eskayML/electra_interview_new

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: mrm8488/electra-small-finetuned-squadv2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: electra_interview_duplicated
+  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. -->
+
+# electra_interview_duplicated
+
+This model is a fine-tuned version of [mrm8488/electra-small-finetuned-squadv2](https://huggingface.co/mrm8488/electra-small-finetuned-squadv2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2204
+- Accuracy: 0.3581
+
+## 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: 2e-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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.5854        | 1.0   | 2121  | 2.5418          | 0.2014   |
+| 2.4462        | 2.0   | 4242  | 2.4187          | 0.2898   |
+| 2.3656        | 3.0   | 6363  | 2.3080          | 0.3204   |
+| 2.2985        | 4.0   | 8484  | 2.2448          | 0.3298   |
+| 2.2479        | 5.0   | 10605 | 2.2204          | 0.3581   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "mrm8488/electra-small-finetuned-squadv2",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "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,
+  "intermediate_size": 1024,
+  "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
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e7e76e0c92b0fd65613ad9088a6e2c2ec0fed5f4fbbe17b8ef93ce15128465
+size 54239712

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18338bf3ea3bc3266fedad86a6ed71864d3445c6ad89fbcf7585c5330b841661
+size 5176