tu101 commited on
Commit
6bd1c8f
·
verified ·
1 Parent(s): d2d9fc7

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. README.md +83 -1
  2. SHA256SUMS.txt +32 -0
  3. ablation500/A0/seed-0-checkpoint-400/adapter_config.json +57 -0
  4. ablation500/A0/seed-0-checkpoint-400/adapter_model.safetensors +3 -0
  5. ablation500/A0/seed-1-checkpoint-400/adapter_config.json +57 -0
  6. ablation500/A0/seed-2-checkpoint-400/adapter_config.json +57 -0
  7. ablation500/A2/seed-0-checkpoint-400/adapter_config.json +57 -0
  8. ablation500/A2/seed-0-checkpoint-400/adapter_model.safetensors +3 -0
  9. ablation500/A2/seed-1-checkpoint-400/adapter_config.json +57 -0
  10. ablation500/A2/seed-1-checkpoint-400/adapter_model.safetensors +3 -0
  11. ablation500/A2/seed-2-checkpoint-400/adapter_config.json +57 -0
  12. ablation500/A2/seed-2-checkpoint-400/adapter_model.safetensors +3 -0
  13. ablation500/A4/seed-0-checkpoint-400/adapter_config.json +57 -0
  14. ablation500/A4/seed-1-checkpoint-400/adapter_config.json +57 -0
  15. ablation500/A4/seed-2-checkpoint-400/adapter_config.json +57 -0
  16. ablation500/B1/seed-0-checkpoint-400/adapter_config.json +57 -0
  17. ablation500/B1/seed-0-checkpoint-400/adapter_model.safetensors +3 -0
  18. ablation500/B1/seed-1-checkpoint-400/adapter_config.json +57 -0
  19. ablation500/B1/seed-1-checkpoint-400/adapter_model.safetensors +3 -0
  20. ablation500/B1/seed-2-checkpoint-400/adapter_config.json +57 -0
  21. ablation500/B1/seed-2-checkpoint-400/adapter_model.safetensors +3 -0
  22. adapter_manifest.json +336 -0
  23. continuation-arms/A0/seed-2-checkpoint-400/adapter_config.json +57 -0
  24. continuation-arms/A0/seed-2-checkpoint-400/adapter_model.safetensors +3 -0
  25. continuation-arms/A0/seed-3-checkpoint-400/adapter_config.json +57 -0
  26. continuation-arms/A0/seed-3-checkpoint-400/adapter_model.safetensors +3 -0
  27. continuation-arms/A0/seed-4-checkpoint-400/adapter_config.json +57 -0
  28. continuation-arms/A0/seed-4-checkpoint-400/adapter_model.safetensors +3 -0
  29. continuation-arms/A0/seed-5-checkpoint-400/adapter_config.json +57 -0
  30. continuation-arms/A2/seed-1-checkpoint-400/adapter_config.json +57 -0
  31. continuation-arms/A2/seed-2-checkpoint-400/adapter_config.json +57 -0
  32. continuation-arms/A2/seed-3-checkpoint-400/adapter_config.json +57 -0
  33. continuation-arms/A2/seed-4-checkpoint-400/adapter_config.json +57 -0
  34. continuation-arms/A2/seed-5-checkpoint-400/adapter_config.json +57 -0
  35. continuation-arms/A4/seed-1-checkpoint-400/adapter_config.json +57 -0
  36. continuation-arms/A4/seed-1-checkpoint-400/adapter_model.safetensors +3 -0
  37. continuation-arms/A4/seed-2-checkpoint-400/adapter_config.json +57 -0
  38. continuation-arms/A4/seed-2-checkpoint-400/adapter_model.safetensors +3 -0
  39. continuation-arms/B1/seed-1-checkpoint-400/adapter_config.json +57 -0
  40. continuation-arms/B1/seed-2-checkpoint-400/adapter_config.json +57 -0
  41. continuation-arms/B1/seed-3-checkpoint-400/adapter_config.json +57 -0
  42. continuation-arms/B1/seed-4-checkpoint-400/adapter_config.json +57 -0
  43. continuation-arms/B1/seed-5-checkpoint-400/adapter_config.json +57 -0
  44. continuation/selected-A0-seed1-checkpoint-400/adapter_config.json +57 -0
  45. main/seed-0-checkpoint-1500/adapter_config.json +57 -0
  46. main/seed-0-checkpoint-1500/adapter_model.safetensors +3 -0
  47. main/seed-1-checkpoint-1500/adapter_config.json +57 -0
  48. main/seed-1-checkpoint-1500/adapter_model.safetensors +3 -0
  49. main/seed-2-checkpoint-1500/adapter_config.json +57 -0
  50. main/seed-2-checkpoint-1500/adapter_model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,85 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen3.5-4B
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - qwen3.5
8
+ - peft
9
+ - lora
10
+ - reinforcement-learning
11
+ - tool-use
12
+ - least-privilege
13
  ---
14
+
15
+ # Least-Privilege RL adapters
16
+
17
+ LoRA adapters for the least-privilege terminal-agent experiments. The adapters
18
+ target [`Qwen/Qwen3.5-4B`](https://huggingface.co/Qwen/Qwen3.5-4B) and use PEFT
19
+ LoRA rank 32, alpha 64, and dropout 0.
20
+
21
+ ## Recommended adapters
22
+
23
+ - `main/seed-1-checkpoint-1500`: primary policy selected by the frozen internal
24
+ protocol before external-benchmark analysis.
25
+ - `continuation/selected-A0-seed1-checkpoint-400`: selected post-hoc corrective
26
+ continuation from the primary policy, trained on 200 corrective tasks
27
+ interleaved with 200 source-exact replay tasks.
28
+
29
+ ## Repository contents
30
+
31
+ The release contains 32 physical final experiment endpoints:
32
+
33
+ - three primary checkpoint-1500 seeds;
34
+ - the selected continuation-400 endpoint;
35
+ - 12 base-start reward-ablation endpoints (`A0`, `A2`, `A4`, and `B1`, three
36
+ seeds each);
37
+ - 16 production-policy continuation reward-arm endpoints (`A0` seeds 2-5,
38
+ `A2` seeds 1-5, `A4` seeds 1-2, and `B1` seeds 1-5).
