entity_model_nov5

README.md

@@ -0,0 +1,68 @@
+---
+license: cc-by-sa-4.0
+base_model: nlpaueb/bert-base-uncased-contracts
+tags:
+- generated_from_trainer
+model-index:
+- name: entity_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# entity_model
+
+This model is a fine-tuned version of [nlpaueb/bert-base-uncased-contracts](https://huggingface.co/nlpaueb/bert-base-uncased-contracts) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0230
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2326        | 1.0   | 208  | 0.1823          |
+| 0.1492        | 2.0   | 416  | 0.1103          |
+| 0.1086        | 3.0   | 624  | 0.0816          |
+| 0.0727        | 4.0   | 832  | 0.0594          |
+| 0.0652        | 5.0   | 1040 | 0.0471          |
+| 0.0594        | 6.0   | 1248 | 0.0388          |
+| 0.0472        | 7.0   | 1456 | 0.0327          |
+| 0.0417        | 8.0   | 1664 | 0.0283          |
+| 0.0353        | 9.0   | 1872 | 0.0250          |
+| 0.0289        | 10.0  | 2080 | 0.0230          |
+
+
+### Framework versions
+
+- Transformers 4.42.0
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "nlpaueb/bert-base-uncased-contracts",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "eos_token_ids": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-AGREEMENT_DATE",
+    "2": "B-COST",
+    "3": "B-DOCUMENT_NAME",
+    "4": "B-EFFECTIVE_DATE",
+    "5": "B-EXPIRATION_DATE",
+    "6": "B-GOVERNING_LAW",
+    "7": "B-NOTICE_PERIOD_TO_TERMINATE_RENEWAL",
+    "8": "B-PARTIES",
+    "9": "B-PARTY_ADDRESS",
+    "10": "B-RENEWAL_TERM",
+    "11": "I-AGREEMENT_DATE",
+    "12": "I-COST",
+    "13": "I-DOCUMENT_NAME",
+    "14": "I-EFFECTIVE_DATE",
+    "15": "I-EXPIRATION_DATE",
+    "16": "I-GOVERNING_LAW",
+    "17": "I-NOTICE_PERIOD_TO_TERMINATE_RENEWAL",
+    "18": "I-PARTIES",
+    "19": "I-PARTY_ADDRESS",
+    "20": "I-RENEWAL_TERM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGREEMENT_DATE": 1,
+    "B-COST": 2,
+    "B-DOCUMENT_NAME": 3,
+    "B-EFFECTIVE_DATE": 4,
+    "B-EXPIRATION_DATE": 5,
+    "B-GOVERNING_LAW": 6,
+    "B-NOTICE_PERIOD_TO_TERMINATE_RENEWAL": 7,
+    "B-PARTIES": 8,
+    "B-PARTY_ADDRESS": 9,
+    "B-RENEWAL_TERM": 10,
+    "I-AGREEMENT_DATE": 11,
+    "I-COST": 12,
+    "I-DOCUMENT_NAME": 13,
+    "I-EFFECTIVE_DATE": 14,
+    "I-EXPIRATION_DATE": 15,
+    "I-GOVERNING_LAW": 16,
+    "I-NOTICE_PERIOD_TO_TERMINATE_RENEWAL": 17,
+    "I-PARTIES": 18,
+    "I-PARTY_ADDRESS": 19,
+    "I-RENEWAL_TERM": 20,
+    "O": 0
+  },
+  "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": null,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c0eb2fa4d193340c434b18d49f339a4f864f89e010a9cc3b9007a40e2ee480
+size 435654532

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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8ece6c976f9ec1d45ceaedd542e1d291ceb051bdbf357a9b2c69e1a48ac193
+size 5112