Training complete

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [d4data/biomedical-ner-all](https://huggingface.co/d4data/biomedical-ner-all) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5565
-- Accuracy: 0.7909
+- Loss: 0.6342
+- Accuracy: 0.7903
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 20
 
@@ -50,31 +50,31 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.641         | 1.0   | 10   | 1.5081          | 0.3577   |
-| 1.338         | 2.0   | 20   | 0.9042          | 0.6165   |
-| 0.877         | 3.0   | 30   | 0.6942          | 0.7081   |
-| 0.6363        | 4.0   | 40   | 0.5950          | 0.7520   |
-| 0.4868        | 5.0   | 50   | 0.5515          | 0.7573   |
-| 0.3798        | 6.0   | 60   | 0.5296          | 0.7688   |
-| 0.3047        | 7.0   | 70   | 0.5217          | 0.7825   |
-| 0.2521        | 8.0   | 80   | 0.5290          | 0.7788   |
-| 0.2123        | 9.0   | 90   | 0.5283          | 0.7852   |
-| 0.1819        | 10.0  | 100  | 0.5309          | 0.7880   |
-| 0.1585        | 11.0  | 110  | 0.5345          | 0.7835   |
-| 0.1388        | 12.0  | 120  | 0.5430          | 0.7823   |
-| 0.1235        | 13.0  | 130  | 0.5350          | 0.7871   |
-| 0.1128        | 14.0  | 140  | 0.5406          | 0.7882   |
-| 0.1036        | 15.0  | 150  | 0.5561          | 0.7873   |
-| 0.0985        | 16.0  | 160  | 0.5603          | 0.7887   |
-| 0.0924        | 17.0  | 170  | 0.5559          | 0.7894   |
-| 0.0883        | 18.0  | 180  | 0.5575          | 0.7909   |
-| 0.0832        | 19.0  | 190  | 0.5545          | 0.7910   |
-| 0.0843        | 20.0  | 200  | 0.5565          | 0.7909   |
+| 2.5437        | 1.0   | 10   | 1.6009          | 0.3671   |
+| 1.3262        | 2.0   | 20   | 0.9660          | 0.6254   |
+| 0.8675        | 3.0   | 30   | 0.7436          | 0.7145   |
+| 0.6199        | 4.0   | 40   | 0.6544          | 0.7385   |
+| 0.4707        | 5.0   | 50   | 0.6131          | 0.7660   |
+| 0.3735        | 6.0   | 60   | 0.6027          | 0.7709   |
+| 0.3049        | 7.0   | 70   | 0.6056          | 0.7786   |
+| 0.2507        | 8.0   | 80   | 0.5992          | 0.7792   |
+| 0.2144        | 9.0   | 90   | 0.6115          | 0.7780   |
+| 0.1801        | 10.0  | 100  | 0.6062          | 0.7863   |
+| 0.1539        | 11.0  | 110  | 0.6101          | 0.7854   |
+| 0.1372        | 12.0  | 120  | 0.6157          | 0.7892   |
+| 0.1234        | 13.0  | 130  | 0.6269          | 0.7896   |
+| 0.1119        | 14.0  | 140  | 0.6285          | 0.7881   |
+| 0.1025        | 15.0  | 150  | 0.6364          | 0.7879   |
+| 0.0945        | 16.0  | 160  | 0.6326          | 0.7896   |
+| 0.09          | 17.0  | 170  | 0.6297          | 0.7916   |
+| 0.0861        | 18.0  | 180  | 0.6318          | 0.7908   |
+| 0.083         | 19.0  | 190  | 0.6317          | 0.7901   |
+| 0.0817        | 20.0  | 200  | 0.6342          | 0.7903   |
 
