Hugging Face's logo

skumar1998
/
result

Transformers
TensorBoard
Safetensors
Generated from Trainer
unsloth
sft
trl
Model card Files
xet
 Metrics Community
skumar1998 commited on
Commit
30a8914
·
verified ·
1 Parent(s): 541cdbe

Training in progress, step 79

Browse files
Files changed (9) hide show
  1. adapter_model.safetensors +1 -1
  2. doctype_entity_distribution.json +15 -15
  3. entity_distribution.json +15 -15
  4. file.log +42 -43
  5. ground_truth_data.json +0 -0
  6. gt_json.json +0 -0
  7. removed_files.json +2 -2
  8. runs/Jul28_10-30-22_b6fbf603f302/events.out.tfevents.1785234622.b6fbf603f302.9985.0 +3 -0
  9. training_args.bin +1 -1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78ddd53ad4dc14f587af62bae4945ce1067180a821135bc73397ba3b29590e89
3
  size 1991027464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e63bb3ef3645490c86e3b5416d472d4221b8c3e8e386d0d58c91494655b2bca
3
  size 1991027464
doctype_entity_distribution.json CHANGED
@@ -1,29 +1,29 @@
1
  {
2
  "facesheet": {
 
 
 
 
 
 
 
 
 
 
3
  "accession_number": 1513,
4
  "collection_date": 2801,
5
- "facility.address": 5652,
6
- "facility.city": 5678,
7
- "facility.name": 5647,
8
- "facility.state": 5694,
9
- "facility.zip": 5721,
10
  "other_insurance_name_1": 1962,
11
  "other_insurance_number_1": 1967,
12
- "patient.dob": 5673,
13
- "patient.first_name": 6051,
14
- "patient.last_name": 6056,
15
- "patient.sex": 5636,
16
  "provider_npi": 5017,
17
  "sample_code": 5012,
18
- "medicaid_insurance_number": 2052,
19
  "medicare_insurance_number": 1597,
20
- "patient.address": 2303,
21
- "patient.city": 2321,
22
- "patient.state": 2429,
23
- "patient.zip": 2363,
 
24
  "phone_number": 1269,
25
  "social_security_number": 180,
26
- "patient.middle_name": 974,
27
  "other_insurance_name_2": 17,
28
  "other_insurance_number_2": 18
29
  }
 
1
  {
2
  "facesheet": {
3
+ "facility_address": 5652,
4
+ "facility_city": 5678,
5
+ "facility_name": 5647,
6
+ "facility_state": 5694,
7
+ "facility_zip": 5721,
8
+ "medicaid_insurance_number": 2052,
9
+ "patient_dob": 5673,
10
+ "patient_first_name": 6051,
11
+ "patient_last_name": 6056,
12
+ "patient_sex": 5636,
13
  "accession_number": 1513,
14
  "collection_date": 2801,
 
 
 
 
 
15
  "other_insurance_name_1": 1962,
16
  "other_insurance_number_1": 1967,
 
 
 
 
17
  "provider_npi": 5017,
18
  "sample_code": 5012,
 
19
  "medicare_insurance_number": 1597,
20
+ "patient_address": 2303,
21
+ "patient_city": 2321,
22
+ "patient_middle_name": 974,
23
+ "patient_state": 2429,
24
+ "patient_zip": 2363,
25
  "phone_number": 1269,
26
  "social_security_number": 180,
 
27
  "other_insurance_name_2": 17,
28
  "other_insurance_number_2": 18
29
  }
entity_distribution.json CHANGED
@@ -1,28 +1,28 @@
1
  {
 
 
 
 
 
 
 
 
 
 
2
  "accession_number": 1513,
3
  "collection_date": 2801,
4
- "facility.address": 5652,
5
- "facility.city": 5678,
6
- "facility.name": 5647,
7
- "facility.state": 5694,
8
- "facility.zip": 5721,
9
  "other_insurance_name_1": 1962,
10
  "other_insurance_number_1": 1967,
11
- "patient.dob": 5673,
12
- "patient.first_name": 6051,
13
- "patient.last_name": 6056,
14
- "patient.sex": 5636,
15
  "provider_npi": 5017,
16
  "sample_code": 5012,
17
- "medicaid_insurance_number": 2052,
18
  "medicare_insurance_number": 1597,
19
- "patient.address": 2303,
20
- "patient.city": 2321,
21
- "patient.state": 2429,
22
- "patient.zip": 2363,
 
