpo",
+  "ref_model_type": null,
+  "ref_model_id_or_path": null,
+  "ref_model_revision": null,
+  "beta": 0.1,
+  "label_smoothing": 0.0,
+  "loss_type": "sigmoid",
+  "rpo_alpha": 0.1,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "reward_model_id_or_path": null,
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "local_rollout_forward_batch_size": 64,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_sample_generations": 10,
+  "ref_model_free": false,
+  "use_self_cognition": false,
+  "is_multimodal": true,
+  "is_vision": true,
+  "lora_use_embedding": false,
+  "lora_use_all": false,
+  "lora_m2s_use_embedding": false,
+  "lora_m2s_use_ln": false,
+  "torch_dtype": "torch.bfloat16",
+  "fp16": false,
+  "bf16": true,
+  "rank": -1,
+  "local_rank": -1,
+  "world_size": 1,
+  "local_world_size": 1,
+  "bnb_4bit_compute_dtype": "torch.bfloat16",
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "train_sampler_random": true,
+  "train_type": "dpo",
+  "training_args": "DPOConfig(output_dir='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=5, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, beta=0.1, label_smoothing=0.0, loss_type='sigmoid', label_pad_token_id=-100, padding_value=None, truncation_mode='keep_end', max_length=None, max_prompt_length=None, max_target_length=None, max_completion_length=None, is_encoder_decoder=None, disable_dropout=True, generate_during_eval=False, precompute_ref_log_probs=False, dataset_num_proc=None, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, reference_free=False, force_use_ref_model=False, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, sync_ref_model=False, ref_model_mixup_alpha=0.9, ref_model_sync_steps=64, rpo_alpha=0.1, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)"
+}

checkpoint-20-merged/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-20-merged/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-20-merged/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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 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 %}{{ message['content'] }}<|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 %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-20/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /home/ec2-user/.cache/modelscope/hub/qwen/Qwen2-VL-2B-Instruct
+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 0.12.0

checkpoint-20/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/ec2-user/.cache/modelscope/hub/qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-20/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b6899e250356c6632d0121dc77edb5ffb4c8127f340a2d51aba694000d7a9a
+size 36981072

checkpoint-20/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

checkpoint-20/configuration.json

@@ -0,0 +1,14 @@
+{
+    "framework": "pytorch",
+    "task": "image-text-to-text",
+    "allow_remote": true,
+    "adapter_cfg": {
+        "model_id_or_path": "qwen/Qwen2-VL-2B-Instruct",
+        "model_revision": "master",
+        "sft_type": "lora",
+        "tuner_backend": "peft",
+        "template_type": "qwen2-vl",
+        "dtype": "bf16",
+        "system": null
+    }
+}

checkpoint-20/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.47.0"
+}

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e67c823ceaedec86ab62de462ac7c86959daff9cce82588067b9000a32ad209
+size 74188650

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4b34a50c55a680830f99a77a52585bb05290e33d30ce86746475157ba56d09
+size 1064