 
 ### Framework versions
 
 - Transformers 4.47.1
-- Pytorch 2.5.1+cu124
+- Pytorch 2.5.1+cu121
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -12,171 +12,171 @@
     "0": "O",
     "1": "B-Age",
     "2": "I-Age",
-    "3": "B-History",
-    "4": "I-History",
-    "5": "B-Sex",
-    "6": "B-Clinical_event",
-    "7": "B-Sign_symptom",
-    "8": "B-Duration",
-    "9": "I-Duration",
-    "10": "I-Sign_symptom",
-    "11": "B-Coreference",
-    "12": "B-Frequency",
-    "13": "I-Frequency",
-    "14": "B-Detailed_description",
-    "15": "I-Detailed_description",
-    "16": "B-Biological_structure",
-    "17": "I-Biological_structure",
-    "18": "B-Lab_value",
-    "19": "I-Lab_value",
-    "20": "B-Diagnostic_procedure",
-    "21": "I-Diagnostic_procedure",
-    "22": "B-Disease_disorder",
-    "23": "I-Disease_disorder",
-    "24": "B-Therapeutic_procedure",
-    "25": "I-Therapeutic_procedure",
-    "26": "I-Clinical_event",
-    "27": "B-Date",
-    "28": "I-Date",
-    "29": "I-Coreference",
-    "30": "B-Texture",
-    "31": "I-Texture",
-    "32": "B-Severity",
-    "33": "B-Biological_attribute",
-    "34": "I-Biological_attribute",
-    "35": "B-Activity",
-    "36": "I-Activity",
-    "37": "B-Shape",
-    "38": "I-Shape",
-    "39": "B-Color",
-    "40": "I-Color",
-    "41": "B-Outcome",
-    "42": "I-Outcome",
-    "43": "B-Personal_background",
-    "44": "B-Medication",
-    "45": "I-Medication",
-    "46": "B-Dosage",
-    "47": "I-Dosage",
-    "48": "B-Nonbiological_location",
-    "49": "I-Severity",
-    "50": "B-Other_event",
-    "51": "I-Other_event",
-    "52": "B-Administration",
-    "53": "I-Administration",
-    "54": "I-Personal_background",
-    "55": "I-Nonbiological_location",
-    "56": "B-Occupation",
-    "57": "B-Other_entity",
-    "58": "I-Other_entity",
-    "59": "B-Distance",
-    "60": "I-Distance",
-    "61": "B-Time",
-    "62": "I-Time",
-    "63": "B-Area",
-    "64": "I-Area",
-    "65": "B-Family_history",
-    "66": "I-Family_history",
-    "67": "B-Subject",
+    "3": "B-Occupation",
+    "4": "I-Occupation",
+    "5": "B-Nonbiological_location",
+    "6": "I-Nonbiological_location",
+    "7": "B-Duration",
+    "8": "I-Duration",
+    "9": "B-Sign_symptom",
+    "10": "B-Lab_value",
+    "11": "I-Lab_value",
+    "12": "B-Detailed_description",
+    "13": "I-Detailed_description",
+    "14": "I-Sign_symptom",
+    "15": "B-Disease_disorder",
+    "16": "B-Medication",
+    "17": "I-Medication",
+    "18": "B-History",
+    "19": "I-History",
+    "20": "B-Clinical_event",
+    "21": "B-Diagnostic_procedure",
+    "22": "I-Diagnostic_procedure",
+    "23": "B-Biological_structure",
+    "24": "I-Biological_structure",
+    "25": "B-Severity",
+    "26": "I-Disease_disorder",
+    "27": "B-Dosage",
+    "28": "I-Dosage",
+    "29": "B-Therapeutic_procedure",
+    "30": "B-Date",
+    "31": "I-Date",
+    "32": "B-Outcome",
+    "33": "B-Sex",
+    "34": "I-Therapeutic_procedure",
+    "35": "B-Distance",
+    "36": "I-Distance",
+    "37": "I-Clinical_event",
+    "38": "B-Coreference",
+    "39": "I-Coreference",
+    "40": "B-Area",
+    "41": "I-Area",
+    "42": "B-Frequency",
+    "43": "I-Severity",
