3huvan commited on Jun 17, 2025

Commit

8f6f06a

verified ·

1 Parent(s): 7147937

Add fine-tuned model for rhetorical role prediction

Browse files

Files changed (41) hide show

epoch_1_checkpoint/config.json +55 -0
epoch_1_checkpoint/label_mapping.json +15 -0
epoch_1_checkpoint/metrics.json +7 -0
epoch_1_checkpoint/model.safetensors +3 -0
epoch_1_checkpoint/special_tokens_map.json +7 -0
epoch_1_checkpoint/tokenizer.json +0 -0
epoch_1_checkpoint/tokenizer_config.json +58 -0
epoch_1_checkpoint/vocab.txt +0 -0
epoch_2_checkpoint/config.json +55 -0
epoch_2_checkpoint/label_mapping.json +15 -0
epoch_2_checkpoint/metrics.json +7 -0
epoch_2_checkpoint/model.safetensors +3 -0
epoch_2_checkpoint/special_tokens_map.json +7 -0
epoch_2_checkpoint/tokenizer.json +0 -0
epoch_2_checkpoint/tokenizer_config.json +58 -0
epoch_2_checkpoint/vocab.txt +0 -0
epoch_3_checkpoint/config.json +55 -0
epoch_3_checkpoint/label_mapping.json +15 -0
epoch_3_checkpoint/metrics.json +7 -0
epoch_3_checkpoint/model.safetensors +3 -0
epoch_3_checkpoint/special_tokens_map.json +7 -0
epoch_3_checkpoint/tokenizer.json +0 -0
epoch_3_checkpoint/tokenizer_config.json +58 -0
epoch_3_checkpoint/vocab.txt +0 -0
final_checkpoint/config.json +55 -0
final_checkpoint/label_mapping.json +15 -0
final_checkpoint/metrics.json +89 -0
final_checkpoint/model.safetensors +3 -0
final_checkpoint/special_tokens_map.json +7 -0
final_checkpoint/tokenizer.json +0 -0
final_checkpoint/tokenizer_config.json +58 -0
final_checkpoint/vocab.txt +0 -0
initial_checkpoint/config.json +54 -0
initial_checkpoint/label_mapping.json +15 -0
initial_checkpoint/metrics.json +1 -0
initial_checkpoint/model.safetensors +3 -0
initial_checkpoint/special_tokens_map.json +7 -0
initial_checkpoint/tokenizer.json +0 -0
initial_checkpoint/tokenizer_config.json +58 -0
initial_checkpoint/vocab.txt +0 -0
label_mapping.json +15 -0

epoch_1_checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

epoch_1_checkpoint/label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}

epoch_1_checkpoint/metrics.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "epoch": 1,
+  "train_loss": 1.2134970770511473,
+  "train_f1": 0.5850159013978483,
+  "train_acc": 0.6113641068101843,
+  "epoch_time": 1287.0544500350952
+}

epoch_1_checkpoint/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d26daf9e3671da9093947c854929451d2362a41213f0d8397ab655a6c598f0e
+size 439737380

epoch_1_checkpoint/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

epoch_1_checkpoint/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

epoch_1_checkpoint/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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,
+  "extra_special_tokens": {},
+  "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]"
+}

epoch_1_checkpoint/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

epoch_2_checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

epoch_2_checkpoint/label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}

epoch_2_checkpoint/metrics.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "epoch": 2,
+  "train_loss": 0.9067330668838675,
+  "train_f1": 0.6805352949525697,
+  "train_acc": 0.6975781411716001,
+  "epoch_time": 1287.245393037796
+}

epoch_2_checkpoint/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f808d381da5c8b91a29b36cfc2797e30f86a186c5fc99df07fdb64c34c52902
+size 439737380

epoch_2_checkpoint/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

epoch_2_checkpoint/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

epoch_2_checkpoint/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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,
+  "extra_special_tokens": {},
+  "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]"
+}

epoch_2_checkpoint/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

epoch_3_checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

epoch_3_checkpoint/label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}

epoch_3_checkpoint/metrics.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "epoch": 3,
+  "train_loss": 0.6808817090361767,
+  "train_f1": 0.7583717663390656,
+  "train_acc": 0.7675774511833299,
+  "epoch_time": 1287.229285478592
+}

epoch_3_checkpoint/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:21aeeb6e862bae2aad96138026892716ca643740c2a41b8ba04caace16a607f1
+size 439737380

epoch_3_checkpoint/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

epoch_3_checkpoint/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

epoch_3_checkpoint/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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,
+  "extra_special_tokens": {},
+  "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]"
+}

