eskayML/bert_interview_new

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_interview_new
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert_interview_new
+
+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: 0.9106
+- Accuracy: 0.7697
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.5257        | 1.0   | 759  | 2.1260          | 0.4079   |
+| 1.9969        | 2.0   | 1518 | 1.7308          | 0.5066   |
+| 1.7415        | 3.0   | 2277 | 1.4204          | 0.6316   |
+| 1.5223        | 4.0   | 3036 | 1.2385          | 0.6743   |
+| 1.3484        | 5.0   | 3795 | 1.1238          | 0.7039   |
+| 1.2576        | 6.0   | 4554 | 1.0478          | 0.7336   |
+| 1.1427        | 7.0   | 5313 | 0.9814          | 0.7467   |
+| 1.0499        | 8.0   | 6072 | 0.9471          | 0.75     |
+| 1.0145        | 9.0   | 6831 | 0.9234          | 0.7632   |
+| 0.911         | 10.0  | 7590 | 0.9106          | 0.7697   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "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"
+  },
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149a9d8e3b01a3b88776b9549a68c36e9a8e0d5d9045d8623e488bfa81770a85
+size 267887936

runs/Sep13_13-28-17_0294381cf3b7/events.out.tfevents.1726234098.0294381cf3b7.540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b1ae096a957f051fa52b4faccf8e7a7e9fe10cba070d0539987529888da9c2
+size 11980

runs/Sep13_13-49-13_0294381cf3b7/events.out.tfevents.1726235354.0294381cf3b7.540.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7739b9c15f0843dc6a194d575600c07bfb666df51998b67bdeaefc0ab48f5e8
+size 12613

runs/Sep13_14-46-10_0294381cf3b7/events.out.tfevents.1726238770.0294381cf3b7.540.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd4023160bb0f8ceaa9f73aa46d3070fbab332f19c2a804411587c096d0f637
+size 6947

runs/Sep13_14-47-32_0294381cf3b7/events.out.tfevents.1726238853.0294381cf3b7.540.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb7df138f72733282c00fd010afe127291a9e3a86eccdc5fba7f45e6e941317
+size 12613

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11b28af5d635c99b0ece872a85d26404ddaef6bb47baa37d9a9e428a8ccbae8
+size 5240