skumar1998 commited on
Commit
dd3ec66
·
verified ·
1 Parent(s): 525ae02

Training in progress, step 60

Browse files
README.md CHANGED
@@ -1,17 +1,18 @@
1
  ---
2
- base_model: 314e/dexit-VLM-Gemma3-Entity-test5-integration
3
  library_name: transformers
4
  model_name: result
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - sft
 
 
9
  licence: license
10
  ---
11
 
12
  # Model Card for result
13
 
14
- This model is a fine-tuned version of [314e/dexit-VLM-Gemma3-Entity-test5-integration](https://huggingface.co/314e/dexit-VLM-Gemma3-Entity-test5-integration).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -30,15 +31,16 @@ print(output["generated_text"])
30
 
31
 
32
 
 
33
  This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
- - TRL: 0.13.0
38
- - Transformers: 4.51.1
39
- - Pytorch: 2.5.1
40
- - Datasets: 3.2.0
41
- - Tokenizers: 0.21.0
42
 
43
  ## Citations
44
 
@@ -47,12 +49,11 @@ This model was trained with SFT.
47
  Cite TRL as:
48
 
49
  ```bibtex
50
- @misc{vonwerra2022trl,
51
- title = {{TRL: Transformer Reinforcement Learning}},
52
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
- year = 2020,
54
- journal = {GitHub repository},
55
- publisher = {GitHub},
56
- howpublished = {\url{https://github.com/huggingface/trl}}
57
  }
58
  ```
 
1
  ---
2
+ base_model: Qwen/Qwen3.5-9b
3
  library_name: transformers
4
  model_name: result
5
  tags:
6
  - generated_from_trainer
 
7
  - sft
8
+ - unsloth
9
+ - trl
10
  licence: license
11
  ---
12
 
13
  # Model Card for result
14
 
15
+ This model is a fine-tuned version of [Qwen/Qwen3.5-9b](https://huggingface.co/Qwen/Qwen3.5-9b).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
 
31
 
32
 
33
 
34
+
35
  This model was trained with SFT.
36
 
37
  ### Framework versions
38
 
39
+ - TRL: 1.9.0
40
+ - Transformers: 5.14.1
41
+ - Pytorch: 2.7.1
42
+ - Datasets: 4.3.0
43
+ - Tokenizers: 0.22.2
44
 
45
  ## Citations
46
 
 
49
  Cite TRL as:
50
 
51
  ```bibtex
52
+ @software{vonwerra2020trl,
53
+ title = {{TRL: Transformers Reinforcement Learning}},
54
+ author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
55
+ license = {Apache-2.0},
56
+ url = {https://github.com/huggingface/trl},
57
+ year = {2020}
 
58
  }
59
  ```
adapter_config.json CHANGED
@@ -1,8 +1,16 @@
1
  {
 
2
  "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "314e/dexit-VLM-Gemma3-Entity-test5-integration",
 
 
 
 
 
5
  "bias": "none",
 
 
6
  "eva_config": null,
7
  "exclude_modules": null,
8
  "fan_in_fan_out": false,
@@ -15,23 +23,22 @@
15
  "lora_alpha": 256,
16
  "lora_bias": false,
17
  "lora_dropout": 0.05,
 
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
  "modules_to_save": null,
21
  "peft_type": "LORA",
22
- "r": 126,
 
 
23
  "rank_pattern": {},
24
  "revision": null,
25
- "target_modules": [
26
- "v_proj",
27
- "q_proj",
28
- "up_proj",
29
- "down_proj",
30
- "o_proj",
31
- "k_proj",
32
- "gate_proj"
33
- ],
34
  "task_type": "CAUSAL_LM",
 
 
35
  "use_dora": false,
 
36
  "use_rslora": false
37
  }
 
1
  {
2
+ "alora_invocation_tokens": null,
3
  "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForConditionalGeneration",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "Qwen/Qwen3.5-9b",
11
  "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
  "eva_config": null,
15
  "exclude_modules": null,
16
  "fan_in_fan_out": false,
 
23
  "lora_alpha": 256,
24
  "lora_bias": false,
25
  "lora_dropout": 0.05,
26
+ "lora_ga_config": null,
27
  "megatron_config": null,
28
  "megatron_core": "megatron.core",
29
  "modules_to_save": null,
30
  "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 128,
34
  "rank_pattern": {},
35
  "revision": null,
36
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
37
+ "target_parameters": null,
 
 
 
 
 
 
 
