Duplicate from aliangdw/libero_ablation_prog_pref_with_fail_lora_ft_4frames

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-VL-4B-Instruct
+tags:
+- reward_model
+- rfm
+- preference_comparisons
+library_name: transformers
+---
+
+# aliangdw/libero_ablation_prog_pref_with_fail_lora_ft_4frames
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3-VL-4B-Instruct
+- **Model Type**: qwen3_vl
+
+## Training Run
+
+- **Wandb Run**: [libero_ablation_prog_pref_with_fail_lora_ft_4frames_2000steps](https://wandb.ai/clvr/rfm/runs/f4yifl7b)
+- **Wandb ID**: `f4yifl7b`
+- **Project**: rfm
+- **Notes**: libero prog pref with fail lora ft
+
+## Citation
+
+If you use this model, please cite:

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "RFM"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151654,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151674
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.10.11",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

config.yaml

@@ -0,0 +1,198 @@
+custom_eval:
+  comparisons_per_task: 5
+  confusion_matrix:
+  - mw
+  custom_eval_random_seed: 42
+  eval_types:
+  - reward_alignment
+  - policy_ranking
+  max_comparisons: null
+  num_examples_per_quality_pr: 5
+  num_partial_successes: 5
+  pad_frames: true
+  policy_ranking:
+  - libero_pi0
+  policy_ranking_max_tasks: 100
+  quality_preference:
+  - mw
+  reward_alignment:
+  - libero_pi0
+  reward_alignment_max_trajectories: 10
+  similarity_score:
+  - aliangdw_metaworld_metaworld_eval
+  subsample_n_frames: null
+  use_frame_steps: true
+data:
+  data_source_weights:
+    metaworld_train: 1.0
+    molmoact_dataset_household: 1.0
+    molmoact_dataset_tabletop: 1.0
+    oxe_droid: 1.0
+    roboarena: 1.0
+  dataloader_num_workers: 8
+  dataloader_persistent_workers: true
+  dataloader_pin_memory: true
+  dataset_preference_ratio: 0.7
+  dataset_success_cutoff_file: rfm/data/dataset_success_cutoff.txt
+  dataset_type: strategy_first
+  eval_datasets:
+  - mw
+  eval_subset_size: null
+  fps: 10
+  load_embeddings: false
+  max_frames: 4
+  max_frames_after_preprocessing: 64
+  max_success: 1.0
+  max_trajectories: -1
+  min_frames_per_trajectory: 1
+  min_success: 0.5
+  n_wrong_tasks: 5
+  num_bins: 10
+  partial_success_threshold: 0.2
+  predict_last_frame_partial_progress: false
+  preference_strategy_ratio:
+  - 1.0
+  - 1.0
+  - 1.0
+  - 1.0
+  progress_discrete_bins: 32
+  progress_loss_type: discrete
+  progress_pred_type: absolute_wrt_total_frames
+  progress_strategy_ratio:
+  - 1.0
+  - 1.0
+  - 1.0
+  - 1.0
+  resized_height: null
+  resized_width: null
+  sample_type_ratio:
+  - 1.0
+  - 0.0
+  - 0.0
+  seed: 42
+  shuffle: true
+  shuffle_progress_frames: false
+  similarity_strategy_ratio:
+  - 1.0
+  - 1.0
+  - 1.0
+  train_datasets:
+  - libero_pi0
+  traj_same_source_prob: 0.5
+  use_data_source_balance: false
+  use_multi_image: true
+  use_per_frame_progress_token: true
+debug: false
+logging:
+  log_level: debug
+  log_to:
+  - wandb
+  save_best:
+    greater_is_better:
+    - true
+    - true
+    - true
+    hub_private: false
+    hub_save_every: 1000
+    hub_token: null
+    keep_top_k: 5
+    metric_names:
+    - eval_p_rank/kendall_rewind_last_libero_90
+    - eval_p_rank/avg_succ_fail_diff_last_libero_90
+    - eval_rew_align/pearson_libero_90
+    save_every: 50
+    upload_to_hub: false
+  save_model: true
+  save_processor: true
+  wandb_entity: clvr
+  wandb_mode: null
+  wandb_notes: libero prog pref with fail lora ft
+  wandb_project: rfm
+loss:
+  predict_last_frame_progress: false
+  progress_discrete_bins: 32
+  progress_loss_type: discrete
+  success_positive_weight: 1.0
+mode: train
+model:
+  average_temporal_patches: true
+  base_model_id: Qwen/Qwen3-VL-4B-Instruct
+  causal_mask: false
+  frame_pooling: mean
+  frame_pooling_attn_temperature: 1.0
+  model_type: default
+  peft_vision_encoder: false
+  progress_discrete_bins: 32
+  progress_loss_type: discrete
+  quantization: false
+  rewind: null
+  rewind_scale_model: false
+  torch_dtype: bfloat16
+  train_language_model: true
+  train_preference_head: true
+  train_progress_head: true
+  train_similarity_head: false