39
+
40
+ `A0` continuation seed 1 is the selected continuation adapter and appears once
41
+ physically; `adapter_manifest.json` records its logical alias. Intermediate
42
+ autosaves and optimizer states are intentionally excluded: they are not reported
43
+ model endpoints and would add roughly 70 GiB of redundant training state.
44
+
45
+ Every weight file is accompanied by its PEFT `adapter_config.json`. The manifest
46
+ records source campaign, arm, seed, step, byte size, and SHA-256 hash, and
47
+ `SHA256SUMS.txt` permits direct integrity checking.
48
+
49
+ ## Loading
50
+
51
+ ```python
52
+ from transformers import AutoModelForCausalLM, AutoTokenizer
53
+ from peft import PeftModel
54
+
55
+ base_id = "Qwen/Qwen3.5-4B"
56
+ repo_id = "tu101/least-privilege-model"
57
+
58
+ tokenizer = AutoTokenizer.from_pretrained(base_id)
59
+ base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
60
+ model = PeftModel.from_pretrained(
61
+ base,
62
+ repo_id,
63
+ subfolder="main/seed-1-checkpoint-1500",
64
+ )
65
+ ```
66
+
67
+ The evaluation environment supplies the tool-interface system prompt and
68
+ executes tool calls through the host-authoritative broker; loading an adapter
69
+ alone does not reproduce the sandbox. Code, first-party task catalogs,
70
+ reproduction instructions, compact result records, and the manuscript are at
71
+ [`Astrowebdeving/least_privilege_grpo`](https://github.com/Astrowebdeving/least_privilege_grpo).
72
+
73
+ ## Result summary and limitations
74
+
75
+ The primary checkpoint improves frozen internal safe success from 64.36% to
76
+ 98.86% and lowers over-privileged success from 4.56% to 0.45%. External transfer
77
+ is heterogeneous: MetaTool and FORTIS direct skill selection improve modestly,
78
+ whereas the primary policy is approximately tied with base on aggregate
79
+ ToolPrivBench and has category-specific regressions. The corrective continuation
80
+ reduces ToolPrivBench over-privileged selection from 44.85% at its parent to
81
+ 38.05% while retaining frozen internal performance; with ToolPrivBench's
82
+ privilege-aware prompt it reaches 26.65%.
83
+
84
+ These are research adapters, not a security boundary or a guarantee that tool
85
+ use is safe. Use the broker, sandbox, and policy controls from the code release.
SHA256SUMS.txt ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ b6d0687dcf6e263132991830b0c146e7774fbe3bcfa37f8f30f68c86490ae80f main/seed-0-checkpoint-1500/adapter_model.safetensors
2
+ 41ce33e4f31433057d6396800b871bb2d45129037ae9698e8ddfbbb13ec70275 main/seed-1-checkpoint-1500/adapter_model.safetensors
3
+ ef91460fef71a7d56d3ecec17e4c29db201bc94ac9f4dc4a34957572f0d4af02 main/seed-2-checkpoint-1500/adapter_model.safetensors
4
+ 63c81f8d77d671361190058ac32e072dae260c3632ffba8f4cf22a73726192e2 continuation/selected-A0-seed1-checkpoint-400/adapter_model.safetensors
5
+ fc5ebebcd2241101e02d66715d499a3a18e5e8c2aafd4314dd9802b42488a6a6 ablation500/A0/seed-0-checkpoint-400/adapter_model.safetensors
6
+ a99d5c1f4ca86b8f68a333a6081aed44054f86ad0b94cc4f1b6e99e30d8c0b15 ablation500/A0/seed-1-checkpoint-400/adapter_model.safetensors
7
+ 6c2751680c83ad331802d57ec0818f736cca9264102dbc335b43f2191a381748 ablation500/A0/seed-2-checkpoint-400/adapter_model.safetensors
8
+ 7491a845b6bd70343a8333bf087c1112634ec4c5afc217fa46c69f698b4c238d ablation500/A2/seed-0-checkpoint-400/adapter_model.safetensors
9
+ a70fec52970ab01221aa0ba6b6f016373698aaf73a28170d2d011c54e48e0e86 ablation500/A2/seed-1-checkpoint-400/adapter_model.safetensors
10
+ 4e8c970a3a86dadef381d3586aa41c8ea6f9403adb044036e3fc29d84dac4a12 ablation500/A2/seed-2-checkpoint-400/adapter_model.safetensors
11
+ 972966bfea23e485ac0988ef32431482005840f17ee7d7f6df1f25e6ea8487c3 ablation500/A4/seed-0-checkpoint-400/adapter_model.safetensors
12
+ c37e7ef2c1ce12c48fd2a6d7d668c7fb668c9039439f2afc2fd1b15fe36ecc44 ablation500/A4/seed-1-checkpoint-400/adapter_model.safetensors
13
+ 69a7a6af7f7b39832e0ee8f7190a59dd64c48a74f0d58ac62fc039e370d1243c ablation500/A4/seed-2-checkpoint-400/adapter_model.safetensors
14
+ 8d835ed634e343414a44d268882b82da1a2fd5ff137b34599fa456fa2faf2bd0 ablation500/B1/seed-0-checkpoint-400/adapter_model.safetensors
15
+ 49a77f04837ecd7e96365aa8ed4c5a807d37c8770edefdf900fd25869b81db39 ablation500/B1/seed-1-checkpoint-400/adapter_model.safetensors
16
+ 71a293817c0c61eda22a0b9bcd1eac569968c96dd0b56ec23113883d4ac6f98e ablation500/B1/seed-2-checkpoint-400/adapter_model.safetensors
17
+ 0da054a58393ead2557f6b874dab8fdcc8de76778b747c40811bebd84c27ee34 continuation-arms/A0/seed-2-checkpoint-400/adapter_model.safetensors
18
+ 4fc83d3490a0f1fc189bc32014de2af46fa56fb322988faaef394ba949db96ce continuation-arms/A0/seed-3-checkpoint-400/adapter_model.safetensors
19
+ 43fc42e0570c27ae33d1daf7b59bb3a422392e7a16e66f2624a689527c795c4b continuation-arms/A0/seed-4-checkpoint-400/adapter_model.safetensors
20
+ dc47c3224ccac39372a0cbd79e4fbd8389842b9dac85b933767363f6a6f31a96 continuation-arms/A0/seed-5-checkpoint-400/adapter_model.safetensors
