clause_model_nov14

README.md

@@ -0,0 +1,71 @@
+---
+license: cc-by-sa-4.0
+base_model: nlpaueb/bert-base-uncased-contracts
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: clause_model_nov14
+  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. -->
+
+# clause_model_nov14
+
+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: 0.9001
+- Accuracy: 0.8546
+
+## 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: 500
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.3476        | 1.0   | 1269  | 0.8415          | 0.8147   |
+| 0.5667        | 2.0   | 2538  | 0.6364          | 0.8466   |
+| 0.3336        | 3.0   | 3807  | 0.6719          | 0.8537   |
+| 0.2592        | 4.0   | 5076  | 0.6984          | 0.8582   |
+| 0.1558        | 5.0   | 6345  | 0.7896          | 0.8466   |
+| 0.1148        | 6.0   | 7614  | 0.8543          | 0.8493   |
+| 0.0722        | 7.0   | 8883  | 0.8264          | 0.8626   |
+| 0.0716        | 8.0   | 10152 | 0.9042          | 0.8520   |
+| 0.0589        | 9.0   | 11421 | 0.8841          | 0.8564   |
+| 0.0349        | 10.0  | 12690 | 0.9001          | 0.8546   |
+
+
+### Framework versions
+
+- Transformers 4.42.0
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "nlpaueb/bert-base-uncased-contracts",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "Renewal Term",
+    "1": "Governing Law",
+    "2": "Competitive Restriction Exception",
+    "3": "Non-Compete",
+    "4": "Exclusivity",
+    "5": "No Solicitation",
+    "6": "Non-Disparagement",
+    "7": "Rofr/Rofo/Rofn",
+    "8": "Change Of Control",
+    "9": "Revenue/Profit Sharing",
+    "10": "Price Restrictions",
+    "11": "Minimum Commitment",
+    "12": "Ip Ownership Assignment",
+    "13": "Joint Ip Ownership",
+    "14": "License Grant",
+    "15": "Post-Termination Services",
+    "16": "Audits",
+    "17": "Uncapped Liability",
+    "18": "Cap On Liability",
+    "19": "Liquidated Damages",
+    "20": "Warranty Duration",
+    "21": "Insurance",
+    "22": "Covenant Not To Sue",
+    "23": "Severability",
+    "24": "Indemnification",
+    "25": "Waiver",
+    "26": "Compensation",
+    "27": "Confidentiality",
+    "28": "Termination",
+    "29": "Arbitration",
+    "30": "Force Majeure",
+    "31": "Definition",
+    "32": "Survival",
+    "33": "Assignment",
+    "34": "Dispute Resolution",
+    "35": "Security Deposit",
+    "36": "Breach",
+    "37": "Intellectual Property Rights",
+    "38": "Obligations",
+    "39": "Others"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arbitration": 29,
+    "Assignment": 33,
+    "Audits": 16,
+    "Breach": 36,
+    "Cap On Liability": 18,
+    "Change Of Control": 8,
+    "Compensation": 26,
+    "Competitive Restriction Exception": 2,
+    "Confidentiality": 27,
+    "Covenant Not To Sue": 22,
+    "Definition": 31,
+    "Dispute Resolution": 34,
+    "Exclusivity": 4,
+    "Force Majeure": 30,
+    "Governing Law": 1,
+    "Indemnification": 24,
+    "Insurance": 21,
+    "Intellectual Property Rights": 37,
+    "Ip Ownership Assignment": 12,
+    "Joint Ip Ownership": 13,
+    "License Grant": 14,
+    "Liquidated Damages": 19,
+    "Minimum Commitment": 11,
+    "No Solicitation": 5,
+    "Non-Compete": 3,
+    "Non-Disparagement": 6,
+    "Obligations": 38,
+    "Others": 39,
+    "Post-Termination Services": 15,
+    "Price Restrictions": 10,
+    "Renewal Term": 0,
+    "Revenue/Profit Sharing": 9,
+    "Rofr/Rofo/Rofn": 7,
+    "Security Deposit": 35,
+    "Severability": 23,
+    "Survival": 32,
+    "Termination": 28,
+    "Uncapped Liability": 17,
+    "Waiver": 25,
+    "Warranty Duration": 20
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "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 sha256:8d60d61f1e9921e57c0ca88943d28916fbbe5d23bb34394f5c06824ff1cf946f
+size 438075536

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 sha256:89a23253c00eb96deba706fe3511e0c73918ff24b036628e58448caf5f2c383b
+size 5112