Upload fine-tuned encoder

README.md

@@ -0,0 +1,11 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags: [text-classification, compliance, cross-encoder]
+---
+
+# CallGuard encoder
+
+DeBERTa-v3-small fine-tuned as a cross-encoder: input is (rule or event description, previous turn +
+current turn of a loan-collection call), output is whether the turn matches the description. Trained on
+synthetic, Gemini-written calls only. Part of the CallGuard portfolio project; not for production use.

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484141b37446507a630c5fed12f7b529cb1f731b7d234fd59125469cd6b78170
+size 567598552

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training.json

@@ -0,0 +1,14 @@
+{
+  "data": "/kaggle/working/callguard/data/synthetic.jsonl",
+  "out": "data/models/encoder",
+  "base": "microsoft/deberta-v3-small",
+  "epochs": 3,
+  "batch": 32,
+  "lr": 3e-05,
+  "neg_ratio": 4.0,
+  "seed": 13,
+  "positives": 2964,
+  "negatives": 11856,
+  "hard_negatives": 4396,
+  "seconds": 371.22081422805786
+}