+  train_success_head: false
+  train_vision_encoder: false
+  trust_remote_code: true
+  use_multi_image: true
+  use_peft: true
+  use_per_frame_progress_token: true
+  use_unsloth: true
+peft:
+  bias: none
+  lora_alpha: 64
+  lora_dropout: 0.05
+  peft_vision_encoder: false
+  r: 32
+  target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - gate_proj
+  - up_proj
+  - down_proj
+trainer_cls: rfm_heads
+training:
+  beta: 0.1
+  bf16: true
+  custom_eval_steps: 50
+  dataloader_num_workers: 8
+  dataloader_persistent_workers: true
+  dataloader_pin_memory: true
+  ddp_bucket_cap_mb: 25
+  ddp_find_unused_parameters: false
+  do_eval: true
+  eval_steps: 50
+  evaluation_strategy: steps
+  exp_name: libero_ablation_prog_pref_with_fail_lora_ft_4frames_2000steps
+  fp16: false
+  gradient_accumulation_steps: 1
+  gradient_checkpointing: true
+  learning_rate: 2.5e-05
+  logging_steps: 1
+  lr_scheduler_type: cosine
+  max_grad_norm: 10.0
+  max_seq_length: 1024
+  max_steps: 2000
+  num_gpus: 2
+  num_train_epochs: -1
+  output_dir: ./logs
+  overwrite_output_dir: true
+  per_device_eval_batch_size: 64
+  per_device_train_batch_size: 64
+  predict_pref_progress: true
+  predict_pref_sim: false
+  predict_sim_progress: false
+  prediction_loss_only: true
+  remove_unused_columns: false
+  resume_from_checkpoint: null
+  run_default_eval: false
+  save_steps: 200
+  save_strategy: 'no'
+  vision_encoder_lr: 1.0e-05
+  vision_encoder_num_layers: 3
+  warmup_ratio: 0.1
+  warmup_steps: 0
+  weight_decay: 0.05

dataset_random_state.json

@@ -0,0 +1,1266 @@
+{
+  "dataset": [
+    3,
+    [
+      2147483648,
+      3564348608,
+      1266698288,
+      4212342371,
+      3595291661,
+      3180588708,
+      3037210256,
+      946923017,
+      2565409715,
+      2900535780,
+      924383152,
+      4180157270,
+      4230508198,
+      2039675917,
+      3755350407,
+      2362848650,
+      2818100609,
+      2097423432,
+      524478045,
+      540883378,
+      281170210,
+      1485176884,
+      1493190386,
+      1773214509,
+      380915208,
+      3667698522,
+      2648371337,
+      2961234806,
+      3857480267,
+      1582950522,
+      246289694,
+      3322185604,
+      1944574775,
+      302623699,
+      169865066,
+      1143540808,
+      3733177770,
+      513116636,
+      1411153081,
+      3205493053,
+      768926902,
+      549624109,
+      1470655403,
+      59539609,
+      3678480009,
+      3087139671,
+      1176835859,
+      2078491503,
+      2299934332,
+      1592059249,
+      1062716176,
+      2654193596,
+      3531838733,
+      2661260596,
+      3881209635,
+      2106865768,
+      4154287292,
+      2082185616,
+      2301197011,
+      2177349827,
+      3082181756,
+      1787663536,
+      3714670796,
+      3018262113,
+      1670056238,
+      1856738750,
+      99824592,
+      2279837081,
+      1414647942,
+      3416675731,
+      3458782472,
+      3997022236,
+      468762002,
+      2666158583,
+      953353270,
+      1788980658,
+      3802061067,
+      407586584,
+      1844776834,
+      1906917274,
+      3154715663,
+      3028370222,
+      4156024188,
+      3996363428,
+      80495456,
+      2659800972,
+      2005649973,
+      3818358673,
+      3952623596,
+      2506862371,
+      3282302532,
+      263923435,
+      3384662671,
+      3292439172,
+      3119957588,
+      1224426111,
+      899864150,
+      215262826,
+      1619647231,
+      3347694949,
+      3497868538,
+      2029552053,
+      2992804824,
+      4080010250,
+      2023513186,
+      1885979437,
+      3564622190,
+      3775424270,
+      2297810139,
+      3549449169,
+      2664856277,
+      3274801974,
+      2794883969,
+      980412666,
+      2980215653,
+      2794389321,
+      2816521934,
+      1266970739,
+      542306338,
+      3646225311,
+      3598997630,
+      2111980720,
+      2949252482,
+      2489027658,
+      352815024,
+      11610683,
+      1386663624,
+      2004196796,
+      1161461546,
+      1921293780,
+      2463949525,
+      1647009713,
+      3550093655,
+      2563894064,
+      3486310554,
+      1506105865,