21
+ bf23cdcba788c27b69350eb9c03ab13fd916be256ede69b9e781e22e34709009 continuation-arms/A2/seed-1-checkpoint-400/adapter_model.safetensors
22
+ e6731a578801798bf37a4cbfa708a73fdc2efa38e367e7a576f3f88069371494 continuation-arms/A2/seed-2-checkpoint-400/adapter_model.safetensors
23
+ 7a34e1ecb83b10b5f79614090abfde0ddf18703ba8a313373c0154401ed191e4 continuation-arms/A2/seed-3-checkpoint-400/adapter_model.safetensors
24
+ e544fb40dd12a9e5c43e53892a81a9ca944628386eb3e9a9ef00ac4f341c84d5 continuation-arms/A2/seed-4-checkpoint-400/adapter_model.safetensors
25
+ 629d8151977ac7dc6e20f59a0a2ff8ec062942a1e365adca17501da3d48e8dd9 continuation-arms/A2/seed-5-checkpoint-400/adapter_model.safetensors
26
+ 3febd2da73cc5fcaa6ad58667ffddfb4a82b1fcf790109809aa318f2d2a7572e continuation-arms/A4/seed-1-checkpoint-400/adapter_model.safetensors
27
+ ed63f4fedce10c43055e54e52c6ef87482b0c95886be97ef678e4aa0e921eb9b continuation-arms/A4/seed-2-checkpoint-400/adapter_model.safetensors
28
+ 5dc8b2c14e65d43ddc30b1fd7c9c25a1020b65a54a28632ad4eb7500256f457a continuation-arms/B1/seed-1-checkpoint-400/adapter_model.safetensors
29
+ 52ede1aba4b1027cf9fe94c5584833de621e479186d7df30d0a11995dd0b1cc9 continuation-arms/B1/seed-2-checkpoint-400/adapter_model.safetensors
30
+ 21b47884ab18d03d7709e752f518589069fc8e9402c20e63c45797b336a8104b continuation-arms/B1/seed-3-checkpoint-400/adapter_model.safetensors
31
+ 995bd82551dba281621ac25fd0be2a839c20199f08e1e3ccf8491a09c26c7c80 continuation-arms/B1/seed-4-checkpoint-400/adapter_model.safetensors
32
+ a2b58c6e7f7f397ade49dc1a34a6d99eda2590996535ed83097cb36f05fe5cec continuation-arms/B1/seed-5-checkpoint-400/adapter_model.safetensors
ablation500/A0/seed-0-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_b",
34
+ "v_proj",
35
+ "out_proj",
36
+ "in_proj_z",
37
+ "down_proj",
38
+ "attn.proj",
39
+ "q_proj",
40
+ "linear_fc1",
41
+ "o_proj",
42
+ "qkv",
43
+ "gate_proj",
44
+ "up_proj",
45
+ "in_proj_a",
46
+ "k_proj",
47
+ "in_proj_qkv",
48
+ "linear_fc2"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A0/seed-0-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5ebebcd2241101e02d66715d499a3a18e5e8c2aafd4314dd9802b42488a6a6
3
+ size 312053840
ablation500/A0/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "o_proj",
34
+ "in_proj_b",
35
+ "gate_proj",
36
+ "v_proj",
37
+ "linear_fc2",
38
+ "k_proj",
39
+ "up_proj",
40
+ "in_proj_z",
41
+ "down_proj",
42
+ "out_proj",
43
+ "attn.proj",
44
+ "q_proj",
45
+ "in_proj_a",
46
+ "qkv",
47
+ "in_proj_qkv",
48
+ "linear_fc1"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A0/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "attn.proj",
34
+ "in_proj_b",
35
+ "in_proj_qkv",
36
+ "down_proj",
37
+ "gate_proj",
38
+ "in_proj_z",
39
+ "out_proj",
40
+ "up_proj",
41
+ "o_proj",
42
+ "v_proj",
43
+ "q_proj",
44
+ "in_proj_a",
45
+ "linear_fc1",
46
+ "linear_fc2",
47
+ "qkv",
48
+ "k_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A2/seed-0-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc1",
34
+ "in_proj_z",
35
+ "attn.proj",
36
+ "q_proj",
37
+ "qkv",
38
+ "v_proj",
39
+ "o_proj",
40
+ "gate_proj",
41
+ "linear_fc2",
42
+ "in_proj_a",
43
+ "in_proj_b",
44
+ "k_proj",
45
+ "down_proj",
46
+ "in_proj_qkv",
47
+ "out_proj",
48
+ "up_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A2/seed-0-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7491a845b6bd70343a8333bf087c1112634ec4c5afc217fa46c69f698b4c238d
3
+ size 312053840
ablation500/A2/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "qkv",
34
+ "in_proj_qkv",
35
+ "linear_fc1",
36
+ "o_proj",
37
+ "attn.proj",
38
+ "in_proj_b",
39
+ "gate_proj",
40
+ "in_proj_z",
41
+ "q_proj",
42
+ "down_proj",
43
+ "k_proj",
44
+ "up_proj",
45
+ "in_proj_a",
46
+ "out_proj",
47
+ "v_proj",
48
+ "linear_fc2"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A2/seed-1-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70fec52970ab01221aa0ba6b6f016373698aaf73a28170d2d011c54e48e0e86
3
+ size 312053840
ablation500/A2/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_qkv",
34
+ "in_proj_b",
35
+ "v_proj",
36
+ "linear_fc2",
37
+ "linear_fc1",
38
+ "up_proj",
39
+ "attn.proj",
40
+ "gate_proj",
41
+ "in_proj_z",
42
+ "in_proj_a",
43
+ "down_proj",
44
+ "out_proj",
45
+ "q_proj",
46
+ "o_proj",
47
+ "qkv",
48
+ "k_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A2/seed-2-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8c970a3a86dadef381d3586aa41c8ea6f9403adb044036e3fc29d84dac4a12
3
+ size 312053840
ablation500/A4/seed-0-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "gate_proj",
34
+ "out_proj",
35
+ "o_proj",
36
+ "up_proj",
37
+ "v_proj",
38
+ "in_proj_a",
39
+ "q_proj",
40
+ "attn.proj",
41
+ "in_proj_qkv",
42
+ "linear_fc2",
43
+ "in_proj_z",
44
+ "linear_fc1",
45
+ "in_proj_b",
46
+ "down_proj",
47
+ "qkv",
48
+ "k_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A4/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "out_proj",
