eskayML/bert_interview_new

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2980
-- Accuracy: 0.3679
+- Loss: 1.5132
+- Accuracy: 0.5128
 
 ## Model description
 
@@ -42,29 +42,24 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 152  | 2.5214          | 0.2263   |
-| No log        | 2.0   | 304  | 2.4518          | 0.2272   |
-| No log        | 3.0   | 456  | 2.3823          | 0.3004   |
-| 2.461         | 4.0   | 608  | 2.3026          | 0.3432   |
-| 2.461         | 5.0   | 760  | 2.2736          | 0.3531   |
-| 2.461         | 6.0   | 912  | 2.2958          | 0.3490   |
-| 1.7996        | 7.0   | 1064 | 2.2739          | 0.3671   |
-| 1.7996        | 8.0   | 1216 | 2.2829          | 0.3737   |
-| 1.7996        | 9.0   | 1368 | 2.2985          | 0.3638   |
-| 1.3781        | 10.0  | 1520 | 2.2980          | 0.3679   |
+| No log        | 1.0   | 468  | 1.4160          | 0.4658   |
+| 1.5252        | 2.0   | 936  | 1.2773          | 0.5299   |
+| 1.2542        | 3.0   | 1404 | 1.3040          | 0.5385   |
+| 0.9887        | 4.0   | 1872 | 1.4397          | 0.5299   |
+| 0.7766        | 5.0   | 2340 | 1.5132          | 0.5128   |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.19.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -9,49 +9,23 @@
   "dropout": 0.1,
   "hidden_dim": 3072,
   "id2label": {
-    "0": "ALGORITHM",
-    "1": "COMANAGEMENT",
-    "2": "COMPETING PRIORITIES",
-    "3": "COST",
-    "4": "COVID",
-    "5": "EHR",
-    "6": "GUIDELINES",
-    "7": "HFREF COMFORT MANAGING",
-    "8": "INFO NEEDS",
-    "9": "INTERNAL & EXTERNAL SUPPORT BAR",
-    "10": "JUICY QUOTE",
-    "11": "MAGIC WAND",
-    "12": "MED MANAGEMENT",
-    "13": "OTHER",
-    "14": "PATIENT DIGITAL TOOLS",
-    "15": "PATIENTS",
-    "16": "PROVIDER EDUCATION",
-    "17": "ROLE OF OTHER STAFF",
-    "18": "TIME CONSTRAINTS",
-    "19": "WORKFLOW"
+    "0": "EXTERNAL ENVIRONMENT",
+    "1": "ORGANIZATIONAL CHARACTERISTICS",
+    "2": "PATIENT CHARACTERISTICS",
+    "3": "IMPLEMENTATION SUSTAINABILITY INFRASTRUCTURE",
+    "4": "CLINICIAN PERSPECTIVE",
+    "5": "PATIENT PERSPECTIVES",
+    "6": "STAFF CHARACTERISTICS"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "ALGORITHM": 0,
-    "COMANAGEMENT": 1,
-    "COMPETING PRIORITIES": 2,
-    "COST": 3,
-    "COVID": 4,
-    "EHR": 5,
-    "GUIDELINES": 6,
-    "HFREF COMFORT MANAGING": 7,
-    "INFO NEEDS": 8,
-    "INTERNAL & EXTERNAL SUPPORT BAR": 9,
-    "JUICY QUOTE": 10,
-    "MAGIC WAND": 11,
-    "MED MANAGEMENT": 12,
-    "OTHER": 13,
-    "PATIENT DIGITAL TOOLS": 14,
-    "PATIENTS": 15,
-    "PROVIDER EDUCATION": 16,
-    "ROLE OF OTHER STAFF": 17,
-    "TIME CONSTRAINTS": 18,
-    "WORKFLOW": 19
+    "CLINICIAN PERSPECTIVE": 4,
+    "EXTERNAL ENVIRONMENT": 0,
+    "IMPLEMENTATION SUSTAINABILITY INFRASTRUCTURE": 3,
+    "ORGANIZATIONAL CHARACTERISTICS": 1,
+    "PATIENT CHARACTERISTICS": 2,
+    "PATIENT PERSPECTIVES": 5,
+    "STAFF CHARACTERISTICS": 6
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
@@ -64,6 +38,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e109b3a53fe39a6a0a4b54d4e6282c3d48011452094b24bbf66430e10de3875
-size 267887936
+oid sha256:c102e0d9508ae4a0a6920b933c1e8a72a94e8deaf94ebdfe8db2ff147b5be991
+size 267847948

tokenizer_config.json

@@ -41,7 +41,7 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",