+      243092931,
+      2659437476,
+      4200687059,
+      2284345122,
+      1974438610,
+      3591096528,
+      967119212,
+      3362401375,
+      140678365,
+      311602112,
+      2361740275,
+      2139598582,
+      3632873481,
+      2762232439,
+      4156482318,
+      381637792,
+      3253346525,
+      2492118775,
+      1502434558,
+      3164497290,
+      3550998357,
+      2412448305,
+      2223955385,
+      4122879535,
+      350121793,
+      1835149778,
+      2175117867,
+      989674750,
+      3178241202,
+      3553093569,
+      3470650311,
+      2829698151,
+      3209427769,
+      1779174943,
+      275388428,
+      4044574515,
+      715447260,
+      3180940440,
+      4020772289,
+      1322708567,
+      3189868792,
+      4250485633,
+      716970023,
+      2307550151,
+      1074996711,
+      1217573599,
+      197006094,
+      2178394212,
+      1255233746,
+      4164251484,
+      1405608772,
+      2808160475,
+      1304736088,
+      1796071066,
+      2761748078,
+      3570739698,
+      1616118556,
+      2232868135,
+      3567541936,
+      3470600401,
+      3031621994,
+      3351764214,
+      1359785149,
+      2617497797,
+      3340028190,
+      356162828,
+      2083806068,
+      2503635608,
+      4024838996,
+      2577080371,
+      2897993505,
+      3120733934,
+      905794891,
+      2506078507,
+      4211618666,
+      3777871979,
+      809751414,
+      4080874167,
+      1562977008,
+      3917373055,
+      2132779194,
+      4014249473,
+      4067327082,
+      2582869847,
+      1780081876,
+      1842619106,
+      3381761227,
+      921004274,
+      1393256920,
+      1883566732,
+      2702071861,
+      865327389,
+      1622085203,
+      3021825820,
+      2687061406,
+      1748902923,
+      689023977,
+      308399650,
+      2377287978,
+      1646969411,
+      1051806316,
+      4277884230,
+      2041056290,
+      101134519,
+      2032472116,
+      4112521069,
+      151202901,
+      2773743461,
+      551348559,
+      3476836808,
+      510935951,
+      625057077,
+      3757450756,
+      2977698135,
+      3027776859,
+      2616998041,
+      2773430005,
+      544190486,
+      2241368212,
+      1141105829,
+      1452816309,
+      4199229235,
+      3218013033,
+      4229475816,
+      1659576351,
+      3020348754,
+      1193400518,
+      3208584597,
+      1151197733,
+      2597187966,
+      503065140,
+      2421841572,
+      1437291709,
+      1909275895,
+      2872630545,
+      793588217,
+      3792934707,
+      1784451785,
+      2921385648,
+      1669902526,
+      4189978976,
+      1196986251,
+      434805516,
+      1907541826,
+      2624415034,
+      1687778718,
+      650746582,
+      1949153382,
+      4148493093,
+      841300520,
+      1164202054,
+      4203468658,
+      4106300911,
+      850346789,
+      1715730760,
+      3114661489,
+      2866524548,
+      1360448945,
+      3601318775,
+      1743078223,
+      2413855408,
+      1211895622,
+      325117146,
+      2721152875,
+      1284334485,
+      2446538832,
+      739014618,
+      2237045115,
+      842553465,
+      2538598293,
+      746460793,
+      4010387366,
+      2002655192,
+      4193733112,
+      1194380773,
+      3918217378,
+      1447487475,
+      5659228,
+      3408847694,
+      4190318700,
+      1862549564,
+      781683719,
+      1194618118,
+      755053413,
+      3436011942,
+      2885435303,
+      3081151348,
+      2017642831,
+      1053816502,
+      1086627485,
+      2157296554,
+      110650022,
+      965352898,
+      1003174194,
+      1288956241,
+      4057404871,
+      2965068465,
+      2897064481,
+      2457377317,
+      1879872545,
+      358455290,
+      375086701,
+      3015902095,
+      1676249984,
+      924455526,
+      2084169389,
+      1989014644,
+      1993749926,
+      2009424973,
+      2113340508,
+      3980883273,
+      2915977458,
+      203328382,
+      3020815229,
+      2415050113,
+      4103009585,
+      3700885489,
+      2916647550,
+      1523006503,
+      174302338,
+      2476909338,
+      1969322490,
+      4285741984,
