LoRA fine-tune on RobotSmith task03 - correlation fixed
Browse files- README.md +27 -0
- config.json +69 -0
- dataset_random_state.json +634 -0
- metrics.json +59 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-VL-4B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- reward_model
|
| 6 |
+
- rbm
|
| 7 |
+
- preference_comparisons
|
| 8 |
+
library_name: transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# amburger66/robometer-4b-lora-robotsmith-task03-v2
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
|
| 15 |
+
- **Base Model**: Qwen/Qwen3-VL-4B-Instruct
|
| 16 |
+
- **Model Type**: qwen3_vl
|
| 17 |
+
|
| 18 |
+
## Training Run
|
| 19 |
+
|
| 20 |
+
- **Wandb Run**: [lora_task03](https://wandb.ai/r-pad/rbm-finetune-robotsmith/runs/t2aag6u7)
|
| 21 |
+
- **Wandb ID**: `t2aag6u7`
|
| 22 |
+
- **Project**: rbm-finetune-robotsmith
|
| 23 |
+
- **Notes**: fine-tuning Robometer on RobotSmith
|
| 24 |
+
|
| 25 |
+
## Citation
|
| 26 |
+
|
| 27 |
+
If you use this model, please cite:
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RBM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_name": "unsloth/Qwen3-VL-4B-Instruct",
|
| 8 |
+
"model_type": "qwen3_vl",
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_bias": false,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 151643,
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 151645,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 2560,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 9728,
|
| 21 |
+
"max_position_embeddings": 262144,
|
| 22 |
+
"model_type": "qwen3_vl_text",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 36,
|
| 25 |
+
"num_key_value_heads": 8,
|
| 26 |
+
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"mrope_interleaved": true,
|
| 29 |
+
"mrope_section": [
|
| 30 |
+
24,
|
| 31 |
+
20,
|
| 32 |
+
20
|
| 33 |
+
],
|
| 34 |
+
"rope_type": "default"
|
| 35 |
+
},
|
| 36 |
+
"rope_theta": 5000000,
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 151674
|
| 40 |
+
},
|
| 41 |
+
"tie_word_embeddings": true,
|
| 42 |
+
"transformers_version": "4.57.6",
|
| 43 |
+
"unsloth_fixed": true,
|
| 44 |
+
"unsloth_version": "2026.3.8",
|
| 45 |
+
"video_token_id": 151656,
|
| 46 |
+
"vision_config": {
|
| 47 |
+
"deepstack_visual_indexes": [
|
| 48 |
+
5,
|
| 49 |
+
11,
|
| 50 |
+
17
|
| 51 |
+
],
|
| 52 |
+
"depth": 24,
|
| 53 |
+
"dtype": "bfloat16",
|
| 54 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 55 |
+
"hidden_size": 1024,
|
| 56 |
+
"in_channels": 3,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 4096,
|
| 59 |
+
"model_type": "qwen3_vl",
|
| 60 |
+
"num_heads": 16,
|
| 61 |
+
"num_position_embeddings": 2304,
|
| 62 |
+
"out_hidden_size": 2560,
|
| 63 |
+
"patch_size": 16,
|
| 64 |
+
"spatial_merge_size": 2,
|
| 65 |
+
"temporal_patch_size": 2