34
+ "in_proj_qkv",
35
+ "gate_proj",
36
+ "in_proj_z",
37
+ "k_proj",
38
+ "in_proj_a",
39
+ "o_proj",
40
+ "qkv",
41
+ "up_proj",
42
+ "in_proj_b",
43
+ "v_proj",
44
+ "linear_fc1",
45
+ "attn.proj",
46
+ "q_proj",
47
+ "linear_fc2",
48
+ "down_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/A4/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc1",
34
+ "qkv",
35
+ "o_proj",
36
+ "in_proj_b",
37
+ "attn.proj",
38
+ "in_proj_z",
39
+ "q_proj",
40
+ "v_proj",
41
+ "linear_fc2",
42
+ "k_proj",
43
+ "gate_proj",
44
+ "down_proj",
45
+ "out_proj",
46
+ "in_proj_a",
47
+ "up_proj",
48
+ "in_proj_qkv"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/B1/seed-0-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_b",
34
+ "in_proj_z",
35
+ "out_proj",
36
+ "k_proj",
37
+ "attn.proj",
38
+ "in_proj_qkv",
39
+ "v_proj",
40
+ "down_proj",
41
+ "linear_fc1",
42
+ "qkv",
43
+ "in_proj_a",
44
+ "gate_proj",
45
+ "up_proj",
46
+ "o_proj",
47
+ "linear_fc2",
48
+ "q_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/B1/seed-0-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d835ed634e343414a44d268882b82da1a2fd5ff137b34599fa456fa2faf2bd0
3
+ size 312053840
ablation500/B1/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc2",
34
+ "in_proj_qkv",
35
+ "q_proj",
36
+ "k_proj",
37
+ "o_proj",
38
+ "down_proj",
39
+ "up_proj",
40
+ "v_proj",
41
+ "linear_fc1",
42
+ "in_proj_z",
43
+ "out_proj",
44
+ "gate_proj",
45
+ "qkv",
46
+ "in_proj_b",
47
+ "in_proj_a",
48
+ "attn.proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/B1/seed-1-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a77f04837ecd7e96365aa8ed4c5a807d37c8770edefdf900fd25869b81db39
3
+ size 312053840
ablation500/B1/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_z",
34
+ "down_proj",
35
+ "in_proj_b",
36
+ "qkv",
37
+ "linear_fc2",
38
+ "gate_proj",
39
+ "linear_fc1",
40
+ "out_proj",
41
+ "in_proj_qkv",
42
+ "in_proj_a",
43
+ "q_proj",
44
+ "up_proj",
45
+ "attn.proj",
46
+ "v_proj",
47
+ "o_proj",
48
+ "k_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
ablation500/B1/seed-2-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a293817c0c61eda22a0b9bcd1eac569968c96dd0b56ec23113883d4ac6f98e
3
+ size 312053840
adapter_manifest.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aliases": {
3
+ "continuation-arms/A0/seed-1-checkpoint-400": "continuation/selected-A0-seed1-checkpoint-400"
4
+ },
5
+ "base_model": "Qwen/Qwen3.5-4B",
6
+ "endpoints": [
7
+ {
8
+ "adapter_model_bytes": 312053840,
9
+ "adapter_model_sha256": "b6d0687dcf6e263132991830b0c146e7774fbe3bcfa37f8f30f68c86490ae80f",
10
+ "campaign": "primary",
11
+ "path": "main/seed-0-checkpoint-1500",
12
+ "reward_arm": "A0",
13
+ "seed": 0,
14
+ "source_artifact": "logs/artifacts/bigrun_v2_2026-07-01_003238/seed-0/checkpoint-1500",
15
+ "step": 1500
16
+ },
17
+ {
18
+ "adapter_model_bytes": 312053840,
19
+ "adapter_model_sha256": "41ce33e4f31433057d6396800b871bb2d45129037ae9698e8ddfbbb13ec70275",
20
+ "campaign": "primary",
21
+ "path": "main/seed-1-checkpoint-1500",
22
+ "reward_arm": "A0",
23
+ "seed": 1,
24
+ "source_artifact": "logs/artifacts/bigrun_v2_2026-07-01_003238/seed-1/checkpoint-1500",
25
+ "step": 1500
26
+ },
27
+ {
28
+ "adapter_model_bytes": 312053840,
29
+ "adapter_model_sha256": "ef91460fef71a7d56d3ecec17e4c29db201bc94ac9f4dc4a34957572f0d4af02",
30
+ "campaign": "primary",
31
+ "path": "main/seed-2-checkpoint-1500",
32
+ "reward_arm": "A0",
33
+ "seed": 2,
34
+ "source_artifact": "logs/artifacts/bigrun_v2_2026-07-01_003238/seed-2/checkpoint-1500",
35
+ "step": 1500
36
+ },
37
+ {
38
+ "adapter_model_bytes": 312053840,
39
+ "adapter_model_sha256": "63c81f8d77d671361190058ac32e072dae260c3632ffba8f4cf22a73726192e2",
40
+ "campaign": "corrective-continuation-selected",
41
+ "path": "continuation/selected-A0-seed1-checkpoint-400",
42
+ "reward_arm": "A0",
43
+ "seed": 1,
44
+ "source_artifact": "logs/artifacts/continuation400_v3_seed1_run/train/checkpoint-400",
45
+ "step": 400
46
+ },
47
+ {
48
+ "adapter_model_bytes": 312053840,
49
+ "adapter_model_sha256": "fc5ebebcd2241101e02d66715d499a3a18e5e8c2aafd4314dd9802b42488a6a6",
50
+ "campaign": "base-start-reward-ablation",
51
+ "path": "ablation500/A0/seed-0-checkpoint-400",
52
+ "reward_arm": "A0",
53
+ "seed": 0,
54
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A0-seed0/train/checkpoint-400",
55
+ "step": 400
56
+ },
57
+ {
58
+ "adapter_model_bytes": 312053840,
59
+ "adapter_model_sha256": "a99d5c1f4ca86b8f68a333a6081aed44054f86ad0b94cc4f1b6e99e30d8c0b15",
60
+ "campaign": "base-start-reward-ablation",
61
+ "path": "ablation500/A0/seed-1-checkpoint-400",
62
+ "reward_arm": "A0",
63
+ "seed": 1,
64
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A0-seed1/train/checkpoint-400",
65
+ "step": 400
66
+ },
67
+ {
68
+ "adapter_model_bytes": 312053840,
69
+ "adapter_model_sha256": "6c2751680c83ad331802d57ec0818f736cca9264102dbc335b43f2191a381748",