38
  "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_bdlora": null,
41
  "use_dora": false,
42
+ "use_qalora": false,
43
  "use_rslora": false
44
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:112272277225b2c1516714e8de3608f213cba3a6c084a773c35c1f48ffd9800f
3
- size 2156507696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6499fa033031268113192ba77d65db5b398026bd045c1ab653012c6edf1025b3
3
+ size 1631412872
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
distribution.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "facesheet": 184
3
+ }
doctype_entity_distribution.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "facesheet": {
3
+ "patient.first_name": 184,
4
+ "patient.last_name": 173,
5
+ "patient.middle_name": 45,
6
+ "facility.city": 102,
7
+ "facility.state": 109,
8
+ "facility.zip": 127,
9
+ "patient.city": 96,
10
+ "patient.state": 106,
11
+ "patient.zip": 117,
12
+ "patient.address": 83,
13
+ "phone_number": 51,
14
+ "facility.address": 81,
15
+ "facility.name": 88,
16
+ "medicaid_insurance_number": 41,
17
+ "medicare_insurance_number": 45,
18
+ "patient.dob": 73,
19
+ "patient.sex": 87,
20
+ "social_security_number": 31,
21
+ "accession_number": 13,
22
+ "collection_date": 27,
23
+ "provider_npi": 29,
24
+ "sample_code": 29,
25
+ "other_insurance_name_1": 34,
26
+ "other_insurance_number_1": 30,
27
+ "other_insurance_name_2": 2,
28
+ "other_insurance_number_2": 2
29
+ }
30
+ }
entity_distribution.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "patient.first_name": 184,
3
+ "patient.last_name": 173,
4
+ "patient.middle_name": 45,
5
+ "facility.city": 102,
6
+ "facility.state": 109,
7
+ "facility.zip": 127,
8
+ "patient.city": 96,
9
+ "patient.state": 106,
10
+ "patient.zip": 117,
11
+ "patient.address": 83,
12
+ "phone_number": 51,
13
+ "facility.address": 81,
14
+ "facility.name": 88,
15
+ "medicaid_insurance_number": 41,
16
+ "medicare_insurance_number": 45,
17
+ "patient.dob": 73,
18
+ "patient.sex": 87,
19
+ "social_security_number": 31,
20
+ "accession_number": 13,
21
+ "collection_date": 27,
22
+ "provider_npi": 29,
23
+ "sample_code": 29,
24
+ "other_insurance_name_1": 34,
25
+ "other_insurance_number_1": 30,
26
+ "other_insurance_name_2": 2,
27
+ "other_insurance_number_2": 2
28
+ }
file.log ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-07-24 07:02:42.293 | INFO | app.tasks.entity.vlm.dataset:create:650 - Using pre-split dataset mode
2
+ 2026-07-24 07:02:42.320 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1565 - Downloading train dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/train.json
3
+ 2026-07-24 07:02:42.626 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1422 - Processing %s %s/%s with %d documents
4
+ 2026-07-24 07:02:43.881 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1565 - Downloading val dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/eval.json
5
+ 2026-07-24 07:02:44.108 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1422 - Processing %s %s/%s with %d documents
6
+ 2026-07-24 07:02:44.486 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1565 - Downloading test dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/test.json
7
+ 2026-07-24 07:02:44.667 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1422 - Processing %s %s/%s with %d documents
8
+ 2026-07-24 07:02:45.048 | INFO | app.tasks.entity.vlm.dataset:_download_miscellaneous:1612 - Downloading miscellaneous data from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/miscellaneous.json
9
+ 2026-07-24 07:02:45.236 | INFO | app.tasks.entity.vlm.dataset:_download_previous_datasets:1521 - Found 0 previous dataset(s) to consolidate
10
+ 2026-07-24 07:02:45.237 | INFO | app.tasks.entity.vlm.dataset:download_presplit_datasets:1663 - Successfully downloaded all datasets to /home/ubuntu/dataset
11
+ 2026-07-24 07:02:45.791 | INFO | app.tasks.entity.vlm.dataset:remove_null_files:574 - Removed 1 files with null values
12
+ 2026-07-24 07:02:45.844 | INFO | app.tasks.entity.vlm.reports:get_distribution:1513 - Original number of ground truth files 184
13
+ 2026-07-24 07:02:46.012 | INFO | app.tasks.entity.vlm.reports:get_distribution:1528 - After removing empty files 184
14
+ 2026-07-24 07:02:46.023 | INFO | app.tasks.entity.vlm.reports:get_entity_distribution:1628 - Creating entity distribution for 184 files
15
+ 2026-07-24 07:02:46.363 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
16
+ 2026-07-24 07:02:46.661 | DEBUG | app.commonmlops:get_training_job_queue:891 - Get training job queue status code: 200, api_url: https://aitest.api.dexit.tech/api/v1/mlops/trainingjobqueue/06a629ad-0d3a-795c-8000-dc597c9a9e03
17
+ 2026-07-24 07:02:46.874 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
18
+ 2026-07-24 07:02:46.875 | DEBUG | app.commonmlops:update_training_job_queue:937 - Updating training job queue with merged payload: {'id': '06a629ad-0d3a-795c-8000-dc597c9a9e03', 'modeltype': 'entity', 'modelname': 'vlm_qwen3_5', 'jobtype': 'feedback', 'basemodelversionid': '019f0d56-3844-7c0a-8fab-4aa6a6d1f12e', 'datasetid': '06a629a7-dc39-751c-8000-5e635f470d7a', 'status': 'triggered', 'createddate': '2026-07-23T22:50:56.826848Z', 'createdby': '00000000-0000-0000-0000-000000000000', 'startdate': '2026-07-24T07:02:12.215188Z', 'enddate': None, 'accuracyreport': None, 'metadata': {'clearml_details': {'hf_model_id': '314e/dexit-aitest-vlm_qwen3_5-entity-integration', 'clearml_task_id': '3c76a36747f24e0e8bb6fd18f8081c84', 'trained_entities': ['accession_number', 'collection_date', 'facility.address', 'facility.city', 'facility.name', 'facility.state', 'facility.zip', 'medicaid_insurance_number', 'medicare_insurance_number', 'other_insurance_name_1', 'other_insurance_name_2', 'other_insurance_number_1', 'other_insurance_number_2', 'patient.address', 'patient.city', 'patient.dob', 'patient.first_name', 'patient.last_name', 'patient.middle_name', 'patient.sex', 'patient.state', 'patient.zip', 'phone_number', 