intial commit

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "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": "B-bio",
+    "1": "I-bio",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-bio": 0,
+    "I-bio": 1,
+    "O": 2
+  },
+  "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",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.txt

@@ -0,0 +1,8 @@
+eval_loss = 0.0001628373865969479
+eval_precision = 0.9983676134508651
+eval_recall = 0.9986936642717178
+eval_f1 = 0.9985306122448979
+eval_runtime = 63.4689
+eval_samples_per_second = 39.878
+eval_steps_per_second = 4.995
+epoch = 10.0

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5eafaf6354cda2c2a5b360cf147cd108f88448e955b3b90a5284ea0517fdb4
+size 435660465

special_tokens_map.json

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

test_results.txt

@@ -0,0 +1,7 @@
+test_loss = 0.1286856085062027
+test_precision = 0.8334623123355518
+test_recall = 0.8513833992094861
+test_f1 = 0.8423275457531676
+test_runtime = 127.6505
+test_samples_per_second = 39.679
+test_steps_per_second = 4.967

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed", "tokenizer_class": "ElectraTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bf8d8ab58343ad1b87d903a1dae31ff2c1e45bd93e033f085b765e207cc587
+size 2927