70
+ "campaign": "base-start-reward-ablation",
71
+ "path": "ablation500/A0/seed-2-checkpoint-400",
72
+ "reward_arm": "A0",
73
+ "seed": 2,
74
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A0-seed2/train/checkpoint-400",
75
+ "step": 400
76
+ },
77
+ {
78
+ "adapter_model_bytes": 312053840,
79
+ "adapter_model_sha256": "7491a845b6bd70343a8333bf087c1112634ec4c5afc217fa46c69f698b4c238d",
80
+ "campaign": "base-start-reward-ablation",
81
+ "path": "ablation500/A2/seed-0-checkpoint-400",
82
+ "reward_arm": "A2",
83
+ "seed": 0,
84
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A2-seed0/train/checkpoint-400",
85
+ "step": 400
86
+ },
87
+ {
88
+ "adapter_model_bytes": 312053840,
89
+ "adapter_model_sha256": "a70fec52970ab01221aa0ba6b6f016373698aaf73a28170d2d011c54e48e0e86",
90
+ "campaign": "base-start-reward-ablation",
91
+ "path": "ablation500/A2/seed-1-checkpoint-400",
92
+ "reward_arm": "A2",
93
+ "seed": 1,
94
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A2-seed1/train/checkpoint-400",
95
+ "step": 400
96
+ },
97
+ {
98
+ "adapter_model_bytes": 312053840,
99
+ "adapter_model_sha256": "4e8c970a3a86dadef381d3586aa41c8ea6f9403adb044036e3fc29d84dac4a12",
100
+ "campaign": "base-start-reward-ablation",
101
+ "path": "ablation500/A2/seed-2-checkpoint-400",
102
+ "reward_arm": "A2",
103
+ "seed": 2,
104
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A2-seed2/train/checkpoint-400",
105
+ "step": 400
106
+ },
107
+ {
108
+ "adapter_model_bytes": 312053840,
109
+ "adapter_model_sha256": "972966bfea23e485ac0988ef32431482005840f17ee7d7f6df1f25e6ea8487c3",
110
+ "campaign": "base-start-reward-ablation",
111
+ "path": "ablation500/A4/seed-0-checkpoint-400",
112
+ "reward_arm": "A4",
113
+ "seed": 0,
114
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A4-seed0/train/checkpoint-400",
115
+ "step": 400
116
+ },
117
+ {
118
+ "adapter_model_bytes": 312053840,
119
+ "adapter_model_sha256": "c37e7ef2c1ce12c48fd2a6d7d668c7fb668c9039439f2afc2fd1b15fe36ecc44",
120
+ "campaign": "base-start-reward-ablation",
121
+ "path": "ablation500/A4/seed-1-checkpoint-400",
122
+ "reward_arm": "A4",
123
+ "seed": 1,
124
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A4-seed1/train/checkpoint-400",
125
+ "step": 400
126
+ },
127
+ {
128
+ "adapter_model_bytes": 312053840,
129
+ "adapter_model_sha256": "69a7a6af7f7b39832e0ee8f7190a59dd64c48a74f0d58ac62fc039e370d1243c",
130
+ "campaign": "base-start-reward-ablation",
131
+ "path": "ablation500/A4/seed-2-checkpoint-400",
132
+ "reward_arm": "A4",
133
+ "seed": 2,
134
+ "source_artifact": "logs/artifacts/ablation_campaign_run/A4-seed2/train/checkpoint-400",
135
+ "step": 400
136
+ },
137
+ {
138
+ "adapter_model_bytes": 312053840,
139
+ "adapter_model_sha256": "8d835ed634e343414a44d268882b82da1a2fd5ff137b34599fa456fa2faf2bd0",
140
+ "campaign": "base-start-reward-ablation",
141
+ "path": "ablation500/B1/seed-0-checkpoint-400",
142
+ "reward_arm": "B1",
143
+ "seed": 0,
144
+ "source_artifact": "logs/artifacts/ablation_campaign_run/B1-seed0/train/checkpoint-400",
145
+ "step": 400
146
+ },
147
+ {
148
+ "adapter_model_bytes": 312053840,
149
+ "adapter_model_sha256": "49a77f04837ecd7e96365aa8ed4c5a807d37c8770edefdf900fd25869b81db39",
150
+ "campaign": "base-start-reward-ablation",
151
+ "path": "ablation500/B1/seed-1-checkpoint-400",
152
+ "reward_arm": "B1",
153
+ "seed": 1,
154
+ "source_artifact": "logs/artifacts/ablation_campaign_run/B1-seed1/train/checkpoint-400",
155
+ "step": 400
156
+ },
157
+ {
158
+ "adapter_model_bytes": 312053840,
159
+ "adapter_model_sha256": "71a293817c0c61eda22a0b9bcd1eac569968c96dd0b56ec23113883d4ac6f98e",
160
+ "campaign": "base-start-reward-ablation",
161
+ "path": "ablation500/B1/seed-2-checkpoint-400",
162
+ "reward_arm": "B1",
163
+ "seed": 2,
164
+ "source_artifact": "logs/artifacts/ablation_campaign_run/B1-seed2/train/checkpoint-400",
165
+ "step": 400
166
+ },
167
+ {
168
+ "adapter_model_bytes": 312053840,
169
+ "adapter_model_sha256": "0da054a58393ead2557f6b874dab8fdcc8de76778b747c40811bebd84c27ee34",
170
+ "campaign": "production-policy-reward-ablation",
171
+ "path": "continuation-arms/A0/seed-2-checkpoint-400",
172
+ "reward_arm": "A0",
173
+ "seed": 2,
174
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A0-seed2/train/checkpoint-400",
175
+ "step": 400
176
+ },
177
+ {
178
+ "adapter_model_bytes": 312053840,
179
+ "adapter_model_sha256": "4fc83d3490a0f1fc189bc32014de2af46fa56fb322988faaef394ba949db96ce",
180
+ "campaign": "production-policy-reward-ablation",
181
+ "path": "continuation-arms/A0/seed-3-checkpoint-400",
182
+ "reward_arm": "A0",
183
+ "seed": 3,
184
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A0-seed3/train/checkpoint-400",
185
+ "step": 400
186
+ },
187
+ {
188
+ "adapter_model_bytes": 312053840,
189
+ "adapter_model_sha256": "43fc42e0570c27ae33d1daf7b59bb3a422392e7a16e66f2624a689527c795c4b",
190
+ "campaign": "production-policy-reward-ablation",