'provider_npi', 'sample_code', 'social_security_number'], 'new_modelversion_tag': 'v0.0.0', 'base_modelversion_tag': 'v0.0.0'}, 'hyperparameters': {'DATASET_PARAMS': {'DATASET__EVAL_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/eval.json', 'DATASET__TEST_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/test.json', 'DATASET__TRAIN_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/train.json', 'DATASET__MISCELLANEOUS_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a629a7-dc39-751c-8000-5e635f470d7a/miscellaneous.json'}, 'MODEL_CONFIGURATION': {'SEED': 42, 'MODELNAME': 'vlm_qwen3_5', 'MODELTYPE': 'entity', 'ENVIRONMENT': 'integration', 'HF_MODEL_ID': '314e/dexit-aitest-vlm_qwen3_5-entity-integration', 'MODEL_FAMILY': 'qwen', 'ARTIFACTS_DIR': '/home/ubuntu/result', 'MODELVERSIONTAG': 'v0.0.0', 'HF_BASE_MODEL_ID': 'Qwen/Qwen3.5-9b', 'IMAGE_PATCH_SIZE': 16, 'THRESHOLD_OFFSET': 0.05, 'TRAIN_OOTB_MODEL': True, 'NEW_MODELVERSIONTAG': 'v0.0.0'}, 'MODEL_HYPERPARAMETERS': {'RANK': 128, 'ALPHA': 256, 'TRAIN_EPOCHS': 10, 'EVAL_BATCH_SIZE': 2, 'GRAD_ACCUM_STEPS': 4, 'TRAIN_BATCH_SIZE': 2, 'INFERENCE_BATCH_SIZE': 2}}, 'workflow_details': {'temporal_workflow_id': 'local-model-retraining-entity-ddde4bff', 'skypilot_cluster_name': 'dexit-aitest-skypilot-entity-1784876009-69301', 'temporal_workflow_run_id': '019f92e6-5dfc-73e6-afd1-ae9142d3bb2d'}, 'modelconfig_snapshot': {'modelname': 'vlm_qwen3_5', 'modeltype': 'entity', 'deployment': {'auto_model_deployment_manual': False, 'auto_model_deployment_feedback': False}, 'feedback_config': {'bucket_low': 0.5, 'bucket_high': 0.7, 'auto_trigger_retraining': True, 'non_corrected_sample_ratio': 0.5, 'min_feedback_count_for_retraining': 1500, 'low_bucket_threshold_offset_multiplier': 0.5, 'auto_trigger_retraining_on_new_entities': False, 'high_bucket_threshold_offset_multiplier': 1.5, 'low_precision_bucket_corrected_sample_rate': 0.8, 'mid_precision_bucket_corrected_sample_rate': 0.5, 'high_precision_bucket_corrected_sample_rate': 0.2, 'low_precision_bucket_threshold_sample_count': 100}, 'training_config': {'seed': 42, 'dataset': {'eval_size': 0.1, 'test_size': 0.2, 'train_size': 0.7}, 'cloud_providers': [{'accelerators': ['A100-80GB:1', 'H100:1'], 'provider_name': 'runpod'}], 'hyperparameters': {'rank': 128, 'alpha': 256, 'train_epochs': 10, 'grad_accum_steps': 4, 'train_batch_size': 2}, 'hf_base_model_id': 'Qwen/Qwen3.5-9b', 'train_ootb_model': True, 'previous_datasets': {'eval': {'enabled': True, 'distribution': {'weights': {'n-1': 1.0}, 'strategy': 'equal', 'decay_factor': 0.8}, 'max_versions_to_include': 'all'}, 'test': {'enabled': True, 'distribution': {'weights': {'n-1': 1.0}, 'strategy': 'equal', 'decay_factor': 0.8}, 'max_versions_to_include': 'all'}, 'train': {'enabled': True, 'distribution': {'weights': {'n-1': 1.0}, 'strategy': 'equal', 'decay_factor': 0.8}, 'max_versions_to_include': 'all'}}}, 'threshold_offset': 0.05}}, 'deploymentstatus': None, 'deployeddate': None}
19
+ 2026-07-24 07:02:47.112 | DEBUG | app.commonmlops:update_training_job_queue:940 - Update training job queue status code: 200, api_url: https://aitest.api.dexit.tech/api/v1/mlops/trainingjobqueue/06a629ad-0d3a-795c-8000-dc597c9a9e03
20
+ 2026-07-24 07:02:47.113 | SUCCESS | app.commonmlops:update_trained_entities:979 - Updated trained_entities on training job queue
21
+ 2026-07-24 07:02:47.476 | INFO | app.tasks.entity.vlm.reports:upload_initial_artifacts:1696 - Uploaded intial artifacts to ClearML
22
+ 2026-07-24 07:02:47.476 | INFO | __main__:_run_training_phase:657 - Moving into standard training loop
23
+ 2026-07-24 07:02:47.477 | INFO | __main__:setup_directories:211 - Loading pre-split dataset statistics
24
+ 2026-07-24 07:02:47.557 | INFO | __main__:load_presplit_statistics:188 - Found 161 training samples
25
+ 2026-07-24 07:02:47.595 | INFO | __main__:load_presplit_statistics:190 - Found 20 test samples
26
+ 2026-07-24 07:02:47.625 | INFO | __main__:load_presplit_statistics:192 - Found 3 validation samples
27
+ 2026-07-24 07:02:47.626 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:986 -
28
+ Dataset Split Statistics:
29
+ 2026-07-24 07:02:47.626 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:987 - Total samples: 184
30
+ 2026-07-24 07:02:47.626 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:989 - Train set: 161 (87.5%)
31
+ 2026-07-24 07:02:47.627 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:990 - Test set: 20 (10.9%)
32
+ 2026-07-24 07:02:47.627 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:991 - Validation set: 3 (1.6%)
33
+ 2026-07-24 07:02:47.628 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1000 - Split statistics saved to /home/ubuntu/result/split_statistics.json
34
+ 2026-07-24 07:02:47.632 | INFO | __main__:standard_training_loop:354 - Initializing model
35
+ 2026-07-24 07:02:47.633 | INFO | __main__:initialize_model:243 - Setting up model for retraining
36
+ 2026-07-24 07:02:47.633 | INFO | __main__:initialize_model:246 - Training from base model: Qwen/Qwen3.5-9b
37
+ 2026-07-24 07:02:47.633 | INFO | app.tasks.entity.vlm.model:__post_init__:220 - loading model Qwen/Qwen3.5-9b for training with unsloth
38
+ 2026-07-24 07:03:33.040 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:316 - num_samples: 161, batch_size: 2, gradient_accumulation_steps: 4, epochs: 10
39
+ 2026-07-24 07:03:33.040 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:320 - calculating max steps
40
+ 2026-07-24 07:03:33.071 | INFO | __main__:standard_training_loop:357 - Setting up trainer
41
+ 2026-07-24 07:03:46.968 | INFO | __main__:create_trainer:306 - Materialized datasets: 161 train, 3 eval samples
42
+ 2026-07-24 07:03:47.468 | INFO | __main__:standard_training_loop:360 - Starting training
43
+ 2026-07-24 07:03:47.660 | INFO | app.tasks.entity.vlm.model:train_model:521 - everything is set up, launching training
ground_truth_data.json ADDED
The diff for this file is too large to render. See raw diff
 