|
| 66 |
+
},
|
| 67 |
+
"vision_end_token_id": 151653,
|
| 68 |
+
"vision_start_token_id": 151652
|
| 69 |
+
}
|
dataset_random_state.json
ADDED
|
@@ -0,0 +1,634 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pref_sampler": [
|
| 3 |
+
3,
|
| 4 |
+
[
|
| 5 |
+
2147483648,
|
| 6 |
+
3564348608,
|
| 7 |
+
1266698288,
|
| 8 |
+
4212342371,
|
| 9 |
+
3595291661,
|
| 10 |
+
3180588708,
|
| 11 |
+
3037210256,
|
| 12 |
+
946923017,
|
| 13 |
+
2565409715,
|
| 14 |
+
2900535780,
|
| 15 |
+
924383152,
|
| 16 |
+
4180157270,
|
| 17 |
+
4230508198,
|
| 18 |
+
2039675917,
|
| 19 |
+
3755350407,
|
| 20 |
+
2362848650,
|
| 21 |
+
2818100609,
|
| 22 |
+
2097423432,
|
| 23 |
+
524478045,
|
| 24 |
+
540883378,
|
| 25 |
+
281170210,
|
| 26 |
+
1485176884,
|
| 27 |
+
1493190386,
|
| 28 |
+
1773214509,
|
| 29 |
+
380915208,
|
| 30 |
+
3667698522,
|
| 31 |
+
2648371337,
|
| 32 |
+
2961234806,
|
| 33 |
+
3857480267,
|
| 34 |
+
1582950522,
|
| 35 |
+
246289694,
|
| 36 |
+
3322185604,
|
| 37 |
+
1944574775,
|
| 38 |
+
302623699,
|
| 39 |
+
169865066,
|
| 40 |
+
1143540808,
|
| 41 |
+
3733177770,
|
| 42 |
+
513116636,
|
| 43 |
+
1411153081,
|
| 44 |
+
3205493053,
|
| 45 |
+
768926902,
|
| 46 |
+
549624109,
|
| 47 |
+
1470655403,
|
| 48 |
+
59539609,
|
| 49 |
+
3678480009,
|
| 50 |
+
3087139671,
|
| 51 |
+
1176835859,
|
| 52 |
+
2078491503,
|
| 53 |
+
2299934332,
|
| 54 |
+
1592059249,
|
| 55 |
+
1062716176,
|
| 56 |
+
2654193596,
|
| 57 |
+
3531838733,
|
| 58 |
+
2661260596,
|
| 59 |
+
3881209635,
|
| 60 |
+
2106865768,
|
| 61 |
+
4154287292,
|
| 62 |
+
2082185616,
|
| 63 |
+
2301197011,
|
| 64 |
+
2177349827,
|
| 65 |
+
3082181756,
|
| 66 |
+
1787663536,
|
| 67 |
+
3714670796,
|
| 68 |
+
3018262113,
|
| 69 |
+
1670056238,
|
| 70 |
+
1856738750,
|
| 71 |
+
99824592,
|
| 72 |
+
2279837081,
|
| 73 |
+
1414647942,
|
| 74 |
+
3416675731,
|
| 75 |
+
3458782472,
|
| 76 |
+
3997022236,
|
| 77 |
+
468762002,
|
| 78 |
+
2666158583,
|
| 79 |
+
953353270,
|
| 80 |
+
1788980658,
|
| 81 |
+
3802061067,
|
| 82 |
+
407586584,
|
| 83 |
+
1844776834,
|
| 84 |
+
1906917274,
|
| 85 |
+
3154715663,
|
| 86 |
+
3028370222,
|
| 87 |
+
4156024188,
|
| 88 |
+
3996363428,
|
| 89 |
+
80495456,
|
| 90 |
+
2659800972,
|
| 91 |
+
2005649973,
|
| 92 |
+
3818358673,
|
| 93 |
+
3952623596,
|
| 94 |
+
2506862371,
|
| 95 |
+
3282302532,
|
| 96 |
+
263923435,
|
| 97 |
+
3384662671,
|
| 98 |
+
3292439172,
|
| 99 |
+
3119957588,
|
| 100 |
+
1224426111,
|
| 101 |
+
899864150,
|
| 102 |
+
215262826,
|
| 103 |
+
1619647231,
|
| 104 |
+
3347694949,
|
| 105 |
+
3497868538,
|
| 106 |
+
2029552053,
|
| 107 |
+
2992804824,
|
| 108 |
+
4080010250,
|
| 109 |
+
2023513186,
|
| 110 |
+
1885979437,
|
| 111 |
+
3564622190,
|
| 112 |
+
3775424270,
|
| 113 |
+
2297810139,
|
| 114 |
+
3549449169,
|
| 115 |
+
2664856277,
|
| 116 |
+
3274801974,
|