+      1528449097,
+      3355315515,
+      4217241278,
+      599579127,
+      2572243673,
+      3035856735,
+      1539140489,
+      1782314913,
+      4238644287,
+      1746424142,
+      1978148312,
+      2380746849,
+      184941882,
+      1106717981,
+      1720750349,
+      981701307,
+      3953154731,
+      3257809181,
+      2892339376,
+      3339778166,
+      3676936849,
+      87425948,
+      3029257381,
+      2037942523,
+      3807628706,
+      2861474706,
+      1058852346,
+      1322765211,
+      2686046342,
+      2689342655,
+      2303436168,
+      2571627181,
+      1986057734,
+      1183564308,
+      2829677523,
+      1295563975,
+      503126586,
+      2025890348,
+      4179277821,
+      1735262467,
+      981331774,
+      1613447066,
+      1011606109,
+      2000062246,
+      3581448390,
+      3477731384,
+      3641307373,
+      3508544379,
+      2327233491,
+      3931944343,
+      4189052882,
+      2990416380,
+      422406169,
+      202291313,
+      2531006461,
+      4277024116,
+      3815144003,
+      821314585,
+      1344175168,
+      3562834071,
+      1339615445,
+      1831545190,
+      3115548822,
+      743512780,
+      4006999448,
+      3720181735,
+      1012033521,
+      919931041,
+      2628967879,
+      1151876565,
+      1268107129,
+      3674829936,
+      834977846,
+      743987006,
+      3947536548,
+      3706529695,
+      4121073678,
+      2507605742,
+      1595636918,
+      2708047833,
+      2427507331,
+      3868216331,
+      3254240010,
+      2097683411,
+      3279710596,
+      3686819053,
+      1843541720,
+      1683793619,
+      3245287285,
+      3571828776,
+      3733296431,
+      3806747478,
+      1390930605,
+      3860422228,
+      114397037,
+      1931519825,
+      2770684378,
+      1556101783,
+      1436111731,
+      4031950081,
+      562876656,
+      1775895782,
+      612364620,
+      1313509772,
+      4283410242,
+      3252958463,
+      2176555836,
+      3933073367,
+      3013277102,
+      1444071961,
+      3120949516,
+      2824578890,
+      325676929,
+      943677134,
+      1800649256,
+      1721927060,
+      347498719,
+      1435221321,
+      2623572981,
+      1408548470,
+      4145586315,
+      2901889237,
+      1849377952,
+      1239144551,
+      3382598266,
+      2992893897,
+      3738297588,
+      611280106,
+      3897415338,
+      2370299241,
+      1772308583,
+      3697465753,
+      354508058,
+      2702360134,
+      591308331,
+      3524072501,
+      976616000,
+      2563717192,
+      3078266097,
+      1376594703,
+      4209795919,
+      2454412767,
+      2712206031,
+      2963860163,
+      3734324882,
+      2248653800,
+      324872786,
+      3789837448,
+      3779000146,
+      527733939,
+      2844165793,
+      576499681,
+      1618787435,
+      2638888650,
+      57511068,
+      2804627518,
+      2993670030,
+      481402236,
+      2810124845,
+      1416045214,
+      1723694191,
+      1214944572,
+      3188123783,
+      1139185907,
+      3851015362,
+      1719652470,
+      1661343029,
+      3644307578,
+      3564178709,
+      1256656955,
+      46631590,
+      4231317929,
+      3098958589,
+      1834956625,
+      2206185428,
+      3695688374,
+      3647957317,
+      1064098871,
+      1739100906,
+      2579568980,
+      27974051,
+      2617466775,
+      964075233,
+      907049942,
+      4164146575,
+      3377168066,
+      2524828266,
+      1083546008,
+      2992960953,
+      2260789066,
+      1543742095,
+      2843842831,
+      1375722284,
+      3574521313,
+      110842534,
+      2310998251,
+      3076511734,
+      783145600,
+      1287776608,
+      3087144146,
+      305559823,
+      2356293719,
+      3228441476,
+      1678938122,
+      3775814061,
+      1620283952,
+      2512027726,
+      1031432407,
+      962295099,
+      3877418501,
+      968669928,
+      304126693,
+      3711291137,
+      3847527101,
+      494066767,
+      4050229756,
+      4169448589,
+      671763915,
+      1095747781,
+      4006132710,
+      394725957,
+      200521654,
+      2715998750,
