Upload folder using huggingface_hub

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/my_qwen2.5omni/v5_200w_32gpus_full_params_add_aligner/checkpoint-2400",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(thinker\\.model(?=\\.).*\\.(k_proj|q_proj|up_proj|down_proj|o_proj|v_proj|gate_proj)|thinker\\.audio_tower\\.proj(?=\\.)|thinker\\.visual\\.merger(?=\\.).*\\.(2|0))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72811dc122434be878f1dbaf172198d2feb8f3d87f1d51601d09119a99ce2fea
+size 650829032

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/args.json

@@ -0,0 +1,491 @@
+{
+  "output_dir": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-07,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 1.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 50.0,
+  "save_total_limit": 5,
+  "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": 42,
+  "jit_mode_eval": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 50.0,
+  "dataloader_num_workers": 32,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "project": "huggingface",
+  "trackio_space_id": "trackio",
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "hub_revision": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": "sigmoid",
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/my_qwen2.5omni/v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/",
+  "model_type": "my_qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "my_qwen2_5_omni",
+  "system": null,
+  "max_length": 8192,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "last_round",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/full_length_tagging/train_dpo.jsonl",
+    "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/gemini70w_with_bpm/train_dpo.jsonl",
+    "/apdcephfs_zwfy7/share_304725743/user/dapengwu/qwen2.5/bgm_data/train_dpo.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.001,
+  "dataset_num_proc": 16,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 512,
+  "temperature": 0.9,
+  "top_k": 50,
+  "top_p": 0.9,
+  "repetition_penalty": 1.0,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "ckpt_dir": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/my_qwen2.5omni/v5_200w_32gpus_full_params_add_aligner/checkpoint-2400/",
+  "lora_modules": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": true,
+  "custom_register_path": [
+    "register_model/my_register.py"
+  ],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "sft_alpha": 0,
+  "chord_sft_dataset": [],
+  "chord_sft_per_device_train_batch_size": null,
+  "chord_enable_phi_function": false,
+  "chord_mu_warmup_steps": null,
+  "chord_mu_decay_steps": null,
+  "chord_mu_peak": null,
+  "chord_mu_valley": null,
+  "reward_model": null,
+  "reward_adapters": [],
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "num_ppo_epochs": 4,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_mini_batches": 1,
+  "local_rollout_forward_batch_size": 64,
+  "num_sample_generations": 10,
+  "response_length": 512,
+  "missing_eos_penalty": null,
+  "vllm_gpu_memory_utilization": 0.9,
+  "vllm_tensor_parallel_size": 1,
+  "vllm_pipeline_parallel_size": 1,
+  "vllm_enable_expert_parallel": false,
+  "vllm_max_num_seqs": null,
+  "vllm_max_model_len": null,
+  "vllm_disable_custom_all_reduce": true,
+  "vllm_enforce_eager": false,
+  "vllm_limit_mm_per_prompt": null,
+  "vllm_max_lora_rank": 16,
+  "vllm_enable_prefix_caching": true,
+  "vllm_use_async_engine": null,
+  "vllm_quantization": null,
+  "vllm_reasoning_parser": null,
+  "vllm_disable_cascade_attn": false,
+  "vllm_mm_processor_cache_gb": null,
+  "vllm_speculative_config": null,
+  "vllm_engine_kwargs": {},
+  "vllm_data_parallel_size": 1,
+  "use_vllm": false,
+  "vllm_mode": null,
+  "vllm_enable_lora": false,
+  "vllm_server_base_url": null,
+  "vllm_server_host": null,
+  "vllm_server_port": [
+    8000
+  ],
+  "vllm_server_timeout": 240.0,
+  "vllm_server_group_port": null,
+  "enable_flattened_weight_sync": true,
+  "async_generate": false,
+  "sleep_level": 0,
+  "move_model_batches": null,
+  "offload_optimizer": false,
+  "offload_model": false,
+  "wandb_log_unique_prompts": null,
+  "epsilon": 0.2,
+  "epsilon_high": null,
+  "delta": null,
+  "cosine_min_len_value_wrong": -0.5,
+  "cosine_max_len_value_wrong": 0.0,
+  "cosine_min_len_value_correct": 1.0,
+  "cosine_max_len_value_correct": 0.5,
+  "cosine_max_len": null,
+  "repetition_n_grams": 3,
+  "repetition_max_penalty": -1.0,
+  "reward_model_plugin": null,
+  "sync_ref_model": false,
+  "ref_model_sync_steps": 512,
+  "ref_model_mixup_alpha": 0.6,
+  "multi_turn_scheduler": null,
+  "max_turns": null,