23
  "phone_number": 1269,
24
  "social_security_number": 180,
25
- "patient.middle_name": 974,
26
  "other_insurance_name_2": 17,
27
  "other_insurance_number_2": 18
28
  }
 
1
  {
2
+ "facility_address": 5652,
3
+ "facility_city": 5678,
4
+ "facility_name": 5647,
5
+ "facility_state": 5694,
6
+ "facility_zip": 5721,
7
+ "medicaid_insurance_number": 2052,
8
+ "patient_dob": 5673,
9
+ "patient_first_name": 6051,
10
+ "patient_last_name": 6056,
11
+ "patient_sex": 5636,
12
  "accession_number": 1513,
13
  "collection_date": 2801,
 
 
 
 
 
14
  "other_insurance_name_1": 1962,
15
  "other_insurance_number_1": 1967,
 
 
 
 
16
  "provider_npi": 5017,
17
  "sample_code": 5012,
 
18
  "medicare_insurance_number": 1597,
19
+ "patient_address": 2303,
20
+ "patient_city": 2321,
21
+ "patient_middle_name": 974,
22
+ "patient_state": 2429,
23
+ "patient_zip": 2363,
24
  "phone_number": 1269,
25
  "social_security_number": 180,
 
26
  "other_insurance_name_2": 17,
27
  "other_insurance_number_2": 18
28
  }
file.log CHANGED
@@ -1,44 +1,43 @@
1
- 2026-07-26 19:38:28.335 | INFO | app.tasks.entity.vlm.dataset:create:671 - Using pre-split dataset mode
2
- 2026-07-26 19:38:28.368 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading train dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/train.json
3
- 2026-07-26 19:38:28.892 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
4
- 2026-07-26 19:38:58.376 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading val dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/eval.json
5
- 2026-07-26 19:38:58.778 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
6
- 2026-07-26 19:39:03.312 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading test dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/test.json
7
- 2026-07-26 19:39:03.698 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
8
- 2026-07-26 19:39:12.248 | INFO | app.tasks.entity.vlm.dataset:_download_miscellaneous:1633 - Downloading miscellaneous data from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/miscellaneous.json
9
- 2026-07-26 19:39:12.569 | INFO | app.tasks.entity.vlm.dataset:_download_previous_datasets:1542 - Found 0 previous dataset(s) to consolidate
10
- 2026-07-26 19:39:12.569 | INFO | app.tasks.entity.vlm.dataset:download_presplit_datasets:1684 - Successfully downloaded all datasets to /home/ubuntu/dataset
11
- 2026-07-26 19:39:31.861 | INFO | app.tasks.entity.vlm.dataset:remove_null_files:595 - Removed 2 files with null values
12
- 2026-07-26 19:39:33.896 | INFO | app.tasks.entity.vlm.reports:get_distribution:1513 - Original number of ground truth files 6058
13
- 2026-07-26 19:39:40.447 | INFO | app.tasks.entity.vlm.reports:get_distribution:1528 - After removing empty files 6058
14
- 2026-07-26 19:39:40.700 | INFO | app.tasks.entity.vlm.reports:get_entity_distribution:1628 - Creating entity distribution for 6058 files
15
- 2026-07-26 19:39:45.767 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
16
- 2026-07-26 19:39:46.024 | 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/06a665f8-ebd0-7481-8000-83304d751ace
17
- 2026-07-26 19:39:46.245 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
18
- 2026-07-26 19:39:46.247 | DEBUG | app.commonmlops:update_training_job_queue:937 - Updating training job queue with merged payload: {'id': '06a665f8-ebd0-7481-8000-83304d751ace', 'modeltype': 'entity', 'modelname': 'vlm_qwen3_5', 'jobtype': 'feedback', 'basemodelversionid': '019f0d56-3844-7c0a-8fab-4aa6a6d1f12e', 'datasetid': '06a665f5-06bf-7f15-8000-acbbe709e051', 'status': 'triggered', 'createddate': '2026-07-26T19:27:10.738422Z', 'createdby': '00000000-0000-0000-0000-000000000000', 'startdate': '2026-07-26T19:37:58.449464Z', 'enddate': None, 'accuracyreport': None, 'metadata': {'clearml_details': {'hf_model_id': '314e/dexit-aitest-vlm_qwen3_5-entity-integration', 'clearml_task_id': '035a14b471124d41a1200aa61394cf1b', 'new_modelversion_tag': 'v0.0.0', 'base_modelversion_tag': 'v0.0.0', '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']}, 'hyperparameters': {'DATASET_PARAMS': {'DATASET__EVAL_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/eval.json', 'DATASET__TEST_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/test.json', 'DATASET__TRAIN_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/train.json', 