+    "44": "B-Administration",
+    "45": "I-Administration",
+    "46": "I-Outcome",
+    "47": "B-Shape",
+    "48": "I-Shape",
+    "49": "B-Qualitative_concept",
+    "50": "I-Frequency",
+    "51": "B-Activity",
+    "52": "I-Activity",
+    "53": "B-Subject",
+    "54": "B-Quantitative_concept",
+    "55": "B-Volume",
+    "56": "I-Volume",
+    "57": "I-Sex",
+    "58": "B-Personal_background",
+    "59": "B-Family_history",
+    "60": "I-Family_history",
+    "61": "I-Personal_background",
+    "62": "B-Color",
+    "63": "B-Texture",
+    "64": "I-Texture",
+    "65": "I-Quantitative_concept",
+    "66": "B-Time",
+    "67": "I-Time",
     "68": "I-Subject",
-    "69": "B-Volume",
-    "70": "I-Volume",
-    "71": "B-Quantitative_concept",
-    "72": "I-Quantitative_concept",
-    "73": "B-Height",
-    "74": "I-Height",
-    "75": "B-Weight",
-    "76": "I-Weight",
-    "77": "B-Qualitative_concept",
-    "78": "I-Qualitative_concept",
-    "79": "I-Occupation",
-    "80": "I-Sex",
+    "69": "B-Height",
+    "70": "I-Height",
+    "71": "B-Weight",
+    "72": "I-Weight",
+    "73": "I-Color",
+    "74": "B-Other_entity",
+    "75": "I-Other_entity",
+    "76": "B-Other_event",
+    "77": "I-Other_event",
+    "78": "B-Biological_attribute",
+    "79": "I-Biological_attribute",
+    "80": "I-Qualitative_concept",
     "81": "B-Mass",
     "82": "I-Mass"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "B-Activity": 35,
-    "B-Administration": 52,
+    "B-Activity": 51,
+    "B-Administration": 44,
     "B-Age": 1,
-    "B-Area": 63,
-    "B-Biological_attribute": 33,
-    "B-Biological_structure": 16,
-    "B-Clinical_event": 6,
-    "B-Color": 39,
-    "B-Coreference": 11,
-    "B-Date": 27,
-    "B-Detailed_description": 14,
-    "B-Diagnostic_procedure": 20,
-    "B-Disease_disorder": 22,
-    "B-Distance": 59,
-    "B-Dosage": 46,
-    "B-Duration": 8,
-    "B-Family_history": 65,
-    "B-Frequency": 12,
-    "B-Height": 73,
-    "B-History": 3,
-    "B-Lab_value": 18,
+    "B-Area": 40,
+    "B-Biological_attribute": 78,
+    "B-Biological_structure": 23,
+    "B-Clinical_event": 20,
+    "B-Color": 62,
+    "B-Coreference": 38,
+    "B-Date": 30,
+    "B-Detailed_description": 12,
+    "B-Diagnostic_procedure": 21,
+    "B-Disease_disorder": 15,
+    "B-Distance": 35,
+    "B-Dosage": 27,
+    "B-Duration": 7,
+    "B-Family_history": 59,
+    "B-Frequency": 42,
+    "B-Height": 69,
+    "B-History": 18,
+    "B-Lab_value": 10,
     "B-Mass": 81,
-    "B-Medication": 44,
-    "B-Nonbiological_location": 48,
-    "B-Occupation": 56,
-    "B-Other_entity": 57,
-    "B-Other_event": 50,
-    "B-Outcome": 41,
-    "B-Personal_background": 43,
-    "B-Qualitative_concept": 77,
-    "B-Quantitative_concept": 71,
-    "B-Severity": 32,
-    "B-Sex": 5,
-    "B-Shape": 37,
-    "B-Sign_symptom": 7,
-    "B-Subject": 67,
-    "B-Texture": 30,
-    "B-Therapeutic_procedure": 24,
-    "B-Time": 61,
-    "B-Volume": 69,
-    "B-Weight": 75,
-    "I-Activity": 36,
-    "I-Administration": 53,
+    "B-Medication": 16,
+    "B-Nonbiological_location": 5,
+    "B-Occupation": 3,
+    "B-Other_entity": 74,
+    "B-Other_event": 76,
+    "B-Outcome": 32,
