初始化项目，由ModelHub XC社区提供模型

Model: anime-sh/llama-3_1-8b-undial-bm25-10b-rebuttal
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

config.yaml

@@ -0,0 +1,35 @@
+model_name: meta-llama/Llama-3.1-8B
+forget_path: unlearning-cleanslate/fsid-curated-llama-8b:forget:bm25_10B
+retain_path: unlearning-cleanslate/fsid-curated-llama-8b:retain:bm25_10B
+output_dir: results/rebuttal/train/llama-3_1-8b-undial-bm25-10b
+objective: undial
+num_epochs: 2
+batch_size: 8
+gradient_accum_steps: 4
+lr: 1.0e-05
+weight_decay: 0.0
+warmup_steps: 20
+max_grad_norm: 1.0
+forget_weight: 1.0
+retain_weight: 1.0
+retain_loss_type: nll
+npo_beta: 0.1
+simnpo_delta: 0.0
+rmu_steering_coeff: 2.0
+rmu_module_regex: model\.layers\.7
+rmu_control_vec_seed: 0
+undial_beta: 10.0
+save_every: 200
+fsdp_sharding_strategy: full_shard
+dtype: bfloat16
+seed: 42
+num_workers: 0
+log_every: 10
+gradient_checkpointing: false
+torch_compile: false
+push_to_hub: true
+hub_repo_id: unlearning-cleanslate/llama-3_1-8b-undial-bm25-10b
+hub_private: false
+optim: adamw_torch
+_run_name: undial_Llama-3.1-8B_20260724_004857
+_run_dir: results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.6.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f800d33586a3c01f2d16db241cfafb3894822e57d7164a3c6ff8edbca754b3cb
+size 16060556616

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

train.log

@@ -0,0 +1,6 @@
+2026-07-24 00:49:09,471 INFO cleanslate.fsid.training.trainer: [RANK 0] FSID train: model=meta-llama/Llama-3.1-8B objective=undial run_dir=results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857
+2026-07-24 00:49:09,471 INFO cleanslate.fsid.training.trainer: [RANK 0] Creating frozen reference model for undial (dtype=torch.bfloat16)
+2026-07-24 00:49:14,924 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=undial epochs=2
+2026-07-24 01:02:31,997 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857
+2026-07-24 01:02:32,003 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (755.7s)
+2026-07-24 01:02:32,518 INFO cleanslate.fsid.training.trainer: [RANK 0] Pushing checkpoint dir results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857 to unlearning-cleanslate/llama-3_1-8b-undial-bm25-10b

train_summary.json

@@ -0,0 +1,48 @@
+{
+  "run_name": "undial_Llama-3.1-8B_20260724_004857",
+  "run_dir": "results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857",
+  "config": {
+    "model_name": "meta-llama/Llama-3.1-8B",
+    "forget_path": "unlearning-cleanslate/fsid-curated-llama-8b:forget:bm25_10B",
+    "retain_path": "unlearning-cleanslate/fsid-curated-llama-8b:retain:bm25_10B",
+    "output_dir": "results/rebuttal/train/llama-3_1-8b-undial-bm25-10b",
+    "objective": "undial",
+    "num_epochs": 2,
+    "batch_size": 8,
+    "gradient_accum_steps": 4,
+    "lr": 1e-05,
+    "weight_decay": 0.0,
+    "warmup_steps": 20,
+    "max_grad_norm": 1.0,
+    "forget_weight": 1.0,
+    "retain_weight": 1.0,
+    "retain_loss_type": "nll",
+    "npo_beta": 0.1,
+    "simnpo_delta": 0.0,
+    "rmu_steering_coeff": 2.0,
+    "rmu_module_regex": "model\\.layers\\.7",
+    "rmu_control_vec_seed": 0,
+    "undial_beta": 10.0,
+    "save_every": 200,
+    "fsdp_sharding_strategy": "full_shard",
+    "dtype": "bfloat16",
+    "seed": 42,
+    "num_workers": 0,
+    "log_every": 10,
+    "gradient_checkpointing": false,
+    "torch_compile": false,
+    "push_to_hub": true,
+    "hub_repo_id": "unlearning-cleanslate/llama-3_1-8b-undial-bm25-10b",
+    "hub_private": false,
+    "optim": "adamw_torch"
+  },
+  "num_forget_rows": 6350,
+  "num_forget_pairs": 6350,
+  "num_retain_rows": 1646,
+  "num_retain_sequences": 1646,
+  "num_trainable_params": 8030261248,
+  "num_total_params": 8030261248,
+  "run_seconds": 755.7152915000916,
+  "checkpoint_dir": "results/rebuttal/train/llama-3_1-8b-undial-bm25-10b/undial_Llama-3.1-8B_20260724_004857",
+  "is_main_process": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275ed5dd7331c8f6ea92c6b9e5cad2c39b03f49a22916384e88b76f438fefcd1
+size 5329