eskayML/interview_electra

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: mrm8488/electra-small-finetuned-squadv2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: interview_electra
+  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. -->
+
+# interview_electra
+
+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: 1.3918
+- Accuracy: 0.7261
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 79   | 2.2793          | 0.1720   |
+| No log        | 2.0   | 158  | 2.2569          | 0.2102   |
+| No log        | 3.0   | 237  | 2.2141          | 0.2866   |
+| No log        | 4.0   | 316  | 2.1554          | 0.3121   |
+| No log        | 5.0   | 395  | 2.0661          | 0.5096   |
+| No log        | 6.0   | 474  | 1.9949          | 0.5669   |
+| 2.2016        | 7.0   | 553  | 1.9088          | 0.5987   |
+| 2.2016        | 8.0   | 632  | 1.8361          | 0.5605   |
+| 2.2016        | 9.0   | 711  | 1.7648          | 0.6306   |
+| 2.2016        | 10.0  | 790  | 1.7013          | 0.6561   |
+| 2.2016        | 11.0  | 869  | 1.6548          | 0.6115   |
+| 2.2016        | 12.0  | 948  | 1.5916          | 0.6943   |
+| 1.812         | 13.0  | 1027 | 1.5425          | 0.6943   |
+| 1.812         | 14.0  | 1106 | 1.5137          | 0.7006   |
+| 1.812         | 15.0  | 1185 | 1.4722          | 0.7261   |
+| 1.812         | 16.0  | 1264 | 1.4426          | 0.7197   |
+| 1.812         | 17.0  | 1343 | 1.4216          | 0.7197   |
+| 1.812         | 18.0  | 1422 | 1.4061          | 0.7325   |
+| 1.5304        | 19.0  | 1501 | 1.3961          | 0.7325   |
+| 1.5304        | 20.0  | 1580 | 1.3918          | 0.7261   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,55 @@
+{
+  "_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": "Value equation",
+    "1": "Credentialing / Quality Assurance Infrastructure",
+    "2": "Finanicial Impact",
+    "3": "Health System Characteristics",
+    "4": "Clinical utility & efficiency-Provider perspective",
+    "5": "Workflow related problems",
+    "6": "Provider Characteristics",
+    "7": "Training",
+    "8": "Patient/Physican interaction in LUS",
+    "9": "Imaging modalities in general"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "Clinical utility & efficiency-Provider perspective": 4,
+    "Credentialing / Quality Assurance Infrastructure": 1,
+    "Finanicial Impact": 2,
+    "Health System Characteristics": 3,
+    "Imaging modalities in general": 9,
+    "Patient/Physican interaction in LUS": 8,
+    "Provider Characteristics": 6,
+    "Training": 7,
+    "Value equation": 0,
+    "Workflow related problems": 5
+  },
+  "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": "4.41.1",
+  "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 sha256:3256ccee7c54ed91f76c0961e16713673deaa45fda905519bf0076b18b92385c
+size 54229432

runs/Jun03_14-02-02_ae93aebd6432/events.out.tfevents.1717423323.ae93aebd6432.154.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774e380d4be8d01eabcef9da0691b40fe6f579cc27de99937331e6ebde83e89e
+size 6105

runs/Jun03_14-03-40_ae93aebd6432/events.out.tfevents.1717423421.ae93aebd6432.154.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590ef32a1b7e250f4f4c3af56cb8b4a900e305d66504604630215e5919968691
+size 13229

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 sha256:730a70e966adc43050536a96f84b724c667993f45cc633d476784af89f06405d
+size 5112