Upload checkpoint-48: baseline

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text

baseline/T20260406_Ge59eba20/08_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdb10ca9b1f92463cf3fb7667f446247d707132ba8f1e36b9a69179af85c8a4
+size 2861

baseline/T20260406_Ge59eba20/18_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ab7c3e6394c8e15d1e5dd5f189c8e7e502b2beefa973ce42f850681c827f41
+size 4810

baseline/T20260406_Ge59eba20/28_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51dabab5e06eb700f5aaf46467494936e0d3b5cc5514f10cc7cd82ae6f7afdb2
+size 3178

baseline/T20260406_Ge59eba20/38_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cb10a8f9adb7f1fa852f6e808541605c38eeaa639c7c370af4ee751e09b92a
+size 3370

baseline/T20260406_Ge59eba20/48_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f1dcdb413aad9c3d453c68ce62d9b38402d5e247183d8c35c9d120c1ed86aa
+size 3185

baseline/T20260406_Ge59eba20/58_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2789fb63f44263b482b4897185a6aa67b8ee9e5d6e5f2cec0f01528e7b4d30
+size 3247

baseline/T20260406_Ge59eba20/68_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1786a5f8aece0fee7c27dd34a073749bc0de2d1965242777aa56178b9a887b
+size 3976

baseline/T20260406_Ge59eba20/78_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66671b735c4ad16495304912d8dc56f02cd204c5429e52bbdf0d13bb74a4fedc
+size 4254

baseline/T20260410_G598544dc/04_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ffba6e4207477ff3d0037a68202ffbecc900a938b6195a9185389b13328e68
+size 1437

baseline/T20260410_G598544dc/14_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6536437b51b19b7e9cb13600bcd057ca086c730a6619321d71e0adbc83e3247b
+size 591

baseline/T20260410_G598544dc/24_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63350200f3c34637d1b5d769d648733b971931439bf42f70a977b440891711c6
+size 829

baseline/T20260410_G598544dc/34_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c51a627b0e899c79a31348953ac0fd927f1d37116f4a586d08883ee51a4e733
+size 1301

baseline/T20260412_G598544dc/08_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c1e22c6e31306d9c0a71bce75c4142fdecf1a1d573bcd537e54a8c9a038e5c
+size 395

baseline/T20260412_G598544dc/18_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8962222418092794dc7d65133e5abed2c152cb7be8f96a462df5b14a0cb6004
+size 287

baseline/T20260412_G598544dc/28_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa2c4dbc9ff9a02da727047b46f6a5883389d1c3ffd2b047a045f0cea898d56
+size 509

baseline/T20260412_G598544dc/38_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fd3e07ee540962ab3dbe0675219d67fb45de0c6e288bb86c688141f798ff6e
+size 527

baseline/T20260412_G598544dc/48_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c69c94f71765be1b68858580e470f2df2accfbb1ddfe28b7ae7dfaf63ff015d
+size 443

baseline/T20260412_G598544dc/58_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7feddf60eced63c6685bf81b8e236f971f27e83bd0ae97f2792cf6db8c285bb7
+size 320

baseline/T20260412_G598544dc/68_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a36834566b8cd1da408ccd732a9b07081d800284ed6b1b84b5751c9be77ecf
+size 336

baseline/T20260412_G598544dc/78_VStarBench.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6300b85ff34b78cae3849e455fd037049d5eaeebe145fcd0898cd3bd516abfaa
+size 792

baseline/T20260417_G46902c17/04_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3689a9da11ab9bc01e8ac09d4f724ae9dfb27415c8790e88e610939c4d54f26d
+size 5614

baseline/T20260417_G46902c17/14_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f410f7f33b609bd0677874e22043d940e40f6523f3504c15761996acf850ef67
+size 6682

baseline/T20260418_G46902c17/04_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34758523961a999de9759c8765ecd010c63327c629dda0a6182150f52e908af8
+size 2000

baseline/T20260418_G46902c17/14_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7aee7d9e10efe40bc77a04fd33384104c19864e8eb3ccacb522f3c4a38331f3
+size 3638

