Upload 9 files

This repository contains the final Assignment 3 model artifacts for the QLoRA path (Part C) and downstream PatentSBERTa fine-tuning (Part D).

comparison_table.csv: Required Part E comparison of Baseline vs Assignment 2 vs Assignment 3 F1 scores.
config.json: Model architecture and label configuration for the final sequence-classification model.
model.safetensors: Trained model weights from Assignment 3 Part D (the final model to evaluate/use).
part_d_summary.json: Compact summary of Part D setup, dataset sizes, and final performance metrics.
special_tokens_map.json: Mapping of tokenizer special tokens used with the model.
tokenizer_config.json: Tokenizer runtime settings for preprocessing text consistently.
tokenizer.json: Full tokenizer definition used during training/inference.
training_args.bin: Serialized Hugging Face training arguments for reproducibility of Part D.
vocab.txt: Token vocabulary file required by the tokenizer.

Together, these files document and reproduce the final Assignment 3 model used in the required comparative analysis.

comparison_table.csv

@@ -0,0 +1,4 @@
+Model Version,Training Data Source,F1 Score (Eval Set)
+1. Baseline,Frozen Embeddings (No Fine-tuning),0.7727474955813791
+2. Assignment 2 Model,Fine-tuned on Silver + Gold (Simple LLM),0.49753697103764694
+3. Assignment 3 Model,Fine-tuned on Silver + Gold (QLoRA),0.5006382067789964

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "MPNetForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30527
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62f3eaa65e5b6ff653583ee4fe27d1bb9ba2635728824c27616ab127955a282
+size 437975200

part_d_summary.json

@@ -0,0 +1,12 @@
+{
+  "finetune_model": "AI-Growth-Lab/PatentSBERTa",
+  "n_train_augmented": 20100,
+  "n_eval": 5000,
+  "n_gold": 100,
+  "metrics": {
+    "eval_silver_accuracy": 0.5008,
+    "eval_silver_macro_f1": 0.5006382067789964,
+    "gold_100_accuracy": 0.53,
+    "gold_100_macro_f1": 0.5037482842360892
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e383aafca2b09cf41bd0b36da712bb2087aa885a7a9639a80a2da0de1f5a3a
+size 5841