End of training

README.md

@@ -0,0 +1,49 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/privacy-filter
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [openai/privacy-filter](https://huggingface.co/openai/privacy-filter) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 64
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Framework versions
+
+- Transformers 5.8.0.dev0
+- Pytorch 2.10.0+cu128
+- Datasets 4.8.3
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,104 @@
+{
+  "architectures": [
+    "OpenAIPrivacyFilterForTokenClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_dropout": 0.0,
+  "default_n_ctx": 128000,
+  "dtype": "float16",
+  "eos_token_id": 199999,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 640,
+  "id2label": {
+    "0": "O",
+    "1": "B-COMPETITOR_MENTION",
+    "2": "I-COMPETITOR_MENTION",
+    "3": "E-COMPETITOR_MENTION",
+    "4": "S-COMPETITOR_MENTION",
+    "5": "B-PRIVACY_PII",
+    "6": "I-PRIVACY_PII",
+    "7": "E-PRIVACY_PII",
+    "8": "S-PRIVACY_PII",
+    "9": "B-PROFANITY",
+    "10": "I-PROFANITY",
+    "11": "E-PROFANITY",
+    "12": "S-PROFANITY",
+    "13": "B-FINANCIAL_ADVICE",
+    "14": "I-FINANCIAL_ADVICE",
+    "15": "E-FINANCIAL_ADVICE",
+    "16": "S-FINANCIAL_ADVICE",
+    "17": "B-HARMFUL_CONTENT",
+    "18": "I-HARMFUL_CONTENT",
+    "19": "E-HARMFUL_CONTENT",
+    "20": "S-HARMFUL_CONTENT",
+    "21": "B-CONFIDENTIAL_DISCLOSURE",
+    "22": "I-CONFIDENTIAL_DISCLOSURE",
+    "23": "E-CONFIDENTIAL_DISCLOSURE",
+    "24": "S-CONFIDENTIAL_DISCLOSURE"
+  },
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 640,
+  "label2id": {
+    "B-COMPETITOR_MENTION": 1,
+    "B-CONFIDENTIAL_DISCLOSURE": 21,
+    "B-FINANCIAL_ADVICE": 13,
+    "B-HARMFUL_CONTENT": 17,
+    "B-PRIVACY_PII": 5,
+    "B-PROFANITY": 9,
+    "E-COMPETITOR_MENTION": 3,
+    "E-CONFIDENTIAL_DISCLOSURE": 23,
+    "E-FINANCIAL_ADVICE": 15,
+    "E-HARMFUL_CONTENT": 19,
+    "E-PRIVACY_PII": 7,
+    "E-PROFANITY": 11,
+    "I-COMPETITOR_MENTION": 2,
+    "I-CONFIDENTIAL_DISCLOSURE": 22,
+    "I-FINANCIAL_ADVICE": 14,
+    "I-HARMFUL_CONTENT": 18,
+    "I-PRIVACY_PII": 6,
+    "I-PROFANITY": 10,
+    "O": 0,
+    "S-COMPETITOR_MENTION": 4,
+    "S-CONFIDENTIAL_DISCLOSURE": 24,
+    "S-FINANCIAL_ADVICE": 16,
+    "S-HARMFUL_CONTENT": 20,
+    "S-PRIVACY_PII": 8,
+    "S-PROFANITY": 12
+  },
+  "max_position_embeddings": 131072,
+  "model_type": "openai_privacy_filter",
+  "num_attention_heads": 14,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_theta": 150000.0,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model": 1,
+      "model.onnx": 3,
+      "model_fp16.onnx": 2
+    }
+  },
+  "transformers_version": "5.8.0.dev0",
+  "use_cache": false,
+  "vocab_size": 200064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3cc1c8f915f3c5aed6eccdd049bcca8210454aaa18c2d242b824e6a809a749
+size 2799581050

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a71e738113b99a1bcf3aff22419c7f2d5a227ec2c3e808fdaa576a9726a977f
+size 5265