+  "completion_length_limit_scope": "per_round",
+  "vllm_server_pass_dataset": false,
+  "dynamic_sample": false,
+  "max_resample_times": 3,
+  "overlong_filter": false,
+  "soft_max_length": null,
+  "soft_cache_length": null,
+  "scale_rewards": null,
+  "log_entropy": false,
+  "top_entropy_quantile": 1.0,
+  "importance_sampling_level": "token",
+  "tau_pos": 1.0,
+  "tau_neg": 1.05,
+  "advantage_estimator": "grpo",
+  "kl_in_reward": null,
+  "generation_batch_size": null,
+  "steps_per_generation": null,
+  "num_generations_eval": null,
+  "rollout_importance_sampling_mode": null,
+  "rollout_importance_sampling_threshold": 2.0,
+  "log_rollout_offpolicy_metrics": false,
+  "off_policy_sequence_mask_delta": null,
+  "num_generations": 8,
+  "reward_funcs": [],
+  "reward_weights": null,
+  "log_completions": false,
+  "num_iterations": 1,
+  "teacher_model": null,
+  "teacher_adapters": [],
+  "teacher_model_type": null,
+  "teacher_model_revision": null,
+  "teacher_deepspeed": null,
+  "rlhf_type": "dpo",
+  "ref_model": null,
+  "ref_adapters": [],
+  "ref_model_type": null,
+  "ref_model_revision": null,
+  "beta": 0.3,
+  "label_smoothing": 0,
+  "max_completion_length": 512,
+  "rpo_alpha": null,
+  "ld_alpha": null,
+  "discopop_tau": 0.05,
+  "loss_weights": null,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "center_rewards_coefficient": null,
+  "lmbda": 0.5,
+  "seq_kd": false,
+  "offload_teacher_model": false,
+  "rank": 0,
+  "global_world_size": 24,
+  "local_world_size": 8,
+  "model_suffix": "checkpoint-2400",
+  "model_info": "ModelInfo(model_type='my_qwen2_5_omni', model_dir='/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/my_qwen2.5omni/v5_200w_32gpus_full_params_add_aligner/checkpoint-2400', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='my_qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='my_qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7f13726191c0>, model_arch=MultiModelKeys(arch_name='my_qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model', 'thinker.lm_head'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/apdcephfs_zwfy7/share_304725743/user/dapengwu/ckpts/my_qwen2.5omni/v5_200w_32gpus_full_params_add_aligner/checkpoint-2400",
+  "_val_dataset_exists": true,
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "DPOConfig(output_dir='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-07, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=5, 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=42, jit_mode_eval=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=50, dataloader_num_workers=32, dataloader_prefetch_factor=2, past_index=-1, run_name='/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, force_use_ref_model=False, disable_dropout=True, use_logits_to_keep=None, dataset_num_proc=16, pad_token=None, label_pad_token_id=None, max_prompt_length=512, max_completion_length=512, max_length=8192, truncation_mode='keep_end', padding_free=False, precompute_ref_log_probs=False, precompute_ref_batch_size=None, tools=None, loss_type='sigmoid', use_liger_loss=False, base_model_attribute_name='model', beta=0.3, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, reference_free=False, label_smoothing=0, use_weighting=False, rpo_alpha=None, ld_alpha=None, discopop_tau=0.05, loss_weights=None, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, generate_during_eval=False, padding_value=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
+}

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eb4ecc975a14b33d09fb598afef1dca49ade9b7d06a50ed18bd826a153ab08
+size 1301878966

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06fea830cf5ad73ec00d500ea6fb952740ac936f18e93fa2d32abde1ea3ead92
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be561d1df19be227394d8ea607c54262a06c9bf880af0aa5e04a52596a2a6cb0
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6e873ef7eb1ee764b141e00436d95ae84f5e283b62ef78418499e58bbfe269
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8189b8d6309350dc3f506f84bbf3829366c3e0419ab03423fc6e03db9f84b71
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afe4e0855da5633444c1ccd54a6e135e383e87fcceae975bc844b8ee96b39fc
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ff1f2b4cb6d8075fde051ddb13c19804b2c5b1508ca588a4a0f8a12b779cce
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3f4031fb5ad41c3f19386f9909ea4209390d1c770bf4439a476aad606eb8cd
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad5d3c9e8a237de4f3fe27fb8013bac32e96076a776cb7ad3f0191a3d291522
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92db46b1fbab9acab0551d2192d1c90db4e3e4969f3e2485d9f168bd4d5801d1