| 117 |
+
2794883969,
|
| 118 |
+
980412666,
|
| 119 |
+
2980215653,
|
| 120 |
+
2794389321,
|
| 121 |
+
2816521934,
|
| 122 |
+
1266970739,
|
| 123 |
+
542306338,
|
| 124 |
+
3646225311,
|
| 125 |
+
3598997630,
|
| 126 |
+
2111980720,
|
| 127 |
+
2949252482,
|
| 128 |
+
2489027658,
|
| 129 |
+
352815024,
|
| 130 |
+
11610683,
|
| 131 |
+
1386663624,
|
| 132 |
+
2004196796,
|
| 133 |
+
1161461546,
|
| 134 |
+
1921293780,
|
| 135 |
+
2463949525,
|
| 136 |
+
1647009713,
|
| 137 |
+
3550093655,
|
| 138 |
+
2563894064,
|
| 139 |
+
3486310554,
|
| 140 |
+
1506105865,
|
| 141 |
+
243092931,
|
| 142 |
+
2659437476,
|
| 143 |
+
4200687059,
|
| 144 |
+
2284345122,
|
| 145 |
+
1974438610,
|
| 146 |
+
3591096528,
|
| 147 |
+
967119212,
|
| 148 |
+
3362401375,
|
| 149 |
+
140678365,
|
| 150 |
+
311602112,
|
| 151 |
+
2361740275,
|
| 152 |
+
2139598582,
|
| 153 |
+
3632873481,
|
| 154 |
+
2762232439,
|
| 155 |
+
4156482318,
|
| 156 |
+
381637792,
|
| 157 |
+
3253346525,
|
| 158 |
+
2492118775,
|
| 159 |
+
1502434558,
|
| 160 |
+
3164497290,
|
| 161 |
+
3550998357,
|
| 162 |
+
2412448305,
|
| 163 |
+
2223955385,
|
| 164 |
+
4122879535,
|
| 165 |
+
350121793,
|
| 166 |
+
1835149778,
|
| 167 |
+
2175117867,
|
| 168 |
+
989674750,
|
| 169 |
+
3178241202,
|
| 170 |
+
3553093569,
|
| 171 |
+
3470650311,
|
| 172 |
+
2829698151,
|
| 173 |
+
3209427769,
|
| 174 |
+
1779174943,
|
| 175 |
+
275388428,
|
| 176 |
+
4044574515,
|
| 177 |
+
715447260,
|
| 178 |
+
3180940440,
|
| 179 |
+
4020772289,
|
| 180 |
+
1322708567,
|
| 181 |
+
3189868792,
|
| 182 |
+
4250485633,
|
| 183 |
+
716970023,
|
| 184 |
+
2307550151,
|
| 185 |
+
1074996711,
|
| 186 |
+
1217573599,
|
| 187 |
+
197006094,
|
| 188 |
+
2178394212,
|
| 189 |
+
1255233746,
|
| 190 |
+
4164251484,
|
| 191 |
+
1405608772,
|
| 192 |
+
2808160475,
|
| 193 |
+
1304736088,
|
| 194 |
+
1796071066,
|
| 195 |
+
2761748078,
|
| 196 |
+
3570739698,
|
| 197 |
+
1616118556,
|
| 198 |
+
2232868135,
|
| 199 |
+
3567541936,
|
| 200 |
+
3470600401,
|
| 201 |
+
3031621994,
|
| 202 |
+
3351764214,
|
| 203 |
+
1359785149,
|
| 204 |
+
2617497797,
|
| 205 |
+
3340028190,
|
| 206 |
+
356162828,
|
| 207 |
+
2083806068,
|
| 208 |
+
2503635608,
|
| 209 |
+
4024838996,
|
| 210 |
+
2577080371,
|
| 211 |
+
2897993505,
|
| 212 |
+
3120733934,
|
| 213 |
+
905794891,
|
| 214 |
+
2506078507,
|
| 215 |
+
4211618666,
|
| 216 |
+
3777871979,
|
| 217 |
+
809751414,
|
| 218 |
+
4080874167,
|
| 219 |
+
1562977008,
|
| 220 |
+
3917373055,
|
| 221 |
+
2132779194,
|
| 222 |
+
4014249473,
|
| 223 |
+
4067327082,
|
| 224 |
+
2582869847,
|
| 225 |
+
1780081876,
|
| 226 |
+
1842619106,
|
| 227 |
+
3381761227,
|
| 228 |
+
921004274,
|
| 229 |
+
1393256920,
|
| 230 |
+
1883566732,
|
| 231 |
+
2702071861,
|
| 232 |
+
865327389,
|
| 233 |
+
1622085203,
|
| 234 |
+
3021825820,
|
| 235 |
+
2687061406,