baseline/T20260418_G46902c17/24_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a4ccbacc6ef69ac1096c14a946d166754e68a373afce242061f3e2136d3544
+size 2852

baseline/T20260418_G46902c17/34_HRBench8K.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc53bba40036f6b4aa1f3db8db48719a1c9f5c0c98c9a8d2441169df08bfbe7
+size 4339

baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe300004eff941b191c7fc82e55a8e09616d6b0529047e6e1195bb368a8ed88e
+size 8979

baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv

@@ -0,0 +1,8 @@
+"Category","tot","acc"
+"rec","187","64.59893048128345"
+"ocr","108","73.70370370370371"
+"know","84","46.07142857142857"
+"gen","80","50.125"
+"spat","75","68.66666666666666"
+"math","26","70.76923076923076"
+"Overall","218","64.22018348623857"

baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv

@@ -0,0 +1,18 @@
+"Category","tot","acc"
+"ocr_math","11","72.72727272727273"
+"ocr_spat_math","14","74.28571428571429"
+"rec_ocr_spat_math","1","0.0"
+"rec_spat","12","74.16666666666667"
+"ocr_spat","26","73.07692307692307"
+"rec_ocr_spat","7","42.857142857142854"
+"ocr_know_spat","3","66.66666666666666"
+"rec_ocr","4","100.0"
+"rec_know_spat","2","0.0"
+"ocr","108","73.70370370370371"
+"rec","187","64.59893048128345"
+"rec_know","9","53.333333333333336"
+"rec_know_gen","62","40.48387096774195"
+"rec_ocr_know_gen","8","85.0"
+"rec_ocr_gen_spat","8","85.0"
+"ocr_gen_spat","2","70.0"
+"Overall","218","64.22018348623857"

baseline/T20260423_G2383b931/checkpoint-48_POPE_score.csv

@@ -0,0 +1,5 @@
+"split","Overall","acc","precision","recall"
+"Overall","87.25099601593625","87.83269961977186","90.87136929460581","83.9080459770115"
+"popular","87.4251497005988","88.06818181818183","91.25","83.9080459770115"
+"adversarial","84.39306358381502","84.57142857142857","84.88372093023256","83.9080459770115"
+"random","90.12345679012346","90.85714285714286","97.33333333333334","83.9080459770115"

baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b36bab627c2045b2635b67f76e001ccaf5cb24ed528d582802d31f9e9022fa
+size 17977

baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv

@@ -0,0 +1,2 @@
+"split","Overall"
+"none","0.7266666666666667"

baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b9bbfb7dd6744c1930078c6b184e16908630bdf866722c023c3935642f9320
+size 17154

baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv

@@ -0,0 +1,2 @@
+"split","Overall","Instance Attributes","Instance Identity","Instance Interaction","Instance Location","Instances Counting","Scene Understanding","Spatial Relation","Text Understanding","Visual Reasoning"
+"none","0.7533333333333333","0.8041237113402062","0.8269230769230769","1.0","0.6818181818181818","0.7142857142857143","0.7169811320754716","0.42857142857142855","1.0","0.5"