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09947079a7c5925e88b6b5b900c93fd891395f0bd928be51da90309aab219951
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e297fbb38d5ae0d9c405733ff6c4a03deb6134d8b2603714f52698e2be52ed05
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3133ed4ef991fc8457edb64fb926cd3c5273213f5fa7a3c733b000dc7d2bce
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f3e24417a59435f5a8450a4aeb0f09cc92734b5c3b45a0701b2c043c415c05
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b8fae7b4a035c5a11612a3145e0a2ac25237bf70e2bb9f0c0fbca5c51575a0
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9466e1b74e4eb252fb5e29a4325bb118423bbc7607bdb4a2d1b167a677985a
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20712ff600cec8f8f3b473df93b5799fae819dc1c8c96c582152ad88a9be71ee
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b640ece83306da6f71240c18a22d5b5d5a6817b9d59a0b4b75fc6edbba13104
+size 15997

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bea02744c29f30024590ab1629a0e7b7dabbf1e8476456c2e7c5ce46dc35c28
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041be966454b60c86af576fc1eb7f34189114689abff8f9622b947110f7334c8
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85766f6596d15a810177d77dd259d9b50588cf100ec5f8ebff5fed881d57957
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be75d04b1ebe614241b88fd010a5dda1b7bf703c00c6ebe310ca07975830fe7
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4699833a7ab4cb692996ef7567f934c0bac79d6a067963a873f89a38e412bd48
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89723267a126c5cc4f2c4fb83066b385421402cef9eb7df415224dc4a2b5d99e
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1159bad0a51a4150e76aee1f34e2c15f908a7ed2369755b493e8c6051d0a1d6
+size 15984

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21235947a3c959f8259e4b2baa3c305a2390457096dbd7d825d035f219f109a7
+size 1064

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/trainer_state.json

@@ -0,0 +1,713 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.34822008,
+  "best_model_checkpoint": "/apdcephfs_cq12/share_300883980/user/dapengwu/qwen2.5_omini/dpo_exps/v5_dpo_lora64_adjust_batch_lr_loraalpha128/v0-20260416-232302/checkpoint-200",
+  "epoch": 0.0768787238131847,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0003843936190659235,
+      "grad_norm": 4.293529033660889,
+      "learning_rate": 3.81679389312977e-09,
+      "logits/chosen": -0.4946533441543579,
+      "logits/rejected": -0.6037911176681519,
+      "logps/chosen": -19.720417022705078,
+      "logps/rejected": -43.516265869140625,
+      "loss": 0.6931471824645996,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0019219680953296175,
+      "grad_norm": 4.1817474365234375,
+      "learning_rate": 1.9083969465648856e-08,
+      "logits/chosen": -0.47982221841812134,
+      "logits/rejected": -0.5812068581581116,
+      "logps/chosen": -18.85796356201172,
+      "logps/rejected": -42.22263717651367,
+      "loss": 0.6936763525009155,
+      "rewards/accuracies": 0.3776041865348816,
+      "rewards/chosen": 0.0001914103631861508,
+      "rewards/margins": -4.660768900066614e-05,
+      "rewards/rejected": 0.0002380187506787479,
+      "step": 5
+    },
+    {
+      "epoch": 0.003843936190659235,
+      "grad_norm": 4.946111679077148,
+      "learning_rate": 3.816793893129771e-08,
+      "logits/chosen": -0.46230238676071167,
+      "logits/rejected": -0.5869696140289307,
+      "logps/chosen": -19.085437774658203,
+      "logps/rejected": -45.05614471435547,
+      "loss": 0.6927316188812256,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.0007313586538657546,
+      "rewards/margins": 0.002310951240360737,
+      "rewards/rejected": -0.0030423104763031006,
+      "step": 10
+    },
+    {
+      "epoch": 0.005765904285988853,
+      "grad_norm": 4.139771461486816,
+      "learning_rate": 5.725190839694656e-08,
+      "logits/chosen": -0.48264679312705994,
+      "logits/rejected": -0.600085973739624,
+      "logps/chosen": -18.240331649780273,
+      "logps/rejected": -42.52822494506836,
+      "loss": 0.6923247814178467,
+      "rewards/accuracies": 0.5229166746139526,
+      "rewards/chosen": -0.000312447635224089,
+      "rewards/margins": 0.0029608439654111862,
+      "rewards/rejected": -0.003273291978985071,
+      "step": 15
+    },
+    {
+      "epoch": 0.00768787238131847,
+      "grad_norm": 4.232036113739014,
+      "learning_rate": 7.633587786259542e-08,
+      "logits/chosen": -0.4623951315879822,
+      "logits/rejected": -0.5852587819099426,
+      "logps/chosen": -18.5986385345459,
+      "logps/rejected": -42.8640022277832,