+      1477567673,
+      895171901,
+      3370105999,
+      2684157455,
+      4153990023,
+      3966076501,
+      2043374409,
+      144443759,
+      6764556,
+      1611650045,
+      1480956755,
+      1388276468,
+      4136518438,
+      1538041336,
+      266773992,
+      1623357516,
+      2267298390,
+      3183919402,
+      1084292424,
+      2796136160,
+      2413448816,
+      2850375199,
+      3510894040,
+      2644778623,
+      3317288284,
+      3697317540,
+      1465776787,
+      1843489446,
+      1416711171,
+      744701117,
+      1286781349,
+      3748640476,
+      861982119,
+      2377742909,
+      1171768136,
+      2701877439,
+      3839724288,
+      2869791015,
+      2386067954,
+      2629214347,
+      955801623,
+      3831079317,
+      624
+    ],
+    null
+  ],
+  "pref_sampler": [
+    3,
+    [
+      2147483648,
+      3564348608,
+      1266698288,
+      4212342371,
+      3595291661,
+      3180588708,
+      3037210256,
+      946923017,
+      2565409715,
+      2900535780,
+      924383152,
+      4180157270,
+      4230508198,
+      2039675917,
+      3755350407,
+      2362848650,
+      2818100609,
+      2097423432,
+      524478045,
+      540883378,
+      281170210,
+      1485176884,
+      1493190386,
+      1773214509,
+      380915208,
+      3667698522,
+      2648371337,
+      2961234806,
+      3857480267,
+      1582950522,
+      246289694,
+      3322185604,
+      1944574775,
+      302623699,
+      169865066,
+      1143540808,
+      3733177770,
+      513116636,
+      1411153081,
+      3205493053,
+      768926902,
+      549624109,
+      1470655403,
+      59539609,
+      3678480009,
+      3087139671,
+      1176835859,
+      2078491503,
+      2299934332,
+      1592059249,
+      1062716176,
+      2654193596,
+      3531838733,
+      2661260596,
+      3881209635,
+      2106865768,
+      4154287292,
+      2082185616,
+      2301197011,
+      2177349827,
+      3082181756,
+      1787663536,
+      3714670796,
+      3018262113,
+      1670056238,
+      1856738750,
+      99824592,
+      2279837081,
+      1414647942,
+      3416675731,
+      3458782472,
+      3997022236,
+      468762002,
+      2666158583,
+      953353270,
+      1788980658,
+      3802061067,
+      407586584,
+      1844776834,
+      1906917274,
+      3154715663,
+      3028370222,
+      4156024188,
+      3996363428,
+      80495456,
+      2659800972,
+      2005649973,
+      3818358673,
+      3952623596,
+      2506862371,
+      3282302532,
+      263923435,
+      3384662671,
+      3292439172,
+      3119957588,
+      1224426111,
+      899864150,
+      215262826,
+      1619647231,
+      3347694949,
+      3497868538,
+      2029552053,
+      2992804824,
+      4080010250,
+      2023513186,
+      1885979437,
+      3564622190,
+      3775424270,
+      2297810139,
+      3549449169,
+      2664856277,
+      3274801974,
+      2794883969,
+      980412666,
+      2980215653,
+      2794389321,
+      2816521934,
+      1266970739,
+      542306338,
+      3646225311,
+      3598997630,
+      2111980720,
+      2949252482,
+      2489027658,
+      352815024,
+      11610683,
+      1386663624,
+      2004196796,
+      1161461546,
+      1921293780,
+      2463949525,
+      1647009713,
+      3550093655,
+      2563894064,
+      3486310554,
+      1506105865,
+      243092931,
+      2659437476,
+      4200687059,
+      2284345122,
+      1974438610,
+      3591096528,
+      967119212,
+      3362401375,
+      140678365,
+      311602112,
+      2361740275,
+      2139598582,
+      3632873481,
+      2762232439,
+      4156482318,
+      381637792,
+      3253346525,
+      2492118775,
+      1502434558,
+      3164497290,
+      3550998357,
+      2412448305,
+      2223955385,
+      4122879535,
+      350121793,
+      1835149778,
+      2175117867,
+      989674750,
+      3178241202,
+      3553093569,
+      3470650311,
+      2829698151,
+      3209427769,
+      1779174943,
+      275388428,
+      4044574515,
+      715447260,
+      3180940440,
+      4020772289,
+      1322708567,
+      3189868792,