'DATASET__MISCELLANEOUS_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/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/Qwen3.6-27B', 'IMAGE_PATCH_SIZE': 16, 'THRESHOLD_OFFSET': 0.05, 'TRAIN_OOTB_MODEL': True, 'NEW_MODELVERSIONTAG': 'v0.0.0'}, 'MODEL_HYPERPARAMETERS': {'RANK': 64, 'ALPHA': 128, 'TRAIN_EPOCHS': 2, 'EVAL_BATCH_SIZE': 2, 'GRAD_ACCUM_STEPS': 4, 'TRAIN_BATCH_SIZE': 4, 'INFERENCE_BATCH_SIZE': 8}}, 'workflow_details': {'temporal_workflow_id': 'local-model-retraining-entity-2abc7cca', 'skypilot_cluster_name': 'dexit-aitest-skypilot-entity-1785094240-343135', 'temporal_workflow_run_id': '019f9fe8-4b17-75aa-9387-51d15585a9f1'}, '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': 0.8, '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': 0.7, 'mid_precision_bucket_corrected_sample_rate': 0.7, 'high_precision_bucket_corrected_sample_rate': 0.8, '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': 64, 'alpha': 128, 'train_epochs': 2, 'grad_accum_steps': 4, 'train_batch_size': 4}, 'hf_base_model_id': 'Qwen/Qwen3.6-27B', '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
- 2026-07-26 19:39:46.580 | 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/06a665f8-ebd0-7481-8000-83304d751ace
20
- 2026-07-26 19:39:46.581 | SUCCESS | app.commonmlops:update_trained_entities:979 - Updated trained_entities on training job queue
21
- 2026-07-26 19:39:47.056 | INFO | app.tasks.entity.vlm.reports:upload_initial_artifacts:1696 - Uploaded intial artifacts to ClearML
22
- 2026-07-26 19:39:47.057 | INFO | __main__:_run_training_phase:633 - Moving into standard training loop
23
- 2026-07-26 19:39:47.058 | INFO | __main__:setup_directories:210 - Loading pre-split dataset statistics
24
- 2026-07-26 19:39:48.554 | INFO | __main__:load_presplit_statistics:187 - Found 4250 training samples
25
- 2026-07-26 19:39:48.955 | INFO | __main__:load_presplit_statistics:189 - Found 1245 test samples
26
- 2026-07-26 19:39:49.140 | INFO | __main__:load_presplit_statistics:191 - Found 563 validation samples
27
- 2026-07-26 19:39:49.141 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1007 -
28
  Dataset Split Statistics:
29
- 2026-07-26 19:39:49.141 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1008 - Total samples: 6058
30
- 2026-07-26 19:39:49.142 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1010 - Train set: 4250 (70.2%)
31
- 2026-07-26 19:39:49.142 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1011 - Test set: 1245 (20.6%)
32
- 2026-07-26 19:39:49.142 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1012 - Validation set: 563 (9.3%)
33
- 2026-07-26 19:39:49.144 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1021 - Split statistics saved to /home/ubuntu/result/split_statistics.json
34
- 2026-07-26 19:39:49.214 | INFO | __main__:standard_training_loop:330 - Initializing model
35
- 2026-07-26 19:39:49.215 | INFO | __main__:initialize_model:242 - Setting up model for retraining
36
- 2026-07-26 19:39:49.215 | INFO | __main__:initialize_model:245 - Training from base model: Qwen/Qwen3.6-27B
37
- 2026-07-26 19:39:49.216 | INFO | app.tasks.entity.vlm.model:__post_init__:299 - loading model Qwen/Qwen3.6-27B for training with unsloth
38
- 2026-07-26 19:43:06.143 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:395 - num_samples: 4250, batch_size: 4, gradient_accumulation_steps: 4, epochs: 2
39
- 2026-07-26 19:43:06.144 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:399 - calculating max steps
40
- 2026-07-26 19:43:06.170 | INFO | __main__:standard_training_loop:333 - Setting up trainer
41
- 2026-07-26 19:43:06.171 | INFO | __main__:create_trainer:282 - Datasets: 4250 train, 563 eval samples
42
- 2026-07-26 19:43:06.979 | INFO | __main__:standard_training_loop:336 - Starting training
43
- 2026-07-26 19:43:07.183 | INFO | app.tasks.entity.vlm.model:train_model:600 - everything is set up, launching training
44
- 2026-07-27 03:10:51.427 | INFO | app.tasks.entity.vlm.model:train_model:606 - training complete: TrainOutput(global_step=530, training_loss=0.057691663363069856, metrics={'train_runtime': 26848.6091, 'train_samples_per_second': 0.316, 'train_steps_per_second': 0.02, 'total_flos': 2.7079361524323604e+18, 'train_loss': 0.057691663363069856, 'epoch': 1.9934148635936029})
 