|
| 236 |
+
1748902923,
|
| 237 |
+
689023977,
|
| 238 |
+
308399650,
|
| 239 |
+
2377287978,
|
| 240 |
+
1646969411,
|
| 241 |
+
1051806316,
|
| 242 |
+
4277884230,
|
| 243 |
+
2041056290,
|
| 244 |
+
101134519,
|
| 245 |
+
2032472116,
|
| 246 |
+
4112521069,
|
| 247 |
+
151202901,
|
| 248 |
+
2773743461,
|
| 249 |
+
551348559,
|
| 250 |
+
3476836808,
|
| 251 |
+
510935951,
|
| 252 |
+
625057077,
|
| 253 |
+
3757450756,
|
| 254 |
+
2977698135,
|
| 255 |
+
3027776859,
|
| 256 |
+
2616998041,
|
| 257 |
+
2773430005,
|
| 258 |
+
544190486,
|
| 259 |
+
2241368212,
|
| 260 |
+
1141105829,
|
| 261 |
+
1452816309,
|
| 262 |
+
4199229235,
|
| 263 |
+
3218013033,
|
| 264 |
+
4229475816,
|
| 265 |
+
1659576351,
|
| 266 |
+
3020348754,
|
| 267 |
+
1193400518,
|
| 268 |
+
3208584597,
|
| 269 |
+
1151197733,
|
| 270 |
+
2597187966,
|
| 271 |
+
503065140,
|
| 272 |
+
2421841572,
|
| 273 |
+
1437291709,
|
| 274 |
+
1909275895,
|
| 275 |
+
2872630545,
|
| 276 |
+
793588217,
|
| 277 |
+
3792934707,
|
| 278 |
+
1784451785,
|
| 279 |
+
2921385648,
|
| 280 |
+
1669902526,
|
| 281 |
+
4189978976,
|
| 282 |
+
1196986251,
|
| 283 |
+
434805516,
|
| 284 |
+
1907541826,
|
| 285 |
+
2624415034,
|
| 286 |
+
1687778718,
|
| 287 |
+
650746582,
|
| 288 |
+
1949153382,
|
| 289 |
+
4148493093,
|
| 290 |
+
841300520,
|
| 291 |
+
1164202054,
|
| 292 |
+
4203468658,
|
| 293 |
+
4106300911,
|
| 294 |
+
850346789,
|
| 295 |
+
1715730760,
|
| 296 |
+
3114661489,
|
| 297 |
+
2866524548,
|
| 298 |
+
1360448945,
|
| 299 |
+
3601318775,
|
| 300 |
+
1743078223,
|
| 301 |
+
2413855408,
|
| 302 |
+
1211895622,
|
| 303 |
+
325117146,
|
| 304 |
+
2721152875,
|
| 305 |
+
1284334485,
|
| 306 |
+
2446538832,
|
| 307 |
+
739014618,
|
| 308 |
+
2237045115,
|
| 309 |
+
842553465,
|
| 310 |
+
2538598293,
|
| 311 |
+
746460793,
|
| 312 |
+
4010387366,
|
| 313 |
+
2002655192,
|
| 314 |
+
4193733112,
|
| 315 |
+
1194380773,
|
| 316 |
+
3918217378,
|
| 317 |
+
1447487475,
|
| 318 |
+
5659228,
|
| 319 |
+
3408847694,
|
| 320 |
+
4190318700,
|
| 321 |
+
1862549564,
|
| 322 |
+
781683719,
|
| 323 |
+
1194618118,
|
| 324 |
+
755053413,
|
| 325 |
+
3436011942,
|
| 326 |
+
2885435303,
|
| 327 |
+
3081151348,
|
| 328 |
+
2017642831,
|
| 329 |
+
1053816502,
|
| 330 |
+
1086627485,
|
| 331 |
+
2157296554,
|
| 332 |
+
110650022,
|
| 333 |
+
965352898,
|
| 334 |
+
1003174194,
|
| 335 |
+
1288956241,
|
| 336 |
+
4057404871,
|
| 337 |
+
2965068465,
|
| 338 |
+
2897064481,
|
| 339 |
+
2457377317,
|
| 340 |
+
1879872545,
|
| 341 |
+
358455290,
|
| 342 |
+
375086701,
|
| 343 |
+
3015902095,
|
| 344 |
+
1676249984,
|
| 345 |
+
924455526,
|
| 346 |
+
2084169389,
|
| 347 |
+
1989014644,
|
| 348 |
+
1993749926,
|
| 349 |
+
2009424973,
|
| 350 |
+
2113340508,
|
| 351 |
+
3980883273,
|
| 352 |
+
2915977458,
|
| 353 |
+
203328382,
|
| 354 |
+
3020815229,
|