191
+ "path": "continuation-arms/A0/seed-4-checkpoint-400",
192
+ "reward_arm": "A0",
193
+ "seed": 4,
194
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A0-seed4/train/checkpoint-400",
195
+ "step": 400
196
+ },
197
+ {
198
+ "adapter_model_bytes": 312053840,
199
+ "adapter_model_sha256": "dc47c3224ccac39372a0cbd79e4fbd8389842b9dac85b933767363f6a6f31a96",
200
+ "campaign": "production-policy-reward-ablation",
201
+ "path": "continuation-arms/A0/seed-5-checkpoint-400",
202
+ "reward_arm": "A0",
203
+ "seed": 5,
204
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A0-seed5/train/checkpoint-400",
205
+ "step": 400
206
+ },
207
+ {
208
+ "adapter_model_bytes": 312053840,
209
+ "adapter_model_sha256": "bf23cdcba788c27b69350eb9c03ab13fd916be256ede69b9e781e22e34709009",
210
+ "campaign": "production-policy-reward-ablation",
211
+ "path": "continuation-arms/A2/seed-1-checkpoint-400",
212
+ "reward_arm": "A2",
213
+ "seed": 1,
214
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A2-seed1/train/checkpoint-400",
215
+ "step": 400
216
+ },
217
+ {
218
+ "adapter_model_bytes": 312053840,
219
+ "adapter_model_sha256": "e6731a578801798bf37a4cbfa708a73fdc2efa38e367e7a576f3f88069371494",
220
+ "campaign": "production-policy-reward-ablation",
221
+ "path": "continuation-arms/A2/seed-2-checkpoint-400",
222
+ "reward_arm": "A2",
223
+ "seed": 2,
224
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A2-seed2/train/checkpoint-400",
225
+ "step": 400
226
+ },
227
+ {
228
+ "adapter_model_bytes": 312053840,
229
+ "adapter_model_sha256": "7a34e1ecb83b10b5f79614090abfde0ddf18703ba8a313373c0154401ed191e4",
230
+ "campaign": "production-policy-reward-ablation",
231
+ "path": "continuation-arms/A2/seed-3-checkpoint-400",
232
+ "reward_arm": "A2",
233
+ "seed": 3,
234
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A2-seed3/train/checkpoint-400",
235
+ "step": 400
236
+ },
237
+ {
238
+ "adapter_model_bytes": 312053840,
239
+ "adapter_model_sha256": "e544fb40dd12a9e5c43e53892a81a9ca944628386eb3e9a9ef00ac4f341c84d5",
240
+ "campaign": "production-policy-reward-ablation",
241
+ "path": "continuation-arms/A2/seed-4-checkpoint-400",
242
+ "reward_arm": "A2",
243
+ "seed": 4,
244
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A2-seed4/train/checkpoint-400",
245
+ "step": 400
246
+ },
247
+ {
248
+ "adapter_model_bytes": 312053840,
249
+ "adapter_model_sha256": "629d8151977ac7dc6e20f59a0a2ff8ec062942a1e365adca17501da3d48e8dd9",
250
+ "campaign": "production-policy-reward-ablation",
251
+ "path": "continuation-arms/A2/seed-5-checkpoint-400",
252
+ "reward_arm": "A2",
253
+ "seed": 5,
254
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A2-seed5/train/checkpoint-400",
255
+ "step": 400
256
+ },
257
+ {
258
+ "adapter_model_bytes": 312053840,
259
+ "adapter_model_sha256": "3febd2da73cc5fcaa6ad58667ffddfb4a82b1fcf790109809aa318f2d2a7572e",
260
+ "campaign": "production-policy-reward-ablation",
261
+ "path": "continuation-arms/A4/seed-1-checkpoint-400",
262
+ "reward_arm": "A4",
263
+ "seed": 1,
264
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A4-seed1/train/checkpoint-400",
265
+ "step": 400
266
+ },
267
+ {
268
+ "adapter_model_bytes": 312053840,
269
+ "adapter_model_sha256": "ed63f4fedce10c43055e54e52c6ef87482b0c95886be97ef678e4aa0e921eb9b",
270
+ "campaign": "production-policy-reward-ablation",
271
+ "path": "continuation-arms/A4/seed-2-checkpoint-400",
272
+ "reward_arm": "A4",
273
+ "seed": 2,
274
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/A4-seed2/train/checkpoint-400",
275
+ "step": 400
276
+ },
277
+ {
278
+ "adapter_model_bytes": 312053840,
279
+ "adapter_model_sha256": "5dc8b2c14e65d43ddc30b1fd7c9c25a1020b65a54a28632ad4eb7500256f457a",
280
+ "campaign": "production-policy-reward-ablation",
281
+ "path": "continuation-arms/B1/seed-1-checkpoint-400",
282
+ "reward_arm": "B1",
283
+ "seed": 1,
284
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/B1-seed1/train/checkpoint-400",
285
+ "step": 400
286
+ },
287
+ {
288
+ "adapter_model_bytes": 312053840,
289
+ "adapter_model_sha256": "52ede1aba4b1027cf9fe94c5584833de621e479186d7df30d0a11995dd0b1cc9",
290
+ "campaign": "production-policy-reward-ablation",
291
+ "path": "continuation-arms/B1/seed-2-checkpoint-400",
292
+ "reward_arm": "B1",
293
+ "seed": 2,
294
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/B1-seed2/train/checkpoint-400",
295
+ "step": 400
296
+ },
297
+ {
298
+ "adapter_model_bytes": 312053840,
299
+ "adapter_model_sha256": "21b47884ab18d03d7709e752f518589069fc8e9402c20e63c45797b336a8104b",
300
+ "campaign": "production-policy-reward-ablation",
301
+ "path": "continuation-arms/B1/seed-3-checkpoint-400",
302
+ "reward_arm": "B1",
303
+ "seed": 3,
304
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/B1-seed3/train/checkpoint-400",
305
+ "step": 400
306
+ },
307
+ {
308
+ "adapter_model_bytes": 312053840,
309
+ "adapter_model_sha256": "995bd82551dba281621ac25fd0be2a839c20199f08e1e3ccf8491a09c26c7c80",