+      "loss": 0.6922575950622558,
+      "rewards/accuracies": 0.5333333611488342,
+      "rewards/chosen": 0.00246702553704381,
+      "rewards/margins": 0.0032769222743809223,
+      "rewards/rejected": -0.0008098973776213825,
+      "step": 20
+    },
+    {
+      "epoch": 0.009609840476648087,
+      "grad_norm": 4.684337139129639,
+      "learning_rate": 9.541984732824428e-08,
+      "logits/chosen": -0.4787112772464752,
+      "logits/rejected": -0.5966706275939941,
+      "logps/chosen": -18.455795288085938,
+      "logps/rejected": -43.34617614746094,
+      "loss": 0.6942302227020264,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 0.0012611036654561758,
+      "rewards/margins": -0.0007622581906616688,
+      "rewards/rejected": 0.002023361623287201,
+      "step": 25
+    },
+    {
+      "epoch": 0.011531808571977706,
+      "grad_norm": 4.2680768966674805,
+      "learning_rate": 1.1450381679389312e-07,
+      "logits/chosen": -0.4719389081001282,
+      "logits/rejected": -0.5768855810165405,
+      "logps/chosen": -18.71193504333496,
+      "logps/rejected": -43.73603057861328,
+      "loss": 0.6943673133850098,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.00045108445920050144,
+      "rewards/margins": -0.0010674952063709497,
+      "rewards/rejected": 0.0015185800148174167,
+      "step": 30
+    },
+    {
+      "epoch": 0.013453776667307323,
+      "grad_norm": 4.50374698638916,
+      "learning_rate": 1.3358778625954197e-07,
+      "logits/chosen": -0.46296659111976624,
+      "logits/rejected": -0.5806670784950256,
+      "logps/chosen": -19.136947631835938,
+      "logps/rejected": -45.39435577392578,
+      "loss": 0.6952664375305175,
+      "rewards/accuracies": 0.4854166507720947,
+      "rewards/chosen": -0.002827567746862769,
+      "rewards/margins": -0.0027196344453841448,
+      "rewards/rejected": -0.00010793330147862434,
+      "step": 35
+    },
+    {
+      "epoch": 0.01537574476263694,
+      "grad_norm": 3.9700841903686523,
+      "learning_rate": 1.5267175572519085e-07,
+      "logits/chosen": -0.4721706509590149,
+      "logits/rejected": -0.5723752379417419,
+      "logps/chosen": -19.014514923095703,
+      "logps/rejected": -43.168453216552734,
+      "loss": 0.6937965393066406,
+      "rewards/accuracies": 0.4854167103767395,
+      "rewards/chosen": 0.0013095636386424303,
+      "rewards/margins": 0.0003374307416379452,
+      "rewards/rejected": 0.0009721327805891633,
+      "step": 40
+    },
+    {
+      "epoch": 0.01729771285796656,
+      "grad_norm": 4.344980239868164,
+      "learning_rate": 1.717557251908397e-07,
+      "logits/chosen": -0.47004976868629456,
+      "logits/rejected": -0.5900046229362488,
+      "logps/chosen": -19.65897560119629,
+      "logps/rejected": -44.214195251464844,
+      "loss": 0.6930476188659668,
+      "rewards/accuracies": 0.5104166865348816,
+      "rewards/chosen": 0.002793198451399803,
+      "rewards/margins": 0.0018065006006509066,
+      "rewards/rejected": 0.000986698316410184,
+      "step": 45
+    },
+    {
+      "epoch": 0.019219680953296174,
+      "grad_norm": 4.425153732299805,
+      "learning_rate": 1.9083969465648855e-07,
+      "logits/chosen": -0.45245224237442017,
+      "logits/rejected": -0.5839039087295532,
+      "logps/chosen": -19.584203720092773,
+      "logps/rejected": -45.13101577758789,
+      "loss": 0.6933013439178467,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -7.72332277847454e-05,
+      "rewards/margins": 0.0013835743302479386,
+      "rewards/rejected": -0.0014608076307922602,
+      "step": 50
+    },
+    {
+      "epoch": 0.019219680953296174,
+      "eval_logits/chosen": -0.45866870880126953,
+      "eval_logits/rejected": -0.5743271708488464,
+      "eval_logps/chosen": -18.367704391479492,
+      "eval_logps/rejected": -43.83530044555664,
+      "eval_loss": 0.6924768090248108,
+      "eval_rewards/accuracies": 0.5189394354820251,
+      "eval_rewards/chosen": 0.0011043355334550142,
+      "eval_rewards/margins": 0.004569374956190586,
+      "eval_rewards/rejected": -0.003465038724243641,
+      "eval_runtime": 134.8399,
+      "eval_samples_per_second": 1.839,
+      "eval_steps_per_second": 0.082,
+      "step": 50
+    },
+    {
+      "epoch": 0.021141649048625793,
+      "grad_norm": 4.3253960609436035,
+      "learning_rate": 2.0992366412213738e-07,
+      "logits/chosen": -0.4675160348415375,
+      "logits/rejected": -0.5794423818588257,
+      "logps/chosen": -19.271347045898438,
+      "logps/rejected": -43.26808547973633,
+      "loss": 0.6872461318969727,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0006552102277055383,