gt_json.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "gt_jsons": [
3
+ "/home/ubuntu/dataset/train/facesheet/069fc3f4-80d1-7ede-8000-97fe3064edd8.json",
4
+ "/home/ubuntu/dataset/train/facesheet/069f971d-7ece-7081-8000-ccca54976aba.json",
5
+ "/home/ubuntu/dataset/train/facesheet/069f43d0-c180-7585-8000-f27ab589f9c5.json",
6
+ "/home/ubuntu/dataset/train/facesheet/069f42ca-9043-73e9-8000-8b19883174fc.json",
7
+ "/home/ubuntu/dataset/train/facesheet/0696090f-e348-7e54-8000-7263290f952c.json",
8
+ "/home/ubuntu/dataset/train/facesheet/069f98c4-585f-79f5-8000-d35c11d30866.json",
9
+ "/home/ubuntu/dataset/train/facesheet/069f42c1-fb91-7537-8000-ea091797d5fa.json",
10
+ "/home/ubuntu/dataset/train/facesheet/069fd7ed-3c6c-7a94-8000-382c5c5857ec.json",
11
+ "/home/ubuntu/dataset/train/facesheet/069f43cf-f8be-7593-8000-705da22b6e05.json",
12
+ "/home/ubuntu/dataset/train/facesheet/069f971b-a053-7bb1-8000-8efbff581cc4.json",
13
+ "/home/ubuntu/dataset/train/facesheet/069f8316-7bef-782d-8000-80fcd6aee0c9.json",
14
+ "/home/ubuntu/dataset/train/facesheet/069f96d8-342a-7b14-8000-6b7f909ae1d9.json",
15
+ "/home/ubuntu/dataset/train/facesheet/069f42cb-47d7-7d7d-8000-f58c1edaf762.json",
16
+ "/home/ubuntu/dataset/train/facesheet/069f43cf-f8be-72c9-8000-1ae2572805ec.json",
17
+ "/home/ubuntu/dataset/train/facesheet/069f4398-025d-7fa2-8000-9069e9233766.json",
18
+ "/home/ubuntu/dataset/train/facesheet/069f9068-eb5a-7da7-8000-612e8039adf6.json",
19
+ "/home/ubuntu/dataset/train/facesheet/069fc256-b7d4-74c8-8000-d12b68fdb7fc.json",
20
+ "/home/ubuntu/dataset/train/facesheet/069fd72b-2374-7de1-8000-1d67a5c30399.json",
21
+ "/home/ubuntu/dataset/train/facesheet/069fc157-4bf5-78a5-8000-efaec9d5e8ff.json",
22
+ "/home/ubuntu/dataset/train/facesheet/069f97fe-7c33-734f-8000-e00304e204bd.json",
23
+ "/home/ubuntu/dataset/train/facesheet/069f42c7-0a69-7b38-8000-e1eef6b3ee9c.json",
24
+ "/home/ubuntu/dataset/train/facesheet/069f4399-a6f6-71ff-8000-ff9fa29d81d0.json",
25
+ "/home/ubuntu/dataset/train/facesheet/069f9648-2181-75ec-8000-829a21073fc6.json",
26
+ "/home/ubuntu/dataset/train/facesheet/069fd678-c873-766c-8000-738ae96d210d.json",
27
+ "/home/ubuntu/dataset/train/facesheet/069f43ce-4495-7b0d-8000-6e8f698f2271.json",
28
+ "/home/ubuntu/dataset/train/facesheet/069f4394-6192-7338-8000-a0b6281afe25.json",
29
+ "/home/ubuntu/dataset/train/facesheet/069f96d7-bf11-70d6-8000-8cf96a27e819.json",
30
+ "/home/ubuntu/dataset/train/facesheet/069f434b-b10a-7779-8000-e22aaafd130f.json",
31
+ "/home/ubuntu/dataset/train/facesheet/069f43a2-a15f-7f44-8000-b897bc6225d9.json",
32
+ "/home/ubuntu/dataset/train/facesheet/069f42c9-e8e6-71d6-8000-883d908dfa99.json",
33
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b73-7c37-8000-3877958f442f.json",
34
+ "/home/ubuntu/dataset/train/facesheet/069f43cf-4e99-7174-8000-cf63ccf647d5.json",
35
+ "/home/ubuntu/dataset/train/facesheet/069f42c1-b2b0-73eb-8000-9a8ea05b3df3.json",
36
+ "/home/ubuntu/dataset/train/facesheet/069f96d9-1061-7c0f-8000-a58b1288456e.json",
37
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b74-7bb2-8000-dcbae7262f43.json",
38
+ "/home/ubuntu/dataset/train/facesheet/069fd777-9fee-728f-8000-7a02da4950d4.json",
39
+ "/home/ubuntu/dataset/train/facesheet/0696090f-dbc1-75bc-8000-c4b4b4515ddf.json",
40
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b74-7f6b-8000-6e90a2aacfef.json",
41
+ "/home/ubuntu/dataset/train/facesheet/069f4399-a6f6-70a8-8000-3d6589857300.json",