+      4250485633,
+      716970023,
+      2307550151,
+      1074996711,
+      1217573599,
+      197006094,
+      2178394212,
+      1255233746,
+      4164251484,
+      1405608772,
+      2808160475,
+      1304736088,
+      1796071066,
+      2761748078,
+      3570739698,
+      1616118556,
+      2232868135,
+      3567541936,
+      3470600401,
+      3031621994,
+      3351764214,
+      1359785149,
+      2617497797,
+      3340028190,
+      356162828,
+      2083806068,
+      2503635608,
+      4024838996,
+      2577080371,
+      2897993505,
+      3120733934,
+      905794891,
+      2506078507,
+      4211618666,
+      3777871979,
+      809751414,
+      4080874167,
+      1562977008,
+      3917373055,
+      2132779194,
+      4014249473,
+      4067327082,
+      2582869847,
+      1780081876,
+      1842619106,
+      3381761227,
+      921004274,
+      1393256920,
+      1883566732,
+      2702071861,
+      865327389,
+      1622085203,
+      3021825820,
+      2687061406,
+      1748902923,
+      689023977,
+      308399650,
+      2377287978,
+      1646969411,
+      1051806316,
+      4277884230,
+      2041056290,
+      101134519,
+      2032472116,
+      4112521069,
+      151202901,
+      2773743461,
+      551348559,
+      3476836808,
+      510935951,
+      625057077,
+      3757450756,
+      2977698135,
+      3027776859,
+      2616998041,
+      2773430005,
+      544190486,
+      2241368212,
+      1141105829,
+      1452816309,
+      4199229235,
+      3218013033,
+      4229475816,
+      1659576351,
+      3020348754,
+      1193400518,
+      3208584597,
+      1151197733,
+      2597187966,
+      503065140,
+      2421841572,
+      1437291709,
+      1909275895,
+      2872630545,
+      793588217,
+      3792934707,
+      1784451785,
+      2921385648,
+      1669902526,
+      4189978976,
+      1196986251,
+      434805516,
+      1907541826,
+      2624415034,
+      1687778718,
+      650746582,
+      1949153382,
+      4148493093,
+      841300520,
+      1164202054,
+      4203468658,
+      4106300911,
+      850346789,
+      1715730760,
+      3114661489,
+      2866524548,
+      1360448945,
+      3601318775,
+      1743078223,
+      2413855408,
+      1211895622,
+      325117146,
+      2721152875,
+      1284334485,
+      2446538832,
+      739014618,
+      2237045115,
+      842553465,
+      2538598293,
+      746460793,
+      4010387366,
+      2002655192,
+      4193733112,
+      1194380773,
+      3918217378,
+      1447487475,
+      5659228,
+      3408847694,
+      4190318700,
+      1862549564,
+      781683719,
+      1194618118,
+      755053413,
+      3436011942,
+      2885435303,
+      3081151348,
+      2017642831,
+      1053816502,
+      1086627485,
+      2157296554,
+      110650022,
+      965352898,
+      1003174194,
+      1288956241,
+      4057404871,
+      2965068465,
+      2897064481,
+      2457377317,
+      1879872545,
+      358455290,
+      375086701,
+      3015902095,
+      1676249984,
+      924455526,
+      2084169389,
+      1989014644,
+      1993749926,
+      2009424973,
+      2113340508,
+      3980883273,
+      2915977458,
+      203328382,
+      3020815229,
+      2415050113,
+      4103009585,
+      3700885489,
+      2916647550,
+      1523006503,
+      174302338,
+      2476909338,
+      1969322490,
+      4285741984,
+      1528449097,
+      3355315515,
+      4217241278,
+      599579127,
+      2572243673,
+      3035856735,
+      1539140489,
+      1782314913,
+      4238644287,
+      1746424142,
+      1978148312,
+      2380746849,
+      184941882,
+      1106717981,
+      1720750349,
+      981701307,
+      3953154731,
+      3257809181,
+      2892339376,
+      3339778166,
+      3676936849,
+      87425948,
+      3029257381,
+      2037942523,
+      3807628706,
+      2861474706,
+      1058852346,
+      1322765211,
+      2686046342,
+      2689342655,
+      2303436168,
+      2571627181,
+      1986057734,
+      1183564308,
+      2829677523,
+      1295563975,
+      503126586,
+      2025890348,
+      4179277821,
+      1735262467,