310
+ "campaign": "production-policy-reward-ablation",
311
+ "path": "continuation-arms/B1/seed-4-checkpoint-400",
312
+ "reward_arm": "B1",
313
+ "seed": 4,
314
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/B1-seed4/train/checkpoint-400",
315
+ "step": 400
316
+ },
317
+ {
318
+ "adapter_model_bytes": 312053840,
319
+ "adapter_model_sha256": "a2b58c6e7f7f397ade49dc1a34a6d99eda2590996535ed83097cb36f05fe5cec",
320
+ "campaign": "production-policy-reward-ablation",
321
+ "path": "continuation-arms/B1/seed-5-checkpoint-400",
322
+ "reward_arm": "B1",
323
+ "seed": 5,
324
+ "source_artifact": "logs/artifacts/cont400_arm_campaign/B1-seed5/train/checkpoint-400",
325
+ "step": 400
326
+ }
327
+ ],
328
+ "peft": {
329
+ "alpha": 64,
330
+ "dropout": 0.0,
331
+ "rank": 32,
332
+ "type": "LORA"
333
+ },
334
+ "physical_endpoint_count": 32,
335
+ "schema": "least-privilege-adapter-release/v1"
336
+ }
continuation-arms/A0/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_z",
34
+ "attn.proj",
35
+ "in_proj_a",
36
+ "qkv",
37
+ "up_proj",
38
+ "out_proj",
39
+ "v_proj",
40
+ "linear_fc1",
41
+ "q_proj",
42
+ "in_proj_b",
43
+ "linear_fc2",
44
+ "down_proj",
45
+ "o_proj",
46
+ "gate_proj",
47
+ "k_proj",
48
+ "in_proj_qkv"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A0/seed-2-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da054a58393ead2557f6b874dab8fdcc8de76778b747c40811bebd84c27ee34
3
+ size 312053840
continuation-arms/A0/seed-3-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "q_proj",
34
+ "attn.proj",
35
+ "linear_fc2",
36
+ "linear_fc1",
37
+ "k_proj",
38
+ "v_proj",
39
+ "in_proj_b",
40
+ "qkv",
41
+ "in_proj_z",
42
+ "gate_proj",
43
+ "down_proj",
44
+ "in_proj_a",
45
+ "in_proj_qkv",
46
+ "o_proj",
47
+ "out_proj",
48
+ "up_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A0/seed-3-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc83d3490a0f1fc189bc32014de2af46fa56fb322988faaef394ba949db96ce
3
+ size 312053840
continuation-arms/A0/seed-4-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "out_proj",
34
+ "in_proj_qkv",
35
+ "qkv",
36
+ "down_proj",
37
+ "in_proj_b",
38
+ "q_proj",
39
+ "v_proj",
40
+ "attn.proj",
41
+ "up_proj",
42
+ "linear_fc2",
43
+ "in_proj_z",
44
+ "gate_proj",
45
+ "in_proj_a",
46
+ "linear_fc1",
47
+ "k_proj",
48
+ "o_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A0/seed-4-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fc42e0570c27ae33d1daf7b59bb3a422392e7a16e66f2624a689527c795c4b
3
+ size 312053840
continuation-arms/A0/seed-5-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "k_proj",
34
+ "linear_fc2",
35
+ "out_proj",
36
+ "v_proj",
37
+ "in_proj_b",
38
+ "gate_proj",
39
+ "down_proj",
40
+ "in_proj_qkv",
41
+ "attn.proj",
42
+ "q_proj",
43
+ "in_proj_z",
44
+ "qkv",
45
+ "o_proj",
46
+ "in_proj_a",
47
+ "up_proj",
48
+ "linear_fc1"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A2/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc1",
34
+ "o_proj",
35
+ "qkv",
36
+ "gate_proj",
37
+ "q_proj",
38
+ "in_proj_qkv",
39
+ "up_proj",
40
+ "in_proj_b",
41
+ "in_proj_a",
42
+ "attn.proj",
43
+ "k_proj",
44
+ "down_proj",
45
+ "linear_fc2",
46
+ "in_proj_z",
47
+ "v_proj",
48
+ "out_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A2/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "k_proj",
34
+ "up_proj",
35
+ "down_proj",
36
+ "attn.proj",
37
+ "in_proj_b",
38
+ "linear_fc1",
39
+ "in_proj_a",
40
+ "in_proj_qkv",
41
+ "qkv",
42
+ "gate_proj",
43
+ "v_proj",
44
+ "o_proj",
45
+ "out_proj",
46
+ "linear_fc2",
47
+ "q_proj",
48
+ "in_proj_z"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A2/seed-3-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_b",
34
+ "k_proj",
35
+ "in_proj_qkv",
36
+ "gate_proj",
37
+ "linear_fc1",
38
+ "in_proj_a",
39
+ "linear_fc2",
40
+ "qkv",
41
+ "q_proj",
42
+ "attn.proj",
43
+ "out_proj",
44
+ "in_proj_z",
45
+ "v_proj",
46
+ "up_proj",
47
+ "o_proj",
48
+ "down_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A2/seed-4-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_b",
34
+ "k_proj",
35
+ "in_proj_a",
36
+ "linear_fc1",
37
+ "qkv",
38
+ "in_proj_z",
39
+ "gate_proj",
40
+ "down_proj",
41
+ "in_proj_qkv",
42
+ "q_proj",
43
+ "out_proj",
44
+ "up_proj",
45
+ "v_proj",
46
+ "o_proj",
47
+ "linear_fc2",
48
+ "attn.proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A2/seed-5-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "down_proj",
34
+ "out_proj",
35
+ "gate_proj",
36
+ "attn.proj",
37
+ "linear_fc1",
38
+ "in_proj_z",
39
+ "in_proj_a",
40
+ "up_proj",
41
+ "o_proj",
42
+ "linear_fc2",
43
+ "k_proj",
44
+ "q_proj",
45
+ "qkv",
46
+ "in_proj_qkv",
47
+ "v_proj",
48
+ "in_proj_b"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A4/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "up_proj",
34
+ "out_proj",
35
+ "linear_fc2",
36
+ "in_proj_qkv",
37
+ "linear_fc1",
38
+ "attn.proj",
39