42
+ "/home/ubuntu/dataset/train/facesheet/069f9693-a523-7a28-8000-af9b0a95624f.json",
43
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b75-784a-8000-edb4aea62da5.json",
44
+ "/home/ubuntu/dataset/train/facesheet/069f4395-281e-7bd2-8000-64313e026600.json",
45
+ "/home/ubuntu/dataset/train/facesheet/069f43a4-01b2-79e6-8000-80f72e40de3b.json",
46
+ "/home/ubuntu/dataset/train/facesheet/069f9698-7ab2-72eb-8000-07f589620034.json",
47
+ "/home/ubuntu/dataset/train/facesheet/069f42cd-14e1-7844-8000-1c68c76d4700.json",
48
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b74-7dfa-8000-36731e2c43ff.json",
49
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b74-76ca-8000-b4da8e9c5598.json",
50
+ "/home/ubuntu/dataset/train/facesheet/069fc204-94e8-7f05-8000-18d66135039e.json",
51
+ "/home/ubuntu/dataset/train/facesheet/069fd675-e8ce-7c40-8000-a938cd0574b3.json",
52
+ "/home/ubuntu/dataset/train/facesheet/069f9697-c07a-73da-8000-6d1d6533eb32.json",
53
+ "/home/ubuntu/dataset/train/facesheet/0696090f-dbc1-73c3-8000-d7b19c52f74b.json",
54
+ "/home/ubuntu/dataset/train/facesheet/069fc255-4901-707d-8000-be50fa96eb68.json",
55
+ "/home/ubuntu/dataset/train/facesheet/069f43ce-8bef-71de-8000-3fda945fd12c.json",
56
+ "/home/ubuntu/dataset/train/facesheet/069f971d-7ece-7045-8000-35f027206aa1.json",
57
+ "/home/ubuntu/dataset/train/facesheet/0696485a-1715-7936-8000-1e6ad1a0f4ab.json",
58
+ "/home/ubuntu/dataset/train/facesheet/069fd72c-2f29-7a1a-8000-5c19766519ef.json",
59
+ "/home/ubuntu/dataset/train/facesheet/069f971d-7ecd-7ffd-8000-263c8babf092.json",
60
+ "/home/ubuntu/dataset/train/facesheet/069f97fd-a338-7bac-8000-dd4f65a47683.json",
61
+ "/home/ubuntu/dataset/train/facesheet/069f4399-08bd-79a2-8000-fa13debfba45.json",
62
+ "/home/ubuntu/dataset/train/facesheet/069f43d0-c180-75c3-8000-3519652d3492.json",
63
+ "/home/ubuntu/dataset/train/facesheet/069f98c4-d914-7605-8000-04acc21bb448.json",
64
+ "/home/ubuntu/dataset/train/facesheet/069f971a-dae7-7b28-8000-6547e11e8479.json",
65
+ "/home/ubuntu/dataset/train/facesheet/069f42ca-9043-7270-8000-88784881956b.json",
66
+ "/home/ubuntu/dataset/train/facesheet/069f9693-0ed8-7690-8000-8a73dba85b64.json",
67
+ "/home/ubuntu/dataset/train/facesheet/0696090f-d74e-771f-8000-e15b4c943d8c.json",
68
+ "/home/ubuntu/dataset/train/facesheet/069f434c-6e72-772d-8000-0dd167582ce7.json",
69
+ "/home/ubuntu/dataset/train/facesheet/069f9885-b67a-7e30-8000-d3363930f849.json",
70
+ "/home/ubuntu/dataset/train/facesheet/069f43d0-5dbc-7dcf-8000-3310b691c296.json",
71
+ "/home/ubuntu/dataset/train/facesheet/069e9a54-493b-7632-8000-16d2094a8063.json",
72
+ "/home/ubuntu/dataset/train/facesheet/069fc2b2-fb7c-7918-8000-bcd53f5a41a0.json",
73
+ "/home/ubuntu/dataset/train/facesheet/069f43a4-01b2-7a36-8000-6f4d2539df97.json",
74
+ "/home/ubuntu/dataset/train/facesheet/069f971a-dae7-7bbc-8000-aa4dfbc79614.json",
75
+ "/home/ubuntu/dataset/train/facesheet/069f434b-b10a-7895-8000-839d17ebeb2e.json",
76
+ "/home/ubuntu/dataset/train/facesheet/069f96d8-342a-7c53-8000-00e8da9afee1.json",
77
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b74-717a-8000-f76a1a2dfa74.json",
78
+ "/home/ubuntu/dataset/train/facesheet/069fc449-726b-72da-8000-40c5e3226cb0.json",
79
+ "/home/ubuntu/dataset/train/facesheet/069f43a2-a158-737f-8000-6d42a06c5ff5.json",
80
+ "/home/ubuntu/dataset/train/facesheet/069fbe25-07f8-7624-8000-16d54e830b03.json",
81