| 355 |
+
2415050113,
|
| 356 |
+
4103009585,
|
| 357 |
+
3700885489,
|
| 358 |
+
2916647550,
|
| 359 |
+
1523006503,
|
| 360 |
+
174302338,
|
| 361 |
+
2476909338,
|
| 362 |
+
1969322490,
|
| 363 |
+
4285741984,
|
| 364 |
+
1528449097,
|
| 365 |
+
3355315515,
|
| 366 |
+
4217241278,
|
| 367 |
+
599579127,
|
| 368 |
+
2572243673,
|
| 369 |
+
3035856735,
|
| 370 |
+
1539140489,
|
| 371 |
+
1782314913,
|
| 372 |
+
4238644287,
|
| 373 |
+
1746424142,
|
| 374 |
+
1978148312,
|
| 375 |
+
2380746849,
|
| 376 |
+
184941882,
|
| 377 |
+
1106717981,
|
| 378 |
+
1720750349,
|
| 379 |
+
981701307,
|
| 380 |
+
3953154731,
|
| 381 |
+
3257809181,
|
| 382 |
+
2892339376,
|
| 383 |
+
3339778166,
|
| 384 |
+
3676936849,
|
| 385 |
+
87425948,
|
| 386 |
+
3029257381,
|
| 387 |
+
2037942523,
|
| 388 |
+
3807628706,
|
| 389 |
+
2861474706,
|
| 390 |
+
1058852346,
|
| 391 |
+
1322765211,
|
| 392 |
+
2686046342,
|
| 393 |
+
2689342655,
|
| 394 |
+
2303436168,
|
| 395 |
+
2571627181,
|
| 396 |
+
1986057734,
|
| 397 |
+
1183564308,
|
| 398 |
+
2829677523,
|
| 399 |
+
1295563975,
|
| 400 |
+
503126586,
|
| 401 |
+
2025890348,
|
| 402 |
+
4179277821,
|
| 403 |
+
1735262467,
|
| 404 |
+
981331774,
|
| 405 |
+
1613447066,
|
| 406 |
+
1011606109,
|
| 407 |
+
2000062246,
|
| 408 |
+
3581448390,
|
| 409 |
+
3477731384,
|
| 410 |
+
3641307373,
|
| 411 |
+
3508544379,
|
| 412 |
+
2327233491,
|
| 413 |
+
3931944343,
|
| 414 |
+
4189052882,
|
| 415 |
+
2990416380,
|
| 416 |
+
422406169,
|
| 417 |
+
202291313,
|
| 418 |
+
2531006461,
|
| 419 |
+
4277024116,
|
| 420 |
+
3815144003,
|
| 421 |
+
821314585,
|
| 422 |
+
1344175168,
|
| 423 |
+
3562834071,
|
| 424 |
+
1339615445,
|
| 425 |
+
1831545190,
|
| 426 |
+
3115548822,
|
| 427 |
+
743512780,
|
| 428 |
+
4006999448,
|
| 429 |
+
3720181735,
|
| 430 |
+
1012033521,
|
| 431 |
+
919931041,
|
| 432 |
+
2628967879,
|
| 433 |
+
1151876565,
|
| 434 |
+
1268107129,
|
| 435 |
+
3674829936,
|
| 436 |
+
834977846,
|
| 437 |
+
743987006,
|
| 438 |
+
3947536548,
|
| 439 |
+
3706529695,
|
| 440 |
+
4121073678,
|
| 441 |
+
2507605742,
|
| 442 |
+
1595636918,
|
| 443 |
+
2708047833,
|
| 444 |
+
2427507331,
|
| 445 |
+
3868216331,
|
| 446 |
+
3254240010,
|
| 447 |
+
2097683411,
|
| 448 |
+
3279710596,
|
| 449 |
+
3686819053,
|
| 450 |
+
1843541720,
|
| 451 |
+
1683793619,
|
| 452 |
+
3245287285,
|
| 453 |
+
3571828776,
|
| 454 |
+
3733296431,
|
| 455 |
+
3806747478,
|
| 456 |
+
1390930605,
|
| 457 |
+
3860422228,
|
| 458 |
+
114397037,
|
| 459 |
+
1931519825,
|
| 460 |
+
2770684378,
|
| 461 |
+
1556101783,
|
| 462 |
+
1436111731,
|
| 463 |
+
4031950081,
|
| 464 |
+
562876656,
|
| 465 |
+
1775895782,
|
| 466 |
+
612364620,
|
| 467 |
+
1313509772,
|
| 468 |
+
4283410242,
|
| 469 |
+
3252958463,
|
| 470 |
+
2176555836,
|
| 471 |
+
3933073367,
|
| 472 |
+
3013277102,
|
| 473 |
+
1444071961,