1
+ 2026-07-28 10:25:30.221 | INFO | app.tasks.entity.vlm.dataset:create:671 - Using pre-split dataset mode
2
+ 2026-07-28 10:25:30.241 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading train dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/train.json
3
+ 2026-07-28 10:25:30.803 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
4
+ 2026-07-28 10:26:08.741 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading val dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/eval.json
5
+ 2026-07-28 10:26:09.270 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
6
+ 2026-07-28 10:26:15.444 | INFO | app.tasks.entity.vlm.dataset:_download_current_splits:1586 - Downloading test dataset from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/test.json
7
+ 2026-07-28 10:26:15.807 | INFO | app.tasks.entity.vlm.dataset:_download_split_documents:1443 - Processing %s %s/%s with %d documents
8
+ 2026-07-28 10:26:28.332 | INFO | app.tasks.entity.vlm.dataset:_download_miscellaneous:1633 - Downloading miscellaneous data from s3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/miscellaneous.json
9
+ 2026-07-28 10:26:28.533 | INFO | app.tasks.entity.vlm.dataset:_download_previous_datasets:1542 - Found 0 previous dataset(s) to consolidate
10
+ 2026-07-28 10:26:28.533 | INFO | app.tasks.entity.vlm.dataset:download_presplit_datasets:1684 - Successfully downloaded all datasets to /home/ubuntu/dataset
11
+ 2026-07-28 10:26:51.026 | INFO | app.tasks.entity.vlm.dataset:remove_null_files:595 - Removed 2 files with null values
12
+ 2026-07-28 10:26:52.727 | INFO | app.tasks.entity.vlm.reports:get_distribution:1513 - Original number of ground truth files 6058
13
+ 2026-07-28 10:26:59.987 | INFO | app.tasks.entity.vlm.reports:get_distribution:1528 - After removing empty files 6058
14
+ 2026-07-28 10:27:00.569 | INFO | app.tasks.entity.vlm.reports:get_entity_distribution:1628 - Creating entity distribution for 6058 files
15
+ 2026-07-28 10:27:07.187 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
16
+ 2026-07-28 10:27:07.458 | 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/06a665f8-ebd0-7481-8000-83304d751ace
17
+ 2026-07-28 10:27:07.683 | DEBUG | app.commonmlops:get_oauth_token:834 - OAuth token request status: 200
18
+ 2026-07-28 10:27:07.685 | DEBUG | app.commonmlops:update_training_job_queue:937 - Updating training job queue with merged payload: {'id': '06a665f8-ebd0-7481-8000-83304d751ace', 'modeltype': 'entity', 'modelname': 'vlm_qwen3_5', 'jobtype': 'feedback', 'basemodelversionid': '019f0d56-3844-7c0a-8fab-4aa6a6d1f12e', 'datasetid': '06a665f5-06bf-7f15-8000-acbbe709e051', 'status': 'triggered', 'createddate': '2026-07-26T19:27:10.738422Z', 'createdby': '00000000-0000-0000-0000-000000000000', 'startdate': '2026-07-28T10:24:58.745357Z', 'enddate': None, 'accuracyreport': {'overall': {'recall': 0.9638479703137299, 'f1_score': 0.9643088173252706, 'precision': 0.9647701052394619}, 'patient': {'recall': 0.9570468593654881, 'accuracy': 0.965850180851059, 'f1_score': 0.9578867442511313, 'precision': 0.9588553005522813}, 'facility': {'recall': 0.9681215596546779, 'accuracy': 0.9468811825459762, 'f1_score': 0.9706030656585861, 'precision': 0.9731011770220469}, 'patient.dob': {'recall': 0.9821124361158433, 'accuracy': 0.9706582077716098, 'f1_score': 0.9842082799829279, 'precision': 0.9863130881094953}, 'patient.sex': {'recall': 0.9991423670668954, 'accuracy': 0.9983935742971888, 'f1_score': 0.9991423670668954, 'precision': 0.9991423670668954}, 'patient.zip': {'recall': 0.9663366336633663, 'accuracy': 0.9847512038523274, 'f1_score': 0.9809045226130653, 'precision': 0.9959183673469387}, 'sample-code': {'recall': 0.9757045675413022, 'accuracy': 0.956953642384106, 'f1_score': 0.974757281553398, 'precision': 0.973811833171678}, 