+ "/home/ubuntu/dataset/train/facesheet/069fc164-5836-78f7-8000-6a5338c36bfc.json",
82
+ "/home/ubuntu/dataset/train/facesheet/069f97fd-a338-7bd2-8000-2af4c8ca0216.json",
83
+ "/home/ubuntu/dataset/train/facesheet/069f97fd-a338-7b66-8000-c0662423a8d7.json",
84
+ "/home/ubuntu/dataset/train/facesheet/0696485b-469e-747a-8000-ade8929809ba.json",
85
+ "/home/ubuntu/dataset/train/facesheet/069f42c9-e8e6-7351-8000-501639431a2d.json",
86
+ "/home/ubuntu/dataset/train/facesheet/069fbe25-07f8-77eb-8000-d0e3ec07de56.json",
87
+ "/home/ubuntu/dataset/train/facesheet/069f42c7-0a69-7ac8-8000-3dfa36f3d1bb.json",
88
+ "/home/ubuntu/dataset/train/facesheet/069fc315-6ff5-740b-8000-ce53f64c4edb.json",
89
+ "/home/ubuntu/dataset/train/facesheet/069f43a4-01b2-78a5-8000-e701f14f7e17.json",
90
+ "/home/ubuntu/dataset/train/facesheet/069f43d0-978c-7cec-8000-ac2ba9adc7c4.json",
91
+ "/home/ubuntu/dataset/train/facesheet/069f42cb-47d7-7d1f-8000-6f779a259139.json",
92
+ "/home/ubuntu/dataset/train/facesheet/069f97fe-7c33-738f-8000-e4e6f7bfbe66.json",
93
+ "/home/ubuntu/dataset/train/facesheet/069f96da-7f69-7c1e-8000-e48553586b9a.json",
94
+ "/home/ubuntu/dataset/train/facesheet/0696485a-be17-7240-8000-e83874f23011.json",
95
+ "/home/ubuntu/dataset/train/facesheet/069f42c5-c8f8-74a3-8000-d169f2151ad6.json",
96
+ "/home/ubuntu/dataset/train/facesheet/069f43d0-c180-7525-8000-5f20733212a8.json",
97
+ "/home/ubuntu/dataset/train/facesheet/069f98c5-1ada-75e4-8000-35f99016f110.json",
98
+ "/home/ubuntu/dataset/train/facesheet/069f4e5d-5b73-7c5f-8000-25355ce8b5eb.json",
99
+ "/home/ubuntu/dataset/train/facesheet/069f42cd-14e1-775e-8000-65ee38c60bbc.json",
100
+ "/home/ubuntu/dataset/train/facesheet/069fd678-0144-7a1e-8000-22067d374a72.json",
101
+ "/home/ubuntu/dataset/train/facesheet/069f969a-066a-781f-8000-8fd54b287698.json",
102
+ "/home/ubuntu/dataset/train/facesheet/069f96d9-c8cd-7858-8000-fd4e84e9e94f.json",
103
+ "/home/ubuntu/dataset/train/facesheet/06960937-d690-7bc8-8000-43de34934020.json",
104
+ "/home/ubuntu/dataset/train/facesheet/069615f7-d624-74ec-8000-06ab80d26389.json",
105
+ "/home/ubuntu/dataset/train/facesheet/069615f8-ba01-7654-8000-6e382e6e6a4c.json",
106
+ "/home/ubuntu/dataset/train/facesheet/069fd843-0390-70fa-8000-482a6cc151ff.json",
107
+ "/home/ubuntu/dataset/train/facesheet/06960911-1f1e-7e21-8000-97d51a7c506c.json",
108
+ "/home/ubuntu/dataset/train/facesheet/069fd676-7c23-7e49-8000-4984e15254ab.json",
109
+ "/home/ubuntu/dataset/train/facesheet/06960910-765f-7bc9-8000-0af1fa41af4a.json",
110
+ "/home/ubuntu/dataset/train/facesheet/069615f7-95c0-74ca-8000-fd29a21b30bb.json",
111
+ "/home/ubuntu/dataset/train/facesheet/06964857-8e15-7584-8000-07ee22ec00a0.json",
112
+ "/home/ubuntu/dataset/train/facesheet/0696090f-9301-75a3-8000-ef57573e8175.json",
113
+ "/home/ubuntu/dataset/train/facesheet/069fc4ac-8078-7f20-8000-54c8d05539b1.json",
114
+ "/home/ubuntu/dataset/train/facesheet/0696090f-9033-75d4-8000-a1189f600c4e.json",
115
+ "/home/ubuntu/dataset/train/facesheet/069fc315-6ff5-755c-8000-a5d197f3f929.json",
116
+ "/home/ubuntu/dataset/train/facesheet/06960910-27e9-722f-8000-193d1eed8e06.json",
117
+ "/home/ubuntu/dataset/train/facesheet/06960910-d3fb-7e03-8000-6a02192fd358.json",
118
+ "/home/ubuntu/dataset/train/facesheet/069615f7-c9cc-7c57-8000-89b061e66845.json",
119
+ "/home/ubuntu/dataset/train/facesheet/06960911-1e06-7705-8000-972db402a0dd.json",
120
+ "/home/ubuntu/dataset/train/facesheet/069fc3f1-f127-7e5b-8000-586c4754020a.json",
