/jsdiff-jsdiff-zephyr-cyber-20250526T215524

README.md

@@ -0,0 +1,58 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
+tags:
+- generated_from_trainer
+model-index:
+- name: 20250526T215524
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nmndeep/huggingface/runs/qo6nzsgh)
+# 20250526T215524
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) 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-07
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 150
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.1.post300
+- Datasets 3.6.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

full_config.json

@@ -0,0 +1 @@
+{"args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "results/jsdiff-HuggingFaceH4-zephyr-7b-beta-cyber/20250526T215524", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 1, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 2e-07, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/May26_21-55-24_compute-891", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "no", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 3, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "jsdiff-zephyr-cyber-20250526T215524", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": 0, "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 3\nLocal process index: 3\nDevice: cuda:3\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:3", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7fcbbaf235c0>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None, enable_msamp=False, msamp_opt_level='O1')"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "cyber", "use_chat_template_p": 0.5, "retain_mult": 1.0}}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170dbf9ba1fc6ba8b451795320895dfeb957538b341db0979197ca63980cc400
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905187e3e29190dd5b3bdefb97dd08c154b9b8cf7b84f04c3266ecd49419132d
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37b851f1e77e2565e32139affa19b73734ebbd753fc18fa2cec9fa995bc55a2
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

results.jsonl

@@ -0,0 +1,4 @@
+{"mmlu_unlearned": 0.4215211508332146, "wmdp-bio_unlearned": 0.4587588373919874, "wmdp-chem_unlearned": 0.34558823529411764, "wmdp-cyber_unlearned": 0.3392048314041268, "mmlu_unlearned_chat": 0.39431704885343966, "wmdp-bio_unlearned_chat": 0.37077769049489395, "wmdp-chem_unlearned_chat": 0.2818627450980392, "wmdp-cyber_unlearned_chat": 0.2934071464519376, "args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "results/jsdiff-HuggingFaceH4-zephyr-7b-beta-cyber/20250526T215524", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 1, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 2e-07, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/May26_21-55-24_compute-891", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "no", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 2, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "jsdiff-zephyr-cyber-20250526T215524", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": 0, "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 2\nLocal process index: 2\nDevice: cuda:2\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:2", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7f008b3e5f70>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None, enable_msamp=False, msamp_opt_level='O1')"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "cyber", "use_chat_template_p": 0.5, "retain_mult": 1.0}}
+{"mmlu_unlearned": 0.4215211508332146, "wmdp-bio_unlearned": 0.4587588373919874, "wmdp-chem_unlearned": 0.34558823529411764, "wmdp-cyber_unlearned": 0.3392048314041268, "mmlu_unlearned_chat": 0.39431704885343966, "wmdp-bio_unlearned_chat": 0.37077769049489395, "wmdp-chem_unlearned_chat": 0.2818627450980392, "wmdp-cyber_unlearned_chat": 0.2934071464519376, "args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "results/jsdiff-HuggingFaceH4-zephyr-7b-beta-cyber/20250526T215524", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 1, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 2e-07, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/May26_21-55-24_compute-891", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "no", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 1, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "jsdiff-zephyr-cyber-20250526T215524", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": 0, "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 1\nLocal process index: 1\nDevice: cuda:1\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:1", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7efdc5e9fdd0>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None, enable_msamp=False, msamp_opt_level='O1')"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "cyber", "use_chat_template_p": 0.5, "retain_mult": 1.0}}
+{"mmlu_unlearned": 0.4215211508332146, "wmdp-bio_unlearned": 0.4587588373919874, "wmdp-chem_unlearned": 0.34558823529411764, "wmdp-cyber_unlearned": 0.3392048314041268, "mmlu_unlearned_chat": 0.39431704885343966, "wmdp-bio_unlearned_chat": 0.37077769049489395, "wmdp-chem_unlearned_chat": 0.2818627450980392, "wmdp-cyber_unlearned_chat": 0.2934071464519376, "args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "results/jsdiff-HuggingFaceH4-zephyr-7b-beta-cyber/20250526T215524", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 1, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 2e-07, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/May26_21-55-24_compute-891", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "no", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 3, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "jsdiff-zephyr-cyber-20250526T215524", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": 0, "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 3\nLocal process index: 3\nDevice: cuda:3\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:3", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7fcbbaf235c0>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None, enable_msamp=False, msamp_opt_level='O1')"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "cyber", "use_chat_template_p": 0.5, "retain_mult": 1.0}}
+{"mmlu_unlearned": 0.4215211508332146, "wmdp-bio_unlearned": 0.4587588373919874, "wmdp-chem_unlearned": 0.34558823529411764, "wmdp-cyber_unlearned": 0.3392048314041268, "mmlu_unlearned_chat": 0.39431704885343966, "wmdp-bio_unlearned_chat": 0.37077769049489395, "wmdp-chem_unlearned_chat": 0.2818627450980392, "wmdp-cyber_unlearned_chat": 0.2934071464519376, "args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "results/jsdiff-HuggingFaceH4-zephyr-7b-beta-cyber/20250526T215524", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 1, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 2e-07, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/May26_21-55-24_compute-891", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "no", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 0, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "jsdiff-zephyr-cyber-20250526T215524", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": 0, "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 4\nProcess index: 0\nLocal process index: 0\nDevice: cuda:0\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:0", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7fe1c1907530>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None, enable_msamp=False, msamp_opt_level='O1')"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "cyber", "use_chat_template_p": 0.5, "retain_mult": 1.0}}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b65f83297e06eaff2b33298c73663467a85f4273f5271f8155b0c5f816efa9
+size 7096