+      "rewards/margins": 0.013609659858047962,
+      "rewards/rejected": -0.012954448349773884,
+      "step": 55
+    },
+    {
+      "epoch": 0.02306361714395541,
+      "grad_norm": 3.9266550540924072,
+      "learning_rate": 2.2900763358778623e-07,
+      "logits/chosen": -0.46838292479515076,
+      "logits/rejected": -0.5767039060592651,
+      "logps/chosen": -19.335512161254883,
+      "logps/rejected": -42.57781219482422,
+      "loss": 0.6889264583587646,
+      "rewards/accuracies": 0.5812500715255737,
+      "rewards/chosen": 0.0010080452775582671,
+      "rewards/margins": 0.010165022686123848,
+      "rewards/rejected": -0.009156977757811546,
+      "step": 60
+    },
+    {
+      "epoch": 0.024985585239285027,
+      "grad_norm": 4.375753879547119,
+      "learning_rate": 2.480916030534351e-07,
+      "logits/chosen": -0.4690620005130768,
+      "logits/rejected": -0.5886009335517883,
+      "logps/chosen": -18.43332862854004,
+      "logps/rejected": -43.277679443359375,
+      "loss": 0.6882698059082031,
+      "rewards/accuracies": 0.5583333373069763,
+      "rewards/chosen": -0.0006353260250762105,
+      "rewards/margins": 0.011278504505753517,
+      "rewards/rejected": -0.01191383134573698,
+      "step": 65
+    },
+    {
+      "epoch": 0.026907553334614646,
+      "grad_norm": 4.386475563049316,
+      "learning_rate": 2.6717557251908394e-07,
+      "logits/chosen": -0.47125330567359924,
+      "logits/rejected": -0.5875217318534851,
+      "logps/chosen": -18.752670288085938,
+      "logps/rejected": -43.87419891357422,
+      "loss": 0.6866127014160156,
+      "rewards/accuracies": 0.5687500238418579,
+      "rewards/chosen": -0.003922345582395792,
+      "rewards/margins": 0.014560455456376076,
+      "rewards/rejected": -0.01848280057311058,
+      "step": 70
+    },
+    {
+      "epoch": 0.028829521429944265,
+      "grad_norm": 4.266760349273682,
+      "learning_rate": 2.8625954198473276e-07,
+      "logits/chosen": -0.4496544897556305,
+      "logits/rejected": -0.5769349336624146,
+      "logps/chosen": -19.44444465637207,
+      "logps/rejected": -43.631256103515625,
+      "loss": 0.6767736434936523,
+      "rewards/accuracies": 0.6770833730697632,
+      "rewards/chosen": 0.00023688860528636724,
+      "rewards/margins": 0.034430332481861115,
+      "rewards/rejected": -0.03419344872236252,
+      "step": 75
+    },
+    {
+      "epoch": 0.03075148952527388,
+      "grad_norm": 3.9680099487304688,
+      "learning_rate": 3.053435114503817e-07,
+      "logits/chosen": -0.4664226174354553,
+      "logits/rejected": -0.5924574136734009,
+      "logps/chosen": -19.605226516723633,
+      "logps/rejected": -43.656028747558594,
+      "loss": 0.6792691707611084,
+      "rewards/accuracies": 0.6562500596046448,
+      "rewards/chosen": -0.0025442407932132483,
+      "rewards/margins": 0.029593702405691147,
+      "rewards/rejected": -0.03213794156908989,
+      "step": 80
+    },
+    {
+      "epoch": 0.032673457620603495,
+      "grad_norm": 4.145585060119629,
+      "learning_rate": 3.244274809160305e-07,
+      "logits/chosen": -0.45724764466285706,
+      "logits/rejected": -0.5791772603988647,
+      "logps/chosen": -19.333683013916016,
+      "logps/rejected": -43.472023010253906,
+      "loss": 0.6773215293884277,
+      "rewards/accuracies": 0.6479166746139526,
+      "rewards/chosen": -0.003600208554416895,
+      "rewards/margins": 0.03363274782896042,
+      "rewards/rejected": -0.037232957780361176,
+      "step": 85
+    },
+    {
+      "epoch": 0.03459542571593312,
+      "grad_norm": 3.894664764404297,
+      "learning_rate": 3.435114503816794e-07,
+      "logits/chosen": -0.4617759585380554,
+      "logits/rejected": -0.5696791410446167,
+      "logps/chosen": -18.780393600463867,
+      "logps/rejected": -42.63838195800781,
+      "loss": 0.6733878135681153,
+      "rewards/accuracies": 0.6791667342185974,
+      "rewards/chosen": -0.006427527405321598,
+      "rewards/margins": 0.04172741249203682,
+      "rewards/rejected": -0.048154935240745544,
+      "step": 90
+    },
+    {
+      "epoch": 0.03651739381126273,
+      "grad_norm": 4.265499591827393,
+      "learning_rate": 3.6259541984732823e-07,
+      "logits/chosen": -0.46928292512893677,
+      "logits/rejected": -0.5851999521255493,
+      "logps/chosen": -18.90313720703125,
+      "logps/rejected": -43.33328628540039,
+      "loss": 0.6680079460144043,
+      "rewards/accuracies": 0.7354166507720947,
+      "rewards/chosen": -0.0029404996894299984,
+      "rewards/margins": 0.05274207517504692,
+      "rewards/rejected": -0.055682577192783356,