'facility.zip': {'recall': 0.9847586790855207, 'accuracy': 0.9808, 'f1_score': 0.9897872340425531, 'precision': 0.9948674080410608}, 'patient.city': {'recall': 0.9817444219066938, 'accuracy': 0.988, 'f1_score': 0.9847405900305187, 'precision': 0.9877551020408163}, 'phone-number': {'recall': 0.9820143884892086, 'accuracy': 0.9879711307137129, 'f1_score': 0.9732620320855615, 'precision': 0.9646643109540636}, 'provider-npi': {'recall': 1.0, 'accuracy': 0.9991546914623838, 'f1_score': 0.9995147986414362, 'precision': 0.9990300678952473}, 'facility.city': {'recall': 0.9965841161400513, 'accuracy': 0.9967871485943776, 'f1_score': 0.998289136013687, 'precision': 1.0}, 'facility.name': {'recall': 0.9624252775405636, 'accuracy': 0.9339035769828927, 'f1_score': 0.9636596836254809, 'precision': 0.9648972602739726}, 'patient.state': {'recall': 0.8530534351145038, 'accuracy': 0.8843226788432268, 'f1_score': 0.8546845124282982, 'precision': 0.8563218390804598}, 'facility.state': {'recall': 0.9335604770017035, 'accuracy': 0.8867781155015197, 'f1_score': 0.936351986330628, 'precision': 0.9391602399314481}, 'collection-date': {'recall': 0.9327433628318584, 'accuracy': 0.9297520661157025, 'f1_score': 0.9253731343283583, 'precision': 0.9181184668989547}, 'patient.address': {'recall': 0.9, 'accuracy': 0.9255813953488372, 'f1_score': 0.901840490797546, 'precision': 0.9036885245901639}, 'accession-number': {'recall': 0.9967948717948718, 'accuracy': 0.9991546914623838, 'f1_score': 0.9983948635634029, 'precision': 1.0}, 'facility.address': {'recall': 0.9632792485055508, 'accuracy': 0.9361370716510904, 'f1_score': 0.9649272882805817, 'precision': 0.9665809768637532}, 'patient.last-name': {'recall': 0.9879518072289156, 'accuracy': 0.9785202863961814, 'f1_score': 0.9891435464414957, 'precision': 0.9903381642512077}, 'patient.first-name': {'recall': 0.9911575562700965, 'accuracy': 0.9848242811501597, 'f1_score': 0.9923541247484909, 'precision': 0.9935535858178888}, 'patient.middle-name': {'recall': 0.9519230769230769, 'accuracy': 0.9776, 'f1_score': 0.9339622641509433, 'precision': 0.9166666666666666}, 'other-insurance-name-1': {'recall': 0.8285714285714286, 'accuracy': 0.8828549262994569, 'f1_score': 0.8217237308146399, 'precision': 0.8149882903981265}, 'other-insurance-name-2': {'recall': 0.0, 'accuracy': 0.9975922953451043, 'f1_score': 0.0, 'precision': 0.0}, 'social-security-number': {'recall': 0.9210526315789473, 'accuracy': 0.9847389558232932, 'f1_score': 0.7865168539325842, 'precision': 0.6862745098039216}, 'other-insurance-number-1': {'recall': 0.9285714285714286, 'accuracy': 0.9449321628092577, 'f1_score': 0.9187279151943463, 'precision': 0.9090909090909091}, 'other-insurance-number-2': {'recall': 0.0, 'accuracy': 0.9975922953451043, 'f1_score': 0.0, 'precision': 0.0}, 'medicaid-insurance-number': {'recall': 0.8946135831381733, 'accuracy': 0.9353312302839116, 'f1_score': 0.9030732860520094, 'precision': 0.9116945107398569}, 'medicare-insurance-number': {'recall': 0.9281609195402298, 'accuracy': 0.9611419508326725, 'f1_score': 0.9294964028776977, 'precision': 0.930835734870317}}, 'metadata': {'clearml_details': {'hf_model_id': '314e/dexit-aitest-vlm_qwen3_5-entity-integration', 'clearml_task_id': '3d0bd9fbf92940cb89c5107e1759e60c', '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': 'v1.0.0', 'base_modelversion_tag': 'v0.0.0'}, 'hyperparameters': {'DATASET_PARAMS': {'DATASET__EVAL_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/eval.json', 'DATASET__TEST_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/test.json', 'DATASET__TRAIN_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/train.json', 'DATASET__MISCELLANEOUS_S3_PATH': 's3://aitest-dexit-tech/data/__mlops__/dataset/entity/06a665f5-06bf-7f15-8000-acbbe709e051/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/Qwen3.6-27B', 