|
| 474 |
+
3120949516,
|
| 475 |
+
2824578890,
|
| 476 |
+
325676929,
|
| 477 |
+
943677134,
|
| 478 |
+
1800649256,
|
| 479 |
+
1721927060,
|
| 480 |
+
347498719,
|
| 481 |
+
1435221321,
|
| 482 |
+
2623572981,
|
| 483 |
+
1408548470,
|
| 484 |
+
4145586315,
|
| 485 |
+
2901889237,
|
| 486 |
+
1849377952,
|
| 487 |
+
1239144551,
|
| 488 |
+
3382598266,
|
| 489 |
+
2992893897,
|
| 490 |
+
3738297588,
|
| 491 |
+
611280106,
|
| 492 |
+
3897415338,
|
| 493 |
+
2370299241,
|
| 494 |
+
1772308583,
|
| 495 |
+
3697465753,
|
| 496 |
+
354508058,
|
| 497 |
+
2702360134,
|
| 498 |
+
591308331,
|
| 499 |
+
3524072501,
|
| 500 |
+
976616000,
|
| 501 |
+
2563717192,
|
| 502 |
+
3078266097,
|
| 503 |
+
1376594703,
|
| 504 |
+
4209795919,
|
| 505 |
+
2454412767,
|
| 506 |
+
2712206031,
|
| 507 |
+
2963860163,
|
| 508 |
+
3734324882,
|
| 509 |
+
2248653800,
|
| 510 |
+
324872786,
|
| 511 |
+
3789837448,
|
| 512 |
+
3779000146,
|
| 513 |
+
527733939,
|
| 514 |
+
2844165793,
|
| 515 |
+
576499681,
|
| 516 |
+
1618787435,
|
| 517 |
+
2638888650,
|
| 518 |
+
57511068,
|
| 519 |
+
2804627518,
|
| 520 |
+
2993670030,
|
| 521 |
+
481402236,
|
| 522 |
+
2810124845,
|
| 523 |
+
1416045214,
|
| 524 |
+
1723694191,
|
| 525 |
+
1214944572,
|
| 526 |
+
3188123783,
|
| 527 |
+
1139185907,
|
| 528 |
+
3851015362,
|
| 529 |
+
1719652470,
|
| 530 |
+
1661343029,
|
| 531 |
+
3644307578,
|
| 532 |
+
3564178709,
|
| 533 |
+
1256656955,
|
| 534 |
+
46631590,
|
| 535 |
+
4231317929,
|
| 536 |
+
3098958589,
|
| 537 |
+
1834956625,
|
| 538 |
+
2206185428,
|
| 539 |
+
3695688374,
|
| 540 |
+
3647957317,
|
| 541 |
+
1064098871,
|
| 542 |
+
1739100906,
|
| 543 |
+
2579568980,
|
| 544 |
+
27974051,
|
| 545 |
+
2617466775,
|
| 546 |
+
964075233,
|
| 547 |
+
907049942,
|
| 548 |
+
4164146575,
|
| 549 |
+
3377168066,
|
| 550 |
+
2524828266,
|
| 551 |
+
1083546008,
|
| 552 |
+
2992960953,
|
| 553 |
+
2260789066,
|
| 554 |
+
1543742095,
|
| 555 |
+
2843842831,
|
| 556 |
+
1375722284,
|
| 557 |
+
3574521313,
|
| 558 |
+
110842534,
|
| 559 |
+
2310998251,
|
| 560 |
+
3076511734,
|
| 561 |
+
783145600,
|
| 562 |
+
1287776608,
|
| 563 |
+
3087144146,
|
| 564 |
+
305559823,
|
| 565 |
+
2356293719,
|
| 566 |
+
3228441476,
|
| 567 |
+
1678938122,
|
| 568 |
+
3775814061,
|
| 569 |
+
1620283952,
|
| 570 |
+
2512027726,
|
| 571 |
+
1031432407,
|
| 572 |
+
962295099,
|
| 573 |
+
3877418501,
|
| 574 |
+
968669928,
|
| 575 |
+
304126693,
|
| 576 |
+
3711291137,
|
| 577 |
+
3847527101,
|
| 578 |
+
494066767,
|
| 579 |
+
4050229756,
|
| 580 |
+
4169448589,
|
| 581 |
+
671763915,
|
| 582 |
+
1095747781,
|
| 583 |
+
4006132710,
|
| 584 |
+
394725957,
|
| 585 |
+
200521654,
|
| 586 |
+
2715998750,
|
| 587 |
+
1477567673,
|
| 588 |
+
895171901,
|
| 589 |
+
3370105999,
|
| 590 |
+
2684157455,
|
| 591 |
+
4153990023,
|
| 592 |
+
3966076501,