121
+ "/home/ubuntu/dataset/train/facesheet/0696090f-d74e-775c-8000-49d352c90b86.json",
122
+ "/home/ubuntu/dataset/train/facesheet/06960911-6ca7-7f92-8000-c3e897b16814.json",
123
+ "/home/ubuntu/dataset/train/facesheet/069615f8-c258-7fa7-8000-596dabe4f23a.json",
124
+ "/home/ubuntu/dataset/train/facesheet/06964859-ad73-794a-8000-ff8b3e4e7c52.json",
125
+ "/home/ubuntu/dataset/train/facesheet/06964856-9049-7866-8000-6e46c4db6567.json",
126
+ "/home/ubuntu/dataset/train/facesheet/0696485a-c904-784f-8000-1d0a770445f4.json",
127
+ "/home/ubuntu/dataset/train/facesheet/069fc3f1-f127-7def-8000-bf30f74fd44b.json",
128
+ "/home/ubuntu/dataset/train/facesheet/069fd844-fc86-75fa-8000-9773d8b1f7db.json",
129
+ "/home/ubuntu/dataset/train/facesheet/069fd844-94cc-7b81-8000-dff8da8bffc7.json",
130
+ "/home/ubuntu/dataset/train/facesheet/06964857-e8b2-7660-8000-923d2b0fe851.json",
131
+ "/home/ubuntu/dataset/train/facesheet/0696485b-fb95-78ac-8000-80476091b18a.json",
132
+ "/home/ubuntu/dataset/train/facesheet/06964855-f4ae-75e7-8000-02b85fbf9fb6.json",
133
+ "/home/ubuntu/dataset/train/facesheet/069615f7-8a94-7cba-8000-399f250bbaf8.json",
134
+ "/home/ubuntu/dataset/train/facesheet/069fd775-cf2c-75b6-8000-bbfff8e09094.json",
135
+ "/home/ubuntu/dataset/train/facesheet/06964856-8e62-7ed6-8000-14467fc77200.json",
136
+ "/home/ubuntu/dataset/train/facesheet/0696090f-9301-7412-8000-eb7251a164c4.json",
137
+ "/home/ubuntu/dataset/train/facesheet/069fc44a-7ffa-7a68-8000-08fd0194622b.json",
138
+ "/home/ubuntu/dataset/train/facesheet/06964858-2329-7532-8000-34060cbfe60a.json",
139
+ "/home/ubuntu/dataset/train/facesheet/06964859-5727-73ad-8000-8f5e61ea068c.json",
140
+ "/home/ubuntu/dataset/train/facesheet/069fd72d-50d9-7787-8000-25a487dababa.json",
141
+ "/home/ubuntu/dataset/train/facesheet/0696090f-9033-7469-8000-ff6cf1c1fd0d.json",
142
+ "/home/ubuntu/dataset/train/facesheet/06960910-d129-7181-8000-7fa84af720de.json",
143
+ "/home/ubuntu/dataset/train/facesheet/0696090f-e348-7e99-8000-989099e407af.json",
144
+ "/home/ubuntu/dataset/train/facesheet/06960911-1e06-7597-8000-76ee1a74fd12.json",
145
+ "/home/ubuntu/dataset/train/facesheet/0696090f-e348-7cf0-8000-50c6b1c1b140.json",
146
+ "/home/ubuntu/dataset/train/facesheet/069fd775-cf2c-741e-8000-793e74c3cc61.json",
147
+ "/home/ubuntu/dataset/train/facesheet/06960910-765f-7ef9-8000-a27e7868ffa3.json",
148
+ "/home/ubuntu/dataset/train/facesheet/0696485a-1340-7da7-8000-4352fbe8a05c.json",
149
+ "/home/ubuntu/dataset/train/facesheet/0696090f-d74e-7578-8000-f420429cf9a5.json",
150
+ "/home/ubuntu/dataset/train/facesheet/06964859-1f5c-7ffb-8000-3be048286729.json",
151
+ "/home/ubuntu/dataset/train/facesheet/0696485b-4145-7d2e-8000-49a6ffb264ec.json",
152
+ "/home/ubuntu/dataset/train/facesheet/06964859-6fcc-7506-8000-b7905d90f7ae.json",
153
+ "/home/ubuntu/dataset/train/facesheet/06960910-d128-7ef7-8000-b561498b7e78.json",
154
+ "/home/ubuntu/dataset/train/facesheet/06960938-5126-7cfc-8000-6ef1ae208c50.json",
155
+ "/home/ubuntu/dataset/train/facesheet/06960910-27e9-739f-8000-385a95933d49.json",
156
+ "/home/ubuntu/dataset/train/facesheet/0696485b-04e3-72f1-8000-9810c96a4d90.json",
157
+ "/home/ubuntu/dataset/train/facesheet/06964858-eaee-77e8-8000-42788405e366.json",
158
+ "/home/ubuntu/dataset/train/facesheet/06960911-1f1e-7f86-8000-af2bced355e5.json",
159
+ "/home/ubuntu/dataset/train/facesheet/06964856-d537-76a3-8000-b32be03b3cd0.json",
