Upload folder using huggingface_hub

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "UFNLP/gatortronS",
+  "architectures": [
+    "MegatronBertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-IHC",
+    "1": "B-IHC_modifier",
+    "2": "B-anatomical_site",
+    "3": "B-diagnosis_descriptor",
+    "4": "B-pathological_diagnosis",
+    "5": "I-IHC",
+    "6": "I-IHC_modifier",
+    "7": "I-anatomical_site",
+    "8": "I-diagnosis_descriptor",
+    "9": "I-pathological_diagnosis",
+    "10": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-IHC": 0,
+    "B-IHC_modifier": 1,
+    "B-anatomical_site": 2,
+    "B-diagnosis_descriptor": 3,
+    "B-pathological_diagnosis": 4,
+    "I-IHC": 5,
+    "I-IHC_modifier": 6,
+    "I-anatomical_site": 7,
+    "I-diagnosis_descriptor": 8,
+    "I-pathological_diagnosis": 9,
+    "O": 10
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_type": "BertWordPieceCase",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523648a9c59e9d88bf002885c54843bf52322ba0e3dbdbf405a94d412d147a78
+size 1416962564

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 +1,57 @@
+{
+  "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]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.766226053237915,
+      "learning_rate": 2.6223219590153115e-05,
+      "loss": 0.2037,
+      "step": 546
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.024935245513916,
+      "learning_rate": 0.0,
+      "loss": 0.0756,
+      "step": 1092
+    },
+    {
+      "epoch": 2.0,
+      "step": 1092,
+      "total_flos": 790377348130650.0,
+      "train_loss": 0.13962632832509694,
+      "train_runtime": 294.0097,
+      "train_samples_per_second": 14.836,
+      "train_steps_per_second": 3.714
+    }
+  ],
+  "logging_steps": 546,
+  "max_steps": 1092,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 546,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 790377348130650.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11659d2b5f04737019690a9c641aa1c6b431c463f45b7028731f1530b10d9117
+size 5112