Training in progress, epoch 0

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Epidemic Forecasting",
+    "1": "Treatment",
+    "2": "Prevention",
+    "3": "Mechanism",
+    "4": "Case Report",
+    "5": "Transmission",
+    "6": "Diagnosis",
+    "7": "Long Covid",
+    "8": "General Info",
+    "9": "Communication",
+    "10": "Contact Tracing",
+    "11": "Drug Targets",
+    "12": "Education",
+    "13": "Effect on Medical Specialties",
+    "14": "Health Policy",
+    "15": "Healthcare Workers",
+    "16": "Imaging",
+    "17": "Immunology",
+    "18": "Inequality",
+    "19": "Medical Devices",
+    "20": "Misinformation",
+    "21": "Model Systems & Tools",
+    "22": "Molecular Biology",
+    "23": "Non-human",
+    "24": "Non-medical",
+    "25": "Pediatrics",
+    "26": "Prevalence",
+    "27": "Psychology",
+    "28": "Recommendations",
+    "29": "Risk Factors",
+    "30": "Surveillance",
+    "31": "Vaccines",
+    "32": "AI/ML/statistics",
+    "33": "Comorbidities",
+    "34": "Telemedicine",
+    "35": "Drug Design and Discovery"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AI/ML/statistics": 32,
+    "Case Report": 4,
+    "Communication": 9,
+    "Comorbidities": 33,
+    "Contact Tracing": 10,
+    "Diagnosis": 6,
+    "Drug Design and Discovery": 35,
+    "Drug Targets": 11,
+    "Education": 12,
+    "Effect on Medical Specialties": 13,
+    "Epidemic Forecasting": 0,
+    "General Info": 8,
+    "Health Policy": 14,
+    "Healthcare Workers": 15,
+    "Imaging": 16,
+    "Immunology": 17,
+    "Inequality": 18,
+    "Long Covid": 7,
+    "Mechanism": 3,
+    "Medical Devices": 19,
+    "Misinformation": 20,
+    "Model Systems & Tools": 21,
+    "Molecular Biology": 22,
+    "Non-human": 23,
+    "Non-medical": 24,
+    "Pediatrics": 25,
+    "Prevalence": 26,
+    "Prevention": 2,
+    "Psychology": 27,
+    "Recommendations": 28,
+    "Risk Factors": 29,
+    "Surveillance": 30,
+    "Telemedicine": 34,
+    "Transmission": 5,
+    "Treatment": 1,
+    "Vaccines": 31
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9967d263420918e37d65c39f084bd5fbf50c7d24a86a58d54e965ce89a6f03e
+size 438113077

runs/Jun25_19-43-24_6e93b22df6a9/1719344622.1213255/events.out.tfevents.1719344622.6e93b22df6a9.32.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4fd5c9bc8798e13afb911bfb09427814d6f3a288c42f69c58a05a27a5534e9
+size 5911

runs/Jun25_19-43-24_6e93b22df6a9/events.out.tfevents.1719344622.6e93b22df6a9.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371707c1435d4e3b3a57c6e9e3c1d372e3a07f904e9b1111eda47148ba39970c
+size 7535

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 +1,17 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "padding": true,
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bb5185cbccfbd9f886b6410e97b0c7fed579177fe403e06489817224fcdce9
+size 3643