+ "in_proj_z",
40
+ "v_proj",
41
+ "gate_proj",
42
+ "qkv",
43
+ "q_proj",
44
+ "in_proj_a",
45
+ "in_proj_b",
46
+ "down_proj",
47
+ "k_proj",
48
+ "o_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A4/seed-1-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3febd2da73cc5fcaa6ad58667ffddfb4a82b1fcf790109809aa318f2d2a7572e
3
+ size 312053840
continuation-arms/A4/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc2",
34
+ "linear_fc1",
35
+ "gate_proj",
36
+ "in_proj_qkv",
37
+ "q_proj",
38
+ "down_proj",
39
+ "out_proj",
40
+ "attn.proj",
41
+ "v_proj",
42
+ "in_proj_a",
43
+ "o_proj",
44
+ "k_proj",
45
+ "in_proj_b",
46
+ "up_proj",
47
+ "in_proj_z",
48
+ "qkv"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/A4/seed-2-checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed63f4fedce10c43055e54e52c6ef87482b0c95886be97ef678e4aa0e921eb9b
3
+ size 312053840
continuation-arms/B1/seed-1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "attn.proj",
34
+ "linear_fc2",
35
+ "v_proj",
36
+ "in_proj_a",
37
+ "q_proj",
38
+ "in_proj_qkv",
39
+ "in_proj_b",
40
+ "up_proj",
41
+ "down_proj",
42
+ "k_proj",
43
+ "o_proj",
44
+ "qkv",
45
+ "gate_proj",
46
+ "linear_fc1",
47
+ "out_proj",
48
+ "in_proj_z"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/B1/seed-2-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "o_proj",
34
+ "in_proj_z",
35
+ "in_proj_b",
36
+ "attn.proj",
37
+ "gate_proj",
38
+ "q_proj",
39
+ "linear_fc1",
40
+ "up_proj",
41
+ "in_proj_qkv",
42
+ "k_proj",
43
+ "v_proj",
44
+ "out_proj",
45
+ "down_proj",
46
+ "qkv",
47
+ "linear_fc2",
48
+ "in_proj_a"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/B1/seed-3-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "k_proj",
34
+ "linear_fc1",
35
+ "out_proj",
36
+ "in_proj_b",
37
+ "linear_fc2",
38
+ "qkv",
39
+ "gate_proj",
40
+ "q_proj",
41
+ "up_proj",
42
+ "down_proj",
43
+ "in_proj_a",
44
+ "in_proj_z",
45
+ "v_proj",
46
+ "o_proj",
47
+ "attn.proj",
48
+ "in_proj_qkv"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/B1/seed-4-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "k_proj",
34
+ "v_proj",
35
+ "q_proj",
36
+ "in_proj_a",
37
+ "in_proj_qkv",
38
+ "up_proj",
39
+ "in_proj_z",
40
+ "gate_proj",
41
+ "out_proj",
42
+ "linear_fc1",
43
+ "down_proj",
44
+ "linear_fc2",
45
+ "in_proj_b",
46
+ "o_proj",
47
+ "qkv",
48
+ "attn.proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation-arms/B1/seed-5-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "in_proj_qkv",
34
+ "q_proj",
35
+ "linear_fc2",
36
+ "in_proj_z",
37
+ "down_proj",
38
+ "up_proj",
39
+ "out_proj",
40
+ "in_proj_a",
41
+ "v_proj",
42
+ "qkv",
43
+ "gate_proj",
44
+ "o_proj",
45
+ "k_proj",
46
+ "attn.proj",
47
+ "linear_fc1",
48
+ "in_proj_b"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
continuation/selected-A0-seed1-checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "down_proj",
34
+ "in_proj_b",
35
+ "out_proj",
36
+ "q_proj",
37
+ "qkv",
38
+ "gate_proj",
39
+ "up_proj",
40
+ "k_proj",
41
+ "attn.proj",
42
+ "v_proj",
43
+ "o_proj",
44
+ "in_proj_z",
45
+ "in_proj_qkv",
46
+ "in_proj_a",
47
+ "linear_fc1",
48
+ "linear_fc2"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
main/seed-0-checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "o_proj",
34
+ "down_proj",
35
+ "in_proj_a",
36
+ "in_proj_qkv",
37
+ "qkv",
38
+ "up_proj",
39
+ "in_proj_b",
40
+ "linear_fc2",
41
+ "linear_fc1",
42
+ "v_proj",
43
+ "out_proj",
44
+ "q_proj",
45
+ "gate_proj",
46
+ "in_proj_z",
47
+ "attn.proj",
48
+ "k_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
main/seed-0-checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d0687dcf6e263132991830b0c146e7774fbe3bcfa37f8f30f68c86490ae80f
3
+ size 312053840
main/seed-1-checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "linear_fc2",
34
+ "attn.proj",
35
+ "down_proj",
36
+ "out_proj",
37
+ "k_proj",
38
+ "linear_fc1",
39
+ "in_proj_a",
40
+ "in_proj_z",
41
+ "q_proj",
42
+ "qkv",
43
+ "v_proj",
44
+ "in_proj_qkv",
45
+ "gate_proj",
46
+ "o_proj",
47
+ "in_proj_b",
48
+ "up_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
main/seed-1-checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ce33e4f31433057d6396800b871bb2d45129037ae9698e8ddfbbb13ec70275
3
+ size 312053840
main/seed-2-checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3.5-4B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "v_proj",
34
+ "in_proj_b",
35
+ "gate_proj",
36
+ "in_proj_a",
37
+ "attn.proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "qkv",
41
+ "q_proj",
42
+ "out_proj",
43
+ "linear_fc1",
44
+ "in_proj_z",
45
+ "in_proj_qkv",
46
+ "down_proj",
47
+ "linear_fc2",
48
+ "up_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": "CAUSAL_LM",
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false
57
+ }
main/seed-2-checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef91460fef71a7d56d3ecec17e4c29db201bc94ac9f4dc4a34957572f0d4af02
3
+ size 312053840