Upload repository_library model package

README.md

@@ -0,0 +1,84 @@
+---
+base_model: allenai/scibert_scivocab_uncased
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- bug-localization
+- code
+- r4
+- repositories
+- repository-library
+- research-library
+- t4_repo
+---
+
+# Bug Localization
+
+Ranks likely bug locations inside repository content.
+
+## Model Details
+
+- Artifact type: full fine-tuned model
+- Base model: `allenai/scibert_scivocab_uncased`
+- Model ID: `R4`
+- Tier: `T4_repo`
+- Local mirror: `/arxiv/models/repository_library/bug-localization`
+- Source checkpoint: `models/checkpoints/R4`
+
+This repository is part of the `repository_library` model stack and is mirrored from `/data/repository_library/models/checkpoints` for publication under the `PeytonT` namespace.
+
+## Intended Use
+
+- Primary use: Ranks likely bug locations inside repository content.
+- Secondary use: retrieval, ranking, planning, or scientific paper tooling inside the broader Repository Library system, depending on the model family.
+- Out of scope: production safety claims, benchmark claims beyond the bundled experiment config, or use outside the model's narrow training objective without task-specific validation.
+
+## Training Data
+
+This package was trained from the following declared datasets or corpus sources:
+
+- `source:github_repos`
+
+## Training Procedure
+
+- Sources: `github_repos`
+- Input fields: `repo_context, failure_description`
+- Target fields: `bug_location`
+- Max samples: `4000`
+- Precision: `bf16`
+- Objective: `cross_entropy`
+- Batch size: `8`
+- Learning rate: `5e-05`
+- Max source tokens: `512`
+- Max target tokens: `128`
+- Max steps: `1000`
+
+## Evaluation
+
+- Declared metrics: `accuracy, macro_f1`
+- Status: local experiment artifact mirrored for release; external benchmark reporting has not been standardized across the full model family yet.
+
+## Usage
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+repo_id = "PeytonT/bug-localization"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForSequenceClassification.from_pretrained(repo_id)
+```
+
+## Limitations
+
+- These model cards reflect the packaged experiment configs and mirrored checkpoint contents, not an independently audited benchmark sheet.
+- Some training datasets are local corpora or exported shards, so reproducibility may require access to the surrounding Repository Library data pipeline.
+- Models in this stack are narrow components of a larger paper-and-repository system and should be validated on downstream tasks before deployment.
+
+## Project Context
+
+Repository Library is a research system for indexing, retrieving, aligning, and reasoning over scientific papers, structured paper content, repositories, and cross-domain links between them.
+
+## Contact
+
+Published under `PeytonT` from the local `repository_library` build.

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0
+  },
+  "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",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f51749468b4c4919545963b5570753aeda595f22e32ceb72a2f1f33039d2a65
+size 439703544

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 +1,58 @@
+{
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.492753623188406,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.024382874369621277,
+      "learning_rate": 2.45e-05,
+      "loss": 0.1151,
+      "step": 50
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 0.005299532786011696,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.0004,
+      "step": 100
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 0.0024427291937172413,
+      "learning_rate": 4.727777777777778e-05,
+      "loss": 0.0001,
+      "step": 150
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 0.0012963886838406324,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.0001,
+      "step": 200
+    },
+    {
+      "epoch": 3.6231884057971016,
+      "grad_norm": 0.0011170754441991448,
+      "learning_rate": 4.172222222222222e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.0009609300759620965,
+      "learning_rate": 3.894444444444444e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 5.072463768115942,
+      "grad_norm": 0.0007455663289874792,
+      "learning_rate": 3.6166666666666674e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 5.797101449275362,
+      "grad_norm": 0.0007628346793353558,
+      "learning_rate": 3.338888888888889e-05,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 6.521739130434782,
+      "grad_norm": 0.0006400482379831374,
+      "learning_rate": 3.061111111111111e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 0.0006571674603037536,
+      "learning_rate": 2.7833333333333333e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 7.971014492753623,
+      "grad_norm": 0.0004984458209946752,
+      "learning_rate": 2.5055555555555555e-05,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.0005247824592515826,
+      "learning_rate": 2.2277777777777778e-05,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 9.420289855072463,
+      "grad_norm": 0.0005136411054991186,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.0,
+      "step": 650
+    },
+    {
+      "epoch": 10.144927536231885,
+      "grad_norm": 0.00042652638512663543,
+      "learning_rate": 1.6722222222222222e-05,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 10.869565217391305,
+      "grad_norm": 0.0003991111880168319,
+      "learning_rate": 1.3944444444444446e-05,
+      "loss": 0.0,
+      "step": 750
+    },
+    {
+      "epoch": 11.594202898550725,
+      "grad_norm": 0.00043558661127462983,
+      "learning_rate": 1.1166666666666668e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 12.318840579710145,
+      "grad_norm": 0.00038388941902667284,
+      "learning_rate": 8.38888888888889e-06,
+      "loss": 0.0,
+      "step": 850
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 0.00033727928530424833,
+      "learning_rate": 5.611111111111112e-06,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 13.768115942028986,
+      "grad_norm": 0.00039866630686447024,
+      "learning_rate": 2.8333333333333335e-06,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 14.492753623188406,
+      "grad_norm": 0.0003358957765158266,
+      "learning_rate": 5.555555555555556e-08,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 14.492753623188406,
+      "step": 1000,
+      "total_flos": 2082787114229760.0,
+      "train_loss": 0.005802426487207413,
+      "train_runtime": 92.609,
+      "train_samples_per_second": 86.385,
+      "train_steps_per_second": 10.798
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2082787114229760.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c3a461e3ba2faf007cf1e1a4b4dbacf3ad73530048f577026aed3bb7e7730b
+size 5777