checkpoint-20/sft_args.json

@@ -0,0 +1,273 @@
+{
+  "model_type": "qwen2-vl-2b-instruct",
+  "model_id_or_path": "qwen/Qwen2-VL-2B-Instruct",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "lora",
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "qwen2-vl",
+  "output_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947",
+  "add_output_dir_suffix": true,
+  "ddp_backend": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
+  "seed": 42,
+  "resume_from_checkpoint": null,
+  "resume_only_model": false,
+  "ignore_data_skip": false,
+  "dtype": "bf16",
+  "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": {},
+  "loss_name": null,
+  "dataset": [
+    "/home/ec2-user/train.jsonl"
+  ],
+  "val_dataset": [
+    "/home/ec2-user/val.jsonl"
+  ],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.0,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/opt/conda/envs/old/lib/python3.10/site-packages/swift/llm/agent/default_loss_scale_config.json",
+  "system": null,
+  "tools_prompt": "react_en",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "check_dataset_strategy": "none",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    null
+  ],
+  "quant_method": null,
+  "quantization_bit": 0,
+  "hqq_axis": 0,
+  "hqq_dynamic_config_path": null,
+  "bnb_4bit_comp_dtype": "bf16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "rescale_image": -1,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias_trainable": "none",
+  "lora_dtype": null,
+  "lora_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "rope_scaling": null,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "ia3_feedforward_modules": [],
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "neftune_noise_alpha": null,
+  "neftune_backend": "transformers",
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
+  "gradient_checkpointing": true,
+  "vit_use_gc": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 5,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 5e-05,
+  "weight_decay": 0.1,
+  "gradient_accumulation_steps": 8,
+  "max_grad_norm": 1,
+  "predict_with_generate": false,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.03,
+  "warmup_steps": 0,
+  "eval_steps": 50,
+  "save_steps": 50,
+  "save_only_model": false,
+  "save_total_limit": 2,
+  "logging_steps": 5,
+  "acc_steps": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_drop_last": false,
+  "push_to_hub": false,
+  "hub_model_id": null,
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_strategy": "every_save",
+  "test_oom_error": false,
+  "disable_tqdm": false,
+  "lazy_tokenize": true,
+  "preprocess_num_proc": 1,
+  "use_flash_attn": null,
+  "ignore_args_error": false,
+  "check_model_is_latest": true,
+  "logging_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/runs",
+  "report_to": [
+    "tensorboard"
+  ],
+  "acc_strategy": "token",
+  "save_on_each_node": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps",
+  "save_safetensors": true,
+  "gpu_memory_fraction": null,
+  "include_num_input_tokens_seen": false,
+  "local_repo_path": null,
+  "custom_register_path": null,
+  "custom_dataset_info": null,
+  "device_map_config": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "fsdp": "",
+  "fsdp_config": null,
+  "sequence_parallel_size": 1,
+  "model_layer_cls_name": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "per_device_train_batch_size": null,
+  "per_device_eval_batch_size": null,
+  "eval_strategy": null,
+  "self_cognition_sample": 0,
+  "train_dataset_mix_ratio": 0.0,
+  "train_dataset_mix_ds": [
+    "ms-bench"
+  ],
+  "train_dataset_sample": -1,
+  "val_dataset_sample": null,
+  "safe_serialization": null,
+  "only_save_model": null,
+  "neftune_alpha": null,
+  "deepspeed_config_path": null,
+  "model_cache_dir": null,
+  "lora_dropout_p": null,
+  "lora_target_modules": [],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
+  "custom_train_dataset_path": [],
+  "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
+  "rlhf_type": "dpo",
+  "ref_model_type": null,
+  "ref_model_id_or_path": null,
+  "ref_model_revision": null,
+  "beta": 0.1,
+  "label_smoothing": 0.0,
+  "loss_type": "sigmoid",
+  "rpo_alpha": 0.1,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "reward_model_id_or_path": null,
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "local_rollout_forward_batch_size": 64,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_sample_generations": 10,
+  "ref_model_free": false,
+  "use_self_cognition": false,
+  "is_multimodal": true,
+  "is_vision": true,
+  "lora_use_embedding": false,
+  "lora_use_all": false,
+  "lora_m2s_use_embedding": false,
+  "lora_m2s_use_ln": false,
+  "torch_dtype": "torch.bfloat16",
+  "fp16": false,
+  "bf16": true,
+  "rank": -1,
+  "local_rank": -1,
+  "world_size": 1,
+  "local_world_size": 1,
+  "bnb_4bit_compute_dtype": "torch.bfloat16",
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "train_sampler_random": true,
+  "train_type": "dpo",
+  "training_args": "DPOConfig(output_dir='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=5, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, beta=0.1, label_smoothing=0.0, loss_type='sigmoid', label_pad_token_id=-100, padding_value=None, truncation_mode='keep_end', max_length=None, max_prompt_length=None, max_target_length=None, max_completion_length=None, is_encoder_decoder=None, disable_dropout=True, generate_during_eval=False, precompute_ref_log_probs=False, dataset_num_proc=None, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, reference_free=False, force_use_ref_model=False, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, sync_ref_model=False, ref_model_mixup_alpha=0.9, ref_model_sync_steps=64, rpo_alpha=0.1, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)"
+}

