Update config.json

config.json

@@ -1,238 +1,61 @@
 {
-    "data_config": {
-        "train_json_list": [
-            "dataset/train_250917_v3_preference_overall_num199394_shuflle_tie_case_processed.json"
-        ],
-        "val_json_list": [
-            "/path/to/dataset/meta_data.json"
-        ],
-        "test_json_list": [
-            [
-                "Valid Set 1",
-                [
-                    "dataset/valid_set2_modified.json"
-                ]
-            ],
-            [
-                "Valid Set 2",
-                [
-                    "dataset/valid_aurora_human_ratings_pairwise_modified.json"
-                ]
-            ]
-        ],
-        "soft_label": false,
-        "confidence_threshold": null,
-        "max_pixels": 200704,
-        "min_pixels": 200704,
-        "with_instruction": true,
-        "tied_threshold": null,
-        "reward_dim": "overall_detail"
-    },
-    "training_args": {
-        "output_dir": "",
-        "overwrite_output_dir": false,
-        "do_train": false,
-        "do_eval": true,
-        "do_predict": false,
-        "eval_strategy": "steps",
-        "prediction_loss_only": false,
-        "per_device_train_batch_size": 2,
-        "per_device_eval_batch_size": 8,
-        "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": 2e-06,
-        "weight_decay": 0.0,
-        "adam_beta1": 0.9,
-        "adam_beta2": 0.999,
-        "adam_epsilon": 1e-08,
-        "max_grad_norm": 1.0,
-        "num_train_epochs": 10,
-        "max_steps": -1,
-        "lr_scheduler_type": "constant_with_warmup",
-        "lr_scheduler_kwargs": {},
-        "warmup_ratio": 0.05,
-        "warmup_steps": 0,
-        "log_level": "passive",
-        "log_level_replica": "warning",
-        "log_on_each_node": true,
-        "logging_dir": "",
-        "logging_strategy": "steps",
-        "logging_first_step": false,
-        "logging_steps": 31,
-        "logging_nan_inf_filter": true,
-        "save_strategy": "steps",
-        "save_steps": 31,
-        "save_total_limit": null,
-        "save_safetensors": true,
-        "save_on_each_node": false,
-        "save_only_model": true,
-        "restore_callback_states_from_checkpoint": false,
-        "no_cuda": false,
-        "use_cpu": false,
-        "use_mps_device": false,
-        "seed": 42,
-        "data_seed": null,
-        "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": null,
-        "ddp_backend": null,
-        "tpu_num_cores": null,
-        "tpu_metrics_debug": false,
-        "debug": [],
-        "dataloader_drop_last": false,
-        "eval_steps": 31,
-        "dataloader_num_workers": 8,
-        "dataloader_prefetch_factor": null,
-        "past_index": -1,
-        "run_name": null,
-        "disable_tqdm": false,
-        "remove_unused_columns": false,
-        "label_names": null,
-        "load_best_model_at_end": false,
-        "metric_for_best_model": null,
-        "greater_is_better": null,
-        "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": null,
-        "accelerator_config": {
-            "split_batches": false,
-            "dispatch_batches": null,
-            "even_batches": true,
-            "use_seedable_sampler": true,
-            "non_blocking": false,
-            "gradient_accumulation_kwargs": null,
-            "use_configured_state": false
-        },
-        "parallelism_config": null,
-        "deepspeed": "hpsv3/config/ds_config/zero2.json",
-        "label_smoothing_factor": 0.0,
-        "optim": "adamw_torch",
-        "optim_args": null,
-        "adafactor": false,
-        "group_by_length": false,
-        "length_column_name": "length",
-        "report_to": [
-            "tensorboard"
-        ],
-        "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": {
-            "use_reentrant": false
-        },
-        "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": 1800,
-        "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,
-        "dataset_num_proc": null,
-        "center_rewards_coefficient": null,
-        "disable_flash_attn2": false,
-        "disable_dropout": false,
-        "vision_lr": null,
-        "merger_lr": null,
-        "rm_head_lr": null,
-        "special_token_lr": 2e-06,
-        "conduct_eval": true,
-        "load_from_pretrained": null,
-        "load_from_pretrained_step": null,
-        "logging_epochs": 0.01,
-        "eval_epochs": 0.01,
-        "save_epochs": 0.01,
-        "save_full_model": true,
-        "visualization_steps": 100,
-        "max_viz_samples": 4
-    },
-    "model_config": {
-        "model_name_or_path": "Qwen2.5-VL-7B-Instruct",
-        "model_revision": "main",
-        "rm_head_type": "ranknet_multi_head",
-        "rm_head_kwargs": null,
-        "pooling_strategy": "mean",
-        "output_dim": 2,
-        "use_special_tokens": true,
-        "freeze_vision_tower": false,
-        "freeze_llm": false,
-        "tune_merger": true,
-        "trainable_visual_layers": -1,
-        "torch_dtype": "bfloat16",
-        "trust_remote_code": false,
-        "attn_implementation": null,
-        "load_in_8bit": false,
-        "load_in_4bit": false,
-        "bnb_4bit_quant_type": "nf4",
-        "use_bnb_nested_quant": false,
-        "reward_token": "special",
-        "loss_type": "uncertainty",
-        "loss_hyperparameters": {},
-        "checkpoint_path": null
-    },
-    "peft_lora_config": {
-        "lora_enable": false,
-        "vision_lora": false,
-        "lora_r": 512,
-        "lora_alpha": 1024,
-        "lora_dropout": 0.05,
-        "lora_target_modules": null,
-        "lora_namespan_exclude": [
-            "lm_head",
-            "rm_head",
-            "embed_tokens"
-        ],
-        "lora_modules_to_save": null,
-        "lora_task_type": "CAUSAL_LM",
-        "use_rslora": false,
-        "num_lora_modules": -1
-    }
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
 }