+      "step": 95
+    },
+    {
+      "epoch": 0.03843936190659235,
+      "grad_norm": 4.44418478012085,
+      "learning_rate": 3.816793893129771e-07,
+      "logits/chosen": -0.4603404402732849,
+      "logits/rejected": -0.5695813894271851,
+      "logps/chosen": -18.161109924316406,
+      "logps/rejected": -43.44052505493164,
+      "loss": 0.6560622215270996,
+      "rewards/accuracies": 0.7979167103767395,
+      "rewards/chosen": -0.001533703412860632,
+      "rewards/margins": 0.0778450146317482,
+      "rewards/rejected": -0.07937871664762497,
+      "step": 100
+    },
+    {
+      "epoch": 0.03843936190659235,
+      "eval_logits/chosen": -0.4582119286060333,
+      "eval_logits/rejected": -0.5734547972679138,
+      "eval_logps/chosen": -18.387374877929688,
+      "eval_logps/rejected": -44.120784759521484,
+      "eval_loss": 0.6532808542251587,
+      "eval_rewards/accuracies": 0.803030252456665,
+      "eval_rewards/chosen": -0.004796491004526615,
+      "eval_rewards/margins": 0.08431492745876312,
+      "eval_rewards/rejected": -0.08911141753196716,
+      "eval_runtime": 134.9337,
+      "eval_samples_per_second": 1.838,
+      "eval_steps_per_second": 0.082,
+      "step": 100
+    },
+    {
+      "epoch": 0.04036133000192197,
+      "grad_norm": 3.995300769805908,
+      "learning_rate": 4.0076335877862593e-07,
+      "logits/chosen": -0.46293720602989197,
+      "logits/rejected": -0.5748400688171387,
+      "logps/chosen": -18.307706832885742,
+      "logps/rejected": -42.99942398071289,
+      "loss": 0.6475440979003906,
+      "rewards/accuracies": 0.8458333015441895,
+      "rewards/chosen": 0.0007236793753691018,
+      "rewards/margins": 0.0957290381193161,
+      "rewards/rejected": -0.09500536322593689,
+      "step": 105
+    },
+    {
+      "epoch": 0.042283298097251586,
+      "grad_norm": 4.161820411682129,
+      "learning_rate": 4.1984732824427476e-07,
+      "logits/chosen": -0.46650171279907227,
+      "logits/rejected": -0.5801313519477844,
+      "logps/chosen": -18.438888549804688,
+      "logps/rejected": -43.18963623046875,
+      "loss": 0.6426728248596192,
+      "rewards/accuracies": 0.8833333849906921,
+      "rewards/chosen": -0.0032638213597238064,
+      "rewards/margins": 0.10625370591878891,
+      "rewards/rejected": -0.10951753705739975,
+      "step": 110
+    },
+    {
+      "epoch": 0.0442052661925812,
+      "grad_norm": 3.9095919132232666,
+      "learning_rate": 4.3893129770992364e-07,
+      "logits/chosen": -0.4581224024295807,
+      "logits/rejected": -0.577806293964386,
+      "logps/chosen": -18.798908233642578,
+      "logps/rejected": -44.98973083496094,
+      "loss": 0.6324371337890625,
+      "rewards/accuracies": 0.8791667222976685,
+      "rewards/chosen": -0.0019998387433588505,
+      "rewards/margins": 0.12881803512573242,
+      "rewards/rejected": -0.13081786036491394,
+      "step": 115
+    },
+    {
+      "epoch": 0.04612723428791082,
+      "grad_norm": 4.159756183624268,
+      "learning_rate": 4.5801526717557246e-07,
+      "logits/chosen": -0.474874347448349,
+      "logits/rejected": -0.57114577293396,
+      "logps/chosen": -18.993534088134766,
+      "logps/rejected": -44.4608154296875,
+      "loss": 0.6222764015197754,
+      "rewards/accuracies": 0.9020833969116211,
+      "rewards/chosen": -0.0016362626338377595,
+      "rewards/margins": 0.15149512887001038,
+      "rewards/rejected": -0.1531314104795456,
+      "step": 120
+    },
+    {
+      "epoch": 0.04804920238324044,
+      "grad_norm": 4.110494136810303,
+      "learning_rate": 4.770992366412213e-07,
+      "logits/chosen": -0.4603975713253021,
+      "logits/rejected": -0.5767428874969482,
+      "logps/chosen": -18.49887466430664,
+      "logps/rejected": -42.870094299316406,
+      "loss": 0.6134881019592285,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -0.008454760536551476,
+      "rewards/margins": 0.17117241024971008,
+      "rewards/rejected": -0.1796271950006485,
+      "step": 125
+    },
+    {
+      "epoch": 0.049971170478570054,
+      "grad_norm": 3.689500093460083,
+      "learning_rate": 4.961832061068702e-07,
+      "logits/chosen": -0.47619301080703735,
+      "logits/rejected": -0.5833998918533325,
+      "logps/chosen": -19.196990966796875,
+      "logps/rejected": -43.94451141357422,
+      "loss": 0.5983373641967773,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.008951513096690178,
+      "rewards/margins": 0.20649142563343048,
+      "rewards/rejected": -0.2154429405927658,
+      "step": 130
+    },
+    {
+      "epoch": 0.051893138573899676,
+      "grad_norm": 4.194246292114258,