|
| 593 |
+
2043374409,
|
| 594 |
+
144443759,
|
| 595 |
+
6764556,
|
| 596 |
+
1611650045,
|
| 597 |
+
1480956755,
|
| 598 |
+
1388276468,
|
| 599 |
+
4136518438,
|
| 600 |
+
1538041336,
|
| 601 |
+
266773992,
|
| 602 |
+
1623357516,
|
| 603 |
+
2267298390,
|
| 604 |
+
3183919402,
|
| 605 |
+
1084292424,
|
| 606 |
+
2796136160,
|
| 607 |
+
2413448816,
|
| 608 |
+
2850375199,
|
| 609 |
+
3510894040,
|
| 610 |
+
2644778623,
|
| 611 |
+
3317288284,
|
| 612 |
+
3697317540,
|
| 613 |
+
1465776787,
|
| 614 |
+
1843489446,
|
| 615 |
+
1416711171,
|
| 616 |
+
744701117,
|
| 617 |
+
1286781349,
|
| 618 |
+
3748640476,
|
| 619 |
+
861982119,
|
| 620 |
+
2377742909,
|
| 621 |
+
1171768136,
|
| 622 |
+
2701877439,
|
| 623 |
+
3839724288,
|
| 624 |
+
2869791015,
|
| 625 |
+
2386067954,
|
| 626 |
+
2629214347,
|
| 627 |
+
955801623,
|
| 628 |
+
3831079317,
|
| 629 |
+
624
|
| 630 |
+
],
|
| 631 |
+
null
|
| 632 |
+
],
|
| 633 |
+
"progress_sampler": null
|
| 634 |
+
}
|
metrics.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 1000,
|
| 3 |
+
"metrics": {
|
| 4 |
+
"eval_rew_align/success_auprc_robotsmith": 0.7499203111579319,
|
| 5 |
+
"eval_rew_align/positive_success_acc_robotsmith": 0.9166666666666666,
|
| 6 |
+
"eval_rew_align/negative_success_acc_robotsmith": 0.9577464788732394,
|
| 7 |
+
"eval_rew_align/loss_robotsmith": 4.106191897392273,
|
| 8 |
+
"eval_rew_align/pearson_robotsmith": 0.9856438673457457,
|
| 9 |
+
"eval_p_rank/kendall_last_robotsmith": 0.5733333333333333,
|
| 10 |
+
"eval_p_rank/kendall_rewind_last_robotsmith": 1.0,
|
| 11 |
+
"eval_p_rank/avg_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
|
| 12 |
+
"eval_p_rank/min_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
|
| 13 |
+
"eval_p_rank/max_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
|
| 14 |
+
"eval_p_rank/avg_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
|
| 15 |
+
"eval_p_rank/min_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
|
| 16 |
+
"eval_p_rank/max_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
|
| 17 |
+
"eval_p_rank/avg_succ_fail_diff_last_robotsmith": 0.2167688846588135,
|
| 18 |
+
"eval_p_rank/min_succ_fail_diff_last_robotsmith": 0.2167688846588135,
|
| 19 |
+
"eval_p_rank/max_succ_fail_diff_last_robotsmith": 0.2167688846588135,
|
| 20 |
+
"eval_p_rank/ranking_acc_last_robotsmith": 0.7866666666666666,
|
| 21 |
+
"eval_p_rank/ranking_acc_all_pairs_last_robotsmith": 0.7866666666666666,
|
| 22 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_robotsmith": 0.88,
|
| 23 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_robotsmith": 0.92,
|
| 24 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_robotsmith": 0.56,
|
| 25 |
+
"eval_p_rank/kendall_avg_robotsmith": 0.5733333333333333,
|
| 26 |
+
"eval_p_rank/kendall_rewind_avg_robotsmith": 1.0,
|