+      981331774,
+      1613447066,
+      1011606109,
+      2000062246,
+      3581448390,
+      3477731384,
+      3641307373,
+      3508544379,
+      2327233491,
+      3931944343,
+      4189052882,
+      2990416380,
+      422406169,
+      202291313,
+      2531006461,
+      4277024116,
+      3815144003,
+      821314585,
+      1344175168,
+      3562834071,
+      1339615445,
+      1831545190,
+      3115548822,
+      743512780,
+      4006999448,
+      3720181735,
+      1012033521,
+      919931041,
+      2628967879,
+      1151876565,
+      1268107129,
+      3674829936,
+      834977846,
+      743987006,
+      3947536548,
+      3706529695,
+      4121073678,
+      2507605742,
+      1595636918,
+      2708047833,
+      2427507331,
+      3868216331,
+      3254240010,
+      2097683411,
+      3279710596,
+      3686819053,
+      1843541720,
+      1683793619,
+      3245287285,
+      3571828776,
+      3733296431,
+      3806747478,
+      1390930605,
+      3860422228,
+      114397037,
+      1931519825,
+      2770684378,
+      1556101783,
+      1436111731,
+      4031950081,
+      562876656,
+      1775895782,
+      612364620,
+      1313509772,
+      4283410242,
+      3252958463,
+      2176555836,
+      3933073367,
+      3013277102,
+      1444071961,
+      3120949516,
+      2824578890,
+      325676929,
+      943677134,
+      1800649256,
+      1721927060,
+      347498719,
+      1435221321,
+      2623572981,
+      1408548470,
+      4145586315,
+      2901889237,
+      1849377952,
+      1239144551,
+      3382598266,
+      2992893897,
+      3738297588,
+      611280106,
+      3897415338,
+      2370299241,
+      1772308583,
+      3697465753,
+      354508058,
+      2702360134,
+      591308331,
+      3524072501,
+      976616000,
+      2563717192,
+      3078266097,
+      1376594703,
+      4209795919,
+      2454412767,
+      2712206031,
+      2963860163,
+      3734324882,
+      2248653800,
+      324872786,
+      3789837448,
+      3779000146,
+      527733939,
+      2844165793,
+      576499681,
+      1618787435,
+      2638888650,
+      57511068,
+      2804627518,
+      2993670030,
+      481402236,
+      2810124845,
+      1416045214,
+      1723694191,
+      1214944572,
+      3188123783,
+      1139185907,
+      3851015362,
+      1719652470,
+      1661343029,
+      3644307578,
+      3564178709,
+      1256656955,
+      46631590,
+      4231317929,
+      3098958589,
+      1834956625,
+      2206185428,
+      3695688374,
+      3647957317,
+      1064098871,
+      1739100906,
+      2579568980,
+      27974051,
+      2617466775,
+      964075233,
+      907049942,
+      4164146575,
+      3377168066,
+      2524828266,
+      1083546008,
+      2992960953,
+      2260789066,
+      1543742095,
+      2843842831,
+      1375722284,
+      3574521313,
+      110842534,
+      2310998251,
+      3076511734,
+      783145600,
+      1287776608,
+      3087144146,
+      305559823,
+      2356293719,
+      3228441476,
+      1678938122,
+      3775814061,
+      1620283952,
+      2512027726,
+      1031432407,
+      962295099,
+      3877418501,
+      968669928,
+      304126693,
+      3711291137,
+      3847527101,
+      494066767,
+      4050229756,
+      4169448589,
+      671763915,
+      1095747781,
+      4006132710,
+      394725957,
+      200521654,
+      2715998750,
+      1477567673,
+      895171901,
+      3370105999,
+      2684157455,
+      4153990023,
+      3966076501,
+      2043374409,
+      144443759,
+      6764556,
+      1611650045,
+      1480956755,
+      1388276468,
+      4136518438,
+      1538041336,
+      266773992,
+      1623357516,
+      2267298390,
+      3183919402,
+      1084292424,
+      2796136160,
+      2413448816,
+      2850375199,
+      3510894040,
+      2644778623,
+      3317288284,
+      3697317540,
+      1465776787,
+      1843489446,
+      1416711171,
+      744701117,
+      1286781349,
+      3748640476,
+      861982119,
+      2377742909,
+      1171768136,
+      2701877439,
+      3839724288,
+      2869791015,
+      2386067954,
+      2629214347,