+      "learning_rate": 4.999967671666753e-07,
+      "logits/chosen": -0.47508007287979126,
+      "logits/rejected": -0.5998120903968811,
+      "logps/chosen": -18.90888786315918,
+      "logps/rejected": -45.564056396484375,
+      "loss": 0.5811139106750488,
+      "rewards/accuracies": 0.9479166269302368,
+      "rewards/chosen": -0.011018781922757626,
+      "rewards/margins": 0.24657797813415527,
+      "rewards/rejected": -0.25759679079055786,
+      "step": 135
+    },
+    {
+      "epoch": 0.05381510666922929,
+      "grad_norm": 3.6641292572021484,
+      "learning_rate": 4.999836339245897e-07,
+      "logits/chosen": -0.46252331137657166,
+      "logits/rejected": -0.571671724319458,
+      "logps/chosen": -19.226703643798828,
+      "logps/rejected": -44.05228805541992,
+      "loss": 0.5708660125732422,
+      "rewards/accuracies": 0.9333332777023315,
+      "rewards/chosen": -0.012889032252132893,
+      "rewards/margins": 0.2731468975543976,
+      "rewards/rejected": -0.2860358953475952,
+      "step": 140
+    },
+    {
+      "epoch": 0.05573707476455891,
+      "grad_norm": 4.0169358253479,
+      "learning_rate": 4.999603987519714e-07,
+      "logits/chosen": -0.48701220750808716,
+      "logits/rejected": -0.6042420268058777,
+      "logps/chosen": -19.006437301635742,
+      "logps/rejected": -45.47795867919922,
+      "loss": 0.5474661827087403,
+      "rewards/accuracies": 0.9333333969116211,
+      "rewards/chosen": -0.012812669388949871,
+      "rewards/margins": 0.3334830105304718,
+      "rewards/rejected": -0.34629568457603455,
+      "step": 145
+    },
+    {
+      "epoch": 0.05765904285988853,
+      "grad_norm": 3.84242844581604,
+      "learning_rate": 4.99927062587762e-07,
+      "logits/chosen": -0.4803372323513031,
+      "logits/rejected": -0.5937532186508179,
+      "logps/chosen": -18.84953498840332,
+      "logps/rejected": -45.16160583496094,
+      "loss": 0.5320310592651367,
+      "rewards/accuracies": 0.9645832777023315,
+      "rewards/chosen": -0.015172367915511131,
+      "rewards/margins": 0.3702680170536041,
+      "rewards/rejected": -0.3854404091835022,
+      "step": 150
+    },
+    {
+      "epoch": 0.05765904285988853,
+      "eval_logits/chosen": -0.46074870228767395,
+      "eval_logits/rejected": -0.5761749744415283,
+      "eval_logps/chosen": -18.443073272705078,
+      "eval_logps/rejected": -45.24944305419922,
+      "eval_loss": 0.5201317071914673,
+      "eval_rewards/accuracies": 0.950757622718811,
+      "eval_rewards/chosen": -0.02150591090321541,
+      "eval_rewards/margins": 0.4062042236328125,
+      "eval_rewards/rejected": -0.4277101457118988,
+      "eval_runtime": 135.2247,
+      "eval_samples_per_second": 1.834,
+      "eval_steps_per_second": 0.081,
+      "step": 150
+    },
+    {
+      "epoch": 0.059581010955218144,
+      "grad_norm": 3.291365623474121,
+      "learning_rate": 4.998836267790884e-07,
+      "logits/chosen": -0.4646366238594055,
+      "logits/rejected": -0.5950433015823364,
+      "logps/chosen": -18.720550537109375,
+      "logps/rejected": -45.84073257446289,
+      "loss": 0.508742094039917,
+      "rewards/accuracies": 0.9562500715255737,
+      "rewards/chosen": -0.02036605402827263,
+      "rewards/margins": 0.4351418912410736,
+      "rewards/rejected": -0.4555079936981201,
+      "step": 155
+    },
+    {
+      "epoch": 0.06150297905054776,
+      "grad_norm": 3.447497606277466,
+      "learning_rate": 4.998300930812072e-07,
+      "logits/chosen": -0.4703562259674072,
+      "logits/rejected": -0.5924030542373657,
+      "logps/chosen": -18.56179428100586,
+      "logps/rejected": -44.95166015625,
+      "loss": 0.49778451919555666,
+      "rewards/accuracies": 0.9666666984558105,
+      "rewards/chosen": -0.02062169648706913,
+      "rewards/margins": 0.467169851064682,
+      "rewards/rejected": -0.4877915382385254,
+      "step": 160
+    },
+    {
+      "epoch": 0.06342494714587738,
+      "grad_norm": 3.5075018405914307,
+      "learning_rate": 4.997664636574354e-07,
+      "logits/chosen": -0.47092780470848083,
+      "logits/rejected": -0.5929113626480103,
+      "logps/chosen": -19.233121871948242,
+      "logps/rejected": -45.90349578857422,
+      "loss": 0.4788393020629883,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.02245618775486946,
+      "rewards/margins": 0.5211035013198853,
+      "rewards/rejected": -0.543559730052948,
+      "step": 165
+    },
+    {
+      "epoch": 0.06534691524120699,
+      "grad_norm": 2.9348225593566895,
+      "learning_rate": 4.99692741079061e-07,
+      "logits/chosen": -0.49612101912498474,