checkpoint-20/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": 0.26913971,
+  "best_model_checkpoint": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/checkpoint-20",
+  "epoch": 4.0,
+  "eval_steps": 50,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 47.92485809326172,
+      "learning_rate": 5e-05,
+      "logits/chosen": -1.8237018585205078,
+      "logits/rejected": -1.9020615816116333,
+      "logps/chosen": -191.52467346191406,
+      "logps/rejected": -212.57785034179688,
+      "loss": 5.88650322,
+      "memory(GiB)": 30.84,
+      "nll_loss": 0.42665722966194153,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1,
+      "train_speed(iter/s)": 0.018393
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.606019973754883,
+      "learning_rate": 4.4728512734909844e-05,
+      "logits/chosen": -1.8926528692245483,
+      "logits/rejected": -1.9645055532455444,
+      "logps/chosen": -195.32687377929688,
+      "logps/rejected": -217.2638702392578,
+      "loss": 4.4658556,
+      "memory(GiB)": 31.66,
+      "nll_loss": 0.43571263551712036,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": 0.321090966463089,
+      "rewards/margins": 0.17073126137256622,
+      "rewards/rejected": 0.15035970509052277,
+      "step": 5,
+      "train_speed(iter/s)": 0.020714
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.947022914886475,
+      "learning_rate": 2.7064483636808313e-05,
+      "logits/chosen": -1.8044353723526,
+      "logits/rejected": -1.8731192350387573,
+      "logps/chosen": -175.5177764892578,
+      "logps/rejected": -212.43545532226562,
+      "loss": 1.8374548,
+      "memory(GiB)": 26.6,
+      "nll_loss": 0.3899259567260742,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.1417019367218018,
+      "rewards/margins": 1.649977684020996,
+      "rewards/rejected": 0.49172407388687134,
+      "step": 10,
+      "train_speed(iter/s)": 0.021154
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7851582765579224,
+      "learning_rate": 8.067960709356478e-06,
+      "logits/chosen": -1.728115200996399,
+      "logits/rejected": -1.7883909940719604,
+      "logps/chosen": -163.91143798828125,
+      "logps/rejected": -218.22042846679688,
+      "loss": 0.79830809,
+      "memory(GiB)": 26.6,
+      "nll_loss": 0.36455366015434265,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3023338317871094,
+      "rewards/margins": 3.389106035232544,
+      "rewards/rejected": -0.08677242696285248,
+      "step": 15,
+      "train_speed(iter/s)": 0.021297
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.076888084411621,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.695635199546814,
+      "logits/rejected": -1.7527247667312622,
+      "logps/chosen": -159.94375610351562,
+      "logps/rejected": -223.05526733398438,
+      "loss": 0.61259127,
+      "memory(GiB)": 26.6,
+      "nll_loss": 0.3550187349319458,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.699101448059082,
+      "rewards/margins": 4.269360065460205,
+      "rewards/rejected": -0.5702579617500305,
+      "step": 20,
+      "train_speed(iter/s)": 0.021369
+    },
+    {
+      "epoch": 4.0,
+      "eval_logits/chosen": -1.8032017946243286,
+      "eval_logits/rejected": -1.8270058631896973,
+      "eval_logps/chosen": -159.05787658691406,
+      "eval_logps/rejected": -185.4047393798828,
+      "eval_loss": 0.26913970708847046,
+      "eval_nll_loss": 0.4101408123970032,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.333481788635254,
+      "eval_rewards/margins": 1.5688062906265259,
+      "eval_rewards/rejected": 1.764675498008728,
+      "eval_runtime": 80.7016,
+      "eval_samples_per_second": 0.186,
+      "eval_steps_per_second": 0.186,
+      "step": 20
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4272401148051456.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b3cc2e442f1d48eebf11e4ff601fa10823b88aca4fbfe12b96c03c228c699a
+size 8568