+    "B-Personal_background": 58,
+    "B-Qualitative_concept": 49,
+    "B-Quantitative_concept": 54,
+    "B-Severity": 25,
+    "B-Sex": 33,
+    "B-Shape": 47,
+    "B-Sign_symptom": 9,
+    "B-Subject": 53,
+    "B-Texture": 63,
+    "B-Therapeutic_procedure": 29,
+    "B-Time": 66,
+    "B-Volume": 55,
+    "B-Weight": 71,
+    "I-Activity": 52,
+    "I-Administration": 45,
     "I-Age": 2,
-    "I-Area": 64,
-    "I-Biological_attribute": 34,
-    "I-Biological_structure": 17,
-    "I-Clinical_event": 26,
-    "I-Color": 40,
-    "I-Coreference": 29,
-    "I-Date": 28,
-    "I-Detailed_description": 15,
-    "I-Diagnostic_procedure": 21,
-    "I-Disease_disorder": 23,
-    "I-Distance": 60,
-    "I-Dosage": 47,
-    "I-Duration": 9,
-    "I-Family_history": 66,
-    "I-Frequency": 13,
-    "I-Height": 74,
-    "I-History": 4,
-    "I-Lab_value": 19,
+    "I-Area": 41,
+    "I-Biological_attribute": 79,
+    "I-Biological_structure": 24,
+    "I-Clinical_event": 37,
+    "I-Color": 73,
+    "I-Coreference": 39,
+    "I-Date": 31,
+    "I-Detailed_description": 13,
+    "I-Diagnostic_procedure": 22,
+    "I-Disease_disorder": 26,
+    "I-Distance": 36,
+    "I-Dosage": 28,
+    "I-Duration": 8,
+    "I-Family_history": 60,
+    "I-Frequency": 50,
+    "I-Height": 70,
+    "I-History": 19,
+    "I-Lab_value": 11,
     "I-Mass": 82,
-    "I-Medication": 45,
-    "I-Nonbiological_location": 55,
-    "I-Occupation": 79,
-    "I-Other_entity": 58,
-    "I-Other_event": 51,
-    "I-Outcome": 42,
-    "I-Personal_background": 54,
-    "I-Qualitative_concept": 78,
-    "I-Quantitative_concept": 72,
-    "I-Severity": 49,
-    "I-Sex": 80,
-    "I-Shape": 38,
-    "I-Sign_symptom": 10,
+    "I-Medication": 17,
+    "I-Nonbiological_location": 6,
+    "I-Occupation": 4,
+    "I-Other_entity": 75,
+    "I-Other_event": 77,
+    "I-Outcome": 46,
+    "I-Personal_background": 61,
+    "I-Qualitative_concept": 80,
+    "I-Quantitative_concept": 65,
+    "I-Severity": 43,
+    "I-Sex": 57,
+    "I-Shape": 48,
+    "I-Sign_symptom": 14,
     "I-Subject": 68,
-    "I-Texture": 31,
-    "I-Therapeutic_procedure": 25,
-    "I-Time": 62,
-    "I-Volume": 70,
-    "I-Weight": 76,
+    "I-Texture": 64,
+    "I-Therapeutic_procedure": 34,
+    "I-Time": 67,
+    "I-Volume": 56,
+    "I-Weight": 72,
     "O": 0
   },
   "max_position_embeddings": 512,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c07e2c98ca189a2d17892fde7f3714597bad71bc215278fca628fcfaa54ed2c
+oid sha256:642e10daa0e5f9b621b309c6412185e0b498a4abc044b419d16bf5f92c27c29e
 size 265719180

runs/Feb03_01-58-07_580211c92e0c/events.out.tfevents.1738547888.580211c92e0c.798.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a487f554426a738ce442536b50746eb39684c49d9917673cf7ae5f9a07d52115
+size 9266

runs/Feb03_01-58-28_580211c92e0c/events.out.tfevents.1738547908.580211c92e0c.798.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49cbcb9a4625bb4d7d036c7acd1fd674f342008462d754ca5ce0312c42c4b548
+size 20180

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6ecf50a04256069a24209a7c4a36f2b12311413bc029d760f03a9dd0263ec2
+oid sha256:78613d995b9a08b6f5354d3ccc2649a7e8934b5467b5438b0cef860146e95fd0
 size 5304