'IMAGE_PATCH_SIZE': 16, 'THRESHOLD_OFFSET': 0.05, 'TRAIN_OOTB_MODEL': True, 'NEW_MODELVERSIONTAG': 'v1.0.0'}, 'MODEL_HYPERPARAMETERS': {'RANK': 64, 'ALPHA': 128, 'TRAIN_EPOCHS': 2, 'EVAL_BATCH_SIZE': 2, 'GRAD_ACCUM_STEPS': 4, 'TRAIN_BATCH_SIZE': 8, 'INFERENCE_BATCH_SIZE': 10}}, 'workflow_details': {'temporal_workflow_id': 'local-model-retraining-entity-432acc94', 'skypilot_cluster_name': 'dexit-aitest-skypilot-entity-1785233754-398002', 'temporal_workflow_run_id': '019fa839-1e83-7329-834d-7ab290a0aeb3'}, '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': 0.8, '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': 0.7, 'mid_precision_bucket_corrected_sample_rate': 0.7, 'high_precision_bucket_corrected_sample_rate': 0.8, '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': 64, 'alpha': 128, 'train_epochs': 2, 'grad_accum_steps': 4, 'train_batch_size': 8}, 'hf_base_model_id': 'Qwen/Qwen3.6-27B', '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
+ 2026-07-28 10:27:07.947 | 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/06a665f8-ebd0-7481-8000-83304d751ace
20
+ 2026-07-28 10:27:07.948 | SUCCESS | app.commonmlops:update_trained_entities:979 - Updated trained_entities on training job queue
21
+ 2026-07-28 10:27:08.432 | INFO | app.tasks.entity.vlm.reports:upload_initial_artifacts:1696 - Uploaded intial artifacts to ClearML
22
+ 2026-07-28 10:27:08.433 | INFO | __main__:_run_training_phase:633 - Moving into standard training loop
23
+ 2026-07-28 10:27:08.434 | INFO | __main__:setup_directories:210 - Loading pre-split dataset statistics
24
+ 2026-07-28 10:27:09.791 | INFO | __main__:load_presplit_statistics:187 - Found 4250 training samples
25
+ 2026-07-28 10:27:10.235 | INFO | __main__:load_presplit_statistics:189 - Found 1245 test samples
26
+ 2026-07-28 10:27:10.443 | INFO | __main__:load_presplit_statistics:191 - Found 563 validation samples
27
+ 2026-07-28 10:27:10.444 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1007 -
28
  Dataset Split Statistics:
29
+ 2026-07-28 10:27:10.444 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1008 - Total samples: 6058
30
+ 2026-07-28 10:27:10.445 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1010 - Train set: 4250 (70.2%)
31
+ 2026-07-28 10:27:10.445 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1011 - Test set: 1245 (20.6%)
32
+ 2026-07-28 10:27:10.445 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1012 - Validation set: 563 (9.3%)
33
+ 2026-07-28 10:27:10.447 | INFO | app.tasks.entity.vlm.dataset:print_split_statistics:1021 - Split statistics saved to /home/ubuntu/result/split_statistics.json
34
+ 2026-07-28 10:27:10.509 | INFO | __main__:standard_training_loop:330 - Initializing model
35
+ 2026-07-28 10:27:10.510 | INFO | __main__:initialize_model:242 - Setting up model for retraining
36
+ 2026-07-28 10:27:10.510 | INFO | __main__:initialize_model:245 - Training from base model: Qwen/Qwen3.6-27B
37
+ 2026-07-28 10:27:10.511 | INFO | app.tasks.entity.vlm.model:__post_init__:299 - loading model Qwen/Qwen3.6-27B for training with unsloth
38
+ 2026-07-28 10:30:19.674 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:395 - num_samples: 4250, batch_size: 8, gradient_accumulation_steps: 4, epochs: 2
39
+ 2026-07-28 10:30:19.675 | INFO | app.tasks.entity.vlm.model:calculate_max_steps:399 - calculating max steps
40
+ 2026-07-28 10:30:19.705 | INFO | __main__:standard_training_loop:333 - Setting up trainer
41
+ 2026-07-28 10:30:19.706 | INFO | __main__:create_trainer:282 - Datasets: 4250 train, 563 eval samples
42
+ 2026-07-28 10:30:20.492 | INFO | __main__:standard_training_loop:336 - Starting training
43
+ 2026-07-28 10:30:20.677 | INFO | app.tasks.entity.vlm.model:train_model:600 - everything is set up, launching training
 
