ZhangYiqian commited on
Commit
e8afdae
·
verified ·
1 Parent(s): 0ddc6e3

rl_b1_grpo_v2_lora_step_32 (91ac557) v2 reward (REWARD_VERSION=v2), run r3, global_step_32

Browse files
checkpoints/rl_b1_grpo_v2_lora_step_32/adapter_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "/mnt/raid5/models/Qwen3.8-27B",
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
+ "kasa_config": null,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 128,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0.05,
23
+ "lora_ga_config": null,
24
+ "megatron_config": null,
25
+ "megatron_core": "megatron.core",
26
+ "modules_to_save": null,
27
+ "monteclora_config": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.21.2",
30
+ "qalora_group_size": 16,
31
+ "r": 64,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "in_proj_z",
36
+ "out_proj",
37
+ "q_proj",
38
+ "in_proj_qkv",
39
+ "gate_proj",
40
+ "v_proj",
41
+ "k_proj",
42
+ "down_proj",
43
+ "up_proj",
44
+ "o_proj"
45
+ ],
46
+ "target_parameters": null,
47
+ "task_type": "CAUSAL_LM",
48
+ "trainable_token_indices": null,
49
+ "use_bdlora": null,
50
+ "use_dora": false,
51
+ "use_qalora": false,
52
+ "use_rslora": false,
53
+ "velora_config": null
54
+ }
checkpoints/rl_b1_grpo_v2_lora_step_32/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059b82558bafd7f956d1bf5996fb08a56f1052173ee5f7c7f8aa80329fa94906
3
+ size 1740746640
checkpoints/rl_b1_grpo_v2_lora_step_32/manifest.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "rl_b1_grpo_v2_lora_step_32",
3
+ "uploaded_at": "2026-11-02T07:38:47+0800",
4
+ "git_commit": "91ac557",
5
+ "source_dir": "/myshare/sunwenjie/Agent_Coding_Active/ckpts/rl_b1_grpo_v2/lora_step_32",
6
+ "kind": "lora_adapter",
7
+ "base_model": "/mnt/raid5/models/Qwen3.8-27B",
8
+ "train_args": null,
9
+ "n_files": 2,
10
+ "total_bytes": 1740747878,
11
+ "note": "v2 reward (REWARD_VERSION=v2), run r3, global_step_32"
12
+ }