initial commit

legal-ner/.gitattributes

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

legal-ner/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "nlpaueb/legal-bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_ids": 0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

legal-ner/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9b26b299592c2d23a563270112c2da9c6778c80b93cc4753d727eb94c69a38
+size 435682807

legal-ner/special_tokens_map.json

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

legal-ner/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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": "/root/.cache/huggingface/transformers/1ec992491addc8a43e9196bea3ccaf98f3958ce101f111ba9096813cf1ab493c.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "nlpaueb/legal-bert-base-uncased", "do_basic_tokenize": true, "never_split": null}

legal-ner/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.847380410022779,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.3026,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9689652127847431,
+      "eval_f1": 0.8772689578918271,
+      "eval_loss": 0.10503004491329193,
+      "eval_precision": 0.8721260419529174,
+      "eval_recall": 0.8824728890536657,
+      "eval_runtime": 13.1957,
+      "eval_samples_per_second": 246.292,
+      "step": 878
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.240698557327259e-05,
+      "loss": 0.1276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.610478359908885e-06,
+      "loss": 0.0892,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9735858496674319,
+      "eval_f1": 0.8989136438961518,
+      "eval_loss": 0.0925988033413887,
+      "eval_precision": 0.8929126657521719,
+      "eval_recall": 0.9049958290851794,
+      "eval_runtime": 13.204,
+      "eval_samples_per_second": 246.138,
+      "step": 1756
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.8139711465451785e-06,
+      "loss": 0.0672,
+      "step": 2000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.0174639331814731e-06,
+      "loss": 0.0536,
+      "step": 2500
+    }
+  ],
+  "max_steps": 2634,
+  "num_train_epochs": 3,
+  "total_flos": 1334617302236400,
+  "trial_name": null,
+  "trial_params": null
+}