Add clause model

clause_model_512/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

clause_model_512/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766ce55bbedf906c3cb0fd0e6a97ca6f6ce67df06e34a623a0a40ceaca3a031e
+size 496302125

clause_model_512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0733330814460dc410cacd0c140f64486ec5a7c9858a4c28a67be4dffe5f93
+size 627

clause_model_512/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

clause_model_512/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

clause_model_512/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 490,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.04,
+      "learning_rate": 7.959183673469388e-06,
+      "loss": 0.4344,
+      "step": 100
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 5.918367346938776e-06,
+      "loss": 0.171,
+      "step": 200
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 3.877551020408164e-06,
+      "loss": 0.1436,
+      "step": 300
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 1.8367346938775512e-06,
+      "loss": 0.1312,
+      "step": 400
+    }
+  ],
+  "max_steps": 490,
+  "num_train_epochs": 10,
+  "total_flos": 2032907146629120.0,
+  "trial_name": null,
+  "trial_params": null
+}

clause_model_512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2ab12a1d9c72d6fedfd51aae32ee599bdfe2a9f7e1fb85470f0eda6ebec841
+size 3387