| 27 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
|
| 28 |
+
"eval_p_rank/min_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
|
| 29 |
+
"eval_p_rank/max_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
|
| 30 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
|
| 31 |
+
"eval_p_rank/min_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
|
| 32 |
+
"eval_p_rank/max_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
|
| 33 |
+
"eval_p_rank/avg_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
|
| 34 |
+
"eval_p_rank/min_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
|
| 35 |
+
"eval_p_rank/max_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
|
| 36 |
+
"eval_p_rank/ranking_acc_avg_robotsmith": 0.7866666666666666,
|
| 37 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_robotsmith": 0.7866666666666666,
|
| 38 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_robotsmith": 0.88,
|
| 39 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_robotsmith": 0.92,
|
| 40 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_robotsmith": 0.56,
|
| 41 |
+
"eval_p_rank/kendall_sum_robotsmith": 0.5733333333333333,
|
| 42 |
+
"eval_p_rank/kendall_rewind_sum_robotsmith": 1.0,
|
| 43 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
|
| 44 |
+
"eval_p_rank/min_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
|
| 45 |
+
"eval_p_rank/max_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
|
| 46 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
|
| 47 |
+
"eval_p_rank/min_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
|
| 48 |
+
"eval_p_rank/max_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
|
| 49 |
+
"eval_p_rank/avg_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
|
| 50 |
+
"eval_p_rank/min_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
|
| 51 |
+
"eval_p_rank/max_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
|
| 52 |
+
"eval_p_rank/ranking_acc_sum_robotsmith": 0.7866666666666666,
|
| 53 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_robotsmith": 0.7866666666666666,
|
| 54 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_robotsmith": 0.88,
|
| 55 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_robotsmith": 0.92,
|
| 56 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_robotsmith": 0.56,
|
| 57 |
+
"time/custom_evaluations": 43.09463632851839
|
| 58 |
+
}
|
| 59 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2982610f0ccd8107da144283272036b293d463650736ea9fa5ad26005095f8f1
|
| 3 |
+
size 4996131352
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a88f50169e028271b39276a4a58f12bd9c1029846f25c9a76c5a1670bd914b8c
|
| 3 |
+
size 4162297688
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4baeef43bb862ad3754712e49984f3832701d420189d1eb6180f1bd093a620
|
| 3 |
+
size 5841
|