baseline/args.json

@@ -0,0 +1,376 @@
+{
+  "output_dir": "/raid/icy/Thyme/output_dir/v2-20260406-012551",
+  "per_device_train_batch_size": 1,
+  "num_train_epochs": 3.0,
+  "max_steps": -1,
+  "learning_rate": 1e-06,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": 16,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 5,
+  "logging_first_step": true,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": false,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": null,
+  "report_to": [
+    "wandb"
+  ],
+  "run_name": "/raid/icy/Thyme/output_dir/v2-20260406-012551",
+  "project": "huggingface",
+  "trackio_space_id": "trackio",
+  "eval_strategy": "no",
+  "eval_steps": null,
+  "eval_delay": 0,
+  "per_device_eval_batch_size": 1,
+  "prediction_loss_only": false,
+  "eval_on_start": false,
+  "eval_do_concat_batches": true,
+  "eval_use_gather_object": false,
+  "eval_accumulation_steps": null,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": false,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_on_each_node": false,
+  "save_total_limit": 1,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "restore_callback_states_from_checkpoint": false,
+  "full_determinism": false,
+  "seed": 42,
+  "data_seed": 42,
+  "use_cpu": false,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": 4,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "dataloader_prefetch_factor": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_backend": null,
+  "ddp_timeout": 18000000,
+  "fsdp": [],
+  "fsdp_config": null,
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 1,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "allgather_partitions": true,
+      "allgather_bucket_size": 200000000.0,
+      "overlap_comm": false,
+      "reduce_scatter": true,
+      "reduce_bucket_size": 200000000.0,
+      "contiguous_gradients": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "debug": null,
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "warmup_ratio": 0.05,
+  "logging_dir": "/raid/icy/Thyme/output_dir/v2-20260406-012551/runs",
+  "local_rank": 0,
+  "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,
+  "safe_serialization": true,
+  "max_shard_size": "5GB",
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "group_by_length": false,
+  "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": null,
+  "eval_metric": null,
+  "callbacks": [],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "full",
+  "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,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243",
+  "model_type": "qwen2_5_vl",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "flash_attn",
+  "experts_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": "qwen2_5_vl",
+  "system": null,
+  "max_length": 10240,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/raid/icy/data/Thyme_sft_data/jsonl/computation_without_image.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": false,
+  "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": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": true,
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [
+    "model.visual",
+    "model.visual.merger"
+  ],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "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,
+  "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,
+  "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,
+  "swift_version": "4.1.0.dev0",
+  "ckpt_dir": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243",
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "checkpoint-243",
+  "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], template='qwen2_5_vl', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], template='qwen2_5_vl', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', hf_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-RL', hf_model_id='XiaomiMiMo/MiMo-VL-7B-RL', model_path=None, ms_revision=None, hf_revision=None)], template='mimo_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen2_5VLLoader'>, template=None, model_arch=MultiModelKeys(arch_name='qwen2_vl', 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=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
+  "model_dir": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243",
+  "template_meta": "QwenTemplateMeta(template_type='qwen2_5_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen2_5VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system='You are a helpful assistant.', auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
+  "_val_dataset_exists": false,
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/raid/icy/Thyme/output_dir/v2-20260406-012551', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=-1, learning_rate=1e-06, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.05, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=16, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='/raid/icy/Thyme/output_dir/v2-20260406-012551', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=None, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.05, logging_dir='/raid/icy/Thyme/output_dir/v2-20260406-012551/runs', local_rank=0, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, 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, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
+}

baseline/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe300004eff941b191c7fc82e55a8e09616d6b0529047e6e1195bb368a8ed88e
+size 8979

baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv

@@ -0,0 +1,8 @@
+"Category","tot","acc"
+"rec","187","64.59893048128345"
+"ocr","108","73.70370370370371"
+"know","84","46.07142857142857"
+"gen","80","50.125"
+"spat","75","68.66666666666666"
+"math","26","70.76923076923076"
+"Overall","218","64.22018348623857"

baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv

@@ -0,0 +1,18 @@
+"Category","tot","acc"
+"ocr_math","11","72.72727272727273"
+"ocr_spat_math","14","74.28571428571429"
+"rec_ocr_spat_math","1","0.0"
+"rec_spat","12","74.16666666666667"
+"ocr_spat","26","73.07692307692307"
+"rec_ocr_spat","7","42.857142857142854"
+"ocr_know_spat","3","66.66666666666666"
+"rec_ocr","4","100.0"
+"rec_know_spat","2","0.0"
+"ocr","108","73.70370370370371"
+"rec","187","64.59893048128345"
+"rec_know","9","53.333333333333336"
+"rec_know_gen","62","40.48387096774195"
+"rec_ocr_know_gen","8","85.0"
+"rec_ocr_gen_spat","8","85.0"
+"ocr_gen_spat","2","70.0"
+"Overall","218","64.22018348623857"