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 = 0.00034680875251069665
+eval_precision = 0.9898550724637681
+eval_recall = 0.9592696629213483
+eval_f1 = 0.9743223965763195
+eval_runtime = 98.8985
+eval_samples_per_second = 41.315
+eval_steps_per_second = 5.167
+epoch = 10.0

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c20b92e5d067784088e0a10cfe69255b44a9619decfec2b769c0be2e0c4f477
+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 = 0.01268028561025858
+test_precision = 0.7907523510971787
+test_recall = 0.7041172365666434
+test_f1 = 0.7449243263196751
+test_runtime = 171.8499
+test_samples_per_second = 41.786
+test_steps_per_second = 5.225

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 sha256:4d30954979eaa5911c4dba1e2bd2b05dac840d43e494fc565e724d381f81a770
+size 2927