+      955801623,
+      3831079317,
+      624
+    ],
+    null
+  ],
+  "progress_sampler": null,
+  "similarity_sampler": null
+}

metrics.json

@@ -0,0 +1,58 @@
+{
+  "step": 700,
+  "metrics": {
+    "eval_rew_align/loss_libero_90": 0.11321220770478249,
+    "eval_rew_align/pearson_libero_90": 0.9301406673122348,
+    "eval_p_rank/kendall_last_libero_90": 0.8904109589041096,
+    "eval_p_rank/kendall_rewind_last_libero_90": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_last_libero_90": 0.36485108353503765,
+    "eval_p_rank/min_succ_fail_diff_last_libero_90": 0.005788075923919722,
+    "eval_p_rank/max_succ_fail_diff_last_libero_90": 0.704643115401268,
+    "eval_p_rank/ranking_acc_last_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_all_pairs_last_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_failure_vs_successful_last_libero_90": 0.9452054794520548,
+    "eval_p_rank/kendall_avg_libero_90": 0.8904109589041096,
+    "eval_p_rank/kendall_rewind_avg_libero_90": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_avg_libero_90": 0.36485108353503765,
+    "eval_p_rank/min_succ_fail_diff_avg_libero_90": 0.005788075923919722,
+    "eval_p_rank/max_succ_fail_diff_avg_libero_90": 0.704643115401268,
+    "eval_p_rank/ranking_acc_avg_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_all_pairs_avg_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_failure_vs_successful_avg_libero_90": 0.9452054794520548,
+    "eval_p_rank/kendall_sum_libero_90": 0.8904109589041096,
+    "eval_p_rank/kendall_rewind_sum_libero_90": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_sum_libero_90": 0.36485108353503765,
+    "eval_p_rank/min_succ_fail_diff_sum_libero_90": 0.005788075923919722,
+    "eval_p_rank/max_succ_fail_diff_sum_libero_90": 0.704643115401268,
+    "eval_p_rank/ranking_acc_sum_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_all_pairs_sum_libero_90": 0.9452054794520548,
+    "eval_p_rank/ranking_acc_failure_vs_successful_sum_libero_90": 0.9452054794520548,
+    "eval_rew_align/loss_libero_10": 0.1162563480436802,
+    "eval_rew_align/pearson_libero_10": 0.962842022665807,
+    "eval_p_rank/kendall_last_libero_10": 0.992,
+    "eval_p_rank/kendall_rewind_last_libero_10": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_last_libero_10": 0.4155293563008309,
+    "eval_p_rank/min_succ_fail_diff_last_libero_10": 0.29186664223670966,
+    "eval_p_rank/max_succ_fail_diff_last_libero_10": 0.5371088057756424,
+    "eval_p_rank/ranking_acc_last_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_all_pairs_last_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_failure_vs_successful_last_libero_10": 0.996,
+    "eval_p_rank/kendall_avg_libero_10": 0.992,
+    "eval_p_rank/kendall_rewind_avg_libero_10": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_avg_libero_10": 0.4155293563008309,
+    "eval_p_rank/min_succ_fail_diff_avg_libero_10": 0.29186664223670966,
+    "eval_p_rank/max_succ_fail_diff_avg_libero_10": 0.5371088057756424,
+    "eval_p_rank/ranking_acc_avg_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_all_pairs_avg_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_failure_vs_successful_avg_libero_10": 0.996,
+    "eval_p_rank/kendall_sum_libero_10": 0.992,
+    "eval_p_rank/kendall_rewind_sum_libero_10": 1.0,
+    "eval_p_rank/avg_succ_fail_diff_sum_libero_10": 0.4155293563008309,
+    "eval_p_rank/min_succ_fail_diff_sum_libero_10": 0.29186664223670966,
+    "eval_p_rank/max_succ_fail_diff_sum_libero_10": 0.5371088057756424,
+    "eval_p_rank/ranking_acc_sum_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_all_pairs_sum_libero_10": 0.996,
+    "eval_p_rank/ranking_acc_failure_vs_successful_sum_libero_10": 0.996,
+    "time/custom_evaluations": 50.66930902400054
+  }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670b398b789f3370b92438a18a491b268eb83758829057d051e6f4c92e02f5cb
+size 4980925662

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52783a73ea25bb1acfe15221050bbbecff02c4db50ade0d16671c5b346c5212
+size 4184116144

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048627fb670006ceee7197aeddf596ae746515c3e6a2d0356811abcfbdc7062a
+size 5905