epoch_3_checkpoint/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

final_checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

final_checkpoint/label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}

final_checkpoint/metrics.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "model_name": "SciBERT",
+  "model_checkpoint": "allenai/scibert_scivocab_uncased",
+  "task": "Rhetorical Role Prediction",
+  "train_metrics": {
+    "macro_f1": 0.7369821755810839,
+    "weighted_f1": 0.8643526380515923,
+    "accuracy": 0.8747326295452977,
+    "per_label_f1": {
+      "ANALYSIS": 0.8920888731834445,
+      "ARG_PETITIONER": 0.7804546996946047,
+      "ARG_RESPONDENT": 0.5121951219512195,
+      "FAC": 0.9187826400144067,
+      "ISSUE": 0.9286675639300135,
+      "NONE": 0.928243195475433,
+      "PREAMBLE": 0.9233246624550973,
+      "PRE_NOT_RELIED": 0.037267080745341616,
+      "PRE_RELIED": 0.8005381769256643,
+      "RATIO": 0.23667100130039012,
+      "RLC": 0.800771208226221,
+      "RPC": 0.9221824686940966,
+      "STA": 0.899581589958159
+    },
+    "latency_ms_per_doc": 1.1843175841341813,
+    "latency_ms_per_sentence": 1.1843175841341813,
+    "eval_time_seconds": 415.6238057613373,
+    "num_samples": 28986
+  },
+  "dev_metrics": {
+    "macro_f1": 0.49354567091395296,
+    "weighted_f1": 0.6356316048961237,
+    "accuracy": 0.649183744355679,
+    "per_label_f1": {
+      "ANALYSIS": 0.6848249027237354,
+      "ARG_PETITIONER": 0.27586206896551724,
+      "ARG_RESPONDENT": 0.16326530612244897,
+      "FAC": 0.6260089686098654,
+      "ISSUE": 0.7272727272727273,
+      "NONE": 0.85,
+      "PREAMBLE": 0.7220376522702104,
+      "PRE_NOT_RELIED": 0.0,
+      "PRE_RELIED": 0.4549019607843137,
+      "RATIO": 0.10666666666666667,
+      "RLC": 0.34065934065934067,
+      "RPC": 0.7979274611398963,
+      "STA": 0.6666666666666666
+    },
+    "latency_ms_per_doc": 1.2095364566973903,
+    "latency_ms_per_sentence": 1.2095364566973903,
+    "eval_time_seconds": 41.31308722496033,
+    "num_samples": 2879
+  },
+  "overfitting_gap": 0.22872103315546866,
+  "model_size_mb": 419.35161209106445,
+  "training_memory_footprint_gb": 3.5974082946777344,
+  "label_mapping": {
+    "ANALYSIS": 0,
+    "ARG_PETITIONER": 1,
+    "ARG_RESPONDENT": 2,
+    "FAC": 3,
+    "ISSUE": 4,
+    "NONE": 5,
+    "PREAMBLE": 6,
+    "PRE_NOT_RELIED": 7,
+    "PRE_RELIED": 8,
+    "RATIO": 9,
+    "RLC": 10,
+    "RPC": 11,
+    "STA": 12
+  },
+  "id_mapping": {
+    "0": "ANALYSIS",
+    "1": "ARG_PETITIONER",
+    "2": "ARG_RESPONDENT",
+    "3": "FAC",
+    "4": "ISSUE",
+    "5": "NONE",
+    "6": "PREAMBLE",
+    "7": "PRE_NOT_RELIED",
+    "8": "PRE_RELIED",
+    "9": "RATIO",
+    "10": "RLC",
+    "11": "RPC",
+    "12": "STA"
+  },
+  "training_time_seconds": 3880.8387916088104,
+  "evaluation_time_seconds": 456.9819755554199,
+  "timestamp": "2025-06-17T19:20:10.428589"
+}

final_checkpoint/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:21aeeb6e862bae2aad96138026892716ca643740c2a41b8ba04caace16a607f1
+size 439737380

final_checkpoint/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

final_checkpoint/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

final_checkpoint/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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,
+  "extra_special_tokens": {},
+  "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]"
+}

final_checkpoint/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

initial_checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,54 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

initial_checkpoint/label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}

initial_checkpoint/metrics.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {}

initial_checkpoint/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1422bae0d0227195eb194337325a0d678c4d2b426682781c9754ab186c880338
+size 439737380

initial_checkpoint/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

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

initial_checkpoint/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

initial_checkpoint/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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,
+  "extra_special_tokens": {},
+  "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]"
+}

initial_checkpoint/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

label_mapping.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "ANALYSIS": 0,
+  "ARG_PETITIONER": 1,
+  "ARG_RESPONDENT": 2,
+  "FAC": 3,
+  "ISSUE": 4,
+  "NONE": 5,
+  "PREAMBLE": 6,
+  "PRE_NOT_RELIED": 7,
+  "PRE_RELIED": 8,
+  "RATIO": 9,
+  "RLC": 10,
+  "RPC": 11,
+  "STA": 12
+}