wikimia_unlearned

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openlm-research/open_llama_7b
+model-index:
+- name: grad_ascent_2e-05_WikiMIA_QA_256_50
+  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. -->
+
+# grad_ascent_2e-05_WikiMIA_QA_256_50
+
+This model was trained from scratch 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 26
+- training_steps: 1337
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,91 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.28.self_attn.v_proj",
+    "model.layers.29.self_attn.q_proj",
+    "model.layers.28.self_attn.q_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.30.self_attn.v_proj",
+    "model.layers.31.self_attn.v_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.29.self_attn.v_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.0.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47e906698c3bab89a8e978538163b7103e302e751d3d751698dd64f79d2edec
+size 8405600

config.yaml

@@ -0,0 +1,45 @@
+model_family: llama-7b
+model_path: openlm-research/open_llama_7b
+LoRA:
+  r: 8
+  alpha: 32
+  dropout: 0.05
+lr: 2.0e-05
+split: WikiMIA_QA_256
+data_path: l
+gradient_accumulation_steps: 4
+num_epochs: 50
+forget_loss: grad_ascent
+file_path: /root/kdu/output/openlm-research/open_llama_7b_lluvecwonv_WikiMIA_QA_WikiMIA_QA_256_logit
+save_dir: ${model_family}/${forget_loss}_${lr}_${split}_${num_epochs}
+overwrite_dir: true
+weight_decay: 0.01
+save_model: true
+eval_while_train: false
+eval_only: falseZ
+seed: 42
+master_port: 18765
+eval:
+  model_path: ${..model_path}
+  model_family: ${..model_family}
+  save_dir: ${..save_dir}
+  data_path: luvecwonv/WikiMIA_QA
+  split: ${..split}
+  eval_task:
+  - eval_log
+  - eval_log_forget
+  question_key:
+  - Query
+  - Query
+  answer_key:
+  - Answer
+  - Answer
+generation:
+  max_length: 200
+  max_new_tokens: null
+save_generated_text: true
+ds_size: 300
+overwrite: true
+use_pretrained: false
+batch_size: 4
+retain_result: null

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906c1d35db05a42e793d523b836f1696127f4d67e67aba06ffd32a30a6cad42f
+size 6648