ground_truth_data.json CHANGED
The diff for this file is too large to render. See raw diff
 
gt_json.json CHANGED
The diff for this file is too large to render. See raw diff
 
removed_files.json CHANGED
@@ -1,4 +1,4 @@
1
  [
2
- "/home/ubuntu/dataset/train/facesheet/06973491-2c33-7d17-8000-50d328faf93c.json",
3
- "/home/ubuntu/dataset/train/facesheet/06973491-2c33-78ad-8000-28b22f42c5ca.json"
4
  ]
 
1
  [
2
+ "/home/ubuntu/dataset/train/facesheet/06973491-2c33-78ad-8000-28b22f42c5ca.json",
3
+ "/home/ubuntu/dataset/train/facesheet/06973491-2c33-7d17-8000-50d328faf93c.json"
4
  ]
runs/Jul28_10-30-22_b6fbf603f302/events.out.tfevents.1785234622.b6fbf603f302.9985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e5d303c8806fd38ce882d2c336329b3e423abb9b8b69896b42682d0719c19b
3
+ size 12080
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc41f4875e0fc5e09e20d0efd6d6c0c51024e5fba30837d813a58a3f3c48abb
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5070eb08c40b9750508dc3cb6795b99bf883aa3aa17891381c49feee3e0c261
3
  size 5905