+      "logits/rejected": -0.6107721924781799,
+      "logps/chosen": -19.16659927368164,
+      "logps/rejected": -44.4061279296875,
+      "loss": 0.4735041618347168,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -0.02714378573000431,
+      "rewards/margins": 0.542020857334137,
+      "rewards/rejected": -0.5691645741462708,
+      "step": 170
+    },
+    {
+      "epoch": 0.06726888333653662,
+      "grad_norm": 3.070845127105713,
+      "learning_rate": 4.996089283252405e-07,
+      "logits/chosen": -0.4627957344055176,
+      "logits/rejected": -0.5873203277587891,
+      "logps/chosen": -19.256725311279297,
+      "logps/rejected": -44.887454986572266,
+      "loss": 0.45017590522766116,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.02897927165031433,
+      "rewards/margins": 0.6148258447647095,
+      "rewards/rejected": -0.6438051462173462,
+      "step": 175
+    },
+    {
+      "epoch": 0.06919085143186623,
+      "grad_norm": 2.8429360389709473,
+      "learning_rate": 4.995150287828782e-07,
+      "logits/chosen": -0.47167301177978516,
+      "logits/rejected": -0.5799122452735901,
+      "logps/chosen": -19.113615036010742,
+      "logps/rejected": -44.891456604003906,
+      "loss": 0.4441814422607422,
+      "rewards/accuracies": 0.9812501072883606,
+      "rewards/chosen": -0.03216315060853958,
+      "rewards/margins": 0.6394332051277161,
+      "rewards/rejected": -0.6715964078903198,
+      "step": 180
+    },
+    {
+      "epoch": 0.07111281952719585,
+      "grad_norm": 2.799201726913452,
+      "learning_rate": 4.994110462464891e-07,
+      "logits/chosen": -0.46739059686660767,
+      "logits/rejected": -0.585637092590332,
+      "logps/chosen": -18.893390655517578,
+      "logps/rejected": -45.86699295043945,
+      "loss": 0.4174931526184082,
+      "rewards/accuracies": 0.9750000834465027,
+      "rewards/chosen": -0.0356193371117115,
+      "rewards/margins": 0.7311755418777466,
+      "rewards/rejected": -0.7667949199676514,
+      "step": 185
+    },
+    {
+      "epoch": 0.07303478762252547,
+      "grad_norm": 2.562150001525879,
+      "learning_rate": 4.992969849180458e-07,
+      "logits/chosen": -0.45570650696754456,
+      "logits/rejected": -0.562239408493042,
+      "logps/chosen": -18.608333587646484,
+      "logps/rejected": -44.94340896606445,
+      "loss": 0.40177116394042967,
+      "rewards/accuracies": 0.9854167103767395,
+      "rewards/chosen": -0.029587334021925926,
+      "rewards/margins": 0.7875425815582275,
+      "rewards/rejected": -0.817129909992218,
+      "step": 190
+    },
+    {
+      "epoch": 0.07495675571785508,
+      "grad_norm": 2.4428014755249023,
+      "learning_rate": 4.991728494068082e-07,
+      "logits/chosen": -0.48031896352767944,
+      "logits/rejected": -0.587901771068573,
+      "logps/chosen": -19.2396297454834,
+      "logps/rejected": -46.65198516845703,
+      "loss": 0.387024450302124,
+      "rewards/accuracies": 0.9729167222976685,
+      "rewards/chosen": -0.03882360830903053,
+      "rewards/margins": 0.8606680631637573,
+      "rewards/rejected": -0.8994916677474976,
+      "step": 195
+    },
+    {
+      "epoch": 0.0768787238131847,
+      "grad_norm": 2.5177536010742188,
+      "learning_rate": 4.990386447291382e-07,
+      "logits/chosen": -0.4639020562171936,
+      "logits/rejected": -0.5812386274337769,
+      "logps/chosen": -18.808176040649414,
+      "logps/rejected": -46.88641357421875,
+      "loss": 0.36302528381347654,
+      "rewards/accuracies": 0.98333340883255,
+      "rewards/chosen": -0.047829292714595795,
+      "rewards/margins": 0.9334899187088013,
+      "rewards/rejected": -0.9813192486763,
+      "step": 200
+    },
+    {
+      "epoch": 0.0768787238131847,
+      "eval_logits/chosen": -0.47250106930732727,
+      "eval_logits/rejected": -0.5882436037063599,
+      "eval_logps/chosen": -18.532875061035156,
+      "eval_logps/rejected": -47.33198165893555,
+      "eval_loss": 0.3482200801372528,
+      "eval_rewards/accuracies": 0.9810606241226196,
+      "eval_rewards/chosen": -0.0484466589987278,
+      "eval_rewards/margins": 1.0040230751037598,
+      "eval_rewards/rejected": -1.0524699687957764,
+      "eval_runtime": 135.0347,
+      "eval_samples_per_second": 1.837,
+      "eval_steps_per_second": 0.081,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2602,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.306483865082921e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

v5_dpo_lora64_adjust_batch_lr_loraalpha128/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d0ca7d076dd7edfb68297c0a79fbc307955ad8e578135fc61a3bd2196cf359
+size 7608