160
+ "/home/ubuntu/dataset/train/facesheet/06960911-6ca8-7171-8000-42f2a81203f8.json",
161
+ "/home/ubuntu/dataset/train/facesheet/06960910-d3fb-7f81-8000-b504b9a9bf9e.json",
162
+ "/home/ubuntu/dataset/train/facesheet/069615f8-7552-754a-8000-d1a2548e19cb.json",
163
+ "/home/ubuntu/dataset/train/facesheet/06964859-16ce-79cf-8000-ab2182566417.json",
164
+ "/home/ubuntu/dataset/val/facesheet/069f4e5d-5b73-79d2-8000-7809dce870aa.json",
165
+ "/home/ubuntu/dataset/val/facesheet/069f42bb-c9a5-7f0a-8000-dd173de4a490.json",
166
+ "/home/ubuntu/dataset/val/facesheet/069fbe25-07f8-7831-8000-8fb2553ba2d3.json",
167
+ "/home/ubuntu/dataset/test/facesheet/069f42bc-720e-78a9-8000-d7c922509dc7.json",
168
+ "/home/ubuntu/dataset/test/facesheet/06964857-2aee-71f0-8000-84d6b89aeabd.json",
169
+ "/home/ubuntu/dataset/test/facesheet/069f43d0-c180-7066-8000-c3ff9f7aa513.json",
170
+ "/home/ubuntu/dataset/test/facesheet/06964856-3e4d-773c-8000-f6aad046db2b.json",
171
+ "/home/ubuntu/dataset/test/facesheet/0696485b-e656-78e9-8000-67190c8bf294.json",
172
+ "/home/ubuntu/dataset/test/facesheet/069f9698-7aab-7f38-8000-52d4424533e2.json",
173
+ "/home/ubuntu/dataset/test/facesheet/069f42bf-9b70-7bc0-8000-ee4c8583dfcd.json",
174
+ "/home/ubuntu/dataset/test/facesheet/069f43b5-0004-7dba-8000-a1194fec41b6.json",
175
+ "/home/ubuntu/dataset/test/facesheet/069f4e5d-5b74-7e1f-8000-e3aecd244697.json",
176
+ "/home/ubuntu/dataset/test/facesheet/069f9699-1d2c-7a17-8000-ee2e933add81.json",
177
+ "/home/ubuntu/dataset/test/facesheet/0696485a-4e2a-732b-8000-29fc2f264035.json",
178
+ "/home/ubuntu/dataset/test/facesheet/069615f8-2e75-7c8b-8000-440579cdd9fa.json",
179
+ "/home/ubuntu/dataset/test/facesheet/069f97ff-1174-7792-8000-ff8d773381ea.json",
180
+ "/home/ubuntu/dataset/test/facesheet/06964857-e7c2-71b1-8000-367b8ec5c480.json",
181
+ "/home/ubuntu/dataset/test/facesheet/069f96d7-bf11-7216-8000-99047e23fea0.json",
182
+ "/home/ubuntu/dataset/test/facesheet/069f9884-94ba-7c66-8000-a2bc1236cd84.json",
183
+ "/home/ubuntu/dataset/test/facesheet/069fd677-31e5-7010-8000-9caa8329620e.json",
184
+ "/home/ubuntu/dataset/test/facesheet/0696485b-c6c5-75e6-8000-57a8068f9913.json",
185
+ "/home/ubuntu/dataset/test/facesheet/069f9692-682c-7db5-8000-f6b7f1c2530e.json",
186
+ "/home/ubuntu/dataset/test/facesheet/0696090f-dbc1-7573-8000-019de5cca65b.json"
187
+ ]
188
+ }
null_files.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "null_files": []
3
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
removed_files.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ [
2
+ "/home/ubuntu/dataset/train/facesheet/06960911-1e06-7743-8000-6607c52f0734.json"
3
+ ]
runs/Jul24_07-03-49_c10618854f9e/events.out.tfevents.1784876629.c10618854f9e.9604.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da50228095a3bf8fe59c073426eeb6b097d06acaa02ca73e485fd4b9ba715b4a
3
+ size 10579
sorted_distribution.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "facesheet": 184
3
+ }
split_statistics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"total": 184, "train": 161, "test": 20, "val": 3}
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
- size 33384568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be1065b7f89c7fef368985543b5380ced9cda68aa907e27913a7e739002ec187
3
- size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96485e12654f1e5a68c1ccfa44766cd90c32d49eb6bdaafcb7dcf9b83eebf69c
3
+ size 5905