Upload model checkpoint

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Chemical",
+    "2": "B-Disease",
+    "3": "I-Disease",
+    "4": "I-Chemical"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 1,
+    "B-Disease": 2,
+    "I-Chemical": 4,
+    "I-Disease": 3,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a27ec919eaefeb2a226c99d59bb7bbfb5ab1347b9e1c524d740c57c39563ed
+size 430917436

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fecc8951c83713d096eedec50ce0eff1f4d1a495c6b113aa5b413e22b54d3422
+size 861954618

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11408855cf9f3a8cbd687c4d1bec1d76593c2506255fc8e744677732235116cb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025ca11bfb84e634a6060e1578dcf4dedb5233e981f8b9f59f6b67101541ee03
+size 1064

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 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 4578,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.764525993883792,
+      "grad_norm": 2.860719919204712,
+      "learning_rate": 1.781564001747488e-05,
+      "loss": 0.2481,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9536874012447196,
+      "eval_f1": 0.8924138535986316,
+      "eval_loss": 0.13802066445350647,
+      "eval_precision": 0.8979934094386254,
+      "eval_recall": 0.8869032051840874,
+      "eval_runtime": 25.0596,
+      "eval_samples_per_second": 212.693,
+      "eval_steps_per_second": 26.617,
+      "step": 654
+    },
+    {
+      "epoch": 1.529051987767584,
+      "grad_norm": 2.250061273574829,
+      "learning_rate": 1.563128003494976e-05,
+      "loss": 0.0943,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9569120634613524,
+      "eval_f1": 0.9029714891848114,
+      "eval_loss": 0.1516450196504593,
+      "eval_precision": 0.891004243281471,
+      "eval_recall": 0.9152645802458373,
+      "eval_runtime": 25.372,
+      "eval_samples_per_second": 210.074,
+      "eval_steps_per_second": 26.289,
+      "step": 1308
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.9499523043632507,
+      "learning_rate": 1.344692005242464e-05,
+      "loss": 0.0595,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9584212053787365,
+      "eval_f1": 0.9057778035083657,
+      "eval_loss": 0.17137625813484192,
+      "eval_precision": 0.9023039880042677,
+      "eval_recall": 0.909278470345509,
+      "eval_runtime": 24.0746,
+      "eval_samples_per_second": 221.395,
+      "eval_steps_per_second": 27.706,
+      "step": 1962
+    },
+    {
+      "epoch": 3.058103975535168,
+      "grad_norm": 0.29300621151924133,
+      "learning_rate": 1.126256006989952e-05,
+      "loss": 0.0405,
+      "step": 2000
+    },
+    {
+      "epoch": 3.8226299694189603,
+      "grad_norm": 0.09997886419296265,
+      "learning_rate": 9.0782000873744e-06,
+      "loss": 0.0218,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9578988100996421,
+      "eval_f1": 0.9073512721421696,
+      "eval_loss": 0.20640073716640472,
+      "eval_precision": 0.8972836278911178,
+      "eval_recall": 0.9176474006915991,
+      "eval_runtime": 23.267,
+      "eval_samples_per_second": 229.08,
+      "eval_steps_per_second": 28.667,
+      "step": 2616
+    },
+    {
+      "epoch": 4.587155963302752,
+      "grad_norm": 1.0946885347366333,
+      "learning_rate": 6.89384010484928e-06,
+      "loss": 0.0121,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9587372222759666,
+      "eval_f1": 0.9086317256194029,
+      "eval_loss": 0.22833754122257233,
+      "eval_precision": 0.9076963229323745,
+      "eval_recall": 0.9095690582047482,
+      "eval_runtime": 23.0423,
+      "eval_samples_per_second": 231.314,
+      "eval_steps_per_second": 28.947,
+      "step": 3270
+    },
+    {
+      "epoch": 5.351681957186544,
+      "grad_norm": 0.06167488545179367,
+      "learning_rate": 4.70948012232416e-06,
+      "loss": 0.0106,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9577440263132437,
+      "eval_f1": 0.9077642656688494,
+      "eval_loss": 0.24395699799060822,
+      "eval_precision": 0.8992358576642335,
+      "eval_recall": 0.9164559904687182,
+      "eval_runtime": 29.2986,
+      "eval_samples_per_second": 181.92,
+      "eval_steps_per_second": 22.766,
+      "step": 3924
+    },
+    {
+      "epoch": 6.116207951070336,
+      "grad_norm": 0.0039491127245128155,
+      "learning_rate": 2.5251201397990393e-06,
+      "loss": 0.0067,
+      "step": 4000
+    },
+    {
+      "epoch": 6.8807339449541285,
+      "grad_norm": 0.015259736217558384,
+      "learning_rate": 3.407601572739188e-07,
+      "loss": 0.005,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9576085905001451,
+      "eval_f1": 0.9074234296591107,
+      "eval_loss": 0.2515053153038025,
+      "eval_precision": 0.9006440532417347,
+      "eval_recall": 0.9143056403103479,
+      "eval_runtime": 24.477,
+      "eval_samples_per_second": 217.756,
+      "eval_steps_per_second": 27.25,
+      "step": 4578
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4578,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1242291550958640.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4125a0a079eb46c017a0a84fc05a26f4b31b5c6ba215cfdd41f0ae5155a9c34
+size 5240